{"meta":{"query_hash":"e802a3299282","filters":{"topic":"Advanced Causal Inference Techniques"},"cohort_total":1326,"direct_labels_cover":35,"predictions_cover":1326,"exported":1326,"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/e802a3299282","api":"https://metacan.xera.ac/api/v1/cohort?topic=Advanced+Causal+Inference+Techniques"},"results":[{"id":"W103747493","doi":"10.1007/978-1-4939-2428-8_7","title":"Longitudinal Studies 4: Matching Strategies to Evaluate Risk","year":2015,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Matching (statistics); Psychological intervention; Contrast (vision); Outcome (game theory); Medicine; Econometrics; Statistics; Computer science; Mathematics; Artificial intelligence","score_opus":0.40862711632687365,"score_gpt":0.6147512186106135,"score_spread":0.2061241022837399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W103747493","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":[0.05636031,0.0013381712,0.940167,0.00012867751,0.00016877678,0.00031098563,0.0000034466862,0.00018505483,0.0013375551],"genre_scores_gemma":[0.024157947,0.00009589207,0.9754071,0.000118270415,0.000028690773,0.00013355992,0.0000015373209,0.000028531602,0.000028462538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99651337,0.002167982,0.0004144316,0.0004034006,0.0001239975,0.00037680197],"domain_scores_gemma":[0.9981601,0.00093967473,0.00015162157,0.0004474516,0.00020738106,0.0000937352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050732745,0.00023035219,0.0005176988,0.00020956187,0.000038017086,0.000019783756,0.00028697422,0.00014498655,0.000009582621],"category_scores_gemma":[0.006396609,0.00019241875,0.000060290175,0.0002919732,0.00013668755,0.00009025038,0.00030828518,0.00032131094,0.000012366445],"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":[0.00008944675,0.00010123228,0.0032172103,0.000085145046,0.00019280994,0.00010484727,0.004311669,0.0011118061,0.19929236,0.74157715,0.00019334006,0.04972301],"study_design_scores_gemma":[0.0001891644,0.00025403514,0.000064372514,0.000034392397,0.00003182232,0.000010918644,0.0014748905,0.000059546066,0.04388899,0.9533667,0.00041457955,0.0002105842],"about_ca_topic_score_codex":0.00004917117,"about_ca_topic_score_gemma":0.00007735128,"teacher_disagreement_score":0.21178958,"about_ca_system_score_codex":0.00014155474,"about_ca_system_score_gemma":0.00006994805,"threshold_uncertainty_score":0.78466094},"labels":[],"label_agreement":null},{"id":"W104160504","doi":"10.1007/978-94-007-4044-0_6","title":"Distinctive Population Segments in Multi-mode Risk Management","year":2012,"lang":"en","type":"book-chapter","venue":"","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":"Université de Montréal","funders":"","keywords":"Mode (computer interface); Geography; Business; Computer science","score_opus":0.1553271555204005,"score_gpt":0.41090055369748707,"score_spread":0.2555733981770866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W104160504","genre_codex":"other","genre_gemma":"methods","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":[0.00010520493,0.00006245369,0.31656185,0.0000049089017,0.00008348473,0.0011148303,0.000062209954,0.00041188594,0.6815932],"genre_scores_gemma":[0.031840857,0.0004526237,0.48842463,0.000032913373,0.00005987621,0.00012924122,0.00016601235,0.00014143476,0.47875243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986347,0.00002407432,0.0004713092,0.00033822036,0.00026992997,0.00026175214],"domain_scores_gemma":[0.9989239,0.00011370859,0.00039232388,0.00046506466,0.00004314605,0.000061885876],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020134372,0.00036706892,0.0003969014,0.00021097981,0.000039449373,0.000013404896,0.0001622225,0.00028056634,0.00060489745],"category_scores_gemma":[0.000046136607,0.00033644473,0.00008444547,0.000023655537,0.000031420885,0.00016547139,0.00018974772,0.00038557383,0.00012758945],"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":[0.000010288018,0.00007941498,0.0010978824,0.00010596445,0.00006468346,0.000008715157,0.00009042844,0.0000036491017,0.000002157682,0.9697442,0.000254478,0.028538126],"study_design_scores_gemma":[0.0002647399,0.000022286777,0.0017440511,0.00028830775,0.000113505805,0.0000010501788,0.000019659152,0.00015575199,0.000042734657,0.9942123,0.0027077156,0.0004278498],"about_ca_topic_score_codex":0.00014092634,"about_ca_topic_score_gemma":0.00049243093,"teacher_disagreement_score":0.20284075,"about_ca_system_score_codex":0.00045678052,"about_ca_system_score_gemma":0.000004641019,"threshold_uncertainty_score":0.99990875},"labels":[],"label_agreement":null},{"id":"W142749920","doi":"10.1055/s-2003-39997","title":"Characteristics of Good Causation Studies","year":2003,"lang":"en","type":"review","venue":"Seminars in Reproductive Medicine","topic":"Advanced Causal Inference Techniques","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":"McMaster University","funders":"","keywords":"Confounding; Odds ratio; Causation; Medicine; Causality (physics); Population; Causal inference; Internal medicine; Environmental health; Pathology","score_opus":0.2982394417425489,"score_gpt":0.5066656835073107,"score_spread":0.20842624176476177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W142749920","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":[0.000042514013,0.9960131,0.00042223773,0.000056297096,0.00053169916,0.0013827473,0.000021376025,0.00008718471,0.001442852],"genre_scores_gemma":[0.000015090212,0.98615783,0.011767634,0.000009708493,0.0003674533,0.00024796545,0.00004556187,0.000079767335,0.0013089966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996335,0.0004055681,0.0017059224,0.0008390266,0.0004213004,0.00029316926],"domain_scores_gemma":[0.9950821,0.0014327477,0.0016835516,0.0012912529,0.000465114,0.00004523699],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024717057,0.0005545416,0.0038274315,0.00050835626,0.00003015009,0.000002282302,0.00027681372,0.00027134243,0.000041684732],"category_scores_gemma":[0.016057093,0.0004032266,0.00014123121,0.00082234683,0.00065320905,0.00008841911,0.000112850284,0.0006508069,0.0000042176985],"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":[0.000007960015,0.00014234251,0.00004045745,0.034995493,0.00023075138,0.000040537012,0.001659179,3.5288725e-8,0.000013921339,0.026512403,0.0023909593,0.933966],"study_design_scores_gemma":[0.00021444993,0.0005517899,0.000010016666,0.1436363,0.0013921403,0.00012438792,0.0009506906,2.0785937e-7,0.0002193196,0.20056193,0.65171736,0.0006214142],"about_ca_topic_score_codex":0.000005487024,"about_ca_topic_score_gemma":0.00000220201,"teacher_disagreement_score":0.93334454,"about_ca_system_score_codex":0.00045877942,"about_ca_system_score_gemma":0.00012289555,"threshold_uncertainty_score":0.999842},"labels":[],"label_agreement":null},{"id":"W143496817","doi":"10.1007/978-1-4939-2428-8_14","title":"Randomized Controlled Trials 6: On Contamination and Estimating the Actual Treatment Effect","year":2015,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Memorial University of Newfoundland","funders":"","keywords":"Randomized controlled trial; Contamination; Environmental science; Econometrics; Statistics; Medicine; Mathematics; Biology; Internal medicine; Ecology","score_opus":0.22326473890545312,"score_gpt":0.5631080594861806,"score_spread":0.33984332058072747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W143496817","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":[0.041175842,0.0003072183,0.95443946,0.0002096518,0.00013478518,0.002869789,0.0000014426504,0.000073122625,0.0007886995],"genre_scores_gemma":[0.05660683,0.000018032666,0.9418474,0.00011460672,0.000034411973,0.0013214139,0.000004015916,0.000016082626,0.000037206344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9751581,0.02360132,0.0007481156,0.00023075944,0.000081136655,0.00018058017],"domain_scores_gemma":[0.94772506,0.05150847,0.00042807157,0.00024426007,0.000054826236,0.00003929747],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032751173,0.0002265566,0.00251352,0.0001227357,0.00003297717,0.000018223307,0.000098915545,0.00015606591,0.000005997947],"category_scores_gemma":[0.12040517,0.000100801175,0.00022221076,0.00007672188,0.00018722209,0.000020042731,0.000038974405,0.0001364844,9.71162e-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":[0.08648168,0.0001720396,0.00007251731,0.000029108416,0.0007258631,0.000027221133,0.0016259026,0.00010787362,0.10704007,0.49312168,0.000021324455,0.3105747],"study_design_scores_gemma":[0.18954168,0.0009893122,0.0000014606774,0.000035159366,0.00024374119,0.000007384395,0.00004487875,0.00698791,0.103895865,0.6980953,0.000037233203,0.0001200645],"about_ca_topic_score_codex":0.00001674211,"about_ca_topic_score_gemma":0.0000039251217,"teacher_disagreement_score":0.31045467,"about_ca_system_score_codex":0.00010018306,"about_ca_system_score_gemma":0.000028858787,"threshold_uncertainty_score":0.9959862},"labels":[],"label_agreement":null},{"id":"W1486734343","doi":"10.3747/co.v0i0.339","title":"Panel Discussion 1","year":2008,"lang":"en","type":"article","venue":"Current Oncology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Data science; Bioinformatics; Computer science; Biology","score_opus":0.6416160428976948,"score_gpt":0.542421122104341,"score_spread":0.09919492079335379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486734343","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":[0.52421737,0.00097200746,0.406687,0.0034812693,0.0038031302,0.0014063483,0.00002634553,0.0030942434,0.05631232],"genre_scores_gemma":[0.94669664,0.00062360073,0.05056878,0.000094970164,0.000371762,0.00015453907,0.00001709971,0.000041884123,0.0014307279],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991633,0.0000757378,0.00022760745,0.0001839672,0.000120473254,0.0002288597],"domain_scores_gemma":[0.9992897,0.00021730851,0.00010652684,0.0002515604,0.000060124567,0.00007481569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012665399,0.00011812741,0.00023384985,0.000058255577,0.00009050064,0.00000257974,0.00016119426,0.00009634165,0.00020351769],"category_scores_gemma":[0.00037395972,0.00007353718,0.000053398468,0.00009532133,0.00014277716,0.00008808547,0.00009680101,0.00024407296,0.00009626497],"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":[0.00006631214,0.0018984589,0.010672751,0.00013676293,0.000024763845,0.00013425453,0.0029279792,0.0000014128623,0.0038161017,0.26199946,0.18932845,0.5289933],"study_design_scores_gemma":[0.00037326358,0.00028858552,0.0010862537,0.000047471916,0.000016319624,0.00012970928,0.00010015918,0.00006870806,0.0026193545,0.5249968,0.47004628,0.00022706292],"about_ca_topic_score_codex":9.733412e-7,"about_ca_topic_score_gemma":0.0000039061374,"teacher_disagreement_score":0.5287662,"about_ca_system_score_codex":0.00013985214,"about_ca_system_score_gemma":0.00006886268,"threshold_uncertainty_score":0.29987592},"labels":[],"label_agreement":null},{"id":"W1493983723","doi":"10.2139/ssrn.1617262","title":"Efficient Estimation of Average Treatment Effects Under Treatment-Based Sampling, Second Version","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"University of British Columbia","funders":"","keywords":"Statistics; Estimation; Sampling (signal processing); Mathematics; Econometrics; Computer science; Economics; Telecommunications","score_opus":0.048264251346877104,"score_gpt":0.3639097914497442,"score_spread":0.3156455401028671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493983723","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":[0.6782951,0.000087954526,0.3209492,0.000043696888,0.00009785645,0.00027208566,0.0000056238177,0.000073961935,0.00017454998],"genre_scores_gemma":[0.97781444,0.00007201975,0.021698127,0.000013600958,0.000056238954,0.000021525211,0.000010293898,0.000033585813,0.00028014468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982043,0.00006957012,0.00032567687,0.00019459066,0.00022699748,0.0009788972],"domain_scores_gemma":[0.9987257,0.0004885208,0.00032442095,0.00029662333,0.00008257047,0.00008218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005019467,0.0002451785,0.0003132841,0.00016316777,0.00014649537,0.000022667895,0.00013419708,0.00012700926,0.00014022907],"category_scores_gemma":[0.00012768466,0.00018607336,0.00016496293,0.00011359766,0.00005700811,0.00006720179,0.000013351125,0.0006451463,0.000013946236],"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":[0.00040477223,0.0028535922,0.00035272876,0.00014333421,0.0007693138,0.000015228878,0.0006231022,0.02495211,0.1882123,0.68726826,0.00003953589,0.09436573],"study_design_scores_gemma":[0.0024938497,0.0035736447,0.00010436119,0.00007179703,0.00016649773,0.00011098135,0.00012381791,0.012617512,0.21847536,0.7618387,0.00015663357,0.00026686696],"about_ca_topic_score_codex":0.000026554831,"about_ca_topic_score_gemma":0.00047182804,"teacher_disagreement_score":0.2995194,"about_ca_system_score_codex":0.0017794555,"about_ca_system_score_gemma":0.0009885579,"threshold_uncertainty_score":0.7587851},"labels":[],"label_agreement":null},{"id":"W1504811022","doi":"10.2139/ssrn.1360961","title":"Efficient Estimation of Average Treatment Effects Under Treatment-Based Sampling","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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 British Columbia","funders":"","keywords":"Statistics; Estimation; Sampling (signal processing); Mathematics; Econometrics; Computer science; Engineering","score_opus":0.07719717332674914,"score_gpt":0.3892253488116601,"score_spread":0.31202817548491096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504811022","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":[0.36393914,0.00031475627,0.6351061,0.000115797,0.000027080043,0.0002690355,0.0000016740394,0.00009278855,0.00013367001],"genre_scores_gemma":[0.96925634,0.0002175481,0.030307025,0.00002941815,0.000045144796,0.000014334713,0.000005027069,0.00002274034,0.00010239435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99803495,0.0000862745,0.00036624583,0.00017909436,0.0002289819,0.0011044288],"domain_scores_gemma":[0.99892783,0.00038887878,0.00030265693,0.0002453716,0.00006711115,0.000068175934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044120918,0.00024627548,0.00034876965,0.00015912141,0.00012330663,0.000022123982,0.000114644885,0.00008262873,0.00001281521],"category_scores_gemma":[0.00011097788,0.00018514502,0.00016867003,0.00014691718,0.000030056375,0.000057871875,0.000005488281,0.0003447018,0.0000048894135],"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":[0.00014507356,0.0014146939,0.000039795166,0.000026301319,0.00025746776,0.000007920176,0.0002597506,0.1311139,0.010310988,0.6633917,0.0000037419366,0.19302866],"study_design_scores_gemma":[0.0014096836,0.0046112435,0.000092378694,0.000096906595,0.00012964604,0.000071473594,0.0000857021,0.016651789,0.04366807,0.9329871,0.000010616808,0.00018540733],"about_ca_topic_score_codex":0.000016961654,"about_ca_topic_score_gemma":0.000043007778,"teacher_disagreement_score":0.60531723,"about_ca_system_score_codex":0.0033430317,"about_ca_system_score_gemma":0.0008466544,"threshold_uncertainty_score":0.87419116},"labels":[],"label_agreement":null},{"id":"W1534104826","doi":"10.1002/pds.3299","title":"Comparing the cohort design and the nested case–control design in the presence of both time‐invariant and time‐dependent treatment and competing risks: bias and precision","year":2012,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":"Princess Margaret Cancer Centre; Institute for Clinical Evaluative Sciences; Women's College Hospital; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; U.S. Public Health Service; Government of Ontario; Heart and Stroke Foundation of Canada; Institute for Clinical Evaluative Sciences; Cancer Care Ontario","keywords":"Confidence interval; Statistics; Medicine; Mean squared error; Observational study; Cohort; Monte Carlo method; Clinical study design; Cohort study; Econometrics; Research design; Event (particle physics); Clinical trial; Mathematics; Internal medicine","score_opus":0.23166504252237438,"score_gpt":0.4193350163465059,"score_spread":0.1876699738241315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534104826","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":[0.6464314,0.011635191,0.33524486,0.0020189176,0.00004313763,0.004290993,0.000021875598,0.0000769036,0.00023674831],"genre_scores_gemma":[0.98301613,0.0035632201,0.012947066,0.00026025114,0.000036411926,0.00014386482,0.0000014764504,0.000013878374,0.000017717648],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98810494,0.010487433,0.000632663,0.0003182069,0.000100360296,0.0003563731],"domain_scores_gemma":[0.9226775,0.07662066,0.0003448769,0.00023950728,0.000031143303,0.00008628733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025383841,0.00027350252,0.00072844856,0.000049917406,0.00037402046,0.000023721781,0.00013407992,0.00009193222,0.000009661693],"category_scores_gemma":[0.0028805255,0.00012919163,0.000029618672,0.00007578274,0.0007849173,0.0001885425,0.0001544465,0.00031089588,6.1058773e-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":[0.008470597,0.0007292838,0.82119733,0.0003715535,0.0012499072,0.00014842702,0.043021187,0.0037249615,0.006313066,0.07266195,0.0012841529,0.040827587],"study_design_scores_gemma":[0.011656337,0.00046382155,0.10597647,0.00037266343,0.0018078523,0.0041481596,0.0021622656,0.7681574,0.0023253746,0.101981424,0.00019645345,0.0007517524],"about_ca_topic_score_codex":0.00036334622,"about_ca_topic_score_gemma":0.000019096351,"teacher_disagreement_score":0.7644325,"about_ca_system_score_codex":0.0000260714,"about_ca_system_score_gemma":0.000017800912,"threshold_uncertainty_score":0.8797583},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1534864278","doi":"10.1111/j.1360-0443.2009.02896.x","title":"Modeling missing binary outcome data in a successful web‐based smokeless tobacco cessation program","year":2010,"lang":"en","type":"article","venue":"Addiction","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":39,"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":"National Cancer Institute","keywords":"Missing data; Imputation (statistics); Abstinence; Smokeless tobacco; Randomized controlled trial; Attrition; Medicine; Smoking cessation; Statistics; Environmental health; Psychiatry; Mathematics; Tobacco use","score_opus":0.1909148593675436,"score_gpt":0.4403831945771234,"score_spread":0.24946833520957978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534864278","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":[0.8633977,0.000014674294,0.13389444,0.00025165346,0.00021692796,0.00054834376,0.000028554003,0.0010732218,0.00057445274],"genre_scores_gemma":[0.87058336,0.000005286564,0.12890974,0.000041924668,0.000081547405,0.00010900658,0.0002244447,0.00003312547,0.000011591826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858135,0.00005784502,0.00047203305,0.0003763745,0.00025780709,0.00025460243],"domain_scores_gemma":[0.9986825,0.00015500824,0.00015007627,0.00085683295,0.00009805983,0.000057534584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006535011,0.0001717975,0.00021043546,0.00022179575,0.00009569216,0.00007780916,0.00036546908,0.0001908631,0.00007046784],"category_scores_gemma":[0.000554225,0.00017058112,0.00003156445,0.00032960818,0.000040112565,0.00095574395,0.00011857016,0.00049434265,0.000005846035],"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":[0.00018430887,0.002051184,0.17811526,0.00035372825,0.00005491277,0.000052310297,0.0004261337,0.0048798057,0.07516142,0.017481875,0.0008500653,0.720389],"study_design_scores_gemma":[0.00049088825,0.00006721268,0.0015366435,0.00013726072,0.00003395489,0.000004109853,0.00006817507,0.97048587,0.0020813195,0.024305174,0.00052423426,0.00026517242],"about_ca_topic_score_codex":0.00016762977,"about_ca_topic_score_gemma":0.0009174188,"teacher_disagreement_score":0.96560603,"about_ca_system_score_codex":0.00008312337,"about_ca_system_score_gemma":0.00007464598,"threshold_uncertainty_score":0.69560957},"labels":[],"label_agreement":null},{"id":"W1541868835","doi":"10.1186/1471-2288-1-11","title":"Sample size requirements for case-control study designs","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Royal Victoria Hospital","funders":"","keywords":"Confounding; Sample size determination; Odds ratio; Fortran; Statistics; Computer science; Control (management); Sample (material); Case-control study; Odds; Software; Medicine; Mathematics; Logistic regression; Programming language; Artificial intelligence","score_opus":0.9182700472002921,"score_gpt":0.6957823635411999,"score_spread":0.22248768365909222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541868835","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":[0.048610568,0.000045555553,0.94709015,0.00044337404,0.00012794013,0.0029788502,0.000025945494,0.00025421087,0.0004233809],"genre_scores_gemma":[0.21679673,0.000043488963,0.7806558,0.00019488244,0.00027467,0.0015335869,0.0000014666354,0.000050150207,0.00044924903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9775878,0.017810902,0.00083793636,0.000692502,0.0017227514,0.0013480986],"domain_scores_gemma":[0.58995014,0.40816414,0.000114977614,0.0006929873,0.00057693705,0.00050081365],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06890425,0.00023114041,0.00079479814,0.00025159106,0.000317011,0.00002921901,0.0007488878,0.0003787162,0.0030313283],"category_scores_gemma":[0.71275806,0.00018705562,0.00013070392,0.00047191395,0.0005263082,0.00011794976,0.00029332825,0.0008695167,0.00002326324],"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":[0.0065126787,0.0056811254,0.037200242,0.0010309324,0.00082148286,0.007797044,0.0040878607,0.000008282384,0.008616548,0.46658164,0.025315993,0.43634617],"study_design_scores_gemma":[0.0027827937,0.0025715753,0.0003552846,0.00005399586,0.000054529464,0.00044986757,0.002075778,0.0010320065,0.0008386957,0.98792654,0.0016343305,0.00022462253],"about_ca_topic_score_codex":0.00035377298,"about_ca_topic_score_gemma":0.0018931803,"teacher_disagreement_score":0.64385384,"about_ca_system_score_codex":0.00019632324,"about_ca_system_score_gemma":0.0006844242,"threshold_uncertainty_score":0.99788004},"labels":[],"label_agreement":null},{"id":"W1546136735","doi":"10.1002/pds.3773","title":"On the role of marginal confounder prevalence – implications for the high‐dimensional propensity score algorithm","year":2015,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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; Jewish General Hospital","funders":"Canadian Institutes of Health Research; McGill University Health Centre","keywords":"Propensity score matching; Confounding; Covariate; Medicine; Statistics; Selection bias; Pharmacoepidemiology; Sample size determination; Econometrics; Demography; Mathematics; Internal medicine; Medical prescription","score_opus":0.25710149254751674,"score_gpt":0.4312125604105927,"score_spread":0.17411106786307595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546136735","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":[0.097998045,0.0030552782,0.8314062,0.058399044,0.00042950507,0.005184416,0.0006256279,0.00033403447,0.002567898],"genre_scores_gemma":[0.9656123,0.00027763777,0.03103037,0.002405389,0.00009723354,0.00033391383,0.000013996357,0.000017139366,0.00021200617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985686,0.000499698,0.00036861433,0.00023942726,0.00009008037,0.0002336011],"domain_scores_gemma":[0.9848055,0.014284468,0.00025770103,0.00032471222,0.00025307832,0.00007450345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038599807,0.0001536924,0.00029812768,0.000022403343,0.0002499072,0.0000041278777,0.00025799125,0.00006530483,0.00004306966],"category_scores_gemma":[0.002531033,0.00008000493,0.000058173388,0.00006514848,0.00048310842,0.00007688181,0.00012090496,0.0002641098,0.000003582111],"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":[0.00019785574,0.00006347678,0.0031682218,0.00002978646,0.000056506145,1.878182e-7,0.00011761758,0.000050898878,0.0004631475,0.9739208,0.011195813,0.01073564],"study_design_scores_gemma":[0.00034371956,0.00006587375,0.008096216,0.000029894083,0.000089319015,0.000015895315,0.000045322096,0.0038119627,0.002606225,0.9821598,0.0026278112,0.00010794824],"about_ca_topic_score_codex":0.00003130993,"about_ca_topic_score_gemma":0.0000038047015,"teacher_disagreement_score":0.86761427,"about_ca_system_score_codex":0.000034166147,"about_ca_system_score_gemma":0.00007615105,"threshold_uncertainty_score":0.32625064},"labels":[],"label_agreement":null},{"id":"W1556145289","doi":"","title":"Impact Evaluation for Policy Making: A Close Look at Latin American Countries with Weaker Research Capacities","year":2012,"lang":"en","type":"article","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"International Development Research Centre","keywords":"Latin Americans; Political science; Humanities; Economics; Economic growth; Economy; Sociology; Development economics; Economic history; Welfare economics; Art; Law","score_opus":0.12314337036769715,"score_gpt":0.410159697722024,"score_spread":0.2870163273543268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556145289","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":[0.8725251,0.00052058965,0.03387449,0.013637336,0.0003814025,0.0047745723,0.00036224365,0.00141235,0.0725119],"genre_scores_gemma":[0.965718,0.000049750382,0.03100665,0.00011198345,0.00087678107,0.0016018761,0.0001167286,0.000113532486,0.00040475192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99473554,0.00073004817,0.000697324,0.0006390086,0.0017396403,0.0014584166],"domain_scores_gemma":[0.9945671,0.0016548097,0.0005845475,0.00084521266,0.0018914206,0.00045690167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029268945,0.0005317796,0.00062496803,0.0008262517,0.0010300701,0.00019762132,0.00048423535,0.00033383124,0.000063915075],"category_scores_gemma":[0.0035769541,0.0004364155,0.00020550433,0.0010450019,0.00022819173,0.0008425322,0.00024774193,0.00064007984,0.000013243786],"study_design_candidate":"theoretical_or_conceptual","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":[0.0006468324,0.00038523908,0.004100086,0.0001333912,0.00015201098,0.0000086758355,0.0037635257,0.000021813581,0.0012229518,0.98631364,0.0020445,0.001207348],"study_design_scores_gemma":[0.0022839047,0.0009529459,0.011848027,0.00050752464,0.00026277092,0.000863571,0.002899611,0.0006815983,0.0064089773,0.0748626,0.8970727,0.0013558065],"about_ca_topic_score_codex":0.0000070352417,"about_ca_topic_score_gemma":0.00038175454,"teacher_disagreement_score":0.91145104,"about_ca_system_score_codex":0.004013005,"about_ca_system_score_gemma":0.0013477548,"threshold_uncertainty_score":0.9998104},"labels":[],"label_agreement":null},{"id":"W1556389145","doi":"10.1002/cjs.11254","title":"An imputation based empirical likelihood approach to pretest–posttest studies","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Confidence interval; Imputation (statistics); Statistics; Missing data; Treatment effect; Empirical likelihood; Type I and type II errors; Parametric statistics; Statistical hypothesis testing; Treatment and control groups; Mathematics; Econometrics; Computer science; Psychology; Medicine","score_opus":0.3289284696619818,"score_gpt":0.45212187221249617,"score_spread":0.12319340255051436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556389145","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":[0.02084249,0.000109405155,0.9775917,0.00033528492,0.00017500728,0.00021866316,0.00021349048,0.000036462574,0.00047751926],"genre_scores_gemma":[0.38502488,0.0000021449052,0.6144316,0.00039448545,0.000093051014,0.000005682373,0.000010593751,0.00002521783,0.000012335667],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857455,0.00011836941,0.00051921816,0.0001419111,0.00030538987,0.0003405271],"domain_scores_gemma":[0.9960606,0.00045321404,0.0002855889,0.00021769374,0.0015477807,0.0014351393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072570855,0.00016908596,0.0003398395,0.0003036763,0.00007822527,0.0000681126,0.00026214,0.00007423659,0.000010014488],"category_scores_gemma":[0.0051380764,0.00015278562,0.00003145869,0.00023947794,0.00010186413,0.00021624684,0.000010308236,0.00025741916,0.0000071978657],"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":[0.00016269901,0.0005850342,0.021608781,0.0004632445,0.00034116136,0.0010636279,0.030066306,0.0066370163,0.00038396814,0.14255661,0.7572769,0.038854644],"study_design_scores_gemma":[0.0007204555,0.002561918,0.0012670383,0.00018242974,0.0001600298,0.00018306397,0.003915651,0.0067511555,0.00068195455,0.9802959,0.0027721107,0.0005083233],"about_ca_topic_score_codex":0.00016681521,"about_ca_topic_score_gemma":0.0025492343,"teacher_disagreement_score":0.8377392,"about_ca_system_score_codex":0.0005033852,"about_ca_system_score_gemma":0.0020822925,"threshold_uncertainty_score":0.6230417},"labels":[],"label_agreement":null},{"id":"W1558639712","doi":"10.1002/pds.3485","title":"Evidence of subgroup‐specific treatment effect in the absence of an overall effect: is there really a contradiction?","year":2013,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Subgroup analysis; Medicine; Odds ratio; Treatment effect; Randomization; Sample size determination; Internal medicine; Statistics; Randomized controlled trial; Confidence interval; Mathematics; Traditional medicine","score_opus":0.10108559944306415,"score_gpt":0.4221100691319647,"score_spread":0.3210244696889005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558639712","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":[0.9908003,0.0031292832,0.002930792,0.0010366963,0.0000549383,0.0014096769,0.000015322274,0.000065748995,0.00055719656],"genre_scores_gemma":[0.991011,0.005961315,0.0023578333,0.00034767465,0.00003788439,0.00024551406,0.000003714271,0.000013513021,0.000021527178],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957526,0.0028203765,0.00069869217,0.00032628467,0.00012065294,0.0002813948],"domain_scores_gemma":[0.9782544,0.020829482,0.00037444592,0.00041313155,0.00006256817,0.00006601923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00412386,0.00026145595,0.000786505,0.00006958182,0.000065279026,0.0000049782816,0.00026891974,0.00011301095,0.00015019286],"category_scores_gemma":[0.0008289595,0.00014842373,0.00010512088,0.00012198841,0.000316465,0.00030615457,0.00003747595,0.00025774536,0.000004848238],"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":[0.0046439194,0.0014239168,0.52213997,0.0018052052,0.00048509103,0.0000554721,0.0135229435,0.00012967974,0.10438498,0.14001577,0.009011338,0.20238173],"study_design_scores_gemma":[0.004367187,0.0049502174,0.35933354,0.0011554488,0.00022937842,0.00007076837,0.00025047103,0.0037256186,0.08759696,0.537032,0.0006471134,0.0006413057],"about_ca_topic_score_codex":0.00077957404,"about_ca_topic_score_gemma":0.000045979596,"teacher_disagreement_score":0.39701623,"about_ca_system_score_codex":0.000060719343,"about_ca_system_score_gemma":0.000019822899,"threshold_uncertainty_score":0.6052544},"labels":[],"label_agreement":null},{"id":"W1563314065","doi":"10.29012/jpc.v1i2.571","title":"Maintaining Analytic Utility while Protecting Confidentiality of Survey and Nonsurvey Data","year":2010,"lang":"en","type":"article","venue":"Journal of Privacy and Confidentiality","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"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":"Natural Sciences and Engineering Research Council of Canada; Nutrition Obesity Research Center, University of North Carolina; RTI International; University of Chicago","keywords":"Confidentiality; Computer science; Macro; Actuarial science; Econometrics; Statistics; Data mining; Mathematics; Business; Computer security","score_opus":0.2908189185928526,"score_gpt":0.43491223749864016,"score_spread":0.14409331890578758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563314065","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":[0.9071172,0.00007050261,0.09194873,0.000075711076,0.00020329913,0.0002838638,0.00010757693,0.00003036956,0.00016273255],"genre_scores_gemma":[0.98579127,0.000048950304,0.0140000405,0.000017361146,0.000098926816,0.0000020064736,0.000009891986,0.000015920969,0.00001563459],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996519,0.0010161523,0.0013909915,0.00034958214,0.00046838002,0.00025587564],"domain_scores_gemma":[0.9943809,0.0019433914,0.0016687916,0.0010144276,0.0008125748,0.00017990828],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018271081,0.00021524879,0.00075493555,0.00012942897,0.00016494811,0.00013096735,0.00072480127,0.00017000413,0.00016174164],"category_scores_gemma":[0.0104329195,0.00019199634,0.00007980667,0.00018267203,0.00043123605,0.0007842706,0.0007126154,0.0010696445,3.9715286e-7],"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":[0.0013516608,0.0010889667,0.8185749,0.001664521,0.0011911078,0.000055714194,0.0050661243,0.0000012881468,0.09944436,0.027616907,0.0011012794,0.042843137],"study_design_scores_gemma":[0.0014998614,0.00028891375,0.6708709,0.00029519424,0.0003507336,0.00035063675,0.0011308225,0.000858932,0.026702685,0.2966131,0.00049549434,0.00054271653],"about_ca_topic_score_codex":0.0023260515,"about_ca_topic_score_gemma":0.0022302233,"teacher_disagreement_score":0.26899618,"about_ca_system_score_codex":0.00001628392,"about_ca_system_score_gemma":0.00016349556,"threshold_uncertainty_score":0.99790263},"labels":[],"label_agreement":null},{"id":"W1570060061","doi":"10.1002/0470842555.ch43","title":"Bias and Confounding in Pharmacoepidemiology","year":2000,"lang":"en","type":"other","venue":"Pharmacoepidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":85,"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; Jewish General Hospital","funders":"","keywords":"Pharmacoepidemiology; Confounding; Computer science; Econometrics; Medicine; Mathematics; Pharmacology; Internal medicine","score_opus":0.40457020891237205,"score_gpt":0.5390313703409946,"score_spread":0.13446116142862252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570060061","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018546346,0.01051246,0.010371851,0.0019015926,0.0012593213,0.0021489635,0.00013697638,0.0029283536,0.96888584],"genre_scores_gemma":[0.01993292,0.13138366,0.17363998,0.019164767,0.004744822,0.0020479169,0.00034950333,0.0048424904,0.64389396],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937443,0.0026307232,0.0013526126,0.0010543031,0.0001275931,0.0010904474],"domain_scores_gemma":[0.98908615,0.00927847,0.0008616183,0.0005068993,0.0000175901,0.00024925172],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003051078,0.0008006357,0.002340733,0.0009108883,0.000047275298,0.000009113169,0.000480495,0.0009926038,0.006917593],"category_scores_gemma":[0.00354583,0.0007483205,0.00014927801,0.00025621595,0.0005433251,0.00008819759,0.00020277489,0.0014544673,0.00011506395],"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":[0.000057063127,0.00007339134,0.004642957,0.00028185363,0.00012668659,0.00009719753,0.00007162494,0.0000032812397,0.000539399,0.0361251,0.94980377,0.008177663],"study_design_scores_gemma":[0.0008833348,0.00006232688,0.000061734856,0.00033058267,0.00011056932,0.00010896183,0.000014326788,0.0002539283,0.00024798853,0.19517386,0.80201745,0.00073495874],"about_ca_topic_score_codex":0.0005050217,"about_ca_topic_score_gemma":0.0001650226,"teacher_disagreement_score":0.3249919,"about_ca_system_score_codex":0.00010110213,"about_ca_system_score_gemma":0.000063475025,"threshold_uncertainty_score":0.99949676},"labels":[],"label_agreement":null},{"id":"W1576880634","doi":"10.17848/rpt204","title":"What Works for Whom in Public Employment Policy?","year":2011,"lang":"en","type":"report","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Human Resources and Skills Development Canada; Institut für Arbeitsmarkt- und Berufsforschung; Australian Government; W.E. Upjohn Institute for Employment Research","keywords":"Public policy; Political science; Labour economics; Public administration; Sociology; Economics; Law","score_opus":0.5168958004630927,"score_gpt":0.5017415248250681,"score_spread":0.015154275638024628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576880634","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":[0.0006443053,0.0037113887,0.5586631,0.002899498,0.002846306,0.012207626,0.00006703075,0.0036296414,0.41533116],"genre_scores_gemma":[0.023875766,0.065930165,0.6501555,0.0013467136,0.003121501,0.016188227,0.0005184547,0.0011444311,0.23771924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972897,0.000045008033,0.00090534415,0.0005338426,0.0005508078,0.0006753021],"domain_scores_gemma":[0.9973123,0.0005241274,0.00049900456,0.0009599101,0.00056518323,0.00013948418],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011533765,0.00048043512,0.00088356104,0.0006896868,0.000054598044,0.00048195673,0.0005031812,0.00082637934,0.0004201856],"category_scores_gemma":[0.0021182857,0.00041041634,0.00022613231,0.00029192964,0.00009888389,0.0011163884,0.00024730412,0.0005521263,0.000018648081],"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":[0.000025490173,0.0005428684,0.00022733622,0.0009842272,0.00017183331,0.000024360474,0.00069952017,2.3197043e-7,0.000018321793,0.524446,0.16457187,0.30828792],"study_design_scores_gemma":[0.00015502781,0.000097640026,0.000017476827,0.0019411652,0.000027217478,0.000014404573,0.0002126917,0.000003820382,0.00045518883,0.7409683,0.25564954,0.00045755098],"about_ca_topic_score_codex":0.0004819022,"about_ca_topic_score_gemma":0.0022682187,"teacher_disagreement_score":0.30783036,"about_ca_system_score_codex":0.0011606802,"about_ca_system_score_gemma":0.0018651505,"threshold_uncertainty_score":0.9998348},"labels":[],"label_agreement":null},{"id":"W1577677789","doi":"10.1002/bimj.201400153","title":"Predictive Bayesian inference and dynamic treatment regimes","year":2015,"lang":"en","type":"article","venue":"Biometrical Journal","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":"McGill University Health Centre; McGill University; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Covariate; Bayesian probability; Inference; Bayesian inference; Econometrics; Inverse probability weighting; Computer science; Estimator; Mathematics; Statistics; Artificial intelligence","score_opus":0.2574949456410719,"score_gpt":0.4554466655597026,"score_spread":0.1979517199186307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577677789","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":[0.06156334,0.0009773108,0.9332615,0.00050692813,0.0001556121,0.0002469805,0.000014932222,0.00025207628,0.0030212917],"genre_scores_gemma":[0.88973397,0.00041084792,0.109348595,0.00002810519,0.00008244308,0.000011166091,0.0000013918201,0.000018094504,0.0003653653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988323,0.00008680449,0.0002992595,0.00017973817,0.00034006027,0.00026187437],"domain_scores_gemma":[0.99844515,0.00056560617,0.00017807067,0.00017283564,0.0001974484,0.00044088927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000336336,0.00017315288,0.00027466175,0.0007237374,0.0000789617,0.00008856857,0.00014584462,0.00010859024,0.000024851044],"category_scores_gemma":[0.0021990447,0.00012112412,0.00005419837,0.0009359296,0.00011845699,0.00023826114,0.000066184584,0.00020578077,0.0000075931284],"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":[0.0005904906,0.0021995052,0.025157008,0.00007295432,0.00063227676,0.00076527783,0.0032981427,0.000013956355,0.0027899074,0.098478965,0.013921057,0.85208046],"study_design_scores_gemma":[0.0012602055,0.0034126127,0.002212437,0.00007949774,0.00008951234,0.00072481344,0.00041171006,0.0024714272,0.0017688669,0.98314077,0.0040787356,0.0003494115],"about_ca_topic_score_codex":0.0000067566266,"about_ca_topic_score_gemma":0.0000017577834,"teacher_disagreement_score":0.8846618,"about_ca_system_score_codex":0.00047571072,"about_ca_system_score_gemma":0.0001227543,"threshold_uncertainty_score":0.4939298},"labels":[],"label_agreement":null},{"id":"W1578220446","doi":"10.1007/s00362-007-0099-7","title":"Robert E. Weiss (2006): Modeling longitudinal data","year":2008,"lang":"en","type":"article","venue":"Statistical Papers","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":"University of Manitoba","funders":"","keywords":"Longitudinal data; Sociology; Demography","score_opus":0.292524825356008,"score_gpt":0.4326743019312527,"score_spread":0.14014947657524474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578220446","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":[0.0030555727,0.000049609378,0.9691717,0.00013878515,0.000073521645,0.00018599481,0.0003497753,0.00043011297,0.026544921],"genre_scores_gemma":[0.5440015,0.00005530779,0.45511293,0.000101476144,0.000067338784,0.000013682577,0.000120675424,0.00003581264,0.00049121835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983779,0.000047767968,0.00035136673,0.00046677966,0.00034767578,0.00040847718],"domain_scores_gemma":[0.9981427,0.00068537233,0.00005590637,0.0008742464,0.00007188368,0.0001698464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002156749,0.00020269498,0.0002886339,0.000043535998,0.00016231964,0.000017863866,0.0004683645,0.00008687479,0.0007782923],"category_scores_gemma":[0.0018056575,0.00018135253,0.000027751305,0.000113307746,0.00021387616,0.00021263998,0.00025139435,0.00027685356,0.0000780675],"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":[0.000059148988,0.00019576229,0.0008498519,0.00009198417,0.00006298935,0.00039113322,0.00017740871,0.00021862259,0.00077009236,0.95550424,0.03207607,0.009602701],"study_design_scores_gemma":[0.00041673423,0.00015582239,0.0005058134,0.00008013841,0.000085968044,0.00017728067,0.00010093069,0.09340234,0.00018277638,0.8995762,0.0046208957,0.0006951176],"about_ca_topic_score_codex":0.00008251908,"about_ca_topic_score_gemma":0.000058232294,"teacher_disagreement_score":0.54094595,"about_ca_system_score_codex":0.000061382976,"about_ca_system_score_gemma":0.00006772628,"threshold_uncertainty_score":0.8521755},"labels":[],"label_agreement":null},{"id":"W1583915132","doi":"10.3917/inso.150.0056","title":"L'apport des expérimentations dans l'évaluation de l'impact des dispositifs publics","year":2009,"lang":"fr","type":"article","venue":"Informations sociales","topic":"Advanced Causal Inference Techniques","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":"Musée de la Civilisation","funders":"","keywords":"Humanities; Publics; Political science; Philosophy","score_opus":0.24036194099422475,"score_gpt":0.4615485375554111,"score_spread":0.22118659656118633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583915132","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":[0.3437908,0.00043352242,0.61572915,0.0009777596,0.00012141441,0.0006606105,0.0002095588,0.0005681163,0.037509035],"genre_scores_gemma":[0.7281561,0.00044681772,0.26903042,0.0002449229,0.00017320568,0.000100335965,0.0003040336,0.00003156012,0.0015126069],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753535,0.00021243078,0.00094610796,0.0001653453,0.00043231918,0.00070843863],"domain_scores_gemma":[0.99778837,0.00043980774,0.000500137,0.00037906333,0.00065908494,0.00023354677],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011049616,0.00036017844,0.0003337316,0.0002969432,0.0012147098,0.00041225084,0.00031417733,0.00031572362,0.0004214172],"category_scores_gemma":[0.0012571962,0.00039520932,0.0002537664,0.00080748455,0.0010627236,0.0046122693,0.000052459225,0.00032322409,0.00015944666],"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":[0.000011862531,0.00051783206,0.0052651945,0.00017512529,0.0001272637,0.0000041888475,0.10420943,0.0010447219,0.0016602762,0.7084856,0.007242176,0.17125635],"study_design_scores_gemma":[0.0003146415,0.00023531994,0.05935226,0.00029196107,0.0002021424,0.000060533985,0.011180492,0.0029934084,0.0050012474,0.9191124,0.00079434045,0.0004612829],"about_ca_topic_score_codex":0.00041028688,"about_ca_topic_score_gemma":0.00056394096,"teacher_disagreement_score":0.3843653,"about_ca_system_score_codex":0.0026479112,"about_ca_system_score_gemma":0.0013284143,"threshold_uncertainty_score":0.99985},"labels":[],"label_agreement":null},{"id":"W1593489106","doi":"10.1002/9781118900772.etrds0284","title":"Repeated Cross‐Sections in Survey Data","year":2015,"lang":"en","type":"other","venue":"Emerging Trends in the Social and Behavioral Sciences","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":"University of British Columbia","funders":"","keywords":"Representativeness heuristic; Smoothing; Sample (material); Population; Noise (video); Econometrics; Computer science; Comparability; Voting; Statistics; Mathematics; Politics; Artificial intelligence; Political science; Demography; Sociology","score_opus":0.6413700468407519,"score_gpt":0.5913505308481036,"score_spread":0.05001951599264831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593489106","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":[0.27372867,0.0013197593,0.00017482857,0.0012426594,0.0014743167,0.0009401361,0.0025138336,0.001469409,0.7171364],"genre_scores_gemma":[0.6699957,0.00023960695,0.0094750365,0.00009695053,0.00085269054,0.00014234101,0.0011019916,0.00033962962,0.31775603],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830496,0.00030853352,0.0002736771,0.00043618932,0.00038070412,0.0002959116],"domain_scores_gemma":[0.99933225,0.000097029966,0.00018246713,0.00033449498,0.00002493536,0.000028842966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027473008,0.0001944705,0.00028238783,0.0003835958,0.0002226023,0.000103908686,0.0009515054,0.00019400293,0.00020352338],"category_scores_gemma":[0.0001557879,0.00013328492,0.000024593113,0.0013887708,0.0006862907,0.00017425537,0.00028726042,0.0003422564,0.0000018075423],"study_design_candidate":"not_applicable","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":[0.000015523558,0.0005619691,0.0675965,0.000028774282,0.000011925051,0.00003856503,0.008453238,0.0000018360696,0.000014300972,0.004174974,0.88799363,0.031108728],"study_design_scores_gemma":[0.0028686074,0.001213849,0.2817397,0.0015331602,0.000410247,0.000069288166,0.0181271,0.00034296114,0.000066946945,0.3944917,0.29363084,0.0055055995],"about_ca_topic_score_codex":0.013902938,"about_ca_topic_score_gemma":0.097779594,"teacher_disagreement_score":0.59436285,"about_ca_system_score_codex":0.000043643675,"about_ca_system_score_gemma":0.000053153,"threshold_uncertainty_score":0.99266356},"labels":[],"label_agreement":null},{"id":"W1603529668","doi":"10.18438/b8w90x","title":"Cara Bradley Receives Robert H. Blackburn Distinguished Paper Award for Paper Published in EBLIP Journal","year":2014,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Library science; Computer science","score_opus":0.03978912817808283,"score_gpt":0.3383699424486019,"score_spread":0.2985808142705191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603529668","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":[0.012985436,0.00091715757,0.63745624,0.28907427,0.0010665352,0.0032125076,0.000046507637,0.0015026869,0.053738654],"genre_scores_gemma":[0.288455,0.0021882993,0.5956249,0.111480914,0.00075108424,0.00039696586,0.00013792116,0.0000970111,0.00086788693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768615,0.0004181746,0.0009855337,0.000216354,0.0003475937,0.00034618803],"domain_scores_gemma":[0.9893719,0.008938935,0.0008871692,0.00040262507,0.00022066777,0.00017873177],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0022746169,0.00025163105,0.00033004917,0.00030294113,0.0002174925,0.0010845974,0.00034922367,0.00017363604,0.00043112302],"category_scores_gemma":[0.043429103,0.00021477208,0.00007773806,0.00040769533,0.00008703637,0.28024238,0.00009862541,0.00055781315,0.000010495518],"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":[0.0010204924,0.00014191621,0.0013046603,0.0006490282,0.000034870296,0.000005291005,0.00106885,0.00014224893,0.00035808983,0.91758835,0.041396894,0.0362893],"study_design_scores_gemma":[0.0010182889,0.00040433963,0.0018147418,0.0010279372,0.000055329565,0.000068423826,0.0006269073,0.0044352245,0.0020383259,0.14389639,0.84414846,0.00046562825],"about_ca_topic_score_codex":0.000006582096,"about_ca_topic_score_gemma":5.794824e-7,"teacher_disagreement_score":0.80275154,"about_ca_system_score_codex":0.000037916434,"about_ca_system_score_gemma":0.00019987178,"threshold_uncertainty_score":0.9999524},"labels":[],"label_agreement":null},{"id":"W1616123277","doi":"10.1002/cncr.28359","title":"Which of these things is not like the others?","year":2013,"lang":"en","type":"article","venue":"Cancer","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":112,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Medicine; Epidemiology; Subgroup analysis; Pathology; Meta-analysis","score_opus":0.12941733138142505,"score_gpt":0.4024220275477411,"score_spread":0.27300469616631606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1616123277","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":[0.85229766,0.0010343563,0.035214324,0.025528654,0.00059253303,0.0026777687,0.000061488376,0.0010465264,0.0815467],"genre_scores_gemma":[0.98416317,0.00012349257,0.009194342,0.003007202,0.00006597467,0.00025069504,3.295566e-7,0.00003209545,0.0031626865],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993497,0.000024510082,0.00017581988,0.0001267818,0.00016322402,0.00015994161],"domain_scores_gemma":[0.99894255,0.0002462425,0.00013679707,0.0004382339,0.00020699692,0.000029187242],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014620271,0.000102979684,0.00015509292,0.000021690874,0.000031035583,0.000017586774,0.00028072245,0.000063811334,0.0022565501],"category_scores_gemma":[0.00015010474,0.00006125625,0.0000423837,0.00013428909,0.00008268267,0.00021209409,0.00005766141,0.00014708603,0.00005291665],"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":[0.000052755,0.00019913517,0.0022099358,0.0004765479,0.00027092567,0.0000013977576,0.055787373,0.000015683983,0.13225038,0.3655832,0.3776437,0.06550893],"study_design_scores_gemma":[0.00018334672,0.000061518906,0.00069108204,0.00019822102,0.000041021372,0.0000019031411,0.0008927958,0.00038496082,0.22093152,0.74515843,0.031194473,0.00026071953],"about_ca_topic_score_codex":0.0003808053,"about_ca_topic_score_gemma":0.00005354366,"teacher_disagreement_score":0.37957522,"about_ca_system_score_codex":0.000043465647,"about_ca_system_score_gemma":0.000035314974,"threshold_uncertainty_score":0.9986555},"labels":[],"label_agreement":null},{"id":"W1658181916","doi":"10.3747/co.v0i0.340","title":"Panel Discussion 2","year":2008,"lang":"en","type":"article","venue":"Current Oncology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Data science; Computer science","score_opus":0.6308189263392884,"score_gpt":0.5414606696635275,"score_spread":0.08935825667576092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1658181916","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":[0.5269113,0.0010049322,0.40141186,0.0035042302,0.003882078,0.0014217541,0.000025940932,0.0031342676,0.0587036],"genre_scores_gemma":[0.94731975,0.00065362867,0.04987665,0.00009630827,0.00038408593,0.00015289563,0.000017433053,0.00004239579,0.0014568716],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916357,0.0000757053,0.00022773759,0.00018379225,0.00012043516,0.00022875292],"domain_scores_gemma":[0.99929416,0.00021341194,0.00010671648,0.0002509468,0.000059954687,0.000074801814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012577564,0.00011807967,0.00023392263,0.000058207093,0.000090509064,0.000002586861,0.00016108021,0.000096342366,0.00019865565],"category_scores_gemma":[0.00036823255,0.00007350662,0.000053385338,0.00009522714,0.00014277466,0.00008816222,0.000096783704,0.00024400152,0.000094961215],"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":[0.00006463487,0.0018625568,0.010055281,0.00013578084,0.000024305893,0.00013637207,0.0028768815,0.000001395197,0.0035814533,0.26273942,0.18198322,0.53653866],"study_design_scores_gemma":[0.00036892627,0.00028282846,0.0010426261,0.00004578655,0.000015917065,0.00012745317,0.000096868396,0.000066751425,0.0025462934,0.5179123,0.4772723,0.00022189223],"about_ca_topic_score_codex":9.858289e-7,"about_ca_topic_score_gemma":0.000003935553,"teacher_disagreement_score":0.5363168,"about_ca_system_score_codex":0.00013990307,"about_ca_system_score_gemma":0.00006847331,"threshold_uncertainty_score":0.29975128},"labels":[],"label_agreement":null},{"id":"W1683369961","doi":"10.1111/biom.12269","title":"On Bayesian Estimation of Marginal Structural Models","year":2015,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"McGill University; University of Toronto","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Marginal structural model; Inverse probability; Bayesian probability; Weighting; Bayesian inference; Posterior probability; Inverse probability weighting; Statistics; Inference; Covariate; Marginal likelihood; Population; Econometrics; Computer science; Marginal distribution; Mathematics; Confounding; Estimator; Artificial intelligence; Medicine; Random variable","score_opus":0.2902512635374343,"score_gpt":0.4371757447731041,"score_spread":0.1469244812356698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1683369961","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":[0.10649766,0.000035433877,0.88941807,0.00003231068,0.00008210053,0.00015313715,0.000016950815,0.00015942755,0.0036049115],"genre_scores_gemma":[0.69145066,0.000002260132,0.308447,0.000012644984,0.0000121897265,0.0000042287206,0.0000058077603,0.000011158097,0.000054034837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99908817,0.000024757053,0.00023405049,0.00012500986,0.00038147738,0.00014653984],"domain_scores_gemma":[0.9990459,0.0002849761,0.00015950609,0.0002562607,0.00017061338,0.00008275679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028312125,0.000105822335,0.00017361893,0.0008222827,0.00001805695,0.000012600464,0.00015092854,0.00008104888,0.000016394344],"category_scores_gemma":[0.0015111846,0.000090935275,0.000033079978,0.0015513999,0.00004551425,0.00018681888,0.000038799186,0.00007821248,0.0000057258653],"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":[0.000035178135,0.000058907117,0.00007441694,0.000060723192,0.000011123335,0.0000031713662,0.00016902748,0.0018042868,0.0002749835,0.9651593,0.0022757407,0.030073129],"study_design_scores_gemma":[0.00016449159,0.00021607403,0.0000485246,0.000019925894,0.000008891689,0.0000033812023,0.000023939316,0.089725144,0.0059837555,0.9036828,0.000025293395,0.00009776477],"about_ca_topic_score_codex":0.000009540743,"about_ca_topic_score_gemma":6.1124473e-7,"teacher_disagreement_score":0.584953,"about_ca_system_score_codex":0.000113244125,"about_ca_system_score_gemma":0.000038787468,"threshold_uncertainty_score":0.3708233},"labels":[],"label_agreement":null},{"id":"W1691896301","doi":"10.1111/j.1365-2966.2007.00428.x","title":"Viewpoint: Replication in economics","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":275,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Replication (statistics); Incentive; Work (physics); Positive economics; Computer science; Economics; Biology; Microeconomics","score_opus":0.3158663132890136,"score_gpt":0.28711981340215564,"score_spread":0.028746499886857957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1691896301","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":[0.99150455,0.000100654775,0.0024465914,0.0017029203,0.0005210304,0.000332216,0.000040688796,0.00001858862,0.0033327877],"genre_scores_gemma":[0.983439,0.00023718236,0.014746088,0.00085689774,0.00039388466,0.0000142067665,0.000008094536,0.00007713936,0.00022746141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99706274,0.000045414505,0.0016140918,0.0004138526,0.0000023460752,0.00086157705],"domain_scores_gemma":[0.9961155,0.0004728268,0.0010581645,0.0008079191,0.00019509398,0.0013504899],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028131355,0.00029361804,0.00070374674,0.0011835553,0.00008415737,0.00006484982,0.000642942,0.00026996504,0.00012580991],"category_scores_gemma":[0.001092087,0.00036996114,0.00018418701,0.00016396814,0.0001433516,0.00061844685,0.000022983797,0.00051759137,0.000012357051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039939856,0.0000138489195,0.0028301107,0.000024459661,0.000033450095,0.0000970051,0.00061201875,0.00038389993,0.000035814654,0.98010474,0.00024269585,0.015581989],"study_design_scores_gemma":[0.00040673223,0.00018372275,0.0011065856,0.000108980166,0.000018005472,0.00046880546,0.000313341,0.00029447753,0.001598956,0.9791811,0.015937135,0.0003821364],"about_ca_topic_score_codex":0.03296647,"about_ca_topic_score_gemma":0.9846215,"teacher_disagreement_score":0.9516551,"about_ca_system_score_codex":0.0043832855,"about_ca_system_score_gemma":0.0014990438,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W1746442198","doi":"10.1111/ssqu.12074","title":"A General Approach to Effect Decomposition","year":2014,"lang":"en","type":"article","venue":"Social Science Quarterly","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"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; Statistics Canada","funders":"","keywords":"Covariate; Mediation; Decomposition; Path analysis (statistics); Outcome (game theory); Econometrics; Simple (philosophy); Psychology; Regression analysis; Computer science; Mathematics; Statistics; Sociology; Social science; Epistemology; Mathematical economics","score_opus":0.049040049093019136,"score_gpt":0.41327736973003937,"score_spread":0.36423732063702025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746442198","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":[0.44426286,8.005569e-7,0.4817494,0.00012572705,0.00009924897,0.00036406817,0.0000015360895,0.0003659287,0.073030435],"genre_scores_gemma":[0.9051551,3.5430293e-8,0.09427284,0.00018015942,0.00022352449,0.000080777456,0.0000012871405,0.000011446765,0.00007483203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985938,0.00010375929,0.000166994,0.00032173863,0.00041859492,0.0003950829],"domain_scores_gemma":[0.99941134,0.000108858105,0.00006675732,0.00019827613,0.00008604796,0.00012869197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011914694,0.0001292091,0.00018976747,0.000112341564,0.00040184802,0.00010827435,0.00039045396,0.000059275575,0.000007958565],"category_scores_gemma":[0.00014243853,0.00011247707,0.00005578669,0.000558435,0.00024799464,0.0003271857,0.000019442039,0.00010707808,0.000041906693],"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":[0.0000109557595,0.00006846669,0.000069584436,0.000017936352,0.0000025952363,3.3328558e-7,0.004663475,9.231326e-7,0.079906866,0.82970345,0.00071955734,0.084835865],"study_design_scores_gemma":[0.00031274057,0.0020790102,0.0018621155,0.000022729522,0.000019631923,0.000007777091,0.0004559225,0.0016478375,0.023824371,0.96878463,0.0004813309,0.00050188514],"about_ca_topic_score_codex":0.00001648592,"about_ca_topic_score_gemma":0.0000032530806,"teacher_disagreement_score":0.46089223,"about_ca_system_score_codex":0.00013783757,"about_ca_system_score_gemma":0.000031925993,"threshold_uncertainty_score":0.45866817},"labels":[],"label_agreement":null},{"id":"W1773473668","doi":"10.1186/1742-7622-3-5","title":"Causal criteria and counterfactuals; nothing more (or less) than scientific common sense","year":2006,"lang":"en","type":"article","venue":"Emerging Themes in Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":62,"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":"Counterfactual thinking; Counterfactual conditional; Causation; Common sense; Epistemology; Causality (physics); Set (abstract data type); Consilience; Scientific method; Nothing; Scientific evidence; Computer science; Philosophy","score_opus":0.23304713007442762,"score_gpt":0.47796856405748694,"score_spread":0.24492143398305932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1773473668","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":[0.9669913,0.00047682153,0.027842673,0.0027360555,0.00038418648,0.00030364472,0.00002094314,0.00042433912,0.000820029],"genre_scores_gemma":[0.93382525,0.00004237665,0.06467704,0.0006009095,0.00012697083,0.000042775977,0.000019057155,0.00005009987,0.00061549654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971534,0.0005178094,0.0009178686,0.00058413105,0.00013403074,0.00069277163],"domain_scores_gemma":[0.99336344,0.0055872495,0.0003325465,0.0005887058,0.000061996216,0.00006606624],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002895417,0.0003148418,0.0008107025,0.0002589486,0.00020135133,0.00003390549,0.00024442683,0.00021943732,0.000087510874],"category_scores_gemma":[0.003716114,0.00025535884,0.00005967002,0.00021812011,0.0005784453,0.00023879916,0.00025937855,0.00040898845,0.0000057578586],"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":[0.0005840696,0.0006414127,0.1306892,0.00087342836,0.00013103745,0.00047873982,0.030083096,0.00085418485,0.0395169,0.73501235,0.049480557,0.011655031],"study_design_scores_gemma":[0.00046256903,0.00010230834,0.004313277,0.00033943765,0.000029724126,0.0001717336,0.001249425,0.008592297,0.004295572,0.97032034,0.0095601985,0.00056311523],"about_ca_topic_score_codex":0.0006013078,"about_ca_topic_score_gemma":0.00070692017,"teacher_disagreement_score":0.23530799,"about_ca_system_score_codex":0.00010367877,"about_ca_system_score_gemma":0.000029497813,"threshold_uncertainty_score":0.99998987},"labels":[],"label_agreement":null},{"id":"W1775522749","doi":"10.1186/1471-2288-5-5","title":"Comparison of nested case-control and survival analysis methodologies for analysis of time-dependent exposure","year":2005,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":235,"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":"Canadian Institutes of Health Research; McGill University","keywords":"Nested case-control study; Covariate; Proportional hazards model; Statistics; Regression analysis; Cohort; Nested set model; Cohort study; Regression; Medicine; Survival analysis; Econometrics; Mathematics; Computer science; Data mining","score_opus":0.7964481715181267,"score_gpt":0.6724582142401484,"score_spread":0.12398995727797835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1775522749","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":[0.16807553,0.00049326045,0.83039665,0.00022996389,0.000022648854,0.0005329034,0.000074422656,0.00007387649,0.00010077585],"genre_scores_gemma":[0.4017955,0.00006916381,0.59786344,0.00001346464,0.000040092447,0.000103896666,0.00001057021,0.000015372543,0.00008848887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97346383,0.022330143,0.0015083487,0.0005846072,0.0014462629,0.00066682487],"domain_scores_gemma":[0.75514746,0.24272528,0.0004237086,0.0006047116,0.0008549841,0.00024385298],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066856965,0.00022663835,0.0029600803,0.0019479515,0.00009645441,0.000011350901,0.0005493661,0.00055986573,0.0006436655],"category_scores_gemma":[0.24640135,0.0001796553,0.00048290807,0.0023794766,0.0011177763,0.00008355456,0.00029235022,0.0006170315,0.0000012699126],"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":[0.005934169,0.0021211088,0.28597763,0.002736607,0.04593874,0.00023982408,0.007089669,0.0071059074,0.07011959,0.1779649,0.0012213418,0.39355052],"study_design_scores_gemma":[0.0058723586,0.0044990713,0.022637408,0.00016829176,0.0326031,0.0001506328,0.011444956,0.49922225,0.09363995,0.32832605,0.00029744685,0.0011384677],"about_ca_topic_score_codex":0.00028981984,"about_ca_topic_score_gemma":0.0052478737,"teacher_disagreement_score":0.49211636,"about_ca_system_score_codex":0.000071276,"about_ca_system_score_gemma":0.00028920412,"threshold_uncertainty_score":0.9608671},"labels":[],"label_agreement":null},{"id":"W1826708385","doi":"10.1007/978-3-642-57615-7_4","title":"Evaluating profiling as a means of allocating government services","year":2001,"lang":"en","type":"book-chapter","venue":"ZEW economic studies","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":76,"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":"Profiling (computer programming); CLARITY; Equity (law); Racial profiling; Actuarial science; Computer science; Business; Political science; Law; Sociology","score_opus":0.31366495377120945,"score_gpt":0.4627022160364899,"score_spread":0.14903726226528047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826708385","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010867879,0.0036902553,0.000435307,0.000097016076,0.00028579708,0.0011505277,0.00009236151,0.00034408053,0.98303676],"genre_scores_gemma":[0.06035381,0.018271225,0.4095455,0.0005350685,0.0016103842,0.000769903,0.000052572806,0.00088600913,0.5079755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788517,0.000022267222,0.0010220933,0.0004919482,0.00030164223,0.00027688057],"domain_scores_gemma":[0.99719155,0.00072458363,0.001379153,0.0005268712,0.0001360291,0.000041796804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006944185,0.0004761206,0.001088845,0.000060064514,0.00010612603,0.000017575458,0.0003153941,0.00018355693,0.00026913243],"category_scores_gemma":[0.00025831105,0.00046347262,0.00017502358,0.000012096211,0.00013631275,0.00012134115,0.00045015875,0.00026278873,0.00007725526],"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":[0.000021877975,0.000023176275,0.00008415413,0.001842584,0.0013610724,0.000007713775,0.0021429972,0.00011178861,0.0003591683,0.97946894,0.0003390701,0.01423744],"study_design_scores_gemma":[0.00023500483,0.0002602639,0.0000025791978,0.0024026926,0.00036011485,0.000011848175,0.0025474292,0.00049654517,0.0046201125,0.98492426,0.0035575312,0.00058159645],"about_ca_topic_score_codex":0.00002601396,"about_ca_topic_score_gemma":0.00013418433,"teacher_disagreement_score":0.47506127,"about_ca_system_score_codex":0.00081778737,"about_ca_system_score_gemma":0.00007368634,"threshold_uncertainty_score":0.9997817},"labels":[],"label_agreement":null},{"id":"W1828732580","doi":"10.6000/1929-6029.2015.04.03.1","title":"Assessment of the Performance of Imputation Techniques in Observational Studies with Two Measurements","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Euskal Herriko Unibertsitatea; Eusko Jaurlaritza","keywords":"Missing data; Statistics; Imputation (statistics); Markov chain Monte Carlo; Observational study; Propensity score matching; Sample size determination; Econometrics; Monte Carlo method; Mathematics","score_opus":0.6416042088483054,"score_gpt":0.6419404073228557,"score_spread":0.00033619847455035323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1828732580","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":[0.87426794,0.00006699589,0.123475485,0.0010466592,0.00016694065,0.0002855638,0.000023348151,0.0000059706904,0.00066111115],"genre_scores_gemma":[0.79010946,0.00014869176,0.20965317,0.00002099773,0.000037408,0.000012057731,0.0000015888189,0.0000064937485,0.000010134126],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935007,0.00033903556,0.0009041499,0.0000842264,0.0050321803,0.00013970316],"domain_scores_gemma":[0.9914276,0.0023081843,0.00050079206,0.00010696245,0.0055940724,0.0000623756],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008692099,0.00007376737,0.00025962477,0.00037746652,0.000014506773,0.000008546531,0.0006313077,0.000046702768,0.000020559453],"category_scores_gemma":[0.015812837,0.000046377827,0.000021312433,0.00033594662,0.00040481024,0.00019879785,0.00016263268,0.0006352564,1.3396232e-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":[0.00046368403,0.0009899279,0.6145402,0.0002813677,0.00024830896,0.00012456276,0.0015526082,0.0008494516,0.0021441816,0.34038186,0.0015397259,0.036884118],"study_design_scores_gemma":[0.0022911315,0.0012985338,0.109660275,0.0045546847,0.000015518626,0.000065098364,0.0010636384,0.008429789,0.022279471,0.8501281,0.000081376675,0.00013238325],"about_ca_topic_score_codex":0.00003475031,"about_ca_topic_score_gemma":0.00015734883,"teacher_disagreement_score":0.50974625,"about_ca_system_score_codex":0.00057308824,"about_ca_system_score_gemma":0.0012410437,"threshold_uncertainty_score":0.9924774},"labels":[],"label_agreement":null},{"id":"W1839338819","doi":"10.1111/peps.12020","title":"Balancing Treatment and Control Groups in Quasi‐Experiments: An Introduction to Propensity Scoring","year":2012,"lang":"en","type":"article","venue":"Personnel Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"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","funders":"","keywords":"Propensity score matching; Causal inference; Covariate; Matching (statistics); Psychology; Average treatment effect; Inference; Coaching; Econometrics; Statistics; Computer science; Artificial intelligence; Mathematics","score_opus":0.18058103285990598,"score_gpt":0.4453034020683257,"score_spread":0.26472236920841974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1839338819","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":[0.9587248,0.00008502542,0.039088458,0.0009022683,0.00027513388,0.00056140986,0.0000021376015,0.00015254343,0.00020819705],"genre_scores_gemma":[0.9790673,0.000014311014,0.01980306,0.00035873664,0.0005345383,0.00016768201,0.0000024109693,0.000024158422,0.000027782375],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988303,0.00013274574,0.00021580474,0.00036015073,0.00006612425,0.00039485065],"domain_scores_gemma":[0.99934155,0.00006287579,0.00008811362,0.00033758502,0.000030059997,0.00013979158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004092831,0.0001743384,0.00031021607,0.00013514109,0.000062968145,0.0000135119535,0.000075861244,0.00008993228,0.000040783005],"category_scores_gemma":[0.00018873884,0.00015375284,0.000021555596,0.00010920246,0.000046228168,0.00034095146,0.000024033856,0.00011753451,0.000013220079],"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":[0.0009087592,0.004442019,0.28198037,0.000084030224,0.00011226957,0.00002293945,0.08301813,0.0000090402145,0.53711766,0.058335055,0.0007744849,0.033195265],"study_design_scores_gemma":[0.028014695,0.024753097,0.5347496,0.00046802207,0.00045771647,0.0017909209,0.054415114,0.0015035792,0.1676624,0.17099574,0.009326032,0.00586304],"about_ca_topic_score_codex":0.000076500655,"about_ca_topic_score_gemma":0.000090684596,"teacher_disagreement_score":0.36945525,"about_ca_system_score_codex":0.00019126321,"about_ca_system_score_gemma":0.0000058283326,"threshold_uncertainty_score":0.6269859},"labels":[],"label_agreement":null},{"id":"W1856101391","doi":"10.1177/0272989x15600708","title":"Does Introducing Imprecision around Probabilities for Benefit and Harm Influence the Way People Value Treatments?","year":2015,"lang":"en","type":"article","venue":"Medical Decision Making","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":true,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Harm; Population; Actuarial science; Value (mathematics); Confidence interval; Sample (material); Psychology; Medicine; Econometrics; Statistics; Social psychology; Mathematics; Economics; Environmental health","score_opus":0.08853594138880048,"score_gpt":0.41667049148711355,"score_spread":0.32813455009831305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1856101391","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":[0.62846696,0.00012169708,0.36931247,0.0008248108,0.0002374898,0.0007317957,0.000008047834,0.00016294548,0.00013378166],"genre_scores_gemma":[0.7785849,0.000060707025,0.22040878,0.00025683083,0.00022050149,0.00024144354,0.0000023684522,0.00003338724,0.00019109772],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974824,0.00007571987,0.0005843699,0.00048035377,0.0010172192,0.0003599093],"domain_scores_gemma":[0.99123347,0.0074995942,0.00018855958,0.00060368376,0.00027568947,0.00019898891],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023705906,0.00024096465,0.00038714625,0.00011054717,0.00023949677,0.0001375036,0.00042152533,0.00017262743,0.000057043137],"category_scores_gemma":[0.024656182,0.0001118497,0.00007319613,0.00022697171,0.00017942613,0.00033494283,0.0003698972,0.00025312474,0.000004966637],"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":[0.000311423,0.00017088784,0.0027320613,0.00011553639,0.00005124985,0.000010884344,0.004958636,0.0002353172,0.00027507058,0.16529357,0.0019892391,0.8238561],"study_design_scores_gemma":[0.0005082048,0.0002393355,0.00053474086,0.0005719722,0.00003951676,0.000023078705,0.0009610058,0.0062735775,0.0005935978,0.9885267,0.0015523462,0.00017589734],"about_ca_topic_score_codex":0.000023553404,"about_ca_topic_score_gemma":0.00008072232,"teacher_disagreement_score":0.8236802,"about_ca_system_score_codex":0.0001779924,"about_ca_system_score_gemma":0.00008009964,"threshold_uncertainty_score":0.98355955},"labels":[],"label_agreement":null},{"id":"W1874471881","doi":"","title":"Outcome evaluation of an early psychosis program using pre-post comparison and propensity matching","year":2005,"lang":"en","type":"dissertation","venue":"Memorial University Research Repository (Memorial University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Propensity score matching; Matching (statistics); Population; Quality of life (healthcare); Psychosis; Psychology; Medicine; Outcome (game theory); Psychiatry; Clinical psychology; Gerontology; Environmental health; Nursing; Surgery","score_opus":0.2370272762245498,"score_gpt":0.4585523490014368,"score_spread":0.22152507277688702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874471881","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":[0.9807638,0.000026161228,0.00021474775,0.000009644269,0.0020730735,0.0035806177,0.000048277798,0.000371998,0.0129117025],"genre_scores_gemma":[0.9682462,0.000037857495,0.020926222,0.0000014990786,0.0018775291,0.0000042399133,0.00021008794,0.000112103706,0.008584222],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99208325,0.0026382888,0.0007251043,0.0011638011,0.0026544018,0.00073512533],"domain_scores_gemma":[0.993052,0.0004976392,0.0009520528,0.0010014605,0.0040833135,0.00041351744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027389496,0.00057399244,0.0012224898,0.0016674773,0.0012286659,0.00020558863,0.001251718,0.00096759724,0.000040185027],"category_scores_gemma":[0.0006221496,0.0006913029,0.00026336947,0.0012165286,0.00047942201,0.0017478543,0.00042151922,0.0016944843,0.0000032875778],"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":[0.09168532,0.017593447,0.032376796,0.00941259,0.004738106,0.0024858105,0.06465049,0.0016435934,0.5367814,0.11403338,0.0017703947,0.12282874],"study_design_scores_gemma":[0.05975715,0.031992137,0.102050774,0.011043521,0.02588294,0.0002683972,0.23307574,0.034409612,0.39518365,0.06978697,0.018672066,0.01787703],"about_ca_topic_score_codex":0.004708282,"about_ca_topic_score_gemma":0.0031624804,"teacher_disagreement_score":0.16842525,"about_ca_system_score_codex":0.0019976236,"about_ca_system_score_gemma":0.0010640088,"threshold_uncertainty_score":0.9995538},"labels":[],"label_agreement":null},{"id":"W1888549093","doi":"10.1515/jci-2015-0021","title":"Design and Analysis of Experiments in Networks: Reducing Bias from Interference","year":2016,"lang":"en","type":"preprint","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":50,"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":"Stanford Graduate School of Business; University of California, Davis; York University; Carnegie Mellon University; Johns Hopkins University","keywords":"Estimator; Computer science; Random assignment; Cluster analysis; Graph; Randomized experiment; Interference (communication); Machine learning; Theoretical computer science; Mathematics; Statistics","score_opus":0.2956729877312846,"score_gpt":0.4513108218755544,"score_spread":0.1556378341442698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888549093","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":[0.28655478,0.0007580001,0.7120567,0.000038552043,0.00021310608,0.000221848,0.000024350536,0.000027985208,0.0001046785],"genre_scores_gemma":[0.8595647,0.0011848208,0.13906851,0.000019611021,0.000087513035,0.000018838018,0.0000054720354,0.000032039996,0.000018470908],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99598765,0.00053511176,0.00216672,0.00044806398,0.0005093008,0.00035315947],"domain_scores_gemma":[0.9914204,0.0038443836,0.0032549533,0.0006791693,0.00063234434,0.00016873493],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015983362,0.0004771944,0.0019301375,0.0012320202,0.000026438052,0.00008105155,0.00077192043,0.00047040023,0.000121938145],"category_scores_gemma":[0.0022186767,0.00036709136,0.00025419626,0.0005179521,0.0002218751,0.00037464322,0.00077128824,0.0011549895,5.993872e-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":[0.006279028,0.0045628836,0.23462063,0.002092857,0.03387955,0.0015838312,0.04683184,0.1859835,0.243665,0.07332315,0.0032969182,0.16388083],"study_design_scores_gemma":[0.0009917994,0.0007832082,0.008446084,0.011846948,0.0023778235,0.00001852511,0.0003210065,0.041714113,0.061572056,0.8708033,0.00001291481,0.0011122199],"about_ca_topic_score_codex":0.00012070475,"about_ca_topic_score_gemma":0.00002860453,"teacher_disagreement_score":0.79748017,"about_ca_system_score_codex":0.00026161794,"about_ca_system_score_gemma":0.00030976857,"threshold_uncertainty_score":0.9998781},"labels":[],"label_agreement":null},{"id":"W1902826538","doi":"10.1111/j.1540-5982.2010.01622.x","title":"Viewpoint: An extended class of instrumental variables for the estimation of causal effects","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Endogeneity; Instrumental variable; Econometrics; Identification (biology); Covariate; Class (philosophy); Estimation; Causal model; Contrast (vision); Causality (physics); Mathematics; Economics; Statistics; Computer science; Artificial intelligence","score_opus":0.2702152426523947,"score_gpt":0.2734589607369842,"score_spread":0.0032437180845895086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902826538","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":[0.98083967,0.00007911996,0.017243305,0.00018304496,0.00046853328,0.00063761935,0.0001705701,0.000008737565,0.0003694031],"genre_scores_gemma":[0.94836384,0.000037282894,0.05125257,0.00011953595,0.00010496935,0.000041156425,0.0000074457103,0.00004684114,0.000026352842],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823546,0.00007177181,0.0010702785,0.00019579314,0.0000046398354,0.00042207932],"domain_scores_gemma":[0.99662274,0.0007386384,0.0013380365,0.00045111577,0.00025435962,0.0005951133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096143037,0.00023103534,0.0006727904,0.00036759145,0.000094610026,0.000021161482,0.0005772139,0.00016456279,0.00009199271],"category_scores_gemma":[0.00074307556,0.00021727514,0.00018779031,0.000081840706,0.0002651018,0.00052138505,0.000019077701,0.00021692319,6.45382e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008624795,0.00003173316,0.000225073,0.00019475346,0.00015211295,0.000008946788,0.0015968519,0.00057970063,0.00018618662,0.98731107,0.00009493643,0.009532404],"study_design_scores_gemma":[0.0005516878,0.0011274845,0.00043175503,0.00021808675,0.00013862431,0.00015268609,0.00047692226,0.006019657,0.018771464,0.97166497,0.00022146244,0.00022517593],"about_ca_topic_score_codex":0.03405534,"about_ca_topic_score_gemma":0.74891627,"teacher_disagreement_score":0.7148609,"about_ca_system_score_codex":0.0007800601,"about_ca_system_score_gemma":0.0012461476,"threshold_uncertainty_score":0.97237694},"labels":[],"label_agreement":null},{"id":"W1904240997","doi":"10.1186/1742-5573-3-2","title":"Causal analysis of case-control data","year":2006,"lang":"en","type":"article","venue":"Epidemiologic Perspectives & Innovations","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Alberta Hospital; University of Alberta","funders":"","keywords":"Computer science; Counterfactual thinking; Marginal structural model; Inverse probability; Weighting; Inverse probability weighting; Estimation; Data mining; Econometrics; Statistics; Causal inference; Artificial intelligence; Medicine; Mathematics; Bayesian probability; Estimator","score_opus":0.2722278384757412,"score_gpt":0.4688558202934981,"score_spread":0.19662798181775687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904240997","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":[0.11664105,0.00029758012,0.8717098,0.0010855865,0.00003623891,0.00036870522,0.00092962134,0.0004429691,0.008488432],"genre_scores_gemma":[0.8398858,0.000013407343,0.15955949,0.00010167151,0.000080606675,0.000041758307,0.00016485377,0.0000133859385,0.00013905075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977085,0.0003138245,0.00096989423,0.00054700475,0.0001517031,0.00030906673],"domain_scores_gemma":[0.99329317,0.004091286,0.0006453411,0.0013787171,0.00056156015,0.000029935365],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022006084,0.0002164955,0.0008121539,0.0006648167,0.00014305612,0.000011030054,0.00047102143,0.00014800578,0.0002608557],"category_scores_gemma":[0.010386051,0.00018155892,0.00013152412,0.0029905161,0.00032784702,0.00030535556,0.00015915559,0.00027987783,0.0000036531676],"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":[0.00000743571,0.0001793503,0.012557456,0.000006560561,0.00068961264,0.000037603775,0.00016901258,0.00044305142,0.0011914112,0.97872865,0.0057812417,0.00020859731],"study_design_scores_gemma":[0.00023302175,0.000076725795,0.04685072,0.000012588266,0.0013335914,0.00007051508,0.0019240165,0.009870063,0.00015068836,0.9389087,0.00026642982,0.0003029163],"about_ca_topic_score_codex":0.00069332164,"about_ca_topic_score_gemma":0.00047756886,"teacher_disagreement_score":0.7232447,"about_ca_system_score_codex":0.00013589085,"about_ca_system_score_gemma":0.000054041113,"threshold_uncertainty_score":0.9979499},"labels":[],"label_agreement":null},{"id":"W1932363030","doi":"10.1186/s12874-015-0081-3","title":"Statistical power in parallel group point exposure studies with time-to-event outcomes: an empirical comparison of the performance of randomized controlled trials and the inverse probability of treatment weighting (IPTW) approach","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; McGill University; Heart and Stroke Foundation of Canada","keywords":"Observational study; Statistical power; Inverse probability; Statistics; Marginal structural model; Randomized controlled trial; Weighting; Power analysis; Inverse probability weighting; Propensity score matching; Sample size determination; Computer science; Mathematics; Econometrics; Medicine; Algorithm; Posterior probability; Bayesian probability; Internal medicine","score_opus":0.7529466825685419,"score_gpt":0.6219541855890501,"score_spread":0.13099249697949178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1932363030","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":[0.74675745,0.0003010321,0.24636,0.000648741,0.00002265942,0.0057611633,0.0000066932057,0.0000168477,0.00012540685],"genre_scores_gemma":[0.50847656,0.00006270793,0.4903165,0.000024262203,0.000011330941,0.0010636171,0.0000016311396,0.000011220858,0.000032171112],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8930015,0.100736074,0.003324664,0.00047095702,0.001951458,0.00051533204],"domain_scores_gemma":[0.7537316,0.24401972,0.0007908219,0.000583598,0.00063788943,0.00023636894],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18122926,0.00023870965,0.0066826516,0.00017276137,0.00005369314,0.0000058203755,0.00042957053,0.00019734992,0.000053646327],"category_scores_gemma":[0.4755994,0.00008531229,0.0002546557,0.00029547725,0.0042898073,0.00005275501,0.00035133684,0.00053942093,5.6540466e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.750981,0.0043374877,0.08313236,0.001487014,0.0020750265,0.0000059028507,0.042305052,0.00048906554,0.00032288767,0.110554874,0.0004730429,0.0038363314],"study_design_scores_gemma":[0.5005914,0.011965858,0.002999938,0.0007653569,0.00069432287,0.000017148153,0.017161299,0.06598046,0.0013619376,0.39811018,0.000018742583,0.00033334518],"about_ca_topic_score_codex":0.00009775284,"about_ca_topic_score_gemma":0.0002973432,"teacher_disagreement_score":0.29437014,"about_ca_system_score_codex":0.0001753271,"about_ca_system_score_gemma":0.0007642903,"threshold_uncertainty_score":0.99841994},"labels":[],"label_agreement":null},{"id":"W1935711966","doi":"10.1080/01621459.2012.665615","title":"Comment","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"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 on Drug Abuse; National Institute of Mental Health","keywords":"Mathematics","score_opus":0.08176577088976356,"score_gpt":0.42506965710657935,"score_spread":0.3433038862168158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935711966","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":[0.1300977,0.000028524983,0.85379106,0.013944132,0.0004921654,0.00016164168,0.00003733841,0.000048890153,0.001398547],"genre_scores_gemma":[0.8379387,0.00001088967,0.16056642,0.0011976328,0.00018601367,0.000001939233,3.637943e-7,0.000009677964,0.000088319044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875945,0.00023406859,0.00034504308,0.000033864744,0.0004315652,0.00019603068],"domain_scores_gemma":[0.99625695,0.001958928,0.001438124,0.000107991946,0.00016289939,0.0000751289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010647823,0.00006668378,0.00023171358,0.000027479251,0.00004880929,0.00001301773,0.00015099708,0.00002011082,0.000037911846],"category_scores_gemma":[0.004995873,0.000041260428,0.0000683261,0.0001336407,0.000053818043,0.00013299071,0.000041976975,0.00023506032,0.0000070797014],"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":[0.000051531446,0.00042906127,0.1277759,0.00001409625,0.00016254825,0.0000019835882,0.00046626196,0.0000021343296,0.0010639236,0.573217,0.27785024,0.018965358],"study_design_scores_gemma":[0.00027195073,0.00030498576,0.14119804,0.000045845816,0.000194979,0.000027070195,0.00031207022,0.0000489334,0.0025463358,0.8304043,0.02446724,0.00017829346],"about_ca_topic_score_codex":0.000006627248,"about_ca_topic_score_gemma":0.0000010429409,"teacher_disagreement_score":0.70784104,"about_ca_system_score_codex":0.00055377936,"about_ca_system_score_gemma":0.000022991197,"threshold_uncertainty_score":0.5980888},"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":"W1953676460","doi":"10.6000/1929-6029.2015.04.02.7","title":"Using Propensity Score Matching in Clinical Investigations: A Discussion and Illustration","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Propensity score matching; Observational study; Matching (statistics); Randomized controlled trial; Computer science; Percutaneous coronary intervention; Conventional PCI; Medicine; Internal medicine; Pathology","score_opus":0.7586343223110931,"score_gpt":0.6327789393899821,"score_spread":0.12585538292111098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953676460","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":[0.66468817,0.000029272824,0.33311304,0.0016570949,0.00019863469,0.00015161591,0.000008212509,0.0000062344707,0.00014769855],"genre_scores_gemma":[0.7610258,0.0001731344,0.23853163,0.00006045113,0.0001767993,0.0000032589228,0.0000032412477,0.000009677086,0.0000159968],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954896,0.00070092315,0.0010771578,0.00013733761,0.0024116875,0.0001833055],"domain_scores_gemma":[0.9956936,0.0023463694,0.00026692063,0.00008793672,0.0013146828,0.00029048097],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013049795,0.000076404685,0.00024335786,0.00046160948,0.00002786841,0.00006164115,0.00035930102,0.00012904323,0.000031016636],"category_scores_gemma":[0.0563081,0.00005181908,0.000018977717,0.00021127815,0.0004318491,0.00030961214,0.00021825566,0.0013908293,0.0000012224364],"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":[0.00058968255,0.0009258241,0.23090295,0.00011667989,0.00006049487,0.003554884,0.0034875304,0.00019078651,0.00053392723,0.58978564,0.0026760742,0.16717553],"study_design_scores_gemma":[0.0007620238,0.00015202937,0.010167634,0.0011080591,0.000003096261,0.00015195612,0.0005448888,0.0072736256,0.00006879781,0.97960335,0.00009929273,0.00006523012],"about_ca_topic_score_codex":0.00011818422,"about_ca_topic_score_gemma":0.00038442886,"teacher_disagreement_score":0.38981774,"about_ca_system_score_codex":0.00035054056,"about_ca_system_score_gemma":0.0009606538,"threshold_uncertainty_score":0.951641},"labels":[],"label_agreement":null},{"id":"W1955780894","doi":"10.1186/1742-5573-2-9","title":"An easy approach to the Robins-Breslow-Greenland variance estimator","year":2005,"lang":"en","type":"article","venue":"Epidemiologic Perspectives & Innovations","topic":"Advanced Causal Inference Techniques","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":"Queen's University","funders":"","keywords":"Variance (accounting); Estimator; Statistics; Odds; Variance components; Logarithm; Odds ratio; Computer science; Mathematics; Econometrics; Logistic regression","score_opus":0.18189499696771005,"score_gpt":0.4375992348551201,"score_spread":0.25570423788741004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1955780894","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":[0.01702895,0.00012541248,0.94111574,0.011495771,0.000058705078,0.00088547403,0.000040777526,0.0009144414,0.028334737],"genre_scores_gemma":[0.47508004,0.00001382709,0.52251506,0.001304394,0.00031183203,0.00034301478,0.000015282762,0.000024173441,0.00039240095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975839,0.00039605916,0.00065802527,0.0006582998,0.00020251435,0.0005011704],"domain_scores_gemma":[0.9966729,0.0013756073,0.0002994744,0.0010923703,0.00044510185,0.000114520284],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022348936,0.00031717386,0.00046585148,0.0001888326,0.00048998283,0.000050518996,0.00074915076,0.00016675555,0.00008651352],"category_scores_gemma":[0.008439412,0.0002132872,0.000084513915,0.0011886911,0.00023876975,0.00046404052,0.0001231183,0.0005473519,0.00007020999],"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":[0.000012131727,0.00033026037,0.00050068594,0.0000060083594,0.00003119805,7.26871e-7,0.0014905053,0.002430009,0.0010045808,0.9814391,0.010982559,0.0017721939],"study_design_scores_gemma":[0.00025829428,0.0002609856,0.015960399,0.000039079016,0.000038069542,0.00004364311,0.003510269,0.0128708305,0.00043455628,0.9496241,0.016321892,0.00063784496],"about_ca_topic_score_codex":0.000036468886,"about_ca_topic_score_gemma":0.00002425153,"teacher_disagreement_score":0.4580511,"about_ca_system_score_codex":0.0002886739,"about_ca_system_score_gemma":0.00008023339,"threshold_uncertainty_score":0.9999129},"labels":[],"label_agreement":null},{"id":"W1960011844","doi":"10.1002/sim.6123","title":"Extending the Bayesian Adjustment for Confounding algorithm to binary treatment covariates to estimate the effect of smoking on carotid intima-media thickness: the Multi-Ethnic Study of Atherosclerosis","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"Université du Québec à Montréal","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; Fonds de Recherche du Québec - Santé; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Covariate; Statistics; Bayesian probability; Sample size determination; Medicine; Mathematics; Weighting; Algorithm; Econometrics; Radiology","score_opus":0.10143956355485871,"score_gpt":0.46787909410228273,"score_spread":0.366439530547424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960011844","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":[0.07959876,0.000055753215,0.91457576,0.0003481655,0.00038746838,0.004849413,0.0001035087,0.000053425272,0.000027752325],"genre_scores_gemma":[0.7481006,0.000036582518,0.25025478,0.00011573982,0.00011821248,0.0012913082,0.000011938405,0.000053341242,0.000017554901],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751943,0.0005722384,0.00074152264,0.0003174125,0.00050301437,0.00034636023],"domain_scores_gemma":[0.97917396,0.01951472,0.00037249917,0.00072640873,0.00014174609,0.00007064029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035166242,0.0003318896,0.0007410901,0.00016215598,0.00018285956,0.000011867986,0.00047920118,0.00006021411,0.000014344617],"category_scores_gemma":[0.0066988533,0.00014737136,0.000053863758,0.00037734484,0.00023786124,0.000028066766,0.00012544196,0.00023669138,9.0602936e-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":[0.0009891313,0.0023689822,0.013845601,0.0012890577,0.0012609895,0.000013767339,0.2046039,0.009456728,0.01894476,0.27426437,0.001620893,0.47134185],"study_design_scores_gemma":[0.031603843,0.15818019,0.14849605,0.014686241,0.006026082,0.00002869001,0.06344428,0.2041562,0.06881506,0.3018004,0.00036938913,0.0023935586],"about_ca_topic_score_codex":0.00034347572,"about_ca_topic_score_gemma":0.00036645125,"teacher_disagreement_score":0.6685018,"about_ca_system_score_codex":0.00025274412,"about_ca_system_score_gemma":0.000023789311,"threshold_uncertainty_score":0.80196375},"labels":[],"label_agreement":null},{"id":"W1964475341","doi":"10.1002/sim.3150","title":"A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003","year":2007,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1250,"is_retracted":false,"has_abstract":true,"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","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Wilcoxon signed-rank test; Statistics; Observational study; Matching (statistics); Selection bias; Logistic regression; Sample size determination; Statistical significance; Medicine; Mathematics; Mann–Whitney U test","score_opus":0.2610013184506083,"score_gpt":0.5385518179316583,"score_spread":0.27755049948105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964475341","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":[0.000023897848,0.8471528,0.15052512,0.00013599114,0.00018194476,0.0010049988,0.0002986965,0.00003714857,0.0006393584],"genre_scores_gemma":[0.000092466355,0.8832279,0.11592955,0.00008253232,0.00033030077,0.000058893977,0.00021293393,0.000052662777,0.000012795826],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99605024,0.00057562615,0.001539771,0.0003873369,0.0010481885,0.00039882286],"domain_scores_gemma":[0.97870207,0.020145297,0.00033543305,0.00045795544,0.00023006814,0.00012919214],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004457467,0.00042904716,0.0024102915,0.00040834825,0.000032493997,0.000014250727,0.000513162,0.0005737967,0.00005300863],"category_scores_gemma":[0.04742031,0.00024653197,0.00003858292,0.0009533892,0.0008578071,0.00006270395,0.00015627529,0.0023704416,0.0000011374929],"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":[0.000007285114,0.00008025152,0.00015144087,0.035943996,0.000030003373,0.001268713,0.002018572,9.882061e-9,1.7622652e-7,0.3921306,0.002840202,0.56552875],"study_design_scores_gemma":[0.0005263903,0.00041779105,0.00022267608,0.16966456,0.00060877576,0.00048702862,0.000338661,0.000009597476,7.240726e-7,0.7095591,0.11762336,0.00054134976],"about_ca_topic_score_codex":0.000050213224,"about_ca_topic_score_gemma":0.000113415386,"teacher_disagreement_score":0.5649874,"about_ca_system_score_codex":0.00006538287,"about_ca_system_score_gemma":0.00023372969,"threshold_uncertainty_score":0.9999987},"labels":[],"label_agreement":null},{"id":"W1964746590","doi":"10.1037/a0023910","title":"On the confounds among retest gains and age-cohort differences in the estimation of within-person change in longitudinal studies: A simulation study.","year":2011,"lang":"en","type":"article","venue":"Psychology and Aging","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":75,"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":"National Institute on Aging; National Institutes of Health","keywords":"Psychology; Longitudinal study; Cohort; Cognition; Cohort study; Convergence (economics); Cohort effect; Developmental psychology; Statistics; Mathematics","score_opus":0.5414389222022995,"score_gpt":0.4989594419450636,"score_spread":0.04247948025723591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964746590","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":[0.997424,0.00012269744,0.0012301711,0.00012441461,0.000027387843,0.0005777504,5.1393835e-7,0.000020613252,0.000472444],"genre_scores_gemma":[0.9991557,0.000055644905,0.00052776403,0.00012172947,0.000008686307,0.00012184494,4.3243335e-7,0.0000051342467,0.0000030878393],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99926794,0.00017558968,0.00019811258,0.00017367203,0.00008135084,0.000103328],"domain_scores_gemma":[0.99863183,0.0010450392,0.00013565696,0.00015738937,0.00002087064,0.000009189038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094204425,0.000099636665,0.00019392942,0.00009060006,0.000063426894,0.000008349691,0.00008530091,0.000042298383,0.000003832541],"category_scores_gemma":[0.00037871217,0.00005690991,0.000009372171,0.0001224564,0.00022496356,0.000121529425,0.00001897289,0.00018587935,1.8338719e-7],"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":[0.000025594523,0.00014442584,0.883415,0.000025475281,0.000019290972,0.000013285187,0.10486423,0.000006431461,0.000013648867,0.010073706,0.0000024167248,0.0013965141],"study_design_scores_gemma":[0.00020171922,0.00023587882,0.8851759,0.00012526222,0.000017892919,0.000002265788,0.0069204164,0.0021464338,0.000015673082,0.10509746,8.9784976e-8,0.000061015657],"about_ca_topic_score_codex":0.000073993884,"about_ca_topic_score_gemma":0.00047720489,"teacher_disagreement_score":0.09794382,"about_ca_system_score_codex":0.00000941806,"about_ca_system_score_gemma":0.0000018925051,"threshold_uncertainty_score":0.23207188},"labels":[],"label_agreement":null},{"id":"W1966553403","doi":"10.1002/bimj.201000038","title":"When should one adjust for measurement error in baseline variables in observational studies?","year":2011,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Advanced Causal Inference Techniques","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":"Covariate; Estimator; Statistics; Baseline (sea); Observational study; Observational error; Mathematics; Sample size determination; Standard error; Variable (mathematics); Reliability (semiconductor); Econometrics; Power (physics)","score_opus":0.9081606865968035,"score_gpt":0.5170141048256166,"score_spread":0.3911465817711869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966553403","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":[0.016921945,0.001676328,0.97778994,0.0017690782,0.0002951278,0.0008740815,0.000031523497,0.000115305374,0.00052667735],"genre_scores_gemma":[0.26520923,0.00017040462,0.7339444,0.00031555875,0.00017583511,0.00010397737,0.0000033138042,0.00002848962,0.000048762442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976071,0.00014512117,0.00090183894,0.00022189913,0.00073828717,0.00038575951],"domain_scores_gemma":[0.99720484,0.0014898375,0.00028288466,0.00017207289,0.00072493544,0.00012542157],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004622795,0.0001796727,0.0004521099,0.0015114746,0.00005758736,0.000021967526,0.00028429469,0.0001397385,0.00018350883],"category_scores_gemma":[0.019395472,0.00015029797,0.00008783772,0.0017011961,0.000055691118,0.0002589191,0.00007972431,0.00038116518,0.0000033259287],"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":[0.0025446096,0.018466324,0.123562954,0.0015152469,0.0013092367,0.0003727311,0.006492766,0.000061268925,0.02930819,0.5498653,0.1169465,0.1495549],"study_design_scores_gemma":[0.0016449465,0.00047134544,0.016205367,0.00043188312,0.000054497286,0.000023201545,0.0003273233,0.0006025343,0.0041384683,0.97372127,0.0020402179,0.00033894661],"about_ca_topic_score_codex":0.00001892154,"about_ca_topic_score_gemma":0.00006589713,"teacher_disagreement_score":0.423856,"about_ca_system_score_codex":0.0007483122,"about_ca_system_score_gemma":0.0001289138,"threshold_uncertainty_score":0.9888646},"labels":[],"label_agreement":null},{"id":"W1967188199","doi":"10.2202/1557-4679.1198","title":"Comparing Approaches to Causal Inference for Longitudinal Data: Inverse Probability Weighting versus Propensity Scores","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":45,"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; McGill University","keywords":"Propensity score matching; Causal inference; Inverse probability weighting; Estimator; Covariate; Statistics; Inverse probability; Weighting; Observational study; Average treatment effect; Econometrics; Marginal structural model; Mathematics; Inference; Mean squared error; Global Positioning System; Confidence interval; Computer science; Bayesian probability; Medicine; Posterior probability; Artificial intelligence","score_opus":0.6633736756072357,"score_gpt":0.4530269615981859,"score_spread":0.2103467140090498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967188199","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":[0.5040024,0.000004070826,0.49307737,0.0010519302,0.0011024713,0.00040924374,0.00017324119,0.000034900153,0.00014439765],"genre_scores_gemma":[0.61542636,0.0000032807504,0.3841811,0.000035921377,0.0003069726,0.000006996599,0.000016754813,0.000011987142,0.000010611464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983362,0.000052510048,0.0006243219,0.00021922866,0.0005642172,0.00020350065],"domain_scores_gemma":[0.99538153,0.0024857146,0.0006306467,0.00048820858,0.00090921053,0.000104656756],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001683063,0.00016757667,0.0002923752,0.00009915435,0.000115149734,0.00014380373,0.0016059981,0.00005746256,0.000016117781],"category_scores_gemma":[0.010886909,0.00011538083,0.00005137013,0.000089827736,0.00020135306,0.00036048063,0.0005902982,0.00049784826,0.0000037006066],"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":[0.0022798565,0.0004488319,0.027645703,0.00012536018,0.0004959269,0.000042239473,0.0011015659,0.00030447336,0.007980762,0.94009507,0.009358838,0.010121368],"study_design_scores_gemma":[0.0016940641,0.00064421527,0.0075008883,0.00025648385,0.00023591403,0.00014683853,0.00024852436,0.016948953,0.020434583,0.9496724,0.0017424407,0.00047471668],"about_ca_topic_score_codex":0.000035921094,"about_ca_topic_score_gemma":0.0011337369,"teacher_disagreement_score":0.11142399,"about_ca_system_score_codex":0.000108864115,"about_ca_system_score_gemma":0.00020447817,"threshold_uncertainty_score":0.9974448},"labels":[],"label_agreement":null},{"id":"W1968518701","doi":"10.1016/j.jclinepi.2014.06.021","title":"Regression discontinuity designs are underutilized in medicine, epidemiology, and public health: a review of current and best practice","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":243,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Medical Association; Wellcome Trust; Society for the Psychological Study of Social Issues; World Health Organization","keywords":"Regression discontinuity design; Epidemiology; Public health; Medicine; Regression; MEDLINE; Family medicine; Environmental health; Political science; Statistics; Mathematics; Pathology","score_opus":0.927473019810263,"score_gpt":0.7333156026957495,"score_spread":0.1941574171145135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968518701","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":[0.0000063705756,0.96005887,0.0201165,0.018156866,0.00047834328,0.0010561399,0.000017893579,0.000018831037,0.000090204245],"genre_scores_gemma":[0.000005139694,0.93284607,0.06492895,0.0017461202,0.00038232913,0.0000316247,0.000010093412,0.00003942193,0.000010269035],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8948704,0.077526316,0.025404643,0.0008727734,0.00040783023,0.00091804005],"domain_scores_gemma":[0.5581375,0.38034546,0.05808296,0.0009246902,0.0012847395,0.0012246525],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.214425,0.0006404742,0.026469376,0.00041649461,0.000041609983,0.0000034614484,0.0005809895,0.0010812726,0.00002155333],"category_scores_gemma":[0.82781047,0.0003589456,0.0008164394,0.0003698128,0.0016196258,0.00031744145,0.0003742081,0.0042346497,0.0000013704297],"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":[0.000050995506,0.0004443656,0.0009791211,0.07558021,0.00013362891,0.000018559529,0.000027639919,2.1768443e-8,7.968777e-9,0.020557914,0.01695811,0.88524944],"study_design_scores_gemma":[0.00046509615,0.0012562023,0.000050388902,0.271956,0.00054561585,0.00047977653,0.00006584777,0.0000034426994,3.7287413e-9,0.1908174,0.5341908,0.00016947572],"about_ca_topic_score_codex":0.000029349834,"about_ca_topic_score_gemma":0.000038059843,"teacher_disagreement_score":0.8850799,"about_ca_system_score_codex":0.00022629411,"about_ca_system_score_gemma":0.0015866208,"threshold_uncertainty_score":0.9998863},"labels":[],"label_agreement":null},{"id":"W1970310544","doi":"10.1016/s1098-3015(10)61081-9","title":"PMH15 PREVALENCE AND COSTS OF TREATMENT-RESISTANT DEPRESSION IN A CANADIAN CLAIMS DATABASE","year":2002,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Depression (economics); Treatment-resistant depression; Database; Medicine; Business; Psychiatry; Computer science; Economics; Major depressive disorder","score_opus":0.18937100839147772,"score_gpt":0.40805489499402336,"score_spread":0.21868388660254565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970310544","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":[0.99515355,0.002450941,0.00038069158,0.00027945847,0.000025524365,0.00089254184,0.00014084046,0.000051953837,0.0006244726],"genre_scores_gemma":[0.9828907,0.002640033,0.014295145,0.00004930969,0.000006932997,0.000047024747,0.00000398206,0.000014582402,0.000052262138],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99869484,0.00021626655,0.00040232262,0.000223414,0.00010430224,0.00035884316],"domain_scores_gemma":[0.998962,0.00035504712,0.0001283282,0.00032768943,0.00001911547,0.0002078167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052019686,0.0001179593,0.00025373034,0.000227184,0.000034020624,0.000005525052,0.00009272954,0.000059934013,0.000040809493],"category_scores_gemma":[0.00025906798,0.00010576699,0.000013438277,0.00019667059,0.0000450018,0.00011393574,0.000025187463,0.00011436694,0.0000017508668],"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":[0.00014272088,0.001358317,0.7541128,0.0053277113,0.000024843703,0.00026628078,0.009980057,0.0004258585,0.0035941976,0.14144275,0.0013166913,0.08200777],"study_design_scores_gemma":[0.013432639,0.009078277,0.17147034,0.05401884,0.00011170208,0.00020858625,0.0018961935,0.2071204,0.0262567,0.5071232,0.005695988,0.003587159],"about_ca_topic_score_codex":0.44734964,"about_ca_topic_score_gemma":0.29836148,"teacher_disagreement_score":0.58264244,"about_ca_system_score_codex":0.0011510894,"about_ca_system_score_gemma":0.00020584704,"threshold_uncertainty_score":0.7144416},"labels":[],"label_agreement":null},{"id":"W1970517271","doi":"10.1080/01621459.2011.643743","title":"Partially Hidden Markov Model for Time-Varying Principal Stratification in HIV Prevention Trials","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","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":"Université de Montréal","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Human immunodeficiency virus (HIV); Markov model; Markov chain; Principal (computer security); Mathematics; Econometrics; Statistics; Computer science; Medicine; Virology","score_opus":0.14586056066597575,"score_gpt":0.44569357495264006,"score_spread":0.2998330142866643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970517271","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":[0.06945519,0.000009467631,0.9289343,0.00079821714,0.00007322386,0.00048790933,0.000061402345,0.000022367469,0.00015792705],"genre_scores_gemma":[0.5960547,0.000007781229,0.40328163,0.000046934056,0.00015711406,0.000031029773,0.000006573007,0.000014689575,0.00039956038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738663,0.0006810182,0.0011162843,0.00009109694,0.00045360683,0.000271348],"domain_scores_gemma":[0.9925819,0.0037068937,0.0032485414,0.000137138,0.00025433747,0.000071160204],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005527363,0.00011514739,0.00054190867,0.00007530759,0.000059378326,0.000033117645,0.00017262746,0.000058201167,0.000021782764],"category_scores_gemma":[0.0168615,0.00008336475,0.00014758747,0.00016701374,0.000039661587,0.00034314638,0.00002897994,0.00022837371,0.0000033201823],"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":[0.0029378773,0.003664772,0.075434014,0.00030180422,0.00095628324,0.0000038678477,0.0049125,0.002165211,0.073033385,0.4242457,0.061749563,0.35059506],"study_design_scores_gemma":[0.0010098547,0.00029156523,0.02105415,0.00014118152,0.00037654195,0.0000061976457,0.00011971817,0.109349124,0.0029540637,0.8643467,0.00009400911,0.00025691366],"about_ca_topic_score_codex":0.0000033502413,"about_ca_topic_score_gemma":0.0000076079505,"teacher_disagreement_score":0.52659947,"about_ca_system_score_codex":0.0007108729,"about_ca_system_score_gemma":0.00012699334,"threshold_uncertainty_score":0.9914199},"labels":[],"label_agreement":null},{"id":"W1972445384","doi":"10.1002/sim.5690","title":"On estimating average effects for multiple treatment groups","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"St. Michael's Hospital","funders":"","keywords":"Covariate; Statistics; Propensity score matching; Robustness (evolution); Population; Econometrics; Observational study; Variable (mathematics); Average treatment effect; Instrumental variable; Mathematics; Medicine; Biology","score_opus":0.10760751865554542,"score_gpt":0.4506370219169127,"score_spread":0.3430295032613673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972445384","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":[0.013592341,0.00005133771,0.9841381,0.000052678293,0.00039647843,0.00088952435,0.00006482866,0.00012755835,0.0006871889],"genre_scores_gemma":[0.38432974,0.000009241334,0.6149774,0.00008726097,0.00021027814,0.00022999232,0.00003876751,0.000026668875,0.00009061086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891776,0.000053111977,0.00031963724,0.00015968045,0.0001866882,0.0003631168],"domain_scores_gemma":[0.98969185,0.009800056,0.0001250805,0.00024244409,0.000045216253,0.00009534961],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00045582678,0.00019406341,0.0003690188,0.00010047293,0.00005529474,0.0000040803093,0.00007953839,0.000060171653,0.00004287949],"category_scores_gemma":[0.009383791,0.00014407157,0.000019341343,0.00008062042,0.00007688413,0.0000573506,0.000017610662,0.00011960859,0.0000075646967],"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":[0.000056662735,0.00031496675,0.0010996264,0.00037670715,0.000023213655,0.000017771381,0.002295094,0.0000480418,0.0007933324,0.95719403,0.0051352447,0.032645334],"study_design_scores_gemma":[0.0018728095,0.0014032816,0.00040783285,0.00043476594,0.000045510827,0.000004082263,0.00007856427,0.01481785,0.0028686698,0.9776277,0.00025937508,0.00017953562],"about_ca_topic_score_codex":0.000022912125,"about_ca_topic_score_gemma":0.000027372784,"teacher_disagreement_score":0.3707374,"about_ca_system_score_codex":0.00024361904,"about_ca_system_score_gemma":0.000012213944,"threshold_uncertainty_score":0.9989606},"labels":[],"label_agreement":null},{"id":"W1972795335","doi":"10.1002/sim.3989","title":"Estimation of relative risk and prevalence ratio","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","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 Alberta","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Statistics; Mathematics; Binomial regression; Logistic regression; Binomial (polynomial); Negative binomial distribution; Confounding; Point estimation; Relative risk; Econometrics; Computer science; Confidence interval; Poisson distribution","score_opus":0.056982222668341694,"score_gpt":0.4327492605441972,"score_spread":0.3757670378758555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972795335","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":[0.05781436,0.00003970984,0.940701,0.000056771358,0.00006515989,0.0002178851,0.000062974446,0.00003455107,0.0010076076],"genre_scores_gemma":[0.47495788,0.00011964642,0.52480847,0.0000074742647,0.000014474924,0.000009342782,0.0000047755057,0.0000061705937,0.000071741466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992433,0.000049999933,0.00032899526,0.0001196496,0.00017069142,0.000087327746],"domain_scores_gemma":[0.9975757,0.0018908296,0.00022732806,0.00018412468,0.00008914509,0.000032891683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006248485,0.00008269612,0.00019985877,0.00008197681,0.000022912103,0.0000020367115,0.00006519543,0.000055725457,0.00010656935],"category_scores_gemma":[0.011664962,0.00006738107,0.0000045498796,0.000101489575,0.00035937296,0.000088621724,0.00002403262,0.0003281997,9.879419e-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":[0.000008938409,0.000020874466,0.0030222544,0.00019464786,0.0000050248523,0.000003323901,0.0014299875,0.000008518454,0.0024409562,0.9680081,0.0004394016,0.024418],"study_design_scores_gemma":[0.00025036663,0.00015344564,0.005594871,0.000171975,0.00003577688,0.0000032774342,0.00006877559,0.0119521385,0.0022259015,0.9794637,0.000017300496,0.00006246008],"about_ca_topic_score_codex":0.000031900618,"about_ca_topic_score_gemma":0.00008375703,"teacher_disagreement_score":0.41714352,"about_ca_system_score_codex":0.0000132376035,"about_ca_system_score_gemma":0.000018930956,"threshold_uncertainty_score":0.99666023},"labels":[],"label_agreement":null},{"id":"W1972903893","doi":"10.2202/1557-4679.1207","title":"Impact of Outcome Model Misspecification on Regression and Doubly-Robust Inverse Probability Weighting to Estimate Causal Effect","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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":"University of British Columbia; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Inverse probability weighting; Covariate; Estimator; Propensity score matching; Statistics; Average treatment effect; Econometrics; Confounding; Outcome (game theory); Regression analysis; Regression; Weighting; Mathematics; Observational study; Inverse probability; Medicine; Bayesian probability","score_opus":0.14815524905517047,"score_gpt":0.470020886576831,"score_spread":0.32186563752166053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972903893","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":[0.83579457,0.000002572744,0.16316856,0.00043188862,0.00019381753,0.00019933381,0.00006518187,0.000018857923,0.00012522002],"genre_scores_gemma":[0.7262388,0.0000044290036,0.273621,0.000026067197,0.00007001304,0.0000026276703,0.0000029607688,0.000013102585,0.000021018208],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854755,0.00006380797,0.00064088474,0.00012116475,0.0005063777,0.00012020978],"domain_scores_gemma":[0.99699855,0.001201261,0.00077582983,0.00023184529,0.0006981715,0.00009433368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011061078,0.00015653012,0.00026272002,0.00014221162,0.0000479064,0.000040584287,0.0003960585,0.00006458637,0.000020438396],"category_scores_gemma":[0.0037243653,0.00008932099,0.00007766524,0.00007176698,0.00011600831,0.00012366305,0.00009000976,0.0004006464,0.000001986826],"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":[0.0036406666,0.0008935545,0.060802836,0.0002489452,0.0005318205,0.0000929983,0.0027745678,0.02843456,0.45408633,0.404622,0.009375091,0.034496658],"study_design_scores_gemma":[0.0012752444,0.0017619476,0.019232778,0.00057744374,0.0001416958,0.00026923497,0.000035852474,0.07887905,0.07507081,0.8223613,0.00003668353,0.00035794708],"about_ca_topic_score_codex":0.000014674922,"about_ca_topic_score_gemma":0.000025318652,"teacher_disagreement_score":0.41773933,"about_ca_system_score_codex":0.00013445878,"about_ca_system_score_gemma":0.00006355269,"threshold_uncertainty_score":0.44586822},"labels":[],"label_agreement":null},{"id":"W1973426926","doi":"10.1111/j.1365-2753.2005.00624.x","title":"Quantifying the impact of survivor treatment bias in observational studies","year":2005,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Observational study; Medicine; Hazard ratio; Treatment effect; Proportional hazards model; Survival analysis; Average treatment effect; Intensive care medicine; Emergency medicine; Confidence interval; Propensity score matching; Internal medicine","score_opus":0.9136852754774484,"score_gpt":0.7239443433973133,"score_spread":0.1897409320801351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973426926","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":[0.99133396,0.0008536286,0.0015295096,0.0052259224,0.00015223338,0.0004119614,0.0000021444073,0.000007717656,0.0004829488],"genre_scores_gemma":[0.9300108,0.0012617463,0.06838429,0.000108264416,0.00019523854,0.000015333128,6.992246e-7,0.000009306039,0.000014355229],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941126,0.0022450492,0.002605479,0.00011946656,0.00078713096,0.00013026973],"domain_scores_gemma":[0.9352709,0.059625067,0.0029697537,0.0002338504,0.0018625604,0.00003784076],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03031873,0.00011869656,0.00050759065,0.00014979189,0.000029568704,0.000015560841,0.0001424116,0.0000871412,0.00007224886],"category_scores_gemma":[0.17982912,0.00006748438,0.00022096424,0.00032283514,0.00008725508,0.00093127653,0.00003075972,0.00045246613,0.000003354924],"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":[0.0033099821,0.011665986,0.6019461,0.00010511514,0.0018543344,0.00005815634,0.009225696,0.06890342,0.00064011686,0.04624615,0.0056925877,0.25035232],"study_design_scores_gemma":[0.005640645,0.0040186103,0.56813467,0.0008050358,0.0006488147,0.00012932303,0.0050147707,0.029078515,0.00055099616,0.3840368,0.0016221816,0.00031965497],"about_ca_topic_score_codex":0.000065049164,"about_ca_topic_score_gemma":0.00044639574,"teacher_disagreement_score":0.33779067,"about_ca_system_score_codex":0.0006593464,"about_ca_system_score_gemma":0.00047010087,"threshold_uncertainty_score":0.9984909},"labels":[],"label_agreement":null},{"id":"W1973852387","doi":"10.1007/978-1-4939-2428-8_4","title":"Longitudinal Studies 1: Determination of Risk","year":2015,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Memorial University of Newfoundland","funders":"","keywords":"Observational study; Confounding; Casual; Selection bias; Computer science; Clinical study design; Risk analysis (engineering); Econometrics; Psychology; Medicine; Statistics; Clinical trial; Mathematics","score_opus":0.3593001423795641,"score_gpt":0.5920642771108096,"score_spread":0.23276413473124546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973852387","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":[0.021311672,0.0011778529,0.9767728,0.000018140967,0.00008399611,0.00012537009,0.0000029325888,0.000052181247,0.0004550682],"genre_scores_gemma":[0.03029705,0.000111995825,0.96951324,0.000014365793,0.0000102316935,0.00003265547,0.0000013716004,0.000011269583,0.000007808895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811435,0.0011629143,0.00032632743,0.00018458116,0.00006264819,0.00014915639],"domain_scores_gemma":[0.99820983,0.0011035452,0.00021202589,0.0002598056,0.0001867539,0.000028062213],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023831148,0.00010763796,0.00034539585,0.00015035296,0.000010328234,0.000001695744,0.00014008248,0.00011612628,0.0000036834083],"category_scores_gemma":[0.012918166,0.00009196131,0.000042846914,0.0001792706,0.00017796019,0.00003646847,0.00011430582,0.000142787,9.0530295e-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":[0.000058893114,0.00015931526,0.023892077,0.00011660428,0.00006257253,0.000040112867,0.0017571062,0.000012998413,0.22975323,0.43576124,0.000038093804,0.30834773],"study_design_scores_gemma":[0.0001317513,0.00011606119,0.00009043624,0.000016442198,0.000016045591,0.0000045396105,0.00013417641,0.00008657359,0.23164296,0.76760036,0.00008871015,0.00007196737],"about_ca_topic_score_codex":0.000010594111,"about_ca_topic_score_gemma":0.000020475703,"teacher_disagreement_score":0.33183908,"about_ca_system_score_codex":0.00006093479,"about_ca_system_score_gemma":0.00002049308,"threshold_uncertainty_score":0.99539644},"labels":[],"label_agreement":null},{"id":"W1974429147","doi":"10.1136/annrheumdis-2014-eular.2210","title":"THU0416 Attrition Bias in Rheumatoid Arthritis Randomised Trials with Different Modified Intention-To-Treat Approaches: A Meta-Epidemiological Study","year":2014,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McMaster University","funders":"","keywords":"Medicine; Randomized controlled trial; Population; Rheumatoid arthritis; Meta-analysis; Internal medicine; Intention-to-treat analysis; Sample size determination; Physical therapy; Imputation (statistics); Study heterogeneity; Missing data; Statistics","score_opus":0.6572351615281036,"score_gpt":0.44747438123377986,"score_spread":0.2097607802943237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974429147","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":[0.9457786,0.0005577875,0.04773262,0.0009078414,0.000040020634,0.004547081,0.000058239202,0.0001901363,0.00018766335],"genre_scores_gemma":[0.99482375,0.000497969,0.0024047112,0.0001434373,0.0000103230095,0.0020306432,0.0000133119365,0.000037550988,0.000038294053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99232614,0.0042371014,0.0019797503,0.00047047794,0.0005766143,0.00040990443],"domain_scores_gemma":[0.9866925,0.010833746,0.0011123366,0.000990726,0.00017682964,0.0001938524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050612288,0.0005110107,0.0031926022,0.00022062649,0.00010218041,0.000051840783,0.00055886805,0.000094773,0.00009092163],"category_scores_gemma":[0.033633053,0.00024221106,0.00085681217,0.00035311352,0.00018752142,0.0001815049,0.0001820125,0.0001852763,0.0000045936545],"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":[0.049207836,0.066729434,0.09167966,0.006591593,0.020461792,0.00004156403,0.012112012,0.0061140787,0.0004670206,0.4710855,0.016228653,0.25928086],"study_design_scores_gemma":[0.015849346,0.0015384281,0.023208547,0.003472989,0.0012486029,0.000008746874,0.001630544,0.002030072,0.0023899353,0.94789886,0.000008056888,0.00071586703],"about_ca_topic_score_codex":0.00009714511,"about_ca_topic_score_gemma":0.00010068565,"teacher_disagreement_score":0.47681338,"about_ca_system_score_codex":0.000032299024,"about_ca_system_score_gemma":0.000031430467,"threshold_uncertainty_score":0.98770803},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad","metaepi_narrow"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W1974723978","doi":"10.1002/sim.6378","title":"A cautionary note concerning the use of stabilized weights in marginal structural models","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"Concordia University; Hôpital du Sacré-Cœur de Montréal; Université Laval; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal structural model; Inverse probability; Econometrics; Confounding; Inverse; Statistics; Computer science; Mathematics; Posterior probability; Bayesian probability","score_opus":0.20423091439008736,"score_gpt":0.4260492700041732,"score_spread":0.22181835561408583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974723978","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":[0.10385992,0.000046937497,0.8948511,0.00027828617,0.000093265066,0.00036102254,0.00007746665,0.000043319684,0.00038866815],"genre_scores_gemma":[0.59827,0.00003269379,0.40149266,0.000075667,0.000036274458,0.000017960376,0.000019274712,0.000013903797,0.000041593474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984923,0.00021352647,0.0005659062,0.00017087178,0.0003462136,0.00021120875],"domain_scores_gemma":[0.9953154,0.0039967424,0.00021457257,0.0003082999,0.00012777327,0.000037257058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064240134,0.00014599388,0.00039342104,0.0001226268,0.00003439392,0.000004792307,0.00017295625,0.00006170406,0.00010886332],"category_scores_gemma":[0.0030454237,0.00009376363,0.000014066216,0.00018246098,0.0004531082,0.00011947905,0.000056336794,0.0003387396,6.0375675e-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":[0.0000653055,0.000016143564,0.0010582542,0.00009689721,0.0000057621287,0.000013693237,0.00277434,0.0010962851,0.0004450674,0.9903152,0.0004965016,0.0036165584],"study_design_scores_gemma":[0.0005930746,0.00010624364,0.0012088021,0.00023364933,0.000014590894,0.0000049997825,0.000096004514,0.19642927,0.00011893976,0.8008568,0.00025236545,0.00008523998],"about_ca_topic_score_codex":0.00031506215,"about_ca_topic_score_gemma":0.00039592234,"teacher_disagreement_score":0.49441007,"about_ca_system_score_codex":0.00010646278,"about_ca_system_score_gemma":0.000046732068,"threshold_uncertainty_score":0.382357},"labels":[],"label_agreement":null},{"id":"W1975001673","doi":"10.1016/j.scitotenv.2012.01.006","title":"Response to Letter to the editor from Guzzi, Ronchi, Pigatto and Monoia","year":2012,"lang":"en","type":"article","venue":"The Science of The Total Environment","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":"SNC-Lavalin (Canada)","funders":"","keywords":"Art","score_opus":0.040051548860422614,"score_gpt":0.3073556102019574,"score_spread":0.2673040613415348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975001673","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":[0.9766579,0.00003844865,0.003468551,0.018385245,0.0005914155,0.0006188675,0.000016980324,0.000028007964,0.00019455575],"genre_scores_gemma":[0.98200953,0.0000036920203,0.01567689,0.00071627594,0.0007168016,0.00006393476,1.1467701e-7,0.0000142383815,0.00079851225],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984351,0.00015255492,0.00019964241,0.00021909345,0.00062834757,0.00036527432],"domain_scores_gemma":[0.99819326,0.000468878,0.00010126906,0.0010885642,0.000009458666,0.00013854943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020577288,0.00014566742,0.00013663733,0.00003273812,0.00029315474,0.00003210947,0.0009608281,0.000033315428,0.00006829506],"category_scores_gemma":[0.00046734992,0.00006671298,0.000043856497,0.00016384131,0.0007565971,0.0001657192,0.0011497453,0.00016046525,0.00008673439],"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":[0.000212824,0.00013941868,0.00007525282,0.0000049394966,0.000018674293,3.4977393e-7,0.009743803,0.0017386233,0.9461569,0.0034116402,0.034810483,0.0036870816],"study_design_scores_gemma":[0.00032254224,0.0004817097,0.04952036,0.00013697123,0.000105213665,0.0000134302645,0.0014241653,0.00047998337,0.8270293,0.07928112,0.040517487,0.0006877572],"about_ca_topic_score_codex":0.000035032357,"about_ca_topic_score_gemma":0.000001157592,"teacher_disagreement_score":0.119127646,"about_ca_system_score_codex":0.00013684864,"about_ca_system_score_gemma":0.000017740329,"threshold_uncertainty_score":0.27877134},"labels":[],"label_agreement":null},{"id":"W1975477455","doi":"10.1097/ede.0b013e3181a48c33","title":"Improving Multilevel Analyses","year":2009,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":"University of Alberta; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Multilevel model; Estimation; Computer science; Variation (astronomy); Hierarchical database model; Statistics; Risk analysis (engineering); Econometrics; Data mining; Medicine; Mathematics; Engineering; Systems engineering","score_opus":0.619359881176276,"score_gpt":0.5811842964023198,"score_spread":0.03817558477395622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975477455","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":[0.022581132,0.00017239513,0.9710403,0.0014355859,0.00006849192,0.00015639223,0.0000031203083,0.00064781745,0.0038947617],"genre_scores_gemma":[0.5230754,0.00001615181,0.47467297,0.0018662146,0.00009548593,0.000011500435,0.0000030733345,0.000009755897,0.00024941415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99855787,0.00027033512,0.00048129432,0.0002684373,0.000049140075,0.00037289909],"domain_scores_gemma":[0.9954107,0.0038321624,0.00024252897,0.00038663374,0.00005464512,0.000073343894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001072135,0.00015042517,0.0004917273,0.00008428694,0.000053762084,0.0000028190652,0.00019137199,0.00015192521,0.000098266464],"category_scores_gemma":[0.018655343,0.000121203986,0.00009266542,0.000080947415,0.00007033737,0.00009789213,0.000037894373,0.00021887444,0.000033315173],"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":[0.00001643461,0.00008464327,0.0012620741,0.000018499799,0.000023455586,0.000012263978,0.000093087394,0.000031382016,0.033588387,0.7923111,0.0111698,0.16138889],"study_design_scores_gemma":[0.00008758261,0.000118158525,0.0029912917,0.000012209241,0.000015516576,0.000011754634,0.000013925342,0.0024536182,0.0059736217,0.98762023,0.00056025106,0.00014183503],"about_ca_topic_score_codex":0.00003463081,"about_ca_topic_score_gemma":0.000005800192,"teacher_disagreement_score":0.5004943,"about_ca_system_score_codex":0.000046872232,"about_ca_system_score_gemma":0.000017556285,"threshold_uncertainty_score":0.9896109},"labels":[],"label_agreement":null},{"id":"W1975579902","doi":"10.1016/s0840-4704(10)60455-3","title":"Commentary on the Feature Article","year":2009,"lang":"en","type":"letter","venue":"Healthcare Management Forum","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":"Centre hospitalier universitaire de Québec","funders":"","keywords":"Feature (linguistics); Computer science; Philosophy; Linguistics","score_opus":0.09739661024137902,"score_gpt":0.38588553148050425,"score_spread":0.28848892123912523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975579902","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":[0.000018549135,0.000109125416,0.001419156,0.98204535,0.00022440556,0.0019498918,0.00004443413,0.0006543723,0.01353472],"genre_scores_gemma":[0.0006675411,0.00017139902,0.007390934,0.98368186,0.0008926546,0.0002962542,0.0001435998,0.00008977029,0.006665981],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973754,0.00024253261,0.0003703523,0.00049202883,0.00064722257,0.00087244075],"domain_scores_gemma":[0.9977527,0.00042391493,0.00027018558,0.0014335593,0.000057411184,0.00006221871],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00034763195,0.0004634629,0.0004048622,0.00015401184,0.00030004347,0.00007374897,0.00068381144,0.00048423008,0.00011868743],"category_scores_gemma":[0.00003794086,0.00032269832,0.00016169694,0.0002163633,0.00006726969,0.00007342587,0.00024641078,0.002506451,0.00010709622],"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":[0.000008854056,0.000034056688,0.000010551213,0.00035860846,0.0000490589,0.00021891766,0.00003284517,2.1836406e-7,3.211533e-7,0.108900756,0.8802769,0.0101089],"study_design_scores_gemma":[0.000073596355,0.00014562733,0.000010953465,0.00031417288,0.000031803076,0.0000026931862,0.000121193196,0.000007441375,0.000042258704,0.3621583,0.63688284,0.00020915181],"about_ca_topic_score_codex":0.000032940305,"about_ca_topic_score_gemma":0.000052661067,"teacher_disagreement_score":0.25325754,"about_ca_system_score_codex":0.00034656748,"about_ca_system_score_gemma":0.000012081538,"threshold_uncertainty_score":0.9999225},"labels":[],"label_agreement":null},{"id":"W1975994236","doi":"10.1002/sim.3854","title":"The performance of different propensity-score methods for estimating differences in proportions (risk differences or absolute risk reductions) in observational studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":359,"is_retracted":false,"has_abstract":true,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Confidence interval; Observational study; Estimator; Mean squared error; Relative risk; Matching (statistics); Inverse probability weighting; Mathematics; Econometrics; Medicine","score_opus":0.4011751616883879,"score_gpt":0.5200551633034011,"score_spread":0.11888000161501316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975994236","genre_codex":"empirical","genre_gemma":"methods","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":[0.7761584,0.00008380621,0.22167489,0.0002329681,0.00041971044,0.0011631511,0.00020838242,0.000039622766,0.00001906395],"genre_scores_gemma":[0.3462323,0.0007670073,0.6521072,0.0000068481663,0.000077587334,0.0006567338,0.000025792353,0.00001655622,0.000109972985],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973568,0.000315674,0.001313239,0.00032743596,0.00033757035,0.00034933563],"domain_scores_gemma":[0.98524135,0.013075667,0.00088028074,0.00036208294,0.00039397398,0.00004661301],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026317376,0.00026430312,0.0008062118,0.00023533778,0.00024419138,0.00001417905,0.00032534127,0.00009620264,0.000055214932],"category_scores_gemma":[0.037921865,0.000143284,0.000027221642,0.00043208522,0.0009272676,0.0001196024,0.000102319624,0.0008582094,2.4971754e-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":[0.000309543,0.00046249456,0.7223801,0.0010471061,0.00011272729,0.0000066679922,0.0060770917,0.000057809404,0.0014079055,0.14728266,0.0012090448,0.119646825],"study_design_scores_gemma":[0.0005530612,0.0005105432,0.34951308,0.00087388314,0.000063270716,0.0000040796626,0.0011967294,0.04699414,0.0003690312,0.5997149,0.000019430769,0.00018784823],"about_ca_topic_score_codex":0.00013644459,"about_ca_topic_score_gemma":0.007370234,"teacher_disagreement_score":0.45243225,"about_ca_system_score_codex":0.00009533988,"about_ca_system_score_gemma":0.000121492856,"threshold_uncertainty_score":0.9701821},"labels":[],"label_agreement":null},{"id":"W1976017085","doi":"10.2165/00002018-200225090-00006","title":"Adverse Effects of Observational Studies When Examining Adverse Outcomes of Drugs","year":2002,"lang":"en","type":"article","venue":"Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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 Toronto; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Medicine; Observational study; Adverse effect; Intensive care medicine; Pharmacology; Internal medicine","score_opus":0.2316084619514706,"score_gpt":0.3963446661703264,"score_spread":0.16473620421885576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976017085","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":[0.9838911,0.00046505174,0.0071629346,0.00037048975,0.00026240258,0.0008313405,0.000049526498,0.0003839612,0.0065831565],"genre_scores_gemma":[0.9069564,0.00016475144,0.091092974,0.00009886463,0.000023407692,0.000038039823,0.000005469258,0.000027845934,0.001592248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984841,0.000098737895,0.000641785,0.0002027079,0.0003712718,0.00020140891],"domain_scores_gemma":[0.99530023,0.0035646942,0.00044762625,0.0004023513,0.00024241926,0.00004267802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040088056,0.00020436643,0.0006186739,0.00009674522,0.000051381452,0.0000012954148,0.00021037528,0.000064144326,0.00013439196],"category_scores_gemma":[0.002170933,0.00017623545,0.00011673402,0.00014906043,0.00017743946,0.00024974206,0.00014327296,0.00013168814,0.00001073486],"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":[0.00018737915,0.0017692877,0.18323527,0.0065772748,0.0020993701,0.00005432541,0.14887711,0.0002198428,0.008973123,0.60189646,0.020914271,0.025196258],"study_design_scores_gemma":[0.0040643243,0.00041312317,0.11930093,0.002248926,0.00059058017,0.000005379653,0.0145686045,0.0008466305,0.10152713,0.75248706,0.0026242444,0.0013230523],"about_ca_topic_score_codex":0.0000091495585,"about_ca_topic_score_gemma":0.000007883426,"teacher_disagreement_score":0.15059058,"about_ca_system_score_codex":0.00008260844,"about_ca_system_score_gemma":0.000016046086,"threshold_uncertainty_score":0.7186673},"labels":[],"label_agreement":null},{"id":"W1976472169","doi":"10.1177/0020715204048308","title":"Comparing Social Groups: Wald Statistics for Testing Equality Among Multiple Logit Models","year":2004,"lang":"en","type":"article","venue":"International Journal of Comparative Sociology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Wald test; Statistic; Statistics; Econometrics; Likelihood-ratio test; Test statistic; Score test; Logistic regression; Logit; Mathematics; Test (biology); Statistical hypothesis testing","score_opus":0.5330289314502004,"score_gpt":0.5120957602004778,"score_spread":0.020933171249722604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976472169","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":[0.39822724,0.00001766992,0.60078907,0.00016196205,0.0002212001,0.00013806464,0.000048187154,0.000037101803,0.00035947948],"genre_scores_gemma":[0.7351792,0.0000027516821,0.26433226,0.00008309353,0.0003479244,0.000016946185,0.000014030305,0.0000132280675,0.000010552399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998189,0.00015963792,0.0009022431,0.00016394339,0.00033307273,0.0002521423],"domain_scores_gemma":[0.99367946,0.002998065,0.0012073244,0.000080321595,0.0019722749,0.000062554165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007118963,0.0001924175,0.0006152058,0.0001264482,0.00013672154,0.000034277902,0.0005047453,0.000134069,0.000011535681],"category_scores_gemma":[0.0011498594,0.00017605608,0.00014737583,0.000051844392,0.00048774257,0.0004025226,0.00009981194,0.000441023,0.0000022961924],"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":[0.00033400225,0.00028843302,0.007039582,0.000023971497,0.00041917234,0.000018610737,0.008183321,0.010401621,0.0020258455,0.9699866,0.0010039817,0.000274839],"study_design_scores_gemma":[0.001425946,0.00022834932,0.0031702311,0.00006303497,0.00003472183,0.00002883291,0.00095433975,0.007880707,0.0016216579,0.98437303,0.000047072757,0.00017205872],"about_ca_topic_score_codex":0.00001935249,"about_ca_topic_score_gemma":0.000060388884,"teacher_disagreement_score":0.33695197,"about_ca_system_score_codex":0.0004387453,"about_ca_system_score_gemma":0.00013944879,"threshold_uncertainty_score":0.71793586},"labels":[],"label_agreement":null},{"id":"W1977200598","doi":"10.6000/1929-6029.2012.01.02.01","title":"Estimating the Complier Average Causal Effect for Exponential Survival in the Presence of Mid-Trial Switching","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics 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":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Counterfactual thinking; Estimator; Econometrics; Treatment effect; Delta method; Aggregate (composite); Statistics; Economics; Computer science; Mathematics; Psychology; Medicine; Social psychology","score_opus":0.25044803211524236,"score_gpt":0.5602161870279413,"score_spread":0.30976815491269893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977200598","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":[0.2816783,0.000041238327,0.7158339,0.00071498303,0.0010079767,0.000507746,0.00003001749,0.000003978082,0.00018187614],"genre_scores_gemma":[0.92722213,0.000024919364,0.07177229,0.000028494265,0.00087994465,0.000047271737,0.0000038071128,0.000013359583,0.000007755181],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99336,0.0012859355,0.000987875,0.000106114414,0.0038664867,0.0003936057],"domain_scores_gemma":[0.95290136,0.045719188,0.0003692172,0.00017045654,0.0007423012,0.000097474134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02537024,0.00010784293,0.00030043157,0.00027095838,0.00007023222,0.00005374509,0.0013941964,0.00009145944,0.000098713936],"category_scores_gemma":[0.07214343,0.00006170535,0.00006492004,0.00019036351,0.00028902144,0.00018402272,0.00021648643,0.0014048895,0.0000012327754],"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":[0.017578559,0.0023289064,0.012355518,0.00050617533,0.00033650594,0.00064967683,0.0137537075,0.0006880406,0.0038181474,0.8174998,0.006759259,0.12372572],"study_design_scores_gemma":[0.014156875,0.0013122527,0.0028487905,0.0014465152,0.000029631314,0.00018088758,0.00088569365,0.040276475,0.0024057669,0.93583834,0.00041340094,0.0002053905],"about_ca_topic_score_codex":0.00008465099,"about_ca_topic_score_gemma":0.00007813072,"teacher_disagreement_score":0.6455439,"about_ca_system_score_codex":0.00015959494,"about_ca_system_score_gemma":0.00022802816,"threshold_uncertainty_score":0.9356723},"labels":[],"label_agreement":null},{"id":"W1977271642","doi":"10.1503/cmaj.1060113","title":"Not-so-surprising findings","year":2006,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Randomized controlled trial; Computer science; Data science; Medicine; Pathology","score_opus":0.05183931871537081,"score_gpt":0.3413053131063495,"score_spread":0.2894659943909787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977271642","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":[0.77931607,0.00018471232,0.06888917,0.057223685,0.0018388003,0.0004434841,0.00005955051,0.00060311746,0.09144142],"genre_scores_gemma":[0.9706462,0.000037200007,0.017320307,0.007620426,0.002141577,0.000008065151,0.0000070355886,0.000044409462,0.002174753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762344,0.00010284326,0.00047508496,0.00012332278,0.0011616272,0.00051367027],"domain_scores_gemma":[0.99816847,0.0004917219,0.00021757078,0.000100917074,0.00030499315,0.0007163433],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019198646,0.000120463126,0.00020718544,0.00017725934,0.00035098265,0.00015961514,0.00023180789,0.00037046178,0.0022255532],"category_scores_gemma":[0.0045181806,0.00011603638,0.0000831009,0.00019483856,0.000041780353,0.0001996942,0.0000150992255,0.000912647,0.00009813695],"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":[0.0000054441434,0.00004887244,0.02366271,0.000015617341,0.00006178077,0.0007012193,0.00030526335,0.0000033168685,0.00038682384,0.17769998,0.7701038,0.027005158],"study_design_scores_gemma":[0.0005769348,0.000046113215,0.008108619,0.00017258449,0.000031931566,0.0005070387,0.00017556822,0.00013418199,0.0015755487,0.37572205,0.6125437,0.00040570347],"about_ca_topic_score_codex":0.003465341,"about_ca_topic_score_gemma":0.031071983,"teacher_disagreement_score":0.19802208,"about_ca_system_score_codex":0.0015306104,"about_ca_system_score_gemma":0.0013406195,"threshold_uncertainty_score":0.99868655},"labels":[],"label_agreement":null},{"id":"W1977538915","doi":"10.7326/0003-4819-159-8-201310150-00018","title":"Statin Toxicity From Macrolide Antibiotic Coprescription","year":2013,"lang":"en","type":"letter","venue":"Annals of Internal Medicine","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Antibiotics; Confounding; Macrolide Antibiotics; Population; Family medicine; Internal medicine; Erythromycin; Environmental health","score_opus":0.198259883138723,"score_gpt":0.4345395120581955,"score_spread":0.23627962891947252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977538915","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":[0.09792529,0.0013783121,0.05613806,0.82168573,0.0017811317,0.0015095727,0.0006770173,0.000686806,0.018218085],"genre_scores_gemma":[0.05053145,0.0009524841,0.03150837,0.9012092,0.007224075,0.00004192076,0.00042596227,0.00022225917,0.007884283],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970621,0.00017383324,0.00112618,0.000435053,0.000767229,0.00043560233],"domain_scores_gemma":[0.99622977,0.0012286421,0.0011315353,0.00072190736,0.0005929155,0.00009520491],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037753757,0.00047364156,0.0011711853,0.00026746403,0.000024956846,0.00001840379,0.0006818177,0.000593617,0.0019034743],"category_scores_gemma":[0.0020919256,0.00036051864,0.00015802086,0.00010586637,0.00035908175,0.00018738779,0.00014963152,0.0016307703,0.000079447454],"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":[0.000031474752,0.000036392048,0.000079190104,0.0003183069,0.00015617006,0.00014616792,0.00021155167,1.1934709e-7,0.012077115,0.00068765355,0.983897,0.0023589018],"study_design_scores_gemma":[0.00042535315,0.0010479133,0.00019787875,0.008345125,0.00014580537,0.000026332831,0.00009080078,0.000050285395,0.19055294,0.67276293,0.12582831,0.00052633847],"about_ca_topic_score_codex":0.0025621746,"about_ca_topic_score_gemma":0.000025404262,"teacher_disagreement_score":0.85806865,"about_ca_system_score_codex":0.00004785535,"about_ca_system_score_gemma":0.000032408603,"threshold_uncertainty_score":0.99988467},"labels":[],"label_agreement":null},{"id":"W1980091283","doi":"10.1097/ede.0b013e31815c4d0e","title":"Estimating Interaction Between Genetic and Environmental Risk Factors","year":2008,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Université Laval","funders":"National Heart, Lung, and Blood Institute","keywords":"Cohort; Nested case-control study; Framingham Heart Study; Statistics; Cohort study; Environmental health; Demography; Medicine; Econometrics; Framingham Risk Score; Disease; Internal medicine; Mathematics","score_opus":0.26043985756527305,"score_gpt":0.4336198720691994,"score_spread":0.17318001450392634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980091283","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":[0.7307888,0.00004562516,0.26878402,0.00003629306,0.00004816047,0.0000868776,0.00001054436,0.000113294416,0.00008634743],"genre_scores_gemma":[0.7103625,0.00007655645,0.289393,0.000034382316,0.00007883094,0.00000903427,0.000010628951,0.00001206903,0.000023022372],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880725,0.00033704558,0.00038082368,0.00022188759,0.000040367373,0.00021260948],"domain_scores_gemma":[0.994209,0.005267831,0.00027570294,0.00017789473,0.000004545452,0.000065021166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038252896,0.00013235793,0.00034865914,0.000047363214,0.00012137762,0.0000013851212,0.000069177666,0.00011469282,0.000058551774],"category_scores_gemma":[0.0038882142,0.00011336029,0.000037903785,0.000024121018,0.00018456545,0.00008497406,0.00006885856,0.00025653292,0.000011262269],"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":[0.0000023902087,0.00001299506,0.99319315,0.000007217624,0.000019275032,0.0000030644956,0.00031370323,0.00006898693,0.00021011951,0.0007308971,0.00038951862,0.0050486773],"study_design_scores_gemma":[0.000117231546,0.00016463603,0.46684724,0.000018440962,0.00003766755,0.00007765936,0.00012576817,0.0051498124,0.0010717554,0.52590257,0.00027187917,0.00021535734],"about_ca_topic_score_codex":0.000063679,"about_ca_topic_score_gemma":0.0000024800147,"teacher_disagreement_score":0.5263459,"about_ca_system_score_codex":0.000055390818,"about_ca_system_score_gemma":0.000004542247,"threshold_uncertainty_score":0.46548364},"labels":[],"label_agreement":null},{"id":"W1980199310","doi":"10.2202/1557-4679.1400","title":"Special Issue on Causal Inference in Health Research","year":2012,"lang":"en","type":"editorial","venue":"The International Journal of Biostatistics","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Causal inference; Biostatistics; Inference; Library science; Data science; Computer science; Econometrics; Mathematics; Public health; Medicine; Artificial intelligence","score_opus":0.26051950652904116,"score_gpt":0.5478536902653409,"score_spread":0.28733418373629976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980199310","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":[0.000065926826,0.00016811136,0.011320143,0.0035653017,0.9794168,0.00043633903,0.000953701,0.00003309993,0.004040619],"genre_scores_gemma":[0.0011158028,0.0014629719,0.018848402,0.00014376009,0.97729474,0.000008509545,0.000057647485,0.000063131105,0.0010050568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931746,0.0006625053,0.0015125666,0.0002028297,0.0039297775,0.00051769643],"domain_scores_gemma":[0.97068435,0.024416545,0.0016408927,0.00036850927,0.0027324825,0.00015721963],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006832744,0.00030004734,0.0006192147,0.0007415628,0.000090454865,0.00014206028,0.0019301138,0.0003700094,0.00040765907],"category_scores_gemma":[0.039248466,0.00021444878,0.00009549125,0.00023322937,0.00028918093,0.00016523334,0.00029704435,0.0038035284,0.00007577533],"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":[0.00021690247,0.0001962493,0.000010222497,0.000054915123,0.00007250819,0.00010550283,0.00063725724,0.00001052883,0.0000082515435,0.054233015,0.9326647,0.011789926],"study_design_scores_gemma":[0.00029899736,0.0004599616,0.0000147002365,0.00097607024,0.0000118690405,0.000013891492,0.00013003236,0.000011817873,0.000104104096,0.24252053,0.7553101,0.00014791758],"about_ca_topic_score_codex":0.00014115598,"about_ca_topic_score_gemma":0.00027873012,"teacher_disagreement_score":0.1882875,"about_ca_system_score_codex":0.0014860949,"about_ca_system_score_gemma":0.0014605499,"threshold_uncertainty_score":0.99849474},"labels":[],"label_agreement":null},{"id":"W1980722267","doi":"10.1016/j.jclinepi.2008.11.004","title":"Absolute risk reductions, relative risks, relative risk reductions, and numbers needed to treat can be obtained from a logistic regression model","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":193,"is_retracted":false,"has_abstract":false,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Logistic regression; Relative risk; Confounding; Medicine; Absolute risk reduction; Cohort; Statistics; Odds ratio; Population; Cohort study; Regression analysis; Number needed to treat; Covariate; Confidence interval; Demography; Internal medicine; Mathematics; Environmental health","score_opus":0.5899278137115219,"score_gpt":0.5881755421570074,"score_spread":0.0017522715545145173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980722267","genre_codex":"empirical","genre_gemma":"methods","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":[0.49755216,0.00054482353,0.4734118,0.026601167,0.00045498397,0.00055304146,0.00016090351,0.00014302622,0.0005780847],"genre_scores_gemma":[0.40559888,0.0063728536,0.58574885,0.0011579887,0.0006011412,0.000015564268,0.000010378103,0.000035726956,0.000458599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878893,0.0059084618,0.0047725723,0.00064035767,0.00027097168,0.0005183479],"domain_scores_gemma":[0.95141035,0.040169377,0.006589465,0.0006308849,0.00053759094,0.00066234317],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011513628,0.00043368753,0.0028144093,0.00027646788,0.00030697478,0.000014749323,0.00033677666,0.0008213981,0.000036516107],"category_scores_gemma":[0.24857713,0.00031668277,0.00056934415,0.0003052685,0.0006090935,0.0004546368,0.00010059395,0.003069641,0.0000063170028],"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":[0.011300182,0.00280428,0.044904176,0.000075101685,0.0026942303,0.00024876374,0.00845053,0.03937725,0.000907167,0.3965517,0.33565176,0.15703486],"study_design_scores_gemma":[0.0010703712,0.0015963903,0.009799481,0.00029257397,0.00074270583,0.00009041101,0.00061944826,0.006554402,0.000056397195,0.9784461,0.00042861214,0.00030310373],"about_ca_topic_score_codex":0.00093859504,"about_ca_topic_score_gemma":0.00008777257,"teacher_disagreement_score":0.5818944,"about_ca_system_score_codex":0.00026847006,"about_ca_system_score_gemma":0.0002477139,"threshold_uncertainty_score":0.99992853},"labels":[],"label_agreement":null},{"id":"W1981158530","doi":"10.1002/cjs.11162","title":"Q‐learning for estimating optimal dynamic treatment rules from observational data","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Mailman School of Public Health, Columbia University; National Institutes of Health","keywords":"Observational study; Covariate; Randomized experiment; Propensity score matching; Causal inference; Randomized controlled trial; Computer science; Analysis of covariance; Machine learning; Inference; Econometrics; Vocabulary; Statistics; Set (abstract data type); Artificial intelligence; Medicine; Mathematics","score_opus":0.3868564774755924,"score_gpt":0.4250497342740967,"score_spread":0.03819325679850433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981158530","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":[0.034203522,0.00016311099,0.961759,0.00008397058,0.00026413254,0.00013358603,0.00333325,0.000016848,0.00004258737],"genre_scores_gemma":[0.1119761,0.0000112485295,0.88707215,0.000026401573,0.0002588198,0.0000054486195,0.0005491818,0.000029408482,0.00007122002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989473,0.000037996215,0.00044599522,0.00009976014,0.00013888757,0.0003300212],"domain_scores_gemma":[0.9971786,0.001513743,0.00043461967,0.0002206976,0.0002559044,0.00039642624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003502975,0.00013905078,0.00025463715,0.00009731432,0.00015798249,0.00005092651,0.0002844944,0.000057487527,0.00011415167],"category_scores_gemma":[0.0030981984,0.00012812625,0.000032266853,0.000044360702,0.00005921393,0.00039672072,0.000020113428,0.00016307662,0.0000039467577],"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":[0.000114411705,0.00031735087,0.041554064,0.000286085,0.0010255007,0.0002396723,0.008383714,0.006907481,0.00083356386,0.45566562,0.05155256,0.43311998],"study_design_scores_gemma":[0.0010968444,0.0008511296,0.0072451434,0.00035957058,0.0005252986,0.00012865687,0.0010056738,0.3361853,0.00022519534,0.6318231,0.019925416,0.00062861067],"about_ca_topic_score_codex":0.00069790374,"about_ca_topic_score_gemma":0.0027128106,"teacher_disagreement_score":0.43249136,"about_ca_system_score_codex":0.0004049471,"about_ca_system_score_gemma":0.0006872784,"threshold_uncertainty_score":0.52248365},"labels":[],"label_agreement":null},{"id":"W1981620646","doi":"10.6000/1929-6029.2013.02.02.04","title":"Comparison of Post Hoc Multiple Pairwise Testing Procedures as Applied to Small k-Group Logrank Tests","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health","keywords":"Bonferroni correction; Multiple comparisons problem; Pairwise comparison; Post-hoc analysis; Post hoc; False discovery rate; Statistics; Type I and type II errors; Log-rank test; Statistical hypothesis testing; Mathematics; Censoring (clinical trials); Computer science; Medicine; Survival analysis; Internal medicine; Biology","score_opus":0.302127508600054,"score_gpt":0.5532020893034955,"score_spread":0.25107458070344146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981620646","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":[0.6837605,0.00008723429,0.31109124,0.0018063732,0.00021156968,0.00082164246,0.00006144291,0.00004106137,0.0021188965],"genre_scores_gemma":[0.6742347,0.000032645934,0.32543772,0.00010139653,0.00010919305,0.000036145168,0.000005319106,0.00001844731,0.000024452604],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947179,0.00018219139,0.0012491065,0.00018580255,0.003285155,0.0003798375],"domain_scores_gemma":[0.9789871,0.015327355,0.00043929735,0.00016973996,0.0046855174,0.00039099288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030985265,0.0001433192,0.00042284114,0.0007149187,0.000042308493,0.00006413292,0.0011475161,0.00013631613,0.00045159046],"category_scores_gemma":[0.1321234,0.000119495526,0.000039666666,0.00039376598,0.00032555297,0.00010762683,0.00032070294,0.0011845273,0.00003247967],"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":[0.0011296199,0.003520447,0.07318009,0.00061478245,0.00022544345,0.00079934247,0.0033249275,0.00015609806,0.046671506,0.26686314,0.023738885,0.5797757],"study_design_scores_gemma":[0.0017211934,0.0024190508,0.024062216,0.0023583823,0.000013604007,0.00013791697,0.0018035689,0.005485539,0.0063032107,0.9549161,0.00048380697,0.00029541663],"about_ca_topic_score_codex":0.00025136134,"about_ca_topic_score_gemma":0.00052320765,"teacher_disagreement_score":0.68805295,"about_ca_system_score_codex":0.00024127317,"about_ca_system_score_gemma":0.00056816975,"threshold_uncertainty_score":0.8751871},"labels":[],"label_agreement":null},{"id":"W1981772720","doi":"10.2202/1557-4679.1285","title":"A Tutorial on Methods to Estimating Clinically and Policy-Meaningful Measures of Treatment Effects in Prospective Observational Studies: A Review","year":2011,"lang":"en","type":"review","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":98,"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","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":"Observational study; Covariate; Number needed to treat; Propensity score matching; Medicine; Randomized controlled trial; Average treatment effect; Absolute risk reduction; Relative risk; Regression toward the mean; Treatment effect; Statistics; Confidence interval; Econometrics; Mathematics; Internal medicine","score_opus":0.6067013277402696,"score_gpt":0.62685556926826,"score_spread":0.02015424152799039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981772720","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":[0.000007792983,0.8636306,0.1331329,0.00027013422,0.00097433967,0.0016438263,0.00015326403,0.000018907613,0.00016822612],"genre_scores_gemma":[0.0000066142243,0.558949,0.44046506,0.00012097997,0.00036756953,0.000052450265,0.0000029169444,0.00002201654,0.000013394512],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963072,0.00066709204,0.0021342242,0.00021021809,0.00052414817,0.00015710287],"domain_scores_gemma":[0.9805916,0.015091253,0.00274928,0.00023312331,0.0012606645,0.00007408856],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030242512,0.00035810974,0.0019817736,0.00035346652,0.00003066106,0.00002245351,0.000590878,0.0001064046,0.000005899132],"category_scores_gemma":[0.04849284,0.00020865949,0.00024767275,0.00024793117,0.00013119452,0.00006578911,0.00016310504,0.00041629135,0.0000014607391],"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":[0.00009761901,0.00014454205,0.000007794778,0.0049092053,0.00094691094,0.000028612798,0.00085157447,0.00000356658,0.0000022970623,0.16715106,0.0005716042,0.8252852],"study_design_scores_gemma":[0.0007071448,0.0034910461,0.000026673897,0.16487041,0.0016115977,0.00023359434,0.0000562695,0.000033626093,0.000045991197,0.7509033,0.07763145,0.00038890037],"about_ca_topic_score_codex":0.000020511286,"about_ca_topic_score_gemma":0.000010036999,"teacher_disagreement_score":0.82489634,"about_ca_system_score_codex":0.0010518503,"about_ca_system_score_gemma":0.00075137574,"threshold_uncertainty_score":0.9595221},"labels":[],"label_agreement":null},{"id":"W1982364633","doi":"10.1016/j.jspi.2009.03.024","title":"Analytic bounds on causal risk differences in directed acyclic graphs involving three observed binary variables","year":2009,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"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","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Mathematics; Directed acyclic graph; Combinatorics; Covariate; Monotonic function; Binary number; Upper and lower bounds; Measure (data warehouse); Discrete mathematics; Statistics","score_opus":0.1552871777379599,"score_gpt":0.3901827679038079,"score_spread":0.234895590165848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982364633","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":[0.8601053,0.00033580873,0.13879348,0.00008333677,0.000073798765,0.00011007306,0.000032655575,0.00009682713,0.00036877563],"genre_scores_gemma":[0.9367703,0.00027068643,0.062815994,0.00007120029,0.000040542676,0.0000029316413,0.000004258922,0.000013090378,0.000010986951],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99783087,0.00019465269,0.0009017188,0.00025934595,0.00042453417,0.0003888567],"domain_scores_gemma":[0.99427795,0.0045359503,0.0006152708,0.00019391552,0.00017460668,0.00020233195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007984693,0.00028914565,0.00072800874,0.00039292825,0.0001391153,0.0001276881,0.0002587702,0.0001492566,0.000035550613],"category_scores_gemma":[0.006061313,0.00022084043,0.000053271437,0.0003700186,0.00021522389,0.000372745,0.000044009917,0.0009538045,0.0000011307619],"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":[0.0005323136,0.00065924745,0.5120233,0.00012766707,0.00012023858,0.0006771588,0.001083434,0.00017323512,0.0021659634,0.46959302,0.0010123441,0.011832022],"study_design_scores_gemma":[0.00033408692,0.0011227527,0.38196504,0.00077768497,0.000051239847,0.000021263633,0.0000894938,0.0054966537,0.00006807179,0.6098804,0.000004981986,0.00018833298],"about_ca_topic_score_codex":0.000048382553,"about_ca_topic_score_gemma":0.000026026164,"teacher_disagreement_score":0.14028737,"about_ca_system_score_codex":0.000078821344,"about_ca_system_score_gemma":0.000094203046,"threshold_uncertainty_score":0.90056115},"labels":[],"label_agreement":null},{"id":"W1982959065","doi":"10.1002/sim.5795","title":"Propensity scores used for analysis of cluster randomized trials with selection bias: a simulation study","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Western University","funders":"","keywords":"Propensity score matching; CRTS; Inverse probability weighting; Statistics; Selection bias; Weighting; Regression; Causal inference; Selection (genetic algorithm); Type I and type II errors; Matching (statistics); Randomization; Econometrics; Randomized controlled trial; Computer science; Mathematics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.32206622457838024,"score_gpt":0.502459386483331,"score_spread":0.18039316190495075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982959065","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":[0.24543943,0.0000049667333,0.74939615,0.000039694616,0.000019971842,0.0050133835,0.000024853043,0.000040452564,0.000021083775],"genre_scores_gemma":[0.7375147,0.0000037238144,0.2618847,0.000021420796,0.000025262709,0.00046295128,0.000033388016,0.00001379364,0.000040089235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973118,0.0008303371,0.0011545098,0.00020660809,0.00035479656,0.00014195882],"domain_scores_gemma":[0.97643083,0.02185102,0.00078375894,0.00020689814,0.0006932798,0.000034229637],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006009087,0.00015460174,0.0020175464,0.00049592956,0.000031977463,0.00001014026,0.000077987,0.00005071025,0.0001348092],"category_scores_gemma":[0.037013765,0.000090891765,0.00005645108,0.00068995805,0.0001635674,0.00009049121,0.000016768046,0.00010368074,4.4363844e-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":[0.24775867,0.007520863,0.21609351,0.003321195,0.024529135,0.000031372143,0.0584238,0.12714763,0.009944974,0.26418948,0.011902966,0.029136397],"study_design_scores_gemma":[0.1001675,0.0018293341,0.0048639495,0.0002350871,0.0059866435,4.295905e-7,0.0008711296,0.4503499,0.0006976824,0.43477148,0.000003193251,0.00022366417],"about_ca_topic_score_codex":0.00042229035,"about_ca_topic_score_gemma":0.0013163375,"teacher_disagreement_score":0.49207523,"about_ca_system_score_codex":0.000057966186,"about_ca_system_score_gemma":0.000032884775,"threshold_uncertainty_score":0.9710979},"labels":[],"label_agreement":null},{"id":"W1982990880","doi":"10.1037/0012-1649.44.2.407","title":"Effects of kindergarten retention on children's social-emotional development: An application of propensity score method to multivariate, multilevel data.","year":2008,"lang":"en","type":"article","venue":"Developmental Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":110,"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":"Social Sciences and Humanities Research Council of Canada; Spencer Foundation","keywords":"Psychology; Developmental psychology; Multivariate statistics; Multilevel model; Grade retention; Propensity score matching; Child development; Early childhood; Academic achievement; Statistics","score_opus":0.3121952142747555,"score_gpt":0.45775660082990777,"score_spread":0.14556138655515227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982990880","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":[0.49133468,0.000001948416,0.50734043,0.000038000486,0.000042115065,0.00092199957,0.000033405522,0.00009414787,0.00019323463],"genre_scores_gemma":[0.52113235,0.0000012197387,0.47830367,0.00013638701,0.000019521567,0.0000681376,0.00029129046,0.000023396073,0.000024044102],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9978578,0.00021643823,0.00066220097,0.00065689755,0.00034357575,0.00026305192],"domain_scores_gemma":[0.99869394,0.00019547272,0.0004169551,0.00041723743,0.00019150194,0.00008489375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051347434,0.0002499364,0.00045986156,0.00023556991,0.00016245067,0.0000037606694,0.00053363584,0.00020710383,0.000019215311],"category_scores_gemma":[0.00021735468,0.00024491493,0.000037783757,0.00026858793,0.00012535402,0.00022843457,0.00023743817,0.00019315793,0.000019094303],"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":[0.0008909611,0.0056711514,0.032956675,0.00042209102,0.0005052069,0.000023125853,0.0084071,0.000013985155,0.60400504,0.026231432,0.0039209393,0.3169523],"study_design_scores_gemma":[0.00084730954,0.00016095687,0.8056326,0.00007298517,0.000015707003,0.00004991736,0.000015310543,0.000043357486,0.18476194,0.008020274,0.00010689637,0.00027277274],"about_ca_topic_score_codex":0.000027378439,"about_ca_topic_score_gemma":0.000011397296,"teacher_disagreement_score":0.77267593,"about_ca_system_score_codex":0.00010672119,"about_ca_system_score_gemma":0.000106317726,"threshold_uncertainty_score":0.9987342},"labels":[],"label_agreement":null},{"id":"W1984304455","doi":"10.1007/s00038-012-0357-x","title":"Context by treatment interactions as the primary object of study in cluster randomized controlled trials of population health interventions","year":2012,"lang":"en","type":"article","venue":"International Journal of Public Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"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 de Montréal","funders":"","keywords":"Randomized controlled trial; Context (archaeology); Psychological intervention; Intervention (counseling); Population; Cluster randomised controlled trial; Randomization; Population health; Public health; Medicine; Psychology; Nursing; Environmental health; Geography","score_opus":0.32418478063056677,"score_gpt":0.5514621425283893,"score_spread":0.22727736189782255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984304455","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":[0.8170131,0.004327894,0.12303356,0.044217154,0.0018881606,0.0087737525,0.0001292886,0.00004888127,0.000568211],"genre_scores_gemma":[0.99574023,0.00046507953,0.0027840608,0.00054791325,0.00014761095,0.00014899063,0.00002638019,0.000016139016,0.00012361615],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.98503226,0.0073070587,0.006399085,0.00012093488,0.00084530486,0.00029534832],"domain_scores_gemma":[0.98124313,0.00944754,0.008179443,0.00020248757,0.00077210454,0.00015530275],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035252556,0.00018021143,0.0030214707,0.0006761799,0.000048990332,0.00003616908,0.00033674,0.00004350743,0.00014956608],"category_scores_gemma":[0.014108106,0.000101774756,0.00097375887,0.00016818348,0.00007525158,0.00060950336,0.000049859515,0.0002640893,9.89344e-7],"study_design_candidate":"randomized_trial","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":[0.12506872,0.06263399,0.06571257,0.000849644,0.019614192,0.000012077438,0.08648991,0.0001144484,0.0005790487,0.26917863,0.019896701,0.34985006],"study_design_scores_gemma":[0.8113196,0.008824791,0.019124711,0.0044602947,0.00080062007,0.00033057085,0.026759846,0.00042323477,0.0004922923,0.12199805,0.0048362394,0.0006297391],"about_ca_topic_score_codex":0.0016789581,"about_ca_topic_score_gemma":0.0006454901,"teacher_disagreement_score":0.68625087,"about_ca_system_score_codex":0.0012884687,"about_ca_system_score_gemma":0.0005996073,"threshold_uncertainty_score":0.9941965},"labels":[],"label_agreement":null},{"id":"W1985629392","doi":"10.1198/073500102288618702","title":"Was There a Riverside Miracle? A Hierarchical Framework for Evaluating Programs With Grouped Data","year":2003,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"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":"Connaught Fund","keywords":"Pooling; Computer science; Econometrics; Independence (probability theory); Statistics; Mathematics; Artificial intelligence","score_opus":0.25498042265165877,"score_gpt":0.42733799986754506,"score_spread":0.1723575772158863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985629392","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":[0.09141849,0.00007989345,0.9078508,0.00010625144,0.000086740394,0.00025514982,0.000113279035,0.000016068707,0.000073343756],"genre_scores_gemma":[0.14593285,0.000101628924,0.85379875,0.000027289685,0.00007614698,0.000008139862,0.000011710983,0.00002691279,0.000016597392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990024,0.00004536578,0.00046895415,0.0001734249,0.00010970548,0.00020015327],"domain_scores_gemma":[0.9974527,0.0013344388,0.00060622446,0.00028067105,0.0002426047,0.000083414045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007225352,0.00014764599,0.00038192671,0.000058703197,0.000090103764,0.00008262895,0.00021510337,0.00007274614,0.000041720694],"category_scores_gemma":[0.0016985615,0.000112293725,0.0000220031,0.00005644591,0.00011192402,0.0002911728,0.000052632044,0.00020908879,8.661637e-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":[0.00040249483,0.00019869788,0.0042723618,0.00036563328,0.00021329758,0.00004516476,0.00041741692,0.000111160065,0.000039267565,0.93308693,0.0012705482,0.059577025],"study_design_scores_gemma":[0.00083638343,0.00048458317,0.0011406047,0.0003133944,0.00016366522,0.00019541645,0.00030498332,0.005135118,0.000032539825,0.99035084,0.0008518135,0.00019067706],"about_ca_topic_score_codex":0.000009647721,"about_ca_topic_score_gemma":0.000034219676,"teacher_disagreement_score":0.059386346,"about_ca_system_score_codex":0.00006560383,"about_ca_system_score_gemma":0.00018845781,"threshold_uncertainty_score":0.45792052},"labels":[],"label_agreement":null},{"id":"W1986440280","doi":"10.1002/sim.3276","title":"The performance of different propensity score methods for estimating marginal odds ratios, <i>Statistics in Medicine</i> 2007; <b>26</b>:3078–3094","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Citation; Library science; Odds; Sociology; Medicine; Statistics; Mathematics; Computer science; Logistic regression","score_opus":0.19247240902296991,"score_gpt":0.4680823787825111,"score_spread":0.27560996975954116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986440280","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":[0.0222688,0.0001966231,0.9747572,0.00038253388,0.0004848087,0.0013609685,0.00011104465,0.00009258793,0.00034546497],"genre_scores_gemma":[0.071556084,0.00077343755,0.92669344,0.00016996816,0.00022432163,0.00020152378,0.00006148145,0.00007088732,0.000248862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638146,0.00034473787,0.0016372951,0.00040516924,0.0006467756,0.00058458775],"domain_scores_gemma":[0.98863745,0.009389437,0.0007388814,0.0006004172,0.00052268617,0.00011115289],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030601656,0.0004095415,0.0011735132,0.00021187485,0.00024795753,0.0000081815515,0.00046782143,0.00012816986,0.000061153034],"category_scores_gemma":[0.014307525,0.0002637259,0.000029746083,0.00036130467,0.0014437668,0.000106621184,0.000121144345,0.0006385849,0.0000014356148],"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":[0.0008931606,0.0004272232,0.022132302,0.0035420298,0.00009830869,0.00014128823,0.0064406954,0.00021146318,0.007594073,0.79066145,0.059175324,0.10868269],"study_design_scores_gemma":[0.0043844637,0.0031707825,0.01473248,0.0034735466,0.00021018792,0.0001215954,0.0006731837,0.22578458,0.009636201,0.7361155,0.0008865321,0.0008109135],"about_ca_topic_score_codex":0.00009889554,"about_ca_topic_score_gemma":0.00022187544,"teacher_disagreement_score":0.22557312,"about_ca_system_score_codex":0.0002097405,"about_ca_system_score_gemma":0.00015094421,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W1986731614","doi":"10.1002/pds.1733","title":"The concept of the marginally matched subject in propensity‐score matched analyses","year":2009,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"University Health Network; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Medicine; Covariate; Calipers; Observational study; Internal medicine; Matching (statistics); Selection bias; Sample size determination; Statistics; Cardiology; Mathematics","score_opus":0.216395270431413,"score_gpt":0.4526145897411571,"score_spread":0.2362193193097441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986731614","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":[0.9621765,0.0020309077,0.010838877,0.020381281,0.00018348344,0.0013132212,0.000022767195,0.00020160565,0.0028513386],"genre_scores_gemma":[0.994034,0.00073108217,0.003578766,0.0013367877,0.000039035203,0.000022572654,0.000003129722,0.000011933918,0.00024267564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968997,0.0015229443,0.00078357744,0.00028718862,0.00012382054,0.00038273662],"domain_scores_gemma":[0.9940342,0.004960225,0.00044073447,0.00041735912,0.00008946688,0.00005805397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003402957,0.00023070668,0.00069145666,0.00004943703,0.00019596773,0.0000072039375,0.00043184572,0.000109437686,0.00003310067],"category_scores_gemma":[0.0022476166,0.00012208491,0.000117531425,0.00026093383,0.00051867263,0.00011558903,0.00013808206,0.0005158795,0.0000018299226],"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":[0.0024041715,0.0005613489,0.22353639,0.00021448452,0.00037369336,0.00004625384,0.005163796,0.0004382996,0.0725241,0.63311607,0.020416936,0.04120447],"study_design_scores_gemma":[0.0009570511,0.00008106222,0.15425746,0.00013237205,0.00012788239,0.000035108387,0.0003274335,0.00047991902,0.069715634,0.77231365,0.0012528806,0.0003195109],"about_ca_topic_score_codex":0.00007651889,"about_ca_topic_score_gemma":0.00011030688,"teacher_disagreement_score":0.13919762,"about_ca_system_score_codex":0.000046033027,"about_ca_system_score_gemma":0.000057541187,"threshold_uncertainty_score":0.4978478},"labels":[],"label_agreement":null},{"id":"W1987839835","doi":"10.1503/cmaj.120592","title":"Adjustment for continuous confounders: an example of how to prevent residual confounding","year":2013,"lang":"en","type":"review","venue":"Canadian Medical Association Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confounding; Observational study; Psychology; Medicine; Internal medicine","score_opus":0.2625521002949927,"score_gpt":0.4363196477322771,"score_spread":0.1737675474372844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987839835","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":[0.00009638531,0.9322093,0.049762372,0.0041714455,0.0027330178,0.008746045,0.00057754235,0.00021093909,0.0014929355],"genre_scores_gemma":[0.00002892766,0.9580518,0.03396194,0.0011716172,0.003310231,0.00069652736,0.00013120951,0.00016177919,0.00248594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959086,0.000482851,0.0012421627,0.00032430806,0.0013023,0.00073974807],"domain_scores_gemma":[0.993054,0.0020166584,0.0016436282,0.00031509355,0.0009920121,0.0019786335],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035692195,0.00037991535,0.0017939191,0.00041294075,0.00016679637,0.00016912566,0.000620434,0.0009442605,0.0010300127],"category_scores_gemma":[0.008088531,0.0003282099,0.0003332845,0.00019466227,0.000050321352,0.00023068833,0.00003909423,0.0009899356,0.000020930976],"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":[0.0000017687404,0.00006050147,0.000002480231,0.0016237452,0.0003430946,0.000019652669,0.00030185693,1.02052915e-7,6.8781213e-7,0.025222145,0.15410487,0.8183191],"study_design_scores_gemma":[0.00021212576,0.0002798882,9.563655e-7,0.0048363744,0.0003273052,0.000105790445,0.00042467055,0.0000040361,0.0000046600007,0.014741089,0.97873574,0.000327367],"about_ca_topic_score_codex":0.0019300549,"about_ca_topic_score_gemma":0.01333758,"teacher_disagreement_score":0.82463086,"about_ca_system_score_codex":0.0032882825,"about_ca_system_score_gemma":0.0053827153,"threshold_uncertainty_score":0.999917},"labels":[],"label_agreement":null},{"id":"W1988058236","doi":"10.1016/j.jval.2013.03.280","title":"Properties of propensity score matching procedures on covariate balancing and estimation: Influence of the number of propensity score digits used on matched sets created","year":2013,"lang":"en","type":"article","venue":"Value in Health","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":"Western University","funders":"","keywords":"Propensity score matching; Covariate; Confounding; Statistics; Matching (statistics); Confidence interval; Numerical digit; Demography; Mathematics; Medicine; Arithmetic","score_opus":0.22731307978205686,"score_gpt":0.3683948052331946,"score_spread":0.14108172545113776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988058236","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":[0.9967869,0.000018557905,0.00020129954,0.00027332065,0.00001928992,0.0025207466,0.000009823199,0.00007957781,0.0000904876],"genre_scores_gemma":[0.9926861,0.000014865279,0.007085636,0.00010002533,0.000004982857,0.00006548269,0.0000014905308,0.000027348746,0.000014064022],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99789226,0.00027220242,0.0008712924,0.00028091428,0.00041985992,0.0002634912],"domain_scores_gemma":[0.9979622,0.00026930985,0.00089624216,0.0004778025,0.0003311886,0.00006328762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007694449,0.0002228858,0.0006695695,0.00008152639,0.00008560865,0.000021735867,0.0002259475,0.00009834165,0.0000051028533],"category_scores_gemma":[0.0014888877,0.00014157477,0.00003642899,0.00029967492,0.00020274473,0.00031452673,0.00013555771,0.00028552255,0.000002226647],"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":[0.000574323,0.0010693568,0.8124654,0.025594564,0.00007625045,0.000004777605,0.014653712,0.0327694,0.060787603,0.050718207,0.00007338982,0.001212981],"study_design_scores_gemma":[0.0007306696,0.00046352553,0.533551,0.023195092,0.00002054633,0.000025860007,0.00019372537,0.0046960614,0.24480249,0.19199395,3.950076e-7,0.0003266859],"about_ca_topic_score_codex":0.0041399836,"about_ca_topic_score_gemma":0.00007691641,"teacher_disagreement_score":0.27891442,"about_ca_system_score_codex":0.00014955108,"about_ca_system_score_gemma":0.00036876567,"threshold_uncertainty_score":0.6258445},"labels":[],"label_agreement":null},{"id":"W1988221738","doi":"10.1080/00273171.2010.498292","title":"Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":398,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Bootstrapping (finance); Computer science; Type I and type II errors; Bayesian probability; Statistics; Confidence interval; Statistical hypothesis testing; Econometrics; Null hypothesis; Prior probability; Mathematics","score_opus":0.6989123915737223,"score_gpt":0.608930368580515,"score_spread":0.08998202299320734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988221738","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":[0.7655777,0.000005899952,0.23285206,0.000056625635,0.00010025396,0.0009465636,0.000011515343,0.00023472188,0.00021472156],"genre_scores_gemma":[0.55185777,4.866892e-7,0.4477169,0.0000031218947,0.00005106341,0.00030920218,0.000009895136,0.000026212101,0.000025330311],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981856,0.00018022669,0.00029449863,0.0003525856,0.000536491,0.00045064077],"domain_scores_gemma":[0.9920731,0.006798242,0.00010813516,0.00024162987,0.00064909435,0.0001297579],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025478955,0.00016324395,0.00023476941,0.00026336944,0.0003216194,0.00026383917,0.00019901879,0.00019093676,0.00001228137],"category_scores_gemma":[0.010572958,0.00014896889,0.000036273283,0.0002627974,0.00016714235,0.0009648094,0.0001951366,0.00078829203,0.0000030111437],"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":[0.00006368414,0.0004916356,0.003210707,0.00031806584,0.000015706984,0.000014300291,0.0012731532,0.000041104417,0.5571062,0.054263126,0.00012891,0.38307342],"study_design_scores_gemma":[0.0005746021,0.00025017824,0.006332192,0.00016908417,0.000026044081,0.000008552565,0.000087725166,0.23311906,0.048025142,0.7111719,0.000010321245,0.00022517802],"about_ca_topic_score_codex":0.00016579659,"about_ca_topic_score_gemma":0.000047730024,"teacher_disagreement_score":0.6569088,"about_ca_system_score_codex":0.00009869297,"about_ca_system_score_gemma":0.00012387062,"threshold_uncertainty_score":0.9977614},"labels":[],"label_agreement":null},{"id":"W1989087635","doi":"10.2139/ssrn.720061","title":"Estimation of Panel Data Models with Binary Indicators when Treatment Effects are not Constant over Time","year":2004,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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 Toronto","funders":"","keywords":"Constant (computer programming); Panel data; Econometrics; Binary number; Estimation; Statistics; Binary data; Mathematics; Computer science; Economics","score_opus":0.09702859518878437,"score_gpt":0.35155092146082867,"score_spread":0.2545223262720443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989087635","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":[0.49827158,0.00039628134,0.5002674,0.00017649577,0.00001745557,0.0004793784,0.00003530173,0.00013627489,0.00021984256],"genre_scores_gemma":[0.9654419,0.0005184175,0.03381083,0.000023779035,0.000027384795,0.000015045705,0.000023183873,0.00004098819,0.00009849244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998047,0.00006596665,0.0003540733,0.00024698192,0.00035535853,0.0009306498],"domain_scores_gemma":[0.99857384,0.00018565898,0.00055073155,0.000560108,0.000051049865,0.00007862041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005938699,0.00023738138,0.00038347807,0.00019173676,0.000092355855,0.00002177654,0.00036856675,0.000092365895,0.000013269002],"category_scores_gemma":[0.0001002718,0.00016916345,0.00005066744,0.00015591411,0.00010374643,0.0005650519,0.000072047646,0.0006130022,0.0000058875885],"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":[0.00044945918,0.0010484448,0.0002463487,0.000120848905,0.0007828912,0.00007635129,0.00084342866,0.0063825366,0.0040702093,0.9476237,0.00008662201,0.038269147],"study_design_scores_gemma":[0.0013633919,0.001654112,0.000042822747,0.00029553176,0.00017170596,0.0002792948,0.00012763086,0.004064983,0.009237801,0.9825521,0.0000074869963,0.00020314213],"about_ca_topic_score_codex":0.000033666933,"about_ca_topic_score_gemma":0.00008265692,"teacher_disagreement_score":0.4671703,"about_ca_system_score_codex":0.0014992253,"about_ca_system_score_gemma":0.0015382268,"threshold_uncertainty_score":0.6898286},"labels":[],"label_agreement":null},{"id":"W1991570465","doi":"10.1016/s0895-4356(00)00210-9","title":"Choice of effect measure for epidemiological data","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":196,"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":"Relative risk; Number needed to treat; Measure (data warehouse); Statistics; Econometrics; Medicine; Absolute risk reduction; Odds ratio; Statistical model; Confidence interval; Mathematics; Actuarial science; Computer science; Data mining; Economics","score_opus":0.8208651165333847,"score_gpt":0.6680076360632555,"score_spread":0.15285748047012915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991570465","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":[0.37045574,0.0014238803,0.6161167,0.007851921,0.000947665,0.001034394,0.000109269204,0.00012990835,0.0019305168],"genre_scores_gemma":[0.3582844,0.0011438839,0.6361558,0.0021496497,0.0019804875,0.000019208397,0.000017306316,0.000045528297,0.00020374419],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98211694,0.008702781,0.007996814,0.00045370765,0.00022550984,0.0005042763],"domain_scores_gemma":[0.5949437,0.39823386,0.004970032,0.0011383243,0.0004182472,0.00029585385],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08886345,0.0002590036,0.0049899295,0.00007396859,0.000040097628,0.0000024982874,0.0013971525,0.0007221398,0.0003478109],"category_scores_gemma":[0.6484413,0.00015823393,0.00091263937,0.000113597234,0.0005139169,0.00022435364,0.00014023493,0.0011837377,0.000008749462],"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":[0.0035618898,0.00089587294,0.23163077,0.000426383,0.0007185648,0.000023500612,0.000021473332,0.00015193404,0.00021235122,0.081646286,0.14159726,0.5391137],"study_design_scores_gemma":[0.001736446,0.0051140133,0.022564724,0.00030172052,0.0002795659,0.0000874125,0.0000043023933,0.0012336939,0.00014008168,0.93058074,0.037743695,0.00021361439],"about_ca_topic_score_codex":0.000007974565,"about_ca_topic_score_gemma":0.000007561102,"teacher_disagreement_score":0.8489345,"about_ca_system_score_codex":0.000025507634,"about_ca_system_score_gemma":0.00012269842,"threshold_uncertainty_score":0.9382068},"labels":[],"label_agreement":null},{"id":"W1993260957","doi":"10.1037/a0024918","title":"Marginal mean weighting through stratification: A generalized method for evaluating multivalued and multiple treatments with nonexperimental data.","year":2011,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"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 Academy of Education; Spencer Foundation; Social Sciences and Humanities Research Council of Canada; William T. Grant Foundation","keywords":"Causal inference; Covariate; Propensity score matching; Weighting; Average treatment effect; Inverse probability weighting; Statistics; Mathematics; Randomized experiment; Econometrics; Nonparametric statistics; Inference; Binary data; Computer science; Artificial intelligence; Binary number","score_opus":0.793516695385926,"score_gpt":0.6567447400249953,"score_spread":0.13677195536093067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993260957","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":[0.055552408,0.00010061974,0.93977046,0.000041340958,0.000059313516,0.0013898439,0.00004010181,0.00030705836,0.002738848],"genre_scores_gemma":[0.04467795,0.000013844708,0.9545158,0.000104221996,0.000052983753,0.0004797073,0.000046534307,0.0000446073,0.00006430633],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968522,0.0011141576,0.0005100788,0.00093308307,0.00021680062,0.00037368244],"domain_scores_gemma":[0.9957712,0.0027786104,0.00034252685,0.00088895037,0.00011563128,0.0001030773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024881833,0.000336573,0.0005060565,0.000043078522,0.00021146671,0.00003807781,0.0004030967,0.00015935888,0.00014720214],"category_scores_gemma":[0.0015793359,0.00022557011,0.00005791933,0.00015420164,0.00016019389,0.00034105263,0.00014563592,0.00019111189,0.0000014423022],"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":[0.0021797845,0.002014185,0.0010881376,0.00010603667,0.00043603455,0.00001695605,0.0070400042,0.0000021860787,0.5194012,0.1545401,0.00014543705,0.31302997],"study_design_scores_gemma":[0.004305995,0.0024574334,0.0010569615,0.00008293605,0.0003035872,0.00011158451,0.0011811375,0.028153807,0.1842142,0.77735406,0.00012908266,0.0006492066],"about_ca_topic_score_codex":0.000034635505,"about_ca_topic_score_gemma":0.000003858791,"teacher_disagreement_score":0.62281394,"about_ca_system_score_codex":0.00004910014,"about_ca_system_score_gemma":0.000012464101,"threshold_uncertainty_score":0.9198482},"labels":[],"label_agreement":null},{"id":"W1993593244","doi":"10.1037/a0030785","title":"Correct effect size estimates for strength of association statistics: Comment on Odgaard and Fowler (2010).","year":2013,"lang":"en","type":"letter","venue":"Journal of Consulting and Clinical Psychology","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"Jefferson Scholars Foundation; International Max Planck Research School for Environmental, Cellular and Molecular Microbiology; Association for Psychological Science; National Institute of Mental Health; American Psychological Foundation","keywords":"Statistics; Association (psychology); Psychology; Confidence interval; Econometrics; Estimation; Mathematics; Engineering","score_opus":0.1792739430403617,"score_gpt":0.507155372582864,"score_spread":0.3278814295425023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993593244","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16417947,0.0012466365,0.12631293,0.69048285,0.010462059,0.0043546013,0.0012367576,0.00026376918,0.0014609423],"genre_scores_gemma":[0.026614018,0.0021421805,0.59770834,0.3683208,0.0037206654,0.00009139343,0.00007116529,0.00021862263,0.0011127888],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996968,0.0005153952,0.0017404401,0.0002607405,0.00024162121,0.00027382254],"domain_scores_gemma":[0.91453093,0.08126131,0.0033419242,0.00020585192,0.00058634084,0.000073651085],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027897037,0.00027948973,0.0014038545,0.00009904359,0.000049785063,0.00002819746,0.00016290705,0.0009258598,0.000039985076],"category_scores_gemma":[0.036812957,0.00020958387,0.00016545279,0.00003695181,0.00020508659,0.00004758882,0.000037710284,0.0019110672,0.0000022358033],"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":[0.00025066975,0.00013480282,0.0056830714,0.00027229937,0.00038655906,0.0000143648285,0.00003553225,1.1939645e-7,0.000032442662,0.00021608983,0.96899426,0.023979789],"study_design_scores_gemma":[0.023512643,0.04529147,0.014737538,0.0058728196,0.0047055483,0.00038613475,0.000117375166,0.0006631173,0.0009041255,0.5786924,0.3232683,0.0018485604],"about_ca_topic_score_codex":0.000004606945,"about_ca_topic_score_gemma":0.00000158447,"teacher_disagreement_score":0.64572597,"about_ca_system_score_codex":0.00005782998,"about_ca_system_score_gemma":0.000042445372,"threshold_uncertainty_score":0.97130036},"labels":[],"label_agreement":null},{"id":"W1995014100","doi":"10.1016/j.jclinepi.2012.02.012","title":"Treatment effects on patient-important outcomes can be small, even with large effects on surrogate markers","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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":"Surrogate endpoint; Medicine; Randomized controlled trial; Confidence interval; Intensive care medicine; Clinical trial; Outcome (game theory); Internal medicine","score_opus":0.32462153297885415,"score_gpt":0.5232699659370967,"score_spread":0.19864843295824258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995014100","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":[0.9890312,0.00012438065,0.003052229,0.0057321102,0.0009501689,0.0006518249,0.000014853143,0.00008292989,0.00036032192],"genre_scores_gemma":[0.9553344,0.0003145167,0.037299216,0.006357492,0.0004888846,0.000045728295,0.000004744521,0.00005854512,0.00009644997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.990575,0.004592419,0.0033409619,0.0003152396,0.0002959189,0.0008804374],"domain_scores_gemma":[0.8757413,0.1194238,0.003636892,0.0004975449,0.0001314922,0.0005689478],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009873944,0.0004585995,0.0032971073,0.00014962046,0.0000722771,0.000005805333,0.0002655744,0.00043401166,0.000027426438],"category_scores_gemma":[0.07730119,0.0002495947,0.00070772547,0.00009695333,0.00012832154,0.00011401267,0.000058579415,0.0010136714,0.000011517683],"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":[0.0021379648,0.0018735778,0.9199738,0.00012935074,0.000828158,0.00030566117,0.00017481284,0.000009301063,0.00003065573,0.034435946,0.0023655982,0.037735164],"study_design_scores_gemma":[0.012530625,0.0938473,0.6748552,0.0017763407,0.001138065,0.00032913554,0.00014536959,0.000086809545,0.006346589,0.19225536,0.015514359,0.0011749063],"about_ca_topic_score_codex":0.000016024253,"about_ca_topic_score_gemma":0.00005018841,"teacher_disagreement_score":0.24511866,"about_ca_system_score_codex":0.00023983823,"about_ca_system_score_gemma":0.00012735603,"threshold_uncertainty_score":0.99999565},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W1995405631","doi":"10.1592/phco.24.13.1105.38083","title":"Pharmacoepidemiology II: The Nested Case‐Control Study—A Novel Approach in Pharmacoepidemiologic Research","year":2004,"lang":"en","type":"article","venue":"Pharmacotherapy The Journal of Human Pharmacology and Drug Therapy","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Pharmacoepidemiology; Nested case-control study; Confounding; Matching (statistics); Medicine; Propensity score matching; Cohort study; Case-control study; Cohort; Epidemiology; Research design; Control (management); Statistics; Econometrics; Computer science; Internal medicine; Mathematics; Pathology; Artificial intelligence","score_opus":0.34458929487121653,"score_gpt":0.538914238796219,"score_spread":0.1943249439250025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995405631","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":[0.97560483,0.0077172657,0.0051764143,0.0076004267,0.0004921414,0.0031232743,0.000014563086,0.00011480229,0.00015628718],"genre_scores_gemma":[0.9827227,0.0077571315,0.0013775321,0.0067964057,0.0009067673,0.00027742074,7.830652e-7,0.000090608635,0.00007067196],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985598,0.010181217,0.0019871064,0.0005262835,0.00057009445,0.0011372723],"domain_scores_gemma":[0.9870016,0.010504719,0.0012486726,0.00046709809,0.0005292506,0.00024868487],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.037179656,0.00064783473,0.0012965885,0.00066104566,0.0016834636,0.00004014107,0.0016762437,0.00019302133,0.00036059634],"category_scores_gemma":[0.00028070292,0.00034991038,0.0002586902,0.00087478355,0.001427693,0.0004795594,0.00020228891,0.0038512836,0.0000025367392],"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":[0.0064209485,0.009192636,0.005070343,0.00006447371,0.0021046435,0.0011953177,0.031961765,0.0038718772,0.90522355,0.009601271,0.014734458,0.010558717],"study_design_scores_gemma":[0.15626395,0.012421602,0.0041097896,0.00021045179,0.0021822748,0.0284942,0.027385075,0.0029765295,0.16551761,0.5857793,0.011744773,0.0029144548],"about_ca_topic_score_codex":0.00014769158,"about_ca_topic_score_gemma":0.000034543773,"teacher_disagreement_score":0.7397059,"about_ca_system_score_codex":0.00026165385,"about_ca_system_score_gemma":0.00018617793,"threshold_uncertainty_score":0.9998953},"labels":[],"label_agreement":null},{"id":"W1995875958","doi":"10.1257/aer.91.2.112","title":"Reconciling Conflicting Evidence on the Performance of Propensity-Score Matching Methods","year":2001,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":336,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Propensity score matching; Economics; Matching (statistics); Econometrics; Actuarial science; Positive economics; Statistics; Mathematics","score_opus":0.43998595875878393,"score_gpt":0.49663935314736035,"score_spread":0.05665339438857642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995875958","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":[0.977187,0.0048085647,0.01115541,0.0011603626,0.000063379826,0.001036211,0.0000017995332,0.0001435442,0.0044437526],"genre_scores_gemma":[0.62582487,0.20771626,0.16206564,0.0038279938,0.00009084148,0.00021159663,0.0000012744714,0.000068498135,0.00019305064],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9983347,0.00035014396,0.000721952,0.0002791739,0.00008288622,0.00023112015],"domain_scores_gemma":[0.9954023,0.0027614562,0.0010134255,0.0007189006,0.000059601025,0.000044350094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003068012,0.00019368727,0.0007632904,0.00003719233,0.000085988555,0.000015986923,0.00042574873,0.000021870876,0.00014547158],"category_scores_gemma":[0.0013409076,0.00013216525,0.000116654555,0.00014642108,0.00022053062,0.00024425148,0.00009822082,0.0002654356,0.000046934812],"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":[0.000031119427,0.000031826192,0.005573479,0.0022247916,0.00007622454,0.000003328118,0.0004237679,0.000053315383,0.0026029276,0.023077063,0.0007508332,0.9651513],"study_design_scores_gemma":[0.0009516475,0.006146652,0.010336709,0.3299316,0.0016067445,0.0012584126,0.0029023928,0.008132525,0.22945143,0.16519625,0.237329,0.006756635],"about_ca_topic_score_codex":0.00007649188,"about_ca_topic_score_gemma":0.000009837152,"teacher_disagreement_score":0.9583947,"about_ca_system_score_codex":0.00014319978,"about_ca_system_score_gemma":0.000064404056,"threshold_uncertainty_score":0.53895426},"labels":[],"label_agreement":null},{"id":"W1996144317","doi":"10.1515/jci-2014-0022","title":"A Boosting Algorithm for Estimating Generalized Propensity Scores with Continuous Treatments","year":2014,"lang":"en","type":"article","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":153,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Institutes of Health","keywords":"Covariate; Mathematics; Propensity score matching; Statistics; Boosting (machine learning); Causal inference; Estimator; Average treatment effect; Nonparametric statistics; Curse of dimensionality; Weighting; Econometrics; Algorithm; Computer science; Machine learning; Medicine","score_opus":0.13914851500014766,"score_gpt":0.40452671844930155,"score_spread":0.26537820344915386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996144317","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":[0.1676282,0.00002371304,0.8313773,0.000057956047,0.000111623995,0.00041967435,0.000007179153,0.0000918374,0.0002825026],"genre_scores_gemma":[0.2652986,0.000006242033,0.7342339,0.00006567767,0.0002188104,0.00002951986,0.0000021358471,0.000033196513,0.00011189377],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981277,0.00011899442,0.00077330857,0.0002096372,0.0004017897,0.0003685929],"domain_scores_gemma":[0.99595934,0.0013338204,0.0012807521,0.00026044625,0.0010100547,0.00015556793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009218158,0.00028733586,0.0007604758,0.00012921088,0.00014805613,0.0001019316,0.00027850305,0.00009536163,0.000015199306],"category_scores_gemma":[0.0028691783,0.0001943295,0.00011062189,0.00013549709,0.000112498,0.00047543668,0.00006211674,0.0002853617,0.0000017339762],"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":[0.0008040614,0.0009533172,0.013792096,0.00048094196,0.0008474111,0.00020547393,0.0015234642,0.0007090348,0.023003932,0.069894664,0.002064478,0.88572115],"study_design_scores_gemma":[0.00840787,0.010934141,0.0018908043,0.0036158224,0.00097441376,0.0012343685,0.00017884099,0.1482566,0.083846554,0.7383304,0.00083910924,0.0014910734],"about_ca_topic_score_codex":0.000021208423,"about_ca_topic_score_gemma":0.000014589786,"teacher_disagreement_score":0.8842301,"about_ca_system_score_codex":0.000108575936,"about_ca_system_score_gemma":0.00015432312,"threshold_uncertainty_score":0.7924527},"labels":[],"label_agreement":null},{"id":"W1996851858","doi":"10.1214/14-ejs920","title":"Dynamic treatment regimes: Technical challenges and applications","year":2014,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":170,"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 Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; University of Michigan; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Estimator; Operationalization; Inference; Mathematics; Variety (cybernetics); Decision rule; Machine learning; Econometrics; Computer science; Mathematical optimization; Artificial intelligence; Statistics","score_opus":0.0495202221317277,"score_gpt":0.3737772155890598,"score_spread":0.3242569934573321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996851858","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":[0.0007372231,0.0035228068,0.99410397,0.00027350066,0.000013310101,0.00017443181,0.000009274691,0.00005407806,0.0011114101],"genre_scores_gemma":[0.52164286,0.03400447,0.44390094,0.00002700106,0.00009053828,0.00004028259,0.0000034343109,0.00003926773,0.00025122662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99901694,0.00005571351,0.0003641065,0.000115690644,0.00016111483,0.00028645797],"domain_scores_gemma":[0.99848735,0.000755536,0.00034269746,0.00019987389,0.00014066641,0.00007387832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039681568,0.00013580167,0.0002897896,0.000082536244,0.00004651612,0.000011725279,0.00013125515,0.000064733984,0.0000070802434],"category_scores_gemma":[0.0002618264,0.00010744635,0.00003417779,0.000047642436,0.0000874439,0.00006904009,0.000019874878,0.00026492387,0.0000022007282],"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":[0.000009887617,0.00007598562,0.000002781803,0.000021743515,0.000026659089,0.0000020950858,0.00005832565,0.000001284461,0.00035724256,0.8585392,0.00011685562,0.14078791],"study_design_scores_gemma":[0.0002747261,0.0013728455,0.000058490277,0.000030914114,0.00007995737,0.00025300842,0.000068039066,0.00013728601,0.00027580926,0.9816329,0.015710725,0.00010530284],"about_ca_topic_score_codex":7.271484e-7,"about_ca_topic_score_gemma":0.000045440538,"teacher_disagreement_score":0.550203,"about_ca_system_score_codex":0.0003210323,"about_ca_system_score_gemma":0.00012440092,"threshold_uncertainty_score":0.4381535},"labels":[],"label_agreement":null},{"id":"W1996867876","doi":"10.1200/jco.2007.11.3670","title":"Statistical Power of Negative Randomized Controlled Trials Presented at American Society for Clinical Oncology Annual Meetings","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":61,"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 of Toronto","funders":"","keywords":"Sample size determination; Medicine; Post-hoc analysis; Randomized controlled trial; Hazard ratio; Odds ratio; Logistic regression; Internal medicine; Post hoc; Clinical endpoint; Statistical power; Confidence interval; Clinical trial; Clinical Oncology; Statistics; Cancer","score_opus":0.41193859149800466,"score_gpt":0.6415961380156108,"score_spread":0.22965754651760611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996867876","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":[0.3247707,0.00028456803,0.6540225,0.0072156847,0.0024680728,0.005714006,0.00019019454,0.00010431578,0.005229941],"genre_scores_gemma":[0.3267157,0.0010186079,0.6684257,0.0018612724,0.00137995,0.000086523505,0.0000049726304,0.000051314863,0.00045598717],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9607486,0.012079502,0.02494841,0.00049327104,0.0009939434,0.00073624955],"domain_scores_gemma":[0.37820008,0.58727014,0.029926647,0.00033814003,0.0036505715,0.00061438454],"candidate_categories":["metaresearch","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19649172,0.0003927796,0.02173187,0.00017586467,0.00008022659,0.0000097540915,0.00053413666,0.0011967107,0.000210735],"category_scores_gemma":[0.60230196,0.00024006706,0.0073424634,0.00021360682,0.0037945523,0.00017432585,0.00021451258,0.0018741168,0.0000036325205],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8341862,0.004156451,0.0008530651,0.000044521785,0.005822788,0.000096993645,0.0007555648,0.0000026492874,0.00021000567,0.03098384,0.0797488,0.04313911],"study_design_scores_gemma":[0.66543,0.039135475,0.0013878279,0.0001400925,0.0046467637,0.00008291541,0.0026793557,0.00026327572,0.000605275,0.24630246,0.03891649,0.00041005845],"about_ca_topic_score_codex":0.000022934337,"about_ca_topic_score_gemma":0.000071081195,"teacher_disagreement_score":0.58254856,"about_ca_system_score_codex":0.00040011047,"about_ca_system_score_gemma":0.0020743394,"threshold_uncertainty_score":0.99891657},"labels":[],"label_agreement":null},{"id":"W1997094667","doi":"10.1016/j.jclinepi.2007.10.024","title":"Fitting marginal structural models: estimating covariate-treatment associations in the reweighted data set can guide model fitting","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Covariate; Marginal structural model; Inverse probability weighting; Observational study; Inverse probability; Confounding; Data set; Econometrics; Statistics; Set (abstract data type); Weighting; Computer science; Medicine; Mathematics; Propensity score matching; Bayesian probability; Posterior probability","score_opus":0.8597393166556409,"score_gpt":0.631203739722787,"score_spread":0.22853557693285387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997094667","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":[0.35552382,0.000115307186,0.633898,0.0089602005,0.00036773563,0.00036805862,0.00013999059,0.0000783448,0.00054853427],"genre_scores_gemma":[0.40779507,0.0001572872,0.590641,0.0008985419,0.00041889545,0.00000617004,0.000034090426,0.000018372108,0.000030528692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9882704,0.004261702,0.006169136,0.00039929792,0.00033760545,0.0005618455],"domain_scores_gemma":[0.91068774,0.081408985,0.006312862,0.0010073392,0.0004062073,0.00017685948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028031608,0.00028112417,0.0021232236,0.00012321402,0.0002507886,0.000014085703,0.0011306719,0.0003660534,0.0000122764595],"category_scores_gemma":[0.15842731,0.00017486201,0.00031981297,0.00019735335,0.00022117014,0.00044662898,0.00023978164,0.0014304332,0.00000104336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042922108,0.00093360984,0.25574407,0.00012179407,0.0010212959,0.0007192647,0.007065149,0.39570767,0.00006117449,0.26935795,0.04851336,0.020325447],"study_design_scores_gemma":[0.00046728607,0.00017588562,0.002817026,0.000072894385,0.000058970072,0.00018985911,0.00010046192,0.55246186,0.000002057547,0.4434974,0.000055673012,0.000100633326],"about_ca_topic_score_codex":0.00021647957,"about_ca_topic_score_gemma":0.00016033859,"teacher_disagreement_score":0.25292704,"about_ca_system_score_codex":0.0002644346,"about_ca_system_score_gemma":0.00054804015,"threshold_uncertainty_score":0.9715252},"labels":[],"label_agreement":null},{"id":"W1997700012","doi":"10.1016/j.annepidem.2015.02.008","title":"Does selection bias explain the obesity paradox among individuals with cardiovascular disease?","year":2015,"lang":"en","type":"article","venue":"Annals of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":113,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Confounding; Obesity; Confidence interval; Selection bias; National Health and Nutrition Examination Survey; Demography; Disease; Meta-analysis; Collider; Internal medicine; Information bias; Environmental health; Population; Pathology","score_opus":0.4596529075982262,"score_gpt":0.4456589622107649,"score_spread":0.013993945387461293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997700012","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":[0.8736662,0.0011246132,0.1208265,0.0028044267,0.00008821298,0.0006759961,0.000026842119,0.00027180888,0.0005153738],"genre_scores_gemma":[0.97866625,0.00031967805,0.02007246,0.0005889956,0.000109239445,0.00013733495,0.000011783352,0.000025469624,0.00006876245],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99653673,0.001852169,0.000565683,0.00034456153,0.00025465534,0.0004462167],"domain_scores_gemma":[0.9940804,0.0041427948,0.0004418598,0.00079768634,0.0003274669,0.00020976673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009387061,0.00021313304,0.00078317337,0.00007997682,0.00008129831,0.0000058014302,0.0003070379,0.00014404158,0.000022601407],"category_scores_gemma":[0.019379629,0.00009864367,0.0002344231,0.00021426818,0.00046077947,0.00019393505,0.00009343054,0.00025166228,0.0000057172765],"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":[0.000082148414,0.000118740936,0.8752505,0.000060859667,0.0006553442,0.0000070181236,0.00033848386,0.0010869018,0.0000068814097,0.100359485,0.020672964,0.001360632],"study_design_scores_gemma":[0.00015523021,0.00022412412,0.06846953,0.00007577007,0.00014078878,0.000006404249,0.00021549704,0.00019227201,0.0017191085,0.92254084,0.0060600596,0.00020035695],"about_ca_topic_score_codex":0.00024573965,"about_ca_topic_score_gemma":0.000057855043,"teacher_disagreement_score":0.82218134,"about_ca_system_score_codex":0.000021616152,"about_ca_system_score_gemma":0.00007160704,"threshold_uncertainty_score":0.9888806},"labels":[],"label_agreement":null},{"id":"W1998083820","doi":"10.1007/s11336-004-1261-y","title":"Causal Inferences with Group Based Trajectory Models","year":2005,"lang":"en","type":"article","venue":"Psychometrika","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":111,"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":"Trajectory; Observational study; Causal inference; Psychology; Juvenile delinquency; Propensity score matching; Event (particle physics); Covariate; Econometrics; Longitudinal study; Outcome (game theory); Psychopathology; Time point; Causal model; Computer science; Developmental psychology; Statistics; Mathematics; Clinical psychology","score_opus":0.18948909795287625,"score_gpt":0.3953022201017843,"score_spread":0.20581312214890804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998083820","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":[0.119825855,0.0002519439,0.8505318,0.00033226094,0.00009579776,0.0005123608,0.00002055536,0.001200473,0.027228964],"genre_scores_gemma":[0.7105015,0.00003145299,0.28876314,0.00023591425,0.00011210922,0.000094637006,0.0000064918017,0.000043290358,0.00021150062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823403,0.00006342851,0.00036340987,0.00041083893,0.0004949073,0.00043335595],"domain_scores_gemma":[0.99812424,0.00085126545,0.00017137881,0.00057540945,0.0001228396,0.00015486032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037738355,0.00029936436,0.0003599958,0.0005900802,0.00008395813,0.000054055614,0.00035252338,0.00013689681,0.000483628],"category_scores_gemma":[0.00024893595,0.00023417233,0.00007479933,0.0010988386,0.00012818398,0.00053788815,0.000024848789,0.00030980483,0.00004059153],"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":[0.0007232856,0.003456654,0.0125833545,0.00039961594,0.00031902816,0.00004005726,0.0017053916,0.0020404106,0.0046239756,0.7226388,0.024511876,0.22695756],"study_design_scores_gemma":[0.0043440084,0.0025311748,0.004286662,0.0005030489,0.00018359353,0.000043325952,0.0004264917,0.015174542,0.018070878,0.92435163,0.0276003,0.0024843419],"about_ca_topic_score_codex":0.00001934339,"about_ca_topic_score_gemma":0.00018498278,"teacher_disagreement_score":0.5906756,"about_ca_system_score_codex":0.00010792354,"about_ca_system_score_gemma":0.00005619627,"threshold_uncertainty_score":0.954927},"labels":[],"label_agreement":null},{"id":"W1998147618","doi":"10.5555/3191835.3191958","title":"Adjustments to propensity score matching for network structures","year":2014,"lang":"en","type":"article","venue":"Advances in Social Networks Analysis and Mining","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":"Canadian Imperial Bank of Commerce (Canada)","funders":"","keywords":"Propensity score matching; Computer science; Inference; Metric (unit); Matching (statistics); Data mining; Observational study; Robustness (evolution); Machine learning; Artificial intelligence; Econometrics; Statistics; Mathematics; Engineering","score_opus":0.08983792281091064,"score_gpt":0.394851842228658,"score_spread":0.30501391941774736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998147618","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":[0.22688691,0.00037607935,0.7718104,0.00003121037,0.00007067408,0.0003256703,0.0000028459863,0.00007176721,0.00042441892],"genre_scores_gemma":[0.82883775,0.00012801099,0.17016527,0.00024643386,0.0004764496,0.00008264932,0.0000135915325,0.000021785745,0.000028053544],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858814,0.000087200046,0.00038327926,0.00037097442,0.00014393267,0.00042649606],"domain_scores_gemma":[0.99893737,0.0005352052,0.00022296747,0.00015955449,0.00007316531,0.00007175059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066134246,0.0002022242,0.0006274173,0.00011943051,0.0003252585,0.00005176674,0.00014990111,0.000106485306,0.000007092956],"category_scores_gemma":[0.00018535639,0.00018208257,0.00011876958,0.00072556303,0.00005538074,0.0002419272,0.00011510805,0.00014228706,1.3648912e-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":[0.00015525128,0.000056620756,0.110041745,0.00012238357,0.0004501933,0.0000034303346,0.0024066947,0.17181814,0.00004697275,0.27998215,0.0007183634,0.43419805],"study_design_scores_gemma":[0.00041265716,0.00014132056,0.024429211,0.00013497291,0.00060860836,8.394343e-7,0.00047576395,0.018197255,0.000046823097,0.95255864,0.0024333089,0.0005605976],"about_ca_topic_score_codex":0.000013889787,"about_ca_topic_score_gemma":0.00068240415,"teacher_disagreement_score":0.6725765,"about_ca_system_score_codex":0.000044797507,"about_ca_system_score_gemma":0.0000071921722,"threshold_uncertainty_score":0.74251115},"labels":[],"label_agreement":null},{"id":"W2002688922","doi":"10.1007/s10654-005-7919-7","title":"Methods to Account for Attrition in Longitudinal Data: Do They Work? A Simulation Study","year":2005,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":112,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital; Institute for Work & Health","funders":"","keywords":"Missing data; Imputation (statistics); Attrition; Statistics; Weighting; Confounding; Inverse probability weighting; Selection bias; Logistic regression; Econometrics; Medicine; Mathematics; Propensity score matching","score_opus":0.6859470613835384,"score_gpt":0.6042021005713848,"score_spread":0.08174496081215366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002688922","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":[0.09736588,0.00018025703,0.90057755,0.0009725166,0.000115353236,0.0005128844,0.000006723666,0.000033614757,0.00023520929],"genre_scores_gemma":[0.4869457,0.000012110725,0.51249206,0.00019733231,0.00031330448,0.0000045087777,0.000002560102,0.000020754216,0.000011643394],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931051,0.0044260314,0.0017235366,0.00031379372,0.00010802368,0.00032350922],"domain_scores_gemma":[0.98756903,0.01069066,0.0008680904,0.00053155236,0.00024238563,0.000098267345],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031044485,0.00016432346,0.00065784965,0.0002717283,0.000042888838,0.000012974083,0.0005802748,0.00004293758,0.00002278577],"category_scores_gemma":[0.034679856,0.00013108538,0.00007968126,0.00016248514,0.00003068967,0.00037843364,0.0001934288,0.0003508446,0.000010226447],"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":[0.002708435,0.0028358675,0.108591594,0.00010845966,0.00035232186,0.0002146235,0.0045203227,0.16662648,0.001212954,0.02762345,0.024837598,0.6603679],"study_design_scores_gemma":[0.005792613,0.007829036,0.17391637,0.0009992536,0.0003977157,0.00023255633,0.001252811,0.012816651,0.00021574355,0.71033615,0.085053936,0.0011571851],"about_ca_topic_score_codex":0.000002229765,"about_ca_topic_score_gemma":0.000025368523,"teacher_disagreement_score":0.6827127,"about_ca_system_score_codex":0.00012662353,"about_ca_system_score_gemma":0.000022038665,"threshold_uncertainty_score":0.9977436},"labels":[],"label_agreement":null},{"id":"W2004722883","doi":"10.1097/ede.0b013e3181a819a1","title":"Overadjustment Bias and Unnecessary Adjustment in Epidemiologic Studies","year":2009,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1947,"is_retracted":false,"has_abstract":true,"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; National Institutes of Health","keywords":"Selection bias; Omitted-variable bias; Confounding; Information bias; Econometrics; Statistics; Proxy (statistics); Causal structure; Sampling bias; Non-response bias; Outcome (game theory); Causal inference; Sample size determination; Mathematics","score_opus":0.6176038876181804,"score_gpt":0.5397161510959915,"score_spread":0.07788773652218894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004722883","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":[0.8449751,0.07231061,0.03387222,0.039631553,0.0006065691,0.0020482114,0.00001611194,0.0012602174,0.005279379],"genre_scores_gemma":[0.76158464,0.01706808,0.20638202,0.014316038,0.00019579267,0.0001735499,0.000009686608,0.000024917428,0.0002452794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99620813,0.0014850032,0.0010673671,0.0005440801,0.00007643207,0.00061901164],"domain_scores_gemma":[0.9830894,0.015975092,0.00037492454,0.00040883012,0.00005018404,0.00010155829],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049428595,0.00031259557,0.0012887395,0.0001689442,0.00005382099,0.0000020676914,0.0001762378,0.00023623931,0.000030510626],"category_scores_gemma":[0.02941776,0.00023346419,0.000077257515,0.00016182024,0.00022837333,0.00012777031,0.00012275965,0.00036796895,0.000010127239],"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":[0.000037248992,0.00014458594,0.019371614,0.000053415402,0.000044255175,0.000028187193,0.00029533225,0.000060917446,0.0001608376,0.93636245,0.013695243,0.029745916],"study_design_scores_gemma":[0.0002767082,0.00046740705,0.061904814,0.000093469615,0.000018236971,0.000026105268,0.00019464384,0.00018631891,0.00014683172,0.9357155,0.0007547453,0.00021524014],"about_ca_topic_score_codex":0.000023799073,"about_ca_topic_score_gemma":0.000035418758,"teacher_disagreement_score":0.17250979,"about_ca_system_score_codex":0.00021913498,"about_ca_system_score_gemma":0.000020055575,"threshold_uncertainty_score":0.97875786},"labels":[],"label_agreement":null},{"id":"W2005088899","doi":"10.1080/03610910801942430","title":"The Performance of Two Data-Generation Processes for Data with Specified Marginal Treatment Odds Ratios","year":2008,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","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":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Estimator; Monte Carlo method; Marginal model; Marginal structural model; Statistics; Econometrics; Marginal distribution; Marginal likelihood; Computer science; Random effects model; Observational study; Mathematics; Regression analysis; Meta-analysis; Random variable; Maximum likelihood; Medicine","score_opus":0.6337313364642472,"score_gpt":0.5459520870387204,"score_spread":0.08777924942552673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005088899","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":[0.045766957,0.00020710734,0.9527059,0.000111610425,0.000016529346,0.0007454748,0.00035080058,0.00004175267,0.000053851185],"genre_scores_gemma":[0.6094804,0.0008914462,0.38731027,0.000005717029,0.000014140867,0.000052941894,0.002219054,0.000009685086,0.000016343776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990153,0.00009779935,0.00043850197,0.00021474462,0.00013361138,0.00010008869],"domain_scores_gemma":[0.9942576,0.0036782129,0.00023493673,0.0013834225,0.0004243843,0.000021407388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003349721,0.00011705346,0.0001597668,0.00006557973,0.00043330804,0.00003751833,0.00050971063,0.00002890069,0.0000011678784],"category_scores_gemma":[0.00053943635,0.00008969694,0.000005288933,0.00020439556,0.00022696408,0.00039182603,0.00017513668,0.000066753906,3.1679082e-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":[0.0005351759,0.0010299723,0.014758394,0.00042599335,0.00013987943,0.0000013708582,0.004117918,0.25888836,0.0003341888,0.32854775,0.0010210532,0.39019993],"study_design_scores_gemma":[0.0005779005,0.00019691173,0.0011255656,0.00004492471,0.000032718683,0.0000036170488,0.000054249955,0.9838923,0.00014338312,0.013232918,0.00059272384,0.00010275824],"about_ca_topic_score_codex":0.00001528309,"about_ca_topic_score_gemma":0.000599275,"teacher_disagreement_score":0.72500396,"about_ca_system_score_codex":0.000054924505,"about_ca_system_score_gemma":0.00014397544,"threshold_uncertainty_score":0.36577353},"labels":[],"label_agreement":null},{"id":"W2006163668","doi":"10.1002/cjs.11161","title":"Effect of vitamin A deficiency on respiratory infection: Causal inference for a discretely observed continuous time non‐stationary Markov process","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Markov chain Monte Carlo; Humanities; Markov chain; Computer science; Mathematics; Algorithm; Statistics; Philosophy; Monte Carlo method","score_opus":0.07634929076482239,"score_gpt":0.3699508109128798,"score_spread":0.2936015201480574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006163668","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":[0.5829854,0.00009242406,0.41405204,0.00003056564,0.00029075364,0.000825177,0.0010266013,0.000027861486,0.00066918705],"genre_scores_gemma":[0.95178527,0.000005386384,0.04785805,0.00005683124,0.00011469711,0.000041264175,0.000016711647,0.000040443094,0.000081353035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983119,0.00015129488,0.0007053514,0.0001236358,0.0002781258,0.00042970447],"domain_scores_gemma":[0.99505866,0.0027666702,0.0007705753,0.00019083165,0.00076243014,0.00045084194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011475893,0.00022560716,0.0004962584,0.00030584293,0.00011755258,0.000028048498,0.00019711693,0.0001152989,0.00007743075],"category_scores_gemma":[0.0058827526,0.00019675742,0.00007871822,0.00020062443,0.00017447531,0.00031039419,0.000010430015,0.0002743727,0.000005045248],"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":[0.0030303076,0.0011943007,0.3246888,0.011518333,0.0007739954,0.00067024434,0.011885368,0.00063050166,0.012524688,0.40105397,0.07582574,0.15620376],"study_design_scores_gemma":[0.01491577,0.08609119,0.16548859,0.008605856,0.002994281,0.000906217,0.0011489155,0.0043854355,0.13747676,0.56375265,0.008815191,0.005419127],"about_ca_topic_score_codex":0.00016236975,"about_ca_topic_score_gemma":0.000624785,"teacher_disagreement_score":0.36879987,"about_ca_system_score_codex":0.00024293146,"about_ca_system_score_gemma":0.0009134904,"threshold_uncertainty_score":0.8023535},"labels":[],"label_agreement":null},{"id":"W2006185186","doi":"10.1080/00036840701721315","title":"The impact of the employment insurance repayment policy: nonexperimental approaches","year":2008,"lang":"en","type":"article","venue":"Applied Economics","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":true,"ca_institutions":"Ontario Ministry of Labour; Statistics Canada","funders":"","keywords":"Economics; Sample (material); Matching (statistics); Currency; Estimation; Quality (philosophy); Income Support; Percentage point; Actuarial science; Econometrics; Demographic economics; Labour economics; Statistics; Macroeconomics; Finance; Mathematics","score_opus":0.18490539785629295,"score_gpt":0.3678257837093825,"score_spread":0.18292038585308956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006185186","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":[0.98361427,0.00004081267,0.00043684186,0.00014788564,0.00003520834,0.00060710276,0.000021742244,0.0000789242,0.015017214],"genre_scores_gemma":[0.99527013,0.0001673652,0.004096598,0.000049727285,0.000061149454,0.00017953533,0.0000018900473,0.000031280655,0.00014233004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990454,0.000020072972,0.00040165524,0.00019745668,0.0000762524,0.00025919653],"domain_scores_gemma":[0.998685,0.00018968157,0.00031289275,0.0007527269,0.000014165826,0.0000455121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018834294,0.00018318502,0.00023880436,0.000027629785,0.00027568272,0.0000149318475,0.0004276997,0.000061490304,0.000010456242],"category_scores_gemma":[0.000033014247,0.000106190666,0.00016182532,0.00008436691,0.00030652925,0.00006197915,0.0001956564,0.00013028375,0.0000073165256],"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":[0.000078099976,0.0002433018,0.00490351,0.000009927277,0.00016178968,3.2812903e-7,0.0020764316,0.00096454396,0.0025456187,0.98439324,0.0013567556,0.003266461],"study_design_scores_gemma":[0.00070494355,0.00016653698,0.020585695,0.000018437639,0.0000153366,0.000041591735,0.0006361291,0.00037090905,0.2949834,0.681135,0.00087208353,0.00046993006],"about_ca_topic_score_codex":0.00010847937,"about_ca_topic_score_gemma":0.000017995188,"teacher_disagreement_score":0.3032582,"about_ca_system_score_codex":0.00043845247,"about_ca_system_score_gemma":0.00013472348,"threshold_uncertainty_score":0.433033},"labels":[],"label_agreement":null},{"id":"W2006416503","doi":"10.1016/j.ahj.2013.04.016","title":"Effects of nonpersistence with medication on outcomes in high-risk patients with cardiovascular disease","year":2013,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":62,"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; Population Health Research Institute","funders":"","keywords":"Medicine; Hazard ratio; Internal medicine; Myocardial infarction; Heart failure; Stroke (engine); Cardiology; Clinical endpoint; Diabetes mellitus; Placebo; Randomized controlled trial; Confidence interval","score_opus":0.026138853117505963,"score_gpt":0.30273977181490114,"score_spread":0.27660091869739517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006416503","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":[0.9897692,0.000028961495,0.0095372535,0.00013889831,0.000019494635,0.00044574233,0.0000028483612,0.0000344254,0.000023141676],"genre_scores_gemma":[0.96445674,0.000046300185,0.035294164,0.00009824957,0.000015688582,0.000059121565,0.0000010124181,0.00002215678,0.000006579631],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985686,0.00017198615,0.000248848,0.00016691622,0.00063295965,0.00021070403],"domain_scores_gemma":[0.99852896,0.0004898626,0.00028517967,0.00034210863,0.00017741135,0.00017649906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020223651,0.00015127157,0.000462718,0.00013137526,0.000051634222,0.000014618821,0.00012804157,0.000019436593,0.000014407869],"category_scores_gemma":[0.00048161283,0.00009323557,0.000096512005,0.00020981171,0.00023890958,0.00020095076,0.000018002842,0.00027550518,0.00000629871],"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":[0.00008331309,0.00033227674,0.98935235,0.00004548076,0.0002060083,0.000013116954,0.00015533072,0.00012887486,0.00003159889,0.00019807655,0.00009809346,0.009355477],"study_design_scores_gemma":[0.00075805344,0.0012576312,0.99253774,0.00028893378,0.00014200372,0.000004971666,0.000098377815,0.00002719414,0.00052364165,0.004179537,0.000024268065,0.0001576401],"about_ca_topic_score_codex":0.00040487212,"about_ca_topic_score_gemma":0.000007799096,"teacher_disagreement_score":0.025756909,"about_ca_system_score_codex":0.00008592885,"about_ca_system_score_gemma":0.000058132282,"threshold_uncertainty_score":0.38020363},"labels":[],"label_agreement":null},{"id":"W2007805548","doi":"10.1080/0266476032000075976","title":"Impact evaluation of job training programmes: Selection bias in multilevel models","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"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":"Regione Lombardia; Memorial University of Newfoundland","keywords":"Selection (genetic algorithm); Multilevel model; Computer science; Selection bias; Observational study; Propensity score matching; Set (abstract data type); Hierarchical database model; Random effects model; Sample (material); Sample size determination; Statistics; Econometrics; Machine learning; Data mining; Mathematics; Meta-analysis","score_opus":0.47239335593781373,"score_gpt":0.4972340829281534,"score_spread":0.02484072699033968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007805548","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":[0.18841039,0.000017615921,0.80971664,0.0000022469776,0.000031091502,0.00034746577,0.000020942369,0.000017260898,0.0014363526],"genre_scores_gemma":[0.57177025,0.0000111223335,0.42817262,0.0000032365072,0.000012710344,0.000010756978,0.0000014193629,0.000015014109,0.0000028728225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979603,0.000125605,0.00090240897,0.00010352944,0.0006941315,0.00021398765],"domain_scores_gemma":[0.9974146,0.0006059438,0.0009706573,0.000109539265,0.00083074416,0.000068528956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028832525,0.00015200366,0.00040961942,0.00026245907,0.0000263691,0.000017766588,0.00009707956,0.000094575786,0.000042750795],"category_scores_gemma":[0.0017796428,0.00012934032,0.00005573319,0.00024349432,0.00004460928,0.00015953605,0.000008027752,0.00032039086,4.894156e-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":[0.00022845977,0.000591312,0.0007777693,0.00015967974,0.00015549628,0.00000901916,0.0073890095,0.061356675,0.00722804,0.7213435,0.0006932118,0.20006779],"study_design_scores_gemma":[0.0009265413,0.00027004708,0.0005012873,0.00008589641,0.000101339865,0.000029191264,0.0007050096,0.06442361,0.0035570657,0.9292655,0.000011033098,0.00012348167],"about_ca_topic_score_codex":0.000006076107,"about_ca_topic_score_gemma":0.000025748162,"teacher_disagreement_score":0.38335988,"about_ca_system_score_codex":0.00033195675,"about_ca_system_score_gemma":0.00045939197,"threshold_uncertainty_score":0.52743447},"labels":[],"label_agreement":null},{"id":"W2010284623","doi":"10.1515/jci-2012-0003","title":"A Marginal Structural Modeling Approach with Super Learning for a Study on Oral Bisphosphonate Therapy and Atrial Fibrillation","year":2013,"lang":"en","type":"article","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Marginal structural model; Medicine; Observational study; Pharmacoepidemiology; Confounding; Inverse probability weighting; Atrial fibrillation; Protocol (science); Inverse probability; Population; Intensive care medicine; Computer science; Alternative medicine; Surgery; Propensity score matching; Medical prescription; Internal medicine; Artificial intelligence","score_opus":0.18807789415654155,"score_gpt":0.4048811529188942,"score_spread":0.21680325876235265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010284623","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":[0.80306387,0.00006488449,0.19594637,0.000048871265,0.000045784636,0.0007383899,0.000001338198,0.000044609445,0.000045877285],"genre_scores_gemma":[0.92026824,0.000047246183,0.07942032,0.000015702712,0.00016519772,0.000017033726,0.000001686858,0.000032778924,0.000031799707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845344,0.000111476824,0.00053870236,0.0002113531,0.0004184497,0.00026657106],"domain_scores_gemma":[0.9981471,0.000532428,0.0004317914,0.00014829235,0.00063349406,0.000106917076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005188686,0.0002557037,0.00047492198,0.00015731827,0.00013250874,0.00015187352,0.00014953062,0.00008985128,0.000026022459],"category_scores_gemma":[0.0004387582,0.00016736468,0.0000911239,0.00013517137,0.000058087873,0.0006949288,0.000036184923,0.000442412,8.25409e-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":[0.019111795,0.0006222495,0.2597982,0.0005212461,0.0023286166,0.00007793858,0.02758092,0.24920891,0.013372368,0.09136696,0.00035478856,0.335656],"study_design_scores_gemma":[0.009825369,0.022606151,0.013983007,0.00043437918,0.0002544736,0.00033066602,0.0047089425,0.5449274,0.0015785682,0.3999925,0.0001743752,0.0011841492],"about_ca_topic_score_codex":0.000054601092,"about_ca_topic_score_gemma":0.000007691469,"teacher_disagreement_score":0.33447185,"about_ca_system_score_codex":0.00006412476,"about_ca_system_score_gemma":0.00009497156,"threshold_uncertainty_score":0.6824933},"labels":[],"label_agreement":null},{"id":"W201096548","doi":"10.1023/a:1015777918028","title":"Guest Editorial: Revealing the spaces of urban health","year":2001,"lang":"en","type":"article","venue":"GeoJournal","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":"Queen's University; University of Calgary","funders":"","keywords":"Human geography; Geography; Economic geography","score_opus":0.13768216906553424,"score_gpt":0.42979501540699777,"score_spread":0.2921128463414635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W201096548","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":[0.49884906,0.0053652497,0.27884457,0.03551853,0.15182558,0.0028055483,0.00008310943,0.0019785825,0.024729768],"genre_scores_gemma":[0.756343,0.0017560077,0.0726143,0.0006322151,0.16645864,0.0000309871,0.0000048073375,0.00010014857,0.0020598897],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875695,0.000103656166,0.00041434547,0.00010149971,0.0003539028,0.00026964437],"domain_scores_gemma":[0.99870133,0.00033535744,0.00045188572,0.00028440903,0.0001484184,0.000078607634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012245185,0.00010864971,0.00023638396,0.000052520754,0.00015375752,0.000029267645,0.00025731497,0.000060274353,0.000044905843],"category_scores_gemma":[0.00052133214,0.00007105349,0.00006529772,0.00014515193,0.000073093055,0.00012547086,0.00005014392,0.00036439486,0.0000059189233],"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":[0.00004342019,0.00010682098,0.0025898025,0.00007250567,0.00004127456,0.0000119556435,0.0015151328,0.00001577158,0.0017913323,0.037041746,0.9545697,0.0022005662],"study_design_scores_gemma":[0.00046229476,0.0004053262,0.00041198495,0.00052028266,0.000035052843,0.00024600007,0.0012485682,0.000038774095,0.006443407,0.52303267,0.46685958,0.00029606625],"about_ca_topic_score_codex":0.00007940113,"about_ca_topic_score_gemma":0.0000315232,"teacher_disagreement_score":0.4877101,"about_ca_system_score_codex":0.000061287,"about_ca_system_score_gemma":0.00008679023,"threshold_uncertainty_score":0.28974771},"labels":[],"label_agreement":null},{"id":"W2010986175","doi":"10.1007/bf02753910","title":"Exact analysis of a paired sibling study","year":2004,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Goodness of fit; Exact test; Sibling; Monte Carlo method; Mathematics; Independence (probability theory); Statistics; Set (abstract data type); Combinatorics; Computer science; Psychology; Developmental psychology","score_opus":0.18145033049602313,"score_gpt":0.44952925693685314,"score_spread":0.26807892644083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010986175","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":[0.15251207,0.000007327293,0.84680575,0.000014456555,0.000019358788,0.00020712457,0.00019006722,0.000106815016,0.00013702462],"genre_scores_gemma":[0.5529842,9.281853e-7,0.44691205,0.000014046132,0.000006905132,0.000008520916,0.000055633478,0.000008672047,0.000009037632],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988147,0.000047194488,0.00045021327,0.00017535816,0.00038453506,0.00012801477],"domain_scores_gemma":[0.9979852,0.0012045096,0.00023983218,0.00017231527,0.0003510853,0.000047096128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023212661,0.00011895202,0.00033634566,0.0003326766,0.000058047186,0.00001663303,0.00012655658,0.000030986663,0.000066940716],"category_scores_gemma":[0.00066307536,0.00011856233,0.00005816921,0.00088441896,0.000060117938,0.000065048436,0.000044581917,0.00008376529,0.000003978224],"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":[0.000017604963,0.00081991614,0.006078957,0.00003794895,0.0008329234,0.000024577843,0.0013507344,0.27159515,0.000051398445,0.7170114,0.00020803293,0.00197138],"study_design_scores_gemma":[0.00035683712,0.00019167057,0.022658773,0.000014874079,0.00053855695,0.0000010055139,0.0002647768,0.025553718,0.000083814535,0.9502003,0.0000061311025,0.00012953077],"about_ca_topic_score_codex":0.00003839861,"about_ca_topic_score_gemma":0.0000623158,"teacher_disagreement_score":0.40047213,"about_ca_system_score_codex":0.000087748165,"about_ca_system_score_gemma":0.0000787199,"threshold_uncertainty_score":0.48348317},"labels":[],"label_agreement":null},{"id":"W2012160149","doi":"10.1016/j.healthpol.2014.10.006","title":"Inclusion of quasi-experimental studies in systematic reviews of health systems research","year":2014,"lang":"en","type":"article","venue":"Health Policy","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":100,"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":"Alliance for Health Policy and Systems Research; Wellcome Trust; World Health Organization","keywords":"Causal inference; Systematic review; Management science; Clinical study design; Research design; Quasi-experiment; Instrumental variable; Inclusion (mineral); Inference; Data science; Computer science; Regression discontinuity design; Critical appraisal; Psychology; MEDLINE; Medicine; Econometrics; Sociology; Social science; Clinical trial; Alternative medicine; Social psychology; Political science; Artificial intelligence; Machine learning; Mathematics; Engineering","score_opus":0.7361369618667926,"score_gpt":0.6844399371634319,"score_spread":0.05169702470336068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012160149","genre_codex":"review","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":[0.3015902,0.522289,0.058109388,0.029605433,0.0013952062,0.07642456,0.00010468596,0.0012509222,0.0092306],"genre_scores_gemma":[0.9870044,0.005309021,0.0067042704,0.0002820987,0.000084976215,0.0005044297,0.00000177749,0.000031647054,0.000077406294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895746,0.0060872636,0.0028245612,0.00025175544,0.00066344306,0.00059836585],"domain_scores_gemma":[0.995018,0.002396313,0.0015187133,0.00069261534,0.0002534016,0.00012096667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022121599,0.0001790217,0.0021762608,0.00066470786,0.00019829592,0.000004326366,0.00029855946,0.0000758971,0.0000029763983],"category_scores_gemma":[0.008728137,0.0001378014,0.00006855184,0.00076795096,0.00020530901,0.00008517522,0.00053530623,0.00026251638,0.000006560466],"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":[0.000012155501,0.00065582694,0.00006157906,0.36620867,0.000013938368,4.0975556e-7,0.029420348,0.0000030971635,0.00047033347,0.5999234,0.002412918,0.00081731874],"study_design_scores_gemma":[0.0020928888,0.014351378,0.00010224094,0.33508858,0.00001873271,0.000045793768,0.034917183,0.0014666708,0.009477512,0.59611017,0.005472645,0.00085621513],"about_ca_topic_score_codex":0.0053918264,"about_ca_topic_score_gemma":0.00018010242,"teacher_disagreement_score":0.6854142,"about_ca_system_score_codex":0.0011371324,"about_ca_system_score_gemma":0.0004622028,"threshold_uncertainty_score":0.99962175},"labels":[],"label_agreement":null},{"id":"W2012650559","doi":"10.1016/j.jclinepi.2009.02.001","title":"Local estimates of population attributable risk","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"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":"Statistics; Variance (accounting); Population; Attributable risk; Econometrics; Sample size determination; Mathematics; Estimation; Medicine; Environmental health; Economics","score_opus":0.5435159796539971,"score_gpt":0.6108650887029108,"score_spread":0.06734910904891367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012650559","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":[0.2324546,0.00018608985,0.7657426,0.0010959208,0.00019141319,0.00007690912,0.0000045271313,0.000035401874,0.00021251815],"genre_scores_gemma":[0.6619231,0.00031665835,0.33729106,0.00030107854,0.00014940319,4.6650447e-7,0.0000017232207,0.0000066705843,0.0000098660985],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992684,0.0016823489,0.00505648,0.00015295997,0.00015986961,0.00026435993],"domain_scores_gemma":[0.94495744,0.048233263,0.0060223215,0.00026879215,0.00036090144,0.00015730709],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019616192,0.00013988934,0.0025728263,0.00009416917,0.00002998261,0.000002145293,0.0002561671,0.00036242796,0.000058054167],"category_scores_gemma":[0.213647,0.00009929805,0.00047600016,0.00011153559,0.00019520918,0.00017154549,0.0000317794,0.0008487205,0.0000040151144],"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":[0.0004909988,0.0006039843,0.5313013,0.000051358027,0.00012811708,0.000019997917,0.000026007954,0.001750952,0.00011243811,0.28800744,0.007256716,0.17025067],"study_design_scores_gemma":[0.00033311438,0.0013219275,0.15394108,0.00009540477,0.00007391473,0.00004170064,0.00000898827,0.0020565137,0.0002685198,0.8415436,0.00024296416,0.00007226414],"about_ca_topic_score_codex":0.000025502748,"about_ca_topic_score_gemma":0.000004355796,"teacher_disagreement_score":0.5535362,"about_ca_system_score_codex":0.000038339414,"about_ca_system_score_gemma":0.000053204538,"threshold_uncertainty_score":0.7929768},"labels":[],"label_agreement":null},{"id":"W2013010700","doi":"10.1002/pds.1692","title":"Validating a method that deals with missing drug information in the Saskatchewan Drug Plan database","year":2008,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Medicine; Prostate cancer; Logistic regression; Conditional logistic regression; Warfarin; Drug; Incidence (geometry); Confidence interval; Cancer; Internal medicine; Pharmacology","score_opus":0.17595479739598152,"score_gpt":0.43304702020577746,"score_spread":0.25709222280979593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013010700","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":[0.2673676,0.0003734945,0.7188627,0.008621002,0.00010037709,0.0011960823,0.00010848811,0.00044898666,0.0029212467],"genre_scores_gemma":[0.659668,0.0003348401,0.3355228,0.0041433843,0.00006220517,0.00008578678,0.00010458618,0.000019716757,0.00005862572],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99560237,0.0026200148,0.00077107793,0.00031800743,0.00020253226,0.00048602722],"domain_scores_gemma":[0.98657817,0.012379126,0.00049438933,0.00038370246,0.000056496792,0.00010814249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00920331,0.00031157493,0.0005761275,0.00013809063,0.0004262075,0.000017897339,0.00032587358,0.00007929582,0.00004523643],"category_scores_gemma":[0.0013314135,0.00020222539,0.0000536236,0.00019139754,0.00023406322,0.0010299681,0.00012794891,0.0007451103,0.0000071739737],"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":[0.0034842598,0.0008550061,0.24737538,0.0021974074,0.0005451128,0.00051394396,0.3421989,0.0017751826,0.0051066414,0.11636393,0.14532669,0.13425754],"study_design_scores_gemma":[0.01131035,0.00022228865,0.015153725,0.0017988484,0.00078975677,0.004086516,0.077444054,0.039725386,0.09027833,0.697965,0.057053573,0.0041721393],"about_ca_topic_score_codex":0.00052992837,"about_ca_topic_score_gemma":0.00024721446,"teacher_disagreement_score":0.5816011,"about_ca_system_score_codex":0.000061949395,"about_ca_system_score_gemma":0.00009477458,"threshold_uncertainty_score":0.82465124},"labels":[],"label_agreement":null},{"id":"W2013188809","doi":"10.1023/b:ejep.0000036568.02655.f8","title":"Loss to Follow-Up in Cohort Studies: How Much is Too Much?","year":2004,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":732,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Institute for Work & Health; University of Toronto","funders":"","keywords":"Medicine; Confounding; Cohort; Logistic regression; Missing data; Cohort study; Odds; Statistics; Demography; Internal medicine; Mathematics","score_opus":0.3441335696772531,"score_gpt":0.4711298412925512,"score_spread":0.12699627161529808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013188809","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":[0.73806673,0.0011386642,0.22987571,0.026721414,0.0007697392,0.0004171177,0.000007579254,0.00011339141,0.002889652],"genre_scores_gemma":[0.7644584,0.0009640883,0.22726478,0.0062520346,0.00033733484,0.00000653146,9.494098e-7,0.00006926597,0.0006466151],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955139,0.001760663,0.0016190356,0.00033262634,0.00018811588,0.0005856175],"domain_scores_gemma":[0.9951249,0.0027840775,0.0009817587,0.0004643176,0.0004086884,0.00023629917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010253387,0.00028468572,0.0012425629,0.00031700925,0.000056182376,0.000009558556,0.00058313983,0.00007461091,0.00003650262],"category_scores_gemma":[0.035566945,0.00022360285,0.00021686341,0.00027559398,0.00019069992,0.00021105299,0.00020714983,0.0006850924,0.000066717854],"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":[0.0007762179,0.00066209876,0.09914224,0.00029989687,0.0016233533,0.0070885164,0.015957527,0.0006341856,0.0045873662,0.3639541,0.488837,0.016437517],"study_design_scores_gemma":[0.0018876665,0.0017810304,0.006773563,0.0006704708,0.00009847148,0.00069457426,0.001519997,0.0000059922186,0.0022524877,0.95995796,0.02388141,0.0004763966],"about_ca_topic_score_codex":0.000005607847,"about_ca_topic_score_gemma":0.0000151792765,"teacher_disagreement_score":0.59600383,"about_ca_system_score_codex":0.0003161662,"about_ca_system_score_gemma":0.00006776921,"threshold_uncertainty_score":0.9725569},"labels":[],"label_agreement":null},{"id":"W2013245256","doi":"10.1002/sim.3764","title":"A weighted Cox model for modelling time‐dependent exposures in the analysis of case–control studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","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; Université de Montréal","funders":"Canadian Institutes of Health Research; Health Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; McGill University","keywords":"Proportional hazards model; Computer science; Econometrics; Statistics; Mathematics","score_opus":0.14315108448926323,"score_gpt":0.4545637737110838,"score_spread":0.3114126892218206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013245256","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":[0.035001937,0.0001594189,0.96354365,0.000120534074,0.00003739513,0.0006075918,0.00039167333,0.000026925349,0.00011084135],"genre_scores_gemma":[0.61930096,0.000053643525,0.3803869,0.000046883382,0.000023145047,0.000114428956,0.00001718797,0.000011771878,0.000045069737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984654,0.000094990195,0.00071051525,0.00019837593,0.000317538,0.00021314014],"domain_scores_gemma":[0.9932083,0.005870746,0.00024434263,0.0003785898,0.00026969577,0.000028359795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020510445,0.00016138592,0.0007176003,0.00039787692,0.00004113197,0.000004371869,0.00019976062,0.00007578805,0.000025172918],"category_scores_gemma":[0.0021338623,0.00010365402,0.0000389925,0.00039935327,0.00022651536,0.000039268405,0.000022655324,0.0003103905,2.7511703e-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":[0.00022108006,0.00036733525,0.00061325356,0.0005117057,0.0015516147,0.00048462293,0.034106843,0.08013266,0.00505751,0.8714249,0.002105624,0.0034228582],"study_design_scores_gemma":[0.00043382746,0.00006550817,0.000007789007,0.0000421697,0.00061247393,0.0000067648507,0.00095185195,0.55765045,0.00009070187,0.4400775,0.0000017167464,0.000059252612],"about_ca_topic_score_codex":0.00008278547,"about_ca_topic_score_gemma":0.0021590535,"teacher_disagreement_score":0.584299,"about_ca_system_score_codex":0.00003758319,"about_ca_system_score_gemma":0.000029915978,"threshold_uncertainty_score":0.42268884},"labels":[],"label_agreement":null},{"id":"W2013850221","doi":"10.1186/1742-5573-6-5","title":"Covariate balance in a Bayesian propensity score analysis of beta blocker therapy in heart failure patients","year":2009,"lang":"en","type":"article","venue":"Epidemiologic Perspectives & Innovations","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":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto; University of British Columbia; Simon Fraser University","funders":"","keywords":"Propensity score matching; Covariate; Observational study; Confounding; Frequentist inference; Statistics; Medicine; Bayesian probability; Context (archaeology); Outcome (game theory); Econometrics; Internal medicine; Bayesian inference; Mathematics","score_opus":0.17663021973562892,"score_gpt":0.4049208873765729,"score_spread":0.22829066764094397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013850221","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":[0.96611696,0.00006454555,0.028133458,0.004311724,0.00001334997,0.00072458416,0.000030392883,0.00012781553,0.000477184],"genre_scores_gemma":[0.92935896,0.00004310782,0.06999689,0.000467498,0.0000130233975,0.00005969447,0.0000366005,0.000009542283,0.000014689046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976186,0.00040167963,0.0009627945,0.0004916084,0.00017179351,0.0003534831],"domain_scores_gemma":[0.9977852,0.00070805557,0.00046070217,0.00051387446,0.00049844844,0.000033705113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014925867,0.00024339774,0.0010100392,0.0009507842,0.000060264745,0.00000953397,0.0002531294,0.00017673353,0.00006900605],"category_scores_gemma":[0.003746811,0.00020001864,0.00012912723,0.0047432245,0.00015724353,0.0002400026,0.000045964513,0.00044190162,0.000001289187],"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":[0.000034014647,0.0005858419,0.72336817,0.0000040832856,0.00008358668,0.0000013819674,0.001012446,0.00013576237,0.0013692599,0.27280816,0.0003500445,0.00024723186],"study_design_scores_gemma":[0.00030907075,0.00017979839,0.738563,0.000041502408,0.000023369903,3.5985207e-7,0.00023596609,0.00042542286,0.00026431642,0.2597846,0.000016873086,0.0001557062],"about_ca_topic_score_codex":0.00014181054,"about_ca_topic_score_gemma":0.00029032954,"teacher_disagreement_score":0.041863438,"about_ca_system_score_codex":0.00025062758,"about_ca_system_score_gemma":0.000058457736,"threshold_uncertainty_score":0.8156523},"labels":[],"label_agreement":null},{"id":"W2013920814","doi":"10.1002/sim.4200","title":"Comparing paired vs non‐paired statistical methods of analyses when making inferences about absolute risk reductions in propensity‐score matched samples","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Confidence interval; Confounding; Sample size determination; Selection bias; Observational study; Statistical significance; Statistical inference; Matching (statistics); Causal inference; Medicine; Mathematics","score_opus":0.6053372113795614,"score_gpt":0.5275261212026646,"score_spread":0.0778110901768968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013920814","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":[0.08581615,0.00010420826,0.9114445,0.000042413696,0.00015527585,0.0005861518,0.0001259834,0.00011683779,0.0016084836],"genre_scores_gemma":[0.46800825,0.00009729292,0.53173524,0.000016605589,0.000022380967,0.00004679545,0.000027806385,0.000024464181,0.000021185142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641496,0.0006600106,0.001585777,0.00046752457,0.0004049093,0.00046682527],"domain_scores_gemma":[0.9953412,0.0029471603,0.0007358047,0.0005739904,0.0003085739,0.00009331571],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002377219,0.00034803335,0.0014254736,0.0006387852,0.00008582623,0.000014965807,0.0003881759,0.00014946693,0.00034684464],"category_scores_gemma":[0.009036527,0.00029271893,0.000038211205,0.0005980207,0.00096417224,0.00013995654,0.00017575081,0.00063786015,0.0000022637637],"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":[0.0005824228,0.0007308396,0.31245413,0.0014685509,0.000359229,0.00017041237,0.027554257,0.00010960089,0.006081633,0.61489916,0.003428724,0.032161053],"study_design_scores_gemma":[0.0005951396,0.00024546165,0.23654388,0.0012500089,0.00019832262,0.0000057135067,0.0015930324,0.004142211,0.0018935741,0.7532755,0.000015680382,0.00024148115],"about_ca_topic_score_codex":0.003637289,"about_ca_topic_score_gemma":0.0041072345,"teacher_disagreement_score":0.38219208,"about_ca_system_score_codex":0.00016392721,"about_ca_system_score_gemma":0.00013608554,"threshold_uncertainty_score":0.9999525},"labels":[],"label_agreement":null},{"id":"W2016251103","doi":"10.1016/s0895-4356(02)00571-1","title":"Neyman's bias re-visited","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Spurious relationship; Risk factor; Disease; Medicine; Statistics; Econometrics; Mathematics; Internal medicine","score_opus":0.8056101711120327,"score_gpt":0.6447404634119401,"score_spread":0.16086970770009257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016251103","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":[0.2889857,0.00061404007,0.67980427,0.0072290436,0.0020359282,0.00028063136,0.0000036039598,0.00018459365,0.020862225],"genre_scores_gemma":[0.44485205,0.0007563956,0.54870594,0.0046111643,0.0006228898,0.000003350955,6.709343e-7,0.000033697917,0.0004138468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858587,0.007167749,0.006098991,0.00024386229,0.00020258424,0.00042815765],"domain_scores_gemma":[0.88247705,0.11079612,0.00536412,0.0005094248,0.00047824855,0.00037504442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043049563,0.00019734947,0.0026106539,0.00013821138,0.00004253083,0.0000053648578,0.00037205743,0.0004992101,0.0004035269],"category_scores_gemma":[0.51281494,0.00013798241,0.00072629657,0.00017180397,0.00028188273,0.00016614058,0.000048165137,0.0014236991,0.000033085777],"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":[0.00014731236,0.0003206416,0.084723234,0.000033002296,0.00014507379,0.00009408473,0.00003664943,0.00002751508,0.000051966013,0.841876,0.06346622,0.0090783285],"study_design_scores_gemma":[0.0005461425,0.0008069121,0.004971726,0.00008201328,0.000054063676,0.00015757447,0.000037416652,0.00005747906,0.00017173584,0.94443613,0.048543848,0.00013495205],"about_ca_topic_score_codex":0.0000027128797,"about_ca_topic_score_gemma":0.0000043335276,"teacher_disagreement_score":0.4697654,"about_ca_system_score_codex":0.000040727515,"about_ca_system_score_gemma":0.00016147833,"threshold_uncertainty_score":0.98538184},"labels":[],"label_agreement":null},{"id":"W2016403661","doi":"10.1002/bimj.200810488","title":"Some Methods of Propensity‐Score Matching had Superior Performance to Others: Results of an Empirical Investigation and Monte Carlo simulations","year":2009,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":769,"is_retracted":false,"has_abstract":true,"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":"Propensity score matching; Statistics; Monte Carlo method; Matching (statistics); Standard deviation; Logit; Mathematics; Medicine","score_opus":0.37447359939304903,"score_gpt":0.48375300248447506,"score_spread":0.10927940309142603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016403661","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":[0.9511,0.00007823835,0.048140716,0.00034273934,0.000029369208,0.00022716327,0.000015217617,0.00004474408,0.000021845417],"genre_scores_gemma":[0.6206691,0.00001876545,0.37916532,0.000076516946,0.000050133494,0.0000010399029,7.8986244e-7,0.00000890998,0.000009400995],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99829465,0.00021467906,0.00074751524,0.00018624612,0.0003594303,0.00019745127],"domain_scores_gemma":[0.99835426,0.0005239095,0.0003485568,0.00022515435,0.000304389,0.0002437187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011439275,0.00014417522,0.00040331596,0.0010166683,0.000091204245,0.000043681404,0.00018575737,0.00011153638,0.0000039763354],"category_scores_gemma":[0.0022745668,0.00011268503,0.00005423292,0.0015001368,0.000096862736,0.00061401905,0.000051417403,0.00026134923,3.7687047e-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":[0.00076750736,0.0007556958,0.022810273,0.0001920886,0.000090583744,0.00002144319,0.007186863,0.0014939723,0.6800453,0.0020943664,0.00033605428,0.28420582],"study_design_scores_gemma":[0.0019506894,0.0062738457,0.2810068,0.0007031971,0.00013854646,0.00024567396,0.00039503546,0.013465012,0.4268679,0.2680264,0.00021318962,0.0007136629],"about_ca_topic_score_codex":0.000012974057,"about_ca_topic_score_gemma":0.0000016740667,"teacher_disagreement_score":0.33102462,"about_ca_system_score_codex":0.00007911846,"about_ca_system_score_gemma":0.000061107035,"threshold_uncertainty_score":0.45951623},"labels":[],"label_agreement":null},{"id":"W2017135084","doi":"10.1016/j.prevetmed.2013.09.006","title":"Making valid causal inferences from observational data","year":2013,"lang":"en","type":"review","venue":"Preventive Veterinary Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"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 Guelph","funders":"","keywords":"Counterfactual thinking; Causal inference; Observational study; Confounding; Causation; Causal model; Outcome (game theory); Propensity score matching; Causality (physics); Econometrics; Marginal structural model; Randomized experiment; Psychology; Computer science; Statistics; Mathematics; Social psychology; Epistemology","score_opus":0.8719276078117765,"score_gpt":0.607940885409455,"score_spread":0.26398672240232146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017135084","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":[0.000052325013,0.9703467,0.024626099,0.000084575484,0.00059918594,0.0018000668,0.00074999756,0.00042519742,0.0013158664],"genre_scores_gemma":[0.000038019476,0.9080792,0.08584064,0.000054469234,0.0009883676,0.0005311979,0.0036292584,0.00011886367,0.00071998587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99542654,0.00083931006,0.001499699,0.0010923803,0.00068376,0.00045834258],"domain_scores_gemma":[0.9920659,0.0042430814,0.0013326168,0.0020307656,0.00019773166,0.00012987305],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010018804,0.00085177657,0.0027132554,0.0002656705,0.00011318903,0.000043552995,0.0020487073,0.00040130437,0.0033478069],"category_scores_gemma":[0.0027154107,0.00061580754,0.00018961272,0.0003760877,0.00034838525,0.00070796284,0.0018594518,0.0007975034,0.00013595539],"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":[0.000010154141,0.00012387316,0.000015566953,0.009797859,0.0005665826,0.00012721382,0.00018617565,2.9166547e-8,0.000025833613,0.009158562,0.015416836,0.9645713],"study_design_scores_gemma":[0.00014937308,0.00042996163,0.000017827377,0.046516135,0.0010561489,0.000074108735,0.000047466292,0.000020770678,0.0000014822865,0.1632192,0.78790003,0.0005674964],"about_ca_topic_score_codex":0.00008798804,"about_ca_topic_score_gemma":0.0000068095437,"teacher_disagreement_score":0.9640038,"about_ca_system_score_codex":0.00018028702,"about_ca_system_score_gemma":0.000257124,"threshold_uncertainty_score":0.9996293},"labels":[],"label_agreement":null},{"id":"W2017582953","doi":"10.3109/13693786.2011.635387","title":"Comment on the paper by Kpodzo<i>et al.</i>","year":2012,"lang":"en","type":"letter","venue":"Medical Mycology","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":"University of Alberta","funders":"","keywords":"MEDLINE; Political science; Law","score_opus":0.10164081757898306,"score_gpt":0.3981729930860049,"score_spread":0.2965321755070218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017582953","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":[0.000022865755,0.00012459588,0.003944523,0.98151356,0.00061763905,0.00057614245,0.000053766893,0.00033185814,0.01281507],"genre_scores_gemma":[0.0001677683,0.0002502538,0.0018438887,0.9947284,0.0009470514,0.0005473533,0.00016482225,0.00009387688,0.0012565928],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640244,0.00090284506,0.00052504236,0.000399078,0.0009904685,0.00078009575],"domain_scores_gemma":[0.98883384,0.009802399,0.0002644955,0.0008884836,0.000053591706,0.00015721303],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0014863441,0.0004337946,0.00068111677,0.00006007937,0.000092099624,0.000016447615,0.00094215106,0.0013389507,0.014240268],"category_scores_gemma":[0.0030543483,0.00025798197,0.00013601923,0.00008638786,0.00047638797,0.000051259874,0.00032775398,0.005196111,0.0004933312],"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":[0.0000057487496,0.000120430464,0.0000036441463,0.000031744446,0.000049051778,0.000098004915,0.000042698255,3.711598e-9,0.00003859141,0.050438628,0.94849443,0.00067701325],"study_design_scores_gemma":[0.00013460225,0.00018580539,0.0000010915708,0.00009482787,0.000036695532,0.000032925484,0.0000066435787,0.0000018131309,0.0001423317,0.13460274,0.86452156,0.00023895316],"about_ca_topic_score_codex":0.000019427956,"about_ca_topic_score_gemma":0.00000653304,"teacher_disagreement_score":0.08416411,"about_ca_system_score_codex":0.00015660792,"about_ca_system_score_gemma":0.00009412709,"threshold_uncertainty_score":0.99998724},"labels":[],"label_agreement":null},{"id":"W2018472295","doi":"10.1007/s12561-013-9103-z","title":"Q-Learning: Flexible Learning About Useful Utilities","year":2013,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":110,"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","funders":"","keywords":"Observational study; Machine learning; Biostatistics; Computer science; Covariate; Linear model; Artificial intelligence; Econometrics; Mathematical optimization; Mathematics; Statistics; Medicine","score_opus":0.1224448115109042,"score_gpt":0.40824360456375525,"score_spread":0.28579879305285105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018472295","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":[0.46557373,0.00020748773,0.47646892,0.00030928355,0.0005605749,0.0010395537,0.000058150483,0.001892074,0.053890217],"genre_scores_gemma":[0.7288471,0.00014434413,0.2654428,0.00004480861,0.000027035383,0.00006616394,0.0000051601814,0.000017811608,0.0054048058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99821925,0.00012895413,0.00040491534,0.00034441098,0.0004105313,0.00049196085],"domain_scores_gemma":[0.9981221,0.0012484844,0.00018505,0.00019713416,0.00015907476,0.00008814776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046240893,0.00018834823,0.0002515057,0.00020802488,0.00022471575,0.00017042684,0.0003769468,0.00008348388,0.000736755],"category_scores_gemma":[0.0037929725,0.00016327619,0.0000250266,0.0004442045,0.0006029133,0.0004051474,0.00012464696,0.00044204723,0.000102134385],"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":[0.000005126725,0.00009315108,0.055582155,0.000115339506,0.000006497476,0.00001070485,0.0030808754,0.000103320024,0.0019193965,0.9150398,0.0041896687,0.019853987],"study_design_scores_gemma":[0.00009527897,0.00026067483,0.0100502195,0.00008440084,0.0000045694323,0.0000036479778,0.0038822666,0.0036663988,0.003100653,0.9755664,0.0030016045,0.00028391607],"about_ca_topic_score_codex":0.00020685639,"about_ca_topic_score_gemma":0.00008362322,"teacher_disagreement_score":0.26327336,"about_ca_system_score_codex":0.0000708594,"about_ca_system_score_gemma":0.00007693613,"threshold_uncertainty_score":0.8066951},"labels":[],"label_agreement":null},{"id":"W2019126071","doi":"10.1007/s10260-012-0193-4","title":"Assessing the effect of the amount of financial aids to Piedmont firms using the generalized propensity score","year":2012,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for International Peace and Security","funders":"Regione Piemonte; European Commission","keywords":"Propensity score matching; Business; Economics; Econometrics; Internal medicine; Medicine","score_opus":0.27944644578738637,"score_gpt":0.5413451885789704,"score_spread":0.26189874279158404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019126071","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":[0.11620154,0.00004172056,0.8813734,0.00012692685,0.00005247298,0.0019000224,0.000054678672,0.000039206217,0.00021000499],"genre_scores_gemma":[0.39185235,0.0000011482297,0.6075877,0.00005735282,0.000055404646,0.00042043344,0.0000015385249,0.000015338675,0.000008739831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974188,0.0013245494,0.0004929359,0.00018704215,0.0002889428,0.00028771927],"domain_scores_gemma":[0.99234664,0.006197714,0.0003195162,0.0008972715,0.00016532172,0.000073533134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031020623,0.00017505907,0.00039553607,0.000029269564,0.00031872594,0.000029260571,0.00048571927,0.00007483775,0.000026823387],"category_scores_gemma":[0.004897626,0.000078912955,0.0000903351,0.00046479946,0.00046944342,0.00009971316,0.0002710446,0.00028470036,0.0000015223326],"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":[0.000018625888,0.00007464115,0.0027735685,0.00010593517,0.000021376094,8.446116e-8,0.00033163946,0.000025945694,0.06206144,0.85430026,0.0001704454,0.08011604],"study_design_scores_gemma":[0.0002172106,0.00017185001,0.035627797,0.0001195378,0.00044244944,0.000009592594,0.00008103275,0.00096053135,0.27924454,0.68110293,0.0017711329,0.00025140846],"about_ca_topic_score_codex":0.00009243765,"about_ca_topic_score_gemma":0.000009775205,"teacher_disagreement_score":0.2756508,"about_ca_system_score_codex":0.00007545913,"about_ca_system_score_gemma":0.00007363139,"threshold_uncertainty_score":0.58632696},"labels":[],"label_agreement":null},{"id":"W2020018188","doi":"10.1002/oby.20666","title":"Selection bias: A missing factor in the obesity paradox debate","year":2013,"lang":"en","type":"letter","venue":"Obesity","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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 Cancer Institute","keywords":"Obesity paradox; Obesity; Selection bias; Disease; Population; Risk factor; Medicine; Selection (genetic algorithm); Outcome (game theory); Demography; Internal medicine; Economics; Environmental health; Pathology","score_opus":0.17870836129354653,"score_gpt":0.3700703666514758,"score_spread":0.19136200535792927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020018188","genre_codex":"empirical","genre_gemma":"commentary","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":[0.61067194,0.00023532323,0.076739624,0.29451877,0.00073001435,0.005930165,0.00013278208,0.0028926437,0.008148751],"genre_scores_gemma":[0.4045992,0.00020347448,0.09216371,0.49088696,0.0051560234,0.0008960952,0.00027377487,0.0004801215,0.0053406563],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974612,0.00043507045,0.0004915118,0.0005070772,0.00052103197,0.00058412034],"domain_scores_gemma":[0.9976657,0.0010286163,0.00041436788,0.00072217773,0.00012577503,0.000043363652],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00053270214,0.00048657128,0.0006090566,0.00018155001,0.00019123932,0.00016859965,0.0006500168,0.0009674308,0.00039135877],"category_scores_gemma":[0.00072114513,0.0003517163,0.00016520097,0.0003309429,0.00008868619,0.0002972595,0.00010345792,0.0027400404,0.00014027116],"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":[0.0000038803873,0.00015802051,0.0077971537,0.00037506048,0.000028927678,0.0001257199,0.0006836016,3.886485e-7,0.00025014585,0.00084122556,0.98844534,0.0012905637],"study_design_scores_gemma":[0.00031150092,0.00015953806,0.012484699,0.0007899524,0.00013645612,0.0001444618,0.00011587332,0.00027342877,0.005386368,0.83324975,0.14545946,0.001488507],"about_ca_topic_score_codex":0.00029300322,"about_ca_topic_score_gemma":0.00013929943,"teacher_disagreement_score":0.84298587,"about_ca_system_score_codex":0.00034670962,"about_ca_system_score_gemma":0.0000824145,"threshold_uncertainty_score":0.9998935},"labels":[],"label_agreement":null},{"id":"W2020811073","doi":"10.1093/aje/kwh266","title":"Bias due to Aggregation of Individual Covariates in the Cox Regression Model","year":2004,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":30,"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":"Covariate; Censoring (clinical trials); Statistics; Proportional hazards model; Econometrics; Confidence interval; Regression; Regression analysis; Linear regression; Mathematics","score_opus":0.25939609129629715,"score_gpt":0.4621107514322537,"score_spread":0.20271466013595657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020811073","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":[0.5270107,0.000064364634,0.4699028,0.0027986807,0.000027519673,0.00010997533,0.0000042802653,0.000010349572,0.00007131347],"genre_scores_gemma":[0.6456327,0.000057151967,0.3531476,0.001117136,0.000029123852,0.0000053379295,0.0000010167065,0.000007933276,0.0000020527348],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99742585,0.0009328912,0.0010978809,0.00012167426,0.00018667146,0.00023503957],"domain_scores_gemma":[0.9919924,0.0057822852,0.0017400333,0.00024975179,0.00016849578,0.000067029396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0060788346,0.0001291573,0.000783032,0.00023840393,0.000026505713,0.0000029773016,0.0004499837,0.00006662662,0.0000053443364],"category_scores_gemma":[0.016643569,0.00007590274,0.000094818395,0.0003508798,0.00029189562,0.0001096265,0.000053786443,0.00036247884,0.000001148564],"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":[0.0005151817,0.0004913672,0.0123097375,0.000045970697,0.0001234017,0.000099079705,0.012946179,0.058560245,0.0031554387,0.82739866,0.0029943848,0.08136037],"study_design_scores_gemma":[0.00026635165,0.0011419525,0.0024048642,0.0002865548,0.000027380393,0.00022493678,0.00092864776,0.00032420296,0.0016560983,0.9926086,0.00004005065,0.00009034212],"about_ca_topic_score_codex":0.000108049884,"about_ca_topic_score_gemma":0.000034754103,"teacher_disagreement_score":0.16520998,"about_ca_system_score_codex":0.000079448655,"about_ca_system_score_gemma":0.00011428928,"threshold_uncertainty_score":0.9916397},"labels":[],"label_agreement":null},{"id":"W2020907145","doi":"10.1007/s10985-013-9255-7","title":"On computing standard errors for marginal structural Cox models","year":2013,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Social Innovation; General Dynamics (Canada); Ottawa Public Health; University of Guelph","funders":"H2020 Marie Skłodowska-Curie Actions; Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal structural model; Weighting; Standard error; Computer science; Parametric statistics; Marginal model; Econometrics; Parametric model; Confidence interval; Statistics; Marginal likelihood; Algorithm; Mathematics; Regression analysis; Maximum likelihood","score_opus":0.1554158125401682,"score_gpt":0.4239885117570113,"score_spread":0.2685726992168431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020907145","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":[0.04771526,0.000015863969,0.9490728,0.00022821795,0.000028121287,0.0004880672,0.0016901938,0.0002973598,0.0004641234],"genre_scores_gemma":[0.57892454,0.0000032853436,0.41914514,0.00014019068,0.00005494251,0.000025381705,0.001493203,0.000028795015,0.00018455499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981641,0.000066526576,0.00046017033,0.0005557106,0.00037758407,0.0003758659],"domain_scores_gemma":[0.997022,0.0008152579,0.0002606971,0.0015863505,0.00020017999,0.000115529474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042671754,0.00024800276,0.00058528245,0.00026451168,0.00015959893,0.000112364025,0.0008569633,0.000093089366,0.00063040765],"category_scores_gemma":[0.0004992625,0.00020991232,0.00016257218,0.00051256624,0.00007228486,0.00061529747,0.00032513682,0.00017399041,0.00003089838],"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":[0.00043900163,0.0002353964,0.0020721809,0.00038748156,0.0073708515,0.000017604056,0.001009443,0.04656201,0.0008512178,0.69285923,0.21693839,0.03125719],"study_design_scores_gemma":[0.00016805515,0.00007505686,0.0000745229,0.000020109735,0.0006614617,0.0000010290821,0.00006874226,0.56014615,0.00021567072,0.43815437,0.00019485538,0.00021997603],"about_ca_topic_score_codex":0.00012002283,"about_ca_topic_score_gemma":0.0000462049,"teacher_disagreement_score":0.5312093,"about_ca_system_score_codex":0.00007308125,"about_ca_system_score_gemma":0.00002911305,"threshold_uncertainty_score":0.8559976},"labels":[],"label_agreement":null},{"id":"W2021261432","doi":"10.1016/j.jclinepi.2009.05.009","title":"Survivor treatment bias, treatment selection bias, and propensity scores in observational research","year":2010,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":63,"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; Institute for Clinical Evaluative Sciences; University of Toronto; Public Health Ontario","funders":"","keywords":"Selection bias; Observational study; Scopus; Publication bias; Medicine; Propensity score matching; Meta-analysis; MEDLINE; Internal medicine; Pathology; Political science","score_opus":0.93795884518816,"score_gpt":0.6625431311432628,"score_spread":0.2754157140448972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021261432","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5128471,0.00044519815,0.0022059774,0.4818241,0.0010878186,0.0012831326,0.0000389076,0.00006908672,0.00019866884],"genre_scores_gemma":[0.046658788,0.03630591,0.58188516,0.28716853,0.03944389,0.00054125336,0.00028150552,0.00045319204,0.0072617945],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9765385,0.015450613,0.0060506947,0.0006681685,0.0005233266,0.0007687001],"domain_scores_gemma":[0.83954954,0.15472998,0.0040845186,0.00044762928,0.0009871267,0.00020121073],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.039897334,0.0004741004,0.004654179,0.00057156547,0.000106800166,0.000024521401,0.00035728342,0.0035329608,0.00008654641],"category_scores_gemma":[0.16035749,0.00029795986,0.0005822533,0.0002689703,0.00072445034,0.00018796796,0.000110326895,0.008885572,0.000008843288],"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":[0.0005393961,0.00086770667,0.6350773,0.00013932536,0.0003665584,0.0004352402,0.000065566535,0.000009104787,0.000037629765,0.0054261517,0.33021122,0.026824811],"study_design_scores_gemma":[0.0015363224,0.007639513,0.11784295,0.0004436018,0.00014227904,0.00034720148,0.000009738625,0.00017319908,0.00010730094,0.5637218,0.30767804,0.00035806312],"about_ca_topic_score_codex":0.0008331089,"about_ca_topic_score_gemma":0.0023462242,"teacher_disagreement_score":0.57967913,"about_ca_system_score_codex":0.00059433235,"about_ca_system_score_gemma":0.0010142706,"threshold_uncertainty_score":0.99994725},"labels":[],"label_agreement":null},{"id":"W2021583648","doi":"10.2202/1557-4679.1208","title":"Accuracy of Conventional and Marginal Structural Cox Model Estimators: A Simulation Study","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Gas Technologies Centre; Montreal General Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Marginal structural model; Proportional hazards model; Estimator; Statistics; Inverse probability weighting; Weighting; Logistic regression; Marginal model; Confounding; Econometrics; Inverse probability; Mathematics; Censoring (clinical trials); Accelerated failure time model; Regression analysis; Computer science; Medicine; Bayesian probability","score_opus":0.0926583015508293,"score_gpt":0.4578373595405563,"score_spread":0.36517905798972705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021583648","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":[0.7312929,0.0000114315035,0.2679836,0.00020065991,0.00024103562,0.00013877044,0.00008510212,0.000011135016,0.00003537984],"genre_scores_gemma":[0.83878016,0.000006968003,0.16107027,0.000025669378,0.000086098255,0.0000014276062,0.0000033670622,0.000009862305,0.000016151609],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862456,0.000039744922,0.00058074214,0.00007640163,0.0005956194,0.00008295184],"domain_scores_gemma":[0.9962986,0.0016890004,0.00088683463,0.00012604648,0.0009554895,0.00004404133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052072096,0.00010815773,0.00018685819,0.00010906661,0.000045188797,0.000043926604,0.0003747026,0.00003884162,0.00005613436],"category_scores_gemma":[0.0023607847,0.00007471787,0.000044305038,0.000046645982,0.0001646045,0.00020613176,0.00008778385,0.0003043994,5.7503263e-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":[0.0009070318,0.00065424474,0.013304765,0.0000664368,0.0006579107,0.00009074701,0.0027258398,0.01281476,0.031735625,0.92040676,0.0012616826,0.015374201],"study_design_scores_gemma":[0.00072652794,0.00021442979,0.0035517325,0.00004904902,0.00008031103,0.00017353139,0.00024488728,0.2178113,0.0021299247,0.7748844,0.000034385168,0.00009953464],"about_ca_topic_score_codex":0.0000077276545,"about_ca_topic_score_gemma":0.000013670024,"teacher_disagreement_score":0.20499654,"about_ca_system_score_codex":0.000029815252,"about_ca_system_score_gemma":0.00010263148,"threshold_uncertainty_score":0.30469063},"labels":[],"label_agreement":null},{"id":"W2021688446","doi":"10.1046/j.0039-0402.2003.00254.x","title":"Regressor and random‐effects dependencies in multilevel models","year":2004,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":81,"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":"Independence (probability theory); Econometrics; Monte Carlo method; Random effects model; Computer science; Multilevel model; Statistics; Machine learning; Mathematics; Meta-analysis","score_opus":0.10038898709520844,"score_gpt":0.38229869015186063,"score_spread":0.2819097030566522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021688446","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":[0.034069546,0.0001632987,0.96289986,0.00011075007,0.00004017888,0.00057071587,0.00006495076,0.00023438605,0.0018463166],"genre_scores_gemma":[0.70985496,0.00008611683,0.28979754,0.00004756894,0.000013145764,0.000096953736,0.000006081285,0.000024127108,0.00007350954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987746,0.00005761185,0.00030803608,0.00028061066,0.00024593266,0.0003332294],"domain_scores_gemma":[0.9980872,0.0014324615,0.00009278905,0.00023507525,0.00004144188,0.0001109899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025528314,0.0002023841,0.00036928224,0.00014026205,0.00006148356,0.0000312975,0.00012669998,0.00010273435,0.000023277451],"category_scores_gemma":[0.001438441,0.00017195052,0.000024987812,0.000102497186,0.00014750924,0.00018556262,0.000065636195,0.00023143122,0.000007999388],"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":[0.00013363097,0.00011771403,0.00013155528,0.00024549893,0.000020806363,0.00022312684,0.0014712906,0.000096062584,0.0010825746,0.98813325,0.00041480325,0.007929683],"study_design_scores_gemma":[0.0025682144,0.00011115998,0.0006379302,0.00022284384,0.000021731,0.000024920979,0.000051334373,0.002276406,0.002364627,0.9914722,0.000032476455,0.00021617013],"about_ca_topic_score_codex":0.00009434405,"about_ca_topic_score_gemma":0.00016741388,"teacher_disagreement_score":0.6757854,"about_ca_system_score_codex":0.00008208274,"about_ca_system_score_gemma":0.00005395233,"threshold_uncertainty_score":0.70119387},"labels":[],"label_agreement":null},{"id":"W2021792499","doi":"10.1016/j.jval.2014.03.1130","title":"The inherent bias from using partitioned survival models in economic evaluation","year":2014,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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 Lethbridge; University of Ottawa","funders":"","keywords":"Survival analysis; Clinical trial; Markov model; Medicine; Randomized controlled trial; Progression-free survival; Markov chain; Overall survival; Statistics; Oncology; Internal medicine; Mathematics","score_opus":0.659809391040091,"score_gpt":0.4838394291682127,"score_spread":0.17596996187187824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021792499","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":[0.9032632,0.00015632705,0.09425202,0.000601588,0.00023741605,0.0008367977,0.00000998983,0.00008642672,0.0005562523],"genre_scores_gemma":[0.98079264,0.00011746749,0.018831493,0.00006482278,0.00007166897,0.00008867445,0.0000084502,0.000020365069,0.0000044263948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975692,0.0010725181,0.0006430996,0.00021725977,0.00021470523,0.0002832049],"domain_scores_gemma":[0.9977784,0.0015266382,0.00026085068,0.0003475578,0.000036039924,0.00005051854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045220363,0.00011328184,0.0002407303,0.00008218908,0.00008870357,0.000028688508,0.00013812602,0.00006485141,0.000022324573],"category_scores_gemma":[0.0004938836,0.00009474047,0.00002722952,0.00009373007,0.000034829965,0.00017563548,0.00004006315,0.00017958188,0.000008862351],"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":[0.000029144345,0.000085842395,0.0025443668,0.000050419087,0.0000067711976,4.0232635e-7,0.0012228097,0.43762007,0.000077549164,0.54616493,0.00010257732,0.012095127],"study_design_scores_gemma":[0.00016187255,0.000021432861,0.00029383224,0.00008775027,0.0000017404993,1.7466138e-7,0.000077284174,0.48002997,0.00009145158,0.5191428,0.00004073249,0.000050927196],"about_ca_topic_score_codex":0.009182096,"about_ca_topic_score_gemma":0.003958184,"teacher_disagreement_score":0.077529445,"about_ca_system_score_codex":0.0009843702,"about_ca_system_score_gemma":0.0002592042,"threshold_uncertainty_score":0.99741584},"labels":[],"label_agreement":null},{"id":"W2024255505","doi":"10.6000/1929-6029.2014.03.02.13","title":"Adjusting Complex Heterogeneity in Treatment Assignment in Observational Studies","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Pfizer","keywords":"Propensity score matching; Observational study; Estimator; Statistics; Cluster analysis; Weighting; Inverse probability weighting; Regression; Econometrics; Partial least squares regression; Inverse probability; Regression analysis; Mathematics; Computer science; Medicine","score_opus":0.7635707781039781,"score_gpt":0.6555082445573583,"score_spread":0.10806253354661977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024255505","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":[0.6347613,0.00021962251,0.35817456,0.004954755,0.00043721637,0.0003885147,0.000059958467,0.000017272476,0.0009868459],"genre_scores_gemma":[0.8926734,0.0007394211,0.106243916,0.000103495666,0.00016879918,0.00002733792,0.0000082934475,0.000011770275,0.000023615657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948455,0.00066866516,0.0011328696,0.00016600385,0.0028719564,0.00031498715],"domain_scores_gemma":[0.98713833,0.011338528,0.00024351772,0.00011171626,0.0010408072,0.00012712376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007290449,0.00011835901,0.00038415866,0.00066194613,0.00002581919,0.000026704063,0.00054317736,0.00008534286,0.00016551286],"category_scores_gemma":[0.038355704,0.00009630746,0.00003426992,0.00024208956,0.00024110057,0.00011985182,0.00017786844,0.00075594493,0.0000034002053],"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":[0.00036208832,0.0019287919,0.12205632,0.00012020875,0.00017667751,0.0023989102,0.0018375985,0.0007980427,0.0007554815,0.589209,0.0029312684,0.2774256],"study_design_scores_gemma":[0.002047148,0.0005582892,0.056885358,0.0011372283,0.0000045459465,0.000055739467,0.0005968173,0.014919173,0.0005618273,0.9219312,0.0011676238,0.0001350499],"about_ca_topic_score_codex":0.00007995791,"about_ca_topic_score_gemma":0.0016790217,"teacher_disagreement_score":0.33272216,"about_ca_system_score_codex":0.0017326506,"about_ca_system_score_gemma":0.00032242248,"threshold_uncertainty_score":0.9697446},"labels":[],"label_agreement":null},{"id":"W2024692342","doi":"10.1016/j.jeconom.2003.10.006","title":"How robust is the evidence on the effects of college quality? Evidence from matching","year":2004,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":690,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Propensity score matching; Matching (statistics); Regression; Quality (philosophy); Linear regression; Econometrics; Statistics; Average treatment effect; Regression analysis; Mathematics","score_opus":0.49673908869137284,"score_gpt":0.40482836758179297,"score_spread":0.09191072110957987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024692342","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":[0.85597044,0.0029664543,0.1287681,0.011376006,0.00031714537,0.00042404849,0.000016765736,0.000025592728,0.00013545228],"genre_scores_gemma":[0.9658851,0.0018281012,0.03148984,0.0005393606,0.0001461765,0.000008507458,9.38438e-8,0.000021741282,0.00008107806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981328,0.00021291627,0.0007965499,0.00016353554,0.0004892945,0.00020488212],"domain_scores_gemma":[0.9650238,0.03218746,0.0017863453,0.00060187484,0.00032587908,0.00007462104],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026335819,0.00018790878,0.0005086945,0.0003634958,0.00011508419,0.00010694869,0.00095651485,0.000094846255,0.00003520352],"category_scores_gemma":[0.032482896,0.00010336123,0.00024293936,0.0009733664,0.000120473276,0.00088413537,0.00011459352,0.0005768527,0.000004991183],"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":[0.00048606566,0.0011290377,0.0074037835,0.0018575991,0.0010364223,0.00017686027,0.013297602,0.0021247629,0.021400608,0.92381096,0.014809895,0.012466407],"study_design_scores_gemma":[0.0003322153,0.00078814017,0.0033279224,0.0039751763,0.000115703486,0.00002312917,0.0012459119,0.000021914357,0.078893885,0.91092384,0.00013748172,0.00021468157],"about_ca_topic_score_codex":0.0000471716,"about_ca_topic_score_gemma":0.000013720338,"teacher_disagreement_score":0.10991467,"about_ca_system_score_codex":0.000315695,"about_ca_system_score_gemma":0.00013534226,"threshold_uncertainty_score":0.9756669},"labels":[],"label_agreement":null},{"id":"W2024981049","doi":"10.1093/jnci/djk189","title":"Statisticians Set Sights on Observational Studies","year":2007,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"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":"Observational study; Checklist; Strengthening the reporting of observational studies in epidemiology; Set (abstract data type); Quality (philosophy); Research design; Clinical study design; Reliability (semiconductor); Randomized controlled trial; Computer science; Medical physics; Medicine; Medical education; Psychology; Statistics; Clinical trial; Mathematics; Pathology; Cognitive psychology; Epistemology","score_opus":0.6932597929031257,"score_gpt":0.5775303768137539,"score_spread":0.11572941608937182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024981049","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":[0.6809903,0.0013976617,0.2582332,0.019529164,0.015765607,0.0012993151,0.0008359704,0.0002485156,0.021700311],"genre_scores_gemma":[0.9379287,0.00014681951,0.055298258,0.0034176442,0.0020485802,0.000015555835,0.0000037883904,0.000024802566,0.0011158503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978403,0.00004114952,0.00062382256,0.000102963124,0.0012234069,0.00016835271],"domain_scores_gemma":[0.99632293,0.0010677396,0.000729521,0.00009819426,0.0017271859,0.000054454482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011060112,0.00014187909,0.00024207961,0.00018671827,0.0001846411,0.000018047185,0.00036398834,0.000057675268,0.000038996477],"category_scores_gemma":[0.0032228567,0.000088795176,0.0001096775,0.0003277654,0.00017439855,0.0003882801,0.000050233426,0.00034981864,0.0000036580905],"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":[0.000121690726,0.00008043816,0.0006039706,0.000036906535,0.00020255795,0.000016884638,0.00045663936,0.0016701444,0.0010941001,0.9297002,0.06452316,0.00149328],"study_design_scores_gemma":[0.0003662449,0.00009884887,0.0054664686,0.00032033684,0.000050919356,0.00004617055,0.00006949085,0.00003375086,0.009291888,0.9398518,0.044259872,0.00014418525],"about_ca_topic_score_codex":0.0000051311404,"about_ca_topic_score_gemma":0.00019183359,"teacher_disagreement_score":0.25693843,"about_ca_system_score_codex":0.0008940214,"about_ca_system_score_gemma":0.00041503325,"threshold_uncertainty_score":0.38582933},"labels":[],"label_agreement":null},{"id":"W2026576563","doi":"10.5301/jn.2011.6429","title":"Propensity score methods and their application in nephrology research","year":2011,"lang":"en","type":"article","venue":"Journal of Nephrology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Calgary","funders":"","keywords":"Propensity score matching; Medicine; Covariate; Observational study; Internal medicine; Selection bias; Matching (statistics); Statistics; Mathematics; Pathology","score_opus":0.5116448045137748,"score_gpt":0.5133853228660754,"score_spread":0.0017405183523006018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026576563","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":[0.8277553,0.0001723187,0.17034888,0.00052014965,0.000030161636,0.0002911224,5.029511e-7,0.000024001873,0.0008575676],"genre_scores_gemma":[0.75360954,0.00012467739,0.24569014,0.00045035002,0.00007445618,0.000020467192,2.1423695e-7,0.000015522792,0.000014632555],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796665,0.0009422197,0.0005182417,0.00016687266,0.000109095614,0.00029692412],"domain_scores_gemma":[0.99801177,0.00093660824,0.00033855689,0.00026066208,0.00037789028,0.000074538984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004404819,0.00011604175,0.0004376441,0.0003901571,0.00004872655,0.0000066732964,0.00027557547,0.00021653372,0.000034383353],"category_scores_gemma":[0.0006345057,0.00008297958,0.000039578477,0.00023904281,0.000362284,0.0001841708,0.00015706314,0.00082230335,0.0000026290652],"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":[0.0015514873,0.0006942029,0.023029385,0.00010778374,0.00012663136,0.00016822001,0.0078848805,0.0000018161265,0.50419354,0.3171984,0.003664351,0.14137933],"study_design_scores_gemma":[0.00030279584,0.00080659974,0.022137793,0.000017520906,0.000009675369,0.00056199776,0.00014150234,0.00007529016,0.014836974,0.95667315,0.004356808,0.0000798761],"about_ca_topic_score_codex":0.000045467765,"about_ca_topic_score_gemma":0.0001514305,"teacher_disagreement_score":0.63947475,"about_ca_system_score_codex":0.00006077468,"about_ca_system_score_gemma":0.00007185798,"threshold_uncertainty_score":0.35725448},"labels":[],"label_agreement":null},{"id":"W2026656096","doi":"10.1136/bmj.b5087","title":"Problem of immortal time bias in cohort studies: example using statins for preventing progression of diabetes","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1155,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Kingston Health Sciences Centre; McGill University; Queen's University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Diabetes mellitus; Cohort; Internal medicine; Endocrinology","score_opus":0.2976455350419575,"score_gpt":0.5009101891130961,"score_spread":0.20326465407113864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026656096","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":[0.9950122,0.000030718802,0.0028739457,0.000012230299,0.000023641436,0.001833592,0.000014713376,0.000057603724,0.00014131698],"genre_scores_gemma":[0.50501657,0.0000014694369,0.49473205,0.0000018022942,0.00001876194,0.00017759019,0.00000387308,0.000017338576,0.000030569805],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883574,0.000040225583,0.00061474077,0.00015232626,0.00016380096,0.00019315991],"domain_scores_gemma":[0.9982124,0.00076965574,0.00058637466,0.0002174673,0.00019437658,0.000019710415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012720512,0.00010889029,0.00037479837,0.000079590485,0.000024874382,0.0000042045112,0.00010178276,0.00006309821,0.000014265681],"category_scores_gemma":[0.0013312435,0.0000907308,0.00005022518,0.000121857345,0.00008610208,0.00011729505,0.000084952284,0.00010404652,2.83233e-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":[0.00002398263,0.00045904718,0.23472042,0.002432319,0.00015588096,0.000001389958,0.0021132354,0.00003079858,0.7404705,0.0076506757,0.0004964605,0.011445274],"study_design_scores_gemma":[0.00059502514,0.00044135834,0.003300564,0.0020915216,0.00011387847,0.0000017590451,0.0004889728,0.007764402,0.68734026,0.2974395,0.0000895154,0.00033325708],"about_ca_topic_score_codex":0.000015212996,"about_ca_topic_score_gemma":0.00004413509,"teacher_disagreement_score":0.4918581,"about_ca_system_score_codex":0.000020971347,"about_ca_system_score_gemma":0.000042836687,"threshold_uncertainty_score":0.36998945},"labels":[],"label_agreement":null},{"id":"W2028610170","doi":"10.1097/ede.0b013e31823b539c","title":"Is Probabilistic Bias Analysis Approximately Bayesian?","year":2011,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Frequentist inference; Probabilistic logic; Bayesian probability; Statistics; Computer science; Bayes' theorem; Econometrics; Bayesian inference; Artificial intelligence; Mathematics","score_opus":0.6188697775386927,"score_gpt":0.47532603402570855,"score_spread":0.1435437435129841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028610170","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":[0.026331807,0.00009618145,0.9496609,0.00051118666,0.00007496212,0.0004035469,0.00001676997,0.0007583262,0.022146316],"genre_scores_gemma":[0.48188108,0.000026877588,0.5162124,0.0011542812,0.000047452922,0.00013488579,0.000010017082,0.000029184042,0.0005038201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99744594,0.00062295573,0.00082435797,0.000501275,0.0000844523,0.00052099675],"domain_scores_gemma":[0.9947743,0.0037434953,0.0004172401,0.000833998,0.00010435199,0.00012664983],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023117824,0.00024427727,0.0009777457,0.00025239398,0.000061699146,0.0000033411625,0.00034634557,0.0002520658,0.0016804165],"category_scores_gemma":[0.012422126,0.00019710901,0.0002715993,0.0005624522,0.000247373,0.00009695979,0.00011001909,0.00025649037,0.00009083306],"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":[0.000024974224,0.00014472054,0.051993426,0.00006400508,0.00042292636,0.000011142073,0.00080073194,0.000007975374,0.00004549035,0.938341,0.006659674,0.0014839172],"study_design_scores_gemma":[0.00006698367,0.00010197701,0.0055043907,0.000010477238,0.00033825004,0.00000905722,0.000036020756,0.0023401848,0.00080336526,0.99011916,0.00045456542,0.00021556475],"about_ca_topic_score_codex":0.00012059866,"about_ca_topic_score_gemma":0.000053509084,"teacher_disagreement_score":0.45554927,"about_ca_system_score_codex":0.00006258867,"about_ca_system_score_gemma":0.000026674235,"threshold_uncertainty_score":0.9992322},"labels":[],"label_agreement":null},{"id":"W2028695612","doi":"10.1016/j.jclinepi.2009.07.018","title":"Author's response: the design of observational studies—defining baseline time","year":2010,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; University of Toronto; Public Health Ontario; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Observational study; Propensity score matching; Selection bias; Medicine; Randomized controlled trial; Baseline (sea); Selection (genetic algorithm); Surgery; Internal medicine; Computer science; Political science; Pathology; Artificial intelligence","score_opus":0.8515153525868473,"score_gpt":0.6448775021619372,"score_spread":0.20663785042491012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028695612","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008192128,0.0006183179,0.21952067,0.7773418,0.001305988,0.00028479318,0.00003594029,0.00004296967,0.000030335828],"genre_scores_gemma":[0.0001640243,0.00035899933,0.604741,0.38758612,0.005234935,0.000018568919,0.000013390749,0.00007402806,0.0018089429],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9427065,0.041174393,0.014134245,0.0005210281,0.00077322393,0.0006905943],"domain_scores_gemma":[0.36402655,0.61788267,0.015254457,0.00086065807,0.0018596326,0.00011601451],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.18183206,0.00046000606,0.0059647905,0.00021875012,0.000091362715,0.000006465364,0.0012957255,0.003712897,0.0002682149],"category_scores_gemma":[0.769794,0.0002635007,0.001205261,0.0001942438,0.0012937462,0.0001280186,0.00025081538,0.015530399,0.00003283454],"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":[0.00095464307,0.00006575408,0.00038300443,0.0000816895,0.00049998605,0.00013289526,0.000038999326,0.000061886596,0.00006343253,0.0057812533,0.99037176,0.0015646652],"study_design_scores_gemma":[0.00032399886,0.001082867,0.000769134,0.00047544434,0.00031430385,0.00022989039,0.000012943527,0.0005540643,0.000020611456,0.6542802,0.3417218,0.00021475428],"about_ca_topic_score_codex":0.0000013982406,"about_ca_topic_score_gemma":6.82294e-7,"teacher_disagreement_score":0.64865,"about_ca_system_score_codex":0.00007755481,"about_ca_system_score_gemma":0.0009092533,"threshold_uncertainty_score":0.9999817},"labels":[],"label_agreement":null},{"id":"W2028896959","doi":"10.1016/s0025-5564(01)00050-5","title":"Resource allocation for epidemic control over short time horizons","year":2001,"lang":"en","type":"article","venue":"Mathematical Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":115,"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","funders":"Division of Mathematical Sciences; National Institute on Drug Abuse","keywords":"Heuristics; Time horizon; Mathematical optimization; Resource allocation; Computer science; Constraint (computer-aided design); Set (abstract data type); Function (biology); Production (economics); Operations research; Mathematics; Economics; Microeconomics","score_opus":0.11517627921030515,"score_gpt":0.4088815399018293,"score_spread":0.29370526069152414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028896959","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":[0.040226478,0.000026321535,0.941446,0.0018120841,0.000044862016,0.0011087719,0.000020616959,0.000588549,0.014726321],"genre_scores_gemma":[0.80449903,0.00001227484,0.1922456,0.00051479886,0.00014527277,0.0003631254,0.000006714093,0.0000395586,0.0021736512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806684,0.00007106294,0.00054016657,0.00040587454,0.00042460542,0.00049145403],"domain_scores_gemma":[0.99649125,0.0027064525,0.00013077154,0.00042551084,0.000097356446,0.0001486682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015022326,0.00022260068,0.0004158453,0.00011189248,0.00019565744,0.00007118575,0.00048429047,0.00013435462,0.00025421116],"category_scores_gemma":[0.003718037,0.00016655413,0.00012552827,0.00034722962,0.00038835706,0.00027938932,0.000056953035,0.00012449852,0.00009338326],"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":[0.000049378406,0.0003666193,0.0002613632,0.00012647882,0.000028592214,0.000004621468,0.00025131032,0.000007910295,0.045782264,0.9317601,0.009919712,0.011441653],"study_design_scores_gemma":[0.00019338942,0.00023622361,0.000046258643,0.00008916284,0.000045036566,0.000020313562,0.00009188082,0.018414455,0.00520683,0.9700988,0.005285074,0.00027256107],"about_ca_topic_score_codex":0.0000015988318,"about_ca_topic_score_gemma":0.000002363451,"teacher_disagreement_score":0.7642725,"about_ca_system_score_codex":0.00006872083,"about_ca_system_score_gemma":0.000039717946,"threshold_uncertainty_score":0.679188},"labels":[],"label_agreement":null},{"id":"W2029059557","doi":"10.1080/03610911003650383","title":"How Big is a Big Odds Ratio? Interpreting the Magnitudes of Odds Ratios in Epidemiological Studies","year":2010,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1932,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Columbia College","funders":"","keywords":"Odds ratio; Odds; Epidemiology; Index (typography); Statistics; Medicine; Demography; Psychology; Mathematics; Computer science; Internal medicine; Sociology; Logistic regression","score_opus":0.5103286940819939,"score_gpt":0.559314319333483,"score_spread":0.048985625251489084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029059557","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":[0.077166826,0.00028036832,0.92033786,0.0014603955,0.00008520175,0.000468629,0.000031040094,0.000058903144,0.000110804656],"genre_scores_gemma":[0.7898632,0.00030092653,0.20957838,0.00011291755,0.000015757189,0.00006749013,0.000035477828,0.0000110000965,0.000014810785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982825,0.0004937297,0.00073677674,0.0001924902,0.00015366687,0.00014086098],"domain_scores_gemma":[0.98451495,0.014064396,0.00042616983,0.0005663136,0.0004019486,0.000026232121],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011533224,0.00016136306,0.00033368822,0.00019927944,0.0001604884,0.00005960737,0.00032274702,0.000104188526,0.000004225817],"category_scores_gemma":[0.008766515,0.0001288171,0.000027301854,0.00036555162,0.0004757952,0.00014129104,0.00025389605,0.0004590303,6.6331546e-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":[0.000031758354,0.00022780865,0.008732584,0.00013258056,0.0000352222,0.0000010401641,0.009354492,0.011664697,0.0010947977,0.76345587,0.00012448773,0.20514467],"study_design_scores_gemma":[0.0002271184,0.000046384557,0.004260319,0.0001156057,0.000014189956,0.0000011972726,0.0011056894,0.55729115,0.00011913737,0.43662935,0.00008152588,0.00010829734],"about_ca_topic_score_codex":0.00002145288,"about_ca_topic_score_gemma":0.00071333133,"teacher_disagreement_score":0.71269643,"about_ca_system_score_codex":0.00005039937,"about_ca_system_score_gemma":0.000039160794,"threshold_uncertainty_score":0.99958307},"labels":[],"label_agreement":null},{"id":"W2029739696","doi":"10.1080/03610918.2011.575505","title":"Comparison of Selected Methods for Modeling of Multi-State Disease Progression Processes: A Simulation Study","year":2011,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Covariate; Proportional hazards model; Markov model; Markov chain; Event (particle physics); Computer science; Econometrics; Regression analysis; Regression; Statistics; Type I and type II errors; Mathematics; Machine learning","score_opus":0.642218000239422,"score_gpt":0.6481872947404852,"score_spread":0.005969294501063205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029739696","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":[0.044698693,0.00019445975,0.9532209,0.0000041531584,0.000013489714,0.0017200804,0.000053985856,0.00007987969,0.000014325792],"genre_scores_gemma":[0.51211375,0.000013125816,0.48769754,0.0000012727664,0.0000011671491,0.00008722062,0.00007198112,0.000012637278,0.000001311966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981481,0.00039039896,0.001004288,0.00019796411,0.00014471188,0.00011454958],"domain_scores_gemma":[0.99393785,0.0033959323,0.00065739406,0.0004297061,0.0015320119,0.00004709249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062520173,0.00014552097,0.00034704417,0.0002468673,0.00011369466,0.000013745497,0.00020929617,0.00005058339,0.0000021463009],"category_scores_gemma":[0.0029602968,0.00015231446,0.000019663748,0.00050743384,0.00009929881,0.00018983152,0.000108514316,0.00011666779,1.1167744e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002033153,0.0021482727,0.013063804,0.00045110716,0.000024616485,9.889139e-8,0.013340675,0.89172035,0.0000740141,0.0053918283,9.890772e-7,0.07358092],"study_design_scores_gemma":[0.0006683608,0.00020276701,0.0027755757,0.00017137318,0.000058783487,4.9763084e-8,0.00059116667,0.83342534,0.0001393883,0.16185024,0.0000015535918,0.000115396135],"about_ca_topic_score_codex":0.000018396064,"about_ca_topic_score_gemma":0.000062393025,"teacher_disagreement_score":0.46741503,"about_ca_system_score_codex":0.000041785912,"about_ca_system_score_gemma":0.00009651598,"threshold_uncertainty_score":0.6211204},"labels":[],"label_agreement":null},{"id":"W2030531780","doi":"10.1177/1740774509105223","title":"Evaluating the benefit of event adjudication of cardiovascular outcomes in large simple RCTs","year":2009,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":114,"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; Population Health Research Institute","funders":"","keywords":"Adjudication; Medicine; Randomized controlled trial; Event (particle physics); Simple (philosophy); Cardiovascular event; Medical physics; Intensive care medicine; Internal medicine; Myocardial infarction; Political science","score_opus":0.7228107795496578,"score_gpt":0.6578663880181861,"score_spread":0.06494439153147169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030531780","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":[0.96146053,0.0005552793,0.035548054,0.000443931,0.00010486132,0.001482416,0.000028890348,0.00006829565,0.00030776396],"genre_scores_gemma":[0.9837435,0.00018162264,0.015847744,0.00008900304,0.00007014132,0.000034219767,0.0000041312214,0.000010102269,0.000019538673],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99463147,0.001676383,0.0028180957,0.00022259864,0.0004715308,0.00017994424],"domain_scores_gemma":[0.98337185,0.014444555,0.0011126273,0.0008466934,0.00018642722,0.00003781762],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041488606,0.000120406505,0.0015748497,0.00005631385,0.00002440674,0.0000046168825,0.0002849875,0.00015199864,0.000043399185],"category_scores_gemma":[0.097495705,0.000075931974,0.00078922947,0.00018706072,0.000064393615,0.00006316936,0.00006211902,0.00020847376,0.0000026138728],"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":[0.00042179113,0.0029229373,0.032080743,0.00020821416,0.0012064195,0.000003920766,0.00060780573,0.0014443339,0.0037384804,0.33820066,0.0004943178,0.6186704],"study_design_scores_gemma":[0.0015403137,0.00060595194,0.03072087,0.00012256108,0.00025952343,3.1306072e-7,0.00005517758,0.00050494936,0.0057709194,0.9601352,0.00017788704,0.00010633978],"about_ca_topic_score_codex":0.000013282359,"about_ca_topic_score_gemma":0.0000074316854,"teacher_disagreement_score":0.62193453,"about_ca_system_score_codex":0.000027177242,"about_ca_system_score_gemma":0.000052586318,"threshold_uncertainty_score":0.9869892},"labels":[],"label_agreement":null},{"id":"W2030555037","doi":"10.1016/j.ahj.2010.07.004","title":"Determination of hospitalization type by investigator case report form or adjudication committee in a large heart failure clinical trial (β-Blocker Evaluation of Survival Trial [BEST])","year":2010,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute","funders":"U.S. Food and Drug Administration","keywords":"Medicine; Adjudication; Heart failure; Clinical trial; Randomized controlled trial; Surgery; Internal medicine; Law","score_opus":0.26140179206123343,"score_gpt":0.5129205021851289,"score_spread":0.25151871012389543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030555037","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":[0.990164,0.000010901458,0.0072909147,0.0005648949,0.00057030463,0.0013161363,0.000015450085,0.00003638698,0.000031035128],"genre_scores_gemma":[0.9192446,0.0000143480565,0.08023947,0.00007072936,0.00029682746,0.000060756076,0.0000245269,0.0000319214,0.000016856518],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99583566,0.0008375511,0.0019394045,0.00025836148,0.0008749655,0.00025407478],"domain_scores_gemma":[0.9953557,0.00092862267,0.0018338923,0.0004462418,0.0012454212,0.00019010979],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00816014,0.00018506672,0.0007486894,0.0002308131,0.00008156767,0.000023181672,0.00014390143,0.00019064246,0.00013237105],"category_scores_gemma":[0.02208985,0.00016104309,0.00015162873,0.0006055037,0.00032364915,0.00038353555,0.000044891498,0.00065738783,0.0000021115984],"study_design_candidate":"randomized_trial","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":[0.22828232,0.023534343,0.40010294,0.00051211275,0.0005790992,0.0017561539,0.0058618076,0.000016677075,0.06951011,0.009766179,0.12679373,0.13328452],"study_design_scores_gemma":[0.5316387,0.06419111,0.015088767,0.0013169374,0.0024123886,0.033427835,0.0073848264,0.022975607,0.06413731,0.24028677,0.01367955,0.0034602424],"about_ca_topic_score_codex":0.00011818289,"about_ca_topic_score_gemma":0.00063764624,"teacher_disagreement_score":0.38501418,"about_ca_system_score_codex":0.00010734727,"about_ca_system_score_gemma":0.0008726969,"threshold_uncertainty_score":0.9861475},"labels":[],"label_agreement":null},{"id":"W2030597325","doi":"10.1097/mlr.0b013e31805371bf","title":"Studying Prescription Drug Use and Outcomes With Medicaid Claims Data","year":2007,"lang":"en","type":"article","venue":"Medical Care","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":150,"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 of Health Services and Policy Research","funders":"National Institute of Mental Health; Agency for Healthcare Research and Quality","keywords":"Medicaid; Identification (biology); Medical prescription; Prescription drug; Data science; Medicine; MEDLINE; Outcomes research; Computer science; Health care; Alternative medicine; Nursing","score_opus":0.22936142604086154,"score_gpt":0.4384770445704938,"score_spread":0.20911561852963226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030597325","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":[0.8297768,0.00027482145,0.16691725,0.00083254115,0.0001395764,0.0005590728,0.00003625287,0.0006632415,0.00080042094],"genre_scores_gemma":[0.951594,0.00004590685,0.04760162,0.00043712198,0.00006886965,0.000013614189,0.00006195211,0.000030174051,0.00014671592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980927,0.000053251595,0.00029040626,0.00033339104,0.0009520962,0.00027814496],"domain_scores_gemma":[0.9979246,0.00090057845,0.00008323862,0.00069933425,0.00011294012,0.00027927133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009927496,0.00016079609,0.000265448,0.00006026317,0.00008292901,0.000038147817,0.00039810155,0.00012744244,0.00010002937],"category_scores_gemma":[0.002866692,0.00010670085,0.000016013828,0.000100495046,0.0002003988,0.00041968218,0.00038707996,0.00038986118,0.000002754742],"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":[0.00016594697,0.00035383413,0.74781406,0.0009372277,0.00020614613,0.0009092318,0.019855496,3.2439712e-7,0.00017848844,0.036550976,0.02393965,0.1690886],"study_design_scores_gemma":[0.013293387,0.002229416,0.48991692,0.006477913,0.0015376012,0.0006710894,0.11513298,0.0015616266,0.0088960985,0.25271773,0.10227757,0.0052876896],"about_ca_topic_score_codex":0.00008872421,"about_ca_topic_score_gemma":0.0016375759,"teacher_disagreement_score":0.25789717,"about_ca_system_score_codex":0.000054286786,"about_ca_system_score_gemma":0.000055982113,"threshold_uncertainty_score":0.43511343},"labels":[],"label_agreement":null},{"id":"W2033230645","doi":"10.1016/j.jclinepi.2008.10.008","title":"Nonrandomized quality improvement intervention trials might overstate the strength of causal inference of their findings","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"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; Institute of Population and Public Health; Research Canada; Simon Fraser University; Arthritis Research Centre of Canada; University of British Columbia","funders":"","keywords":"Causal inference; Causality (physics); Randomized controlled trial; Medicine; Inference; Psychological intervention; Intervention (counseling); Randomized experiment; Physical therapy; Internal medicine; Psychiatry; Pathology; Artificial intelligence","score_opus":0.6187292978161297,"score_gpt":0.6310399181908967,"score_spread":0.012310620374766934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033230645","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":[0.79803,0.00014421892,0.19861116,0.0022659865,0.0003665811,0.00040588804,0.000026370595,0.000016680331,0.000133127],"genre_scores_gemma":[0.96843773,0.0009201045,0.030005516,0.00041028307,0.00017877833,0.000004890202,0.0000021869987,0.000008833415,0.000031684183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9690998,0.014108722,0.015868507,0.00024770963,0.00033461227,0.00034062733],"domain_scores_gemma":[0.7574617,0.22252072,0.018584251,0.00054971845,0.00073696877,0.00014659228],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11705524,0.00022249675,0.005216184,0.00011231443,0.00003157896,0.000004796711,0.00053121865,0.0003130627,0.00012142396],"category_scores_gemma":[0.36308044,0.000114000075,0.0017597527,0.00012096884,0.00040383433,0.00016137291,0.00008369047,0.0008998235,7.3118815e-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":[0.031809982,0.0053465227,0.023898143,0.0005243599,0.0022526057,0.000013918866,0.0012591619,0.00008947752,0.022303585,0.5387329,0.006557113,0.36721224],"study_design_scores_gemma":[0.0076614562,0.004558209,0.012562509,0.00040443297,0.00020453549,0.000006674656,0.00019182153,0.00015350009,0.011917724,0.9619522,0.00026002259,0.00012693011],"about_ca_topic_score_codex":0.000034214,"about_ca_topic_score_gemma":0.000016997858,"teacher_disagreement_score":0.4232193,"about_ca_system_score_codex":0.000045096807,"about_ca_system_score_gemma":0.00013331755,"threshold_uncertainty_score":0.9091774},"labels":[],"label_agreement":null},{"id":"W2033411871","doi":"10.1198/0003130031450","title":"Type I Error Inflation in the Presence of a Ceiling Effect","year":2003,"lang":"en","type":"article","venue":"The American Statistician","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":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Statistics; Ceiling (cloud); Econometrics; Statistical significance; Variables; Ceiling effect; Type I and type II errors; Mathematics; Standard error; Alcohol consumption; Variable (mathematics); Linear regression; Psychology; Medicine; Engineering; Biology; Alcohol","score_opus":0.09602044591037069,"score_gpt":0.43714101278193035,"score_spread":0.34112056687155967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033411871","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":[0.84511846,0.00002736659,0.14945863,0.0001083464,0.000037086884,0.00059947436,0.000011702774,0.00006431257,0.0045746104],"genre_scores_gemma":[0.9612555,0.000007696263,0.03856019,0.00010279504,0.000010474845,0.000030294448,0.0000012941189,0.000011936568,0.000019825859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987663,0.00054852566,0.00023122289,0.000101874226,0.00018947244,0.00016258682],"domain_scores_gemma":[0.9955008,0.0038180295,0.00027070843,0.00034429095,0.00005133187,0.000014813303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008896797,0.00009536771,0.00021322492,0.000044493016,0.000045060588,0.00000972187,0.00022356368,0.000013287327,0.00001592903],"category_scores_gemma":[0.0038017475,0.000054039127,0.000019329022,0.00047079803,0.0002885575,0.000046345667,0.000017893297,0.0001502585,0.0000051470715],"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":[0.000147515,0.00011157322,0.010418754,0.00011370801,0.00003161253,0.000017701568,0.008092303,0.00022015153,0.00779716,0.93554187,0.0010534199,0.036454216],"study_design_scores_gemma":[0.00027246567,0.0011740319,0.02410483,0.00014613388,0.00007346521,0.000015044214,0.0035254217,0.0015706086,0.011255934,0.9570352,0.00054158905,0.00028531702],"about_ca_topic_score_codex":0.00018716908,"about_ca_topic_score_gemma":0.00011713366,"teacher_disagreement_score":0.11613703,"about_ca_system_score_codex":0.000025117066,"about_ca_system_score_gemma":0.000031815198,"threshold_uncertainty_score":0.45513216},"labels":[],"label_agreement":null},{"id":"W2033511646","doi":"10.1016/j.csda.2013.09.011","title":"The effect of the prior distribution in the Bayesian Adjustment for Confounding algorithm","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Confounding; Outcome (game theory); Estimator; Prior probability; Bayesian probability; Mathematics; Econometrics","score_opus":0.0632994742926309,"score_gpt":0.4135541767843135,"score_spread":0.3502547024916826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033511646","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":[0.001128076,0.000048214846,0.9934658,0.00026033694,0.000042256997,0.00093282235,0.0040923394,0.00001695904,0.000013216055],"genre_scores_gemma":[0.45985988,0.000030579446,0.532751,0.00006113939,0.00005689166,0.00035169168,0.006837985,0.000016032242,0.000034783316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984509,0.00029465352,0.00045203525,0.00021074669,0.0004138675,0.00017783647],"domain_scores_gemma":[0.98938465,0.009387194,0.0003260002,0.00067511323,0.00020361961,0.000023417866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011824132,0.00013131605,0.00024974789,0.000046650803,0.0002770603,0.00008837576,0.00076660584,0.000034388067,0.000022728593],"category_scores_gemma":[0.0017906026,0.000065084954,0.00008084647,0.0005351355,0.00015326838,0.0001241774,0.00017414545,0.00011912218,0.0000021296244],"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":[0.00002935372,0.00012876635,0.004183375,0.00014564862,0.0011972494,0.0000014293199,0.00033411462,0.0077862716,0.0000137094075,0.6891048,0.032466892,0.2646084],"study_design_scores_gemma":[0.00016920654,0.000054211214,0.015694687,0.000014411685,0.00063003576,8.680198e-7,0.00004758297,0.5806621,0.00003073802,0.40217942,0.0004436146,0.00007311057],"about_ca_topic_score_codex":0.00017990766,"about_ca_topic_score_gemma":0.00018790427,"teacher_disagreement_score":0.57287586,"about_ca_system_score_codex":0.00009001124,"about_ca_system_score_gemma":0.00004056252,"threshold_uncertainty_score":0.26540875},"labels":[],"label_agreement":null},{"id":"W2034959910","doi":"10.1002/pds.1757","title":"Bias–variance trade‐off in pharmacoepidemiological studies using physician‐preference‐based instrumental variables: a simulation study","year":2009,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":36,"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; McGill University Health Centre","funders":"","keywords":"Confounding; Medicine; Instrumental variable; Preference; Variance (accounting); Operationalization; Statistics; Econometrics; Omitted-variable bias; Pharmacoepidemiology; Mathematics; Internal medicine; Medical prescription; Economics","score_opus":0.5073631578960011,"score_gpt":0.5216853837449187,"score_spread":0.014322225848917625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034959910","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":[0.9066015,0.0015697813,0.08653673,0.00207541,0.0002753226,0.0019474471,0.000041844105,0.0005476192,0.00040437942],"genre_scores_gemma":[0.96478856,0.0006539175,0.02930098,0.004982893,0.00016751827,0.000055442586,0.0000150416945,0.00002521926,0.0000104581895],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925304,0.0040202155,0.0015811147,0.00090037973,0.00020423072,0.0007636357],"domain_scores_gemma":[0.9850653,0.013739317,0.00063052797,0.00033303676,0.000071137656,0.00016069684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0069276094,0.00057845475,0.0015356715,0.00021834637,0.00028850403,0.000013052956,0.0003060764,0.00020725068,0.000040802646],"category_scores_gemma":[0.004743181,0.00048106935,0.00012753785,0.00045915003,0.00030401984,0.00048632582,0.00012036243,0.0008831583,0.000003074457],"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":[0.0074715456,0.013247987,0.31482342,0.00071815186,0.0013427017,0.00035320682,0.013103773,0.25973678,0.02257045,0.12723295,0.004165203,0.23523383],"study_design_scores_gemma":[0.0065986747,0.00071663834,0.026576342,0.00040203374,0.0004137121,0.000017440583,0.0023858808,0.5037127,0.0018852799,0.4552646,0.0007129465,0.0013137653],"about_ca_topic_score_codex":0.00003184467,"about_ca_topic_score_gemma":0.000014210728,"teacher_disagreement_score":0.32803163,"about_ca_system_score_codex":0.00028762844,"about_ca_system_score_gemma":0.00006873099,"threshold_uncertainty_score":0.9997641},"labels":[],"label_agreement":null},{"id":"W2035194246","doi":"10.1007/s11749-010-0230-2","title":"Rejoinder on: Nonparametric inference based on panel count data","year":2010,"lang":"en","type":"article","venue":"Test","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":58,"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":"Medicine; Magnetic resonance imaging; Pathological; Ultrasound; Concordance; Radiology; Immunohistochemistry; Radiofrequency ablation; Retrospective cohort study; Internal medicine; Surgery; Ablation","score_opus":0.3627079804759021,"score_gpt":0.4519888626851039,"score_spread":0.08928088220920183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035194246","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":[0.2995789,0.00003408247,0.38002688,0.0046804254,0.0016165467,0.0035877351,0.0014152023,0.007769603,0.3012906],"genre_scores_gemma":[0.9215603,0.000003361253,0.07697833,0.00095155416,0.00009632791,0.000033924447,0.000051371728,0.0000397765,0.0002850615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985683,0.000025739419,0.0002683151,0.00043339815,0.0004097382,0.00029453693],"domain_scores_gemma":[0.992505,0.0047550383,0.00014960988,0.0023916606,0.00009735289,0.00010133395],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004765792,0.00022397318,0.00024037511,0.0001812678,0.00007473282,0.00005441938,0.0008303248,0.00015952661,0.00048671584],"category_scores_gemma":[0.011298839,0.00018780188,0.000028443888,0.00039544943,0.00011488091,0.00017004463,0.00016012309,0.00070146285,0.00032927404],"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":[0.0001511611,0.0058100694,0.029984275,0.0003680389,0.000053253323,0.00020396269,0.0002636722,0.00011304435,0.04518064,0.7303334,0.13434601,0.053192463],"study_design_scores_gemma":[0.0017341184,0.0022370033,0.017767005,0.00056153664,0.00011621735,0.00002864424,0.000057258956,0.075090244,0.05897146,0.79010355,0.051227607,0.0021053655],"about_ca_topic_score_codex":0.000020014613,"about_ca_topic_score_gemma":0.000041685802,"teacher_disagreement_score":0.6219814,"about_ca_system_score_codex":0.000047172496,"about_ca_system_score_gemma":0.00010403855,"threshold_uncertainty_score":0.9970294},"labels":[],"label_agreement":null},{"id":"W2035305268","doi":"10.1002/pds.1674","title":"Assessing balance in measured baseline covariates when using many‐to‐one matching on the propensity‐score","year":2008,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":184,"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; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Propensity score matching; Covariate; Medicine; Matching (statistics); Statistics; Inverse probability weighting; Internal medicine; Mathematics","score_opus":0.41891381304108016,"score_gpt":0.4484603936667629,"score_spread":0.029546580625682717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035305268","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":[0.57475996,0.00016755551,0.4176489,0.005925718,0.00009983125,0.0006549413,0.000009876213,0.00019367872,0.0005395367],"genre_scores_gemma":[0.8816648,0.00020782204,0.113386504,0.004513113,0.00010858739,0.00004015143,0.000005918409,0.000031357733,0.00004174371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960572,0.0021091597,0.0007158234,0.00047043248,0.00016758098,0.00047980633],"domain_scores_gemma":[0.99190015,0.007281578,0.00027799953,0.00033179767,0.00009519238,0.00011327274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075865965,0.0002912125,0.00069892703,0.000114700044,0.00040623345,0.00001633034,0.00025532002,0.0001161529,0.000075451346],"category_scores_gemma":[0.004636771,0.0002091289,0.000056411478,0.00019035593,0.00019402566,0.0003167394,0.00017845309,0.0007344459,0.000010071823],"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":[0.002538555,0.00127498,0.25107938,0.00064750615,0.00041227142,0.0004318066,0.012468296,0.007323011,0.17399956,0.5204187,0.014899121,0.014506779],"study_design_scores_gemma":[0.0014368095,0.00007376275,0.025111176,0.001013035,0.0001128242,0.00020825512,0.0002712649,0.030200778,0.020740453,0.9189899,0.0009080282,0.0009337408],"about_ca_topic_score_codex":0.00017563821,"about_ca_topic_score_gemma":0.000029810293,"teacher_disagreement_score":0.39857113,"about_ca_system_score_codex":0.00011534694,"about_ca_system_score_gemma":0.00006035683,"threshold_uncertainty_score":0.85280293},"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":"W2036193982","doi":"10.1080/00273171.2011.568786","title":"An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11884,"is_retracted":false,"has_abstract":true,"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","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Observational study; Covariate; Confounding; Statistics; Inverse probability weighting; Econometrics; Mathematics","score_opus":0.8974226593536919,"score_gpt":0.6794649079660394,"score_spread":0.2179577513876525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036193982","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":[0.9202135,0.000022144797,0.07665904,0.00020195756,0.00016533416,0.0026595446,0.0000032414498,0.00006038761,0.000014840273],"genre_scores_gemma":[0.58024377,0.0000039873366,0.4189482,0.000005200957,0.00007632076,0.00064324035,0.0000031979241,0.00001906868,0.000057012254],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99763095,0.0009212406,0.0003871311,0.00035927343,0.00032590583,0.00037548895],"domain_scores_gemma":[0.9958278,0.0023781403,0.000111100744,0.00049141847,0.0011282375,0.00006328556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067533776,0.00013203618,0.00032604675,0.0002465841,0.00018893168,0.000023301007,0.0003384725,0.0000790503,0.000009914063],"category_scores_gemma":[0.010852301,0.000092967835,0.000039917817,0.00050057867,0.0002033273,0.0003066678,0.00020073452,0.0003656098,0.000001178264],"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":[0.00035559895,0.0006330891,0.005786605,0.0003384953,0.00002239347,0.0000035293046,0.015909398,0.000005958023,0.8450568,0.094109856,0.00017766858,0.03760062],"study_design_scores_gemma":[0.00043097223,0.0015041771,0.047009274,0.00029732336,0.00003366003,0.0000019214062,0.001437723,0.00029813507,0.74971914,0.1989969,0.000077346354,0.00019341597],"about_ca_topic_score_codex":0.0006518969,"about_ca_topic_score_gemma":0.00010462125,"teacher_disagreement_score":0.34228915,"about_ca_system_score_codex":0.00025818826,"about_ca_system_score_gemma":0.000084135405,"threshold_uncertainty_score":0.99747974},"labels":[],"label_agreement":null},{"id":"W2036514462","doi":"10.1080/00273171.2011.589280","title":"Multilevel SEM Strategies for Evaluating Mediation in Three-Level Data","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"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":"Mount Allison University","keywords":"Mediation; Multilevel model; Computer science; Structural equation modeling; Psychology; Data mining; Econometrics; Statistics; Mathematics; Machine learning; Sociology","score_opus":0.9563346823471308,"score_gpt":0.6781517874356203,"score_spread":0.2781828949115105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036514462","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":[0.59485775,0.000022466149,0.40054375,0.00004655635,0.000115751034,0.002982783,0.0004281544,0.00030023593,0.0007025687],"genre_scores_gemma":[0.6194851,0.0000037439527,0.3796761,0.0000033518422,0.00003979581,0.00054688123,0.00009945428,0.00004804397,0.00009754101],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649805,0.00036276336,0.00063830154,0.0007135706,0.0009399936,0.0008473084],"domain_scores_gemma":[0.9961129,0.0015708628,0.00016306013,0.0012425025,0.00078694813,0.00012377117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063841245,0.00024727665,0.00034645337,0.00040504656,0.00019598256,0.00009798583,0.0011847529,0.0002499108,0.00019422312],"category_scores_gemma":[0.0036019357,0.00022768197,0.00004653877,0.00038718467,0.00017183431,0.0011665507,0.0007630719,0.0007046744,0.00002350985],"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":[0.0014783116,0.0049844054,0.027676648,0.00060462294,0.000071362134,0.00009795224,0.026818126,0.00002428371,0.19611375,0.31621918,0.0013801217,0.42453125],"study_design_scores_gemma":[0.0016841129,0.00067334645,0.03755224,0.00018989138,0.000030456891,0.0000023939863,0.0027739902,0.055996906,0.010399449,0.89019483,0.000037276794,0.0004651028],"about_ca_topic_score_codex":0.0033749777,"about_ca_topic_score_gemma":0.0037928445,"teacher_disagreement_score":0.5739757,"about_ca_system_score_codex":0.00026672406,"about_ca_system_score_gemma":0.0004240744,"threshold_uncertainty_score":0.9284602},"labels":[],"label_agreement":null},{"id":"W2037889113","doi":"10.1002/sim.5530","title":"Efficient analysis of case‐control studies with sample weights","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"St. Michael's Hospital","funders":"","keywords":"Estimator; Covariate; Statistics; Sample (material); Population; Sample size determination; Mathematics; Bootstrapping (finance); Robustness (evolution); Econometrics; Computer science","score_opus":0.1146731685975503,"score_gpt":0.4553308516164282,"score_spread":0.3406576830188779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037889113","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":[0.073625505,0.0006331108,0.92476493,0.000051071962,0.000055662316,0.00024070924,0.00029229603,0.000044764456,0.0002919405],"genre_scores_gemma":[0.62646806,0.000029843231,0.37338576,0.000030868072,0.000033323548,0.000019792202,0.000008479999,0.000009888209,0.000014008466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987212,0.00008348097,0.0004721508,0.0001379143,0.00032016882,0.0002650915],"domain_scores_gemma":[0.9936838,0.0054709013,0.00023652031,0.00030442947,0.00023266538,0.00007169324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008312558,0.00015113881,0.0007353694,0.0003953418,0.00003386749,0.0000014031141,0.00007808117,0.000036994654,0.00012809975],"category_scores_gemma":[0.003564691,0.00009571629,0.000022060904,0.00070084084,0.0003347388,0.000022878463,0.000024073071,0.00013165787,7.45479e-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":[0.000052161235,0.0002024613,0.018330678,0.00020099647,0.0015954719,0.00019981293,0.0060876263,0.0003581073,0.0001061831,0.9705385,0.00070331077,0.0016246813],"study_design_scores_gemma":[0.003211778,0.0013564331,0.011302361,0.0007633663,0.013844886,0.00015778029,0.011188621,0.028327258,0.0008380226,0.9280299,0.000270478,0.00070910715],"about_ca_topic_score_codex":0.00011993587,"about_ca_topic_score_gemma":0.0004528627,"teacher_disagreement_score":0.55284256,"about_ca_system_score_codex":0.0000828697,"about_ca_system_score_gemma":0.000015156161,"threshold_uncertainty_score":0.42675254},"labels":[],"label_agreement":null},{"id":"W2043051651","doi":"10.1089/pop.2011.0104","title":"Exploring Robust Methods for Evaluating Treatment and Comparison Groups in Chronic Care Management Programs","year":2012,"lang":"en","type":"article","venue":"Population Health Management","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":78,"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":"Toyota Motor Corporation; York University; Institute for Quantitative Social Science, Harvard University; Harvard University","keywords":"Matching (statistics); Propensity score matching; Average treatment effect; Statistic; Medicine; Psychological intervention; Variance (accounting); Statistics; Health care; Population; Analysis of variance; Operations management; Mathematics; Nursing; Environmental health; Engineering","score_opus":0.7243465867818727,"score_gpt":0.5958023742768924,"score_spread":0.12854421250498027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043051651","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":[0.109764025,0.002452323,0.87736124,0.0002502414,0.00022869326,0.008981896,0.0000023853622,0.00045628162,0.00050290907],"genre_scores_gemma":[0.4311839,0.00034909317,0.564858,0.00002736145,0.00004655306,0.0034202111,0.000057441426,0.000027084818,0.000030367823],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979909,0.00022781674,0.00068536313,0.0003301741,0.00017625044,0.00058946584],"domain_scores_gemma":[0.99909633,0.00014351882,0.0002975534,0.00031052623,0.00003352667,0.0001185436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014672368,0.00023038476,0.0003824957,0.00023499885,0.00017538913,0.000033532437,0.000083094565,0.000036237285,0.0000052061955],"category_scores_gemma":[0.000024923156,0.00022194826,0.000047338614,0.0002101401,0.000013676295,0.00037009045,0.00009887623,0.00006028693,0.0000013479572],"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":[0.00001718683,0.0001371244,0.012510468,0.002158549,0.000033358774,2.3280187e-7,0.0023980162,0.00061652437,0.000001913975,0.11960446,0.0000114092045,0.86251074],"study_design_scores_gemma":[0.012211917,0.0075369673,0.42064348,0.004935383,0.0010037129,0.000007390403,0.05445476,0.14983921,0.0006139288,0.31466407,0.03087216,0.0032170443],"about_ca_topic_score_codex":0.00015438664,"about_ca_topic_score_gemma":0.00020168195,"teacher_disagreement_score":0.8592937,"about_ca_system_score_codex":0.0026255485,"about_ca_system_score_gemma":0.000010213609,"threshold_uncertainty_score":0.9050787},"labels":[],"label_agreement":null},{"id":"W2044678740","doi":"10.1016/j.jclinepi.2003.07.014","title":"Commonalities in the classical, collapsibility and counterfactual concepts of confounding","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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 Alberta","funders":"","keywords":"Counterfactual thinking; Confounding; Counterfactual conditional; Econometrics; Key (lock); Abstraction; Computer science; Covariate; Observational study; Medicine; Risk analysis (engineering); Statistics; Mathematics; Psychology; Epistemology; Social psychology; Computer security","score_opus":0.7854842182921576,"score_gpt":0.6818694211313308,"score_spread":0.10361479716082689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044678740","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":[0.0012562552,0.99211395,0.004532333,0.0006642959,0.0004528093,0.00060938275,0.00003996681,0.000014949998,0.0003160312],"genre_scores_gemma":[0.0026108418,0.984303,0.01240871,0.00033765513,0.0002766935,0.000012706796,0.0000030602807,0.000023162584,0.00002417426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97519714,0.012576693,0.011253006,0.0003094826,0.0003017905,0.00036190648],"domain_scores_gemma":[0.7177345,0.27198833,0.009438876,0.00045703832,0.0002583098,0.00012290923],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04978111,0.00037210126,0.010352217,0.00014448428,0.00003862753,0.000010297961,0.0007678613,0.00096199795,0.00003253113],"category_scores_gemma":[0.18041122,0.00020116192,0.0010589323,0.00015891009,0.0020719885,0.0001095833,0.00014096391,0.0027938182,0.0000017968011],"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":[0.00018085036,0.0006701586,0.0024636881,0.021302538,0.0004988386,0.000082330334,0.00058215496,0.0000033472388,1.6693097e-7,0.697206,0.0035004402,0.27350947],"study_design_scores_gemma":[0.00045583557,0.00089944043,0.00016374642,0.014441267,0.000387719,0.00031336152,0.000241382,0.0000035832495,2.439236e-7,0.6706728,0.31224602,0.00017458458],"about_ca_topic_score_codex":0.000012864062,"about_ca_topic_score_gemma":0.000029715642,"teacher_disagreement_score":0.3087456,"about_ca_system_score_codex":0.00015078095,"about_ca_system_score_gemma":0.0008819886,"threshold_uncertainty_score":0.9995068},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2046661414","doi":"10.1016/j.jmpt.2013.07.009","title":"Examination of the Relationship Between Theory-Driven Policies and Allowed Lost-Time Back Claims in Workers' Compensation: A System Dynamics Model","year":2013,"lang":"en","type":"article","venue":"Journal of Manipulative and Physiological Therapeutics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Tech University; University of Toronto; Canadian Memorial Chiropractic College","funders":"","keywords":"Compensation (psychology); Econometrics; Gini coefficient; Statistics; Actuarial science; Operations research; Inequality; Economics; Mathematics; Economic inequality","score_opus":0.480003074903353,"score_gpt":0.40753078081697447,"score_spread":0.07247229408637851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046661414","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":[0.977504,0.000037559843,0.021662638,0.00018897762,0.000011031695,0.00030242105,0.0000053729996,0.000009985433,0.0002779852],"genre_scores_gemma":[0.9922749,0.000021643318,0.0075479746,0.000043460048,0.000027879973,0.000003286823,0.0000019800175,0.000009839163,0.000069040005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986406,0.00046440042,0.0005153966,0.000097893775,0.00016562929,0.00011608849],"domain_scores_gemma":[0.99713457,0.0019386318,0.0005739245,0.0001285216,0.00019040307,0.000033959608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046941594,0.00013571778,0.0003823225,0.00006803449,0.000057725967,0.000019850475,0.00014784848,0.00013931489,0.000008501173],"category_scores_gemma":[0.000110045476,0.000081622005,0.00006343844,0.00014308265,0.00021632585,0.0001927794,0.00007207095,0.00030283903,0.000001555731],"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":[0.00008650231,0.00013786972,0.18723255,0.00016695507,0.00014294434,8.454513e-7,0.0029431437,0.0019437921,0.0066305017,0.7986475,0.00001762435,0.0020497695],"study_design_scores_gemma":[0.00017149221,0.00012899711,0.4823552,0.00016337131,0.000032240754,0.0000031948648,0.00053006306,0.029824054,0.00011174246,0.48661485,5.065802e-7,0.00006426654],"about_ca_topic_score_codex":0.0000026523303,"about_ca_topic_score_gemma":0.0000020004024,"teacher_disagreement_score":0.31203264,"about_ca_system_score_codex":0.000081629296,"about_ca_system_score_gemma":0.000014804477,"threshold_uncertainty_score":0.33284488},"labels":[],"label_agreement":null},{"id":"W2046889498","doi":"10.1093/cid/ciu036","title":"Reply to Strandberg and Tienari","year":2014,"lang":"en","type":"letter","venue":"Clinical Infectious Diseases","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Dermatology","score_opus":0.1764704338020869,"score_gpt":0.4638362948799244,"score_spread":0.28736586107783746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046889498","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":[0.02141008,0.000585866,0.059977368,0.88092226,0.0030421442,0.004951362,0.00060121226,0.0090684835,0.019441243],"genre_scores_gemma":[0.009216217,0.00018780126,0.0017844319,0.98205274,0.0047884136,0.00023319169,0.00009472227,0.00017085506,0.0014715999],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967804,0.000381529,0.0010765309,0.00092282344,0.00033683836,0.0005018545],"domain_scores_gemma":[0.99270654,0.005191497,0.0004179975,0.0011043721,0.00020189765,0.0003776713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045602312,0.00051387365,0.0011531962,0.0001641938,0.00011970141,0.00011449882,0.00031977202,0.0008378038,0.00017955757],"category_scores_gemma":[0.0071854223,0.0004561605,0.0003563896,0.00015496931,0.00034362634,0.000107340034,0.00023952806,0.0017240599,0.00013733887],"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":[0.000010444312,0.00012525826,0.004495394,0.00026701108,0.00008064438,0.000094479685,0.000011581383,5.4884987e-7,9.50114e-7,0.0015370684,0.99026,0.0031166426],"study_design_scores_gemma":[0.00027716783,0.0006043903,0.00074535236,0.00023752557,0.00025706962,0.000012640325,0.00000210243,0.0000063976736,0.000006640367,0.295663,0.7016744,0.0005132962],"about_ca_topic_score_codex":0.000021388669,"about_ca_topic_score_gemma":0.0000084854855,"teacher_disagreement_score":0.29412594,"about_ca_system_score_codex":0.0000705075,"about_ca_system_score_gemma":0.00009410449,"threshold_uncertainty_score":0.999789},"labels":[],"label_agreement":null},{"id":"W2048433325","doi":"10.1016/j.prevetmed.2008.02.013","title":"Linking causal concepts, study design, analysis and inference in support of one epidemiology for population health","year":2008,"lang":"en","type":"article","venue":"Preventive Veterinary Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"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 Guelph","funders":"","keywords":"Observational study; Causal inference; Causation; Interpretation (philosophy); Inference; Management science; Research design; Population; Causality (physics); Observational methods in psychology; Computer science; Data science; Psychology; Medicine; Epistemology; Engineering; Environmental health; Mathematics; Statistics; Artificial intelligence; Pathology","score_opus":0.46485013698536204,"score_gpt":0.5435031123947849,"score_spread":0.07865297540942284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048433325","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":[0.5236807,0.00012435344,0.4750228,0.00013983861,0.000017615395,0.000967399,0.0000058788837,0.000035296984,0.0000060977554],"genre_scores_gemma":[0.87965065,0.00018603189,0.119792484,0.00010093247,0.000026930307,0.00015737287,0.000043465123,0.0000127848125,0.00002934492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974181,0.00088297384,0.00096968096,0.00032941424,0.00014463531,0.0002551638],"domain_scores_gemma":[0.99471414,0.004269394,0.0005929924,0.00024251931,0.00011020775,0.00007075927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003033079,0.00016925459,0.0010928334,0.00039389773,0.00006908751,8.9942625e-7,0.00010871576,0.00006793613,0.000036222664],"category_scores_gemma":[0.0029048421,0.00014999752,0.000050022005,0.0004266697,0.00021155569,0.00011861614,0.00007498249,0.00014130645,1.7134452e-7],"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":[0.00040378753,0.0007981795,0.9764044,0.00047381068,0.00042516013,0.000039548704,0.008520952,0.00006635386,0.0025606821,0.0036682207,0.000066605025,0.006572248],"study_design_scores_gemma":[0.0022867539,0.022995457,0.7624825,0.000493176,0.00044002975,0.000036936017,0.00078590185,0.0011036416,0.0003800435,0.20863259,0.000037357095,0.00032556825],"about_ca_topic_score_codex":0.00045621124,"about_ca_topic_score_gemma":0.000117279495,"teacher_disagreement_score":0.35596994,"about_ca_system_score_codex":0.00007502503,"about_ca_system_score_gemma":0.00004705203,"threshold_uncertainty_score":0.6116721},"labels":[],"label_agreement":null},{"id":"W2050044081","doi":"10.1093/aje/kwq154","title":"RE: \"SMOKING AND PARKINSON'S DISEASE: USING PARENTAL SMOKING AS A PROXY TO EXPLORE CAUSALITY\"","year":2010,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","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","funders":"","keywords":"Causality (physics); Proxy (statistics); Medicine; Disease; Environmental health; Internal medicine; Statistics; Mathematics","score_opus":0.23258208226122842,"score_gpt":0.45636287507312523,"score_spread":0.2237807928118968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050044081","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":[0.37941292,0.0013390533,0.09295084,0.5229681,0.0015393728,0.0011928868,0.00009411994,0.00029382497,0.00020883215],"genre_scores_gemma":[0.24281488,0.00047499948,0.27930626,0.47189754,0.00505631,0.000076175435,0.000035781028,0.00027730514,0.000060761296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994092,0.0017869283,0.0019719652,0.0006898265,0.0004408181,0.0010185029],"domain_scores_gemma":[0.98657906,0.007660296,0.0041387663,0.0007596458,0.00033441462,0.0005277917],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0036019802,0.00067483616,0.0025772967,0.0005455106,0.0001517347,0.000033673747,0.000678258,0.00080374494,0.000080333266],"category_scores_gemma":[0.019736378,0.0005699245,0.00035081184,0.0003042473,0.0009903093,0.00023471833,0.00033888727,0.0064072106,0.000002218418],"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":[0.0006231494,0.00017925397,0.33295646,0.0007683754,0.0013544175,0.0057933507,0.0025370508,0.000069119174,0.0005000338,0.0041331104,0.6122175,0.03886821],"study_design_scores_gemma":[0.00033744387,0.0014784813,0.002306062,0.0020450403,0.0008055999,0.0016542118,0.0010248653,0.000094901305,0.00009244986,0.39426032,0.5946642,0.0012363966],"about_ca_topic_score_codex":0.00019055254,"about_ca_topic_score_gemma":0.000012685592,"teacher_disagreement_score":0.3901272,"about_ca_system_score_codex":0.00035356104,"about_ca_system_score_gemma":0.00031321595,"threshold_uncertainty_score":0.9996752},"labels":[],"label_agreement":null},{"id":"W2050419204","doi":"10.1111/1468-2354.t01-1-00074","title":"2001 Lawrence R. Klein Lecture Estimating Distributions of Treatment Effects with an Application to the Returns to Schooling and Measurement of the Effects of Uncertainty on College Choice*","year":2003,"lang":"en","type":"article","venue":"International Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":351,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Counterfactual conditional; LISREL; Veil of ignorance; Econometrics; Economics; Matching (statistics); Pairwise comparison; Probit model; Actuarial science; Mathematics; Statistics; Psychology; Microeconomics; Structural equation modeling; Counterfactual thinking; Social psychology","score_opus":0.052827051661603466,"score_gpt":0.3680734952222458,"score_spread":0.31524644356064235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050419204","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":[0.6051443,0.0049109384,0.37079084,0.0039553354,0.00040433096,0.012970982,0.00037346862,0.00008344744,0.0013663288],"genre_scores_gemma":[0.9785174,0.0004962344,0.020373328,0.00013058726,0.000020440642,0.00043949566,0.0000046776477,0.00000983517,0.0000079824495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991562,0.00010472369,0.00034701472,0.00016849718,0.00013717265,0.00008643863],"domain_scores_gemma":[0.99857074,0.00054545637,0.00034975173,0.00034600578,0.0001509704,0.000037094414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439132,0.00012098718,0.00028462897,0.00002893776,0.000038152237,0.000005980643,0.00021043826,0.000023321745,0.0000066699417],"category_scores_gemma":[0.0016303932,0.00006803751,0.000047258098,0.00008653223,0.00003601829,0.00004975188,0.000027007885,0.000059811686,0.0000012866585],"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":[0.00016272962,0.00088461617,0.0032393248,0.009574544,0.00078087015,0.0000014020912,0.00086687837,0.032863278,0.027984194,0.85230434,0.0030936713,0.06824417],"study_design_scores_gemma":[0.0030430881,0.007688483,0.0067604827,0.08370168,0.0011702238,0.00006113772,0.00012506344,0.015296673,0.62524045,0.22190502,0.0337151,0.001292602],"about_ca_topic_score_codex":0.00009215679,"about_ca_topic_score_gemma":0.00045141118,"teacher_disagreement_score":0.6303993,"about_ca_system_score_codex":0.00044421625,"about_ca_system_score_gemma":0.000085856715,"threshold_uncertainty_score":0.27744892},"labels":[],"label_agreement":null},{"id":"W2050791524","doi":"10.1097/ede.0b013e3181f2f8e8","title":"The Multitime Case-control Design for Time-varying Exposures","year":2010,"lang":"en","type":"article","venue":"Epidemiology","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":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Confidence interval; Odds ratio; Estimator; Statistics; Mathematics; Variance (accounting); Moment (physics); Control (management); Correlation; Odds; Medicine; Econometrics; Computer science; Logistic regression; Economics","score_opus":0.22077592784573954,"score_gpt":0.4448999796850942,"score_spread":0.22412405183935466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050791524","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":[0.0068570944,0.00011906447,0.98885614,0.0019180991,0.00025068442,0.0010090754,0.00001769334,0.0003995905,0.00057258346],"genre_scores_gemma":[0.26931494,0.000011492392,0.7282174,0.00081864704,0.00030542654,0.000612737,0.0000025917286,0.00004197912,0.0006747536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796945,0.00066267943,0.0005428623,0.00026710113,0.000044566325,0.0005133553],"domain_scores_gemma":[0.9253269,0.07375479,0.0002546283,0.0004895052,0.000103138555,0.00007104149],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054552522,0.00017898434,0.00044891838,0.00003694913,0.00033393744,0.000009848684,0.00026671746,0.00024268856,0.0001003225],"category_scores_gemma":[0.048045773,0.00011641205,0.00011670973,0.00004256046,0.00023430573,0.00007802431,0.000041018797,0.0003818997,0.000047321304],"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":[0.00023878545,0.00007960042,0.00090403244,0.00004137549,0.00016779847,0.00010982296,0.0002418464,0.00022175084,0.05305227,0.8266531,0.08003425,0.038255323],"study_design_scores_gemma":[0.00035946356,0.00015749007,0.00004767042,0.000007796164,0.000034595574,0.00040499732,0.000012850329,0.017642386,0.0037289842,0.97264254,0.00479632,0.00016490392],"about_ca_topic_score_codex":0.000017953611,"about_ca_topic_score_gemma":0.000037207385,"teacher_disagreement_score":0.26245785,"about_ca_system_score_codex":0.000021312137,"about_ca_system_score_gemma":0.000030878102,"threshold_uncertainty_score":0.9599729},"labels":[],"label_agreement":null},{"id":"W2051341588","doi":"10.1016/j.jclinepi.2009.06.003","title":"Methods to elicit beliefs for Bayesian priors: a systematic review","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":192,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University Health Network; University of Toronto; Toronto General Hospital; Hospital for Sick Children; Public Health Ontario; Sinai Health System","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Expert elicitation; Prior probability; Bayes' theorem; Bayesian probability; Reliability (semiconductor); Context (archaeology); Point estimation; Statistics; Medicine; Computer science; Mathematics","score_opus":0.7724243414633696,"score_gpt":0.7300403061625055,"score_spread":0.0423840353008641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051341588","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":[1.0064986e-8,0.53286314,0.46256688,0.0009979631,0.0003193555,0.0031170216,0.000009705121,0.00004724673,0.0000786968],"genre_scores_gemma":[8.670851e-9,0.51545656,0.47916943,0.004313916,0.00066171517,0.00021748034,0.000003135996,0.000059685583,0.00011803608],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9360711,0.030936677,0.03104023,0.00073815865,0.00035147122,0.00086234993],"domain_scores_gemma":[0.67492414,0.2958188,0.026228806,0.0013849487,0.00089865545,0.0007446758],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.15232192,0.0008829043,0.042646192,0.00041818238,0.000058563728,0.000013302235,0.0017877965,0.0016362695,0.00004498793],"category_scores_gemma":[0.7313355,0.0005343968,0.007331326,0.00045025442,0.00013928635,0.00012477934,0.00017849443,0.0026553227,0.000028893606],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000111249865,0.00009587678,3.160647e-7,0.5579371,0.00038570218,0.000011101533,0.000005889467,1.6415373e-7,2.2931859e-8,0.019545596,0.01363085,0.40837628],"study_design_scores_gemma":[0.000092405055,0.0009939924,1.8975342e-7,0.4407834,0.0039758133,0.00029216707,0.0000016990317,0.0000034679417,8.9738684e-8,0.21754785,0.33605692,0.00025198905],"about_ca_topic_score_codex":9.183625e-7,"about_ca_topic_score_gemma":0.0000014413921,"teacher_disagreement_score":0.5790136,"about_ca_system_score_codex":0.00023160854,"about_ca_system_score_gemma":0.00074808433,"threshold_uncertainty_score":0.99971074},"labels":[],"label_agreement":null},{"id":"W2051866975","doi":"10.1016/j.jtcvs.2007.07.021","title":"Propensity-score matching in the cardiovascular surgery literature from 2004 to 2006: A systematic review and suggestions for improvement","year":2007,"lang":"en","type":"review","venue":"Journal of Thoracic and Cardiovascular Surgery","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":598,"is_retracted":false,"has_abstract":false,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Systematic review; Matching (statistics); Medicine; MEDLINE; General surgery; Surgery; Political science; Pathology","score_opus":0.19215338945083002,"score_gpt":0.4069807759266218,"score_spread":0.21482738647579178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051866975","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":[0.00014274419,0.95085144,0.04381116,0.000056062072,0.00021780867,0.004761902,0.00011568118,0.000034982622,0.000008235802],"genre_scores_gemma":[0.00006971319,0.9943367,0.004271526,0.00023163228,0.00033783057,0.0005868983,0.000038524566,0.00010754121,0.000019587758],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99310094,0.0018202001,0.0028193423,0.0005865056,0.0011449616,0.00052802253],"domain_scores_gemma":[0.9902063,0.0061901566,0.0013134071,0.0014571466,0.0006099101,0.00022308578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02690726,0.00079102686,0.010304021,0.00079337985,0.0001544646,0.00024509724,0.00042443175,0.00043803095,0.0000027264527],"category_scores_gemma":[0.0041796044,0.0004748191,0.0071813683,0.0009147411,0.00006598463,0.00034247452,0.00014919449,0.0011155753,0.000001295338],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012383144,0.000048515027,0.0000060440884,0.6770965,0.0054472447,0.0004684678,0.0001675296,0.000002780814,2.0204136e-7,0.00004481219,0.0015281462,0.3151774],"study_design_scores_gemma":[0.00007293532,0.000046211262,0.000007900733,0.86471295,0.036569364,0.0027440737,0.00010733314,3.4526389e-7,0.0000037327245,0.0041676643,0.090811506,0.00075595884],"about_ca_topic_score_codex":0.000028940089,"about_ca_topic_score_gemma":0.000006260065,"teacher_disagreement_score":0.31442145,"about_ca_system_score_codex":0.00018623669,"about_ca_system_score_gemma":0.0003088178,"threshold_uncertainty_score":0.99977034},"labels":[],"label_agreement":null},{"id":"W2052420143","doi":"10.1016/j.cct.2006.08.007","title":"The effect of omitted covariates on confidence interval and study power in binary outcome analysis: A simulation study","year":2006,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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","funders":"","keywords":"Covariate; Statistics; Confidence interval; Medicine; Coverage probability; Outcome (game theory); Point estimation; Econometrics; Statistical power; Demography; Mathematics","score_opus":0.5132328047401201,"score_gpt":0.6017763023662334,"score_spread":0.08854349762611324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052420143","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":[0.99239254,0.00013086612,0.002536444,0.00008537179,0.00013611311,0.0043828324,0.000012098414,0.00011189756,0.00021186618],"genre_scores_gemma":[0.9995169,0.0000044711437,0.00018060076,0.000025609606,0.000047632493,0.00013928405,0.0000041624517,0.000019697876,0.00006163859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98487335,0.009847088,0.0042414847,0.00048610757,0.00037039444,0.00018155549],"domain_scores_gemma":[0.9042718,0.09349097,0.0014128435,0.0006606412,0.00011222577,0.000051566818],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035439,0.00027365223,0.0022862726,0.00024190206,0.00006854473,0.00005537624,0.00029904814,0.00015148848,0.000013781669],"category_scores_gemma":[0.03935661,0.0001606576,0.00035484493,0.0005403579,0.0001758616,0.00016388882,0.00014577415,0.0003821227,0.000002674608],"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":[0.0032054132,0.0017295261,0.99203295,0.000017532084,0.000607871,0.000034517143,0.00016657465,0.00017495918,0.00004202079,0.0014571182,0.0000879053,0.00044362294],"study_design_scores_gemma":[0.013064814,0.022768905,0.9035909,0.00016235105,0.0011568312,3.4648468e-7,0.0012427645,0.0025717262,0.00025486414,0.054747663,0.00003592612,0.0004029019],"about_ca_topic_score_codex":0.00019692082,"about_ca_topic_score_gemma":0.0001138562,"teacher_disagreement_score":0.088442035,"about_ca_system_score_codex":0.000028239712,"about_ca_system_score_gemma":0.00003528461,"threshold_uncertainty_score":0.99321854},"labels":[],"label_agreement":null},{"id":"W2052462306","doi":"10.1016/j.jclinepi.2014.10.003","title":"A reanalysis of cluster randomized trials showed interrupted time-series studies were valuable in health system evaluation","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":133,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Norges Forskningsråd; McMaster University","keywords":"Randomized controlled trial; Interrupted time series; Medicine; N of 1 trial; Interrupted Time Series Analysis; Psychological intervention; Research design; Cluster (spacecraft); Cluster randomised controlled trial; Statistics; Computer science; Surgery; Mathematics","score_opus":0.7544714292539911,"score_gpt":0.66713741394165,"score_spread":0.08733401531234108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052462306","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":[0.14370754,0.0038448474,0.8229892,0.02351953,0.0014843203,0.0030918696,0.000010257379,0.00012311299,0.001229298],"genre_scores_gemma":[0.56951624,0.0021269608,0.42674306,0.0009174304,0.00043172718,0.00007548008,0.000004407179,0.000032400792,0.00015229014],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78988975,0.17500596,0.033228584,0.0005045397,0.00078892277,0.00058223814],"domain_scores_gemma":[0.4189849,0.54330176,0.03424397,0.00082393305,0.0023833907,0.0002620637],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5154079,0.0002463388,0.01518616,0.00039076034,0.000035472338,0.0000051048137,0.00033247677,0.00034979935,0.000092180824],"category_scores_gemma":[0.81081223,0.00015135677,0.0015986516,0.00021847902,0.00046629878,0.00020647641,0.00010415502,0.0007241053,0.0000051927873],"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":[0.31622127,0.0020377906,0.01664329,0.005630867,0.014616006,0.000024217772,0.0029154003,0.009226447,0.00032708683,0.48253122,0.053656332,0.09617008],"study_design_scores_gemma":[0.051468145,0.0015308742,0.00027685883,0.0022453782,0.0010233526,0.000030269426,0.0005678738,0.041552283,0.000058066846,0.9008746,0.00020553201,0.00016675175],"about_ca_topic_score_codex":0.000028528699,"about_ca_topic_score_gemma":0.00004307065,"teacher_disagreement_score":0.42580873,"about_ca_system_score_codex":0.00023382262,"about_ca_system_score_gemma":0.00029211855,"threshold_uncertainty_score":0.9994344},"labels":[],"label_agreement":null},{"id":"W2052567024","doi":"10.1037/1082-989x.12.3.247","title":"Combining propensity score matching and group-based trajectory analysis in an observational study.","year":2007,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":285,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Mental Health","keywords":"Propensity score matching; Covariate; Observational study; Matching (statistics); Mahalanobis distance; Statistics; Trajectory; Mathematics; Econometrics","score_opus":0.7505569186862165,"score_gpt":0.6029601374272204,"score_spread":0.1475967812589961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052567024","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":[0.53224874,0.000008115736,0.46711665,0.000018491732,0.000020585596,0.0002803985,0.000001146544,0.00014043052,0.00016540561],"genre_scores_gemma":[0.51991904,5.851282e-7,0.4798669,0.00016659955,0.000009833866,0.000023662134,0.0000045982624,0.000006699965,0.0000020826403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973857,0.0010480005,0.0005275923,0.00052029284,0.0002229732,0.00029545047],"domain_scores_gemma":[0.9964577,0.0028170345,0.00016705121,0.00037771137,0.000068456044,0.00011207951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071391575,0.00019653807,0.00052360696,0.00028343173,0.00008469209,0.000035924266,0.00021048693,0.00014730004,0.000056194614],"category_scores_gemma":[0.001111004,0.00015566885,0.00006999222,0.00086318987,0.0001068295,0.00018244417,0.00005779812,0.0004400316,5.900721e-7],"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":[0.00018829828,0.0020710246,0.92895716,0.000020964879,0.00006376801,0.00005678197,0.00073295145,0.000044860226,0.011234982,0.017358858,0.0000035778921,0.03926678],"study_design_scores_gemma":[0.00034023804,0.00044387815,0.7458445,0.000011814829,0.00006288737,0.0000019154754,0.00020856019,0.00022907305,0.00030403188,0.25238758,0.000002279458,0.00016325148],"about_ca_topic_score_codex":0.000022235577,"about_ca_topic_score_gemma":0.00018574718,"teacher_disagreement_score":0.23502871,"about_ca_system_score_codex":0.000052018342,"about_ca_system_score_gemma":0.0000061425344,"threshold_uncertainty_score":0.6347992},"labels":[],"label_agreement":null},{"id":"W2052946410","doi":"10.1007/s10654-009-9341-z","title":"The impact of unmeasured baseline effect modification on estimates from an inverse probability of treatment weighted logistic model","year":2009,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"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":"Logistic regression; Marginal structural model; Statistics; Confounding; Inverse probability; Medicine; Econometrics; Marginal model; Conditional probability; Outcome (game theory); Inverse; Mathematics; Regression analysis; Posterior probability","score_opus":0.3754827724468073,"score_gpt":0.4844572698861677,"score_spread":0.10897449743936044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052946410","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":[0.6590368,0.00009868149,0.34012738,0.00021099256,0.000023183427,0.00024018962,0.000025966845,0.000030653282,0.00020615684],"genre_scores_gemma":[0.86611295,0.00010107625,0.13368234,0.000030444968,0.000042449286,0.0000016586639,0.000010192726,0.000015076147,0.0000037838133],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99358964,0.0044660345,0.0014424068,0.00018494636,0.00010613371,0.00021083109],"domain_scores_gemma":[0.98855543,0.00859555,0.0018502488,0.00057805167,0.00030881946,0.000111879686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008120124,0.00021592999,0.00081371894,0.000081013655,0.000046299345,0.0000033002768,0.00031537501,0.00005397425,0.000009668511],"category_scores_gemma":[0.0201963,0.00011093933,0.0002525964,0.000081335544,0.00023485006,0.000089410685,0.000015609958,0.00022200227,0.0000018934725],"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":[0.009370861,0.004176166,0.022171395,0.000113663526,0.001095158,0.0000711366,0.0015093744,0.5639545,0.1470204,0.08749802,0.0032484299,0.15977095],"study_design_scores_gemma":[0.0006563862,0.011799791,0.009964371,0.000121121055,0.00012344457,0.000012009597,0.000007966219,0.22722673,0.0066602235,0.74331695,0.00000514613,0.00010583954],"about_ca_topic_score_codex":0.000030047715,"about_ca_topic_score_gemma":0.0000042267634,"teacher_disagreement_score":0.65581894,"about_ca_system_score_codex":0.00023472455,"about_ca_system_score_gemma":0.000081780745,"threshold_uncertainty_score":0.988057},"labels":[],"label_agreement":null},{"id":"W2053148876","doi":"10.1007/s10464-013-9604-4","title":"Drawing Causal Inferences Using Propensity Scores: A Practical Guide for Community Psychologists","year":2013,"lang":"en","type":"article","venue":"American Journal of Community Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":114,"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 Drug Policy Research Network; St. Michael's Hospital","funders":"National Institute on Drug Abuse","keywords":"Propensity score matching; Causal inference; Observational study; Confounding; Psychology; Context (archaeology); Matching (statistics); Population; Reading (process); Developmental psychology; Medicine","score_opus":0.4407666304698102,"score_gpt":0.5491168697343298,"score_spread":0.10835023926451964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053148876","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":[0.7319887,0.000015833532,0.26479185,0.0014385016,0.00017454871,0.00044169754,0.000005161763,0.00008612077,0.0010575654],"genre_scores_gemma":[0.69428074,0.00003256036,0.30404067,0.0014936113,0.000074782874,0.000026051224,0.000002559555,0.000035670117,0.00001335067],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9929542,0.0047283783,0.0013069438,0.000142359,0.00030501047,0.0005630847],"domain_scores_gemma":[0.98888123,0.006175598,0.002066945,0.0013165178,0.0013199126,0.00023976657],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0043728678,0.00034683125,0.001104611,0.0003140223,0.00072621804,0.00009483484,0.0013116712,0.00017067243,0.000080775135],"category_scores_gemma":[0.006450225,0.00028927054,0.000220858,0.00041564516,0.0018884898,0.0007575141,0.00030205733,0.0033392645,0.000008764142],"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":[0.004929186,0.022532435,0.08903548,0.0008300157,0.0031567237,0.00024889442,0.056383286,0.00011175112,0.17124262,0.06743705,0.14572863,0.4383639],"study_design_scores_gemma":[0.0020280085,0.011383692,0.038319375,0.00043325857,0.00025057863,0.0038891237,0.012476776,0.00011644443,0.0012431892,0.9258906,0.0030984725,0.00087045704],"about_ca_topic_score_codex":0.0016226531,"about_ca_topic_score_gemma":0.00026849593,"teacher_disagreement_score":0.8584536,"about_ca_system_score_codex":0.00014779498,"about_ca_system_score_gemma":0.00022108514,"threshold_uncertainty_score":0.99995595},"labels":[],"label_agreement":null},{"id":"W2053903767","doi":"10.1016/j.jclinepi.2006.07.016","title":"Simulations showed that validation of database-derived diagnostic criteria based on a small subsample reduced bias","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Arthritis Research Centre of Canada; McGill University Health Centre; Montreal General Hospital; University of British Columbia; McGill University","funders":"","keywords":"Statistics; Database; Medicine; Computer science; Mathematics","score_opus":0.7902486332320969,"score_gpt":0.6113332320112396,"score_spread":0.17891540122085736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053903767","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":[0.5065871,0.000015813792,0.49168336,0.00090105005,0.0003449278,0.00019545767,0.000028675648,0.00003838467,0.00020523061],"genre_scores_gemma":[0.7279072,0.0000543278,0.27114594,0.00057389674,0.00025848046,0.000002834022,0.00002402556,0.000023762592,0.000009520985],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99053735,0.0034258754,0.005090294,0.00028918358,0.00026644615,0.00039087466],"domain_scores_gemma":[0.67542547,0.31857827,0.004667209,0.0005504019,0.00053462596,0.00024399489],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028698279,0.00022687556,0.002002042,0.00028799506,0.000050080685,0.0000062909785,0.0003792035,0.00037921977,0.00038104446],"category_scores_gemma":[0.5076091,0.00017774683,0.0004832877,0.00019283166,0.00027837118,0.0001684034,0.000061499515,0.00081981445,0.000005065433],"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":[0.008955144,0.008320542,0.7176142,0.0009144724,0.0009121232,0.00024771647,0.0005188875,0.010164288,0.092303745,0.10837519,0.024430864,0.027242852],"study_design_scores_gemma":[0.0033273315,0.0040499484,0.14125662,0.001242355,0.0004008338,0.000050644325,0.000118442214,0.013249036,0.07834996,0.7564519,0.0009445238,0.000558384],"about_ca_topic_score_codex":0.000015349886,"about_ca_topic_score_gemma":0.000034676985,"teacher_disagreement_score":0.6480767,"about_ca_system_score_codex":0.000059343944,"about_ca_system_score_gemma":0.00017066303,"threshold_uncertainty_score":0.9946308},"labels":[],"label_agreement":null},{"id":"W2054723033","doi":"10.2202/1557-4679.1146","title":"Type I Error Rates, Coverage of Confidence Intervals, and Variance Estimation in Propensity-Score Matched Analyses","year":2009,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":189,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Confidence interval; Matching (statistics); Sample size determination; Observational study; Hazard ratio; Poisson regression; Type I and type II errors; Mathematics; Selection bias; Poisson distribution; Econometrics; Medicine; Population","score_opus":0.23169680834955775,"score_gpt":0.46242425669277515,"score_spread":0.2307274483432174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054723033","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":[0.39586854,0.00013840871,0.60246295,0.0010564016,0.00015187873,0.00014857114,0.00003071132,0.0000124475255,0.00013011583],"genre_scores_gemma":[0.91051656,0.00023231034,0.08901347,0.00017271382,0.000024881945,5.794464e-7,0.0000037371874,0.0000063215,0.000029424473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878424,0.000078459205,0.0006175352,0.000079833655,0.0003544423,0.0000854835],"domain_scores_gemma":[0.9977137,0.000642649,0.000756833,0.00012047074,0.0007367491,0.000029611369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001221,0.00010323472,0.00027183382,0.00012997858,0.000017860486,0.00004099621,0.00034467236,0.000042134532,0.000022326205],"category_scores_gemma":[0.0022444031,0.0000717439,0.00002881018,0.00012729003,0.00009224318,0.00020690158,0.00004662605,0.00021406425,0.0000010052395],"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":[0.0017859385,0.00073317846,0.0064249383,0.00017118147,0.00047333742,0.0005352585,0.003938177,0.0026315935,0.13741635,0.78732747,0.003423775,0.055138815],"study_design_scores_gemma":[0.00043275696,0.0004054245,0.017070042,0.00056692294,0.000055671186,0.00021214307,0.00011949825,0.005402871,0.031890642,0.9436967,0.000029388088,0.000117969874],"about_ca_topic_score_codex":0.00002360756,"about_ca_topic_score_gemma":0.000021472366,"teacher_disagreement_score":0.514648,"about_ca_system_score_codex":0.00006783221,"about_ca_system_score_gemma":0.00008127855,"threshold_uncertainty_score":0.29256314},"labels":[],"label_agreement":null},{"id":"W2054826081","doi":"10.1002/sim.3036","title":"Use of instrumental variables in the analysis of generalized linear models in the presence of unmeasured confounding with applications to epidemiological research","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":72,"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; University of Toronto; St. Paul's Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Confounding; Generalized linear model; Instrumental variable; Epidemiology; Poisson distribution; Econometrics; Poisson regression; Linear model; Statistics; Logistic regression; Medicine; Computer science; Mathematics; Population; Environmental health; Internal medicine","score_opus":0.4857623800456914,"score_gpt":0.5493356677123323,"score_spread":0.06357328766664094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054826081","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":[0.18486494,0.000020090147,0.8138846,0.00015186194,0.000004152489,0.0007751886,0.000070248294,0.0000048205816,0.00022408832],"genre_scores_gemma":[0.62936425,0.000047993566,0.37044644,0.00004078486,0.0000070860942,0.000069207505,0.00001682031,0.0000040806553,0.0000033283986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973165,0.0006899157,0.00090667955,0.00017247275,0.0006860294,0.00022842066],"domain_scores_gemma":[0.9836292,0.015388818,0.00023999992,0.0004445317,0.0002691509,0.000028253786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011111337,0.00009676557,0.00055440626,0.00057201006,0.000023381172,0.0000026259693,0.00039989466,0.00006144163,0.000012855481],"category_scores_gemma":[0.0078057987,0.00005076166,0.000017123248,0.0024230038,0.0005956807,0.000047660495,0.000051483392,0.00033439917,6.377226e-8],"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":[0.0001371149,0.00018064323,0.014631403,0.00007702376,0.0000465273,0.000007272327,0.004636482,0.0063631986,0.0027990453,0.97033715,0.000099631725,0.00068450975],"study_design_scores_gemma":[0.0005830284,0.0004546605,0.01702068,0.00040232515,0.00014345351,0.0000025185973,0.006075015,0.043363858,0.0012314704,0.9305879,0.000032737065,0.00010233857],"about_ca_topic_score_codex":0.0013984608,"about_ca_topic_score_gemma":0.0022614794,"teacher_disagreement_score":0.4444993,"about_ca_system_score_codex":0.000065370616,"about_ca_system_score_gemma":0.000044196924,"threshold_uncertainty_score":0.9344834},"labels":[],"label_agreement":null},{"id":"W2054829060","doi":"10.2202/1557-4679.1205","title":"Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"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":"Propensity score matching; Bayesian probability; Outcome (game theory); Bayesian linear regression; Statistics; Regression; Econometrics; Bayes' theorem; Confounding; Regression analysis; Posterior probability; Mathematics; Bayesian inference; Computer science","score_opus":0.1513029616466612,"score_gpt":0.41370864719192163,"score_spread":0.26240568554526045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054829060","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":[0.1672452,0.00009933176,0.8208956,0.008388559,0.002210033,0.000737385,0.00008070514,0.000031640455,0.00031153875],"genre_scores_gemma":[0.8278555,0.00007992966,0.17120446,0.00027957,0.00045434228,0.000010300489,0.0000028458314,0.000017649054,0.00009536627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988306,0.00003977483,0.00048641613,0.000078976336,0.00043207366,0.00013216285],"domain_scores_gemma":[0.9965772,0.001960562,0.0006140758,0.00018093419,0.0006332103,0.00003402566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010745877,0.00010805203,0.00015923125,0.00007212295,0.000074929005,0.000052531726,0.0007145498,0.00004812908,0.000034693556],"category_scores_gemma":[0.0027614892,0.000052665808,0.00006113832,0.000060878607,0.00011123024,0.00010802465,0.000104135965,0.0004655292,0.0000014228756],"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":[0.0007588313,0.00038592474,0.0040741717,0.000066616274,0.0002644867,0.000105247746,0.0018731931,0.00009769273,0.03486011,0.6685491,0.028988417,0.2599762],"study_design_scores_gemma":[0.00077651,0.0001817338,0.0073016984,0.00041612645,0.0000676352,0.00030499217,0.00036644895,0.003634653,0.02593419,0.95810664,0.0027497443,0.00015963515],"about_ca_topic_score_codex":0.000017136486,"about_ca_topic_score_gemma":0.00014779667,"teacher_disagreement_score":0.6606103,"about_ca_system_score_codex":0.000080481164,"about_ca_system_score_gemma":0.00008899316,"threshold_uncertainty_score":0.330596},"labels":[],"label_agreement":null},{"id":"W2055216855","doi":"10.1016/j.jclinepi.2013.05.003","title":"The exposure-crossover design is a new method for studying sustained changes in recurrent events","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":36,"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 Toronto; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Health Sciences Centre","funders":"","keywords":"Confounding; Crossover; Crossover study; Confidence interval; Research design; Matching (statistics); Statistical power; Relative risk; Clinical study design; Statistics; Causal inference; Medicine; Psychology; Computer science; Mathematics; Artificial intelligence; Clinical trial; Internal medicine","score_opus":0.7022817653295406,"score_gpt":0.6384360823110963,"score_spread":0.06384568301844429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055216855","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":[0.011622772,0.00063625193,0.96418893,0.021943139,0.0005596565,0.0009990596,0.0000014727439,0.000024133988,0.00002455378],"genre_scores_gemma":[0.025892967,0.0014387505,0.9683775,0.0029752909,0.0007319805,0.00010253224,3.8002463e-7,0.00003190278,0.00044875417],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98972,0.0051566795,0.004103862,0.00026031688,0.00018702548,0.00057213305],"domain_scores_gemma":[0.78914255,0.20565431,0.0039737523,0.00040285118,0.0005594557,0.00026706565],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04374929,0.00020202599,0.0018560111,0.00009436111,0.00007888144,0.000013829054,0.0005220107,0.00032289905,0.000055423523],"category_scores_gemma":[0.19758753,0.000116734365,0.00040844624,0.00012195889,0.000104111794,0.00015458456,0.00010789727,0.000888973,0.0000048342304],"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":[0.0019989596,0.0005844306,0.024942143,0.00010271605,0.00038115346,0.0000116129995,0.00080050324,0.000089137844,0.00013885366,0.060153086,0.14043619,0.77036124],"study_design_scores_gemma":[0.0014378914,0.0021588008,0.0043178927,0.00012677409,0.000043546945,0.000016125874,0.00022796425,0.0014950635,0.0001298283,0.9858481,0.004073343,0.00012463292],"about_ca_topic_score_codex":0.000022623919,"about_ca_topic_score_gemma":0.000042685497,"teacher_disagreement_score":0.92569506,"about_ca_system_score_codex":0.000089618836,"about_ca_system_score_gemma":0.0002197187,"threshold_uncertainty_score":0.98466134},"labels":[],"label_agreement":null},{"id":"W2055588546","doi":"10.2202/1557-4679.1240","title":"Special Issue on Causal Inference","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Causal inference; Biostatistics; Inference; Computer science; Library science; Econometrics; Data science; Management science; Mathematics; Engineering; Medicine; Artificial intelligence; Public health","score_opus":0.07737566703058796,"score_gpt":0.4291898214705514,"score_spread":0.35181415443996344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055588546","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":[0.29682028,0.000027414822,0.5139879,0.026088787,0.046649117,0.0008462745,0.00076630677,0.00030037505,0.11451357],"genre_scores_gemma":[0.76940686,0.00008263264,0.19819285,0.0012221795,0.03003765,0.0000037991913,0.000007008761,0.000042337448,0.00100471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985591,0.000037740523,0.00047663765,0.00008231892,0.00071097596,0.0001332021],"domain_scores_gemma":[0.99664414,0.001797336,0.00052821724,0.00019952079,0.0007660053,0.00006476112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051862164,0.00012766493,0.00016970215,0.000118702614,0.000050774088,0.00007687051,0.00086027675,0.00006357709,0.0009110947],"category_scores_gemma":[0.0042245104,0.0000830088,0.00005962692,0.000063852545,0.0001579962,0.00011684373,0.000083743456,0.00067474344,0.00005830829],"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":[0.00013356398,0.0001354013,0.00016175838,0.000004642292,0.00008600962,0.00013499559,0.00037281372,0.000009952352,0.006069054,0.8101667,0.14187203,0.040853072],"study_design_scores_gemma":[0.0003109713,0.00027810782,0.00044559131,0.00006567483,0.00003125392,0.00023414608,0.00009601616,0.00009661476,0.019890243,0.856764,0.12164264,0.00014469452],"about_ca_topic_score_codex":0.0000067204505,"about_ca_topic_score_gemma":0.00004880181,"teacher_disagreement_score":0.47258654,"about_ca_system_score_codex":0.000058928308,"about_ca_system_score_gemma":0.00010696412,"threshold_uncertainty_score":0.9975848},"labels":[],"label_agreement":null},{"id":"W2055787965","doi":"10.3138/cpp.34.3.321","title":"The Employment Impacts of Active Labour Market Policy: The Case of SSP Plus","year":2008,"lang":"fr","type":"article","venue":"Canadian Public Policy","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.08530499071836906,"score_gpt":0.3722538840639553,"score_spread":0.28694889334558626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055787965","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":[0.5411287,0.0051640333,0.0006872262,0.34081805,0.00061660755,0.0032062014,0.007631747,0.00021417305,0.100533254],"genre_scores_gemma":[0.9763542,0.0015594835,0.00065115275,0.0018636215,0.0005909127,0.0000843891,0.0000070660294,0.000084991145,0.018804196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658036,0.00046275384,0.0007914541,0.00029179646,0.0003139584,0.0015596873],"domain_scores_gemma":[0.99462205,0.0013785171,0.0006777364,0.0014778707,0.0006421007,0.0012017206],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008706077,0.00041754395,0.00057232025,0.00076225965,0.000729382,0.00007701508,0.0009767013,0.00031321004,0.00039874497],"category_scores_gemma":[0.0072428263,0.00029904436,0.00021959505,0.0017260718,0.0019002507,0.0004198023,0.00019859114,0.000557508,0.000018672496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001896095,0.000055432807,0.00010227203,0.0001111761,0.00019385968,0.00039982493,0.003783717,0.0000019120369,0.000044927252,0.90579027,0.053312026,0.036185637],"study_design_scores_gemma":[0.0010235503,0.0004664401,0.0047733923,0.00032643153,0.00012267148,0.0073936908,0.0042944876,0.00028303865,0.005223502,0.45201275,0.52324045,0.0008395804],"about_ca_topic_score_codex":0.85414714,"about_ca_topic_score_gemma":0.7513916,"teacher_disagreement_score":0.46992844,"about_ca_system_score_codex":0.0037016578,"about_ca_system_score_gemma":0.025655884,"threshold_uncertainty_score":0.9999462},"labels":[],"label_agreement":null},{"id":"W2056327417","doi":"10.1007/s10928-012-9285-x","title":"Compliance spectrum as a drug fingerprint of drug intake and drug disposition","year":2012,"lang":"en","type":"article","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"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 Health Centre; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; World Health Organization","keywords":"Drug; Disposition; Computer science; Population; Bayesian probability; Compliance (psychology); Quality (philosophy); Risk analysis (engineering); Medicine; Econometrics; Pharmacology; Artificial intelligence; Mathematics; Psychology; Social psychology","score_opus":0.060639695914000286,"score_gpt":0.39738881001022913,"score_spread":0.3367491140962289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056327417","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":[0.98083806,0.0019803161,0.0151203945,0.00075930334,0.00043207288,0.00026356493,0.000039526138,0.000038763035,0.00052798685],"genre_scores_gemma":[0.9735493,0.0048148558,0.020956676,0.0001973605,0.0003056427,0.000004484024,0.0000029685261,0.000041887528,0.0001268112],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981745,0.00012019226,0.0008258035,0.00015660109,0.00037038076,0.0003525629],"domain_scores_gemma":[0.9979705,0.00041650728,0.0009369976,0.00014680279,0.00021406297,0.00031508968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095975917,0.00028130985,0.00049935473,0.00019004648,0.000080061975,0.00003619798,0.00023211965,0.00004542072,0.00008397668],"category_scores_gemma":[0.00007310996,0.00025184322,0.00010849092,0.00016816719,0.00018034127,0.00042690095,0.00015907377,0.00058041204,0.0000015335893],"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":[0.0015191477,0.0028835011,0.020131808,0.0036356684,0.0010147203,0.00014294406,0.018087057,0.00047243637,0.75329095,0.13314962,0.012258469,0.053413697],"study_design_scores_gemma":[0.005718762,0.00041197077,0.0039320006,0.0016289292,0.0016215984,0.0014435011,0.0011938898,0.03792476,0.58072776,0.35409856,0.009780549,0.0015177365],"about_ca_topic_score_codex":0.000013425758,"about_ca_topic_score_gemma":0.00000395117,"teacher_disagreement_score":0.22094892,"about_ca_system_score_codex":0.00007618852,"about_ca_system_score_gemma":0.000036756162,"threshold_uncertainty_score":0.9999934},"labels":[],"label_agreement":null},{"id":"W2056621649","doi":"10.1214/10-sts321","title":"Identification, Inference and Sensitivity Analysis for Causal Mediation Effects","year":2010,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1558,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; University of Wisconsin-Madison; University of Pennsylvania; Harvard University; National Science Foundation","keywords":"Causal inference; Estimator; Robustness (evolution); Identification (biology); Sensitivity (control systems); Randomized experiment; Inference; Causal model; Parametric statistics","score_opus":0.05207382361030993,"score_gpt":0.4371451219746848,"score_spread":0.38507129836437487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056621649","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":[0.18196751,0.000001050317,0.8173853,0.000081725404,0.00008277083,0.00025845933,0.000057069694,0.00009072391,0.00007535482],"genre_scores_gemma":[0.7764116,0.0000014634646,0.22346887,0.000023325589,0.000022454999,0.00004510211,0.000007246261,0.0000043623463,0.000015575552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987804,0.000040717165,0.00021147699,0.00037923042,0.00033488488,0.00025323688],"domain_scores_gemma":[0.99408096,0.005082025,0.00010447693,0.00026225278,0.00031784826,0.00015244556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016607294,0.000098535515,0.00018165815,0.00014770863,0.00022145496,0.000104654115,0.00010115028,0.000051454812,0.00001976052],"category_scores_gemma":[0.023385517,0.00008530857,0.00002013267,0.0006903958,0.00084091845,0.00031484847,0.000064305255,0.00013764962,0.0000037598386],"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":[0.0000031213578,0.000022621021,0.003487406,0.000028107042,0.000008956951,0.0000018878368,0.00008474752,0.0000019666754,0.14909129,0.8422166,0.00003918402,0.005014085],"study_design_scores_gemma":[0.000077205026,0.000044522072,0.09991317,0.0000041834155,0.00009859279,0.000002692269,0.000011114556,0.022031447,0.036300242,0.84135634,0.000018941853,0.00014157593],"about_ca_topic_score_codex":0.00002195275,"about_ca_topic_score_gemma":0.00034688856,"teacher_disagreement_score":0.5944441,"about_ca_system_score_codex":0.000030140995,"about_ca_system_score_gemma":0.000080307356,"threshold_uncertainty_score":0.9848409},"labels":[],"label_agreement":null},{"id":"W2057800162","doi":"10.1515/em-2013-0017","title":"On the Impact of Misclassification in an Ordinal Exposure Variable","year":2014,"lang":"en","type":"article","venue":"Epidemiologic Methods","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":"University of British Columbia","funders":"","keywords":"Statistics; Variable (mathematics); Ordinal data; Variables; Ordinal regression; Econometrics; Linear regression; Outcome (game theory); Mathematics; Regression analysis; Test (biology); Power (physics); Psychology; Mathematical economics","score_opus":0.49120425733089457,"score_gpt":0.5830706497350668,"score_spread":0.09186639240417227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057800162","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":[0.13747644,0.00001630763,0.8546106,0.00017373348,0.00002786401,0.00023414081,0.0000022217084,0.00009442928,0.0073642605],"genre_scores_gemma":[0.37746802,0.000005239514,0.62231314,0.00009397641,0.000023183016,0.000050479073,0.0000022713962,0.000008544981,0.00003510897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99358386,0.0052476926,0.00058108894,0.0002580571,0.00008429863,0.0002450054],"domain_scores_gemma":[0.96760285,0.03111091,0.0004103432,0.0007480867,0.000078079254,0.000049755163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0189144,0.0001643113,0.0005070185,0.00007526592,0.000041025243,0.0000059334457,0.0003432255,0.00017328064,0.00021125816],"category_scores_gemma":[0.07083631,0.0000852773,0.000092687864,0.0002406305,0.00010254176,0.00008295176,0.00003863851,0.0003261352,0.000003107845],"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":[0.00002863081,0.00009361103,0.0051286854,0.00001250914,0.000008566197,1.7583419e-7,0.00007096356,0.00037553956,0.021304367,0.96002597,0.0011792141,0.01177177],"study_design_scores_gemma":[0.00007468719,0.00065205275,0.011237732,0.000038380596,0.0000061511887,0.0000014716566,0.000036529167,0.010150022,0.004757248,0.9728947,0.000055433655,0.00009553915],"about_ca_topic_score_codex":0.00006800758,"about_ca_topic_score_gemma":0.0000028997677,"teacher_disagreement_score":0.23999159,"about_ca_system_score_codex":0.00008108823,"about_ca_system_score_gemma":0.000027845506,"threshold_uncertainty_score":0.93699044},"labels":[],"label_agreement":null},{"id":"W2058108606","doi":"10.1007/s11135-011-9452-y","title":"Reporting missing data: a study of selected articles published from 2003–2007","year":2011,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"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":"Missing data; Empirical research; Consistency (knowledge bases); Set (abstract data type); Psychology; Medicine; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.7002650406185921,"score_gpt":0.5250751842288542,"score_spread":0.17518985638973783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058108606","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":[0.9415895,0.000036026344,0.05625086,0.000025611935,0.0001147489,0.000505537,0.00005385719,0.00057760463,0.00084628887],"genre_scores_gemma":[0.84965026,0.0000024369626,0.15017237,0.000026352664,0.00004560037,0.000011451491,0.000036524612,0.00002704836,0.000027944068],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953106,0.0005738194,0.0025910998,0.0006350868,0.00053053943,0.00035882366],"domain_scores_gemma":[0.9930218,0.00059584255,0.0030320007,0.0022693824,0.0009644191,0.0001165859],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005039407,0.0002252506,0.00075301854,0.00009619814,0.000121714496,0.00007167942,0.00067402085,0.00012681288,0.00036105185],"category_scores_gemma":[0.044730593,0.00021095457,0.000044445376,0.00087125844,0.00011396206,0.0011238063,0.0004060348,0.00033277055,0.00000810955],"study_design_candidate":"observational","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":[0.0002878784,0.007897157,0.88199943,0.00032372968,0.00043214325,0.0000844292,0.017285414,5.15093e-7,0.03305797,0.044093672,0.007067103,0.007470546],"study_design_scores_gemma":[0.0010668654,0.0005097124,0.4167272,0.00020672684,0.0002786849,0.0000070718843,0.008264817,0.0005710956,0.08003349,0.4913895,0.00012874955,0.0008160869],"about_ca_topic_score_codex":0.014909669,"about_ca_topic_score_gemma":0.0035358137,"teacher_disagreement_score":0.46527225,"about_ca_system_score_codex":0.000053425876,"about_ca_system_score_gemma":0.00015071596,"threshold_uncertainty_score":0.9916501},"labels":[],"label_agreement":null},{"id":"W2058823385","doi":"10.1002/pds.1360","title":"Application of lag‐time into exposure definitions to control for protopathic bias","year":2007,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":174,"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; Université de Montréal; Hôtel-Dieu de Montréal; Montreal General Hospital; Hotel Dieu Hospital","funders":"","keywords":"Quartile; Medicine; Lag; Logistic regression; Odds ratio; Distributed lag; Statistics; Lag time; Pharmacoepidemiology; Time lag; Confidence interval; Internal medicine; Mathematics; Computer science","score_opus":0.15843834965811754,"score_gpt":0.44706519676730516,"score_spread":0.2886268471091876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058823385","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":[0.023953618,0.00013482888,0.9708581,0.001762416,0.000034616867,0.0024090405,0.00006894008,0.00017425406,0.0006041659],"genre_scores_gemma":[0.8369892,0.000046496778,0.16083631,0.0011283213,0.00007577558,0.00084587635,0.000020991796,0.000018007255,0.00003898402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983491,0.00031534123,0.0007140413,0.0002757825,0.00006407548,0.00028168035],"domain_scores_gemma":[0.9897849,0.009423424,0.00028841698,0.00021134886,0.00017176152,0.00012012921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061574522,0.00016016421,0.000471044,0.00009998482,0.00012444337,0.0000019491226,0.00013066625,0.00012618938,0.000023796309],"category_scores_gemma":[0.004052314,0.00014184922,0.000074617856,0.00012280872,0.00013089672,0.000079240104,0.00004262042,0.00017839993,0.0000102345475],"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":[0.0013945055,0.00026289726,0.014303202,0.00046515797,0.0000939137,0.0000023049372,0.0010746778,0.00006361619,0.078718275,0.8571143,0.0040218406,0.0424853],"study_design_scores_gemma":[0.0010916089,0.00017585755,0.0016235,0.000048717586,0.00009132976,0.00001274465,0.00006145341,0.001247421,0.030320745,0.9587809,0.0063149324,0.00023079028],"about_ca_topic_score_codex":0.000020685042,"about_ca_topic_score_gemma":0.000016057942,"teacher_disagreement_score":0.8130356,"about_ca_system_score_codex":0.000034739758,"about_ca_system_score_gemma":0.000025201503,"threshold_uncertainty_score":0.5784443},"labels":[],"label_agreement":null},{"id":"W2059088090","doi":"10.5539/jmr.v4n4p40","title":"Index for Proportional Reduction in Error in Two-way Contingency Tables with Ordinal Categories","year":2012,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Contingency table; Mathematics; Measure (data warehouse); Statistics; Ordinal data; Variable (mathematics); Degree (music); Value (mathematics); Index (typography); Contingency; Data mining; Computer science","score_opus":0.3614183464519599,"score_gpt":0.5403584006621065,"score_spread":0.17894005421014658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059088090","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":[0.8936471,0.00018059062,0.10383016,0.00035174642,0.00008664988,0.0009487408,0.0000045384304,0.000023582086,0.00092690956],"genre_scores_gemma":[0.8010738,0.000023105127,0.19837357,0.000002073416,0.00017734313,0.00009356917,0.0000013315558,0.00003081681,0.00022441239],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718666,0.0001477542,0.00096667954,0.00012189239,0.0009838005,0.00059322984],"domain_scores_gemma":[0.99714655,0.00095172145,0.0005525923,0.00020155012,0.0010324813,0.00011509636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075621647,0.00015409676,0.0004548047,0.0007939361,0.00007869047,0.00004532146,0.00026724162,0.000085110834,0.000065185675],"category_scores_gemma":[0.0025002228,0.00011074828,0.00005930666,0.00055526884,0.0001856166,0.0007224258,0.000062086234,0.00076418713,0.000002220158],"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":[0.001141607,0.0058379634,0.07302367,0.0028762866,0.00015554171,0.00008483998,0.016610142,0.00027038285,0.019554012,0.8723243,0.0035472612,0.0045740018],"study_design_scores_gemma":[0.0013664409,0.00053687434,0.0014224077,0.000869005,0.000019302286,0.00046991248,0.0090854205,0.0007625098,0.013641214,0.97135806,0.00025006713,0.00021881064],"about_ca_topic_score_codex":0.000034548437,"about_ca_topic_score_gemma":0.00016461991,"teacher_disagreement_score":0.09903374,"about_ca_system_score_codex":0.00035627323,"about_ca_system_score_gemma":0.00028127228,"threshold_uncertainty_score":0.4516184},"labels":[],"label_agreement":null},{"id":"W2060057132","doi":"10.5539/ijsp.v2n4p93","title":"Performance of Principal Stratification Method Adjusting for Treatment Noncompliance in Two Arms of a Randomized Trial","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Statistics; Mathematics; Econometrics; Robustness (evolution); Stratification (seeds); Hazard ratio; Confidence interval","score_opus":0.14819206932506174,"score_gpt":0.4638851354841705,"score_spread":0.31569306615910875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060057132","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":[0.526318,0.000013305479,0.47261983,0.00005562668,0.00006595472,0.00081884797,0.00005670571,0.00000270905,0.000049034814],"genre_scores_gemma":[0.51472574,0.00003523375,0.4851472,0.0000018009885,0.00002459707,0.000054968743,0.0000026428354,0.000002984736,0.0000048213205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830836,0.000121340134,0.0011712088,0.00009482166,0.00022849647,0.000075790966],"domain_scores_gemma":[0.99492836,0.0025951692,0.0012142949,0.00008705258,0.0011459077,0.00002919123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016525284,0.00008961673,0.00053099747,0.0000787097,0.000011108111,0.000013103137,0.0001275208,0.000026173051,0.000019834602],"category_scores_gemma":[0.0021818066,0.00006573221,0.00007250263,0.000038121994,0.000103210434,0.00014432863,0.000017349917,0.00006092284,8.095239e-8],"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":[0.25937796,0.0018592484,0.0066646365,0.0008671868,0.00047324493,0.0000028221646,0.002936707,0.0012493936,0.008704888,0.4790937,0.00003623549,0.23873396],"study_design_scores_gemma":[0.11965128,0.00076018396,0.0010427393,0.0001835908,0.000055063265,0.000007710663,0.000050289444,0.03684783,0.006589839,0.8347359,0.0000046289997,0.000070992035],"about_ca_topic_score_codex":0.000071542025,"about_ca_topic_score_gemma":0.000026461674,"teacher_disagreement_score":0.35564214,"about_ca_system_score_codex":0.00009860373,"about_ca_system_score_gemma":0.000092814174,"threshold_uncertainty_score":0.26804817},"labels":[],"label_agreement":null},{"id":"W2061078339","doi":"10.4212/cjhp.v67i5.1391","title":"An Introduction to the Fundamentals of Cohort and Case–Control Studies","year":2014,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canadian Institutes of Health Research; Canadian Diabetes Association","keywords":"Observational study; Critical appraisal; Clinical study design; Randomized controlled trial; Cohort study; Medicine; Pharmacist; Control (management); Research design; Cohort; Family medicine; Psychology; Clinical trial; Alternative medicine; Computer science; Pharmacy; Artificial intelligence; Surgery; Pathology","score_opus":0.07284946037865118,"score_gpt":0.4074823582009747,"score_spread":0.3346328978223235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061078339","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":[0.97652274,0.0005415672,0.0024201544,0.019608775,0.00040199183,0.00040668194,0.000017852672,0.00001149589,0.00006875439],"genre_scores_gemma":[0.9974782,0.000035306617,0.0014705902,0.0003356234,0.00063568226,0.000007997209,2.1236131e-7,0.000014215442,0.000022182508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990755,0.00016153499,0.0003445796,0.0000898442,0.00014842184,0.00018015249],"domain_scores_gemma":[0.9986792,0.0002618154,0.00028418316,0.0002339619,0.00030840884,0.00023240477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015169762,0.00011076536,0.00024602073,0.0000905004,0.00021725144,0.00004279424,0.00024334743,0.00001558645,0.000033224474],"category_scores_gemma":[0.0006975286,0.000062471874,0.000044522894,0.00009733082,0.00022294882,0.00023541368,0.00001570914,0.00020587537,0.0000013340738],"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":[0.0005645478,0.00056251895,0.0846764,0.00045191692,0.0070561543,0.0014321675,0.0769448,0.0018387458,0.015641863,0.3263672,0.30125666,0.18320705],"study_design_scores_gemma":[0.004562941,0.009334094,0.009973047,0.0003519839,0.0033596288,0.009739497,0.01936603,0.0011215961,0.06348981,0.79985195,0.07737851,0.0014708851],"about_ca_topic_score_codex":0.0011246839,"about_ca_topic_score_gemma":0.009067654,"teacher_disagreement_score":0.47348478,"about_ca_system_score_codex":0.00011535592,"about_ca_system_score_gemma":0.00010002385,"threshold_uncertainty_score":0.50599635},"labels":[],"label_agreement":null},{"id":"W2061407842","doi":"10.1002/sim.2618","title":"Conditioning on the propensity score can result in biased estimation of common measures of treatment effect: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":227,"is_retracted":false,"has_abstract":true,"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":"Propensity score matching; Statistics; Covariate; Hazard ratio; Observational study; Mathematics; Econometrics; Confidence interval","score_opus":0.20389167045157128,"score_gpt":0.42466937770647534,"score_spread":0.22077770725490406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061407842","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":[0.98644376,0.000016436728,0.011403142,0.00009518329,0.000023732038,0.0015523476,0.00012248525,0.000026145033,0.0003167688],"genre_scores_gemma":[0.99206644,0.000005251086,0.007735792,0.000012896182,0.0000121343,0.000106856576,0.000031102885,0.000012885799,0.000016646774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99848163,0.0003205381,0.0005981983,0.00014335285,0.00033257555,0.0001236802],"domain_scores_gemma":[0.996643,0.00259557,0.00032214238,0.00030249936,0.00011926027,0.000017503582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010144653,0.00014991396,0.0005247193,0.00015780743,0.000032651307,0.0000030410758,0.000095340736,0.000037233327,0.000007700153],"category_scores_gemma":[0.002681419,0.000088262015,0.00001303845,0.00022553538,0.00020149321,0.000021215968,0.000016648059,0.00015174689,1.8903305e-7],"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":[0.0016231446,0.005766741,0.42524713,0.0012766479,0.00022153764,0.00044568407,0.028328497,0.032605913,0.010711916,0.46100995,0.0038631156,0.02889972],"study_design_scores_gemma":[0.007982511,0.017106254,0.26197192,0.004273138,0.00030751948,0.000005993682,0.0022034978,0.017809616,0.051758155,0.6361921,0.000004717701,0.00038459868],"about_ca_topic_score_codex":0.008497692,"about_ca_topic_score_gemma":0.01650867,"teacher_disagreement_score":0.17518212,"about_ca_system_score_codex":0.00024425043,"about_ca_system_score_gemma":0.00004269863,"threshold_uncertainty_score":0.9981048},"labels":[],"label_agreement":null},{"id":"W2061691003","doi":"10.1002/sim.3200","title":"Impact of mis‐specification of the treatment model on estimates from a marginal structural model","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":66,"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":"Estimator; Marginal structural model; Confounding; Inverse probability; Context (archaeology); Computer science; Econometrics; Specification; Mean squared error; Average treatment effect; Statistics; Sample size determination; Mathematics; Bayesian probability","score_opus":0.1925234186916368,"score_gpt":0.4631170529289025,"score_spread":0.2705936342372657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061691003","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":[0.49542767,0.000028162987,0.50355285,0.00002247739,0.00001813244,0.00020281393,0.00040346687,0.00001697841,0.00032742883],"genre_scores_gemma":[0.62819445,0.00007210279,0.3716346,0.0000061398077,0.000013533147,0.0000073346214,0.000027138547,0.00001079035,0.00003388441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989405,0.000022936947,0.00044799887,0.00014206709,0.00030947337,0.00013699701],"domain_scores_gemma":[0.9984182,0.0007552904,0.00028002268,0.00038629406,0.00012438293,0.00003578318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103016806,0.00015616648,0.00036067632,0.000084616666,0.000029277131,9.4193564e-7,0.000154721,0.00005256547,0.000045627698],"category_scores_gemma":[0.00054841355,0.000088505476,0.000036858313,0.00011231729,0.00032288543,0.000027344215,0.000012426073,0.00011829466,3.576693e-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":[0.0008612474,0.0008506037,0.028461697,0.00017107493,0.00021302098,0.000030605668,0.01878209,0.11291463,0.0476409,0.7757717,0.004274994,0.010027436],"study_design_scores_gemma":[0.0004228677,0.00038896562,0.009656379,0.000113755195,0.00002872555,0.0000018160734,0.000042651758,0.3936989,0.0047344225,0.5908553,3.0145145e-7,0.00005588481],"about_ca_topic_score_codex":0.0002644936,"about_ca_topic_score_gemma":0.000036448047,"teacher_disagreement_score":0.28078428,"about_ca_system_score_codex":0.00022955639,"about_ca_system_score_gemma":0.00007285726,"threshold_uncertainty_score":0.36091486},"labels":[],"label_agreement":null},{"id":"W2062040186","doi":"10.1002/jrsm.1056","title":"Issues relating to study design and risk of bias when including non‐randomized studies in systematic reviews on the effects of interventions","year":2012,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":187,"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 of Population and Public Health; University of Ottawa","funders":"National Institutes of Health; National Institute for Health and Care Research; Scottish Government","keywords":"Randomized controlled trial; Psychological intervention; Systematic review; Randomized experiment; Research design; Clinical study design; Psychology; Computer science; MEDLINE; Management science; Medicine; Applied psychology; Clinical trial; Social science; Psychiatry; Sociology; Engineering","score_opus":0.8578401848948041,"score_gpt":0.6814907782416452,"score_spread":0.1763494066531589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062040186","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":[0.29506612,0.017651029,0.66524845,0.00010364203,0.00006339275,0.021624653,0.0000015369026,0.000056699533,0.00018444733],"genre_scores_gemma":[0.35599095,0.0027154835,0.6370519,0.0000021453704,0.000013422496,0.004144137,2.5074389e-8,0.000023382174,0.000058586156],"study_design_codex":"systematic_review","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.908967,0.08822193,0.0015874606,0.00024672714,0.00058176287,0.00039508656],"domain_scores_gemma":[0.4823799,0.515647,0.0008099584,0.0007706991,0.0003119553,0.00008048552],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19958735,0.00020610333,0.002215457,0.0005687288,0.00015730993,0.000016197824,0.00034107963,0.00006435932,0.000009840491],"category_scores_gemma":[0.7106343,0.000111657784,0.00021613244,0.0005723989,0.00031799692,0.00014027208,0.00045892064,0.0004154517,0.0000025759427],"study_design_candidate":"systematic_review","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":[0.004785346,0.0048903706,0.00652895,0.4168761,0.0056648743,0.000013183708,0.37595093,0.000028494052,0.036062445,0.06121167,0.000935411,0.0870522],"study_design_scores_gemma":[0.003631867,0.0010767782,0.0002279887,0.17337315,0.0011422439,0.0000024032126,0.02792336,0.0006734966,0.43398032,0.35762712,0.000005203264,0.00033606196],"about_ca_topic_score_codex":0.000084352134,"about_ca_topic_score_gemma":0.000008057466,"teacher_disagreement_score":0.51104695,"about_ca_system_score_codex":0.00010950849,"about_ca_system_score_gemma":0.000013031858,"threshold_uncertainty_score":0.8241933},"labels":[],"label_agreement":null},{"id":"W2062834232","doi":"10.1097/ede.0b013e318162afb9","title":"Case-Crossover Designs Compared With Dynamic Follow-up Designs","year":2008,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of Health; University of Victoria","funders":"","keywords":"Crossover; Crossover study; Computer science; Medicine; Artificial intelligence","score_opus":0.4774975879361858,"score_gpt":0.45694392957968044,"score_spread":0.020553658356505355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062834232","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":[0.3040696,0.00009222831,0.6932381,0.0002197618,0.00010645922,0.00042413606,0.000014112536,0.0006100208,0.0012256076],"genre_scores_gemma":[0.695819,0.00003445568,0.30238578,0.00054907915,0.000037575915,0.000098852426,0.000012791524,0.000050269646,0.0010121736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972021,0.00071223936,0.0007033855,0.00051727216,0.00011615048,0.00074885157],"domain_scores_gemma":[0.9911489,0.0074411132,0.00038177476,0.00072035205,0.00013806553,0.00016979044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011131344,0.0003545521,0.0010005881,0.00011064949,0.00027643115,0.0000050884832,0.0002770044,0.00027300604,0.00021084458],"category_scores_gemma":[0.00408924,0.00027744708,0.00012341034,0.00020650953,0.0005927578,0.0001704983,0.0000834314,0.0004246624,0.00008013084],"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":[0.002294409,0.0009967113,0.08437856,0.00036561477,0.0010229594,0.024707291,0.0063001732,0.0014877681,0.011841763,0.68144816,0.18115836,0.0039981916],"study_design_scores_gemma":[0.002107401,0.00092284783,0.0019087767,0.00009248116,0.00011756842,0.026789531,0.00022256881,0.004850039,0.0019286745,0.9583974,0.0016615775,0.0010011413],"about_ca_topic_score_codex":0.00010004543,"about_ca_topic_score_gemma":0.0002991707,"teacher_disagreement_score":0.39174944,"about_ca_system_score_codex":0.00017744022,"about_ca_system_score_gemma":0.000096565454,"threshold_uncertainty_score":0.99996775},"labels":[],"label_agreement":null},{"id":"W2063548620","doi":"10.1016/j.jclinepi.2004.10.016","title":"Propensity score methods gave similar results to traditional regression modeling in observational studies: a systematic review","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":497,"is_retracted":false,"has_abstract":false,"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","funders":"","keywords":"Propensity score matching; Observational study; Confounding; Medicine; Odds ratio; Statistics; Regression analysis; Hazard ratio; Confidence interval; Internal medicine; Mathematics","score_opus":0.9794651742196404,"score_gpt":0.7432106376404088,"score_spread":0.23625453657923157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063548620","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":[0.0000049443192,0.90735376,0.086462185,0.0028810736,0.0004685654,0.0026888435,0.000045212648,0.000040402254,0.000055032684],"genre_scores_gemma":[7.95075e-7,0.61194956,0.38497746,0.002234484,0.0006066497,0.000140476,0.000017544131,0.00003995965,0.000033046923],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.92963624,0.03670861,0.03147855,0.0008736961,0.0006791626,0.0006237342],"domain_scores_gemma":[0.70502657,0.2670707,0.024245456,0.0012256847,0.0018892805,0.00054233737],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15394065,0.0007703802,0.028026631,0.00044247496,0.00006792699,0.0000086906075,0.00105748,0.0011083465,0.000020044205],"category_scores_gemma":[0.72183806,0.00044535432,0.00273617,0.00055857236,0.00018857021,0.00026822506,0.00028658565,0.0036579883,0.000013305336],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014436265,0.00038040386,0.000008518411,0.8017644,0.00077239756,0.00011390932,0.000050160943,0.00018862734,5.1103235e-8,0.014132369,0.011958153,0.17048663],"study_design_scores_gemma":[0.00027613048,0.0004171562,0.0000032409102,0.786927,0.0017952574,0.00033953186,0.000008575838,0.0005853752,4.6500592e-8,0.18853061,0.020765841,0.00035123908],"about_ca_topic_score_codex":0.0000013393907,"about_ca_topic_score_gemma":0.000007855634,"teacher_disagreement_score":0.56789744,"about_ca_system_score_codex":0.0005815147,"about_ca_system_score_gemma":0.0010179514,"threshold_uncertainty_score":0.99979985},"labels":[],"label_agreement":null},{"id":"W2063846874","doi":"10.1002/sim.3460","title":"Bayesian propensity score analysis for observational data","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; University of British Columbia; Simon Fraser University","funders":"","keywords":"Propensity score matching; Observational study; Statistics; Confounding; Confidence interval; Bayesian probability; Markov chain Monte Carlo; Credible interval; Econometrics; Odds ratio; Outcome (game theory); Medicine; Mathematics","score_opus":0.5909869107336676,"score_gpt":0.490360892353943,"score_spread":0.10062601837972462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063846874","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":[0.0071757687,0.000025279489,0.9907711,0.00036532583,0.000051773877,0.00045672624,0.0007191345,0.000075833574,0.00035904223],"genre_scores_gemma":[0.17815456,0.000057404304,0.8194624,0.00022163137,0.000108741406,0.000043708857,0.0016039438,0.000018487573,0.0003290916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865234,0.000041949195,0.00045978415,0.00031188375,0.00033302282,0.00020101304],"domain_scores_gemma":[0.9973747,0.0014261405,0.0001632981,0.0007299104,0.000244806,0.000061133884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072613114,0.00013333406,0.0004612968,0.00018623346,0.000081700244,0.0000037509863,0.00037503158,0.000054855784,0.00016674025],"category_scores_gemma":[0.0065129953,0.00010897227,0.000017746725,0.000521474,0.00024722805,0.000115028,0.00010788451,0.00015497366,0.0000013451569],"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":[0.0000753707,0.00015083198,0.22463904,0.00020173882,0.000235417,0.0001035622,0.0006362728,0.000054900058,0.00020968939,0.680292,0.09114838,0.0022527738],"study_design_scores_gemma":[0.0005780605,0.00014320135,0.062243514,0.00007867767,0.00027348418,0.000008611961,0.000039494505,0.021770526,0.00008835609,0.9137309,0.0008612667,0.00018387655],"about_ca_topic_score_codex":0.00007261337,"about_ca_topic_score_gemma":0.00056183664,"teacher_disagreement_score":0.23343891,"about_ca_system_score_codex":0.00006198909,"about_ca_system_score_gemma":0.000083043094,"threshold_uncertainty_score":0.7797134},"labels":[],"label_agreement":null},{"id":"W2064228679","doi":"10.1198/016214506000000258","title":"Statistical Inference for the Difference Between the Best Treatment Mean and a Control Mean","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","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":"Memorial University of Newfoundland","funders":"","keywords":"Confidence interval; Mathematics; Mean difference; Inference; Upper and lower bounds; Homogeneous; Statistics; Coverage probability; Mathematical optimization; Computer science; Artificial intelligence","score_opus":0.05773673034347347,"score_gpt":0.39316321320818587,"score_spread":0.3354264828647124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064228679","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":[0.10133026,0.000033578,0.89427483,0.0032259068,0.00006164232,0.0004945815,0.00051308324,0.000020223333,0.00004591216],"genre_scores_gemma":[0.96438414,0.00004938514,0.034940045,0.00017216246,0.0002621995,0.00004145877,0.000003723052,0.000018519067,0.0001283855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979892,0.00040089202,0.0006347722,0.00013989312,0.00053776725,0.0002974745],"domain_scores_gemma":[0.9702163,0.027678683,0.0014839988,0.0002246558,0.00032873813,0.000067668094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000917814,0.00019182307,0.00051662175,0.000032644326,0.0002983831,0.00010157742,0.0003155944,0.000044915094,0.0000081213],"category_scores_gemma":[0.0044859233,0.00008410919,0.00010242619,0.00014573027,0.00039088135,0.0000703354,0.000044894823,0.000298022,0.0000014446287],"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":[0.00044599458,0.00066065794,0.2969039,0.000053153315,0.001093021,0.000009815174,0.0011447537,0.00006256021,0.0014333805,0.47840223,0.0060578757,0.21373264],"study_design_scores_gemma":[0.00084950594,0.0011750729,0.31325775,0.000042948715,0.0009970736,0.0000102774175,0.00035195198,0.0012222099,0.00037150737,0.6809965,0.0005496959,0.00017552497],"about_ca_topic_score_codex":0.0003216727,"about_ca_topic_score_gemma":0.00026224807,"teacher_disagreement_score":0.86305386,"about_ca_system_score_codex":0.0005038359,"about_ca_system_score_gemma":0.00009486824,"threshold_uncertainty_score":0.53703934},"labels":[],"label_agreement":null},{"id":"W2064579426","doi":"10.1097/ccm.0b013e3181b785a2","title":"Ten reasons why we should NOT use severity scores as entry criteria for clinical trials or in our treatment decisions*","year":2009,"lang":"en","type":"review","venue":"Critical Care Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":133,"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. Michael's Hospital","funders":"","keywords":"Medicine; Clinical trial; Intensive care medicine; Psychological intervention; Context (archaeology); Illness severity; MEDLINE; Severity of illness; Physical therapy; Internal medicine; Psychiatry","score_opus":0.8033210656543764,"score_gpt":0.6755904427212177,"score_spread":0.12773062293315873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064579426","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":[0.000012477626,0.9708686,0.01378123,0.0065022735,0.0011844727,0.0059714536,0.00095315464,0.0004532159,0.0002731105],"genre_scores_gemma":[0.000071819595,0.933936,0.06060564,0.001205054,0.0021506867,0.0012051429,0.00030462188,0.00014103077,0.00038000286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99023485,0.002646056,0.004297123,0.0012162868,0.0007639422,0.0008417671],"domain_scores_gemma":[0.9231703,0.07359935,0.000529364,0.0014074035,0.0006309305,0.00066260033],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005034182,0.001098301,0.008527356,0.00043225303,0.00011796596,0.000088110464,0.00063007046,0.0014295689,0.0002868231],"category_scores_gemma":[0.34419212,0.00062632427,0.0012143258,0.0004221231,0.00039818484,0.00021555749,0.00016787097,0.0010936343,0.00002056353],"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":[0.00040596852,0.00046811852,0.000009259626,0.0070921215,0.00008964573,0.0004354297,0.00014382444,6.678653e-9,6.908569e-7,0.013118403,0.060045138,0.9181914],"study_design_scores_gemma":[0.0017494482,0.0038597947,0.0000054385528,0.066086054,0.003916699,0.00014974938,0.0007091195,0.0000031882596,0.000011869755,0.06278603,0.860008,0.00071463775],"about_ca_topic_score_codex":0.000054509597,"about_ca_topic_score_gemma":0.00013316952,"teacher_disagreement_score":0.9174768,"about_ca_system_score_codex":0.00074703,"about_ca_system_score_gemma":0.0007881734,"threshold_uncertainty_score":0.9998668},"labels":[],"label_agreement":null},{"id":"W2065171209","doi":"10.1016/j.jclinepi.2013.06.011","title":"Limitations of within-person study designs","year":2013,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"","keywords":"Censoring (clinical trials); Confounding; Context (archaeology); Scopus; Chen; Clinical study design; Psychology; Statistics; Research design; Econometrics; Assertion; Computer science; Medicine; MEDLINE; Mathematics; Clinical trial","score_opus":0.9047580115839973,"score_gpt":0.6154556940241707,"score_spread":0.2893023175598266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065171209","genre_codex":"commentary","genre_gemma":"methods","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":[0.036585186,0.0005531901,0.3099166,0.64435977,0.0040963995,0.0020833206,0.000030712636,0.00016481432,0.0022100278],"genre_scores_gemma":[0.021896891,0.0007332211,0.6602266,0.30886284,0.0068114945,0.000053231008,0.0000108618915,0.00014221811,0.0012626564],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97730464,0.011091754,0.010280149,0.00039899256,0.00045222483,0.0004722467],"domain_scores_gemma":[0.75738007,0.22440542,0.01619647,0.00070081983,0.001152656,0.00016457544],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.026972514,0.0004134536,0.0060765655,0.0003236361,0.000041289848,0.00000734533,0.00092403445,0.0018778458,0.000115943796],"category_scores_gemma":[0.35748637,0.0002891687,0.0011949893,0.00014926892,0.0005183252,0.00018532218,0.00008772528,0.00700238,0.00002646153],"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":[0.000054279997,0.0004598695,0.005080098,0.000079986574,0.00054134714,0.00014912126,0.00022740054,0.000015454685,0.000008445706,0.0048723267,0.9865708,0.0019408846],"study_design_scores_gemma":[0.00095786346,0.008035974,0.002804605,0.00040232716,0.0008371879,0.00015963061,0.0004926362,0.00009667784,0.000023478462,0.9373643,0.048399378,0.00042593517],"about_ca_topic_score_codex":0.000019729938,"about_ca_topic_score_gemma":0.000009011936,"teacher_disagreement_score":0.9381714,"about_ca_system_score_codex":0.0000673114,"about_ca_system_score_gemma":0.00037810227,"threshold_uncertainty_score":0.9999561},"labels":[],"label_agreement":null},{"id":"W2065314067","doi":"10.1162/rest_a_00475","title":"Estimating and Testing Models with Many Treatment Levels and Limited Instruments","year":2014,"lang":"en","type":"article","venue":"The Review of Economics and Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":47,"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":"Endogeneity; Instrumental variable; Econometrics; Estimator; Hausman test; Ordinary least squares; Test (biology); Statistical hypothesis testing; Value (mathematics); Statistics; Economics; Mathematics; Fixed effects model; Panel data","score_opus":0.2115334824506652,"score_gpt":0.3665306850046302,"score_spread":0.154997202553965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065314067","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":[0.29076153,0.004049572,0.7028082,0.00018421852,0.000017781796,0.00077730924,0.00019652779,0.000039554827,0.0011652958],"genre_scores_gemma":[0.1273271,0.020745529,0.8517779,0.00008990828,0.000010151557,0.000017158538,0.0000034005147,0.0000151858785,0.000013654003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99941236,0.000033676373,0.0002971569,0.00013121564,0.000025528534,0.00010003857],"domain_scores_gemma":[0.9987296,0.00074858655,0.0002680082,0.00016877528,0.000043890752,0.000041134903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030847391,0.00012893953,0.00035152852,0.0000167258,0.00006889967,0.000022201099,0.000046837667,0.000019327648,0.0000017216149],"category_scores_gemma":[0.0002574255,0.000080571444,0.000007877632,0.000023898388,0.00010907545,0.00006954567,0.000048375798,0.000043959022,1.4778871e-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":[0.0000033430617,0.000014113758,0.00018227432,0.0018017988,0.00003093859,2.5248414e-7,0.00010841884,0.000054199372,0.0000049805885,0.65803987,0.000012296417,0.33974752],"study_design_scores_gemma":[0.00020191549,0.00028423374,0.00015879664,0.001978251,0.000111411275,0.000024662442,0.000015739122,0.29853174,0.00004391185,0.698437,0.000095268806,0.000117079915],"about_ca_topic_score_codex":0.000013965923,"about_ca_topic_score_gemma":0.000008479458,"teacher_disagreement_score":0.33963045,"about_ca_system_score_codex":0.00001903834,"about_ca_system_score_gemma":0.000015701515,"threshold_uncertainty_score":0.3285608},"labels":[],"label_agreement":null},{"id":"W2065417422","doi":"10.1080/00273171.2011.540480","title":"A Tutorial and Case Study in Propensity Score Analysis: An Application to Estimating the Effect of In-Hospital Smoking Cessation Counseling on Mortality","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":421,"is_retracted":false,"has_abstract":true,"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","funders":"Canadian Institutes of Health Research; U.S. Public Health Service; Ontario Ministry of Health and Long-Term Care","keywords":"Propensity score matching; Covariate; Medicine; Inverse probability weighting; Observational study; Matching (statistics); Statistics; Internal medicine; Mathematics","score_opus":0.49956942762470347,"score_gpt":0.5544291490721748,"score_spread":0.05485972144747131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065417422","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":[0.98936915,0.0000012595694,0.007351854,0.0000036939489,0.000029825354,0.0031861255,0.0000048774486,0.00004452715,0.000008693598],"genre_scores_gemma":[0.99444634,2.407144e-7,0.0048762024,7.645751e-7,0.00002559479,0.0006285615,0.000004531065,0.000016952388,8.0962093e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972368,0.0010037763,0.00045886624,0.00042802902,0.0005897137,0.00028285445],"domain_scores_gemma":[0.998486,0.00053905667,0.00014269941,0.00052335876,0.00024220298,0.00006671725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068433364,0.00015068626,0.0003569563,0.00042444875,0.00013683566,0.00004745501,0.00021134714,0.00008689401,0.0000035283792],"category_scores_gemma":[0.00083836785,0.00010841024,0.00002990818,0.0010628183,0.00008308078,0.00024502043,0.00015112603,0.0005047229,5.0810513e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023312334,0.0011006668,0.967175,0.000035740148,0.000024478131,0.00017112825,0.023173565,0.00025548652,0.0018024233,0.00025988856,2.6731973e-7,0.005768243],"study_design_scores_gemma":[0.0014548715,0.0056238207,0.9465007,0.0001685695,0.00026748588,0.000006815613,0.0040699034,0.028412258,0.008239657,0.004967135,1.10514236e-7,0.00028866707],"about_ca_topic_score_codex":0.038054578,"about_ca_topic_score_gemma":0.009327245,"teacher_disagreement_score":0.028727332,"about_ca_system_score_codex":0.00018904873,"about_ca_system_score_gemma":0.000032473046,"threshold_uncertainty_score":0.9683511},"labels":[],"label_agreement":null},{"id":"W2067158811","doi":"10.1097/ede.0b013e3181e00730","title":"Marginalia","year":2010,"lang":"fr","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":33,"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; McGill University Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Minority Health and Health Disparities","keywords":"Marginal structural model; Covariate; Inverse probability; Marginal distribution; Econometrics; Statistics; Inverse probability weighting; Mathematics; Confounding; Contrast (vision); Marginal model; Weighting; Computer science; Posterior probability; Propensity score matching; Regression analysis; Medicine; Bayesian probability; Artificial intelligence","score_opus":0.31837564892118636,"score_gpt":0.4717226469922707,"score_spread":0.15334699807108432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067158811","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039767087,0.0012825578,0.22537187,0.7445061,0.0045965444,0.00075786543,0.00012522549,0.0006994235,0.022262713],"genre_scores_gemma":[0.00011474115,0.0005344473,0.47348657,0.456898,0.008051766,0.0002626599,0.00028486628,0.00020145386,0.06016549],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992131,0.0026407142,0.001975036,0.0011898775,0.00019866833,0.0018646907],"domain_scores_gemma":[0.9687984,0.027274227,0.0014797946,0.0019761492,0.00023937608,0.00023204871],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.004313915,0.0010135944,0.0028130074,0.00025779585,0.0001644048,0.000014125889,0.001169755,0.010285108,0.013010158],"category_scores_gemma":[0.032179896,0.0009526266,0.00054189994,0.00018735751,0.0014888438,0.00015359231,0.000433105,0.015776703,0.004640507],"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":[0.0000074247637,0.000035345893,0.0008036275,0.00034548002,0.00007259757,0.00017193049,0.00004318145,0.0000012527631,0.00027342973,0.3138413,0.6801784,0.0042260033],"study_design_scores_gemma":[0.000075333555,0.00010550764,0.00014326588,0.00014991229,0.0000883103,0.00017623881,0.0000040008035,0.00006869453,0.00015962533,0.48489627,0.5136803,0.00045252603],"about_ca_topic_score_codex":0.00022780478,"about_ca_topic_score_gemma":0.0001138358,"teacher_disagreement_score":0.28760812,"about_ca_system_score_codex":0.00027424036,"about_ca_system_score_gemma":0.00016004356,"threshold_uncertainty_score":0.99929243},"labels":[],"label_agreement":null},{"id":"W2068432346","doi":"10.1016/j.socscimed.2012.10.013","title":"Some models just can't be fixed. A commentary on Mortensen","year":2012,"lang":"en","type":"letter","venue":"Social Science & Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canada Research Chairs","keywords":"Econometrics; Economics; Demography; Mathematical economics; Sociology","score_opus":0.2135639124965578,"score_gpt":0.4319060999376298,"score_spread":0.218342187441072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068432346","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":[0.0011109828,0.00014169667,0.0010130256,0.98474216,0.0011327723,0.0008059163,0.0001139661,0.00051710627,0.010422387],"genre_scores_gemma":[0.010210513,0.000083113824,0.0010994215,0.965341,0.021792563,0.00012552353,0.00012978674,0.000093746734,0.0011243853],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951441,0.000118208125,0.0005803384,0.0006798859,0.0022092888,0.0012681202],"domain_scores_gemma":[0.99780154,0.00055562844,0.00047913328,0.00069201685,0.00024433812,0.00022732568],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001355574,0.00055887207,0.00093314436,0.00037747755,0.0006284299,0.000035060453,0.0012225637,0.00063400454,0.00023024317],"category_scores_gemma":[0.0004884899,0.00043472915,0.00012519519,0.00061885774,0.003075273,0.0005740599,0.00021740221,0.0022518376,0.000010802576],"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":[0.000003950574,0.000038422757,0.000009072693,0.000071371214,0.000016960317,0.000067443994,0.0051655932,3.282981e-7,0.00036090135,0.021738198,0.9716876,0.0008401333],"study_design_scores_gemma":[0.00045167835,0.00027976173,0.00000928193,0.0005707659,0.0002649099,0.000017102933,0.0008833235,0.000056366058,0.00062165654,0.73899484,0.2569924,0.0008579149],"about_ca_topic_score_codex":0.0004507551,"about_ca_topic_score_gemma":0.00001876038,"teacher_disagreement_score":0.71725667,"about_ca_system_score_codex":0.000935484,"about_ca_system_score_gemma":0.00022964968,"threshold_uncertainty_score":0.99981046},"labels":[],"label_agreement":null},{"id":"W2068564314","doi":"10.1007/s10742-014-0124-y","title":"A data-adaptive strategy for inverse weighted estimation of causal effects","year":2014,"lang":"en","type":"article","venue":"Health Services and Outcomes Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"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 Waterloo","funders":"National Institute on Drug Abuse; National Institutes of Health; National Science Foundation","keywords":"Causal inference; Propensity score matching; Observational study; Nonparametric statistics; Covariate; Estimator; Confounding; Inverse probability; Econometrics; Statistics; Average treatment effect; Logistic regression; Consistency (knowledge bases); Randomized experiment; Marginal structural model; Computer science; Mathematics; Artificial intelligence; Posterior probability; Bayesian probability","score_opus":0.6899585491834566,"score_gpt":0.6385585072369091,"score_spread":0.05140004194654746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068564314","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":[0.06253128,0.00020039649,0.93397814,0.0009783104,0.000090829446,0.0018292646,0.00011146731,0.00012083979,0.00015945335],"genre_scores_gemma":[0.11237817,0.00014521326,0.8866697,0.0004772171,0.000040620645,0.000137078,0.00006886807,0.000027311378,0.000055800232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946097,0.0035385243,0.0005363676,0.0004308694,0.00031060973,0.00057390385],"domain_scores_gemma":[0.971457,0.027040917,0.000304824,0.0006953468,0.0003167673,0.00018516797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0120730875,0.00016930218,0.0007934681,0.00026140522,0.00017420198,0.000017305085,0.0004184131,0.00016662896,0.000011405712],"category_scores_gemma":[0.0022477347,0.00013157501,0.000037352813,0.0002292818,0.00019438734,0.00023204988,0.0003533105,0.00031848587,0.0000021583676],"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":[0.00044991207,0.00016026924,0.001237978,0.014589926,0.00013505647,0.0000030598749,0.0027472025,0.00004303477,0.00054345257,0.8067031,0.000612516,0.1727745],"study_design_scores_gemma":[0.0007272452,0.0016468783,0.0021020668,0.000173752,0.000022246395,0.000005054762,0.0008247179,0.0983908,0.00094262103,0.89454997,0.00048568394,0.00012896108],"about_ca_topic_score_codex":0.0010058304,"about_ca_topic_score_gemma":0.0019137154,"teacher_disagreement_score":0.17264554,"about_ca_system_score_codex":0.000054347976,"about_ca_system_score_gemma":0.00014544875,"threshold_uncertainty_score":0.53654736},"labels":[],"label_agreement":null},{"id":"W2068928172","doi":"10.1016/s0895-4356(02)00437-7","title":"Quasi-experimental longitudinal designs to evaluate drug benefit policy changes with low policy compliance","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"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 Victoria","funders":"National Institute on Aging; Agency for Healthcare Research and Quality","keywords":"Counterfactual thinking; Null hypothesis; Compliance (psychology); Econometrics; Policy analysis; Population; Medicine; Longitudinal study; Public economics; Economics; Actuarial science; Psychology; Social psychology; Political science; Environmental health","score_opus":0.7124647347952494,"score_gpt":0.6126733016475715,"score_spread":0.09979143314767791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068928172","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":[0.55079836,0.0011460426,0.31664738,0.12669143,0.0006432512,0.0010482444,0.000039736515,0.00026810955,0.0027174193],"genre_scores_gemma":[0.77590555,0.00052137626,0.21315405,0.007353504,0.0023654155,0.00002898436,0.0000012064767,0.000057534602,0.0006124082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99344873,0.0018840536,0.0030011553,0.00045313218,0.00040872837,0.0008042256],"domain_scores_gemma":[0.9758655,0.0194282,0.0029204958,0.0005653152,0.00051917764,0.00070134125],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0102079585,0.0003877527,0.0028643277,0.00038487485,0.00010485997,0.000015373234,0.00070548034,0.00028374986,0.00026784692],"category_scores_gemma":[0.051282674,0.00027257996,0.00040644314,0.000431813,0.00044885924,0.00019968093,0.00016306982,0.0010425317,0.000081968625],"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":[0.0029793016,0.010497288,0.07545141,0.0003399973,0.0010971486,0.00045245158,0.0016975098,0.001529061,0.0013964586,0.7458473,0.08453918,0.07417291],"study_design_scores_gemma":[0.003957751,0.028709413,0.016055077,0.0017315146,0.00021570447,0.0014293414,0.00026509145,0.0035315824,0.0031905002,0.9322355,0.0074797194,0.0011988049],"about_ca_topic_score_codex":0.00007404022,"about_ca_topic_score_gemma":0.00008582318,"teacher_disagreement_score":0.22510715,"about_ca_system_score_codex":0.00026714886,"about_ca_system_score_gemma":0.00018417143,"threshold_uncertainty_score":0.99997264},"labels":[],"label_agreement":null},{"id":"W2068953434","doi":"10.1002/sim.2053","title":"The use of the propensity score for estimating treatment effects: administrative versus clinical data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":225,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Women's College Hospital; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Econometrics; Medicine; Mathematics","score_opus":0.7319400186447765,"score_gpt":0.5861486378777672,"score_spread":0.14579138076700937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068953434","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":[0.01549587,0.000066865,0.9797662,0.00111236,0.00055776286,0.002327585,0.0004949808,0.0000497405,0.00012862856],"genre_scores_gemma":[0.049235564,0.0000871212,0.95013106,0.0000664967,0.00021719802,0.00008160062,0.00004991374,0.00001829628,0.00011275917],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984651,0.00024001612,0.0006567328,0.00022616086,0.00022753466,0.00018442783],"domain_scores_gemma":[0.9709049,0.027620975,0.00036920857,0.0009219985,0.00014228605,0.000040650393],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012477124,0.00014548094,0.00038003482,0.000017948552,0.00013485868,0.000010693555,0.00040691943,0.000053559303,0.000005410871],"category_scores_gemma":[0.045166507,0.00006860535,0.000023411896,0.00009262591,0.00062374223,0.00008210537,0.00014739438,0.0002233639,5.8874974e-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":[0.0011321597,0.00057269965,0.0037579779,0.00039070396,0.00022029711,0.000019440316,0.0016079505,0.000068844325,0.00012872266,0.44610476,0.044826068,0.5011704],"study_design_scores_gemma":[0.012847803,0.011549864,0.006923924,0.002944713,0.001094058,0.000014677775,0.00072465214,0.18848853,0.004366419,0.7459511,0.024433661,0.0006605966],"about_ca_topic_score_codex":0.000033034023,"about_ca_topic_score_gemma":0.0010106215,"teacher_disagreement_score":0.5005098,"about_ca_system_score_codex":0.000101741316,"about_ca_system_score_gemma":0.00012353768,"threshold_uncertainty_score":0.96287644},"labels":[],"label_agreement":null},{"id":"W2070570347","doi":"10.5539/jmr.v7n2p90","title":"Probabilistic Analysis of Balancing Scores for Causal Inference","year":2015,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Forskningsrådet om Hälsa, Arbetsliv och Välfärd; Vetenskapsrådet","keywords":"Propensity score matching; Causal inference; Covariate; Confounding; Observational study; Outcome (game theory); Causal model; Inference","score_opus":0.5381036112364946,"score_gpt":0.5669298269646585,"score_spread":0.028826215728163906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070570347","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":[0.51465976,0.00011677848,0.48329374,0.00014172932,0.00007140528,0.0006484564,0.000025268997,0.000036955338,0.0010058826],"genre_scores_gemma":[0.6920053,0.000022776108,0.3077323,0.000004171345,0.0000618437,0.000025822124,0.0000015813175,0.000025335394,0.000120865174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964398,0.00019854159,0.0012716823,0.00014975492,0.0015395186,0.0004007015],"domain_scores_gemma":[0.986405,0.007447413,0.0008986376,0.0004763819,0.004542994,0.00022957854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009304725,0.00015822894,0.0009160412,0.0012663467,0.000058609978,0.000053104446,0.0006301712,0.00011590706,0.00003573169],"category_scores_gemma":[0.036430683,0.00011882288,0.00025276546,0.0012741613,0.00023881195,0.0002364229,0.00015437478,0.0004755724,0.000002380192],"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":[0.00026686228,0.0020507362,0.0033950664,0.0030704834,0.0022972631,0.000048674578,0.010336994,0.002160311,0.011770335,0.95420694,0.008517098,0.0018792609],"study_design_scores_gemma":[0.0004136505,0.0008113257,0.00009643268,0.00042057803,0.0004893499,0.000019752051,0.0013161034,0.015033194,0.0075422,0.9736141,0.00010742395,0.00013592023],"about_ca_topic_score_codex":0.00001212546,"about_ca_topic_score_gemma":0.00004410445,"teacher_disagreement_score":0.17734551,"about_ca_system_score_codex":0.00025079906,"about_ca_system_score_gemma":0.0005392057,"threshold_uncertainty_score":0.9716859},"labels":[],"label_agreement":null},{"id":"W2070754959","doi":"10.1002/1098-2272(200102)20:2<149::aid-gepi1>3.0.co;2-a","title":"Design considerations for association studies of candidate genes in families","year":2001,"lang":"en","type":"article","venue":"Genetic Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Mount Sinai Hospital; Montreal General Hospital; University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"National Institute of General Medical Sciences; Health Canada; National Institutes of Health","keywords":"Sample size determination; Covariate; Statistics; Correlation; Proband; Trait; Family aggregation; Sample (material); Econometrics; Generalized linear model; Mathematics; Genetics; Biology; Medicine; Computer science; Population; Gene; Mutation; Environmental health","score_opus":0.4847477091923624,"score_gpt":0.4999049966129594,"score_spread":0.015157287420597021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070754959","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":[0.17689826,0.0023997603,0.8179964,0.001559875,0.00010935398,0.00080317305,0.000013002981,0.00008683913,0.00013335992],"genre_scores_gemma":[0.20485675,0.003773087,0.79053825,0.00033808,0.00003668924,0.000326442,0.0000026274952,0.000012966707,0.00011508198],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981316,0.0005544047,0.0007948739,0.00018941428,0.000049233528,0.00028052268],"domain_scores_gemma":[0.96728325,0.03186314,0.00043100657,0.00018977579,0.00021008392,0.000022739872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021758666,0.00011531372,0.00058227096,0.00011206092,0.000047075904,0.0000015023107,0.00006589083,0.00013442388,0.000013954987],"category_scores_gemma":[0.041839477,0.00010409273,0.000045844794,0.00009125992,0.00008917095,0.000032639622,0.00003060092,0.000070485024,0.0000017244449],"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":[0.00013895622,0.00032025107,0.5378476,0.0004706702,0.0006753912,0.000015897378,0.005374509,0.025497863,0.024970021,0.3337012,0.044225074,0.026762608],"study_design_scores_gemma":[0.00022301683,0.0001358223,0.003795796,0.000025169922,0.000029143435,0.000005659798,0.00022429969,0.00082979683,0.00471734,0.98963886,0.00027870742,0.00009640964],"about_ca_topic_score_codex":0.00005446109,"about_ca_topic_score_gemma":0.0005219564,"teacher_disagreement_score":0.6559377,"about_ca_system_score_codex":0.00012491444,"about_ca_system_score_gemma":0.00004988897,"threshold_uncertainty_score":0.9662315},"labels":[],"label_agreement":null},{"id":"W2071109714","doi":"10.1002/sim.2655","title":"Analysing and interpreting competing risk data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Hazard; Computer science; Event (particle physics); Population; Interpretation (philosophy); Econometrics; Statistics; Risk analysis (engineering); Mathematics; Medicine; Environmental health","score_opus":0.11141470997664706,"score_gpt":0.46070952155919104,"score_spread":0.349294811582544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071109714","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":[0.02219973,0.00017477889,0.9734604,0.000110090885,0.000046209727,0.00011179183,0.00012349345,0.00009792814,0.0036755856],"genre_scores_gemma":[0.3950902,0.00006674259,0.6045966,0.000034998287,0.000078959456,0.0000022677893,0.000089525165,0.0000145163085,0.000026169986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877965,0.00010779264,0.00046884132,0.00026024715,0.0001938509,0.00018958464],"domain_scores_gemma":[0.9967938,0.0024529926,0.0002305615,0.0004346174,0.000055170512,0.000032855314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014048404,0.00012328548,0.00030590044,0.0001291136,0.000060112277,0.000013126376,0.00020773798,0.0000382111,0.00004983817],"category_scores_gemma":[0.0062879394,0.0001053035,0.000004862316,0.00016935471,0.00021576707,0.00008150197,0.00021454564,0.00028777466,0.000001007496],"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":[0.000029510476,0.00008964951,0.10078013,0.00033956114,0.00004453839,0.00017514717,0.0018995893,0.00004696964,0.0024909542,0.7953867,0.016463082,0.08225418],"study_design_scores_gemma":[0.0002839835,0.000050364244,0.0019861339,0.0004991248,0.00006505438,0.000009054184,0.0006647958,0.042242214,0.000100934005,0.9536461,0.00031445315,0.00013774981],"about_ca_topic_score_codex":0.00058121904,"about_ca_topic_score_gemma":0.0006890958,"teacher_disagreement_score":0.37289047,"about_ca_system_score_codex":0.000041200336,"about_ca_system_score_gemma":0.00001136297,"threshold_uncertainty_score":0.7527705},"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":"W2075615602","doi":"10.1007/s11292-007-9023-3","title":"Using group-based trajectory modeling in conjunction with propensity scores to improve balance","year":2007,"lang":"en","type":"article","venue":"Journal of Experimental Criminology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; RAND Corporation; National Science Foundation","keywords":"Covariate; Causal inference; Propensity score matching; Observational study; Trajectory; Econometrics; Matching (statistics); Inference; Statistics; Randomized experiment; Balance (ability); Psychology; Computer science; Mathematics; Artificial intelligence","score_opus":0.37432864595407206,"score_gpt":0.4279812160766541,"score_spread":0.053652570122582066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075615602","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":[0.66453594,0.00007992567,0.33496213,0.000014964962,0.00010643241,0.00018830498,4.5047895e-7,0.000024683632,0.00008715222],"genre_scores_gemma":[0.80650795,0.0000012702475,0.19325241,0.00015116892,0.00006027015,0.0000045801553,3.3959736e-7,0.000019570152,0.0000024528763],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987263,0.000053939013,0.00054239837,0.00017492045,0.00020471694,0.00029772316],"domain_scores_gemma":[0.99921924,0.000101151825,0.00030612215,0.00015494152,0.00012878214,0.00008976112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004800216,0.00016554311,0.00037633308,0.0003105307,0.00004268093,0.000012272008,0.00014520157,0.00010104883,0.00001386537],"category_scores_gemma":[0.00010090238,0.00013246524,0.00005003548,0.000098808414,0.0000797102,0.0002494946,0.000036150734,0.00031189012,7.204772e-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":[0.0013981793,0.0003321969,0.0015249578,0.000022706108,0.000015180486,0.00014379513,0.00051428046,0.00097063323,0.99200505,0.0025155076,0.000010720729,0.00054677704],"study_design_scores_gemma":[0.0013594207,0.0026778579,0.00037489584,0.00020327618,0.000025623965,0.00026065583,0.0012597484,0.006225492,0.9817661,0.005605807,0.0000063437124,0.00023476972],"about_ca_topic_score_codex":0.000058964575,"about_ca_topic_score_gemma":0.000058574642,"teacher_disagreement_score":0.14197196,"about_ca_system_score_codex":0.0004278784,"about_ca_system_score_gemma":0.00007178429,"threshold_uncertainty_score":0.5401776},"labels":[],"label_agreement":null},{"id":"W2077156951","doi":"10.1016/j.jclinepi.2007.07.007","title":"New insights on the relation between untreated and treated outcomes for a given therapy effect model is not necessarily linear","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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 British Columbia","funders":"","keywords":"Linear model; Outcome (game theory); Econometrics; Relation (database); Disease; Medicine; Constant (computer programming); Mathematics; Computer science; Statistics; Mathematical economics; Internal medicine; Data mining","score_opus":0.5645195566477534,"score_gpt":0.581479820362613,"score_spread":0.01696026371485959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077156951","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":[0.5614728,0.00007316707,0.4292102,0.0086112805,0.000068998284,0.0004027901,0.000005350222,0.000040286614,0.000115140436],"genre_scores_gemma":[0.882447,0.00040279984,0.11253071,0.0038513679,0.00046527057,0.000006774764,0.000003389344,0.000034852,0.00025780083],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99486667,0.0015049604,0.0029403814,0.00023835337,0.00015963161,0.0002899756],"domain_scores_gemma":[0.8349837,0.16207887,0.0022662496,0.000276047,0.00020402958,0.00019111185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015627174,0.00024256541,0.002033275,0.000121433586,0.00008322425,0.0000067396973,0.0002441767,0.000547176,0.000012967254],"category_scores_gemma":[0.05662049,0.00011954416,0.0004650563,0.00010566062,0.000146221,0.0001222177,0.000030824744,0.0008538724,0.0000027815136],"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":[0.006688574,0.00029101493,0.6678298,0.00005432022,0.0012385718,0.00001765401,0.0006168922,0.00036210462,0.0003482769,0.16462594,0.013929412,0.14399743],"study_design_scores_gemma":[0.0025873757,0.0040928433,0.14243126,0.00010577258,0.00015868268,0.0000071383843,0.000008923977,0.0053289346,0.001637788,0.84230363,0.0011733988,0.00016422746],"about_ca_topic_score_codex":0.000017281138,"about_ca_topic_score_gemma":0.0000072371895,"teacher_disagreement_score":0.6776777,"about_ca_system_score_codex":0.000039589995,"about_ca_system_score_gemma":0.00006962842,"threshold_uncertainty_score":0.951326},"labels":[],"label_agreement":null},{"id":"W2077482180","doi":"10.1016/j.jclinepi.2007.05.006","title":"A sensitivity analysis using information about measured confounders yielded improved uncertainty assessments for unmeasured confounding","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Michael Smith Health Research BC","keywords":"Confounding; Observational study; Statistics; Prior probability; Odds ratio; Medicine; Credible interval; Confidence interval; Econometrics; Bayesian probability; Mathematics","score_opus":0.5885736479901069,"score_gpt":0.6149718249995361,"score_spread":0.026398177009429147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077482180","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":[0.17113991,0.000020223863,0.8272765,0.00022991604,0.00072312844,0.00038388016,0.000010629236,0.000053165102,0.00016264604],"genre_scores_gemma":[0.6845298,0.0000291521,0.31418827,0.000954827,0.00026448816,0.0000033816514,0.000008144584,0.000013469121,0.000008487715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98891616,0.0026899965,0.007098474,0.0002607766,0.00038372402,0.000650878],"domain_scores_gemma":[0.9068683,0.08177912,0.008619648,0.0003914492,0.0019870617,0.00035441885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09915524,0.00028533424,0.0032695348,0.00048199657,0.00013580777,0.000028766868,0.0002460434,0.0006566398,0.000017110204],"category_scores_gemma":[0.21829306,0.00023262645,0.0013412578,0.0004337267,0.0003031938,0.0006891249,0.000054515185,0.0009999714,0.0000010723833],"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":[0.017045204,0.0017488601,0.36777613,0.0010095077,0.024888976,0.000115186725,0.0013504382,0.026542818,0.018436307,0.36902246,0.002762383,0.16930173],"study_design_scores_gemma":[0.0058341357,0.0021872725,0.049604647,0.00037049348,0.004590284,0.00017378203,0.0011468042,0.2562831,0.0008418108,0.67590374,0.0021495796,0.0009143505],"about_ca_topic_score_codex":0.00008766306,"about_ca_topic_score_gemma":0.000244641,"teacher_disagreement_score":0.5133899,"about_ca_system_score_codex":0.00035527375,"about_ca_system_score_gemma":0.00044570313,"threshold_uncertainty_score":0.9486231},"labels":[],"label_agreement":null},{"id":"W2077926906","doi":"10.1161/circoutcomes.108.790634","title":"Primer on Statistical Interpretation or Methods Report Card on Propensity-Score Matching in the Cardiology Literature From 2004 to 2006","year":2008,"lang":"en","type":"review","venue":"Circulation Cardiovascular Quality and Outcomes","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":154,"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":"Propensity score matching; Matching (statistics); Medicine; Internal medicine; Covariate; Cardiology; Statistics; Mathematics; Pathology","score_opus":0.41148365305155504,"score_gpt":0.5222492141402588,"score_spread":0.11076556108870378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077926906","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089911657,0.4928925,0.5019193,0.0000892019,0.00030261467,0.0031376332,0.00024611343,0.0001719849,0.0003414804],"genre_scores_gemma":[0.0041857436,0.90718234,0.08378347,0.0011743879,0.0005345003,0.0010664124,0.0017773447,0.00021374246,0.000082036204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99063134,0.005780397,0.0014752544,0.0010076498,0.00076941744,0.0003359111],"domain_scores_gemma":[0.9920774,0.005521781,0.0004755218,0.001664918,0.0001607139,0.00009967689],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0042280136,0.00066798506,0.0038506093,0.00031165328,0.00015641656,0.00011693802,0.0003204743,0.00062109745,0.0000063883676],"category_scores_gemma":[0.0050731367,0.00040357132,0.0012713643,0.00045154398,0.00010196206,0.00014812866,0.000103183505,0.0010701448,0.000011394295],"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":[0.00008871659,0.000086935186,0.0010822276,0.004264959,0.0027365366,0.001388006,0.00297362,0.0007969271,0.0000010382307,0.016645717,0.00039467413,0.96954066],"study_design_scores_gemma":[0.0016202125,0.00048251305,0.0935013,0.030004447,0.0067410516,0.0035854138,0.00046441003,0.00005374105,0.000016306773,0.22664699,0.6323438,0.004539771],"about_ca_topic_score_codex":0.00015277088,"about_ca_topic_score_gemma":0.000019135541,"teacher_disagreement_score":0.96500087,"about_ca_system_score_codex":0.00031780597,"about_ca_system_score_gemma":0.00015023875,"threshold_uncertainty_score":0.99984163},"labels":[],"label_agreement":null},{"id":"W2078671558","doi":"10.1016/j.jclinepi.2011.06.012","title":"Treatment effect estimates varied depending on the definition of the provider prescribing preference-based instrumental variables","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"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 Health Centre; McGill University","funders":"","keywords":"Covariate; Confounding; Instrumental variable; Medicine; Observational study; Statistics; Average treatment effect; Point estimation; Confidence interval; Population; Variance (accounting); Econometrics; Demography; Affect (linguistics); Mathematics; Propensity score matching; Psychology; Economics; Environmental health","score_opus":0.7143918541365805,"score_gpt":0.5086633126554404,"score_spread":0.20572854148114006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078671558","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":[0.93010265,0.000044977613,0.06335919,0.0010855623,0.0005665341,0.0007814605,0.000010721837,0.000051958847,0.0039969287],"genre_scores_gemma":[0.87054974,0.000044732908,0.12893687,0.00032837124,0.00008606171,0.000030854037,9.765041e-7,0.000016541137,0.0000058625355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99248016,0.0040809284,0.0027508792,0.00020452219,0.00020023879,0.000283276],"domain_scores_gemma":[0.9087194,0.0871302,0.0034994206,0.00043235987,0.00013116669,0.00008744477],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010031854,0.00024127026,0.001491308,0.000064384694,0.00010462442,0.0000065529025,0.00045845742,0.00026704962,0.00010614618],"category_scores_gemma":[0.0891931,0.00010043,0.00055492844,0.00009372609,0.00038661144,0.00011565248,0.00007820472,0.00068205595,0.0000028065444],"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":[0.0015468072,0.0009838502,0.2554337,0.000116262985,0.00040262225,0.000011235935,0.00020924046,0.000071188624,0.000613474,0.72833824,0.00033399128,0.011939388],"study_design_scores_gemma":[0.001049186,0.0050253477,0.019612404,0.00055045146,0.00026994292,0.00004200981,0.00003787631,0.00082685956,0.02082037,0.9516111,0.00003908733,0.000115391456],"about_ca_topic_score_codex":0.00003837835,"about_ca_topic_score_gemma":0.000009014287,"teacher_disagreement_score":0.2358213,"about_ca_system_score_codex":0.00009795048,"about_ca_system_score_gemma":0.00018373877,"threshold_uncertainty_score":0.918479},"labels":[],"label_agreement":null},{"id":"W2079118756","doi":"10.1002/pds.1201","title":"Estimation of time‐dependent rate ratios in case‐control studies: comparison of two approaches for exposure assessment","year":2006,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Université de Montréal","funders":"Canadian Institutes of Health Research; Canadian Lung Association","keywords":"Medicine; Duration (music); Pharmacoepidemiology; Statistics; Relative risk; Cohort; Confidence interval; Exposure duration; Cohort study; Toxicology; Internal medicine; Environmental health; Pharmacology; Mathematics","score_opus":0.21786663133218764,"score_gpt":0.5032988095763224,"score_spread":0.2854321782441348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079118756","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":[0.21278293,0.0010876618,0.78402096,0.00052958826,0.000049278748,0.0011641271,0.000087738874,0.000057572735,0.00022012599],"genre_scores_gemma":[0.9015566,0.00006921916,0.09803069,0.000050927763,0.00003038442,0.00019369379,0.000021636482,0.000011683481,0.000035143443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971302,0.0011085704,0.0012209145,0.00025448613,0.00007056138,0.00021525656],"domain_scores_gemma":[0.9879583,0.0110741295,0.00068637164,0.00015786482,0.000094171475,0.000029172146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052230046,0.00018657376,0.0009617955,0.000093989765,0.00006563392,0.0000018831649,0.00008263252,0.000079197984,0.000012125432],"category_scores_gemma":[0.001164507,0.00015849304,0.00006739907,0.00007640391,0.00017241309,0.0001297496,0.000041185594,0.00018416712,3.7265062e-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":[0.001574383,0.0019336956,0.13947856,0.0028392074,0.00089274306,0.000041991672,0.0033075504,0.32941785,0.019130528,0.43804786,0.005746455,0.057589177],"study_design_scores_gemma":[0.004036605,0.00020340242,0.0014398214,0.00010939731,0.00031521567,0.000030006851,0.00068592257,0.5130637,0.022108836,0.45771274,0.000029180314,0.00026517114],"about_ca_topic_score_codex":0.00006319375,"about_ca_topic_score_gemma":0.00010642567,"teacher_disagreement_score":0.6887737,"about_ca_system_score_codex":0.00006477145,"about_ca_system_score_gemma":0.000032415937,"threshold_uncertainty_score":0.6463159},"labels":[],"label_agreement":null},{"id":"W2079826663","doi":"10.2202/1557-4679.1210","title":"Model Checking with Residuals for g-estimation of Optimal Dynamic Treatment Regimes","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Health Canada; UNICEF; Thrasher Research Fund","keywords":"Counterfactual thinking; Residual; Context (archaeology); Estimation; Computer science; Econometrics; Mathematics; Statistics; Algorithm; Economics","score_opus":0.08719899470162384,"score_gpt":0.4254682716849469,"score_spread":0.33826927698332304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079826663","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":[0.18119255,0.000011397338,0.8176613,0.00062137825,0.00010741546,0.00016287621,0.00013092038,0.000014183085,0.00009800886],"genre_scores_gemma":[0.5014082,0.00002041079,0.49841568,0.000015945823,0.00003208573,0.000004806383,0.000005633375,0.000011115658,0.00008610036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900013,0.000015688287,0.00045352033,0.00006989928,0.00036573995,0.00009501206],"domain_scores_gemma":[0.9973002,0.00089590985,0.0008346021,0.0001490736,0.00078992994,0.00003026804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037836577,0.000110634835,0.00019775263,0.00009912742,0.000036916463,0.000029057042,0.0003380859,0.00004237781,0.000008830415],"category_scores_gemma":[0.00077455526,0.000065704546,0.00005686406,0.000039071096,0.00011465397,0.000126392,0.000025319088,0.00013509407,3.3324716e-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":[0.0011213624,0.00040602539,0.00008144346,0.00006274732,0.00065085874,0.000028743389,0.0022191058,0.03797589,0.05993248,0.85562825,0.0016987654,0.040194303],"study_design_scores_gemma":[0.0007683305,0.0006771574,0.000054777312,0.00015047392,0.00014727507,0.00017915519,0.00017717406,0.2744632,0.077863514,0.6453077,0.00009423715,0.00011699002],"about_ca_topic_score_codex":0.000004940126,"about_ca_topic_score_gemma":0.000025640797,"teacher_disagreement_score":0.32021567,"about_ca_system_score_codex":0.00008898136,"about_ca_system_score_gemma":0.00015067398,"threshold_uncertainty_score":0.26793537},"labels":[],"label_agreement":null},{"id":"W2081922084","doi":"10.1007/s40471-014-0030-4","title":"Counterfactual Theory in Social Epidemiology: Reconciling Analysis and Action for the Social Determinants of Health","year":2015,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":33,"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","funders":"","keywords":"Causal inference; Counterfactual thinking; Social epidemiology; Causality (physics); Observational study; Health equity; Social determinants of health; Socioeconomic status; Causal model; Race and health; Consistency (knowledge bases); Inference; Psychology; Econometrics; Social psychology; Medicine; Public health; Computer science; Mathematics; Population; Statistics; Environmental health","score_opus":0.6977796672949589,"score_gpt":0.6023984078918089,"score_spread":0.09538125940315001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081922084","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":[0.59898514,0.0025438885,0.39628282,0.0008759216,0.00048866315,0.00069451565,0.000020757574,0.00008224034,0.000026053796],"genre_scores_gemma":[0.9925206,0.00026177062,0.0066304854,0.00017128304,0.00018544254,0.00017298506,0.000021772858,0.000017702312,0.000017983963],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99450386,0.0022463247,0.0022121512,0.00045774513,0.000087229855,0.00049267977],"domain_scores_gemma":[0.98257315,0.014305196,0.0026055018,0.000272103,0.00017492483,0.000069128146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031698987,0.00020904223,0.0016438755,0.00019115381,0.00021026497,0.0000024718897,0.00011911043,0.00023842666,0.0000061898936],"category_scores_gemma":[0.034209326,0.0001516713,0.00021713704,0.00023608854,0.0004700011,0.00010440733,0.00008385081,0.0003449097,2.6209415e-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":[0.00013650683,0.00010433983,0.8028506,0.00021579201,0.00023117254,0.0000031745192,0.0025774145,0.0000434303,0.000013741183,0.026928969,0.0033294458,0.16356544],"study_design_scores_gemma":[0.00021446777,0.00010974269,0.050861012,0.00004610026,0.00024430436,0.00003868671,0.00081929815,0.0016561311,0.00007560924,0.94495136,0.00081588834,0.00016739394],"about_ca_topic_score_codex":0.000086556625,"about_ca_topic_score_gemma":0.00019548339,"teacher_disagreement_score":0.9180224,"about_ca_system_score_codex":0.00019915734,"about_ca_system_score_gemma":0.00018263848,"threshold_uncertainty_score":0.99706966},"labels":[],"label_agreement":null},{"id":"W2082209076","doi":"10.1016/j.jclinepi.2012.07.012","title":"Calculating additive treatment effects from multiple randomized trials provides useful estimates of combination therapies","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Pairwise comparison; Medicine; Meta-analysis; Additive function; Treatment effect; Clinical trial; Intensive care medicine; Econometrics; Statistics; Internal medicine; Mathematics; Traditional medicine","score_opus":0.6189721366302209,"score_gpt":0.5998256028561627,"score_spread":0.019146533774058172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082209076","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":[0.78201115,0.0012623185,0.21466105,0.00046716974,0.00056440104,0.00091570016,0.00001868618,0.000045260884,0.000054255186],"genre_scores_gemma":[0.7399899,0.00048500934,0.25891554,0.000111232956,0.00042080804,0.000046903653,0.0000069501807,0.000017558077,0.0000061345304],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9719636,0.020221448,0.0071380343,0.00017232694,0.00018564302,0.00031896328],"domain_scores_gemma":[0.37494698,0.61512077,0.009270358,0.000204949,0.00030384434,0.0001530973],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057780836,0.0002623033,0.008112618,0.00010593533,0.000040594256,0.000004967766,0.00017091997,0.00036382006,0.00005804323],"category_scores_gemma":[0.72313076,0.00014463725,0.0014430564,0.000062773746,0.00043520998,0.00028492935,0.000041094638,0.00040480483,0.000002755252],"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":[0.060439166,0.0028874534,0.6550752,0.00021735762,0.00492084,0.000014376583,0.0019580186,0.000045804594,0.0021474606,0.08227111,0.0009927584,0.18903045],"study_design_scores_gemma":[0.064504385,0.002408175,0.023990164,0.00047650622,0.000993768,0.000010930237,0.00007881873,0.0018520111,0.013437448,0.8919546,0.00011974662,0.00017343415],"about_ca_topic_score_codex":0.0000571859,"about_ca_topic_score_gemma":0.0000050860326,"teacher_disagreement_score":0.8096835,"about_ca_system_score_codex":0.00007455728,"about_ca_system_score_gemma":0.00007145807,"threshold_uncertainty_score":0.97021294},"labels":[],"label_agreement":null},{"id":"W2082644600","doi":"10.1002/bimj.200800182","title":"Risk Factor Adjustment in Marginal Structural Model Estimation of Optimal Treatment Regimes","year":2009,"lang":"en","type":"article","venue":"Biometrical Journal","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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Marginal structural model; Confounding; Weighting; Econometrics; Context (archaeology); Inverse probability weighting; Marginal model; Statistics; Propensity score matching; Model selection; Selection (genetic algorithm); Marginal distribution; Outcome (game theory); Computer science; Mathematics; Regression analysis; Medicine; Machine learning; Random variable","score_opus":0.1747576457312704,"score_gpt":0.42918240355515974,"score_spread":0.25442475782388935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082644600","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":[0.65077364,0.0002642152,0.34842703,0.00009441456,0.000041848856,0.00018657667,0.00003245835,0.000050724815,0.0001291066],"genre_scores_gemma":[0.64768404,0.00017209955,0.35205236,0.0000077757995,0.000035109773,0.0000026601151,0.0000015570112,0.000007240042,0.00003713701],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985212,0.00007406648,0.0005669509,0.00016111092,0.00040086318,0.00027582707],"domain_scores_gemma":[0.99894184,0.00023375906,0.0004196173,0.00017426607,0.00009571161,0.00013481113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019166296,0.00019205942,0.00036613742,0.0011082649,0.000051507097,0.000027680393,0.00016689264,0.00010802484,0.000060908686],"category_scores_gemma":[0.00055744953,0.00013773597,0.00012245064,0.0009499319,0.000044147728,0.00024592792,0.00002065362,0.00023930814,0.000001944901],"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":[0.00029358242,0.00072868296,0.0014041442,0.000020717764,0.000074091644,0.00004405937,0.00057283,0.016648436,0.0030184602,0.019421458,0.00031278946,0.95746076],"study_design_scores_gemma":[0.0021815998,0.0034921188,0.04797749,0.000115630326,0.00010476784,0.0002096837,0.000093756695,0.37539226,0.02336297,0.546585,0.000028900196,0.00045583167],"about_ca_topic_score_codex":0.0000074382438,"about_ca_topic_score_gemma":6.1876034e-7,"teacher_disagreement_score":0.9570049,"about_ca_system_score_codex":0.0005782337,"about_ca_system_score_gemma":0.00007170454,"threshold_uncertainty_score":0.56167096},"labels":[],"label_agreement":null},{"id":"W2082859497","doi":"10.1038/jes.2009.61","title":"Selection bias in case–control studies on household exposure to pesticides and childhood acute leukemia","year":2009,"lang":"en","type":"review","venue":"Journal of Exposure Science & Environmental Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"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","funders":"Association pour la Recherche sur le Cancer","keywords":"Selection bias; Selection (genetic algorithm); Pesticide; Childhood leukemia; Exposure assessment; Environmental health; Information bias; Case-control study; Medicine; Psychology; Leukemia; Biology; Immunology; Internal medicine; Computer science; Lymphoblastic Leukemia; Pathology","score_opus":0.2599263132490099,"score_gpt":0.4546188708369223,"score_spread":0.19469255758791243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082859497","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":[0.086400226,0.9102869,0.0013816733,0.00016397936,0.0003551978,0.0012612458,0.000056038185,0.00006293542,0.00003182997],"genre_scores_gemma":[0.11457636,0.8612794,0.023292148,0.00052457413,0.00021684017,0.000038639748,0.000001395445,0.000051606978,0.000019030178],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940549,0.0012075271,0.0027971407,0.0007518831,0.00044208614,0.0007464431],"domain_scores_gemma":[0.9913681,0.0051972596,0.002633973,0.0004148456,0.000040304272,0.0003454919],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008501383,0.0006985906,0.003756906,0.0010640328,0.00023252412,0.000027458585,0.00061297294,0.00044359866,0.000010016812],"category_scores_gemma":[0.0097998055,0.0004948123,0.00036058592,0.0005330706,0.00082403875,0.0004340976,0.00017850143,0.0014055638,0.000005466816],"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":[0.00011052829,0.0005973691,0.0041985414,0.0009167135,0.00062574976,0.0028230445,0.0012096096,0.002016845,0.0004890101,0.003920162,0.00059745234,0.98249495],"study_design_scores_gemma":[0.006849502,0.0879735,0.047317162,0.07004414,0.013075817,0.3100776,0.003878622,0.000093474446,0.0010423963,0.39851958,0.05257128,0.008556932],"about_ca_topic_score_codex":0.0000037321386,"about_ca_topic_score_gemma":0.000012830786,"teacher_disagreement_score":0.97393805,"about_ca_system_score_codex":0.0020957573,"about_ca_system_score_gemma":0.00029130434,"threshold_uncertainty_score":0.9997504},"labels":[],"label_agreement":null},{"id":"W2082908413","doi":"10.1007/s10654-011-9637-7","title":"The positivity assumption and marginal structural models: the example of warfarin use and risk of bleeding","year":2011,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":false,"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":"Canadian Institutes of Health Research; McGill University Health Centre","keywords":"Medicine; Warfarin; Confidence interval; Inverse probability weighting; Marginal structural model; Odds ratio; Logistic regression; Statistics; Randomized controlled trial; Internal medicine; Surgery; Mathematics; Propensity score matching; Atrial fibrillation","score_opus":0.47016498274215435,"score_gpt":0.39560946937919,"score_spread":0.07455551336296434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082908413","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":[0.87108254,0.00043137313,0.12793282,0.00007263886,0.00004260713,0.00007145677,0.0000051941133,0.000008118877,0.0003532825],"genre_scores_gemma":[0.91524565,0.0015077048,0.083168685,0.000020414349,0.000036104986,3.556875e-7,2.0171478e-7,0.000012077368,0.0000087912795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99623173,0.0026370762,0.0007931645,0.00010126857,0.00007451572,0.00016225985],"domain_scores_gemma":[0.99189425,0.006164944,0.0015167147,0.00020083382,0.00017422541,0.000049020153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008811626,0.00010625959,0.0003720712,0.000047157424,0.00009765689,0.0000059857243,0.00019171117,0.00003074745,0.0000057473685],"category_scores_gemma":[0.005160628,0.000054054304,0.000060921146,0.00003795145,0.00047067352,0.00024983662,0.00012645403,0.0003556178,1.395267e-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":[0.00060977606,0.000045103072,0.2216493,0.00008087201,0.00038317437,0.000025319465,0.0036535107,0.00017944424,0.005050653,0.73525417,0.0004433836,0.03262531],"study_design_scores_gemma":[0.00024213654,0.0005314085,0.25050125,0.00009078078,0.00013172209,0.00028186414,0.00016189739,0.002185464,0.00092224893,0.7447795,0.00009144009,0.00008029766],"about_ca_topic_score_codex":0.00013658003,"about_ca_topic_score_gemma":0.00001564063,"teacher_disagreement_score":0.044764128,"about_ca_system_score_codex":0.000011878616,"about_ca_system_score_gemma":0.0000095545565,"threshold_uncertainty_score":0.61781263},"labels":[],"label_agreement":null},{"id":"W2084602542","doi":"10.1097/mlr.0b013e3181e419fd","title":"Using Administrative Datasets to Study Outcomes in Dialysis Patients","year":2010,"lang":"en","type":"article","venue":"Medical Care","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"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; St. Michael's Hospital; Western University; Health Sciences Centre; London Health Sciences Centre; University of Calgary; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Dialysis; Medicine; Baseline (sea); Medical record; Intensive care medicine; Modality (human–computer interaction); Health care; Emergency medicine; Computer science; Internal medicine","score_opus":0.23539668479596035,"score_gpt":0.5217783212771887,"score_spread":0.2863816364812284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084602542","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":[0.9969269,0.000001873724,0.0019179517,0.00007646371,0.00010879934,0.0005352411,0.00014626682,0.00007926464,0.00020725178],"genre_scores_gemma":[0.9791781,2.0357653e-7,0.020514952,0.000141991,0.000027013575,0.000060533,0.00005774537,0.000014849562,0.0000046687856],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99854136,0.00007830992,0.00031356615,0.00024325373,0.00062204327,0.00020149468],"domain_scores_gemma":[0.9989153,0.0003305789,0.00006021495,0.00039821994,0.00008917497,0.0002064879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025610867,0.00013927063,0.00030515104,0.00009179016,0.000041885432,0.000014838405,0.0002937874,0.000105471336,0.0003555392],"category_scores_gemma":[0.0054222904,0.00010918214,0.00003372928,0.00019813154,0.000043459968,0.00008107871,0.00019449295,0.00037999355,0.000009800975],"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":[0.000017691094,0.0011162397,0.97363317,0.000032614415,0.000030316101,0.000120664656,0.009460219,3.1794195e-7,0.00010847254,0.0011555078,0.00029726117,0.014027526],"study_design_scores_gemma":[0.00736823,0.0038282657,0.8391655,0.00045195993,0.00045339714,0.000011117779,0.038777214,0.00021741801,0.015589698,0.08890214,0.002555802,0.002679264],"about_ca_topic_score_codex":0.00007672979,"about_ca_topic_score_gemma":0.004090885,"teacher_disagreement_score":0.13446768,"about_ca_system_score_codex":0.00005702497,"about_ca_system_score_gemma":0.00006622135,"threshold_uncertainty_score":0.649138},"labels":[],"label_agreement":null},{"id":"W2085721543","doi":"10.12927/hcpol.2015.24044","title":"“Frankly, My Dear, I Don’t Give a Damn”","year":2014,"lang":"fr","type":"article","venue":"Healthcare policy","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":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Philosophy","score_opus":0.12900457714244246,"score_gpt":0.4559563712802988,"score_spread":0.32695179413785636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085721543","genre_codex":"commentary","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":[0.028024713,0.015075111,0.27818474,0.56417364,0.003082308,0.0043607126,0.00073745084,0.0038781862,0.10248312],"genre_scores_gemma":[0.7885272,0.0030321288,0.15406491,0.020059293,0.005998988,0.00034323786,0.000054085423,0.00038179228,0.027538354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99545616,0.0007705803,0.00095653074,0.0006882655,0.0005185269,0.0016099251],"domain_scores_gemma":[0.9960708,0.00082050957,0.00046677413,0.00139989,0.0004519705,0.0007900458],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009180472,0.0006049507,0.00086843455,0.00039059785,0.00031222968,0.00009063944,0.00056632346,0.00072039175,0.0005768988],"category_scores_gemma":[0.0025300656,0.0006531882,0.00022826118,0.00073147623,0.00043091192,0.0003546377,0.00031204525,0.0010865545,0.0011056364],"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":[0.000020133042,0.00014909824,0.0004130682,0.0016684773,0.00002967159,0.000013892272,0.0019001398,0.0000031006311,0.00007233139,0.8286201,0.011669396,0.15544063],"study_design_scores_gemma":[0.00037210475,0.0005450597,0.0005864911,0.0008361103,0.000039206654,0.00008609566,0.00023472299,0.00033760135,0.0010465378,0.67106205,0.32433087,0.00052312127],"about_ca_topic_score_codex":0.043237686,"about_ca_topic_score_gemma":0.003348719,"teacher_disagreement_score":0.7605025,"about_ca_system_score_codex":0.0009895909,"about_ca_system_score_gemma":0.0009120352,"threshold_uncertainty_score":0.9996721},"labels":[],"label_agreement":null},{"id":"W2086560295","doi":"10.1007/s12561-011-9038-1","title":"A Data Augmentation Method for Estimating the Causal Effect of Adherence to Treatment Regimens Targeting Control of an Intermediate Measure","year":2011,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"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 Waterloo","funders":"","keywords":"Regimen; Censoring (clinical trials); Covariate; Causal inference; Medicine; Observational study; Inverse probability weighting; Hazard ratio; Proportional hazards model; Repeated measures design; Statistics; Internal medicine; Econometrics; Mathematics; Confidence interval","score_opus":0.2405471980053799,"score_gpt":0.49007497699211644,"score_spread":0.24952777898673653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086560295","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":[0.039464388,0.0000122649635,0.95820504,0.0000108824215,0.000121326615,0.0010177556,0.0010983993,0.000026299182,0.00004364511],"genre_scores_gemma":[0.4334019,0.0000015212735,0.566473,0.0000065760787,0.000009630744,0.00008448175,0.000014191597,0.0000057205466,0.0000029519992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984772,0.00028647503,0.00048810773,0.00029496863,0.000248256,0.00020495566],"domain_scores_gemma":[0.99595577,0.003020081,0.0004362748,0.0004122972,0.0001299581,0.000045621353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027472319,0.00014080074,0.00032006513,0.00008605745,0.00006749108,0.000013968777,0.0005696128,0.0000349919,0.00000904476],"category_scores_gemma":[0.005028422,0.00008686729,0.000018797997,0.00020630544,0.00022174344,0.00018274592,0.000077289864,0.00005656893,2.9032296e-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":[0.001388159,0.0009024189,0.00783785,0.0012039632,0.00017466865,0.000016361788,0.041628994,0.000496136,0.16980027,0.18582039,0.0005808418,0.59014994],"study_design_scores_gemma":[0.0015237128,0.012608213,0.0007862359,0.0004417517,0.00021167399,0.0000036455872,0.0023048709,0.3572751,0.27336636,0.35111454,0.000010378775,0.000353501],"about_ca_topic_score_codex":0.00028827402,"about_ca_topic_score_gemma":0.0005450785,"teacher_disagreement_score":0.5897965,"about_ca_system_score_codex":0.000049573213,"about_ca_system_score_gemma":0.00007029888,"threshold_uncertainty_score":0.6019854},"labels":[],"label_agreement":null},{"id":"W2086622613","doi":"10.1111/j.0006-341x.2004.00234.x","title":"Marginal Analysis of Incomplete Longitudinal Binary Data: A Cautionary Note on LOCF Imputation","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":87,"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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Waterloo","keywords":"Missing data; Imputation (statistics); Estimator; Inverse probability; Econometrics; Inverse probability weighting; Statistics; Longitudinal data; Binary data; Computer science; Drop out; Mathematics; Binary number; Data mining; Bayesian probability; Posterior probability; Economics","score_opus":0.30781272951886274,"score_gpt":0.4634387367916948,"score_spread":0.15562600727283205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086622613","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":[0.2359715,0.00010854258,0.76239777,0.00019186897,0.00008367795,0.00023205124,0.00051923137,0.0002110456,0.00028429358],"genre_scores_gemma":[0.82330126,0.000045295317,0.1761205,0.00003347465,0.00003509846,0.000008178188,0.0004205006,0.00001759625,0.000018115712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830526,0.000041598098,0.00046893262,0.0003924664,0.0005631538,0.00022857545],"domain_scores_gemma":[0.9978893,0.00063405535,0.00034538552,0.00083392684,0.00022420527,0.0000731195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005346804,0.00018419293,0.00040845742,0.004304598,0.00007041186,0.000019758629,0.00045211415,0.00011816051,0.000037546044],"category_scores_gemma":[0.0011066218,0.0001738642,0.00010997592,0.011919675,0.00011442798,0.00028633288,0.00025403808,0.00015123603,0.000015242573],"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":[0.0007516406,0.0059615993,0.036195725,0.0010455156,0.004294108,0.00054151495,0.00077964814,0.01861095,0.032701354,0.8297152,0.004405391,0.06499734],"study_design_scores_gemma":[0.0021411586,0.002692429,0.31010976,0.0002771126,0.0041940273,0.000047359903,0.000152152,0.02721343,0.01296174,0.63681245,0.001876941,0.0015214195],"about_ca_topic_score_codex":0.00007549175,"about_ca_topic_score_gemma":0.000019593563,"teacher_disagreement_score":0.58732975,"about_ca_system_score_codex":0.0003070493,"about_ca_system_score_gemma":0.000093752984,"threshold_uncertainty_score":0.7089976},"labels":[],"label_agreement":null},{"id":"W2087644214","doi":"10.1080/00273171.2013.752267","title":"Abstract: Longitudinal Examination of the Interpersonal Impact of Behavioral Variability","year":2013,"lang":"en","type":"article","venue":"Multivariate Behavioral 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":true,"ca_institutions":"McGill University","funders":"","keywords":"Interpersonal communication; Psychology; Supervisor; Longitudinal study; Interpersonal relationship; Behavioural sciences; Applied psychology; Social psychology; Political science; Medicine; Psychotherapist; Law","score_opus":0.5059692537244797,"score_gpt":0.5698292122761865,"score_spread":0.0638599585517069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087644214","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":[0.9969784,0.000004134005,0.0009902566,0.000024017383,0.000072281364,0.0012066099,0.000070698596,0.000059981256,0.00059360353],"genre_scores_gemma":[0.992356,0.0000016627437,0.007205941,7.0642494e-7,0.00002444976,0.00017998918,0.000008119241,0.00003374018,0.00018937557],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99669814,0.00057695067,0.0006970953,0.0003696058,0.0011267132,0.0005314878],"domain_scores_gemma":[0.9961406,0.0009548774,0.00032331047,0.00085664657,0.0016023747,0.00012220786],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029284144,0.00023027614,0.0004035896,0.00022642959,0.00012409301,0.000042994794,0.00073206844,0.00022302338,0.0016580241],"category_scores_gemma":[0.000937844,0.00015331098,0.00027783748,0.00056302577,0.000691254,0.00046927185,0.00046192115,0.0008339851,0.000016884696],"study_design_candidate":"observational","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":[0.00011952319,0.005056804,0.20793137,0.00018967676,0.00004546983,0.0000058881906,0.0039368263,0.000006973147,0.73036337,0.008270805,0.00040843635,0.043664865],"study_design_scores_gemma":[0.00031078252,0.00048572867,0.919775,0.00013206615,0.0000270707,0.0000029692933,0.00030908705,0.00020798491,0.05165557,0.026940783,0.000002003348,0.00015096],"about_ca_topic_score_codex":0.010799967,"about_ca_topic_score_gemma":0.00009170511,"teacher_disagreement_score":0.7118436,"about_ca_system_score_codex":0.0004879779,"about_ca_system_score_gemma":0.00021204853,"threshold_uncertainty_score":0.9992546},"labels":[],"label_agreement":null},{"id":"W2089198100","doi":"10.1186/1471-2288-8-70","title":"Reducing bias through directed acyclic graphs","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1410,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"McGill University Health Centre; McGill University","keywords":"Directed acyclic graph; Confounding; Causal inference; Selection bias; Computer science; Outcome (game theory); Econometrics; Simple (philosophy); Causality (physics); Statistics; Mathematics; Algorithm","score_opus":0.9122827611924192,"score_gpt":0.6583154278917019,"score_spread":0.2539673333007173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089198100","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":[0.24533026,0.0004719148,0.7387174,0.00097219244,0.0002521286,0.0006140576,0.0000037393427,0.0012540383,0.012384324],"genre_scores_gemma":[0.058896493,0.0019364805,0.93708444,0.00022798682,0.0002520871,0.00024437776,0.0000071586423,0.00006499829,0.0012859666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97646815,0.018254254,0.0008217107,0.0007357324,0.00238709,0.0013330897],"domain_scores_gemma":[0.8679871,0.1298494,0.00015319769,0.0009571065,0.000520641,0.0005325641],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025562007,0.00025241065,0.0008368503,0.00041865517,0.0003921919,0.000013905558,0.0009846976,0.0006212333,0.001962332],"category_scores_gemma":[0.4471436,0.00020130165,0.00016933294,0.0012855377,0.0021799912,0.00018523999,0.00058741437,0.0020213875,0.00011169577],"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":[0.00037927827,0.0005769926,0.0032757928,0.00047843976,0.000119459706,0.00088728376,0.0041815974,0.0000021674482,0.0139849745,0.85528874,0.07480704,0.04601822],"study_design_scores_gemma":[0.00042319752,0.00027946048,0.000663108,0.0001834521,0.000009799307,0.00036345638,0.00026967798,0.00024007904,0.023843,0.9677824,0.00571103,0.00023134761],"about_ca_topic_score_codex":0.00053610746,"about_ca_topic_score_gemma":0.00026155575,"teacher_disagreement_score":0.42158163,"about_ca_system_score_codex":0.00013922634,"about_ca_system_score_gemma":0.0011077498,"threshold_uncertainty_score":0.99895},"labels":[],"label_agreement":null},{"id":"W2091956653","doi":"10.2202/1557-4679.1106","title":"Missing Confounding Data in Marginal Structural Models: A Comparison of Inverse Probability Weighting and Multiple Imputation","year":2008,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":62,"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; McGill University","funders":"","keywords":"Inverse probability weighting; Missing data; Inverse probability; Imputation (statistics); Marginal structural model; Statistics; Weighting; Confounding; Censoring (clinical trials); Computer science; Econometrics; Mathematics; Inverse distance weighting; Estimator; Data mining; Posterior probability; Bayesian probability; Medicine","score_opus":0.33358293714958803,"score_gpt":0.4591081692735752,"score_spread":0.12552523212398714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091956653","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":[0.7083291,0.00004674148,0.29112524,0.00019551846,0.000102178965,0.00009173891,0.000062991225,0.000008061272,0.000038414957],"genre_scores_gemma":[0.6903223,0.000025304113,0.30958474,0.0000144628475,0.0000357886,2.6929382e-7,0.000009617639,0.0000058095948,0.000001757586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985723,0.000080137754,0.0007234146,0.00009982578,0.0004270475,0.00009728432],"domain_scores_gemma":[0.9971243,0.0014295607,0.0008296272,0.00015901061,0.0004239461,0.00003354713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007023558,0.000093640614,0.00023103667,0.00011478369,0.0000545276,0.000025664842,0.000460314,0.000034910885,0.000005866494],"category_scores_gemma":[0.0023202042,0.000069222755,0.000020572996,0.00006788277,0.00020142112,0.0003893088,0.00016948301,0.0002338491,1.2405815e-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":[0.0021839354,0.0007595311,0.34091747,0.00061300973,0.00069684855,0.0004340625,0.04037927,0.015653918,0.035603162,0.47703153,0.0022780416,0.08344922],"study_design_scores_gemma":[0.0004613806,0.0000605444,0.0020228315,0.00016633423,0.000020304231,0.00023494598,0.0005158538,0.419043,0.0020047745,0.57538563,0.000011849391,0.000072562085],"about_ca_topic_score_codex":0.000062061496,"about_ca_topic_score_gemma":0.000076250224,"teacher_disagreement_score":0.4033891,"about_ca_system_score_codex":0.000113373164,"about_ca_system_score_gemma":0.00009954568,"threshold_uncertainty_score":0.2822822},"labels":[],"label_agreement":null},{"id":"W2096521417","doi":"10.1002/sim.5317","title":"A simulation study of finite‐sample properties of marginal structural Cox proportional hazards models","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Center for Research Resources; National Institute of Allergy and Infectious Diseases; National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health","keywords":"Statistics; Confidence interval; Hazard ratio; Proportional hazards model; Mathematics; Estimator; Standard error; Confounding; Mean squared error; Sample size determination; Marginal structural model; Range (aeronautics); Nominal level; Econometrics; Coverage probability","score_opus":0.21699590011067962,"score_gpt":0.45071684087391395,"score_spread":0.23372094076323432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096521417","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":[0.4085655,0.000049099646,0.59065837,0.000012418085,0.000055276607,0.00047961037,0.00008834166,0.000024905958,0.00006650207],"genre_scores_gemma":[0.82216924,0.000004252023,0.17768885,0.000007164631,0.000049037928,0.000027010004,0.000022690641,0.000014106466,0.000017648052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833757,0.00008501991,0.000710599,0.000116992174,0.00055032305,0.00019951613],"domain_scores_gemma":[0.9975891,0.0014382387,0.0003585074,0.00021311564,0.0003545136,0.00004650373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059786544,0.00013547846,0.0004070235,0.00014951994,0.000025686386,0.000001797671,0.00010668556,0.000046646637,0.000112233756],"category_scores_gemma":[0.0051361076,0.0000993599,0.000012077731,0.00016152894,0.00022588122,0.00015154984,0.00004409122,0.00015177645,2.6655553e-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":[0.0005281237,0.001576764,0.050929185,0.0015612482,0.00012122496,0.000009911147,0.034704532,0.074315846,0.0033268405,0.8270581,0.00029434153,0.0055739232],"study_design_scores_gemma":[0.0009514368,0.0008623108,0.0033882866,0.000276641,0.000067369925,0.0000013370537,0.002478516,0.2209786,0.0009929349,0.7698551,0.000005691521,0.00014180924],"about_ca_topic_score_codex":0.00018932018,"about_ca_topic_score_gemma":0.000065829765,"teacher_disagreement_score":0.41360372,"about_ca_system_score_codex":0.00005561445,"about_ca_system_score_gemma":0.00005091401,"threshold_uncertainty_score":0.61487716},"labels":[],"label_agreement":null},{"id":"W2096945117","doi":"10.1142/s0217590809003483","title":"DECRIMINALIZATION POLICY AND MARIJUANA SMOKING PREVALENCE: A LOOK AT THE LITERATURE","year":2009,"lang":"en","type":"article","venue":"The Singapore Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Agency for Healthcare Research and Quality; McGill University","keywords":"Decriminalization; Marijuana smoking; Econometrics; Economics; Smoking prevalence; Psychology; Actuarial science; Environmental health; Medicine; Substance use; Criminology; Psychiatry","score_opus":0.08718352098033268,"score_gpt":0.4013340714161663,"score_spread":0.3141505504358336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096945117","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":[0.14719032,0.75882107,0.0046480903,0.048089087,0.00024393892,0.0058093155,0.00004696772,0.0007904174,0.034360785],"genre_scores_gemma":[0.26201293,0.70318925,0.0056732288,0.021063188,0.0008026739,0.0001605825,0.000048735234,0.000099013254,0.0069504157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998919,0.0001579324,0.00040231424,0.00023410686,0.00007976779,0.00020686639],"domain_scores_gemma":[0.9986171,0.00032725197,0.00032735136,0.0006497216,0.000036008478,0.000042573178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009636289,0.00019642182,0.00030781864,0.00003753535,0.00022069516,0.00008402819,0.00030185567,0.000061062085,0.00012406721],"category_scores_gemma":[0.000495317,0.000108614586,0.00008318661,0.00012107743,0.000119760705,0.000183724,0.000104228384,0.00018967174,0.000014577521],"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":[0.000019962354,0.000038775626,0.00027719332,0.0054297443,0.000060169135,0.000008502237,0.0023258203,0.000007323884,0.00015441574,0.5650726,0.042737048,0.38386846],"study_design_scores_gemma":[0.00012432467,0.00007763183,0.00048822814,0.0102397725,0.00026218535,0.0002503525,0.00006204535,0.00008409742,0.00043523233,0.9441306,0.04352148,0.00032403498],"about_ca_topic_score_codex":0.000006784055,"about_ca_topic_score_gemma":0.000008639612,"teacher_disagreement_score":0.38354445,"about_ca_system_score_codex":0.00023087757,"about_ca_system_score_gemma":0.000053731674,"threshold_uncertainty_score":0.4429174},"labels":[],"label_agreement":null},{"id":"W2097027506","doi":"10.1002/1097-0258(20000730)19:14<1849::aid-sim506>3.0.co;2-1","title":"Estimating treatment effects in randomized clinical trials in the presence of non-compliance","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Universiteit Leiden","keywords":"Confounding; Randomization; Randomized controlled trial; Outcome (game theory); Clinical trial; Medicine; Placebo; Estimator; Statistics; Instrumental variable; Causal inference; Econometrics; Internal medicine; Mathematics","score_opus":0.28974091353382553,"score_gpt":0.5720931192616544,"score_spread":0.2823522057278289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097027506","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":[0.06532778,0.00021742121,0.9277225,0.00035107107,0.0001810141,0.0036778743,0.00002769681,0.00003456976,0.0024600537],"genre_scores_gemma":[0.38336784,0.0003487446,0.6156754,0.00008453342,0.00008428524,0.00035036614,0.000008801272,0.000013921755,0.00006613875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925598,0.00402531,0.0025681623,0.00025249846,0.00033910314,0.0002551406],"domain_scores_gemma":[0.89139515,0.10769333,0.00047100225,0.0003656458,0.000040971056,0.000033877826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0237718,0.000185358,0.002218789,0.00013153783,0.000015921349,0.000004809496,0.0002545853,0.00008334205,0.000117637195],"category_scores_gemma":[0.096706964,0.000105053674,0.000062355786,0.00029815236,0.0004613751,0.000041956853,0.000016597212,0.00031846878,0.0000030807055],"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":[0.01638176,0.0018500695,0.0058648996,0.0016065361,0.000106682295,0.0006734867,0.018114759,0.001065722,0.0004275819,0.20661384,0.0028811505,0.7444135],"study_design_scores_gemma":[0.05925073,0.00052266585,0.0015449094,0.0026452292,0.00006761331,0.0000040119867,0.00016165253,0.07916347,0.00015210787,0.8563522,0.000015315793,0.000120095734],"about_ca_topic_score_codex":0.00030281502,"about_ca_topic_score_gemma":0.00022892322,"teacher_disagreement_score":0.7442934,"about_ca_system_score_codex":0.000076813856,"about_ca_system_score_gemma":0.00005067522,"threshold_uncertainty_score":0.91090184},"labels":[],"label_agreement":null},{"id":"W2097413632","doi":"10.1093/aje/kws127","title":"\"Toward a Clearer Definition of Confounding\" Revisited With Directed Acyclic Graphs","year":2012,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":142,"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; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Directed acyclic graph; Confounding; Medicine; Computer science; Mathematics; Combinatorics; Statistics","score_opus":0.22031216098194287,"score_gpt":0.4361126226322491,"score_spread":0.21580046165030622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097413632","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":[0.8422334,0.00047058557,0.15474302,0.0005327695,0.00009355769,0.00016964725,0.000007767075,0.000117618154,0.0016315902],"genre_scores_gemma":[0.7011962,0.00026014226,0.29812065,0.00033517883,0.000057694877,0.000004234542,0.000001998729,0.000020221414,0.0000036733513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971562,0.0010599014,0.00110022,0.00012150167,0.00014319127,0.00041900127],"domain_scores_gemma":[0.9902273,0.006191301,0.0027785045,0.0002523467,0.00036702747,0.00018353875],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028520303,0.00017947271,0.0012088191,0.00026848525,0.000030103878,0.0000023189625,0.0002021807,0.000062329535,0.0000677681],"category_scores_gemma":[0.009829914,0.00012454238,0.00015619532,0.00041818517,0.00070884684,0.00022352539,0.000031688945,0.00039152306,0.000004689933],"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":[0.00077564636,0.00031643888,0.23661269,0.000112267895,0.00045668051,0.000022639017,0.0010539392,0.000004223733,0.0037822188,0.7428559,0.0026340676,0.011373289],"study_design_scores_gemma":[0.0006191097,0.0036005173,0.024377689,0.00055209367,0.0002910735,0.00137715,0.0009315626,0.00001557826,0.001676254,0.96464306,0.001562895,0.00035303857],"about_ca_topic_score_codex":0.00003320198,"about_ca_topic_score_gemma":0.0000019433223,"teacher_disagreement_score":0.22178714,"about_ca_system_score_codex":0.000065493165,"about_ca_system_score_gemma":0.000042027386,"threshold_uncertainty_score":0.9985107},"labels":[],"label_agreement":null},{"id":"W2097814090","doi":"","title":"Estimation of Dose-Response Functions for Longitudinal Data","year":2007,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","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":"McGill University","funders":"","keywords":"Propensity score matching; Statistics; Estimation; Confounding; Regression; Global Positioning System; Generalization; Longitudinal study; Binary data; Mathematics; Regression analysis; Computer science; Econometrics; Medicine; Binary number","score_opus":0.4378421577236633,"score_gpt":0.5507619228625688,"score_spread":0.11291976513890545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097814090","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":[0.012322962,0.000013199043,0.9834594,0.00006886528,0.00007353565,0.0009964624,0.0020932592,0.000059420003,0.00091289735],"genre_scores_gemma":[0.4432726,0.000013759425,0.55602473,0.0000017612253,0.000023776285,0.000041687,0.00018856033,0.000018182825,0.000414944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979635,0.0002622196,0.00057394645,0.0003100997,0.0005575646,0.00033267646],"domain_scores_gemma":[0.9827357,0.015349765,0.0002477206,0.00068570033,0.00088170706,0.000099416524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004880608,0.00011406826,0.00024578127,0.0007949265,0.00025555003,0.000015506714,0.00036288792,0.00006671187,0.00003876959],"category_scores_gemma":[0.023393342,0.00011519617,0.00004239948,0.00084071717,0.0005090968,0.00014143813,0.00022952248,0.00024752237,0.000003631226],"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":[0.020659875,0.0014810507,0.0006941205,0.0014229887,0.00031157196,0.000018981167,0.001952516,0.00047569402,0.17760153,0.5013472,0.21125603,0.08277846],"study_design_scores_gemma":[0.0007288287,0.0020170368,0.0035577295,0.00013839173,0.000039946994,0.000011436088,0.0004154645,0.06706213,0.062047634,0.8628831,0.00093617395,0.00016211023],"about_ca_topic_score_codex":0.00007302505,"about_ca_topic_score_gemma":0.00027659058,"teacher_disagreement_score":0.43094963,"about_ca_system_score_codex":0.00012355729,"about_ca_system_score_gemma":0.00034125184,"threshold_uncertainty_score":0.984833},"labels":[],"label_agreement":null},{"id":"W2098643226","doi":"10.1177/0272989x15598540","title":"The CREATE Method for Expressing Continuous Outcome Data in Absolute Terms for Use in Patient Treatment Decision Aids","year":2015,"lang":"en","type":"article","venue":"Medical Decision Making","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":"Hamilton Health Sciences; Montreal Heart Institute; McMaster University; University of Toronto; University Health Network","funders":"","keywords":"Absolute risk reduction; Outcome (game theory); Statistics; Kurtosis; Computer science; Medicine; Mathematics; Confidence interval","score_opus":0.4356436343332973,"score_gpt":0.5447473935557257,"score_spread":0.10910375922242838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098643226","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":[0.0920723,0.00010783089,0.9059069,0.000100338366,0.00026063385,0.0013558163,0.000049016646,0.00008959545,0.00005755722],"genre_scores_gemma":[0.14641085,0.000029864173,0.85287094,0.00015012972,0.00005665948,0.00038029888,0.000016045633,0.0000460898,0.000039141494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965252,0.00019687932,0.001294439,0.0005929512,0.00086917833,0.00052133045],"domain_scores_gemma":[0.97131556,0.0268252,0.00031242147,0.0012287988,0.00013389051,0.00018411575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047339494,0.0002706665,0.0006294021,0.00019362765,0.00012424312,0.00015593991,0.00080655684,0.00022376855,0.000011564611],"category_scores_gemma":[0.046572313,0.00016129213,0.00010013346,0.00020123649,0.00007147396,0.00037981058,0.0005754362,0.00021757795,0.0000024251083],"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":[0.00055479456,0.00015616014,0.0014232205,0.000012483364,0.000009562721,0.000053530246,0.00030964302,0.000028822336,0.000030586634,0.0028058237,0.0011442137,0.99347115],"study_design_scores_gemma":[0.0037962005,0.0008951638,0.00040230353,0.001842065,0.0000406553,0.000027401833,0.00043196956,0.1266396,0.00035160393,0.8373538,0.027858773,0.00036044727],"about_ca_topic_score_codex":0.000044858523,"about_ca_topic_score_gemma":0.00066449033,"teacher_disagreement_score":0.9931107,"about_ca_system_score_codex":0.00037359446,"about_ca_system_score_gemma":0.000096051444,"threshold_uncertainty_score":0.9614588},"labels":[],"label_agreement":null},{"id":"W2102334823","doi":"10.1093/aje/kwt215","title":"Causal Inference in Occupational Epidemiology: Accounting for the Healthy Worker Effect by Using Structural Nested Models","year":2013,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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","funders":"National Cancer Institute","keywords":"Causal inference; Inference; Occupational exposure; Epidemiology; Medicine; Occupational medicine; Econometrics; Environmental health; Computer science; Mathematics; Internal medicine; Artificial intelligence","score_opus":0.2635172900198451,"score_gpt":0.4950818798051624,"score_spread":0.2315645897853173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102334823","genre_codex":"methods","genre_gemma":"commentary","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":[0.063149996,0.0015258857,0.79105383,0.14195456,0.00073481794,0.0014013011,0.000096449505,0.0000707208,0.000012409648],"genre_scores_gemma":[0.13486357,0.0004326271,0.4089586,0.4511003,0.003947504,0.000312997,0.00013385668,0.00021640019,0.000034160108],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98811257,0.0059027034,0.0036873028,0.0006067606,0.0002640506,0.0014266346],"domain_scores_gemma":[0.7760035,0.2155009,0.0072551933,0.0005765137,0.0005346579,0.00012924819],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011929592,0.0007430788,0.0038595404,0.00044422908,0.00018795472,0.000017845387,0.0010748394,0.0009061214,0.00005148406],"category_scores_gemma":[0.067707255,0.0004693529,0.00050258916,0.00038794795,0.001278396,0.00044706534,0.0001619394,0.00445932,0.0000022366294],"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":[0.0011022142,0.000044164044,0.10904875,0.00036763016,0.00073218084,0.000051677715,0.00021052279,0.0150061175,0.00005958886,0.009842839,0.8154834,0.048050944],"study_design_scores_gemma":[0.0008739159,0.0024201947,0.0024566595,0.00093820004,0.00036611728,0.00048400735,0.00008599735,0.09915279,0.0000076293186,0.8829838,0.009264046,0.00096661795],"about_ca_topic_score_codex":0.000960227,"about_ca_topic_score_gemma":0.00003448384,"teacher_disagreement_score":0.873141,"about_ca_system_score_codex":0.00060389674,"about_ca_system_score_gemma":0.0004507536,"threshold_uncertainty_score":0.9997758},"labels":[],"label_agreement":null},{"id":"W2102520493","doi":"10.1002/sim.2328","title":"A comparison of propensity score methods: a case‐study estimating the effectiveness of post‐AMI statin use","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":565,"is_retracted":false,"has_abstract":true,"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":"Propensity score matching; Statin; Statistics; Medicine; Internal medicine; Computer science; Mathematics","score_opus":0.31956570844757465,"score_gpt":0.5520056064708857,"score_spread":0.23243989802331105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102520493","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":[0.4748936,0.000026012112,0.52401406,0.000015214917,0.000033422373,0.0009111875,0.000037801175,0.00002742925,0.000041279665],"genre_scores_gemma":[0.5095511,0.0000012235154,0.49036577,0.0000098497285,0.000015830014,0.000033794102,0.0000050743997,0.000014145979,0.00000318943],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658763,0.0015816797,0.001004126,0.00023062705,0.00038807982,0.00020784079],"domain_scores_gemma":[0.98058593,0.017776186,0.00057873625,0.0004905913,0.0005275191,0.000041008945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051970277,0.000201513,0.0009233155,0.0001338412,0.000058902573,0.0000065934564,0.00020664772,0.00005223488,0.000023291732],"category_scores_gemma":[0.018450016,0.00012941612,0.000021288355,0.00032394603,0.0004314344,0.00009708928,0.000118625045,0.0003791928,4.534697e-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":[0.0012093899,0.0048260028,0.397978,0.0062288884,0.00040315502,0.001375217,0.08864853,0.0029462287,0.040537503,0.27528113,0.0009364065,0.17962953],"study_design_scores_gemma":[0.006051955,0.009193189,0.09257529,0.006477603,0.00093342393,0.00070211745,0.040456716,0.11658138,0.055133637,0.67089397,0.000028782011,0.0009719493],"about_ca_topic_score_codex":0.0011934737,"about_ca_topic_score_gemma":0.00083077396,"teacher_disagreement_score":0.39561284,"about_ca_system_score_codex":0.00008125761,"about_ca_system_score_gemma":0.000059068592,"threshold_uncertainty_score":0.989818},"labels":[],"label_agreement":null},{"id":"W2102880415","doi":"10.1093/ije/dyu107","title":"Mediation misgivings: ambiguous clinical and public health interpretations of natural direct and indirect effects","year":2014,"lang":"en","type":"review","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":92,"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; McGill University Health Centre","funders":"","keywords":"Causal inference; Public health; Independence (probability theory); Inference; Ambiguity; Natural (archaeology); Mediation; Identifiability; Object (grammar); Notation; Population; Epistemology; Econometrics; Psychology; Medicine; Computer science; Sociology; Mathematics; Statistics; Social science; Environmental health; Artificial intelligence; Geography","score_opus":0.32729662388970787,"score_gpt":0.5706358608900225,"score_spread":0.24333923700031462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102880415","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":[0.00041147534,0.96763396,0.029077876,0.0008769089,0.0014859544,0.0003460799,0.00002550823,0.000037012553,0.000105249],"genre_scores_gemma":[0.0056375004,0.955316,0.038106028,0.00042269367,0.00042450556,0.000017127462,0.00002728518,0.000032741747,0.000016102724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99205565,0.0036539685,0.0034554647,0.0003025085,0.00026065903,0.0002717515],"domain_scores_gemma":[0.9609427,0.031903356,0.006174142,0.00019373289,0.000578941,0.00020712026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009497562,0.00030851245,0.0035486512,0.0006524065,0.000032232747,0.000017684033,0.00048732726,0.00035942247,0.000008750021],"category_scores_gemma":[0.094850436,0.00022731254,0.000443271,0.00010610573,0.00043190017,0.00020823802,0.00018018033,0.0009220069,0.0000011410522],"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":[0.000011599069,0.00006555624,0.0006822191,0.0022417225,0.00063236884,0.000007683288,0.000108709704,1.4685816e-7,6.0846173e-7,0.010245765,0.0010189912,0.98498464],"study_design_scores_gemma":[0.0012455446,0.002060272,0.0013949866,0.034817345,0.00083329104,0.002740335,0.000051707415,0.00021152856,0.0000067056076,0.32156506,0.634283,0.00079024193],"about_ca_topic_score_codex":0.000018177256,"about_ca_topic_score_gemma":0.000021065025,"teacher_disagreement_score":0.9841944,"about_ca_system_score_codex":0.00015887816,"about_ca_system_score_gemma":0.0003403947,"threshold_uncertainty_score":0.9269537},"labels":[],"label_agreement":null},{"id":"W2103171295","doi":"10.3390/ijerph120809391","title":"Model Averaging for Improving Inference from Causal Diagrams","year":2015,"lang":"en","type":"article","venue":"International Journal of Environmental Research and Public Health","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Center for Research Resources; National Institute of Child Health and Human Development; National Cancer Institute; March of Dimes Foundation; University of North Carolina at Chapel Hill; Canada Research Chairs; Centers for Disease Control and Prevention; National Institute of Diabetes and Digestive and Kidney Diseases; Electric Power Research Institute","keywords":"Causal inference; Spurious relationship; Weighting; Model selection; Computer science; A priori and a posteriori; Bootstrapping (finance); Inference; Directed acyclic graph; Causal model; Variance (accounting); Econometrics; Selection (genetic algorithm); Statistics; Machine learning; Mathematics; Algorithm; Artificial intelligence; Medicine","score_opus":0.4529308440761285,"score_gpt":0.5176326384787479,"score_spread":0.06470179440261936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103171295","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":[0.5110089,0.00034124177,0.48321956,0.004715254,0.00014279869,0.0002497419,0.00014033959,0.000018712584,0.00016343774],"genre_scores_gemma":[0.93900096,0.00031003967,0.06014943,0.00020256528,0.00021855645,0.000014662285,0.000016728636,0.000015445488,0.00007161943],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99789333,0.000117450676,0.00044991964,0.00015487075,0.001014909,0.00036951777],"domain_scores_gemma":[0.99787486,0.0009454216,0.00027139692,0.00011384453,0.00024656803,0.00054792303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026982431,0.00009769265,0.00018749108,0.00021770623,0.000082769846,0.00013193022,0.00037921808,0.000050806775,0.000026774396],"category_scores_gemma":[0.0022881934,0.00008399882,0.000038993978,0.000045206525,0.00014738353,0.00060116616,0.0002022421,0.00040455465,0.0000020042075],"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":[0.00059889944,0.0023189464,0.032079216,0.00009503988,0.00030261924,0.00007899503,0.0070377183,0.00013269037,0.0075812223,0.13187404,0.006616577,0.811284],"study_design_scores_gemma":[0.0011309421,0.0009606615,0.0009959876,0.00007000504,0.0000030330161,0.00003671646,0.0014800819,0.014645077,0.00047847375,0.9774854,0.0025739905,0.00013959169],"about_ca_topic_score_codex":0.00009535073,"about_ca_topic_score_gemma":0.000035878245,"teacher_disagreement_score":0.8456114,"about_ca_system_score_codex":0.00072394294,"about_ca_system_score_gemma":0.0005435858,"threshold_uncertainty_score":0.34253725},"labels":[],"label_agreement":null},{"id":"W2103371988","doi":"10.1002/sim.5705","title":"The performance of different propensity score methods for estimating marginal hazard ratios","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":995,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Estimator; Matching (statistics); Medicine; Mathematics","score_opus":0.22020753118718697,"score_gpt":0.4904911441960751,"score_spread":0.27028361300888815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103371988","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":[0.06839165,0.000094207935,0.93017393,0.00012031017,0.00026562027,0.0007133104,0.000016702863,0.00003677284,0.00018749823],"genre_scores_gemma":[0.19177236,0.00004180599,0.80780804,0.000025422712,0.00012501192,0.00011226327,0.000010578186,0.000017596733,0.00008695062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867797,0.00013657245,0.0005378662,0.00011770506,0.00021526488,0.00031464512],"domain_scores_gemma":[0.9950841,0.0040758783,0.00029939413,0.00028894373,0.00019292721,0.000058766407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238949,0.00015149084,0.00039684807,0.00005268499,0.0001149006,0.000005728927,0.00018131392,0.00004535697,0.000023089584],"category_scores_gemma":[0.0065260795,0.00008779509,0.00001731552,0.000096663905,0.00029962012,0.00008154345,0.00006211945,0.0002099996,5.209366e-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":[0.00014150966,0.00013102194,0.026839644,0.001189853,0.00003550294,0.0000011662486,0.0017837703,0.000014164555,0.005966098,0.7812556,0.0034087494,0.17923293],"study_design_scores_gemma":[0.0009979375,0.0009844513,0.012969004,0.00101758,0.00012811605,0.000013738967,0.00029301192,0.088986054,0.02950362,0.86437964,0.0004199635,0.00030689983],"about_ca_topic_score_codex":0.0000051866728,"about_ca_topic_score_gemma":0.000018884162,"teacher_disagreement_score":0.17892604,"about_ca_system_score_codex":0.00007045359,"about_ca_system_score_gemma":0.000028404293,"threshold_uncertainty_score":0.7812798},"labels":[],"label_agreement":null},{"id":"W2104419597","doi":"10.1016/j.jclinepi.2006.06.012","title":"Triggered sampling could help improve longitudinal studies of persons with elevated mortality risk","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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 Waterloo","funders":"National Institute on Aging","keywords":"Sampling (signal processing); Medicine; Longitudinal study; Longitudinal data; Environmental health; Demography; Statistics; Gerontology; Mathematics; Computer science; Pathology","score_opus":0.6790793147285508,"score_gpt":0.6119558115004203,"score_spread":0.06712350322813043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104419597","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":[0.7868107,0.001051346,0.21098247,0.00045973842,0.0002687194,0.00019731496,0.00003620026,0.00005081231,0.00014273202],"genre_scores_gemma":[0.78394693,0.0014275685,0.21388981,0.00011823171,0.00052778353,0.0000068673407,0.0000022165073,0.000026093321,0.00005448318],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99048126,0.0024328395,0.0060052103,0.00033238297,0.00030790086,0.00044042393],"domain_scores_gemma":[0.928914,0.059968308,0.0094164405,0.00044222464,0.0011008079,0.00015822146],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023384295,0.0002842338,0.003910033,0.00012750376,0.00007521593,0.000004286149,0.00032481505,0.000401301,0.000027157224],"category_scores_gemma":[0.115690455,0.00017947097,0.0006461993,0.0001914772,0.00097351463,0.00018962933,0.00007934262,0.0014875395,0.0000015205472],"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":[0.0010381887,0.0007009751,0.9505154,0.00023643354,0.0012213122,0.000053187745,0.00006513166,0.00033084812,0.00077040686,0.039069526,0.002536236,0.0034623935],"study_design_scores_gemma":[0.001612153,0.0030097563,0.1253974,0.00033574825,0.000710237,0.00008988272,0.0002464677,0.00026544338,0.0009744509,0.8666842,0.00041579877,0.00025844408],"about_ca_topic_score_codex":0.00007518982,"about_ca_topic_score_gemma":0.00009547593,"teacher_disagreement_score":0.82761467,"about_ca_system_score_codex":0.00007577674,"about_ca_system_score_gemma":0.00018875054,"threshold_uncertainty_score":0.89175844},"labels":[],"label_agreement":null},{"id":"W2104878768","doi":"10.1002/pds.817","title":"Bringing epidemiology into drug utilisation research","year":2003,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Hôtel-Dieu de Montréal; Université de Montréal","funders":"","keywords":"Medicine; Research centre; Library science; Population; Family medicine","score_opus":0.38318131780470827,"score_gpt":0.5487537221390125,"score_spread":0.16557240433430426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104878768","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":[0.2887782,0.011467592,0.6031494,0.027615782,0.0012941363,0.0023381358,0.000023376939,0.0019398322,0.06339353],"genre_scores_gemma":[0.8805776,0.002538549,0.11423707,0.0015931255,0.00014483278,0.00011367479,0.000012252012,0.000040202904,0.0007426862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98657453,0.010482717,0.0010896408,0.0007269526,0.0001511546,0.0009749904],"domain_scores_gemma":[0.9553704,0.04346271,0.00028706665,0.0004354608,0.00019635391,0.00024799258],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038888153,0.00029334225,0.0008063623,0.00025546656,0.00056225754,0.00000641799,0.00025966484,0.00020179448,0.00031938739],"category_scores_gemma":[0.044067677,0.00026339837,0.00009809672,0.0003063824,0.00072162575,0.00026221955,0.00017792436,0.0011833468,0.000046014262],"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":[0.00008416881,0.00006199919,0.026462186,0.000113225295,0.000045569053,0.000007716437,0.0011383166,0.000026026255,0.0010207883,0.9303009,0.02814706,0.012592078],"study_design_scores_gemma":[0.00038229817,0.00002409594,0.0008545937,0.000058041416,0.000026545542,0.00004323497,0.00033391287,0.0012236937,0.0042769536,0.946274,0.04624351,0.0002591358],"about_ca_topic_score_codex":0.00018115,"about_ca_topic_score_gemma":0.000052056766,"teacher_disagreement_score":0.59179944,"about_ca_system_score_codex":0.00015681895,"about_ca_system_score_gemma":0.00007457594,"threshold_uncertainty_score":0.9999818},"labels":[],"label_agreement":null},{"id":"W2106121516","doi":"10.1177/1740774513504151","title":"Beyond intention to treat: What is the right question?","year":2013,"lang":"en","type":"review","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"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; Jewish General Hospital","funders":"","keywords":"Randomized controlled trial; Causal inference; Medicine; Terminology; Treatment effect; Treatment and control groups; Population; Protocol (science); Instrumental variable; Psychology; Alternative medicine; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.7023504462850969,"score_gpt":0.6546002616242445,"score_spread":0.04775018466085246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106121516","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":[0.0000011788783,0.97867805,0.010071589,0.0008911158,0.00163449,0.006173721,0.00006034501,0.00038890284,0.0021005895],"genre_scores_gemma":[3.4901757e-7,0.9746017,0.016435804,0.00074150716,0.0011086062,0.0014518993,0.000048987582,0.000094411385,0.005516745],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9866417,0.0066210446,0.005215742,0.00077368465,0.00038140296,0.00036639394],"domain_scores_gemma":[0.9503146,0.04483816,0.0025408366,0.0017214072,0.00031916593,0.00026585168],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021511031,0.0006152574,0.005549182,0.00014697094,0.00011390126,0.00038329198,0.0009220301,0.0010440572,0.001438549],"category_scores_gemma":[0.04276428,0.00030689678,0.0023324413,0.00034264385,0.00021000743,0.00039800626,0.00029592033,0.0010298166,0.0022514327],"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":[0.0000064584115,0.00009710167,1.9241662e-7,0.0015791316,0.000110928064,0.0000025111774,0.000016433829,3.431236e-9,1.9407548e-7,0.050692525,0.04435958,0.90313494],"study_design_scores_gemma":[0.00011354958,0.00012894289,9.960478e-8,0.010944805,0.0010585085,0.000004811652,0.000010626673,3.2043036e-7,0.000007970327,0.3833423,0.60415816,0.00022991639],"about_ca_topic_score_codex":0.0000075169137,"about_ca_topic_score_gemma":0.0000037306513,"teacher_disagreement_score":0.90290505,"about_ca_system_score_codex":0.00013771481,"about_ca_system_score_gemma":0.00015931998,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W2106436016","doi":"10.1007/s00038-010-0184-x","title":"Using Directed Acyclic Graphs to detect limitations of traditional regression in longitudinal studies","year":2010,"lang":"en","type":"article","venue":"International Journal of Public Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":false,"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":"Confounding; Mediation; Regression; Longitudinal data; Longitudinal study; Econometrics; Statistics; Directed acyclic graph; Regression analysis; Computer science; Mathematics; Data mining; Algorithm; Sociology","score_opus":0.7059062973471197,"score_gpt":0.5424706144778019,"score_spread":0.16343568286931787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106436016","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":[0.93355715,0.00023412103,0.058188885,0.006646824,0.0009377316,0.00019053774,0.000027128555,0.00004904762,0.00016854615],"genre_scores_gemma":[0.78645575,0.00029428088,0.21294658,0.00013581288,0.0001402829,0.000006365108,0.000002764764,0.000012516811,0.0000056424237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977205,0.00017193948,0.0010373013,0.00013195677,0.0007142928,0.00022400287],"domain_scores_gemma":[0.99575055,0.0014523619,0.00094384555,0.00013166691,0.0015307895,0.00019078673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019113879,0.00012836338,0.00037396958,0.0010577556,0.000051215713,0.000028135011,0.0003935511,0.0000631211,0.000030631014],"category_scores_gemma":[0.008867309,0.000106137835,0.00010426811,0.00041452624,0.000092646726,0.00058652344,0.00005927595,0.0004672973,7.7181465e-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":[0.0002668368,0.002243005,0.03503101,0.00024419214,0.0008320348,0.00016529301,0.008920149,0.0001924005,0.06972177,0.54688185,0.005636919,0.32986453],"study_design_scores_gemma":[0.0010226289,0.0006463683,0.046634596,0.000993266,0.000017737662,0.00049665733,0.00083321315,0.0003045691,0.004608664,0.94191474,0.0022632868,0.00026425143],"about_ca_topic_score_codex":0.000023661683,"about_ca_topic_score_gemma":0.0003897878,"teacher_disagreement_score":0.3950329,"about_ca_system_score_codex":0.00032453792,"about_ca_system_score_gemma":0.0005143231,"threshold_uncertainty_score":0.99948144},"labels":[],"label_agreement":null},{"id":"W2107843102","doi":"10.1378/chest.12-1920","title":"The Pros and Cons of Propensity Scores","year":2012,"lang":"en","type":"article","venue":"CHEST Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":84,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; University of Toronto","funders":"","keywords":"cons; Propensity score matching; Psychology; Data science; Computer science; Statistics; Mathematics","score_opus":0.35258928646648297,"score_gpt":0.4242491405310891,"score_spread":0.07165985406460612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107843102","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":[0.9841869,0.0006355305,0.012347926,0.00037108452,0.00008907025,0.00022355396,0.0000013875098,0.000043034204,0.0021014977],"genre_scores_gemma":[0.9754985,0.00014842767,0.024121583,0.000014968736,0.000087569824,0.0000041395847,6.5463254e-8,0.0000075219546,0.00011719823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99950206,0.000035058678,0.0001678217,0.000035058572,0.000104549945,0.00015546624],"domain_scores_gemma":[0.99931103,0.00024559014,0.00016731997,0.00011257045,0.00009281815,0.00007068297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060742034,0.00005805307,0.00010962178,0.000015567473,0.00014237313,0.00002661975,0.00008807599,0.00002919481,0.00001173669],"category_scores_gemma":[0.00066412863,0.00003181419,0.000021426256,0.00003235037,0.00019276129,0.00016658728,0.000049192673,0.00019501778,0.0000015376771],"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":[0.00009997904,0.00039054238,0.29168472,0.00043430857,0.00012718567,0.000013706755,0.004730103,3.4881305e-7,0.07028788,0.5810234,0.012230363,0.038977448],"study_design_scores_gemma":[0.00028700804,0.00014604375,0.046042357,0.00019392942,0.000050069626,0.0007712172,0.0003989406,0.000010094722,0.21821293,0.72649884,0.0072069094,0.000181653],"about_ca_topic_score_codex":8.808411e-7,"about_ca_topic_score_gemma":0.0000023524544,"teacher_disagreement_score":0.24564235,"about_ca_system_score_codex":0.000016044361,"about_ca_system_score_gemma":0.000027739025,"threshold_uncertainty_score":0.12973452},"labels":[],"label_agreement":null},{"id":"W2109203991","doi":"10.1161/circoutcomes.114.001023","title":"Impact of Drug Policy on Regional Trends in Ezetimibe Use","year":2014,"lang":"en","type":"article","venue":"Circulation Cardiovascular Quality and Outcomes","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":"Health Sciences Centre; University Health Network; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Heart, Lung, and Blood Institute; National Institute on Aging; Canadian Institutes of Health Research; Health Canada","keywords":"Ezetimibe; Formulary; Restrictiveness; Population; Medicine; Demography; Geography; Environmental health; Family medicine","score_opus":0.2536716822313487,"score_gpt":0.4643739662308443,"score_spread":0.2107022839994956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109203991","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":[0.97380877,0.00006475577,0.02494248,0.00024165561,0.000021613367,0.00014862101,0.000011924543,0.00010142298,0.00065875123],"genre_scores_gemma":[0.9972969,0.000025491945,0.0024265274,0.00011155777,0.0000421819,0.000011835617,0.000018298613,0.00001872562,0.00004847327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815345,0.0004934531,0.0004847986,0.0002693375,0.00041212147,0.00018683804],"domain_scores_gemma":[0.9981935,0.00084165065,0.00016230768,0.0006474098,0.00008794072,0.00006717107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014781188,0.00018714613,0.000684192,0.00039930124,0.000041633164,0.000022411054,0.00009095383,0.00010465541,0.000013885761],"category_scores_gemma":[0.0013230753,0.00015680204,0.0007951292,0.00032961494,0.00009067526,0.00022799723,0.000032252927,0.0001387468,0.0000014859997],"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":[0.00002039383,0.00010720542,0.6680596,0.000077011224,0.00044490726,0.0000013990755,0.0005802245,0.002806852,0.00008432656,0.30286908,0.000088920366,0.02486012],"study_design_scores_gemma":[0.0005138704,0.00002288786,0.89669746,0.000031904747,0.000031233085,0.000002987295,0.000020302017,0.00016795863,0.00006494065,0.10213436,0.00014899034,0.00016310728],"about_ca_topic_score_codex":0.0009302895,"about_ca_topic_score_gemma":0.000026493266,"teacher_disagreement_score":0.22863789,"about_ca_system_score_codex":0.00014068332,"about_ca_system_score_gemma":0.000034329394,"threshold_uncertainty_score":0.63942015},"labels":[],"label_agreement":null},{"id":"W2110219473","doi":"10.1186/1745-6215-15-377","title":"Accounting for center in the Early External Cephalic Version trials: an empirical comparison of statistical methods to adjust for center in a multicenter trial with binary outcomes","year":2014,"lang":"en","type":"article","venue":"Trials","topic":"Advanced Causal Inference Techniques","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":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Center (category theory); Medicine; Medical physics; Clinical trial; Statistics; Internal medicine; Mathematics","score_opus":0.5515340864068206,"score_gpt":0.6247378332791531,"score_spread":0.07320374687233255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110219473","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":[0.40087378,0.0000063290536,0.5933306,0.00020705814,0.00018318069,0.005178039,0.00015980026,0.00003863907,0.000022534108],"genre_scores_gemma":[0.5184705,9.968167e-7,0.48033956,0.00018384444,0.00018150995,0.00075606,0.000024662966,0.000034062297,0.000008765496],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99107355,0.005148368,0.0024487122,0.00044534646,0.0004039105,0.00048009036],"domain_scores_gemma":[0.9622791,0.036145102,0.00089415046,0.00044615768,0.00014865039,0.00008685939],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0258376,0.00030248138,0.0021545615,0.00027779985,0.000056460136,0.00007176337,0.00043822385,0.0001722781,0.00004166547],"category_scores_gemma":[0.03006111,0.00017900093,0.00024978,0.00017303597,0.00006722495,0.00024933857,0.000077240926,0.00023278278,0.000002034955],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.56856203,0.015009277,0.20601712,0.0012709724,0.00042161395,0.000013261048,0.027314516,0.000120014796,0.020294758,0.030646868,0.008206721,0.12212286],"study_design_scores_gemma":[0.62033165,0.034936447,0.045876045,0.0028737253,0.0013442362,0.000009807657,0.007864069,0.024687754,0.036847778,0.21143574,0.011157627,0.0026351074],"about_ca_topic_score_codex":0.00005402315,"about_ca_topic_score_gemma":0.00011710867,"teacher_disagreement_score":0.18078887,"about_ca_system_score_codex":0.00009346412,"about_ca_system_score_gemma":0.000039921524,"threshold_uncertainty_score":0.9781091},"labels":[],"label_agreement":null},{"id":"W2110425652","doi":"10.1111/j.1537-2995.2011.03324.x","title":"Causal inference in nonrandomized studies via propensity score methods","year":2011,"lang":"en","type":"review","venue":"Transfusion","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"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 Waterloo","funders":"","keywords":"Citation; Statistics; Library science; Medicine; Mathematics; Computer science","score_opus":0.6001654820672533,"score_gpt":0.5487720596401654,"score_spread":0.05139342242708789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110425652","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":[0.000049043425,0.758179,0.23731281,0.0000047244407,0.00018542679,0.0033366412,0.000009267241,0.00036366683,0.00055942894],"genre_scores_gemma":[0.000016322281,0.86649925,0.13248692,0.000009528084,0.000045892088,0.00069157063,0.000014913435,0.00009783587,0.00013778119],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954255,0.00162919,0.0014526711,0.0007500565,0.00025390586,0.0004886708],"domain_scores_gemma":[0.99454004,0.0038369724,0.0004903523,0.0008243657,0.00020833725,0.0000999246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026293676,0.0008335244,0.0048014764,0.0003931253,0.000094413896,0.000020183637,0.0005222589,0.0006166571,0.00014778772],"category_scores_gemma":[0.001971255,0.0005795614,0.0005012917,0.00055037334,0.000209843,0.00022464187,0.00019033988,0.0011505154,0.000032007883],"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":[0.00012485313,0.00017745986,0.0000038345456,0.015747685,0.00012747891,0.00004455538,0.00090666243,8.451637e-8,0.000034595523,0.0044838497,0.000028285616,0.97832066],"study_design_scores_gemma":[0.005628181,0.00076252664,0.000006292821,0.11604819,0.0039012397,0.0001380207,0.00010444184,0.000020436442,0.0011681227,0.6207294,0.24813621,0.0033569692],"about_ca_topic_score_codex":0.00012844443,"about_ca_topic_score_gemma":0.00048775767,"teacher_disagreement_score":0.97496367,"about_ca_system_score_codex":0.0002513294,"about_ca_system_score_gemma":0.00020843167,"threshold_uncertainty_score":0.99966556},"labels":[],"label_agreement":null},{"id":"W2110818436","doi":"10.1002/sim.6607","title":"Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies","year":2015,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4309,"is_retracted":false,"has_abstract":true,"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 Mental Health; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Inverse probability weighting; Observational study; Inverse probability; Weighting; Average treatment effect; Statistics; Treatment and control groups; Econometrics; Sample size determination; Baseline (sea); Mathematics; Selection bias; Computer science; Posterior probability; Medicine; Bayesian probability","score_opus":0.6765608631638398,"score_gpt":0.5702584500397571,"score_spread":0.10630241312408273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110818436","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011806213,0.798593,0.1680657,0.0002591576,0.000776616,0.019474735,0.0005742618,0.00017279174,0.00027753433],"genre_scores_gemma":[0.0000461117,0.22818658,0.7710488,0.000028378035,0.00013268158,0.00038503396,0.000067938774,0.00007215919,0.00003233563],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956156,0.0009921558,0.0016808601,0.00060616253,0.0006564941,0.00044872993],"domain_scores_gemma":[0.9908638,0.00617586,0.001314674,0.0006982357,0.0008240381,0.00012338949],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026964298,0.0007237854,0.0031906613,0.00029772744,0.00010944421,0.0000176138,0.0002717285,0.00018826159,0.000006667016],"category_scores_gemma":[0.023051841,0.00041989377,0.000078120356,0.00056975946,0.00041745664,0.00017842643,0.0002624058,0.0004139525,0.0000011613803],"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":[0.00020542304,0.0020609275,0.0015475958,0.07049702,0.0014108038,0.0009908285,0.027532509,0.0016593756,0.000060217648,0.061163206,0.00041195707,0.83246017],"study_design_scores_gemma":[0.003798125,0.00917749,0.00008317934,0.23041928,0.012964728,0.000320958,0.0029605366,0.013449472,0.00011405706,0.69563556,0.028882224,0.002194393],"about_ca_topic_score_codex":0.0021494594,"about_ca_topic_score_gemma":0.001972817,"teacher_disagreement_score":0.83026576,"about_ca_system_score_codex":0.0070568663,"about_ca_system_score_gemma":0.0015856574,"threshold_uncertainty_score":0.9998253},"labels":[],"label_agreement":null},{"id":"W2111635289","doi":"10.1002/pst.433","title":"Optimal caliper widths for propensity‐score matching when estimating differences in means and differences in proportions in observational studies","year":2010,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3895,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Calipers; Statistics; Estimator; Mathematics; Logit; Matching (statistics); Observational study; Econometrics; Standard deviation; Confidence interval; Logistic regression; Medicine","score_opus":0.5850172035475715,"score_gpt":0.5093227869028153,"score_spread":0.07569441664475618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111635289","genre_codex":"empirical","genre_gemma":"methods","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":[0.7048489,0.000039273156,0.29310173,0.0004205741,0.00010536691,0.0009971044,0.00037524087,0.00007291753,0.000038930175],"genre_scores_gemma":[0.47615474,0.00002361761,0.52334493,0.000063169784,0.00003287132,0.00031639158,0.000026355883,0.000016773818,0.000021136719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798936,0.00010141182,0.00076289114,0.00039474992,0.0002937372,0.00045788183],"domain_scores_gemma":[0.99596053,0.003444055,0.00016898094,0.00013769526,0.00016493128,0.00012377546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067208987,0.00027215754,0.000583042,0.00015059032,0.000107504806,0.00006419125,0.00018363513,0.00010836694,0.00014272657],"category_scores_gemma":[0.0053334255,0.00022610907,0.000023546645,0.00017159648,0.00034571305,0.00026038743,0.00015340246,0.00071759283,0.0000010751643],"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":[0.00011833147,0.00058959285,0.4410522,0.0011636569,0.00004771452,0.00006528252,0.005470528,0.00007393833,0.0017917563,0.54016095,0.00045085553,0.009015203],"study_design_scores_gemma":[0.0006265716,0.00007762445,0.05886068,0.0003398299,0.00003392851,0.000008525208,0.00042438603,0.0989402,0.00025393296,0.84006137,0.00003384267,0.0003391106],"about_ca_topic_score_codex":0.00006342919,"about_ca_topic_score_gemma":0.0018132363,"teacher_disagreement_score":0.38219154,"about_ca_system_score_codex":0.00009149244,"about_ca_system_score_gemma":0.000095098716,"threshold_uncertainty_score":0.92204607},"labels":[],"label_agreement":null},{"id":"W2111736598","doi":"10.1920/wp.cem.2013.6113","title":"Covariate selection and model averaging in semiparametric estimation of treatment effects","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"Simon Fraser University","funders":"Economic and Social Research Council; Yale University","keywords":"Covariate; Semiparametric model; Selection (genetic algorithm); Econometrics; Estimation; Statistics; Semiparametric regression; Model selection; Mathematics; Computer science; Artificial intelligence; Parametric statistics; Economics","score_opus":0.12366938119572668,"score_gpt":0.40286961887864225,"score_spread":0.2792002376829156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111736598","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":[0.3878564,0.000027424772,0.61064965,0.000010624911,0.000018102097,0.00077464664,0.0000018202262,0.00015368761,0.0005076519],"genre_scores_gemma":[0.59895045,0.00006530583,0.4006471,0.0000043247674,0.000004028853,0.00020625678,0.0000060848943,0.000015348598,0.00010107035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990261,0.00005952365,0.00036777553,0.0002896496,0.00010868508,0.00014824943],"domain_scores_gemma":[0.99886924,0.0005314914,0.00026454317,0.00023033582,0.00007103559,0.000033331515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001874016,0.00023499387,0.0004597592,0.00043248682,0.000016488884,0.000025935635,0.00006626573,0.00023402399,0.000010137762],"category_scores_gemma":[0.00034632004,0.00020278238,0.00004045542,0.00018765086,0.000018358007,0.000117155876,0.0001317312,0.00021831387,0.0000017186551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026030735,0.00038283886,0.00059895794,0.0026792774,0.00011839939,0.0000021763367,0.0016323177,0.799508,0.0037258377,0.13543515,0.00009542085,0.05579561],"study_design_scores_gemma":[0.0001238939,0.00006283841,0.000052209758,0.00017023488,0.000026443411,0.0000011886724,0.00000323073,0.5410474,0.017856892,0.4405614,1.5699158e-7,0.000094107054],"about_ca_topic_score_codex":0.0005332344,"about_ca_topic_score_gemma":0.00003368755,"teacher_disagreement_score":0.30512628,"about_ca_system_score_codex":0.0004901814,"about_ca_system_score_gemma":0.000074025906,"threshold_uncertainty_score":0.82692254},"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":"W2115556810","doi":"10.1002/sim.6602","title":"Optimal full matching for survival outcomes: a method that merits more widespread use","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"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 Mental Health; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Matching (statistics); Computer science; Statistics; Survival analysis; Propensity score matching; Econometrics; Mathematics","score_opus":0.33550950521288825,"score_gpt":0.5206100027822268,"score_spread":0.18510049756933855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115556810","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":[0.0067818807,0.000035842706,0.9906246,0.0006453011,0.00042169145,0.0006933033,0.0003053893,0.00021219612,0.00027978036],"genre_scores_gemma":[0.011036522,0.00002152428,0.98783815,0.0002762758,0.00009592873,0.00013654948,0.000084533225,0.00007191842,0.00043859362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978845,0.00016267042,0.0005982985,0.00034273867,0.0005814085,0.0004303471],"domain_scores_gemma":[0.9906164,0.0081773065,0.00025647334,0.0004569849,0.00029583016,0.00019700373],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021452082,0.0003064504,0.0008335517,0.0001801146,0.00004602185,0.000023630444,0.0002802006,0.00011991994,0.000047755297],"category_scores_gemma":[0.013807979,0.00024160316,0.00003665055,0.00014625322,0.0001823218,0.00020312093,0.00010019604,0.0003307874,0.0000040284326],"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":[0.0003229625,0.0001793154,0.0035865745,0.00043752577,0.00011199749,0.00016970362,0.010126838,0.00020691613,0.0012650117,0.9448155,0.028931087,0.009846566],"study_design_scores_gemma":[0.0017136451,0.00045760925,0.00038856504,0.0003126428,0.00010132323,0.000018919887,0.002958239,0.0039536827,0.0005022667,0.98815924,0.0011008888,0.00033296854],"about_ca_topic_score_codex":0.00024445637,"about_ca_topic_score_gemma":0.00023592635,"teacher_disagreement_score":0.04334375,"about_ca_system_score_codex":0.00016923284,"about_ca_system_score_gemma":0.00008108171,"threshold_uncertainty_score":0.99449915},"labels":[],"label_agreement":null},{"id":"W2115685617","doi":"10.1093/aje/kwu276","title":"A Cautionary Note About Estimating Effects of Secondary Exposures in Cohort Studies","year":2015,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Cohort; Cohort study; Medicine; Epidemiology; Statistics; Econometrics; Demography; Mathematics; Internal medicine","score_opus":0.1736686592204544,"score_gpt":0.4889863480783091,"score_spread":0.3153176888578547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115685617","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":[0.7226216,0.0043909834,0.27159336,0.00050907827,0.0003497822,0.00020968974,0.000003093411,0.00003848239,0.00028392382],"genre_scores_gemma":[0.50441486,0.0001618383,0.4950607,0.0002608162,0.00007287247,0.000010638381,6.188461e-7,0.000011831855,0.0000058006153],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968408,0.0011321754,0.0014649022,0.00015146715,0.00012870324,0.000281997],"domain_scores_gemma":[0.9826656,0.014473818,0.002183543,0.0002094759,0.00035001978,0.00011756004],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00510765,0.00016130321,0.0015089256,0.00022831948,0.0000192685,0.0000012084802,0.00021190541,0.0000634175,0.0000042087504],"category_scores_gemma":[0.04877804,0.00012744976,0.000110329005,0.00020101713,0.0007599356,0.00014399605,0.000081830614,0.00044911125,0.000001164652],"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":[0.00046878704,0.00043999485,0.7579279,0.000866375,0.0010833928,0.0005368107,0.008241953,0.0023168416,0.002564083,0.113385215,0.011060303,0.10110836],"study_design_scores_gemma":[0.0004877955,0.002290788,0.024639819,0.00072653964,0.00007926894,0.0003214219,0.000950175,0.00040757222,0.00085226446,0.96895206,0.00012144925,0.00017083787],"about_ca_topic_score_codex":0.00007959627,"about_ca_topic_score_gemma":0.000014893856,"teacher_disagreement_score":0.85556686,"about_ca_system_score_codex":0.00017550544,"about_ca_system_score_gemma":0.00017288032,"threshold_uncertainty_score":0.95923454},"labels":[],"label_agreement":null},{"id":"W2116345053","doi":"10.1007/s10985-006-9012-2","title":"A formal test for the stationarity of the incidence rate using data from a prevalent cohort study with follow-up","year":2006,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":83,"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","funders":"","keywords":"Incidence (geometry); Statistics; Cohort; Null hypothesis; Test (biology); Econometrics; Statistical hypothesis testing; Null (SQL); Medicine; Mathematics; Demography; Computer science; Data mining; Biology","score_opus":0.16039986620700372,"score_gpt":0.4110143209759239,"score_spread":0.2506144547689202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116345053","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":[0.29656556,0.000044767166,0.689873,0.000085709115,0.000016912769,0.0015727764,0.011769337,0.000054378703,0.000017590097],"genre_scores_gemma":[0.90772486,0.0000087734925,0.0891675,0.000032882297,0.000049219565,0.00008897662,0.0027956816,0.00002079582,0.000111290974],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797845,0.00016460879,0.0005617312,0.0005465719,0.00052701565,0.00022164907],"domain_scores_gemma":[0.99130315,0.0030515487,0.0005904346,0.004793815,0.00023307663,0.000028008793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001891503,0.00018965738,0.00044209755,0.00007545023,0.0002535295,0.00006915633,0.0024410684,0.000041727813,0.000067249544],"category_scores_gemma":[0.0017742349,0.000104052146,0.00007790498,0.0008495025,0.00013392846,0.00085935654,0.0014875769,0.00013435057,0.0000012999609],"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":[0.00013487593,0.0006614386,0.9904828,0.00004582056,0.0027047922,0.000002277935,0.00021965688,0.0016534915,0.000455177,0.00066384656,0.0027921414,0.00018370106],"study_design_scores_gemma":[0.0009206799,0.00018204596,0.3544206,0.000092056165,0.023524547,0.0000018619097,0.000808211,0.5959566,0.00084790983,0.022573989,0.00026534265,0.00040612632],"about_ca_topic_score_codex":0.0046849744,"about_ca_topic_score_gemma":0.011296529,"teacher_disagreement_score":0.63606215,"about_ca_system_score_codex":0.000045501052,"about_ca_system_score_gemma":0.00010810843,"threshold_uncertainty_score":0.70823115},"labels":[],"label_agreement":null},{"id":"W2117317003","doi":"10.1002/pds.1357","title":"Immortal time bias in observational studies of drug effects","year":2007,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":569,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; AstraZeneca","keywords":"Medicine; Observational study; Pharmacoepidemiology; COPD; Cohort study; Drug; Disease; Pulmonary disease; Cohort; Internal medicine; Intensive care medicine; Pharmacology; Medical prescription","score_opus":0.3359460404749271,"score_gpt":0.5112862260978849,"score_spread":0.17534018562295778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117317003","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":[0.98314756,0.0027850477,0.010716573,0.001215755,0.00017090455,0.0004618569,0.0000133290205,0.00015655028,0.0013324273],"genre_scores_gemma":[0.9645533,0.00073482096,0.033495136,0.00079185155,0.00007773558,0.000026727525,0.000013631717,0.000016889442,0.0002899187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777555,0.0006608873,0.0008602929,0.00026585467,0.0001037413,0.00033363947],"domain_scores_gemma":[0.9716604,0.027716476,0.0003157487,0.00014601948,0.000095004936,0.00006640219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008221722,0.00019708542,0.0007125695,0.00012347748,0.000061256695,0.0000011402602,0.00012330382,0.000082978564,0.0000361587],"category_scores_gemma":[0.007318458,0.00016409243,0.00006685915,0.00017050371,0.00031831645,0.00014926167,0.000116378695,0.0003040052,0.000005229092],"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":[0.00095931464,0.0004829973,0.43618092,0.0012741713,0.0004395365,0.00009947551,0.0042371065,0.00013025211,0.022636596,0.49139017,0.022015797,0.020153673],"study_design_scores_gemma":[0.0016045712,0.00007407402,0.10538982,0.0002813255,0.00010986535,0.000023069913,0.0003021108,0.0014983976,0.043613836,0.845219,0.0014232169,0.00046067924],"about_ca_topic_score_codex":0.000023002687,"about_ca_topic_score_gemma":0.000048788155,"teacher_disagreement_score":0.35382888,"about_ca_system_score_codex":0.00005451572,"about_ca_system_score_gemma":0.00002199397,"threshold_uncertainty_score":0.87614065},"labels":[],"label_agreement":null},{"id":"W2117578563","doi":"10.1002/sim.6185","title":"Propensity score methods for estimating relative risks in cluster randomized trials with low‐incidence binary outcomes and selection bias","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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":"Agence Nationale de la Recherche","keywords":"Propensity score matching; Covariate; Selection bias; Statistics; Inverse probability weighting; Weighting; Randomization; Regression; Randomized controlled trial; Selection (genetic algorithm); Relative risk; Cluster (spacecraft); Medicine; Econometrics; Mathematics; Computer science; Internal medicine; Artificial intelligence; Confidence interval","score_opus":0.39037839286313425,"score_gpt":0.5488097609618341,"score_spread":0.15843136809869984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117578563","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":[0.041647874,0.000032633467,0.95506805,0.00024965545,0.00007569079,0.0027429555,0.000010616129,0.00007177984,0.00010074537],"genre_scores_gemma":[0.10393599,0.000023667968,0.89546686,0.000111901,0.000046423505,0.00033135636,0.0000101420255,0.000027708875,0.000045962996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99576896,0.0023217485,0.0011276789,0.00032115303,0.0002196726,0.00024078618],"domain_scores_gemma":[0.94126475,0.057576347,0.0007050382,0.00015765263,0.00024019381,0.000056003544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02144462,0.0002392465,0.0019001022,0.00024290135,0.000067975896,0.000013769708,0.00009047767,0.00010430261,0.000013543294],"category_scores_gemma":[0.19310287,0.00014617693,0.00002940782,0.00023871675,0.0003996468,0.00015532775,0.000050557584,0.00036594865,3.1143094e-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":[0.05399907,0.00032666457,0.056473892,0.002938574,0.00033717288,0.000046157675,0.010129942,0.0012413551,0.0021716943,0.70821345,0.0012471611,0.16287485],"study_design_scores_gemma":[0.035881948,0.0004933808,0.0025268327,0.0012327835,0.00015718462,0.000008140283,0.000076855635,0.16402851,0.00035182163,0.79506546,0.0000031206582,0.00017396694],"about_ca_topic_score_codex":0.00023132586,"about_ca_topic_score_gemma":0.00030122718,"teacher_disagreement_score":0.17165825,"about_ca_system_score_codex":0.0001045524,"about_ca_system_score_gemma":0.00004966883,"threshold_uncertainty_score":0.813694},"labels":[],"label_agreement":null},{"id":"W2117770228","doi":"10.1136/bmjopen-2014-005362","title":"Estimating treatment effects in randomised controlled trials with non-compliance: a simulation study","year":2014,"lang":"en","type":"article","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":73,"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; St. Joseph’s Healthcare Hamilton","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Randomized controlled trial; Psychological intervention; Type I and type II errors; Treatment and control groups; Sample size determination; Instrumental variable; Intention-to-treat analysis; Statistics; Surgery; Mathematics; Internal medicine","score_opus":0.35392174226404155,"score_gpt":0.5547976196864092,"score_spread":0.20087587742236762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117770228","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":[0.24342003,0.0000036202678,0.6483109,0.000044927496,0.00005764877,0.10327192,0.0000013294612,0.00015401542,0.0047356277],"genre_scores_gemma":[0.81339604,1.5445308e-7,0.16850112,0.000027077604,0.000057401656,0.017838882,0.0000023769467,0.000026535448,0.00015039677],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711496,0.0012211353,0.00092756166,0.000290995,0.00023374034,0.00021163265],"domain_scores_gemma":[0.9858486,0.01279789,0.0007187477,0.0005033216,0.00008055733,0.00005088384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006627402,0.0002481459,0.0021648877,0.00008655643,0.00006960424,0.00012326756,0.00025221673,0.00005286418,0.000025306694],"category_scores_gemma":[0.011507262,0.00014769021,0.0000906742,0.00013937532,0.000019134322,0.00023206964,0.000081361584,0.00007655539,0.000010773166],"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":[0.38115892,0.016498005,0.030015757,0.0020959903,0.0032663064,0.00036792184,0.025591685,0.29966176,0.005219619,0.017952265,0.00046080156,0.21771097],"study_design_scores_gemma":[0.38236135,0.0034114062,0.0012056109,0.0012874582,0.00032550708,0.0000024672913,0.00021040493,0.5278317,0.0011216964,0.081823945,0.000006548153,0.000411958],"about_ca_topic_score_codex":0.000081220576,"about_ca_topic_score_gemma":0.0001189027,"teacher_disagreement_score":0.56997603,"about_ca_system_score_codex":0.00013483794,"about_ca_system_score_gemma":0.000062768966,"threshold_uncertainty_score":0.99681926},"labels":[],"label_agreement":null},{"id":"W2119030200","doi":"10.1002/0470011815.b2a04017","title":"Drug Utilization Patterns","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":30,"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":"Observational study; Data collection; Nonparametric statistics; Drug; Computer science; Data science; Medicine; Econometrics; Pharmacology; Statistics; Economics; Mathematics","score_opus":0.0715196213504441,"score_gpt":0.38155852799319634,"score_spread":0.31003890664275224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119030200","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008027305,0.00024644664,0.3672789,0.000022270026,0.00024141015,0.0003719696,0.0014902832,0.00047919367,0.6298615],"genre_scores_gemma":[0.00018707747,0.0067403363,0.38044265,0.000036795926,0.0004408011,0.000027615975,0.00029604338,0.0005924412,0.6112362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985338,0.000056331104,0.0005176191,0.00029445428,0.0003473905,0.00025039836],"domain_scores_gemma":[0.99823374,0.00037358108,0.0006913078,0.00054015656,0.0000861558,0.00007503522],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011725281,0.00034870845,0.00051495666,0.00025579834,0.00001925132,0.000008798575,0.00028032617,0.00027427782,0.005450793],"category_scores_gemma":[0.00059708254,0.00034444034,0.00006155158,0.00013317788,0.000099949226,0.000039788792,0.00008347867,0.00022335713,0.00005950072],"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":[0.000002761484,0.00008714247,0.00014034685,0.0004690299,0.000033134816,0.000009094717,0.00015711659,3.2301685e-7,0.0000046334726,0.078098476,0.88771474,0.03328317],"study_design_scores_gemma":[0.00017231508,0.000049618367,0.00005352896,0.0007057498,0.00011554718,0.0000029828527,0.000060708713,0.000024757352,0.0003624162,0.08838322,0.9095619,0.00050728035],"about_ca_topic_score_codex":0.00008570691,"about_ca_topic_score_gemma":0.00048175553,"teacher_disagreement_score":0.03277589,"about_ca_system_score_codex":0.00004940316,"about_ca_system_score_gemma":0.00006997846,"threshold_uncertainty_score":0.99990076},"labels":[],"label_agreement":null},{"id":"W2119138019","doi":"10.1515/em-2012-0006","title":"Comparison of Approaches to Weight Truncation for Marginal Structural Cox Models","year":2013,"lang":"en","type":"article","venue":"Epidemiologic Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":98,"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; Institut National d'Excellence en Santé et en Services Sociaux","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; Johns Hopkins Bloomberg School of Public Health; Feinberg School of Medicine; University of California, Los Angeles; Deutsches Krebsforschungszentrum; Natural Sciences and Engineering Research Council of Canada; University of Pittsburgh; Johns Hopkins University; National Cancer Institute; Fonds Québécois de la Recherche sur la Nature et les Technologies; McGill University; Northwestern University","keywords":"Truncation (statistics); Estimator; Weighting; Marginal structural model; Mean squared error; Mathematics; Statistics; Percentile; Applied mathematics; Computer science; Econometrics; Mathematical optimization; Confounding","score_opus":0.8429178298825912,"score_gpt":0.5997911695234979,"score_spread":0.24312666035909336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119138019","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":[0.032587197,0.00011501864,0.9634397,0.00076197466,0.00008850255,0.0013676913,0.000009372696,0.00018573157,0.0014447899],"genre_scores_gemma":[0.2314574,0.0000035103371,0.767644,0.00010926571,0.000051463197,0.000570832,0.000012295552,0.000016244367,0.0001349983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971889,0.0011078886,0.0008973382,0.00035458838,0.000109936154,0.00034132708],"domain_scores_gemma":[0.98789746,0.010869933,0.00051343156,0.00046315265,0.00015213671,0.000103873565],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040687043,0.00022353766,0.00093546876,0.00009354616,0.00006605735,0.000008957032,0.0003235136,0.00019624633,0.00011563531],"category_scores_gemma":[0.011215723,0.00015936537,0.00013309841,0.00014738481,0.00009869075,0.00019857458,0.00008695841,0.00017828462,0.000004328571],"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":[0.00003402514,0.000039182865,0.0016600759,0.0001325646,0.000027457789,4.4570612e-8,0.00042201264,0.0011005332,0.005352922,0.90792745,0.0053684614,0.07793527],"study_design_scores_gemma":[0.000084568834,0.00018525256,0.00073171,0.000020008192,0.000020632138,0.0000012496247,0.00011225383,0.16026442,0.024287473,0.813922,0.00021831233,0.00015212416],"about_ca_topic_score_codex":0.000026868072,"about_ca_topic_score_gemma":0.0000021317178,"teacher_disagreement_score":0.1988702,"about_ca_system_score_codex":0.000065583066,"about_ca_system_score_gemma":0.000019937614,"threshold_uncertainty_score":0.9971132},"labels":[],"label_agreement":null},{"id":"W2119511462","doi":"10.1002/sim.6433","title":"Penalized regression procedures for variable selection in the potential outcomes framework","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; National Institute on Drug Abuse; National Institutes of Health","keywords":"Causal inference; Imputation (statistics); Computer science; Inference; Missing data; Regression; Multivariate statistics; Feature selection; Regression analysis; Artificial intelligence; Model selection; Selection (genetic algorithm); Machine learning; Data mining; Econometrics; Statistics; Mathematics","score_opus":0.11775119733631027,"score_gpt":0.4738352817476763,"score_spread":0.356084084411366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119511462","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":[0.0022162716,0.000047293135,0.9951704,0.0008451408,0.0001516555,0.0007578935,0.000022181934,0.00007072654,0.00071844866],"genre_scores_gemma":[0.11992375,0.000023222994,0.8791226,0.00036555793,0.00012776275,0.00018375504,0.000024329222,0.000021632442,0.00020736404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866515,0.00012590567,0.00041264802,0.00017977148,0.00038214037,0.00023439499],"domain_scores_gemma":[0.9974202,0.0020232995,0.00015842712,0.00016771154,0.0001852111,0.000045139575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015632868,0.00014762048,0.0003339271,0.00012737079,0.000044914086,0.000011505498,0.00019818706,0.0001121341,0.000047280526],"category_scores_gemma":[0.022077708,0.00008502322,0.000013081002,0.00029574576,0.000093466064,0.000063041174,0.00002530819,0.00032681992,0.000001203842],"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":[0.00011570201,0.00009160449,0.0021278285,0.00015676762,0.000007885732,0.000011917576,0.002164261,0.00003534145,0.0002892188,0.9636171,0.030680649,0.00070174463],"study_design_scores_gemma":[0.00091993215,0.00025197066,0.0012279848,0.00042078737,0.000027509885,0.000009243181,0.0007140399,0.0014147386,0.00006786412,0.99450105,0.00034635965,0.000098488184],"about_ca_topic_score_codex":0.000072349736,"about_ca_topic_score_gemma":0.00012459446,"teacher_disagreement_score":0.117707476,"about_ca_system_score_codex":0.000102914775,"about_ca_system_score_gemma":0.00011263149,"threshold_uncertainty_score":0.98615974},"labels":[],"label_agreement":null},{"id":"W2119675638","doi":"10.1007/3-540-44886-1_4","title":"The Structure Model Interpretation of Wright’s NESS Test","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"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 Saskatchewan","funders":"","keywords":"Wright; Causation; Overdetermination; Epistemology; Test (biology); Interpretation (philosophy); Pearl; Terminology; Philosophy; Computer science; Linguistics; Theology","score_opus":0.049103651438285316,"score_gpt":0.3350629119220473,"score_spread":0.28595926048376197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119675638","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":[0.00013072867,0.00011443721,0.99680954,0.00015510041,0.0002980237,0.0003822763,0.000016330918,0.00008797847,0.0020056101],"genre_scores_gemma":[0.4227777,0.000047906215,0.5762698,0.0003684747,0.000079983925,0.0000066082944,0.0000034920515,0.000050830666,0.0003951727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979975,0.000022188138,0.0005258484,0.0005406726,0.00058740884,0.0003263738],"domain_scores_gemma":[0.99640226,0.0018611451,0.00045474072,0.0008810745,0.00034772308,0.000053071664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045655385,0.00036495875,0.00042007875,0.00023268357,0.00016036129,0.00009627562,0.001138591,0.00028513046,0.000014004213],"category_scores_gemma":[0.00070943247,0.00024303247,0.00008092596,0.00020969077,0.0009570304,0.00020943154,0.00025727993,0.0006704907,0.0000013549685],"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":[0.00001808536,0.000038136994,0.00002838908,0.00018268041,0.000019414076,0.000010772623,0.0015337412,0.06554011,0.0024589866,0.5344979,0.00012473589,0.395547],"study_design_scores_gemma":[0.000043878998,0.000055472265,0.0000013328103,0.00021739729,0.000008858514,0.000010186727,2.4278464e-7,0.26742068,0.006969268,0.72501785,0.000059413152,0.00019544155],"about_ca_topic_score_codex":0.0000017716799,"about_ca_topic_score_gemma":0.000087551605,"teacher_disagreement_score":0.422647,"about_ca_system_score_codex":0.0001927548,"about_ca_system_score_gemma":0.00021918488,"threshold_uncertainty_score":0.99105763},"labels":[],"label_agreement":null},{"id":"W2119762928","doi":"10.1093/aje/kwn299","title":"Instrumental Variable Analysis for Estimation of Treatment Effects With Dichotomous Outcomes","year":2008,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":168,"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":"Instrumental variable; Estimation; Medicine; Statistics; Variable (mathematics); Econometrics; Mathematics; Economics","score_opus":0.1069183705597743,"score_gpt":0.42547931669381167,"score_spread":0.3185609461340374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119762928","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":[0.47342172,0.000020353975,0.52626234,0.00007752234,0.00001660314,0.00014280439,0.0000057727793,0.000013867303,0.00003901678],"genre_scores_gemma":[0.5442217,0.000030272897,0.4556211,0.000072953255,0.000010327743,0.000019063844,0.0000030458675,0.000008210509,0.0000133135745],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984236,0.00032109843,0.000812709,0.0001332061,0.00008371321,0.00022570383],"domain_scores_gemma":[0.9894113,0.008309771,0.0018363617,0.00021151516,0.00014550387,0.000085529835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007794322,0.00016295625,0.001514584,0.00026841424,0.000044753862,0.0000011433248,0.00012698393,0.000042607167,0.0000113600945],"category_scores_gemma":[0.0031143776,0.000100661055,0.00024329417,0.0003549243,0.0003951906,0.000102668884,0.0000125780025,0.000090582056,3.0768066e-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":[0.0008188484,0.0006645103,0.8922752,0.000085067135,0.006025653,0.00003445945,0.00073198805,0.017939873,0.00092994067,0.04038854,0.00023584234,0.039870083],"study_design_scores_gemma":[0.0063866833,0.08204148,0.13399506,0.00032085838,0.008294707,0.0016353729,0.0007051274,0.015699545,0.020743763,0.7286973,0.00043162808,0.0010484672],"about_ca_topic_score_codex":0.00014370338,"about_ca_topic_score_gemma":0.000011039742,"teacher_disagreement_score":0.75828016,"about_ca_system_score_codex":0.00020058628,"about_ca_system_score_gemma":0.00009774265,"threshold_uncertainty_score":0.41048387},"labels":[],"label_agreement":null},{"id":"W2119863846","doi":"10.1016/j.jclinepi.2014.12.018","title":"Interrupted time series analysis in drug utilization research is increasing: systematic review and recommendations","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":486,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Interrupted time series; Interrupted Time Series Analysis; Medicine; MEDLINE; Systematic review; Psychological intervention; Meta-analysis; Research design; Statistics; Pathology; Mathematics","score_opus":0.8623636112980363,"score_gpt":0.7162576385668367,"score_spread":0.14610597273119963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119863846","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":[0.0000038901962,0.9927569,0.0031180766,0.0024651175,0.00009383719,0.0012699763,0.000025042282,0.000029579667,0.00023757687],"genre_scores_gemma":[0.000004125514,0.9667422,0.032163143,0.0004649919,0.00010790188,0.000066331755,0.00003781709,0.000038009275,0.00037543598],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9277359,0.056292128,0.014740167,0.00045735366,0.00036210183,0.00041234388],"domain_scores_gemma":[0.8437547,0.14115447,0.012203568,0.0008564668,0.001669757,0.00036105292],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18579333,0.00039801878,0.019838037,0.0013214712,0.000051746767,0.000019270814,0.0006868938,0.0007414176,0.00017467278],"category_scores_gemma":[0.46344575,0.0002624571,0.0013210706,0.0017717405,0.00039064867,0.00029104511,0.00030461076,0.0028480287,0.000025883879],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047369547,0.00032479205,0.0002526049,0.8643678,0.003177988,0.000032953812,0.00013512251,3.3389168e-7,1.4446556e-8,0.011701195,0.049241308,0.07071853],"study_design_scores_gemma":[0.00018289391,0.00036789436,0.000011037919,0.57980096,0.017941762,0.00035841,0.000060793227,0.00005926472,4.66222e-8,0.2225594,0.17832322,0.00033432266],"about_ca_topic_score_codex":0.000019967854,"about_ca_topic_score_gemma":0.000033476223,"teacher_disagreement_score":0.28456685,"about_ca_system_score_codex":0.00027768448,"about_ca_system_score_gemma":0.00055518164,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null},{"id":"W2120052464","doi":"10.1093/ije/dyh330","title":"Commentary: Insights from cross-population studies: Rose revisited","year":2005,"lang":"en","type":"letter","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute","funders":"","keywords":"Rose (mathematics); Population; Medicine; Demography; Biology; Environmental health; Sociology","score_opus":0.28225431656014194,"score_gpt":0.5234674852899659,"score_spread":0.24121316872982396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120052464","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":[0.010550716,0.006972936,0.026631279,0.950673,0.004103226,0.00034262662,0.00029695168,0.00014726633,0.000282004],"genre_scores_gemma":[0.004556725,0.0029634954,0.11688682,0.85302424,0.021271553,0.0000162159,0.0009779827,0.00008146153,0.00022152663],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99455446,0.0012115305,0.0029489715,0.00038739303,0.0005634858,0.0003341685],"domain_scores_gemma":[0.97761554,0.015828887,0.0044747586,0.00042703934,0.0015776481,0.00007612386],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015380481,0.00044238367,0.0017183018,0.00051536877,0.00005667221,0.000030650048,0.0012044262,0.00089681655,0.0002802825],"category_scores_gemma":[0.017824298,0.00035254867,0.0004498071,0.00008284959,0.00024847337,0.00046713545,0.0002471928,0.0025887112,0.00002151695],"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":[0.000074814445,0.000045331974,0.0028119565,0.000028806742,0.0012208425,0.0004020707,0.00012390189,0.000030892792,0.000027619846,0.0045253984,0.98825765,0.0024507286],"study_design_scores_gemma":[0.00031296298,0.00009074002,0.00056548254,0.0005424585,0.00009424774,0.00009869201,0.0000121662015,0.000032701922,0.000040551167,0.53110516,0.4669054,0.0001994592],"about_ca_topic_score_codex":0.00010088486,"about_ca_topic_score_gemma":0.000025282987,"teacher_disagreement_score":0.52657974,"about_ca_system_score_codex":0.0010386581,"about_ca_system_score_gemma":0.00004635241,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W2122067453","doi":"10.1093/aje/kwt435","title":"Re: \"Estimating the Relative Risk in Cohort Studies and Clinical Trials of Common Outcomes\"","year":2014,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Relative risk; Cohort study; Cohort; Clinical trial; Confidence interval; Internal medicine","score_opus":0.5212791738585023,"score_gpt":0.6000301761944622,"score_spread":0.07875100233595989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122067453","genre_codex":"commentary","genre_gemma":"methods","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":[0.050360736,0.0035564094,0.2635418,0.67986125,0.0010157558,0.0013083944,0.00004472389,0.00005724066,0.00025368066],"genre_scores_gemma":[0.02504941,0.0077142655,0.73148793,0.23374853,0.0018223677,0.000038530343,0.000006349989,0.00008904882,0.00004355938],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9556255,0.035370085,0.008025974,0.00033531737,0.00023065334,0.00041248943],"domain_scores_gemma":[0.59504265,0.38120347,0.022789594,0.0005690783,0.00033310245,0.00006211633],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075973846,0.00039048647,0.008398144,0.0002467768,0.0000577924,0.0000037276793,0.00052089564,0.0004806135,0.000008691599],"category_scores_gemma":[0.42924672,0.00020787411,0.00069162477,0.00017288706,0.0029735838,0.000088311346,0.00017901738,0.0051980945,8.726073e-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":[0.00011108614,0.000048582908,0.6394885,0.00013148092,0.0032425458,0.00007143364,0.0006285286,0.000037201233,5.083855e-7,0.0031050346,0.32586575,0.027269345],"study_design_scores_gemma":[0.00046512688,0.0018672855,0.014245916,0.0009454802,0.001358489,0.00009632003,0.000519418,0.00019830426,0.0000020841633,0.97452396,0.0055131093,0.00026449317],"about_ca_topic_score_codex":0.00017345005,"about_ca_topic_score_gemma":0.000049947193,"teacher_disagreement_score":0.9714189,"about_ca_system_score_codex":0.00012000659,"about_ca_system_score_gemma":0.00007975619,"threshold_uncertainty_score":0.99973977},"labels":[],"label_agreement":null},{"id":"W2122527396","doi":"10.1002/sim.3801","title":"Missing data in the exposure of interest and marginal structural models: A simulation study based on the Framingham Heart Study","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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 Medical Research Council; National Health and Medical Research Council","keywords":"Missing data; Inverse probability; Framingham Heart Study; Marginal structural model; Statistics; Confounding; Propensity score matching; Computer science; Econometrics; Outcome (game theory); Mathematics; Medicine; Framingham Risk Score; Bayesian probability","score_opus":0.3765319600692848,"score_gpt":0.49942054001456876,"score_spread":0.12288857994528396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122527396","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":[0.7440605,0.0000312929,0.2535987,0.000853489,0.0000274913,0.0012641712,0.000045747853,0.00002224686,0.00009636941],"genre_scores_gemma":[0.9628218,0.0000016874533,0.03688197,0.0002312934,0.0000272106,0.000009131877,0.000015881096,0.000008870944,0.0000021890648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984796,0.00036525348,0.00045266066,0.00021835558,0.00035111787,0.00013302053],"domain_scores_gemma":[0.99539953,0.003674304,0.00013768842,0.00070723926,0.0000608835,0.000020348643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018829976,0.00014035738,0.00028816098,0.000113445,0.00005088532,0.000015285048,0.00034209283,0.000030944022,0.000015578265],"category_scores_gemma":[0.0028723385,0.00007611579,0.0000050260664,0.00019410528,0.000119931996,0.00008122604,0.000053491338,0.00035650708,8.091795e-8],"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":[0.001799758,0.008450924,0.18092127,0.00059987075,0.0001264017,0.0006092605,0.19181314,0.029725587,0.00093207916,0.47478625,0.003368959,0.1068665],"study_design_scores_gemma":[0.0009394023,0.0024133392,0.047977347,0.00025429289,0.000035320383,0.0000017097753,0.01218075,0.4453784,0.0000061940955,0.49072635,0.0000024620253,0.000084430816],"about_ca_topic_score_codex":0.00006788295,"about_ca_topic_score_gemma":0.00034041292,"teacher_disagreement_score":0.4156528,"about_ca_system_score_codex":0.000030101324,"about_ca_system_score_gemma":0.000020896168,"threshold_uncertainty_score":0.3438665},"labels":[],"label_agreement":null},{"id":"W2122817910","doi":"10.1093/ije/dyp163","title":"Commentary: Gilding the black box","year":2009,"lang":"en","type":"letter","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; McGill University Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Pearl; Vintage; Field (mathematics); History; Sociology; Classics; Archaeology","score_opus":0.25191257663776434,"score_gpt":0.4847451640458476,"score_spread":0.23283258740808327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122817910","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":[0.00014559475,0.00029074674,0.06689937,0.9297521,0.0014130829,0.00013691332,0.000026587775,0.00004359895,0.00129197],"genre_scores_gemma":[0.00063631346,0.00062869815,0.06541759,0.9227956,0.010103411,0.0000049363007,0.000044066037,0.000039220216,0.00033016957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960278,0.001140948,0.0017558511,0.00021809708,0.00046581207,0.00039147414],"domain_scores_gemma":[0.98176414,0.01426949,0.0028719099,0.00037606712,0.00066575874,0.00005266139],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037631115,0.0003175351,0.0009481558,0.00029135944,0.000048680093,0.0000233477,0.0019630217,0.0005941889,0.00024745514],"category_scores_gemma":[0.010094669,0.00020070263,0.0004548445,0.000061146966,0.00035848923,0.00017005058,0.00016609688,0.0034953472,0.000017036135],"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":[0.00002521402,0.000024557095,0.00012320465,0.000009725041,0.00033928064,0.0003747584,0.000053225365,0.000016204578,0.000016970873,0.018122714,0.9770439,0.003850226],"study_design_scores_gemma":[0.00010805186,0.00009681639,0.000022270204,0.00016047171,0.000047550937,0.00041726005,0.000010253957,0.0000166628,0.000044805838,0.4701747,0.5288012,0.000099922574],"about_ca_topic_score_codex":0.000019002737,"about_ca_topic_score_gemma":0.0000040917457,"teacher_disagreement_score":0.452052,"about_ca_system_score_codex":0.00039325265,"about_ca_system_score_gemma":0.00006763835,"threshold_uncertainty_score":0.9988036},"labels":[],"label_agreement":null},{"id":"W2123190102","doi":"10.1093/ejcts/ezt455","title":"Reply to Yamamoto et al.","year":2013,"lang":"en","type":"letter","venue":"European Journal of Cardio-Thoracic Surgery","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":"Princess Margaret Cancer Centre; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Covariate; Selection bias; Medicine; Matching (statistics); Lung cancer; Surgery; Statistics; Internal medicine; Pathology; Mathematics","score_opus":0.1518692357781406,"score_gpt":0.38860158545271467,"score_spread":0.23673234967457407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123190102","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":[0.0023243118,0.0010224775,0.08360177,0.86882013,0.0035005158,0.00087339873,0.00006577805,0.0006570644,0.039134525],"genre_scores_gemma":[0.0010882101,0.00054525526,0.04987403,0.9389694,0.0050736316,0.00001985608,0.00002670093,0.0006049721,0.0037979968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.988655,0.005857765,0.002428172,0.000584061,0.0015884642,0.00088659185],"domain_scores_gemma":[0.9904529,0.0038752905,0.0024327568,0.0015401768,0.0013040996,0.00039481858],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0152467415,0.0008067478,0.0022022908,0.0011339583,0.00009065437,0.00026007966,0.0010028414,0.00021760371,0.00028560287],"category_scores_gemma":[0.006283466,0.0006950294,0.0015372029,0.00045205269,0.00011315756,0.0005740328,0.00032029286,0.004148904,0.00059771835],"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":[0.00003718875,0.00002023436,0.00003405209,0.00013880357,0.00027502712,0.009983988,0.000112630194,0.0000059020344,0.00011392745,0.000025890968,0.965498,0.023754412],"study_design_scores_gemma":[0.000053071362,0.00014296356,0.0000576978,0.0015643676,0.00016876165,0.0018488903,0.000029895737,5.6919725e-7,0.00076140265,0.0033177247,0.99133295,0.00072168175],"about_ca_topic_score_codex":0.0000048069983,"about_ca_topic_score_gemma":1.6344686e-7,"teacher_disagreement_score":0.07014919,"about_ca_system_score_codex":0.00028246528,"about_ca_system_score_gemma":0.00029843388,"threshold_uncertainty_score":0.9995501},"labels":[],"label_agreement":null},{"id":"W2126049444","doi":"10.1002/sim.3697","title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity‐score matched samples","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6487,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Matching (statistics); Quantile; Mathematics; Medicine","score_opus":0.2114497428934903,"score_gpt":0.42025483801624836,"score_spread":0.20880509512275805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126049444","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":[0.15230395,0.000098473385,0.84526396,0.00060511025,0.000038748258,0.0009897766,0.0006280991,0.00004157511,0.000030334675],"genre_scores_gemma":[0.85829943,0.00028046273,0.14047512,0.000042493666,0.00008786792,0.00006643381,0.00072704774,0.000012301409,0.000008812349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985509,0.000099370336,0.0006959968,0.00019594662,0.00020766862,0.00025012056],"domain_scores_gemma":[0.99332684,0.005925904,0.00026210438,0.00028915348,0.00015637324,0.00003959509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095518754,0.00018726294,0.00068605057,0.000064766224,0.00004160957,0.00000616034,0.00016983658,0.00006288834,0.00000838171],"category_scores_gemma":[0.006444343,0.000121877354,0.000019777766,0.00021636648,0.0001741788,0.00004066479,0.000025537585,0.0001542706,3.7994943e-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":[0.00013245367,0.00034301876,0.24192664,0.00024182738,0.000031256703,0.000019887271,0.0014274303,0.00010539878,0.0004952129,0.7422302,0.0022138017,0.0108329],"study_design_scores_gemma":[0.0013323509,0.00079296425,0.15684673,0.0005623271,0.000084649146,0.0000017250096,0.00019095623,0.0031558268,0.0018495648,0.83494973,0.00009535121,0.0001378101],"about_ca_topic_score_codex":0.0001853483,"about_ca_topic_score_gemma":0.00035487273,"teacher_disagreement_score":0.7059955,"about_ca_system_score_codex":0.00019871801,"about_ca_system_score_gemma":0.000036722482,"threshold_uncertainty_score":0.77149457},"labels":[],"label_agreement":null},{"id":"W2126497011","doi":"10.1093/aje/kwq329","title":"Invited Commentary: Decomposing with a Lot of Supposing","year":2010,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","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","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canada Research Chairs","keywords":"Medicine; Computer science; Intensive care medicine","score_opus":0.1314046313524887,"score_gpt":0.433510131570431,"score_spread":0.3021055002179423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126497011","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":[0.024579512,0.00012266145,0.19091573,0.78386664,0.00020127361,0.00019905705,0.000026081723,0.0000496917,0.00003933967],"genre_scores_gemma":[0.0034946678,0.00007356299,0.4370147,0.55860823,0.0007105651,0.000003984719,0.000021238298,0.00007058479,0.000002473733],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995193,0.0016525311,0.002020594,0.00028397117,0.00024781798,0.0006020981],"domain_scores_gemma":[0.9755033,0.016259456,0.0071042236,0.0005767206,0.0004363102,0.00011997475],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025441775,0.0004409064,0.0029038351,0.0005124187,0.00005120797,0.000006504275,0.0006844926,0.0006284623,0.00003531966],"category_scores_gemma":[0.0036219885,0.00031842437,0.0002937986,0.00027011856,0.0014204216,0.0001369953,0.00010298904,0.0062310854,6.2458116e-7],"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":[0.0001623462,0.000062426676,0.0034882552,0.00011115017,0.00038671235,0.00025924336,0.00016888975,0.000009736084,0.0012994212,0.00030452237,0.9876944,0.0060529322],"study_design_scores_gemma":[0.0009512625,0.009620432,0.0001593146,0.0025512113,0.0009705217,0.005110903,0.00032619556,0.000069319496,0.0034806193,0.3102979,0.66534483,0.0011174588],"about_ca_topic_score_codex":0.00023540317,"about_ca_topic_score_gemma":0.000039057108,"teacher_disagreement_score":0.32234952,"about_ca_system_score_codex":0.00015551072,"about_ca_system_score_gemma":0.00006197027,"threshold_uncertainty_score":0.9999268},"labels":[],"label_agreement":null},{"id":"W2126632863","doi":"10.5334/jopd.ad","title":"Data from Investigating Variation in Replicability: A “Many Labs” Replication Project","year":2014,"lang":"en","type":"article","venue":"Journal of Open Psychology Data","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Mount Saint Vincent University","funders":"","keywords":"Generalizability theory; Replication (statistics); Computer science; Variation (astronomy); Open science; Class (philosophy); Data science; Psychology; World Wide Web; Statistics; Artificial intelligence; Mathematics","score_opus":0.6351073594100903,"score_gpt":0.5925521228023779,"score_spread":0.04255523660771243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126632863","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":[0.36460048,0.000088861016,0.6174285,0.009285823,0.00038244485,0.0017471517,0.001007633,0.00012532031,0.005333799],"genre_scores_gemma":[0.16535845,0.000054955493,0.8324065,0.0011837067,0.00025916015,0.000022827584,0.00065367366,0.000035814428,0.000024881669],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970562,0.00056808896,0.001184872,0.00078539376,0.00022549015,0.00017998012],"domain_scores_gemma":[0.98928326,0.0010326583,0.0014896234,0.007969753,0.00016506916,0.000059654503],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.008997248,0.0001412711,0.0004538735,0.00015391856,0.000047428657,0.00010869103,0.005733593,0.00014934267,0.00005843069],"category_scores_gemma":[0.019628743,0.0001237202,0.00001826791,0.00031237077,0.000075233314,0.0023821692,0.002254166,0.0005466373,0.000009248767],"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":[0.00073602836,0.0024867915,0.04952545,0.00016511601,0.00037562047,0.000055694105,0.0027493453,0.000010936962,0.08802546,0.07345162,0.6567962,0.12562169],"study_design_scores_gemma":[0.0010390109,0.00021816042,0.031035736,0.00026123435,0.000063971645,0.00009370324,0.00007695537,0.0053817304,0.0002818501,0.93720216,0.024132745,0.00021275615],"about_ca_topic_score_codex":0.00014897426,"about_ca_topic_score_gemma":0.00022588349,"teacher_disagreement_score":0.8637505,"about_ca_system_score_codex":0.0000587807,"about_ca_system_score_gemma":0.00012890619,"threshold_uncertainty_score":0.9996459},"labels":[],"label_agreement":null},{"id":"W2127843972","doi":"10.3102/1076998614524823","title":"A State Space Modeling Approach to Mediation Analysis","year":2014,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Mediation; Computer science; Process (computing); Population; State space; Data science; Econometrics; Mathematics; Statistics; Sociology; Social science","score_opus":0.1615246983656391,"score_gpt":0.44512262690147375,"score_spread":0.28359792853583465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127843972","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":[0.27024907,0.000012480784,0.72922647,0.0002632409,0.000048763253,0.00005840522,0.000037586437,0.0000058938062,0.00009810682],"genre_scores_gemma":[0.509676,0.000008209725,0.49007833,0.000027357555,0.00007263616,0.000004422542,0.000013130976,0.0000065096738,0.00011341675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990017,0.00004687535,0.0004197669,0.00010448086,0.00030660804,0.00012060827],"domain_scores_gemma":[0.9986261,0.0003345402,0.00029635828,0.00009181009,0.00049520313,0.00015596866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037946226,0.000102151236,0.00025223475,0.00024570216,0.0000567986,0.000041338837,0.00009493441,0.00003330309,0.000035282043],"category_scores_gemma":[0.00044464317,0.00008502286,0.000045513865,0.00026311263,0.000025406787,0.00013805427,0.000022315911,0.00013648879,0.0000015222663],"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":[0.000100590485,0.002024011,0.032638524,0.00011506861,0.0002939318,0.000002623728,0.0036577727,0.01584639,0.001472838,0.9140487,0.008299534,0.021500027],"study_design_scores_gemma":[0.00019495556,0.00031283265,0.0059491694,0.000022219105,0.00058482005,0.000023794413,0.00022946921,0.038426578,0.00012551327,0.9536723,0.00022505719,0.00023331825],"about_ca_topic_score_codex":0.000020399928,"about_ca_topic_score_gemma":0.000021216796,"teacher_disagreement_score":0.23942691,"about_ca_system_score_codex":0.0000659276,"about_ca_system_score_gemma":0.00007618762,"threshold_uncertainty_score":0.34671316},"labels":[],"label_agreement":null},{"id":"W2127992265","doi":"10.1093/ije/dyp334","title":"Illustrating bias due to conditioning on a collider","year":2009,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":823,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism","keywords":"Collider; Conditioning; Selection bias; Outcome (game theory); Selection (genetic algorithm); Association (psychology); Confounding; Computer science; Physics; Statistics; Psychology; Mathematics; Artificial intelligence; Particle physics; Mathematical economics","score_opus":0.3891479896255752,"score_gpt":0.5215592792262753,"score_spread":0.13241128960070014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127992265","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":[0.3230953,0.00005061262,0.64105374,0.026831156,0.0009044595,0.00019169308,0.000015837299,0.00009165047,0.007765565],"genre_scores_gemma":[0.7786908,0.0000118270045,0.2121663,0.008557294,0.00046801195,0.0000032972011,0.000002752326,0.000008623457,0.00009107568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816066,0.00029077154,0.0009883657,0.00013389817,0.00022270351,0.0002035948],"domain_scores_gemma":[0.9928593,0.0054902495,0.000834112,0.000119832606,0.0005848572,0.00011164125],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022671227,0.00012350727,0.00042707688,0.00026629216,0.00003654045,0.000013467428,0.00036780463,0.00009397934,0.00016196175],"category_scores_gemma":[0.030148134,0.00010095301,0.000121774334,0.00007992604,0.000045205757,0.000154669,0.000027303378,0.0003367775,0.000019852665],"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":[0.00014992074,0.00012094025,0.0010229328,0.0000027476478,0.00009592211,0.00028846986,0.00019537559,0.0011671743,0.0023822687,0.9505446,0.024124835,0.01990483],"study_design_scores_gemma":[0.000259519,0.00079992483,0.0027072774,0.0002309211,0.000010688947,0.0008067984,0.00006541292,0.00015382784,0.0026037556,0.9889048,0.0033428345,0.00011426913],"about_ca_topic_score_codex":0.0000048131624,"about_ca_topic_score_gemma":0.0000047731755,"teacher_disagreement_score":0.45559552,"about_ca_system_score_codex":0.00017213423,"about_ca_system_score_gemma":0.000053030475,"threshold_uncertainty_score":0.9780213},"labels":[],"label_agreement":null},{"id":"W2128334938","doi":"10.1016/j.jclinepi.2009.07.006","title":"Different measures of treatment effect for different research questions","year":2009,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"","keywords":"Observational study; Scopus; Randomized controlled trial; Logistic regression; Medicine; Relative risk; Family medicine; MEDLINE; Psychology; Confidence interval; Internal medicine; Political science","score_opus":0.8291083080550481,"score_gpt":0.6756286593504679,"score_spread":0.1534796487045802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128334938","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040793538,0.0023691575,0.24905714,0.69980884,0.0030008308,0.004033292,0.00019639831,0.00017470788,0.00056606426],"genre_scores_gemma":[0.1635846,0.040927444,0.3811028,0.3225766,0.081806466,0.0017532262,0.0003642707,0.0010040567,0.0068805316],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96704865,0.021312093,0.009283586,0.00061930274,0.00070576766,0.0010305935],"domain_scores_gemma":[0.70966333,0.2821691,0.0059019052,0.00081238535,0.0012153619,0.00023792149],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.031466335,0.0006833094,0.009320046,0.0005808438,0.00009752103,0.000010926483,0.0009115305,0.0026922394,0.000043042804],"category_scores_gemma":[0.2360572,0.0003719479,0.0030514111,0.000121550656,0.00075783854,0.00006826036,0.00010451447,0.0058927154,0.0000034344982],"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":[0.00082777353,0.0008390755,0.004247937,0.0005829453,0.0009974061,0.00008023864,0.000031562147,0.0000090104095,0.00007649612,0.014082478,0.9269336,0.051291518],"study_design_scores_gemma":[0.0013743439,0.027049417,0.0021574972,0.001161631,0.0006109593,0.00006567294,0.000004297804,0.000044631284,0.0003975448,0.8214363,0.14541559,0.00028212386],"about_ca_topic_score_codex":0.00001785051,"about_ca_topic_score_gemma":0.000021366044,"teacher_disagreement_score":0.8073538,"about_ca_system_score_codex":0.00057323056,"about_ca_system_score_gemma":0.00035591738,"threshold_uncertainty_score":0.9998732},"labels":[],"label_agreement":null},{"id":"W2129095037","doi":"10.1111/j.1540-5982.2012.01733.x","title":"Comparing features of convenient estimators for binary choice models with endogenous regressors","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":226,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Heteroscedasticity; Control function; Binary number; Econometrics; M-estimator; Statistics; Function (biology); Mathematics; Computer science; Control (management); Artificial intelligence","score_opus":0.4673828165059883,"score_gpt":0.28297669831909533,"score_spread":0.18440611818689295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129095037","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":[0.9921468,0.0004231588,0.0053241067,0.00017018523,0.0004030981,0.0005469527,0.00013353155,0.000017706327,0.00083449215],"genre_scores_gemma":[0.96328676,0.000029860195,0.03614048,0.00008759934,0.00023963182,0.000044416214,0.000009107021,0.00008542544,0.00007670683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979323,0.000045882352,0.0008927592,0.00022626494,0.0000056419835,0.00089715805],"domain_scores_gemma":[0.9959039,0.00062066264,0.0012080207,0.00042246326,0.00032359984,0.0015213322],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069722795,0.0003296934,0.0009323488,0.00057524035,0.00013219805,0.00003941269,0.00051258947,0.00017129519,0.000027790067],"category_scores_gemma":[0.0003974245,0.0003359514,0.0001980203,0.0000970179,0.00022575255,0.0007681052,0.000022583274,0.00032240662,8.1235453e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013901784,0.00003965493,0.009362607,0.0002058472,0.00024213817,0.000030570936,0.0021021736,0.009321884,0.000108732114,0.9771552,0.00043431474,0.00085787673],"study_design_scores_gemma":[0.0018337496,0.0014640277,0.00078826124,0.00082156906,0.000308192,0.002053118,0.0012073263,0.0064665233,0.009291575,0.9724127,0.002301819,0.0010511497],"about_ca_topic_score_codex":0.032359537,"about_ca_topic_score_gemma":0.7047681,"teacher_disagreement_score":0.6724086,"about_ca_system_score_codex":0.0014820043,"about_ca_system_score_gemma":0.0011886439,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W2130266492","doi":"10.1002/cjs.10080","title":"Nonparametric likelihood and doubly robust estimating equations for marginal and nested structural models","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Nonparametric statistics; Statistics; Marginal likelihood; Regression analysis; Propensity score matching; Estimating equations; Restricted maximum likelihood; Econometrics; Covariate; Maximum likelihood","score_opus":0.11948689421199453,"score_gpt":0.35287077898084285,"score_spread":0.2333838847688483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130266492","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":[0.07947469,0.000044883294,0.9195597,0.00012152179,0.00019326163,0.00019004352,0.00034666143,0.000010352696,0.000058876085],"genre_scores_gemma":[0.40832052,0.0000018468925,0.59155285,0.000022293843,0.00006599101,0.0000030479562,0.000005182326,0.000014722369,0.0000135257205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900085,0.000020787298,0.00046716837,0.000110891415,0.00013269411,0.00026758347],"domain_scores_gemma":[0.99716276,0.0012880305,0.0003889208,0.0001221535,0.00056290225,0.0004752306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040660703,0.0001360628,0.00026447,0.00030658173,0.00018903172,0.00013301104,0.000121795994,0.000083069426,0.000027503658],"category_scores_gemma":[0.0033905616,0.00012504552,0.000023439963,0.00013863706,0.00014420181,0.00027977716,0.000011688936,0.0003488771,2.1903705e-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":[0.000019135094,0.000010178378,0.001402969,0.00017579655,0.000050534338,0.00006402825,0.0007840267,0.0015470162,0.00031579018,0.9502309,0.002953768,0.04244589],"study_design_scores_gemma":[0.00032202483,0.00013083615,0.00047974873,0.000040680123,0.00006326251,0.00021997231,0.000075560114,0.21601783,0.000036074805,0.7824273,0.00005458885,0.0001321102],"about_ca_topic_score_codex":0.0002833116,"about_ca_topic_score_gemma":0.008910614,"teacher_disagreement_score":0.32884583,"about_ca_system_score_codex":0.000054759428,"about_ca_system_score_gemma":0.0004945244,"threshold_uncertainty_score":0.5099209},"labels":[],"label_agreement":null},{"id":"W2130620033","doi":"10.1136/bmjopen-2013-003143","title":"A generalised model for individualising a treatment recommendation based on group-level evidence from randomised clinical trials","year":2013,"lang":"en","type":"article","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","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":"McMaster University","funders":"McMaster University","keywords":"Harm; Medicine; Relative risk; Clinical trial; Randomized controlled trial; Number needed to harm; Placebo; Number needed to treat; Confidence interval; Alternative medicine; Internal medicine; Psychology; Social psychology","score_opus":0.9068940734743981,"score_gpt":0.657280030729765,"score_spread":0.24961404274463306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130620033","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":[0.019380901,0.000004447042,0.94124824,0.0023109794,0.00010859735,0.036132235,0.0002958568,0.00016407899,0.00035464577],"genre_scores_gemma":[0.092193134,0.000017070952,0.8758663,0.0014189587,0.00021666726,0.02957169,0.00031541733,0.000060491773,0.00034026388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956794,0.00160529,0.0016715607,0.00052893074,0.00024103741,0.00027382278],"domain_scores_gemma":[0.9794251,0.018523857,0.0010178923,0.00073328026,0.0001639623,0.0001359097],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009937513,0.00029168473,0.0011703259,0.00008338371,0.0001233878,0.0003184396,0.00050640514,0.00019511688,0.0004428648],"category_scores_gemma":[0.017472787,0.00021558393,0.00031632115,0.000084493084,0.000035835554,0.00072391576,0.00013721007,0.00011860833,0.000026534617],"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":[0.053473465,0.0045106467,0.0014472479,0.0003029402,0.0011244889,0.000008741999,0.0037123577,0.0030169585,0.015810238,0.015361158,0.14241236,0.7588194],"study_design_scores_gemma":[0.028859673,0.0006644939,0.00012768673,0.00069415604,0.00020941677,3.909094e-7,0.000049450093,0.68525845,0.004287295,0.27928716,0.0001556265,0.00040621395],"about_ca_topic_score_codex":0.00040841155,"about_ca_topic_score_gemma":0.000107429325,"teacher_disagreement_score":0.7584132,"about_ca_system_score_codex":0.00021575407,"about_ca_system_score_gemma":0.00020706528,"threshold_uncertainty_score":0.9908035},"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":"W2131839274","doi":"10.1002/sim.6621","title":"Terminating observation within matched pairs of subjects in a matched cohort analysis: a Monte Carlo simulation study","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Censoring (clinical trials); Monte Carlo method; Statistics; Observational study; Cohort; Event (particle physics); Computer science; Cohort study; Econometrics; Mathematics; Physics","score_opus":0.17266836408797095,"score_gpt":0.45042957816131257,"score_spread":0.27776121407334164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131839274","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":[0.7817382,0.000016860853,0.21715459,0.000030046496,0.000047279027,0.0008316194,0.000018658635,0.000069724396,0.000093027564],"genre_scores_gemma":[0.82438165,0.0000031528064,0.1754089,0.000020231557,0.000020443731,0.00007963315,0.000022970084,0.000021902728,0.00004109502],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973416,0.00027279663,0.0012191518,0.0002886085,0.00066551,0.00021233356],"domain_scores_gemma":[0.9970763,0.001417411,0.0006120244,0.00039568174,0.0004260639,0.00007256927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030677083,0.00020336869,0.0008715231,0.0005713999,0.000017522965,0.0000072855405,0.00016355382,0.000089002366,0.000014023644],"category_scores_gemma":[0.008534191,0.00018170236,0.000021731792,0.0013504749,0.000100799734,0.00013217458,0.000051312676,0.00026463406,5.622851e-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":[0.000084941676,0.00040592282,0.92377394,0.00017803928,0.00014650254,0.00009306521,0.036558885,0.033255205,0.0002434475,0.004536859,0.00007621613,0.0006469417],"study_design_scores_gemma":[0.0021136259,0.00069821614,0.32331148,0.0004001662,0.00053121755,0.0000011066895,0.023895135,0.43066865,0.00020972939,0.21791416,7.1701055e-7,0.00025578824],"about_ca_topic_score_codex":0.001484192,"about_ca_topic_score_gemma":0.0050587296,"teacher_disagreement_score":0.6004625,"about_ca_system_score_codex":0.00026955767,"about_ca_system_score_gemma":0.00007621897,"threshold_uncertainty_score":0.9998174},"labels":[],"label_agreement":null},{"id":"W2131931738","doi":"10.1016/j.clinthera.2006.09.021","title":"Toward a standard definition and measurement of persistence with drug therapy: Examples from research on statin and antihypertensive utilization","year":2006,"lang":"en","type":"review","venue":"Clinical Therapeutics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"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 British Columbia","funders":"","keywords":"Persistence (discontinuity); Medicine; Medical prescription; Terminology; MEDLINE; Ranking (information retrieval); Intensive care medicine; Pharmacology; Information retrieval; Computer science","score_opus":0.9320255751568463,"score_gpt":0.5942286578077858,"score_spread":0.3377969173490605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131931738","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":[0.0010949979,0.9831338,0.013484124,0.000066265675,0.00004452115,0.0015268578,0.00028554245,0.0001009345,0.00026295075],"genre_scores_gemma":[0.0016670134,0.96221906,0.03576398,0.00007736729,0.00005946412,0.000067121255,0.00005520157,0.00007950234,0.000011272196],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99577975,0.0012131281,0.0011138794,0.0006353129,0.00097093673,0.00028700044],"domain_scores_gemma":[0.99173105,0.0058638765,0.00068167236,0.0005418019,0.0010972068,0.00008439696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002683847,0.00040978676,0.0017479501,0.00016014128,0.000103843086,0.000056592613,0.00021372936,0.00035438832,0.000008217701],"category_scores_gemma":[0.0005977614,0.00027503815,0.00015207683,0.00026764712,0.0008247433,0.00007065561,0.00008349863,0.0007766195,0.000001018718],"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":[0.00020445616,0.0002276804,0.00005229759,0.0020457942,0.0003065183,0.000007051502,0.00025854568,1.416237e-7,0.0000033030205,0.0071070236,0.0001355638,0.9896516],"study_design_scores_gemma":[0.0019392448,0.00499556,0.00012952376,0.034298494,0.0016396386,0.000016796846,0.0013355021,0.000037405734,0.00025741008,0.3115118,0.6426866,0.0011519816],"about_ca_topic_score_codex":0.000024897712,"about_ca_topic_score_gemma":0.000024040019,"teacher_disagreement_score":0.98849964,"about_ca_system_score_codex":0.000113042675,"about_ca_system_score_gemma":0.00029214527,"threshold_uncertainty_score":0.9999702},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2132557528","doi":"10.3386/w13039","title":"Regression Discontinuity Designs: A Guide to Practice","year":2007,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":888,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Regression discontinuity design; Discontinuity (linguistics); Regression; Computer science; Econometrics; Statistics; Mathematics","score_opus":0.7507059545647676,"score_gpt":0.6941272470872978,"score_spread":0.05657870747746985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132557528","genre_codex":"other","genre_gemma":"methods","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":[0.00016632778,0.00028338368,0.0121603375,0.0010943569,0.00036064614,0.0016423714,0.000094427756,0.00012025316,0.9840779],"genre_scores_gemma":[0.036975604,0.0029134667,0.78515047,0.00023168279,0.0035132233,0.0010095339,0.0004886449,0.00038924048,0.16932815],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99368113,0.0004024412,0.0014357544,0.00073542754,0.003119947,0.0006252917],"domain_scores_gemma":[0.9806991,0.010719654,0.00088492676,0.0007478274,0.0067256093,0.00022286379],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024456067,0.00033374576,0.0007965141,0.0013478933,0.00013146429,0.00007266113,0.0008627385,0.00062574394,0.00044127015],"category_scores_gemma":[0.06483965,0.00030311834,0.0001837189,0.0003301679,0.00023343088,0.00044126564,0.000522326,0.0013033756,0.00016904538],"study_design_candidate":"theoretical_or_conceptual","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":[0.00011888494,0.00013294052,0.000029478328,0.00018646428,0.00009513156,0.000016318587,0.000077487915,0.000010696076,0.00044519774,0.41083628,0.58226085,0.005790293],"study_design_scores_gemma":[0.00013731509,0.00016241883,0.000014936644,0.0006222129,0.000020273936,0.00004268993,0.00010343874,0.000016069696,0.0045388555,0.7317032,0.26238438,0.00025418738],"about_ca_topic_score_codex":0.00087603956,"about_ca_topic_score_gemma":0.0003015001,"teacher_disagreement_score":0.8147497,"about_ca_system_score_codex":0.0049970094,"about_ca_system_score_gemma":0.0047881203,"threshold_uncertainty_score":0.99994206},"labels":[],"label_agreement":null},{"id":"W2133519275","doi":"10.1002/sim.5599","title":"An information criterion for marginal structural models","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Center for Research Resources; National Institute of Child Health and Human Development; National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Institute on Aging","keywords":"Marginal structural model; Marginal model; Econometrics; Specification; Inference; Computer science; Metric (unit); Observational study; Parametric statistics; Causal inference; Regression; Semiparametric regression; Marginal likelihood; Regression analysis; Statistics; Mathematics; Machine learning; Bayesian probability; Artificial intelligence; Economics","score_opus":0.1399503500513534,"score_gpt":0.47609368767591403,"score_spread":0.3361433376245606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133519275","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":[0.01124641,0.00002651156,0.98716384,0.0000818087,0.00019969065,0.00036551568,0.0001519375,0.000088515015,0.0006757653],"genre_scores_gemma":[0.43115345,0.000010516183,0.5683576,0.00012253693,0.00012744498,0.00004251565,0.00016231349,0.000009675886,0.000013942394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990676,0.000031441377,0.0003650694,0.00007241829,0.00019957038,0.00026390812],"domain_scores_gemma":[0.99908966,0.0003745916,0.000121224446,0.00018964817,0.0001395521,0.00008531319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005204866,0.00011687951,0.00020393963,0.00012329537,0.000040760922,0.000009172353,0.00010711068,0.000058192338,0.00008812748],"category_scores_gemma":[0.00081377936,0.00009554342,0.00000862482,0.00007709009,0.0000833715,0.0009795795,0.000015415979,0.00012397201,0.0000018535076],"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":[0.00003529623,0.000014310609,0.00026774246,0.00013400652,0.0000030475221,5.555923e-7,0.0024134615,0.000021472257,0.0002884211,0.9792293,0.0031756111,0.014416814],"study_design_scores_gemma":[0.0004200889,0.00023177826,0.00064461015,0.000065985456,0.000016036516,0.000006160265,0.00043538056,0.03468682,0.00022139629,0.96269304,0.00046374113,0.00011494656],"about_ca_topic_score_codex":0.000022406664,"about_ca_topic_score_gemma":0.000013531598,"teacher_disagreement_score":0.41990703,"about_ca_system_score_codex":0.00008191967,"about_ca_system_score_gemma":0.000015367197,"threshold_uncertainty_score":0.3896148},"labels":[],"label_agreement":null},{"id":"W2133554893","doi":"10.1111/j.1467-985x.2012.01032.x","title":"Experimental Designs for Identifying Causal Mechanisms","year":2012,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":407,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Causality (physics); Imperfect; Causation; Computer science; Causal model; Causal inference; Process (computing); Criticism; Key (lock); Natural (archaeology); Black box; Data science; Cognitive psychology; Psychology; Management science; Artificial intelligence; Epistemology; Econometrics; Engineering; Mathematics; Computer security","score_opus":0.1689160987547828,"score_gpt":0.425026705623513,"score_spread":0.2561106068687302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133554893","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":[0.0025490401,0.00026464887,0.9952503,0.00015924014,0.0007716513,0.0004961493,0.00037649495,0.00004581081,0.000086662054],"genre_scores_gemma":[0.17408706,0.00003849527,0.8248705,0.0002512932,0.00027779248,0.000051085997,0.000007020929,0.00006517523,0.00035151996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99703664,0.0001677057,0.0010832391,0.00020523126,0.00073288794,0.0007742786],"domain_scores_gemma":[0.9959007,0.0025407034,0.00074614165,0.00027151007,0.00030595736,0.00023499473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016243521,0.00034215007,0.0006187377,0.000022603988,0.00035373334,0.00009851739,0.0005149151,0.00023389862,0.00016263104],"category_scores_gemma":[0.0014840043,0.0002589815,0.00050490804,0.00021554575,0.00043401564,0.00037649047,0.00023097661,0.0007144209,0.0000021911344],"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":[0.0000866391,0.00039740565,0.00023719108,0.00022525173,0.00018221358,0.0000057566576,0.0038144733,0.000052773416,0.003902301,0.9099831,0.0806622,0.00045071752],"study_design_scores_gemma":[0.00091923523,0.00040949174,0.00042653087,0.00015730025,0.00019703951,0.000047618247,0.0062168404,0.0023981547,0.016848383,0.9703245,0.0016269893,0.0004279215],"about_ca_topic_score_codex":0.000011554005,"about_ca_topic_score_gemma":0.000007733289,"teacher_disagreement_score":0.17153803,"about_ca_system_score_codex":0.0006703763,"about_ca_system_score_gemma":0.00014325317,"threshold_uncertainty_score":0.99998623},"labels":[],"label_agreement":null},{"id":"W2133940194","doi":"10.1177/1740774512440636","title":"Temporal compliance trends in a cluster randomization with crossover trial of out-of-hospital cardiac arrest","year":2012,"lang":"en","type":"article","venue":"Clinical Trials","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":"University of Toronto; Ottawa Public Health; St. Michael's Hospital; Ottawa Hospital; University of Ottawa","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Crossover study; Medicine; Cardiopulmonary resuscitation; Randomized controlled trial; Randomization; Logistic regression; Emergency medicine; Cluster randomised controlled trial; Resuscitation; Data monitoring committee; Cluster (spacecraft); Internal medicine; Placebo","score_opus":0.5222422213995487,"score_gpt":0.56778038428529,"score_spread":0.04553816288574131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133940194","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":[0.9153984,0.00018367292,0.0673595,0.00025545058,0.008742505,0.0043607997,0.00014233857,0.00019241146,0.0033649306],"genre_scores_gemma":[0.97015685,0.00003594127,0.0285292,0.000020559024,0.00095367065,0.000109669694,0.000018242346,0.000031291973,0.00014456984],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947849,0.0016046839,0.0027954886,0.00024020553,0.00030211583,0.00027258616],"domain_scores_gemma":[0.98848724,0.00910611,0.0016880392,0.00046857313,0.00014829349,0.00010173239],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012094296,0.00019525707,0.0021494676,0.00009653472,0.000017898154,0.000012485227,0.00017995098,0.00025565425,0.000063439824],"category_scores_gemma":[0.013561362,0.00013815534,0.00043819717,0.000240508,0.0002989263,0.00026613407,0.000063221334,0.00025212517,0.0000052168384],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7247234,0.013449181,0.10471962,0.000587865,0.0011261143,0.000007546448,0.0030666098,0.00007189175,0.00043803593,0.04787701,0.014756162,0.08917654],"study_design_scores_gemma":[0.82917696,0.008917688,0.0056307893,0.001736425,0.0010070334,7.231768e-7,0.00027305604,0.00023823138,0.0075698053,0.13796422,0.0058873487,0.0015977403],"about_ca_topic_score_codex":0.000007875744,"about_ca_topic_score_gemma":0.000008445693,"teacher_disagreement_score":0.10445353,"about_ca_system_score_codex":0.000028422193,"about_ca_system_score_gemma":0.000050414947,"threshold_uncertainty_score":0.9947478},"labels":[],"label_agreement":null},{"id":"W2134369111","doi":"","title":"The Effects of Cancer on Employment and Earnings of Cancer Survivors","year":2014,"lang":"en","type":"article","venue":"Analytical Studies Branch Research Paper Series","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"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":"Microdata (statistics); Earnings; Demography; Cancer registry; Wage; Cancer; Matching (statistics); Medicine; Propensity score matching; Causal inference; Econometrics; Actuarial science; Demographic economics; Economics; Census; Environmental health; Labour economics; Surgery; Population; Accounting; Internal medicine; Sociology","score_opus":0.15941032812625305,"score_gpt":0.503943175039,"score_spread":0.34453284691274694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134369111","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":[0.98391515,0.0100697,0.00019274373,0.0032466154,0.000101050464,0.0006846337,0.000006685237,0.00007207429,0.0017113272],"genre_scores_gemma":[0.96756214,0.030247003,0.00027392007,0.00006264259,0.00006270743,0.00034633192,2.8283438e-7,0.000025851376,0.0014191159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977583,0.00036189498,0.00037241165,0.0002737355,0.00076611113,0.00046749227],"domain_scores_gemma":[0.989511,0.009299255,0.000117798125,0.00036579484,0.0006223435,0.00008379722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013105187,0.00017948556,0.0005247413,0.00007661666,0.00031521963,0.00002036602,0.00024060952,0.00006518265,0.000027753016],"category_scores_gemma":[0.00762553,0.00010596289,0.00006818622,0.00033880584,0.0017765815,0.00011628429,0.00032055393,0.00035003806,0.0000014467482],"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":[0.0007025341,0.00031081156,0.09830317,0.0038955533,0.0019972874,0.0000062794948,0.0051894262,0.000015422926,0.012325937,0.7370126,0.0040669786,0.13617395],"study_design_scores_gemma":[0.0011890243,0.0051360745,0.15648413,0.0028773434,0.0002909767,0.0000013050785,0.0031486298,0.00015445134,0.14794788,0.6180268,0.06401241,0.00073098624],"about_ca_topic_score_codex":0.001066361,"about_ca_topic_score_gemma":0.009450192,"teacher_disagreement_score":0.13562194,"about_ca_system_score_codex":0.00007249274,"about_ca_system_score_gemma":0.00003460048,"threshold_uncertainty_score":0.91290224},"labels":[],"label_agreement":null},{"id":"W2134429012","doi":"10.1111/j.1467-9876.2012.01041.x","title":"Estimating the Optimal Dynamic Antipsychotic Treatment Regime: Evidence from the Sequential Multiple-Assignment Randomized Clinical Antipsychotic Trials of Intervention and Effectiveness Schizophrenia Study","year":2012,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":44,"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 on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Antipsychotic; Schizophrenia (object-oriented programming); Perphenazine; Randomized controlled trial; Psychiatry; Intervention (counseling); Marginal structural model; Clinical trial; Psychology; Medicine; Confidence interval; Internal medicine","score_opus":0.14126718593338197,"score_gpt":0.45643209670626445,"score_spread":0.31516491077288245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134429012","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":[0.28938615,0.00034762928,0.7070256,0.00013906731,0.0006859813,0.0020701438,0.0003183042,0.000023359114,0.0000037860882],"genre_scores_gemma":[0.6835493,0.00011573739,0.31597888,0.000018479219,0.00019756211,0.00008773671,0.000006642421,0.000033552038,0.000012076941],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98934174,0.005879841,0.0031025275,0.00034228514,0.000887229,0.00044637226],"domain_scores_gemma":[0.93188536,0.06403825,0.0030859746,0.0005704191,0.00025390415,0.000166097],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017679714,0.00046653472,0.002083899,0.000024795281,0.00046152459,0.00014494319,0.00062008,0.00015497718,0.000073543364],"category_scores_gemma":[0.016491925,0.00021594299,0.00070298865,0.000156263,0.0014493496,0.00020594853,0.00023522456,0.00077211316,0.0000017487506],"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":[0.443585,0.01794188,0.043938294,0.0020513851,0.027388038,0.0000711236,0.03487969,0.0102113215,0.0049518906,0.21107563,0.008398162,0.19550757],"study_design_scores_gemma":[0.14791664,0.0055732275,0.14071405,0.0033571268,0.015406907,0.00009742764,0.008544514,0.13195811,0.001532866,0.543482,0.00005198511,0.0013651162],"about_ca_topic_score_codex":0.000093414536,"about_ca_topic_score_gemma":0.000028348517,"teacher_disagreement_score":0.39416316,"about_ca_system_score_codex":0.0002561582,"about_ca_system_score_gemma":0.000109826746,"threshold_uncertainty_score":0.99179256},"labels":[],"label_agreement":null},{"id":"W2134608496","doi":"10.1093/aje/kwp175","title":"Time-modified Confounding","year":2009,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"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 Institutes of Health; Thrasher Research Fund; National Institute on Alcohol Abuse and Alcoholism; National Institute of Allergy and Infectious Diseases; American Chemistry Council; World Health Organization","keywords":"Confounding; Marginal structural model; Statistics; Econometrics; Medicine; Mathematics","score_opus":0.180643880859676,"score_gpt":0.4805533217382027,"score_spread":0.29990944087852667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134608496","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":[0.3019935,0.00020283721,0.683233,0.0055406885,0.00016707355,0.00013249519,0.000002017475,0.00014450679,0.008583858],"genre_scores_gemma":[0.7335843,0.0000852938,0.2635842,0.0024429387,0.00017981656,0.0000010470634,6.0787625e-7,0.000011821971,0.000109991764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776316,0.0006508684,0.0009993803,0.00013217778,0.00009873468,0.00035571092],"domain_scores_gemma":[0.9914951,0.006316349,0.001625349,0.00023787448,0.00017607104,0.0001492709],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033149743,0.00014784106,0.0009965168,0.00016166069,0.000039428967,0.0000035731123,0.0002964779,0.000060022783,0.00008586083],"category_scores_gemma":[0.013406855,0.00011365914,0.00015900213,0.00016904157,0.0004424092,0.00013097675,0.000019804911,0.00038280632,0.00001684585],"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":[0.00022902607,0.00014374565,0.0012222347,0.000007691316,0.00011637986,0.00007690315,0.00033514644,0.00016594236,0.007693953,0.79278743,0.017157843,0.18006368],"study_design_scores_gemma":[0.00017766989,0.0020045792,0.00057623466,0.0000554352,0.0000334777,0.00041776904,0.000114023685,0.00021701258,0.00042456467,0.9934408,0.0023922483,0.0001461556],"about_ca_topic_score_codex":0.0000059834647,"about_ca_topic_score_gemma":4.768469e-7,"teacher_disagreement_score":0.4315908,"about_ca_system_score_codex":0.00009092022,"about_ca_system_score_gemma":0.000052738043,"threshold_uncertainty_score":0.9949036},"labels":[],"label_agreement":null},{"id":"W2134743308","doi":"10.1146/annurev-statistics-010814-020403","title":"Using Longitudinal Complex Survey Data","year":2015,"lang":"en","type":"article","venue":"Annual Review of Statistics and Its Application","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Attrition; Dropout (neural networks); Computer science; Sample (material); Inference; Longitudinal data; Causal inference; Sampling (signal processing); Longitudinal study; Econometrics; Survey data collection; Sampling design; Statistics; Data science; Data mining; Artificial intelligence; Machine learning; Mathematics; Medicine","score_opus":0.6067950786125046,"score_gpt":0.5342187549497273,"score_spread":0.07257632366277733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134743308","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":[0.00062463916,0.0064720744,0.98812616,0.000042981163,0.00001071745,0.00049985887,0.0039060847,0.000029006816,0.00028845563],"genre_scores_gemma":[0.207552,0.034079503,0.7556811,0.00021215041,0.00004995231,0.00003266175,0.0023287833,0.00003336722,0.00003046049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991086,0.00006208651,0.00035877555,0.00019323752,0.00018577749,0.00009151922],"domain_scores_gemma":[0.9983192,0.00026553465,0.00028679546,0.0004160802,0.0006454921,0.00006686463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010684837,0.0000923073,0.00027099205,0.000019865583,0.000026034464,0.0000066540297,0.0002021891,0.000026613126,0.000011196425],"category_scores_gemma":[0.0015522427,0.00008099422,0.000007150118,0.00011788311,0.000044631994,0.00014925825,0.00016006212,0.000054492946,0.0000038368935],"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":[0.000015377194,0.00013909373,0.0009770609,0.0069058416,0.00003138252,0.0000013015633,0.00012755451,9.26967e-7,0.00047418065,0.8619322,0.051806804,0.077588275],"study_design_scores_gemma":[0.00059823977,0.0004162787,0.012946619,0.0049782256,0.00042591683,0.000046178928,0.00019690277,0.041161887,0.0006440548,0.8751754,0.0624594,0.00095087645],"about_ca_topic_score_codex":0.00007802009,"about_ca_topic_score_gemma":0.000024261837,"teacher_disagreement_score":0.23244506,"about_ca_system_score_codex":0.000017630156,"about_ca_system_score_gemma":0.000044473687,"threshold_uncertainty_score":0.33028483},"labels":[],"label_agreement":null},{"id":"W2135189416","doi":"10.1093/biostatistics/kxg041","title":"Analysis of longitudinal marginal structural models","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"","keywords":"Estimator; Censoring (clinical trials); Inverse probability; Marginal structural model; Confounding; Statistics; Econometrics; Mathematics; Computer science","score_opus":0.15749982260053155,"score_gpt":0.4178060521425315,"score_spread":0.260306229542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135189416","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":[0.12177934,0.000025267354,0.8768933,0.000029404015,0.00003493088,0.000105963736,0.00035237978,0.000105160216,0.00067425874],"genre_scores_gemma":[0.6052962,0.000008639602,0.39461133,0.000010090134,0.00001044963,0.0000032067676,0.000028134871,0.000009938022,0.000022006981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900246,0.000018182758,0.00034955036,0.00018181035,0.00025140084,0.00019658598],"domain_scores_gemma":[0.99903154,0.00020944414,0.0002009848,0.00031404968,0.00018423819,0.000059731137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010278928,0.0001453607,0.00035979907,0.00022473851,0.00004083445,0.000013010552,0.00016131932,0.000064451975,0.00009019829],"category_scores_gemma":[0.00023859993,0.00013177094,0.00008715982,0.00053193077,0.00013042313,0.00011021927,0.000049625785,0.00009758246,0.0000024013082],"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":[0.000015838139,0.000030635303,0.0016163848,0.0000389739,0.00026807832,0.000015779098,0.00016410052,0.002741324,0.0003888974,0.99377096,0.00008819301,0.0008608267],"study_design_scores_gemma":[0.00017485602,0.000084952815,0.005529739,0.000021477746,0.00067715766,0.0000050506424,0.000044078635,0.008599961,0.003125367,0.98156255,0.000008937463,0.0001658609],"about_ca_topic_score_codex":0.00006711926,"about_ca_topic_score_gemma":0.000084062856,"teacher_disagreement_score":0.48351687,"about_ca_system_score_codex":0.00008435136,"about_ca_system_score_gemma":0.000048389073,"threshold_uncertainty_score":0.5373463},"labels":[],"label_agreement":null},{"id":"W2136204757","doi":"10.2202/1557-4679.1349","title":"Double-Robust Estimators: Slightly More Bayesian than Meets the Eye?","year":2012,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Confounding; Bayesian probability; Outcome (game theory); Parametric statistics; Econometrics; Statistics; Mathematics; Nonparametric statistics; Parametric model; Mathematical economics","score_opus":0.12095443698415621,"score_gpt":0.4227510600308651,"score_spread":0.3017966230467089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136204757","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":[0.035292316,0.0003624504,0.9426986,0.016740875,0.0020861914,0.00032567367,0.00011798587,0.00009560142,0.0022803184],"genre_scores_gemma":[0.8227566,0.000084830324,0.17550068,0.00047703212,0.0008587123,0.000006246394,0.0000052651176,0.000034229495,0.000276406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99800545,0.000079584075,0.0006440226,0.00008547159,0.00091162696,0.00027384024],"domain_scores_gemma":[0.99695975,0.0011592609,0.0008098921,0.00030086513,0.00065803545,0.00011222109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010999839,0.00019317973,0.00022639545,0.000106989784,0.00012378403,0.000109374494,0.0012312963,0.0000666814,0.00010609588],"category_scores_gemma":[0.0008349755,0.0001016303,0.000111705645,0.00011183863,0.0002273123,0.00032813282,0.00016173336,0.00041671473,0.00001653778],"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":[0.00024415358,0.00024808256,0.0027585414,0.000021310441,0.00043505715,0.000068271314,0.0024738298,0.000118358,0.0015590081,0.9562929,0.032103524,0.003676962],"study_design_scores_gemma":[0.0019201253,0.00032082587,0.006195929,0.00058445864,0.00048908696,0.0017808834,0.0021280635,0.0026844512,0.037547342,0.9117492,0.033873744,0.0007259303],"about_ca_topic_score_codex":0.000017973836,"about_ca_topic_score_gemma":0.0000107710175,"teacher_disagreement_score":0.7874643,"about_ca_system_score_codex":0.00015170805,"about_ca_system_score_gemma":0.00008340324,"threshold_uncertainty_score":0.41443634},"labels":[],"label_agreement":null},{"id":"W213628847","doi":"10.1016/j.cjca.2015.05.015","title":"A Review of Propensity-Score Methods and Their Use in Cardiovascular Research","year":2015,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":283,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Observational study; Medicine; Covariate; Matching (statistics); Weighting; Inverse probability weighting; Selection bias; Strengths and weaknesses; Randomized controlled trial; Econometrics; Statistics; Internal medicine; Mathematics; Pathology; Psychology","score_opus":0.7264268470364439,"score_gpt":0.5542337611935539,"score_spread":0.17219308584288995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W213628847","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":[0.0000053231474,0.9921182,0.0059546097,0.000019168885,0.00012643747,0.0009759709,0.00004019627,0.000005775548,0.0007543215],"genre_scores_gemma":[0.000011256515,0.9832873,0.0163563,0.000023307217,0.00020777798,0.0000353739,0.000004855642,0.000054707492,0.000019150868],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991142,0.006465213,0.0013829434,0.00028693536,0.00022829215,0.0004946234],"domain_scores_gemma":[0.994501,0.0018153818,0.0006681123,0.00085143925,0.0016483635,0.0005157312],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019920334,0.00034416755,0.006668453,0.0011495576,0.000036290105,0.000019475368,0.00058988493,0.00048637844,0.000004782195],"category_scores_gemma":[0.010434722,0.00023433515,0.0009770304,0.0006325386,0.0005079892,0.00014315492,0.00010777508,0.0017252398,0.000001011472],"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":[0.0000030762067,0.0000015982832,0.000027703838,0.05079683,0.0007684844,0.00025254104,0.00007678917,0.0000012936845,3.9734908e-7,0.0013919099,0.009042874,0.9376365],"study_design_scores_gemma":[0.000074756834,0.00012806393,0.0000031517939,0.08807229,0.0004820773,0.0019062379,0.000022521619,9.554681e-8,0.0000018854893,0.017070608,0.89206797,0.00017033164],"about_ca_topic_score_codex":0.00062377,"about_ca_topic_score_gemma":0.0007958684,"teacher_disagreement_score":0.93746614,"about_ca_system_score_codex":0.00055641436,"about_ca_system_score_gemma":0.004816043,"threshold_uncertainty_score":0.9979008},"labels":[],"label_agreement":null},{"id":"W2138153404","doi":"10.1016/j.jclinepi.2007.07.011","title":"The performance of different propensity-score methods for estimating relative risks","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":215,"is_retracted":false,"has_abstract":false,"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","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Statistics; Confounding; Relative risk; Matching (statistics); Mathematics; Medicine; Confidence interval","score_opus":0.8314351686646472,"score_gpt":0.6606402731520815,"score_spread":0.17079489551256566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138153404","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":[0.41355836,0.00010844655,0.58501095,0.000658271,0.0003420793,0.0002237973,9.3943703e-7,0.000014498312,0.000082658386],"genre_scores_gemma":[0.2533274,0.00066456466,0.74550724,0.00014541493,0.00026386848,0.000012870843,3.2723403e-7,0.000014687785,0.00006363025],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898684,0.0043304046,0.0051489384,0.00018377429,0.00013994814,0.00032852273],"domain_scores_gemma":[0.8111851,0.18169259,0.006075667,0.00031072152,0.0006205956,0.00011529553],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03216964,0.00017432487,0.0023672255,0.000051118364,0.00018868923,0.0000023445284,0.00042466284,0.00027149124,0.0000066882535],"category_scores_gemma":[0.29589948,0.0000884677,0.0005987726,0.00007370536,0.0007461387,0.00015733339,0.00011003713,0.0011424456,7.551884e-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":[0.0018542001,0.0005583025,0.42422754,0.00032541776,0.0006406676,0.000011772265,0.00041910732,0.0005040511,0.0004136163,0.25846744,0.0038023947,0.30877548],"study_design_scores_gemma":[0.00063223846,0.002914534,0.05012852,0.00027056865,0.00011034568,0.00015837023,0.00001823148,0.026176676,0.0014317712,0.9174725,0.0005556011,0.00013064101],"about_ca_topic_score_codex":0.0000020660837,"about_ca_topic_score_gemma":0.000001481912,"teacher_disagreement_score":0.65900505,"about_ca_system_score_codex":0.000036786445,"about_ca_system_score_gemma":0.00012388015,"threshold_uncertainty_score":0.996585},"labels":[],"label_agreement":null},{"id":"W2138898032","doi":"10.1067/mhj.2000.106610","title":"Subgroups, treatment effects, and baseline risks: Some lessons from major cardiovascular trials","year":2000,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":false,"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":"Medicine; Subgroup analysis; Randomized controlled trial; Pharmacotherapy; Clinical trial; Myocardial infarction; Internal medicine; Angina; Randomization; Heart failure; Cardiology; Meta-analysis","score_opus":0.2342638152514535,"score_gpt":0.45158630911453546,"score_spread":0.21732249386308194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138898032","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":[0.96377313,0.007541275,0.026005976,0.0013929697,0.0001168823,0.00065719115,0.000089599365,0.00028344308,0.00013952947],"genre_scores_gemma":[0.81243443,0.014239394,0.17098606,0.00059586024,0.0013261648,0.000104456936,0.000012287674,0.00009657396,0.0002047506],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969786,0.0012846274,0.00064259337,0.0003280694,0.00036016232,0.00040595676],"domain_scores_gemma":[0.9960114,0.0029068943,0.00023778087,0.0004919391,0.000057781213,0.00029420012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018372615,0.00031234283,0.0014979484,0.00010568211,0.00021568201,0.00008970395,0.00012892167,0.00006704144,0.00043106967],"category_scores_gemma":[0.0008910622,0.00023292839,0.0005508343,0.00015618087,0.00022343681,0.00024617417,0.000025760506,0.00032372883,0.00003918177],"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":[0.00020750625,0.00037337354,0.0021900362,0.000029084591,0.0018201141,0.00026090906,0.00043773378,0.00003609212,0.0039502573,0.0013658608,0.004221355,0.98510766],"study_design_scores_gemma":[0.008877627,0.0066339727,0.017537175,0.00091392035,0.005739992,0.002588237,0.0009463012,0.00063926884,0.06354404,0.62300414,0.26692635,0.0026489554],"about_ca_topic_score_codex":0.001299624,"about_ca_topic_score_gemma":0.000022471264,"teacher_disagreement_score":0.9824587,"about_ca_system_score_codex":0.00017839952,"about_ca_system_score_gemma":0.00007156444,"threshold_uncertainty_score":0.94985443},"labels":[],"label_agreement":null},{"id":"W2138916823","doi":"10.1093/biostatistics/kxs024","title":"Targeted maximum likelihood estimation for marginal time-dependent treatment effects under density misspecification","year":2012,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Estimator; Statistics; Generalized estimating equation; Mathematics; Econometrics; Delta method; Parametric statistics; Confounding; Random effects model; Variance (accounting); Computer science; Medicine; Meta-analysis","score_opus":0.08074750171030778,"score_gpt":0.3757055195828782,"score_spread":0.29495801787257037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138916823","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":[0.010366244,0.000089693116,0.9873368,0.000111751,0.00018420535,0.0011656233,0.00017456572,0.00035467502,0.00021642196],"genre_scores_gemma":[0.35529116,0.000020656425,0.64384556,0.00004524639,0.000114248694,0.00015222638,0.00023437921,0.000044066303,0.00025245355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987628,0.00007339808,0.00030641668,0.00022497038,0.00021579872,0.000416625],"domain_scores_gemma":[0.99804837,0.0010761986,0.00021480149,0.00033977974,0.00016994955,0.00015090186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025808287,0.00024759703,0.00026655043,0.00007567987,0.00012505816,0.000033314507,0.00009523938,0.00012566401,0.000059839414],"category_scores_gemma":[0.0006104006,0.00022576582,0.000054914814,0.00008503012,0.000046501795,0.00016035917,0.000025869966,0.000070381844,0.00012607107],"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":[0.00037018987,0.0025555447,0.0011088533,0.00082286174,0.00030509316,0.000014581096,0.0012148406,0.00005080237,0.095572725,0.66402406,0.024154523,0.20980595],"study_design_scores_gemma":[0.0008218311,0.00051891065,0.0026177731,0.000051933326,0.00023692522,0.000015975753,0.000050192317,0.004841069,0.18111208,0.8083027,0.0010101544,0.00042043033],"about_ca_topic_score_codex":0.000009375449,"about_ca_topic_score_gemma":0.0000058741916,"teacher_disagreement_score":0.3449249,"about_ca_system_score_codex":0.00044259452,"about_ca_system_score_gemma":0.000045412256,"threshold_uncertainty_score":0.9206463},"labels":[],"label_agreement":null},{"id":"W2139138216","doi":"","title":"Relaxing monotonicity in the identification of local average treatment effects","year":2012,"lang":"en","type":"preprint","venue":"Alexandria (UniSG) (University of St.Gallen)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"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":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Monotonic function; Identification (biology); Endogeneity; Instrumental variable; Econometrics; Independence (probability theory); Average treatment effect; Mathematical economics; Mathematics; Quarter (Canadian coin); Economics; Statistics; Estimator; Mathematical analysis; Geography","score_opus":0.07965942016178558,"score_gpt":0.3226038725276926,"score_spread":0.24294445236590706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139138216","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":[0.6381052,0.00041068054,0.3561497,0.0002742538,0.00018816449,0.0018475126,0.00012811593,0.00014991999,0.002746434],"genre_scores_gemma":[0.9848719,0.0009076196,0.013655121,0.000009195569,0.000029392098,0.0000121151015,0.00008533098,0.000030676896,0.0003986283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978373,0.00039311638,0.0004880005,0.00047794366,0.00045927687,0.0003443518],"domain_scores_gemma":[0.9966184,0.0009139054,0.0010391183,0.0011856711,0.00016759733,0.00007531688],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090752885,0.00037628037,0.0008048447,0.00031071488,0.00014104323,0.000016988128,0.000926691,0.0004889988,0.00012434283],"category_scores_gemma":[0.000099859324,0.00037088565,0.00029559404,0.00023998493,0.00034311318,0.000380111,0.0005430288,0.0005925372,0.000011847132],"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":[0.0011982678,0.0075920764,0.0038896853,0.008798214,0.0022942915,0.0004125963,0.109442905,0.0035456894,0.024736475,0.75764066,0.0024782838,0.07797085],"study_design_scores_gemma":[0.00700897,0.0015573902,0.043333765,0.004126244,0.0023286634,0.000051025414,0.02632534,0.011808878,0.037297044,0.8602815,0.0030097838,0.0028713602],"about_ca_topic_score_codex":0.0009921753,"about_ca_topic_score_gemma":0.0009797841,"teacher_disagreement_score":0.3467667,"about_ca_system_score_codex":0.0004686005,"about_ca_system_score_gemma":0.00012928662,"threshold_uncertainty_score":0.9998743},"labels":[],"label_agreement":null},{"id":"W2139491581","doi":"10.1080/00273171.2012.640600","title":"Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":52,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; U.S. Public Health Service; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Inverse probability weighting; Statistics; Observational study; Logistic regression; Random forest; Regression; Confounding; Causal inference; Regression analysis; Inverse probability; Econometrics; Mathematics; Computer science; Machine learning; Bayesian probability","score_opus":0.6865806864982038,"score_gpt":0.6435797549976086,"score_spread":0.04300093150059525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139491581","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":[0.4365646,0.000010132011,0.56209415,0.000011543753,0.000079761965,0.0010617627,0.000009028272,0.00015871187,0.000010328649],"genre_scores_gemma":[0.48216012,7.807107e-8,0.51746637,0.00000551157,0.000054285323,0.00022565969,0.000034909528,0.0000489459,0.000004119105],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99560165,0.002031002,0.0006117257,0.00037785125,0.00059922616,0.0007785496],"domain_scores_gemma":[0.9920454,0.006026205,0.00032610234,0.0004153747,0.0009198311,0.00026708117],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006740844,0.0002669632,0.00045568895,0.0005099928,0.00027282708,0.00006097414,0.00024433192,0.00023699249,0.000008600504],"category_scores_gemma":[0.0029578805,0.00025607608,0.00010420394,0.0006066855,0.00023162857,0.0006110904,0.0000702681,0.00040759039,0.0000014667737],"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":[0.00015858053,0.0004959054,0.0037015246,0.00041853206,0.00000941036,0.0000013246366,0.0008943558,0.00058305427,0.9096794,0.0029264274,0.000008639326,0.08112283],"study_design_scores_gemma":[0.00074408966,0.00048557017,0.0013342622,0.00021924137,0.000059130583,6.273977e-7,0.000060497285,0.3801519,0.5877797,0.028969664,0.0000017724884,0.0001935512],"about_ca_topic_score_codex":0.0007821609,"about_ca_topic_score_gemma":0.000024055247,"teacher_disagreement_score":0.37956885,"about_ca_system_score_codex":0.00041290282,"about_ca_system_score_gemma":0.00027909747,"threshold_uncertainty_score":0.99998915},"labels":[],"label_agreement":null},{"id":"W2139552401","doi":"10.1007/s00181-006-0095-0","title":"Evaluating multi-treatment programs: theory and evidence from the U.S. Job Training Partnership Act experiment","year":2007,"lang":"en","type":"article","venue":"Empirical Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Benchmark (surveying); General partnership; Computer science; Sample (material); Training (meteorology); Work (physics); Operations research; Business; Finance; Mathematics; Engineering","score_opus":0.6798412018231792,"score_gpt":0.5532420723404441,"score_spread":0.1265991294827351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139552401","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":[0.9667088,0.0007449009,0.030843372,0.00045353884,0.000051839328,0.0006469123,0.0000024361532,0.00021649418,0.00033173396],"genre_scores_gemma":[0.84053785,0.00012345154,0.15849592,0.00043205055,0.00015098942,0.00013004948,0.0000032737732,0.00003457182,0.00009184958],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840564,0.0002176302,0.00047551145,0.00040983091,0.00009711922,0.00039426298],"domain_scores_gemma":[0.9926596,0.00651166,0.00020634547,0.00044765524,0.000034915673,0.00013980034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026105687,0.00024915332,0.0003149821,0.000027151294,0.00015758006,0.000091473856,0.0002239529,0.00011467409,0.00004869015],"category_scores_gemma":[0.0014676052,0.00017148379,0.00008551718,0.00005399438,0.0001979112,0.00021010576,0.00011014252,0.00018207743,0.000011402188],"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":[0.0004784749,0.00048230565,0.050523687,0.000033313925,0.00027752694,0.000017963814,0.074283406,0.000078866426,0.0017817068,0.05935199,0.00018100155,0.8125098],"study_design_scores_gemma":[0.0024309286,0.0023250475,0.019615492,0.0007893245,0.000309419,0.000033746113,0.024205606,0.0110810185,0.043745786,0.88943285,0.004461857,0.0015689327],"about_ca_topic_score_codex":0.000038153838,"about_ca_topic_score_gemma":0.00019360856,"teacher_disagreement_score":0.83008087,"about_ca_system_score_codex":0.00036671097,"about_ca_system_score_gemma":0.0001001582,"threshold_uncertainty_score":0.6992906},"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":"W2142912667","doi":"10.1001/jama.297.3.278","title":"Analysis of Observational Studies in the Presence of Treatment Selection Bias","year":2007,"lang":"en","type":"article","venue":"JAMA","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":788,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; St. Michael's Hospital; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; York University","funders":"National Institute on Aging; Institute for Clinical Evaluative Sciences; Canadian Institutes of Health Research; Dartmouth College","keywords":"Medicine; Propensity score matching; Relative risk; Observational study; Confidence interval; Cardiac catheterization; Myocardial infarction; Selection bias; Internal medicine; Proportional hazards model; Cohort study; Emergency medicine","score_opus":0.5264523418573861,"score_gpt":0.503462976493724,"score_spread":0.02298936536366214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142912667","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":[0.9895404,0.000052522308,0.009656651,0.000091450165,0.00000842369,0.00013922754,0.000003948313,0.000018910077,0.00048848824],"genre_scores_gemma":[0.982464,0.000048843453,0.0173675,0.000018854382,0.000012642615,0.000017659435,0.0000027625613,0.0000025891693,0.00006514241],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994014,0.00004853404,0.00026727252,0.00006925028,0.00014356333,0.00007000498],"domain_scores_gemma":[0.99765825,0.0018702046,0.0001647002,0.0001309093,0.00016992971,0.000005996869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065219164,0.000052809417,0.00019504908,0.00015519303,0.0000135813125,0.0000023009316,0.00007424925,0.00003020831,0.000009711655],"category_scores_gemma":[0.001106905,0.00003276918,0.000053796015,0.00083189446,0.000054106145,0.000073125964,0.000012227662,0.000037946793,1.8959835e-7],"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":[0.00013459501,0.0008956597,0.63137674,0.00016597414,0.0018206458,0.0000062269137,0.0323463,0.0014294832,0.011972324,0.2937399,0.00061822106,0.025493912],"study_design_scores_gemma":[0.00053236634,0.00072986993,0.58326274,0.00012418281,0.0008384659,0.0000027471417,0.004968049,0.0034628562,0.1540957,0.25135198,0.00045732714,0.00017373612],"about_ca_topic_score_codex":0.00006307025,"about_ca_topic_score_gemma":0.00070514804,"teacher_disagreement_score":0.14212337,"about_ca_system_score_codex":0.00008873458,"about_ca_system_score_gemma":0.000016091913,"threshold_uncertainty_score":0.13362885},"labels":[],"label_agreement":null},{"id":"W2144168223","doi":"10.1002/sim.5984","title":"The use of propensity score methods with survival or time‐to‐event outcomes: reporting measures of effect similar to those used in randomized experiments","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1441,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Observational study; Marginal structural model; Inverse probability weighting; Medicine; Covariate; Randomized controlled trial; Confounding; Average treatment effect; Statistics; Hazard ratio; Selection bias; Population; Survival analysis; Matching (statistics); Proportional hazards model; Confidence interval; Internal medicine; Mathematics","score_opus":0.45447001760427186,"score_gpt":0.5290019207742545,"score_spread":0.0745319031699826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144168223","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":[0.26381022,0.0000207472,0.7315506,0.00019229752,0.00006227529,0.0042370833,0.000013176203,0.000038798327,0.00007485471],"genre_scores_gemma":[0.12916155,0.000013644712,0.8699784,0.00007559598,0.0000111978125,0.00045910204,0.0000049330006,0.00003945955,0.00025609948],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99514264,0.001510572,0.0020939852,0.00027012636,0.0006896854,0.00029299516],"domain_scores_gemma":[0.97988665,0.017772425,0.0012502897,0.00058957766,0.00040212512,0.00009893163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010290257,0.0002563637,0.0019802502,0.0001833278,0.000035023404,0.000011108426,0.00022484535,0.00005974404,0.00008089279],"category_scores_gemma":[0.11958004,0.00011961341,0.00004162958,0.00036492586,0.00030610565,0.00007398292,0.00012142702,0.00022299838,0.0000019682043],"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":[0.15205052,0.0023175764,0.21000072,0.004554696,0.0020690882,0.0008961363,0.05569208,0.0021018754,0.30385748,0.04768069,0.015617619,0.20316154],"study_design_scores_gemma":[0.18452807,0.011637685,0.041002546,0.020066367,0.0010538317,0.000037480706,0.0031927081,0.009401509,0.44179448,0.2845741,0.00040970356,0.0023015132],"about_ca_topic_score_codex":0.00061079394,"about_ca_topic_score_gemma":0.0003401974,"teacher_disagreement_score":0.2368934,"about_ca_system_score_codex":0.00009655355,"about_ca_system_score_gemma":0.0000781067,"threshold_uncertainty_score":0.8878361},"labels":[],"label_agreement":null},{"id":"W2145140835","doi":"10.2307/3316021","title":"Semiparametric efficient estimation for the auxiliary outcome problem with the conditional mean model","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Covariate; Semiparametric regression; Semiparametric model; Outcome (game theory); Mathematics; Conditional expectation; Econometrics; Statistics; Delta method; Score; Variance (accounting); Economics","score_opus":0.12275730340290829,"score_gpt":0.36404272083084915,"score_spread":0.24128541742794085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145140835","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":[0.0030223217,0.000049627335,0.99432504,0.0014948577,0.000042665943,0.00044524582,0.0005181313,0.000012591849,0.00008948899],"genre_scores_gemma":[0.49558762,0.0000021433307,0.5041222,0.00017692332,0.000024895853,0.000018063209,0.0000083766745,0.000015811042,0.000043987224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900085,0.000020594813,0.0003890447,0.00008033525,0.00027219096,0.00023697405],"domain_scores_gemma":[0.99751,0.0012051037,0.00039464363,0.00016918934,0.0005359536,0.00018506651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005564521,0.0001252702,0.00017635491,0.00014814972,0.00028587904,0.00006236019,0.0002669458,0.00004306904,0.000013849365],"category_scores_gemma":[0.00078855007,0.000067687,0.000043521755,0.00019641395,0.00021592209,0.000076333024,0.000006921857,0.0002650291,0.000001570468],"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":[0.000009481681,0.000013136483,0.00003632723,0.000028588278,0.000031565232,0.000013937662,0.0004600962,0.42355788,0.000005264171,0.57101816,0.0039968546,0.0008287203],"study_design_scores_gemma":[0.00040424854,0.00017991035,0.0001373425,0.000057121764,0.0001344143,0.00012586912,0.0002307344,0.120293856,0.00010246331,0.8779837,0.0002336775,0.000116666175],"about_ca_topic_score_codex":0.00017170992,"about_ca_topic_score_gemma":0.003963471,"teacher_disagreement_score":0.4925653,"about_ca_system_score_codex":0.00037052052,"about_ca_system_score_gemma":0.0012110155,"threshold_uncertainty_score":0.27601954},"labels":[],"label_agreement":null},{"id":"W2146231646","doi":"10.3386/w15301","title":"Matching on the Estimated Propensity Score","year":2009,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Banff Centre","funders":"","keywords":"Propensity score matching; Statistics; Matching (statistics); Econometrics; Mathematics; Computer science; Geography","score_opus":0.8414961098396947,"score_gpt":0.6266463557701262,"score_spread":0.21484975406956852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146231646","genre_codex":"other","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":[0.02215804,0.00009607175,0.00017686018,0.001552925,0.00015443233,0.00184307,0.000079959995,0.00016256793,0.9737761],"genre_scores_gemma":[0.97809935,0.00061553426,0.0073651182,0.00009265803,0.0007143677,0.0002676702,0.0002466742,0.000119520875,0.012479119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99616927,0.00025870395,0.0007318978,0.0004619239,0.0019866752,0.00039154032],"domain_scores_gemma":[0.9923411,0.004159419,0.00050399604,0.00061680516,0.0023103445,0.000068312016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008853749,0.00026488284,0.00057546323,0.00050029805,0.00020734817,0.000076273944,0.00080072077,0.00037328925,0.00042659993],"category_scores_gemma":[0.0057389718,0.00018926975,0.00014585466,0.00017057933,0.00028743112,0.00013483598,0.0002160377,0.0015410173,0.00012937555],"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":[0.000031936335,0.00007919624,0.000045521978,0.00011551284,0.00006114713,0.000005251036,0.000035062065,0.00008298255,0.00014312638,0.91428417,0.08365489,0.0014611762],"study_design_scores_gemma":[0.000075483236,0.00012399805,0.00020462136,0.00059177727,0.000008993054,0.000019115825,0.000013862785,0.00008529678,0.0020204184,0.9953512,0.0013366046,0.00016861693],"about_ca_topic_score_codex":0.00042159448,"about_ca_topic_score_gemma":0.00010690464,"teacher_disagreement_score":0.961297,"about_ca_system_score_codex":0.0021455144,"about_ca_system_score_gemma":0.0027686898,"threshold_uncertainty_score":0.7718196},"labels":[],"label_agreement":null},{"id":"W2147784336","doi":"10.1007/s00038-010-0198-4","title":"Marginal Structural Models: unbiased estimation for longitudinal studies","year":2010,"lang":"en","type":"article","venue":"International Journal of Public Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":false,"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; Weighting; Latent variable; Unbiased Estimation; Estimation; Statistics; Econometrics; Inverse probability weighting; Mathematics; Computer science; Medicine; Economics; Estimator","score_opus":0.5599853245882525,"score_gpt":0.564452031610165,"score_spread":0.0044667070219125415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147784336","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":[0.12546104,0.00021212548,0.858103,0.014167651,0.0015769762,0.00024563615,0.000036536825,0.00007043633,0.00012661888],"genre_scores_gemma":[0.6689159,0.000075959346,0.3302758,0.00023539658,0.00043231162,0.000012222691,0.000008430315,0.000015475754,0.000028467708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980428,0.00007338465,0.0008310215,0.00014113598,0.0006317462,0.00027986628],"domain_scores_gemma":[0.9955478,0.00069816376,0.0010380651,0.00014570028,0.0023818596,0.0001884181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002298127,0.00014698275,0.00033605678,0.00032639434,0.000092693655,0.00009185842,0.000479556,0.000065059256,0.00004550348],"category_scores_gemma":[0.0034831706,0.000119023636,0.00012411238,0.00009267806,0.00009671175,0.0012717291,0.000053949545,0.0004023608,0.0000011040642],"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":[0.00008036205,0.00012283948,0.000724656,0.00011656125,0.00028787114,0.000014472606,0.0009895142,0.00022999167,0.000293421,0.84724677,0.005077002,0.14481653],"study_design_scores_gemma":[0.0007208824,0.00029041013,0.00052135513,0.000089395806,0.00001209392,0.00033776666,0.00025818203,0.015541289,0.0002578909,0.9792433,0.0025962992,0.00013116273],"about_ca_topic_score_codex":0.000008592641,"about_ca_topic_score_gemma":0.00006229686,"teacher_disagreement_score":0.5434549,"about_ca_system_score_codex":0.0003449446,"about_ca_system_score_gemma":0.00055956014,"threshold_uncertainty_score":0.48536432},"labels":[],"label_agreement":null},{"id":"W2148009828","doi":"10.1002/bimj.200900277","title":"Simulation‐based power calculations for large cohort studies","year":2010,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Advanced Causal Inference Techniques","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":"Cancer Care Ontario; McMaster University; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Partenariat Canadien Contre Le Cancer; Ontario Institute for Cancer Research","keywords":"Covariate; Statistics; Proportional hazards model; Cohort; Statistical power; Econometrics; Correlation; Cohort study; Demography; Medicine; Mathematics","score_opus":0.33478582725947154,"score_gpt":0.5248926449178022,"score_spread":0.19010681765833065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148009828","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":[0.037521403,0.00008501112,0.96081567,0.0004239403,0.00039355212,0.00036282177,0.00003405574,0.00016698554,0.0001965889],"genre_scores_gemma":[0.7181997,0.0000049121936,0.2813505,0.00013860675,0.0001586236,0.000025392832,0.000003294694,0.000019693693,0.00009932956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987096,0.000035706962,0.00043356564,0.00015580446,0.0003584456,0.00030684785],"domain_scores_gemma":[0.99201447,0.0065905284,0.00022124393,0.00021776573,0.0007994897,0.00015650055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00090679195,0.00014052296,0.0002701641,0.00086870056,0.00028718836,0.00006071561,0.00017797996,0.00013358307,0.0002001961],"category_scores_gemma":[0.027014408,0.000108254026,0.00016059156,0.0012388858,0.000059987484,0.00016995078,0.000041316565,0.0003707889,0.000009999108],"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":[0.00025156766,0.003406376,0.06419566,0.00021164441,0.0015942614,0.00007469559,0.0006019043,0.0024191088,0.02732752,0.82386446,0.057636514,0.018416293],"study_design_scores_gemma":[0.0024227144,0.0006488021,0.008863963,0.0000722782,0.00031313926,0.00003927629,0.00016734064,0.054184873,0.006103458,0.8273685,0.09900242,0.0008132486],"about_ca_topic_score_codex":3.3720846e-7,"about_ca_topic_score_gemma":0.0000021289877,"teacher_disagreement_score":0.68067825,"about_ca_system_score_codex":0.00009308858,"about_ca_system_score_gemma":0.00005895967,"threshold_uncertainty_score":0.98118144},"labels":[],"label_agreement":null},{"id":"W2149706056","doi":"10.1002/sta4.46","title":"Propensity score estimation in the presence of length‐biased sampling: a non‐parametric adjustment approach","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Propensity score matching; Estimator; Statistics; Econometrics; Hazard ratio; Parametric statistics; Survival analysis; Proportional hazards model; Estimation; Survival function; Sample size determination; Mathematics; Parametric model; Economics; Confidence interval","score_opus":0.3111569212399656,"score_gpt":0.40695715277719324,"score_spread":0.09580023153722766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149706056","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":[0.36090913,0.000016100277,0.6364933,0.000027805052,0.000018521969,0.0008266799,0.0000041592907,0.000057888465,0.0016464063],"genre_scores_gemma":[0.7526736,0.000006808349,0.24715163,0.00003006277,0.000009332389,0.00008923553,0.0000072681155,0.000009546176,0.000022472543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99888444,0.00013692942,0.00029734662,0.0001943296,0.00030257512,0.00018436069],"domain_scores_gemma":[0.998335,0.00088866864,0.00018746918,0.00047550543,0.00008724484,0.000026122008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088845147,0.00012216145,0.00023369581,0.000118289005,0.000034685476,0.000016012778,0.00027242835,0.000054715274,0.000008829698],"category_scores_gemma":[0.0021116906,0.00008183145,0.00003381533,0.00041984097,0.00008315637,0.00013917626,0.000062538005,0.00017906842,0.0000031381642],"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":[0.0003610673,0.0041015735,0.0147641115,0.0033210444,0.000096279975,0.000009145262,0.021910219,0.014011411,0.009446794,0.6946422,0.004265159,0.23307098],"study_design_scores_gemma":[0.000828602,0.0006016845,0.02189521,0.00032241,0.00006110014,0.000011142416,0.0008148155,0.1745643,0.019596567,0.78071904,0.00016390717,0.00042120068],"about_ca_topic_score_codex":0.000052946463,"about_ca_topic_score_gemma":0.000013837432,"teacher_disagreement_score":0.39176452,"about_ca_system_score_codex":0.000050725925,"about_ca_system_score_gemma":0.00003042764,"threshold_uncertainty_score":0.33369896},"labels":[],"label_agreement":null},{"id":"W2151471947","doi":"10.1093/bioinformatics/btv219","title":"ESPRESSO: taking into account assessment errors on outcome and exposures in power analysis for association studies","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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":"FP7 Health; Canadian Institutes of Health Research; European Commission","keywords":"Association (psychology); Outcome (game theory); Computer science; Meta-analysis; Econometrics; Statistics; Psychology; Environmental health; Medicine; Mathematics; Internal medicine","score_opus":0.2878465843490817,"score_gpt":0.4961217734300007,"score_spread":0.20827518908091897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151471947","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":[0.736528,0.00009641394,0.2582524,0.00059732574,0.00024975216,0.0011942734,0.00003854769,0.0003331306,0.0027101468],"genre_scores_gemma":[0.7035018,0.000017281944,0.29604435,0.00022680518,0.000014144191,0.00009976722,0.000010342048,0.000012532546,0.00007292488],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984819,0.000036775084,0.00072386354,0.00012281646,0.00039524699,0.00023933947],"domain_scores_gemma":[0.99764186,0.0010601011,0.00070991623,0.00025140526,0.0002766556,0.00006003958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014525634,0.00018564385,0.00048446943,0.00034439733,0.00006148845,0.00006488512,0.00012642972,0.00012103504,0.0000031534341],"category_scores_gemma":[0.0038711368,0.00015220162,0.00007635919,0.00030413715,0.00003071377,0.00042438105,0.00009841868,0.0001408113,0.000002292143],"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":[0.00007058126,0.0002514356,0.86471575,0.00072885636,0.0013131268,0.0000032354242,0.030630218,0.00096403493,0.00005047217,0.09386431,0.0040746806,0.0033332857],"study_design_scores_gemma":[0.004478033,0.0020477772,0.109171525,0.0006774482,0.0017478717,0.0000033283497,0.064871006,0.09799255,0.0018886233,0.7111907,0.0037983877,0.0021327338],"about_ca_topic_score_codex":0.000011538614,"about_ca_topic_score_gemma":0.00018345547,"teacher_disagreement_score":0.75554425,"about_ca_system_score_codex":0.000759822,"about_ca_system_score_gemma":0.000037659207,"threshold_uncertainty_score":0.62066025},"labels":[],"label_agreement":null},{"id":"W2152590022","doi":"10.1002/pds.1673","title":"Goodness‐of‐fit diagnostics for the propensity score model when estimating treatment effects using covariate adjustment with the propensity score","year":2008,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":237,"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","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Medicine; Goodness of fit; Statistics; Econometrics; Internal medicine; Mathematics","score_opus":0.4490533302099411,"score_gpt":0.428672555624695,"score_spread":0.02038077458524612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152590022","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":[0.3289253,0.0008052817,0.6655818,0.0011610682,0.00011143642,0.0032159847,0.00004245196,0.00011529146,0.000041384636],"genre_scores_gemma":[0.7437559,0.0009409906,0.2538694,0.00073806767,0.00013317098,0.0004388802,0.000011466505,0.000043171553,0.000068978225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770486,0.00067748304,0.00056679914,0.0004397376,0.00014836565,0.00046277174],"domain_scores_gemma":[0.9852496,0.013385954,0.00059102196,0.0004624166,0.00021348924,0.00009750976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020943696,0.00040033093,0.00087668974,0.00003482213,0.0008602758,0.000007495613,0.00026621096,0.00010612714,0.0000052232876],"category_scores_gemma":[0.0020192035,0.00019059535,0.00010929532,0.00009479147,0.00068534253,0.00016681563,0.0001943857,0.00032144325,7.672741e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0109661985,0.0033801696,0.21693008,0.005057034,0.00440723,0.00022011258,0.033686895,0.34950474,0.0076299254,0.26431265,0.020086326,0.08381863],"study_design_scores_gemma":[0.003596014,0.0007030664,0.009687382,0.00059881003,0.001964845,0.00021931258,0.00010324769,0.8124983,0.014927611,0.15469976,0.0002558517,0.000745843],"about_ca_topic_score_codex":0.00023098064,"about_ca_topic_score_gemma":0.000073348056,"teacher_disagreement_score":0.4629935,"about_ca_system_score_codex":0.0001345852,"about_ca_system_score_gemma":0.000165067,"threshold_uncertainty_score":0.7772253},"labels":[],"label_agreement":null},{"id":"W2153012086","doi":"10.1111/j.1524-4733.2009.00602.x","title":"Good Research Practices for Comparative Effectiveness Research: Analytic Methods to Improve Causal Inference from Nonrandomized Studies of Treatment Effects Using Secondary Data Sources: The ISPOR Good Research Practices for Retrospective Database Analysis Task Force Report—Part III","year":2009,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":290,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Causal inference; Inference; Confounding; Statistical inference; Comparative effectiveness research; Marginal structural model; Medicine; Propensity score matching; Instrumental variable; Outcomes research; Research design; Computer science; Econometrics; Management science; Statistics; Machine learning; Alternative medicine; Artificial intelligence; Engineering; Mathematics","score_opus":0.8166517374954501,"score_gpt":0.7018213479349174,"score_spread":0.11483038956053271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153012086","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":[0.5135121,0.0045687314,0.44296417,0.0019162559,0.0002416289,0.03379567,0.0026071286,0.00015840618,0.0002359378],"genre_scores_gemma":[0.6271013,0.00057278504,0.36829084,0.000037828202,0.0002534191,0.0031734058,0.00035529447,0.00006411018,0.00015098325],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96398586,0.027522448,0.0023144295,0.002406283,0.001956847,0.0018141078],"domain_scores_gemma":[0.7062866,0.28128207,0.0038601086,0.0038667554,0.0043514986,0.00035297967],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12459832,0.0005535864,0.003031022,0.0017542852,0.0013526665,0.000223041,0.0015076593,0.00023293449,0.0000075857115],"category_scores_gemma":[0.17996778,0.00039510152,0.0002597456,0.0047789086,0.0007757317,0.0013115206,0.0008061209,0.0017699283,0.0000012457767],"study_design_candidate":"theoretical_or_conceptual","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":[0.16504449,0.023659794,0.0127147725,0.029129004,0.050078597,0.0006806336,0.23950289,0.021550875,0.24601012,0.16053239,0.0053843986,0.045712035],"study_design_scores_gemma":[0.02234323,0.032797474,0.0021800515,0.006125017,0.0036124296,0.000028296476,0.05708302,0.18366449,0.13025023,0.5580377,0.0023625628,0.0015155108],"about_ca_topic_score_codex":0.03160303,"about_ca_topic_score_gemma":0.0064466232,"teacher_disagreement_score":0.3975053,"about_ca_system_score_codex":0.0031838967,"about_ca_system_score_gemma":0.0032124508,"threshold_uncertainty_score":0.9999474},"labels":[],"label_agreement":null},{"id":"W2153434255","doi":"10.1111/j.1524-4733.2009.00600.x","title":"Good Research Practices for Comparative Effectiveness Research: Defining, Reporting and Interpreting Nonrandomized Studies of Treatment Effects Using Secondary Data Sources: The ISPOR Good Research Practices for Retrospective Database Analysis Task Force Report—Part I","year":2009,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":410,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Comparative effectiveness research; Observational study; Medicine; Outcomes research; Research design; MEDLINE; Management science; Medical education; Alternative medicine; Political science","score_opus":0.827067872307364,"score_gpt":0.6782163137175784,"score_spread":0.1488515585897856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153434255","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":[0.9424095,0.008197349,0.03010726,0.0011987151,0.00011273366,0.016948294,0.00045576572,0.00012666167,0.00044372698],"genre_scores_gemma":[0.89187384,0.00091050216,0.105256885,0.000020537083,0.00012249079,0.0015128448,0.00016951081,0.000054449545,0.000078963785],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97627944,0.0155941285,0.003201846,0.0018800031,0.0015380159,0.0015065509],"domain_scores_gemma":[0.72642016,0.252839,0.013402926,0.003115965,0.003969515,0.0002524306],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17036594,0.00040283366,0.0022901164,0.0012184435,0.0016352203,0.00020286253,0.00075495784,0.0001686395,0.0000022359307],"category_scores_gemma":[0.31167623,0.0002900872,0.00018371291,0.00250928,0.0008320709,0.0011529517,0.0007538841,0.0015577243,3.187793e-7],"study_design_candidate":"theoretical_or_conceptual","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":[0.09459944,0.014399395,0.10401883,0.0687189,0.028727667,0.0013768144,0.35222408,0.0078105144,0.05414745,0.23800547,0.004931037,0.031040391],"study_design_scores_gemma":[0.020782903,0.031767022,0.0029186436,0.02324623,0.0026798504,0.00037999637,0.15113427,0.1918347,0.05089434,0.520071,0.0026483908,0.0016426184],"about_ca_topic_score_codex":0.006890359,"about_ca_topic_score_gemma":0.0018912434,"teacher_disagreement_score":0.28206557,"about_ca_system_score_codex":0.0017611458,"about_ca_system_score_gemma":0.0017189129,"threshold_uncertainty_score":0.9999551},"labels":[],"label_agreement":null},{"id":"W2153720865","doi":"10.55016/ojs/ajer.v49i3.54984","title":"Which Model is Best? Robustness Properties to Justify Model Choice Among Unidimensional IRT Models under Item Parameter Drift","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Econometrics; Item response theory; Statistical physics; Computer science; Mathematics; Statistics; Psychometrics; Physics","score_opus":0.4434345342535627,"score_gpt":0.4856145623288259,"score_spread":0.042180028075263165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153720865","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":[0.92113864,0.00026986373,0.04831574,0.013937705,0.00013410604,0.00067960477,0.000008250429,0.00000764502,0.0155084515],"genre_scores_gemma":[0.85582787,0.000064685184,0.11790997,0.00033842807,0.000116190466,0.000112920134,0.0000032739895,0.00007673717,0.025549922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958148,0.00033025848,0.00091802346,0.00043984578,0.0017352793,0.0007618082],"domain_scores_gemma":[0.97602785,0.018518433,0.00029537847,0.000596081,0.004015969,0.00054631114],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016009569,0.0003219183,0.00046701022,0.0006543902,0.00032911074,0.00013913387,0.00073724403,0.00023290273,0.00082572585],"category_scores_gemma":[0.025330087,0.00026240083,0.00014282434,0.0008052069,0.00023027755,0.0011750725,0.00016786288,0.001154791,0.000046578483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009627651,0.000808091,0.0004156713,0.00009618629,0.00011231945,5.3262545e-7,0.0013091756,0.6069472,0.0023955016,0.36634237,0.021415787,0.000060894527],"study_design_scores_gemma":[0.0003193071,0.00020899755,0.00006285392,0.0005613208,0.0000672275,0.000058895268,0.0005770514,0.5363625,0.0049448833,0.45614466,0.00028434256,0.00040795238],"about_ca_topic_score_codex":0.00019474022,"about_ca_topic_score_gemma":0.0006164022,"teacher_disagreement_score":0.089802295,"about_ca_system_score_codex":0.00047544934,"about_ca_system_score_gemma":0.0026731926,"threshold_uncertainty_score":0.99998283},"labels":[],"label_agreement":null},{"id":"W2154068546","doi":"10.1162/rest.2009.11453","title":"Estimating Treatment Effects from Contaminated Multiperiod Education Experiments: The Dynamic Impacts of Class Size Reductions","year":2010,"lang":"en","type":"article","venue":"The Review of Economics and Statistics","topic":"Advanced Causal Inference Techniques","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":"Queen's University","funders":"","keywords":"Attrition; Treatment and control groups; Treatment effect; Randomized experiment; Sample size determination; Randomized controlled trial; Class size; Class (philosophy); Econometrics; Cognition; Average treatment effect; Statistics; Mathematics; Psychology; Computer science; Medicine; Propensity score matching; Mathematics education; Artificial intelligence","score_opus":0.037657090147877555,"score_gpt":0.3925355550934054,"score_spread":0.3548784649455278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154068546","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":[0.95841587,0.011321772,0.026598861,0.0005651236,0.00047686562,0.00179122,0.00055922585,0.000033965855,0.00023711512],"genre_scores_gemma":[0.5657573,0.032535993,0.40137833,0.00008756837,0.000032316828,0.00011900661,0.00003545638,0.00002064926,0.00003338774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923533,0.00006780675,0.0004515733,0.00011752641,0.000032566386,0.00009516601],"domain_scores_gemma":[0.9969792,0.001967932,0.0005242458,0.0004026856,0.00009127065,0.000034680717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024095342,0.0001352077,0.0003721426,0.000014451862,0.00007909179,0.000013986975,0.00012672662,0.00003692201,0.00002313576],"category_scores_gemma":[0.0012088318,0.000079855374,0.000041201805,0.00003495363,0.00017915216,0.000051736926,0.000032661275,0.00009878638,8.9030505e-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":[0.00002449934,0.0005533825,0.00008788848,0.0038677538,0.00032352193,5.3257884e-7,0.0025888074,0.000018196826,0.016242005,0.5453028,0.00057656417,0.43041402],"study_design_scores_gemma":[0.000989297,0.00073254976,0.0020042649,0.0068717655,0.0010957243,0.0000309259,0.0010474882,0.041254178,0.029003024,0.9140033,0.0024008679,0.000566619],"about_ca_topic_score_codex":0.00016233319,"about_ca_topic_score_gemma":0.00011413928,"teacher_disagreement_score":0.42984742,"about_ca_system_score_codex":0.00005762869,"about_ca_system_score_gemma":0.00010593661,"threshold_uncertainty_score":0.32564074},"labels":[],"label_agreement":null},{"id":"W2154175900","doi":"10.1186/1471-2288-13-109","title":"Beyond case fatality rate: using potential impact fraction to estimate the effect of increasing treatment uptake on mortality","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"University Health Network; Sunnybrook Health Science Centre; University of Toronto; Toronto General Hospital; Toronto Public Health","funders":"","keywords":"Case fatality rate; Fraction (chemistry); Medicine; Mortality rate; Demography; Environmental health; Statistics; Emergency medicine; Population; Internal medicine; Mathematics; Chemistry","score_opus":0.6528163280579211,"score_gpt":0.6790984179224019,"score_spread":0.026282089864480773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154175900","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":[0.6599902,0.00001611647,0.3385017,0.00011259275,0.00006569871,0.0011105121,0.0000103268385,0.00006093162,0.00013192596],"genre_scores_gemma":[0.7770167,0.000010890757,0.2225688,0.000028068165,0.00012094049,0.00020986337,0.000005693447,0.000026766726,0.000012255538],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9670363,0.029922951,0.0006676745,0.000462945,0.0011577298,0.0007524105],"domain_scores_gemma":[0.91136473,0.086581714,0.00021565272,0.0009286679,0.00035190178,0.0005573238],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042977784,0.0002691529,0.0008019207,0.00023798164,0.00026999754,0.00004035945,0.00035392656,0.00032990685,0.00081751234],"category_scores_gemma":[0.16013522,0.00014741419,0.00019281574,0.00041962607,0.00061622576,0.00014649355,0.00027504645,0.0007744949,0.000027614406],"study_design_candidate":"bench_or_experimental","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":[0.007636567,0.0015332368,0.027560785,0.0017110382,0.001205537,0.0038233013,0.0014935437,0.0019137175,0.3893634,0.03793882,0.0014295976,0.52439046],"study_design_scores_gemma":[0.0024883205,0.0125836395,0.032473136,0.0005137389,0.00034996722,0.003260406,0.0007679777,0.041691776,0.31696913,0.58821845,0.000050914656,0.00063255633],"about_ca_topic_score_codex":0.015306306,"about_ca_topic_score_gemma":0.00070017995,"teacher_disagreement_score":0.5502796,"about_ca_system_score_codex":0.00056403305,"about_ca_system_score_gemma":0.0004586217,"threshold_uncertainty_score":0.9912509},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2154570063","doi":"10.1037/0012-1649.44.2.422","title":"Combining group-based trajectory modeling and propensity score matching for causal inferences in nonexperimental longitudinal data.","year":2008,"lang":"en","type":"article","venue":"Developmental Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; Social Sciences and Humanities Research Council of Canada; Molson Foundation","keywords":"Propensity score matching; Trajectory; Psychology; Observational study; Causal inference; Juvenile delinquency; Matching (statistics); Developmental psychology; Longitudinal study; Covariate; Econometrics; Cognitive psychology; Statistics; Mathematics","score_opus":0.5332881575547377,"score_gpt":0.4577601112091447,"score_spread":0.07552804634559296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154570063","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":[0.8364961,0.000048176742,0.16227832,0.00004221255,0.00010236632,0.00054835033,0.000020238205,0.00014143881,0.00032279993],"genre_scores_gemma":[0.7601708,0.000015146461,0.23937587,0.00017794382,0.000019209067,0.000101359816,0.00010700593,0.000027300805,0.000005374125],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99824154,0.0000667705,0.00049027696,0.0006429185,0.00016343193,0.00039506832],"domain_scores_gemma":[0.9992667,0.00021543082,0.00011925296,0.00028556425,0.000036735768,0.00007634106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004622038,0.00026264176,0.00042337715,0.00017882526,0.00020298512,0.000020061912,0.00033566103,0.00014012311,0.000021214933],"category_scores_gemma":[0.000089333655,0.00025940288,0.000025086545,0.00013149383,0.0002090409,0.00038010319,0.00021127009,0.00027096632,0.0000028718198],"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":[0.0013926093,0.002175829,0.880404,0.00044558744,0.00019060838,0.0004535459,0.009792057,0.0001744688,0.07902569,0.016927805,0.0012532548,0.0077645364],"study_design_scores_gemma":[0.02196347,0.0027992062,0.51653355,0.0018295648,0.00012460804,0.0031558566,0.0049243574,0.041297767,0.025366757,0.37585673,0.00035265464,0.0057954425],"about_ca_topic_score_codex":0.00008269166,"about_ca_topic_score_gemma":0.00034559748,"teacher_disagreement_score":0.3638704,"about_ca_system_score_codex":0.000110404355,"about_ca_system_score_gemma":0.00009879055,"threshold_uncertainty_score":0.9999858},"labels":[],"label_agreement":null},{"id":"W2156131834","doi":"10.1177/1740774507085279","title":"Using causal models to show the effect of untestable assumptions on effect estimates in randomized controlled trials","year":2007,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Estimator; Statistics; Randomized controlled trial; Randomization; Econometrics; Range (aeronautics); Mathematics; Sample size determination; Medicine; Treatment effect; Internal medicine","score_opus":0.6583151342331587,"score_gpt":0.6273959759153646,"score_spread":0.030919158317794126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156131834","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":[0.5177307,0.0002191941,0.46024278,0.00020365579,0.00064788334,0.019369025,0.000032484975,0.0002460461,0.001308188],"genre_scores_gemma":[0.9624643,0.00006274624,0.035971157,0.00012192884,0.00038442173,0.00086012704,0.000004495402,0.00006058855,0.00007028359],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9432672,0.04327198,0.011374402,0.00064954977,0.00073064526,0.0007061757],"domain_scores_gemma":[0.2252969,0.77061814,0.0029150941,0.0008139039,0.00016792104,0.00018801997],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41312757,0.0004729034,0.015407415,0.00033795706,0.00008937819,0.00005995204,0.00039474134,0.00041292014,0.00008167844],"category_scores_gemma":[0.68437517,0.00022415663,0.0025022167,0.0003900766,0.00030113905,0.0001395712,0.000106052044,0.0005902398,0.000013033967],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8893627,0.0006541167,0.0008237333,0.00026803382,0.0017522036,0.000030558098,0.00019167403,0.008773631,0.016605265,0.071230926,0.0007682106,0.009538969],"study_design_scores_gemma":[0.46966487,0.0030755464,0.000024161922,0.001456854,0.0029064505,0.00000354652,0.00002324951,0.01813312,0.08713285,0.4171354,0.000014831555,0.0004291143],"about_ca_topic_score_codex":0.000047626378,"about_ca_topic_score_gemma":0.000026850032,"teacher_disagreement_score":0.7273462,"about_ca_system_score_codex":0.00010845528,"about_ca_system_score_gemma":0.00008262141,"threshold_uncertainty_score":0.9992099},"labels":[],"label_agreement":null},{"id":"W2156390601","doi":"10.1162/003355300554764","title":"Substitution and Dropout Bias in Social Experiments: A Study of an Influential Social Experiment","year":2000,"lang":"en","type":"article","venue":"The Quarterly Journal of Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":270,"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":"Sage Foundation; National Science Foundation","keywords":"Randomized experiment; Substitution (logic); Dropout (neural networks); Drop out; Randomized controlled trial; Treatment and control groups; Psychology; Interpretation (philosophy); Social psychology; Empirical evidence; Econometrics; Computer science; Economics; Statistics; Demographic economics; Medicine; Mathematics","score_opus":0.18143271779288664,"score_gpt":0.41693618600704485,"score_spread":0.2355034682141582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156390601","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":[0.99931586,0.00002903989,0.00015199339,0.00004654334,0.000048763024,0.00023657565,0.0000024745027,0.000011466354,0.00015730018],"genre_scores_gemma":[0.99871844,0.000012252512,0.0010374268,0.000020231388,0.00017839676,0.00000988299,4.3514072e-7,0.000014252641,0.000008689043],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870414,0.00017082682,0.00078462396,0.00010540815,0.00008837092,0.00014664861],"domain_scores_gemma":[0.99919,0.000072446215,0.00052194257,0.00012612945,0.00005235924,0.00003712527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005997059,0.00013206423,0.00036433226,0.0001034944,0.000110552595,0.00004011397,0.00021370889,0.00006382903,0.000073396266],"category_scores_gemma":[0.000011180736,0.00010691315,0.000060465325,0.000051462866,0.00012428188,0.0004690964,0.000012865982,0.00017913828,0.0000011370702],"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":[0.0034311174,0.00906094,0.0025873126,0.00006737856,0.0005998525,0.000057682337,0.66141653,0.00026085315,0.013236712,0.13028744,0.00020948831,0.17878468],"study_design_scores_gemma":[0.012578166,0.015986184,0.008793888,0.00012939514,0.00026861468,0.00018567695,0.17462073,0.0013193461,0.025944725,0.75891334,0.0002943974,0.00096553087],"about_ca_topic_score_codex":0.000038814575,"about_ca_topic_score_gemma":0.00007433481,"teacher_disagreement_score":0.6286259,"about_ca_system_score_codex":0.0001231731,"about_ca_system_score_gemma":0.000042822663,"threshold_uncertainty_score":0.43597916},"labels":[],"label_agreement":null},{"id":"W2156712261","doi":"10.1016/j.jclinepi.2006.11.008","title":"Readers should systematically assess methods used to identify, measure and analyze confounding in observational cohort studies","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"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 Toronto; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Confounding; Medicine; Observational study; Propensity score matching; Cohort study; Internal medicine","score_opus":0.9663047621034415,"score_gpt":0.7829941344178378,"score_spread":0.1833106276856037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156712261","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":[0.00013312897,0.55638736,0.44094047,0.0006176862,0.0007063123,0.0010845809,0.000005623085,0.000038224043,0.00008659354],"genre_scores_gemma":[0.000017990966,0.56265736,0.43636495,0.00045982833,0.00037865737,0.00004419175,0.0000030291817,0.000043950367,0.00003003135],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9448546,0.029532798,0.023112796,0.0008514609,0.0008208993,0.0008274154],"domain_scores_gemma":[0.6288409,0.35858586,0.01038423,0.00056331867,0.0011665509,0.0004591207],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.22236861,0.00066450355,0.019439943,0.0008142145,0.000059412196,0.000027786622,0.00076117367,0.0016163859,0.000019968396],"category_scores_gemma":[0.5964388,0.00044618963,0.0014198589,0.00061652454,0.0004974242,0.00025166175,0.0002848682,0.0033869974,0.0000050822046],"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":[0.00018561404,0.0004527132,0.04346124,0.075712435,0.009196671,0.0004471714,0.000344348,0.000023311371,0.0000033522583,0.2313005,0.0063575166,0.63251513],"study_design_scores_gemma":[0.0008610301,0.0009900326,0.0056362217,0.16552708,0.0056861187,0.0009804446,0.0005997941,0.00007379959,0.0000011753995,0.6842802,0.1341252,0.0012389075],"about_ca_topic_score_codex":0.0000062422714,"about_ca_topic_score_gemma":0.000042596213,"teacher_disagreement_score":0.6312762,"about_ca_system_score_codex":0.0004304609,"about_ca_system_score_gemma":0.0006301027,"threshold_uncertainty_score":0.999799},"labels":[],"label_agreement":null},{"id":"W2157937931","doi":"10.1016/j.jclinepi.2014.12.012","title":"Confounding, effect modification, and the odds ratio: common misinterpretations","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Confounding; Observational study; Covariate; Medicine; Odds ratio; Randomized controlled trial; Odds; Multivariate statistics; Causal inference; Marginal structural model; Effect modification; Logistic regression; Internal medicine; Statistics; Confidence interval; Mathematics; Pathology","score_opus":0.6242836383000328,"score_gpt":0.639468897836851,"score_spread":0.015185259536818263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157937931","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":[0.16874543,0.0004747927,0.8134911,0.014277087,0.0006194704,0.0003043387,0.0000016930404,0.000043450607,0.0020426551],"genre_scores_gemma":[0.9624306,0.0002279207,0.035043735,0.0018586308,0.00030763532,0.00001091549,0.0000010737645,0.000011703113,0.00010777055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891269,0.007226429,0.0031934523,0.00013673124,0.00014544316,0.00017104547],"domain_scores_gemma":[0.8665883,0.12969409,0.0028124384,0.00029602993,0.000404683,0.0002044588],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04576648,0.00012623447,0.0016585678,0.00005621509,0.00005703662,0.000013248849,0.00028486134,0.00020054301,0.000013689689],"category_scores_gemma":[0.27702323,0.00006718269,0.00026301315,0.000068213805,0.0008410942,0.00014710336,0.000054380114,0.0007547934,0.0000065513773],"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":[0.0005843966,0.00005610848,0.015985956,0.000018270466,0.00010044695,0.0000040570335,0.00026913686,0.00005059542,0.00001148148,0.9635284,0.012614566,0.0067765624],"study_design_scores_gemma":[0.0018211036,0.0007643265,0.0030928962,0.00006435084,0.00010976244,0.00012876054,0.00006752103,0.0051655723,0.000042972584,0.98674625,0.0019238145,0.000072643656],"about_ca_topic_score_codex":0.000011556882,"about_ca_topic_score_gemma":0.000009541757,"teacher_disagreement_score":0.7936852,"about_ca_system_score_codex":0.000031354404,"about_ca_system_score_gemma":0.00009855579,"threshold_uncertainty_score":0.98258424},"labels":[],"label_agreement":null},{"id":"W2158224660","doi":"10.1111/ppe.12107","title":"Case–Crossover Designs for More Patient‐Centred Epidemiology","year":2014,"lang":"en","type":"letter","venue":"Paediatric and Perinatal Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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 British Columbia","funders":"","keywords":"Anesthesiology; Medicine; Library science; Columbia university; Citation; Original research; Family medicine; Media studies; Sociology; Psychiatry; Computer science","score_opus":0.31685544979276065,"score_gpt":0.42745046414195775,"score_spread":0.11059501434919711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158224660","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":[0.0041410527,0.025776966,0.43112004,0.52679867,0.0023100968,0.005171156,0.002314682,0.0015317748,0.0008355944],"genre_scores_gemma":[0.008599785,0.001251383,0.2850059,0.6943128,0.006986104,0.0014496843,0.0009387189,0.00031899742,0.0011366144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929148,0.0019161748,0.0019092342,0.0014037209,0.00012865284,0.0017274353],"domain_scores_gemma":[0.9259295,0.07140365,0.0013950146,0.000834463,0.0002115836,0.00022577864],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016383642,0.00095898955,0.0030024226,0.00030717358,0.00029711076,0.000012209857,0.00042406254,0.0030673381,0.0001529043],"category_scores_gemma":[0.042677026,0.00081636326,0.00053393067,0.00016426186,0.0008618318,0.00012884794,0.00034297575,0.0021673478,0.000024213343],"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":[0.00007852452,0.00002000695,0.0010365425,0.0011360793,0.0001193123,0.0009791693,0.00025887464,0.0000055369933,0.0000017725382,0.020979475,0.9688302,0.006554492],"study_design_scores_gemma":[0.00043060348,0.00051510107,0.000015036836,0.000032837943,0.00019467341,0.0042196917,0.000054861663,0.00059386116,0.000007885262,0.4214716,0.5717164,0.0007474294],"about_ca_topic_score_codex":0.000119028504,"about_ca_topic_score_gemma":0.0000066131242,"teacher_disagreement_score":0.4004921,"about_ca_system_score_codex":0.00015866438,"about_ca_system_score_gemma":0.00008687114,"threshold_uncertainty_score":0.99942875},"labels":[],"label_agreement":null},{"id":"W2158460222","doi":"10.1177/0272989x09341755","title":"The Relative Ability of Different Propensity Score Methods to Balance Measured Covariates Between Treated and Untreated Subjects in Observational Studies","year":2009,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":456,"is_retracted":false,"has_abstract":true,"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":"Propensity score matching; Covariate; Statistics; Observational study; Inverse probability weighting; Weighting; Medicine; Mathematics","score_opus":0.4399813510196111,"score_gpt":0.5151726562683904,"score_spread":0.07519130524877926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158460222","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":[0.7554493,0.00016824409,0.24316281,0.0005098166,0.000028291845,0.00056280603,0.0000029697321,0.00006567833,0.00005006706],"genre_scores_gemma":[0.8561302,0.00006013981,0.14367136,0.00007800737,0.000018329423,0.000023359758,0.0000016265535,0.000008071373,0.000008924541],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972337,0.00071466144,0.00076866354,0.000324212,0.0007173566,0.00024142506],"domain_scores_gemma":[0.97994345,0.019013537,0.00024061816,0.00031296772,0.00039647118,0.00009297119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003171956,0.00019242802,0.0006584102,0.00008431691,0.00014236126,0.000014558373,0.00023361399,0.00015535303,0.000010949272],"category_scores_gemma":[0.060828973,0.00010899657,0.000043676704,0.00044508578,0.0001962963,0.0001081311,0.0001788584,0.0003462847,5.832123e-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":[0.00055043097,0.00020412156,0.51702327,0.000095796066,0.00013078097,0.000026381485,0.002262875,0.0000049782184,0.0043193307,0.07273739,0.00018060514,0.40246406],"study_design_scores_gemma":[0.00023666982,0.000121885496,0.48173454,0.0007924183,0.000017842185,7.8300275e-7,0.00003355814,0.00019830793,0.0022428038,0.51454157,0.000006351394,0.000073275405],"about_ca_topic_score_codex":0.000007983872,"about_ca_topic_score_gemma":0.0000727966,"teacher_disagreement_score":0.44180417,"about_ca_system_score_codex":0.00016392393,"about_ca_system_score_gemma":0.000049301027,"threshold_uncertainty_score":0.94708204},"labels":[],"label_agreement":null},{"id":"W2158691927","doi":"10.3747/co.v0i0.341","title":"Panel Discussion 3","year":2008,"lang":"en","type":"article","venue":"Current Oncology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Data science; Computer science","score_opus":0.6356910130670933,"score_gpt":0.5415724644534431,"score_spread":0.09411854861365021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158691927","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":[0.52469903,0.00097083306,0.40629736,0.0034332362,0.0038197332,0.0013953272,0.000025617746,0.0030650406,0.056293838],"genre_scores_gemma":[0.9478102,0.00063004374,0.049428463,0.00009412303,0.0003742714,0.00014965665,0.00001659345,0.00004154815,0.0014551181],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991634,0.00007564442,0.00022773788,0.00018386467,0.00012050496,0.00022883758],"domain_scores_gemma":[0.9992919,0.00021484493,0.000106548505,0.00025107688,0.000060805763,0.000074807605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001265804,0.00011810609,0.00023388049,0.000058230635,0.000090490656,0.0000025865404,0.00016106422,0.00009633115,0.00019711687],"category_scores_gemma":[0.00037383096,0.00007351314,0.0000533941,0.00009527597,0.00014279019,0.000088172426,0.00009671128,0.00024400899,0.00009761727],"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":[0.000066984285,0.0019018651,0.010717084,0.00014010009,0.000024797047,0.00013666332,0.0029352228,0.0000014168407,0.0038375687,0.26059806,0.17995088,0.53968936],"study_design_scores_gemma":[0.000375959,0.00028507313,0.0010666529,0.000046850622,0.000015963966,0.00012682594,0.000098515084,0.00006813295,0.0026644222,0.5210065,0.47402033,0.00022473413],"about_ca_topic_score_codex":9.875363e-7,"about_ca_topic_score_gemma":0.000003940219,"teacher_disagreement_score":0.5394646,"about_ca_system_score_codex":0.00014056421,"about_ca_system_score_gemma":0.000068911526,"threshold_uncertainty_score":0.29977787},"labels":[],"label_agreement":null},{"id":"W2159655250","doi":"10.1093/ntr/ntq170","title":"Using Propensity Score Modeling to Minimize the Influence of Confounding Risks Related to Prenatal Tobacco Exposure","year":2010,"lang":"en","type":"article","venue":"Nicotine & Tobacco Research","topic":"Advanced Causal Inference Techniques","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":"University of Alberta","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Institute of Mental Health; National Institutes of Health","keywords":"Propensity score matching; Confounding; Covariate; Observational study; Selection bias; Medicine; Selection (genetic algorithm); Causal inference; Statistics; Demography; Mathematics; Internal medicine","score_opus":0.5025077699357767,"score_gpt":0.5157942981070719,"score_spread":0.013286528171295164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159655250","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":[0.9878963,0.000019498813,0.008276858,0.00045262274,0.000117822696,0.002123274,0.000016583224,0.00020999105,0.0008870517],"genre_scores_gemma":[0.91576725,0.000006753043,0.083657496,0.000072346586,0.000079469995,0.00010847807,0.0000031147856,0.00006861047,0.0002364912],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958372,0.00034951683,0.0008944705,0.00065008434,0.0013222283,0.00094651576],"domain_scores_gemma":[0.9948158,0.0011975253,0.00020402599,0.0015342031,0.0019371099,0.00031129486],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004573011,0.0003165873,0.000542322,0.00038917933,0.0003888416,0.00015315972,0.0013446165,0.00028283714,0.00009209847],"category_scores_gemma":[0.010719208,0.00023715799,0.00010344636,0.0013856214,0.00029575065,0.00044421022,0.0013533895,0.0019892412,0.00006708051],"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":[0.00046567214,0.00038594037,0.12509368,0.00024704597,0.00010876389,0.000026848638,0.0038619493,0.0360278,0.77236587,0.052309524,0.00054914464,0.008557776],"study_design_scores_gemma":[0.0028886062,0.0019116914,0.034928713,0.0048067844,0.00018940572,0.00023894709,0.0039631166,0.029715067,0.71359664,0.20420136,0.000698873,0.0028607876],"about_ca_topic_score_codex":0.0007852283,"about_ca_topic_score_gemma":0.0003780268,"teacher_disagreement_score":0.15189183,"about_ca_system_score_codex":0.000166953,"about_ca_system_score_gemma":0.0003309575,"threshold_uncertainty_score":0.9976139},"labels":[],"label_agreement":null},{"id":"W2159845576","doi":"10.1111/j.1541-0420.2009.01380.x","title":"Statistical Identifiability and the Surrogate Endpoint Problem, with Application to Vaccine Trials","year":2010,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":52,"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; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Identifiability; Surrogate endpoint; Computer science; Mathematics; Statistics; Econometrics; Computational biology; Medicine; Biology; Internal medicine","score_opus":0.10773568475868464,"score_gpt":0.4320993986802391,"score_spread":0.3243637139215545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159845576","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":[0.10770292,0.000016927184,0.8892772,0.00070952345,0.000047473666,0.0017430115,0.000067247805,0.00017964878,0.00025601554],"genre_scores_gemma":[0.6613379,0.000011276455,0.3382289,0.000050805338,0.00003990272,0.00025946504,0.000009110797,0.000016122429,0.000046527402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856544,0.00016433696,0.00049981405,0.00028695,0.00029516642,0.00018831628],"domain_scores_gemma":[0.99388623,0.005019386,0.00023146639,0.00052577135,0.00022491276,0.00011222633],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005415164,0.00014001077,0.0004008441,0.00034076528,0.000078364654,0.00008112501,0.00018986147,0.00007960399,0.000043648422],"category_scores_gemma":[0.012541904,0.00007681686,0.000029047564,0.0016241556,0.00013303572,0.00008764884,0.00010593776,0.0002069598,0.000012212564],"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":[0.00037219134,0.00016553965,0.0014887839,0.00012262624,0.000033710832,0.0000016979764,0.00020319388,6.3730994e-7,0.015865639,0.9263962,0.0011903088,0.054159503],"study_design_scores_gemma":[0.0013690109,0.00018932502,0.006204351,0.000012607831,0.000096984804,0.000010545697,0.00004466647,0.0001831933,0.015569319,0.9700447,0.0060395463,0.00023578336],"about_ca_topic_score_codex":0.00004205647,"about_ca_topic_score_gemma":0.00008455331,"teacher_disagreement_score":0.553635,"about_ca_system_score_codex":0.00003145905,"about_ca_system_score_gemma":0.00002649947,"threshold_uncertainty_score":0.9957759},"labels":[],"label_agreement":null},{"id":"W2159915215","doi":"10.1002/sim.3012","title":"Effect of exposure misclassification on the mean squared error of population attributable risk and prevented fraction estimates","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McMaster University","funders":"","keywords":"Statistics; Mean squared error; Attributable risk; Fraction (chemistry); Observational error; Population; Variance (accounting); Econometrics; Accuracy and precision; Mathematics; Medicine; Chemistry; Environmental health; Economics","score_opus":0.07347620403333992,"score_gpt":0.4348047438118476,"score_spread":0.36132853977850765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159915215","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":[0.49907443,0.000042231717,0.50018185,0.00004085501,0.0000337957,0.00043945198,0.000051012812,0.000027548818,0.000108850436],"genre_scores_gemma":[0.93930626,0.000041258467,0.060515754,0.0000059603212,0.000018379907,0.000014969833,0.000071446695,0.000012365552,0.000013587926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881476,0.00017298173,0.00050046894,0.00012789035,0.00026862728,0.0001152856],"domain_scores_gemma":[0.9926399,0.006487976,0.00050495996,0.00022812218,0.00011363172,0.000025393485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025012575,0.000113299095,0.00033300673,0.00011731935,0.000037771344,0.000002004074,0.000065357395,0.00006793692,0.000030273735],"category_scores_gemma":[0.008448125,0.000072271825,0.000011326406,0.00017967298,0.00013281543,0.000041784435,0.000012662559,0.00018336078,3.223971e-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":[0.001579141,0.00045525533,0.27435744,0.0027346625,0.0001103843,0.000011795228,0.0035938704,0.00025557465,0.06664604,0.53266364,0.0023631244,0.115229055],"study_design_scores_gemma":[0.0012502699,0.0033358692,0.14686874,0.0012436936,0.0002094663,0.0000033877914,0.0006029409,0.006619196,0.09706731,0.7426176,0.000022669172,0.00015882766],"about_ca_topic_score_codex":0.00019999768,"about_ca_topic_score_gemma":0.00011893232,"teacher_disagreement_score":0.44023186,"about_ca_system_score_codex":0.000061964776,"about_ca_system_score_gemma":0.0000060218026,"threshold_uncertainty_score":0.99990416},"labels":[],"label_agreement":null},{"id":"W2159968952","doi":"10.1002/sim.3243","title":"Discussion of ‘A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003’","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Institute for Clinical Evaluative Sciences","keywords":"Critical appraisal; Matching (statistics); Library science; Citation; Propensity score matching; Psychology; Operations research; Computer science; Medicine; Alternative medicine; Mathematics; Pathology; Surgery","score_opus":0.12894851090037607,"score_gpt":0.4533669741319672,"score_spread":0.3244184632315911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159968952","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":[0.5304736,0.0005043293,0.4640504,0.0032038277,0.00016715021,0.000641431,0.00019893129,0.000042118307,0.0007182053],"genre_scores_gemma":[0.8902272,0.0001914082,0.10937708,0.000057587557,0.00008022059,0.000010202655,0.000032142056,0.000012795821,0.000011349806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981646,0.0002066867,0.0006224179,0.00016380419,0.00066583155,0.00017666443],"domain_scores_gemma":[0.99557406,0.0038555476,0.00012275565,0.00022930383,0.00015391919,0.00006439177],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012082474,0.00013255727,0.0005084225,0.00012761082,0.000029888446,0.0000021050935,0.00020343046,0.000125124,0.00003346062],"category_scores_gemma":[0.019819997,0.000065244996,0.000009561496,0.00038778508,0.0009385181,0.000062942956,0.00008054409,0.0005781499,1.8885568e-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":[0.0000951887,0.00044562906,0.11672717,0.0025425586,0.000020187714,0.0012425793,0.043575745,9.655671e-7,0.000951992,0.8168668,0.006728148,0.010803007],"study_design_scores_gemma":[0.0008417381,0.00049648015,0.09199639,0.0036737565,0.000040748564,0.00015047133,0.0013442455,0.00015152586,0.00040547163,0.90066147,0.00007107785,0.00016661556],"about_ca_topic_score_codex":0.000059783168,"about_ca_topic_score_gemma":0.000062686,"teacher_disagreement_score":0.3597536,"about_ca_system_score_codex":0.000014938898,"about_ca_system_score_gemma":0.000061314364,"threshold_uncertainty_score":0.98843646},"labels":[],"label_agreement":null},{"id":"W2160044639","doi":"10.1111/j.1365-2753.2008.01053.x","title":"Are (the log‐odds of) hospital mortality rates normally distributed? Implications for studying variations in outcomes of medical care","year":2009,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Odds; Medicine; Odds ratio; Mortality rate; Health care; Demography; Emergency medicine; Logistic regression; Internal medicine; Political science","score_opus":0.4096959235620088,"score_gpt":0.6266666729180642,"score_spread":0.21697074935605543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160044639","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":[0.6957853,0.00018896502,0.26991165,0.032224953,0.00028859603,0.0013562851,0.000060762122,0.00001570621,0.00016778719],"genre_scores_gemma":[0.9671983,0.00010394734,0.03231915,0.00024618904,0.00007684563,0.000039419087,0.0000079297,0.0000073786628,8.533357e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99475914,0.00092575635,0.002989047,0.00014739111,0.0010369463,0.00014172844],"domain_scores_gemma":[0.9692132,0.022533512,0.004661413,0.00034176416,0.003183699,0.00006644901],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017992174,0.00011340961,0.0005698903,0.00011743723,0.000050431492,0.000018128649,0.00037505195,0.0001909584,0.000022530874],"category_scores_gemma":[0.21165715,0.000082640625,0.00019344556,0.00036738068,0.00009680015,0.0006160164,0.000047312013,0.00064600044,3.4772853e-7],"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":[0.00016134194,0.0037990708,0.8939738,0.00008112201,0.0002141583,0.0000057720335,0.0014221378,0.00075465726,0.000030357885,0.08705489,0.00048193746,0.012020723],"study_design_scores_gemma":[0.0010369836,0.00049553136,0.77758455,0.00012756487,0.00028437894,0.0000046440778,0.0023003076,0.000983824,0.00003253577,0.21704122,0.00003659021,0.000071888026],"about_ca_topic_score_codex":0.000013451192,"about_ca_topic_score_gemma":0.000095104115,"teacher_disagreement_score":0.27141297,"about_ca_system_score_codex":0.00015575618,"about_ca_system_score_gemma":0.0004589306,"threshold_uncertainty_score":0.7949834},"labels":[],"label_agreement":null},{"id":"W2160584604","doi":"10.1177/0165025410375912","title":"The effect of population heterogeneity on statistical power in the design and evaluation of interventions","year":2010,"lang":"en","type":"article","venue":"International Journal of Behavioral Development","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":"University of Manitoba; York University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Psychological intervention; Covariate; Population; Statistical power; Intervention (counseling); Psychology; Outcome (game theory); Statistics; Homogeneous; Power (physics); Econometrics; Demography; Mathematics; Sociology","score_opus":0.23233457129123217,"score_gpt":0.5249256250806007,"score_spread":0.29259105378936856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160584604","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":[0.9806487,0.000013499691,0.01875623,0.00006780468,0.00020893857,0.00027873332,0.0000036786344,0.00000303876,0.000019361982],"genre_scores_gemma":[0.9684017,0.0000038611774,0.031549934,0.0000041880267,0.000010247762,0.000020147623,0.000003392414,0.0000049279283,0.000001635279],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998066,0.00033353266,0.00065156963,0.00006132748,0.0008227368,0.00006480945],"domain_scores_gemma":[0.99806046,0.0009026449,0.0004909211,0.00008996366,0.0004371793,0.000018810564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004205982,0.00007650969,0.000141757,0.0001164312,0.000030269859,0.000020213454,0.00024411135,0.000038723912,0.000020038166],"category_scores_gemma":[0.0005724171,0.00004256105,0.000053016032,0.00004672137,0.000061280334,0.00009202441,0.000033288386,0.00020568968,3.149287e-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":[0.0019618035,0.0022925637,0.25021917,0.000111801186,0.0003875965,0.000048511814,0.0052377996,0.0006611342,0.041667826,0.07972144,0.0005078925,0.6171825],"study_design_scores_gemma":[0.0015657699,0.0017639213,0.7942953,0.0005571025,0.00016532734,0.00010479321,0.00019124101,0.0003673304,0.12648267,0.07428207,0.00006467951,0.00015976593],"about_ca_topic_score_codex":0.000010937155,"about_ca_topic_score_gemma":0.00008171977,"teacher_disagreement_score":0.6170227,"about_ca_system_score_codex":0.00008550097,"about_ca_system_score_gemma":0.00004430253,"threshold_uncertainty_score":0.17355892},"labels":[],"label_agreement":null},{"id":"W2160704894","doi":"10.1093/aje/kwq224","title":"Statistical Criteria for Selecting the Optimal Number of Untreated Subjects Matched to Each Treated Subject When Using Many-to-One Matching on the Propensity Score","year":2010,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":667,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Propensity score matching; Matching (statistics); Statistics; Estimator; Mathematics; Average treatment effect; Mean squared error; Observational study; Medicine","score_opus":0.26098998981920396,"score_gpt":0.46223968140121985,"score_spread":0.2012496915820159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160704894","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":[0.6153524,0.000001993604,0.3826931,0.001322681,0.000056984663,0.00047498272,0.000017694318,0.000028208802,0.0000519209],"genre_scores_gemma":[0.5916402,0.0000017193387,0.40753457,0.0006674203,0.00009673699,0.000014873535,0.0000018127927,0.00003357015,0.000009093868],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99628544,0.0014239178,0.0012156842,0.00029433714,0.00018747666,0.00059312413],"domain_scores_gemma":[0.9803085,0.017104879,0.0013850664,0.00045529078,0.00055689906,0.00018941781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058729537,0.0002873203,0.0013219386,0.00013101948,0.00017786854,0.000020210418,0.00050858373,0.00010040988,0.00010837597],"category_scores_gemma":[0.020346113,0.000161861,0.0001474524,0.0003321702,0.00044851014,0.000090750174,0.00011156052,0.0008208113,0.0000046318455],"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":[0.0066862768,0.00070226257,0.119004376,0.00017875998,0.0010559016,0.00006067632,0.008694569,0.0010971966,0.5853264,0.2574809,0.003897486,0.015815234],"study_design_scores_gemma":[0.0012831182,0.0077430774,0.028619846,0.0009775439,0.0007506247,0.0018560741,0.0025651723,0.003578674,0.091458865,0.85988486,0.00021044358,0.0010716801],"about_ca_topic_score_codex":0.0006456391,"about_ca_topic_score_gemma":0.000085560176,"teacher_disagreement_score":0.602404,"about_ca_system_score_codex":0.000110620946,"about_ca_system_score_gemma":0.00011728739,"threshold_uncertainty_score":0.9879059},"labels":[],"label_agreement":null},{"id":"W2161040745","doi":"10.1002/sim.2073","title":"Using generalized additive models to reduce residual confounding","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":103,"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 General Hospital","funders":"","keywords":"Covariate; Confounding; Statistics; Logistic regression; Mathematics; Parametric statistics; Context (archaeology); Generalized linear model; Econometrics; Linear regression","score_opus":0.3116101435216381,"score_gpt":0.5048658643751648,"score_spread":0.19325572085352666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161040745","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":[0.02462987,0.00003233004,0.9711519,0.00030294602,0.00016849113,0.0004518037,0.00015219956,0.00012824421,0.0029822534],"genre_scores_gemma":[0.13183816,0.000044589575,0.86731184,0.00035910023,0.00020873822,0.000035023328,0.00003456514,0.000039005146,0.00012897384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838525,0.00006805241,0.0005174557,0.00028216967,0.00039720937,0.00034986986],"domain_scores_gemma":[0.99861205,0.00063138426,0.00014215962,0.00029054942,0.00019240691,0.00013145384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056639174,0.00019953104,0.00043292082,0.00024029127,0.000066403576,0.000010779456,0.00017443432,0.00007740207,0.00012696002],"category_scores_gemma":[0.0024022306,0.00018193117,0.000012382848,0.0003007567,0.00018543174,0.00011077431,0.00006827216,0.00026171506,0.0000056719173],"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":[0.0000384617,0.000028120421,0.000003828779,0.000030218029,0.000011487801,0.00009646357,0.0026342492,0.0019469938,0.008514339,0.9826795,0.0029734431,0.0010428885],"study_design_scores_gemma":[0.0009825913,0.0001741059,0.000011255109,0.00058121997,0.000030409275,0.00001739374,0.0007267386,0.0016542365,0.007301025,0.9882061,0.00011469425,0.00020024058],"about_ca_topic_score_codex":0.00039670483,"about_ca_topic_score_gemma":0.00018239395,"teacher_disagreement_score":0.10720828,"about_ca_system_score_codex":0.00044035516,"about_ca_system_score_gemma":0.00011877996,"threshold_uncertainty_score":0.7418938},"labels":[],"label_agreement":null},{"id":"W2162163884","doi":"10.1136/jech.55.7.508","title":"A heuristic approach to the formulas for population attributable fraction","year":2001,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":289,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Confounding; Fraction (chemistry); Attributable risk; Medicine; Heuristic; Population; Representation (politics); Limit (mathematics); USable; Econometrics; Statistics; Public health; Distribution (mathematics); Estimation; Environmental health; Computer science; Artificial intelligence; Mathematics; Pathology","score_opus":0.5047912795363017,"score_gpt":0.5411379398954912,"score_spread":0.03634666035918954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162163884","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":[0.06435415,0.0002296503,0.9269872,0.0071883956,0.00012568213,0.00063543924,0.000009183831,0.000051536477,0.00041879356],"genre_scores_gemma":[0.61310345,0.0003078964,0.3823632,0.0038827967,0.00020946158,0.0000408525,0.000022979702,0.00002072404,0.00004866477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99541974,0.0026022862,0.001312354,0.000107372594,0.0001205267,0.00043770426],"domain_scores_gemma":[0.9837133,0.01359517,0.0015266633,0.000643639,0.00034004598,0.00018115838],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0178912,0.00014703463,0.0008840103,0.00014650637,0.0006684051,0.000008284289,0.0004508066,0.00013523601,0.000006628159],"category_scores_gemma":[0.02809267,0.00009881703,0.00015141263,0.00021361563,0.000045305896,0.00020965945,0.0000776244,0.0012262703,0.0000022200304],"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":[0.0012950287,0.0023223478,0.09412286,0.0009275347,0.00026629804,0.0000020368889,0.0022261364,0.00660258,0.00009871135,0.635472,0.19031507,0.0663494],"study_design_scores_gemma":[0.00032051856,0.0012396957,0.018119197,0.00013939023,0.000034347664,0.00020666498,0.0004466955,0.001865038,0.00001079991,0.9412343,0.03626934,0.00011404032],"about_ca_topic_score_codex":0.0013325086,"about_ca_topic_score_gemma":0.0007199256,"teacher_disagreement_score":0.54874927,"about_ca_system_score_codex":0.0005320677,"about_ca_system_score_gemma":0.00012683056,"threshold_uncertainty_score":0.98009413},"labels":[],"label_agreement":null},{"id":"W2163206453","doi":"10.1111/biom.12271","title":"Discussion of “On Bayesian Estimation of Marginal Structural Models”","year":2015,"lang":"en","type":"letter","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Bayesian probability; Bayesian inference; Posterior probability; Outcome (game theory); Computer science; Inference; Context (archaeology); Model selection; Econometrics; Statistics; Mathematics; Artificial intelligence; Mathematical economics","score_opus":0.21176795249765404,"score_gpt":0.4128808229036175,"score_spread":0.20111287040596346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163206453","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":[0.0014393444,0.00015164317,0.96731645,0.025553858,0.00048654623,0.00093550683,0.0006568832,0.00032002747,0.0031397133],"genre_scores_gemma":[0.14694749,0.00005647225,0.8412169,0.0079739075,0.0007906436,0.00004762141,0.00094409863,0.00023421804,0.0017886041],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976814,0.000077076875,0.0006592191,0.00028587205,0.0010340428,0.00026239018],"domain_scores_gemma":[0.9975829,0.00042070376,0.00092560315,0.00064321543,0.00037517585,0.00005239598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035342242,0.00031850114,0.00065544504,0.0023646636,0.000022823158,0.0000136574545,0.00040439077,0.0007344379,0.000034074197],"category_scores_gemma":[0.0011007218,0.00020754397,0.00012900973,0.0020028153,0.00012465825,0.00017472522,0.00011037519,0.0006149102,0.0000026883263],"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":[0.00005127277,0.0000788923,0.00002113973,0.0020057752,0.00006514446,0.000027309368,0.00018557887,0.00033352108,0.000300127,0.019865219,0.9351155,0.041950528],"study_design_scores_gemma":[0.00024985723,0.0005104238,0.000013438791,0.0004613898,0.00009886632,0.000008293622,0.000017878232,0.022764402,0.0041083097,0.96394575,0.00740139,0.0004199831],"about_ca_topic_score_codex":0.000012887173,"about_ca_topic_score_gemma":4.018703e-7,"teacher_disagreement_score":0.94408053,"about_ca_system_score_codex":0.00021116264,"about_ca_system_score_gemma":0.00009415484,"threshold_uncertainty_score":0.84633976},"labels":[],"label_agreement":null},{"id":"W2164404559","doi":"10.1136/bmjopen-2014-005297","title":"Interpreting trial results following use of different intention-to-treat approaches for preventing attrition bias: a meta-epidemiological study protocol","year":2014,"lang":"en","type":"article","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"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":"Parker Institute for Cancer Immunotherapy; Oak Foundation","keywords":"Medicine; Protocol (science); Attrition; Epidemiology; Selection bias; Publication bias; Alternative medicine; Meta-analysis; Environmental health; Pathology","score_opus":0.8468178363736624,"score_gpt":0.5865171235954936,"score_spread":0.2603007127781688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164404559","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13026954,3.3986635e-7,0.28690958,0.00013637102,0.00005070685,0.58199924,0.000019154768,0.000161063,0.00045401306],"genre_scores_gemma":[0.33645946,3.5653517e-8,0.15157378,0.000029031713,0.00003961213,0.51166457,0.000011788148,0.000026458216,0.00019527705],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957054,0.0014763727,0.0016654468,0.00056142034,0.00028128986,0.00031005082],"domain_scores_gemma":[0.9922353,0.005903223,0.0009811192,0.0006703017,0.000130256,0.00007979857],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0086612385,0.0003238663,0.001413947,0.0001134771,0.00011213154,0.0001432549,0.00056237594,0.00011561802,0.000011715375],"category_scores_gemma":[0.04870853,0.00020686019,0.00054236787,0.00014383285,0.000029693794,0.0004133851,0.00082698365,0.00014417229,0.0000013221922],"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":[0.55674386,0.042335205,0.039098985,0.010475752,0.011903017,0.000035553283,0.01893378,0.00043485875,0.010945414,0.17075813,0.018149382,0.1201861],"study_design_scores_gemma":[0.14563084,0.03836998,0.0017616124,0.0077164234,0.005774295,0.000012165874,0.0048843385,0.018242978,0.030854527,0.7425047,0.0013926477,0.0028555149],"about_ca_topic_score_codex":0.00005373886,"about_ca_topic_score_gemma":0.00007925493,"teacher_disagreement_score":0.5717466,"about_ca_system_score_codex":0.000068471534,"about_ca_system_score_gemma":0.00002005343,"threshold_uncertainty_score":0.95930463},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2164498941","doi":"10.1002/sim.2580","title":"A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1134,"is_retracted":false,"has_abstract":true,"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":"Propensity score matching; Confounding; Observational study; Outcome (game theory); Statistics; Matching (statistics); Medicine; Average treatment effect; Variables; Econometrics; Mathematics","score_opus":0.20433493146265783,"score_gpt":0.40639983108407973,"score_spread":0.2020648996214219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164498941","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":[0.9213251,0.000050990846,0.07656187,0.00003576731,0.00002073529,0.0016865195,0.00017516842,0.0000431576,0.00010071483],"genre_scores_gemma":[0.98680407,0.000005662152,0.013075461,0.000005283802,0.000016126805,0.000048040885,0.000008825689,0.00001791994,0.000018586725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99790883,0.00027424892,0.00086632,0.00027802837,0.0004722729,0.00020029886],"domain_scores_gemma":[0.9976801,0.0010334514,0.0003561664,0.0005111599,0.0003652949,0.00005382825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055361516,0.00022124,0.0010504442,0.0000942553,0.000040097548,0.0000042505644,0.00020798844,0.00006638189,0.0000050348162],"category_scores_gemma":[0.0013395334,0.00013472083,0.00001687129,0.0003598006,0.00030181766,0.000037096033,0.00010911928,0.00020485187,5.2703072e-8],"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":[0.0001052001,0.00063173217,0.98031086,0.00032172006,0.00004533335,0.000004212744,0.0031102516,0.00017142517,0.0058745127,0.008849548,0.00023459565,0.0003405868],"study_design_scores_gemma":[0.0014005833,0.00096096337,0.68677014,0.00074221875,0.00023533191,6.8247135e-7,0.0005533664,0.0037595704,0.010285085,0.29513085,6.1446383e-7,0.00016060237],"about_ca_topic_score_codex":0.0042367293,"about_ca_topic_score_gemma":0.003110834,"teacher_disagreement_score":0.29354075,"about_ca_system_score_codex":0.000109178196,"about_ca_system_score_gemma":0.000032588752,"threshold_uncertainty_score":0.6404696},"labels":[],"label_agreement":null},{"id":"W2164621115","doi":"10.1186/s13104-015-1042-y","title":"Intracluster correlation coefficients for sample size calculations related to cardiovascular disease prevention and management in primary care practices","year":2015,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa; Bruyère","funders":"Canadian Institutes of Health Research; Pfizer Canada; Pfizer","keywords":"Medicine; Dyslipidemia; Rurality; Sample size determination; Kidney disease; Emergency medicine; Family medicine; Disease; Demography; Internal medicine; Rural area; Statistics","score_opus":0.4115931239208963,"score_gpt":0.5210959032071013,"score_spread":0.109502779286205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164621115","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":[0.26438054,0.00055390137,0.7288123,0.00021812739,0.000059886108,0.005175677,0.00004106599,0.00013975424,0.00061876],"genre_scores_gemma":[0.69590724,0.000052448548,0.30279607,0.000012122366,0.000022875325,0.0008813821,0.000079113815,0.000029028552,0.00021969448],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998034,0.00037010308,0.00028320597,0.00035374903,0.00066272536,0.00029623983],"domain_scores_gemma":[0.994714,0.00410677,0.000092479044,0.0004226134,0.00047868845,0.00018542806],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021906598,0.000111350615,0.00018140688,0.0002355026,0.00011558876,0.0000702842,0.000127202,0.00007149149,0.0000043490268],"category_scores_gemma":[0.021584757,0.00010790578,0.000065332075,0.00041861195,0.00005908744,0.00032648107,0.00020773939,0.00016819898,0.000006288017],"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":[0.0045259004,0.0028086689,0.3295267,0.013121533,0.0011770256,0.000099203426,0.02152138,0.12450268,0.00051097915,0.19334847,0.003332368,0.3055251],"study_design_scores_gemma":[0.0040421,0.00070496625,0.10887617,0.0011459108,0.00033781436,0.0000042349425,0.0045809145,0.03292661,0.00035659724,0.83875304,0.007552464,0.000719183],"about_ca_topic_score_codex":0.00009641665,"about_ca_topic_score_gemma":0.00011950145,"teacher_disagreement_score":0.6454046,"about_ca_system_score_codex":0.00037712906,"about_ca_system_score_gemma":0.00012299609,"threshold_uncertainty_score":0.98665684},"labels":[],"label_agreement":null},{"id":"W2168014332","doi":"10.1186/1742-5573-6-4","title":"Identifiability, exchangeability and confounding revisited","year":2009,"lang":"en","type":"article","venue":"Epidemiologic Perspectives & Innovations","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":158,"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":"National Institute of Allergy and Infectious Diseases","keywords":"Confounding; Identifiability; Perspective (graphical); Epidemiology; Quarter (Canadian coin); Medicine; Data science; Computer science; History; Pathology; Artificial intelligence","score_opus":0.25201067295649354,"score_gpt":0.4872205454819779,"score_spread":0.23520987252548436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168014332","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":[0.7223822,0.000593617,0.2457087,0.009103835,0.00007360725,0.0010029428,0.000021023932,0.0013449583,0.019769127],"genre_scores_gemma":[0.90634173,0.000105718515,0.09265735,0.0005716861,0.000086938344,0.000047265123,0.0000096255635,0.000009530108,0.00017014371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979544,0.00034714973,0.00065912446,0.00056875596,0.00013415751,0.00033639418],"domain_scores_gemma":[0.9962444,0.0023338224,0.00030684148,0.000565688,0.00048404685,0.00006524505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031715117,0.00022950272,0.0005027471,0.0001992307,0.00026009505,0.00003937793,0.00019363035,0.00012197596,0.00014492874],"category_scores_gemma":[0.028231407,0.00019749641,0.000069219015,0.0008028012,0.00037110402,0.00036332267,0.00008717755,0.00037324175,0.0000057132133],"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":[0.00000651252,0.00010626937,0.00632236,0.000016651346,0.000013664238,0.0000016372197,0.00075384206,7.6508644e-7,0.002909414,0.9868506,0.0013307865,0.0016874705],"study_design_scores_gemma":[0.0001038503,0.000113092006,0.074269444,0.000037473837,0.000014556475,0.000013207753,0.0014466607,0.00006303574,0.00021525148,0.9232363,0.00029151991,0.00019557905],"about_ca_topic_score_codex":0.000014241097,"about_ca_topic_score_gemma":0.0000039875413,"teacher_disagreement_score":0.18395956,"about_ca_system_score_codex":0.00025217404,"about_ca_system_score_gemma":0.00002799354,"threshold_uncertainty_score":0.9799542},"labels":[],"label_agreement":null},{"id":"W2168082315","doi":"10.1002/sim.6020","title":"Marginal structural models for skewed outcomes: identifying causal relationships in health care utilization","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Institut National de Santé Publique du Québec; Sante Montreal; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Negative binomial distribution; Causal inference; Generalized linear model; Marginal structural model; Inference; Marginal model; Emergency department; Propensity score matching; Econometrics; Poisson distribution; Psychological intervention; Statistics; Baseline (sea); Generalized linear mixed model; Robustness (evolution); Count data; Medicine; Computer science; Mathematics","score_opus":0.3202027902674543,"score_gpt":0.4968382609247534,"score_spread":0.17663547065729912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168082315","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":[0.009649905,0.0001702917,0.98759514,0.0005866741,0.00016574057,0.0013811509,0.00011392846,0.00009764819,0.00023950031],"genre_scores_gemma":[0.5277285,0.000035917896,0.47160044,0.00010679208,0.000032083295,0.00016668993,0.00021140653,0.00002671609,0.00009147762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980972,0.00015239742,0.0008445088,0.0002529872,0.00030706782,0.00034588654],"domain_scores_gemma":[0.997546,0.0016021187,0.00026841363,0.0002528939,0.00024760643,0.000082925144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066669617,0.00019053655,0.00045579122,0.0002926702,0.00010081748,0.000016394628,0.00014233297,0.000091909125,0.000095473675],"category_scores_gemma":[0.0032569796,0.00016440329,0.000016753283,0.00024320824,0.00010394723,0.0002495614,0.00003377474,0.0003575879,0.0000024959982],"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":[0.000015659944,0.000017833983,0.010550478,0.00077702035,0.000008670732,0.0000053109197,0.0078046443,0.00034609364,0.000031449268,0.97321385,0.0027683768,0.004460609],"study_design_scores_gemma":[0.0008571559,0.00011817773,0.013633044,0.00036312168,0.0000100200195,0.000002314722,0.0036229189,0.034715746,0.000015655689,0.9464912,0.000025891262,0.00014479707],"about_ca_topic_score_codex":0.0005518526,"about_ca_topic_score_gemma":0.0018506531,"teacher_disagreement_score":0.51807857,"about_ca_system_score_codex":0.00041839486,"about_ca_system_score_gemma":0.00009192228,"threshold_uncertainty_score":0.67041713},"labels":[],"label_agreement":null},{"id":"W2168397874","doi":"10.1177/0002716209351525","title":"Strategies for Dealing with the Problem of Non-overlapping Units of Assignment and Outcome Measurement in Field Experiments","year":2010,"lang":"en","type":"article","venue":"The Annals of the American Academy of Political and Social Science","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":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Outcome (game theory); Field (mathematics); Unit (ring theory); Interpretation (philosophy); Operations research; Computer science; Contrast (vision); Measure (data warehouse); Units of measurement; Econometrics; Mathematical economics; Data mining; Mathematics; Artificial intelligence; Mathematics education; Physics","score_opus":0.3526738755658821,"score_gpt":0.4957994352009775,"score_spread":0.14312555963509543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168397874","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":[0.9893058,0.000012329863,0.0027284105,0.0069140317,0.0000038890626,0.00030713278,0.0000053132817,0.0000039929073,0.0007191202],"genre_scores_gemma":[0.9963363,0.0000061867595,0.0032407325,0.00038734594,0.000009539222,0.000012828085,1.5860785e-8,0.0000032635232,0.0000038019734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990053,0.000039693194,0.00026238943,0.0000936773,0.00038262218,0.00021627592],"domain_scores_gemma":[0.9990206,0.00040634428,0.00034000693,0.00008158175,0.00012064239,0.000030842813],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001275464,0.00007259065,0.00024482407,0.000024213607,0.000103444596,0.0000076851775,0.00035503146,0.000025111294,9.057219e-7],"category_scores_gemma":[0.00017934688,0.000034362016,0.000026866603,0.00016859444,0.0028868788,0.00008052571,0.00012803324,0.00015369088,8.431626e-9],"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":[0.000024950312,0.00002213972,0.00067673175,0.00004901744,0.000008215233,1.2313805e-8,0.0014457267,8.677774e-7,0.117978565,0.87857264,0.000006866043,0.0012142638],"study_design_scores_gemma":[0.00012750931,0.00025981682,0.014311467,0.00010476313,0.000019402334,6.2393343e-7,0.008865466,0.00006573963,0.5092641,0.4668794,0.000021909274,0.0000797661],"about_ca_topic_score_codex":0.0002927158,"about_ca_topic_score_gemma":0.000012191395,"teacher_disagreement_score":0.41169325,"about_ca_system_score_codex":0.000008291012,"about_ca_system_score_gemma":0.00006449572,"threshold_uncertainty_score":0.99982667},"labels":[],"label_agreement":null},{"id":"W2169425545","doi":"10.1002/sim.6276","title":"The use of bootstrapping when using propensity‐score matching without replacement: a simulation study","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Services and Policy Research; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Bootstrapping (finance); Statistics; Resampling; Standard error; Matching (statistics); Confidence interval; Sample size determination; Standard deviation; Sampling distribution; Observational study; Econometrics; Mathematics","score_opus":0.38854138632668395,"score_gpt":0.46673056535998564,"score_spread":0.07818917903330169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169425545","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":[0.31987023,0.0000061196915,0.67930335,0.000026313342,0.000048531776,0.0006330695,0.000004784818,0.0000396364,0.00006794722],"genre_scores_gemma":[0.7771273,0.000005420867,0.22270605,0.000033700395,0.000040195144,0.000011784634,0.000004000333,0.000021405865,0.00005013562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982763,0.00024544442,0.00066654215,0.00019718845,0.0004172755,0.00019727722],"domain_scores_gemma":[0.995978,0.0029356012,0.0004056042,0.00044436674,0.00020079683,0.00003562573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001554607,0.00014870871,0.00037340203,0.00009781491,0.000114230155,0.000020143661,0.00014278518,0.000037873004,0.000014553941],"category_scores_gemma":[0.0053917686,0.00009968238,0.000010903054,0.00012532446,0.0001730461,0.00011642481,0.0000767536,0.00022750636,3.8824962e-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":[0.0010276241,0.0010832993,0.26446727,0.0013212413,0.00031423292,0.00006763865,0.054051206,0.058833282,0.01238253,0.5664105,0.0016546133,0.038386587],"study_design_scores_gemma":[0.0010021781,0.00071802764,0.0042902287,0.00088823575,0.000103881386,0.0000036604122,0.0012680774,0.18751277,0.00018580774,0.8036195,0.00021564313,0.00019194983],"about_ca_topic_score_codex":0.00023055822,"about_ca_topic_score_gemma":0.0002849462,"teacher_disagreement_score":0.45725706,"about_ca_system_score_codex":0.00007613562,"about_ca_system_score_gemma":0.000025302415,"threshold_uncertainty_score":0.64548403},"labels":[],"label_agreement":null},{"id":"W2169900945","doi":"10.1002/sim.2733","title":"Accounting for expected attrition in the planning of community intervention trials","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Robarts Clinical Trials; Western University; Ottawa Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Attrition; Sample size determination; Statistics; Randomization; Cohort; Demography; Population; Cluster randomised controlled trial; Sample (material); Cluster (spacecraft); Psychological intervention; Standard error; Econometrics; Medicine; Randomized controlled trial; Mathematics; Computer science; Environmental health; Surgery","score_opus":0.39420011802620225,"score_gpt":0.5438528487911372,"score_spread":0.1496527307649349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169900945","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":[0.14355926,0.000075915865,0.8551678,0.00010663973,0.000050440984,0.0005597048,0.0000679499,0.000028700204,0.0003835768],"genre_scores_gemma":[0.8455027,0.0000053996814,0.1541224,0.000031711577,0.00007039058,0.00009633086,0.00015187403,0.0000093746185,0.000009870144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816483,0.00058521517,0.0008919515,0.00005978696,0.00017734092,0.000120859026],"domain_scores_gemma":[0.9895637,0.009725047,0.0004154799,0.00017729643,0.0001119944,0.0000064803044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062972116,0.000083283994,0.00039515604,0.00015990608,0.0000422721,0.0000050918898,0.00015342719,0.00005010928,0.000019036574],"category_scores_gemma":[0.01397869,0.00005925373,0.000023478418,0.00018909073,0.00009816399,0.000050365914,0.000019137473,0.0002591323,1.1175649e-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":[0.00021972426,0.00067850976,0.005497543,0.0013447335,0.000019698453,0.000012059555,0.011205573,0.000053754156,0.00952422,0.9361147,0.022615956,0.012713517],"study_design_scores_gemma":[0.00121013,0.00021468951,0.0061284713,0.00085966353,0.000025200165,0.0000016039638,0.005225524,0.00032619148,0.001157003,0.9847501,0.000045080644,0.000056337663],"about_ca_topic_score_codex":0.00051953073,"about_ca_topic_score_gemma":0.00048177174,"teacher_disagreement_score":0.7019434,"about_ca_system_score_codex":0.000052684318,"about_ca_system_score_gemma":0.000007925539,"threshold_uncertainty_score":0.994327},"labels":[],"label_agreement":null},{"id":"W2170832176","doi":"10.20982/tqmp.08.2.p070","title":"Using partial components to restore and use the concurrent validity of the Index of Readiness","year":2012,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Index (typography); Concurrent validity; Computer science; Psychology; Reliability engineering; Statistics; Mathematics; Engineering; Programming language; Psychometrics; Internal consistency","score_opus":0.8114562747743347,"score_gpt":0.6701349316774364,"score_spread":0.14132134309689826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170832176","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":[0.438165,0.000050374463,0.5592674,0.00006143739,0.0017325932,0.00066983444,0.000026313975,0.000010593934,0.000016444208],"genre_scores_gemma":[0.46911588,0.000007838967,0.53067285,0.000033260352,0.00008551496,0.00006448757,7.803612e-7,0.000014431838,0.0000049972873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99623233,0.0025289904,0.00064684864,0.00019912311,0.0001313672,0.00026131902],"domain_scores_gemma":[0.98970646,0.009064765,0.0005399794,0.00043349375,0.00021226099,0.000043039763],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0055503,0.00015402935,0.0005502155,0.00009226844,0.00005581865,0.000005783468,0.00026565802,0.000120293,0.0000050528815],"category_scores_gemma":[0.010930322,0.000095019044,0.00007202657,0.0002602931,0.00046417283,0.0001341678,0.00012922412,0.00016346524,1.8461736e-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":[0.0002710576,0.00021413276,0.031424567,0.000085142885,0.0000395286,1.1191411e-7,0.0034917938,0.000007991546,0.18544778,0.776757,0.0001985222,0.0020623873],"study_design_scores_gemma":[0.0011671786,0.0005575062,0.05328914,0.00024159497,0.00014437453,0.0000081847475,0.00041762012,0.00042182492,0.1677012,0.7699177,0.005821784,0.00031186835],"about_ca_topic_score_codex":0.00006229198,"about_ca_topic_score_gemma":0.000011884073,"teacher_disagreement_score":0.03095085,"about_ca_system_score_codex":0.00003988006,"about_ca_system_score_gemma":0.00002040657,"threshold_uncertainty_score":0.99740106},"labels":[],"label_agreement":null},{"id":"W2171478866","doi":"10.1111/ppe.12073","title":"Accuracy Loss Due to Selection Bias in Cohort Studies with Left Truncation","year":2013,"lang":"en","type":"article","venue":"Paediatric and Perinatal Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":110,"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; McGill University Health Centre","funders":"National Institutes of Health","keywords":"Truncation (statistics); Statistics; Medicine; Censoring (clinical trials); Variable (mathematics); Mathematics; Econometrics; Mathematical analysis","score_opus":0.17765060372843616,"score_gpt":0.42979341336149796,"score_spread":0.2521428096330618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171478866","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":[0.96250975,0.00095189677,0.033936165,0.0014985034,0.00005557108,0.00070191326,0.00000376992,0.00014663702,0.00019577905],"genre_scores_gemma":[0.9380657,0.001337344,0.059715305,0.0003840983,0.000104513296,0.00024354104,0.0000051706816,0.000018002367,0.00012634328],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985171,0.0002912373,0.00044470184,0.0003465215,0.00007178705,0.00032865672],"domain_scores_gemma":[0.99273115,0.0066900607,0.00018734885,0.00015873002,0.00014393785,0.00008876843],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011555671,0.00018789216,0.00055682723,0.00018477191,0.00006199618,0.0000073317956,0.0000764944,0.00012732105,0.000060624745],"category_scores_gemma":[0.012545001,0.00013905673,0.000026277652,0.000263298,0.000110004235,0.0002543208,0.00008507831,0.00022130014,0.00003281054],"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":[0.000043354303,0.00003393254,0.9481469,0.00016709582,0.00004766312,0.000011862342,0.0006580652,0.00005222031,0.000049600105,0.03137759,0.0016645006,0.017747257],"study_design_scores_gemma":[0.00041409614,0.00073410646,0.49833846,0.00005821192,0.000048836166,0.00039526253,0.00043118597,0.0008394802,0.00028213655,0.4961126,0.0018715087,0.0004741048],"about_ca_topic_score_codex":0.0003365677,"about_ca_topic_score_gemma":0.00020393677,"teacher_disagreement_score":0.46473503,"about_ca_system_score_codex":0.00009949441,"about_ca_system_score_gemma":0.000029492136,"threshold_uncertainty_score":0.9957728},"labels":[],"label_agreement":null},{"id":"W2171914249","doi":"10.1027/1614-2241/a000041","title":"An Improved Model for Evaluating Change in Randomized Pretest, Posttest, Follow-Up Designs","year":2011,"lang":"en","type":"article","venue":"Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"York University","funders":"","keywords":"Treatment and control groups; Research design; Monte Carlo method; Randomized controlled trial; Randomized experiment; Treatment effect; Computer science; Psychology; Mathematics education; Statistics; Mathematics; Medicine","score_opus":0.8674030637400533,"score_gpt":0.5803188037493868,"score_spread":0.28708425999066645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171914249","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":[0.058230028,0.000056894267,0.9377424,0.000042353706,0.00012145474,0.0031638958,0.00001032868,0.00033448578,0.00029815643],"genre_scores_gemma":[0.13895085,0.000009193798,0.8572371,0.00025785793,0.000045724228,0.003312486,0.000007613034,0.000061897685,0.00011726277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951114,0.0031056777,0.0006955754,0.0004575245,0.00011018079,0.000519657],"domain_scores_gemma":[0.9880812,0.010729972,0.00035578955,0.00054331427,0.00020678733,0.00008291464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013419516,0.00026851604,0.0011637508,0.00021341463,0.000056333145,0.000009516426,0.0003468302,0.0002845224,0.00006018556],"category_scores_gemma":[0.01987813,0.00023412019,0.00017652444,0.00013641462,0.00013389197,0.00028114155,0.00007115976,0.00023291913,0.0000017139885],"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":[0.07496352,0.0005553251,0.0005048416,0.000401363,0.00018539376,0.000011082412,0.054166075,0.00006615729,0.39477432,0.4008765,0.00009144522,0.07340399],"study_design_scores_gemma":[0.017240375,0.00039369075,0.00001427324,0.000022484806,0.000074112846,0.000004155736,0.00005906547,0.3422239,0.018578254,0.62121147,5.7731125e-7,0.00017763318],"about_ca_topic_score_codex":0.00015749726,"about_ca_topic_score_gemma":0.00020396298,"teacher_disagreement_score":0.37619606,"about_ca_system_score_codex":0.00006853769,"about_ca_system_score_gemma":0.00007013648,"threshold_uncertainty_score":0.98837787},"labels":[],"label_agreement":null},{"id":"W2172095467","doi":"10.1002/sim.2663","title":"On estimating treatment effects under non‐compliance in randomized clinical trials: are intent‐to‐treat or instrumental variables analyses perfect solutions?","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":46,"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":"U.S. Food and Drug Administration; Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Instrumental variable; Estimator; Protocol (science); Econometrics; Estimation; Randomized controlled trial; Average treatment effect; Statistics; Computer science; Medicine; Mathematics; Economics; Surgery; Alternative medicine","score_opus":0.5017714453619644,"score_gpt":0.591935176063639,"score_spread":0.0901637307016746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172095467","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":[0.031147245,0.00009740709,0.9650119,0.0002904267,0.0003438477,0.0022050925,0.00008671127,0.00011621967,0.0007011769],"genre_scores_gemma":[0.4517892,0.00008745116,0.5470322,0.0001839411,0.00019760887,0.0004320075,0.00006623706,0.00003693964,0.00017445204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944526,0.0020564443,0.0021571596,0.0004943327,0.00038178364,0.00045766396],"domain_scores_gemma":[0.94734854,0.051411115,0.0006509892,0.00038297745,0.00009537979,0.00011100581],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0067505664,0.0004092062,0.0027133485,0.00042472003,0.000087416076,0.00002254219,0.0001778023,0.00013663886,0.00012989627],"category_scores_gemma":[0.056348767,0.0002559892,0.00011686396,0.00045744685,0.0003654315,0.0000679058,0.000064358544,0.00036025976,0.000012210398],"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":[0.0572212,0.0058817146,0.004442085,0.0019396357,0.00064353045,0.0012738425,0.0016379405,0.009429422,0.002923042,0.7617544,0.02137059,0.13148262],"study_design_scores_gemma":[0.0835676,0.001779157,0.0007648306,0.0047692396,0.00043532663,0.000011853082,0.00044024407,0.07647093,0.00074826996,0.8306346,0.00000737662,0.0003705877],"about_ca_topic_score_codex":0.00085094635,"about_ca_topic_score_gemma":0.0009769944,"teacher_disagreement_score":0.42064196,"about_ca_system_score_codex":0.0006811937,"about_ca_system_score_gemma":0.00008908296,"threshold_uncertainty_score":0.9999892},"labels":[],"label_agreement":null},{"id":"W2173613996","doi":"10.1515/jci-2017-0010","title":"Variable Selection in Causal Inference using a Simultaneous Penalization Method","year":2017,"lang":"en","type":"preprint","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Causal inference; Econometrics; Spurious relationship; Estimator; Outcome (game theory); Variance inflation factor; Confounding; Statistics; Variable (mathematics); Lasso (programming language); Propensity score matching; Average treatment effect; Feature selection; Inflation (cosmology); Mathematics; Population; Computer science; Regression analysis; Medicine; Multicollinearity; Artificial intelligence","score_opus":0.2161748627753796,"score_gpt":0.501343022183107,"score_spread":0.28516815940772744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2173613996","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":[0.03135803,0.00017335218,0.9659774,0.000069422334,0.0006933317,0.0006336714,0.000033043645,0.00014733344,0.00091446954],"genre_scores_gemma":[0.49055496,0.0001721136,0.5086483,0.000040602095,0.0003431911,0.000020026215,0.000008170504,0.00007455307,0.00013809548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943342,0.0007436626,0.0023917048,0.00067146524,0.0011275457,0.00073138694],"domain_scores_gemma":[0.98736763,0.0037913772,0.005212935,0.0008106695,0.0025434557,0.00027390305],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032136608,0.0008136468,0.0018142174,0.0010002641,0.00023116676,0.00050127145,0.0013699761,0.001107333,0.000196267],"category_scores_gemma":[0.021788184,0.0007783091,0.00025155587,0.0004525998,0.00017403284,0.001112391,0.0008763831,0.0034165264,0.0000051821476],"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":[0.0009402732,0.0015691083,0.010406584,0.003162367,0.0008129386,0.0013982805,0.0035196315,0.52473223,0.06636723,0.36703873,0.0007528025,0.019299842],"study_design_scores_gemma":[0.00057499413,0.00038326884,0.00023183555,0.0036760012,0.0002916201,0.00038267142,0.000059895607,0.13937977,0.0060799187,0.84781355,0.00029045471,0.00083601975],"about_ca_topic_score_codex":0.00066888984,"about_ca_topic_score_gemma":0.00038017458,"teacher_disagreement_score":0.48077482,"about_ca_system_score_codex":0.0012161214,"about_ca_system_score_gemma":0.002575919,"threshold_uncertainty_score":0.9994668},"labels":[],"label_agreement":null},{"id":"W2174743136","doi":"10.1515/jci-2014-0035","title":"The Bayesian Causal Effect Estimation Algorithm","year":2015,"lang":"en","type":"article","venue":"Journal of Causal Inference","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":"Université Laval; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Causal inference; Covariate; Model selection; Econometrics; Bayesian probability; Outcome (game theory); Computer science; Causal model; Observational study; Bayesian inference; Confounding; Inference; Regression; Identification (biology); Regression analysis; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.10409491640823053,"score_gpt":0.4294884247078383,"score_spread":0.3253935082996078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174743136","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":[0.014728556,0.00025895995,0.9817437,0.00051456876,0.00062844245,0.00027054362,0.000004552728,0.00012977186,0.0017208994],"genre_scores_gemma":[0.76327395,0.000097180215,0.23580788,0.00008144062,0.00038350667,0.000020539996,0.0000020491173,0.00004467274,0.0002887594],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973967,0.00033103031,0.0008955551,0.00015456733,0.0008422155,0.00037993776],"domain_scores_gemma":[0.9946881,0.0027778544,0.0009312456,0.0004076492,0.00088591455,0.0003092325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002805153,0.00027288852,0.00047692264,0.00014042102,0.00015588947,0.00016606807,0.0005506157,0.00014917052,0.000021572507],"category_scores_gemma":[0.007054141,0.00016762047,0.00012851086,0.0002779086,0.00019559938,0.00070357136,0.00010675831,0.00067263516,0.000021699236],"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":[0.00047771208,0.00033033403,0.002164028,0.00013212509,0.00034117,0.00043069897,0.0017131494,0.0007272673,0.0023998208,0.21270044,0.04433533,0.7342479],"study_design_scores_gemma":[0.0009781226,0.002388993,0.00028380682,0.00029044182,0.00013635596,0.0005323806,0.00017558869,0.01556437,0.015518538,0.95940423,0.004333615,0.00039358024],"about_ca_topic_score_codex":0.000013880412,"about_ca_topic_score_gemma":0.000016657694,"teacher_disagreement_score":0.7485454,"about_ca_system_score_codex":0.0002427527,"about_ca_system_score_gemma":0.00036028126,"threshold_uncertainty_score":0.8444975},"labels":[],"label_agreement":null},{"id":"W2176403014","doi":"10.1002/cjs.11272","title":"Semiparametric maximum likelihood estimation for a two‐sample density ratio model with right‐censored data","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Estimator; Statistics; Mathematics; Statistic; Consistency (knowledge bases); Empirical likelihood; Asymptotic distribution; Likelihood-ratio test; Test statistic; Semiparametric model; Sample (material); Econometrics; Statistical hypothesis testing","score_opus":0.22465987501282447,"score_gpt":0.37762342614858946,"score_spread":0.15296355113576499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176403014","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":[0.0024229272,0.000041672916,0.9941515,0.00014100809,0.00008674042,0.0003325339,0.0027142686,0.00002586842,0.00008352065],"genre_scores_gemma":[0.14606708,0.0000035111398,0.8535601,0.00007738984,0.000058955196,0.000005796137,0.00016366415,0.00003457365,0.000028927885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859786,0.000041886782,0.0005154665,0.00017836646,0.0003022262,0.00036421375],"domain_scores_gemma":[0.9959958,0.0008319599,0.00053084665,0.00049579993,0.001374092,0.00077147724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067582465,0.00018041777,0.00035858242,0.00031974,0.000114316754,0.00009748914,0.00044577982,0.00007238321,0.000014670567],"category_scores_gemma":[0.006698709,0.00015462903,0.000024571316,0.00025260527,0.000105200146,0.00043729495,0.000026046906,0.0002366061,0.0000022568106],"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":[0.00031735303,0.00016128262,0.0011173201,0.00029484276,0.00025432894,0.0005537439,0.002001067,0.029565206,0.00010208724,0.6520639,0.28068906,0.0328798],"study_design_scores_gemma":[0.0005805224,0.00022942429,0.0000109419,0.000051228548,0.00011605713,0.00011722846,0.00007196109,0.31663334,0.00027244445,0.68144804,0.00031763213,0.00015117462],"about_ca_topic_score_codex":0.0010962444,"about_ca_topic_score_gemma":0.026922246,"teacher_disagreement_score":0.28706816,"about_ca_system_score_codex":0.0003892838,"about_ca_system_score_gemma":0.0028683874,"threshold_uncertainty_score":0.9908339},"labels":[],"label_agreement":null},{"id":"W2197328861","doi":"","title":"A Distributional Analysis of Treatment Effects on Subpopulations of a Socioeconomic Experiment","year":2009,"lang":"en","type":"preprint","venue":"Carleton University's Institutional Repository (MacOdrum Library, Carleton University)","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":"Western University; Carleton University","funders":"","keywords":"Treatment and control groups; Intersection (aeronautics); Econometrics; Treatment effect; Socioeconomic status; Control (management); Statistics; Scope (computer science); Distribution (mathematics); Test (biology); Mathematics; Statistical hypothesis testing; Computer science; Medicine; Geography; Artificial intelligence; Cartography; Environmental health","score_opus":0.04025246183550726,"score_gpt":0.29192691483646477,"score_spread":0.25167445300095753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197328861","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":[0.9337965,0.00016741894,0.015055402,0.00019517756,0.000533907,0.0012089987,0.0020025223,0.00049408304,0.04654596],"genre_scores_gemma":[0.9890328,0.00023844675,0.0053055463,0.000034016437,0.00012606387,0.0000035026812,0.0012469273,0.000036065034,0.003976643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969178,0.0004201323,0.0006902763,0.0010215753,0.0005303784,0.00041984115],"domain_scores_gemma":[0.99648005,0.0006686729,0.0012228881,0.001054109,0.00027797354,0.00029632158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000107360414,0.0007194095,0.0014883464,0.002486636,0.00047822078,0.000040453127,0.0009597747,0.00069162465,0.000102617436],"category_scores_gemma":[0.00004951169,0.0008622469,0.001437915,0.0010594747,0.0007049826,0.0006822004,0.0006701887,0.0005392739,0.000003154849],"study_design_candidate":"theoretical_or_conceptual","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":[0.0008403953,0.0010354295,0.00651518,0.00037259352,0.0051195426,0.0007113325,0.0005095989,0.024217604,0.0065276325,0.952511,0.00102837,0.0006113273],"study_design_scores_gemma":[0.012088331,0.006787564,0.045760147,0.0044987253,0.039406728,0.00009167951,0.0044046473,0.008179975,0.68338174,0.07062238,0.1169824,0.007795674],"about_ca_topic_score_codex":0.00028404046,"about_ca_topic_score_gemma":0.000024804702,"teacher_disagreement_score":0.8818886,"about_ca_system_score_codex":0.0042268247,"about_ca_system_score_gemma":0.0019420836,"threshold_uncertainty_score":0.99959576},"labels":[],"label_agreement":null},{"id":"W2198637531","doi":"10.1093/biostatistics/kxv028","title":"Double robust and efficient estimation of a prognostic model for events in the presence of dependent censoring","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Université de Montréal","funders":"National Institutes of Health; National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Censoring (clinical trials); Inverse probability weighting; Inverse probability; Estimator; Computer science; Inference; Statistics; Econometrics; Weighting; Missing data; Estimation; Causal inference; Parametric model; Parametric statistics; Mathematics; Artificial intelligence; Posterior probability","score_opus":0.2544352714323289,"score_gpt":0.4149531699672734,"score_spread":0.16051789853494447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198637531","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":[0.16599455,0.000024222221,0.83313286,0.000017415217,0.00001856662,0.0006934373,0.00006165053,0.000014633611,0.00004267407],"genre_scores_gemma":[0.62993556,0.0000031670338,0.3699932,0.0000018890138,0.0000025929724,0.00004470617,0.0000038021797,0.000005736115,0.000009306256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926466,0.000026053716,0.00027954788,0.000099913865,0.00021871917,0.00011109973],"domain_scores_gemma":[0.99873006,0.0007572192,0.00017422545,0.00015600924,0.00015669416,0.00002581133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047260808,0.000075180826,0.00014532707,0.000046433535,0.000015131724,0.00000420447,0.00010880316,0.000034975757,3.2244884e-7],"category_scores_gemma":[0.0018016566,0.00005705328,0.000011046731,0.00007567147,0.000049304286,0.000035908724,0.000039585506,0.00004789505,1.2710588e-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":[0.00018149165,0.00042517352,0.0022110783,0.0009258334,0.000013705319,0.000002053535,0.006348228,0.38734615,0.00062561355,0.5996433,0.00017065043,0.002106746],"study_design_scores_gemma":[0.00043355438,0.000092994225,0.00022647006,0.000107676395,0.000022439912,0.000001690718,0.00026898878,0.7896598,0.0023856256,0.20674461,6.7313766e-7,0.000055460358],"about_ca_topic_score_codex":0.000015502743,"about_ca_topic_score_gemma":0.000019274778,"teacher_disagreement_score":0.46394104,"about_ca_system_score_codex":0.000028415898,"about_ca_system_score_gemma":0.00004430723,"threshold_uncertainty_score":0.23265652},"labels":[],"label_agreement":null},{"id":"W2208184784","doi":"10.2139/ssrn.2377483","title":"Difference-in-Differences When Treatment Status Is Observed in Only One Period","year":2014,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Period (music); Demography; Medicine; Psychology; Sociology; Philosophy","score_opus":0.13685328697736185,"score_gpt":0.35453460264447295,"score_spread":0.2176813156671111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2208184784","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":[0.9783798,0.00066347077,0.018629842,0.00073672045,0.000059644957,0.00033510188,0.000005034389,0.00011450154,0.0010758816],"genre_scores_gemma":[0.9884811,0.0036116256,0.006044701,0.00007024059,0.000100008605,0.000044372413,0.0000032347018,0.000043756765,0.0016009429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99543864,0.00026644074,0.0006790365,0.00037109895,0.00038200014,0.0028628067],"domain_scores_gemma":[0.998806,0.00029688134,0.00029452864,0.00038335845,0.00007649357,0.0001427467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009967312,0.00037038454,0.00066453684,0.00028590136,0.00009204966,0.00008234925,0.0003909161,0.00016617689,0.0001461645],"category_scores_gemma":[0.00030442138,0.00030037327,0.00012859657,0.00021238643,0.00007658421,0.00022509045,0.000054187924,0.0015614756,0.00001558654],"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":[0.00015422063,0.0010446702,0.17282283,0.000034273435,0.00013969764,0.00001503945,0.0045031235,0.0000024057938,0.0014759294,0.6765995,0.000025237483,0.14318307],"study_design_scores_gemma":[0.0012804677,0.0013996328,0.01958601,0.00014423652,0.000029410476,0.0000717632,0.0012742365,0.00021521341,0.0006202121,0.97488576,0.0001630785,0.0003299871],"about_ca_topic_score_codex":0.00047598092,"about_ca_topic_score_gemma":0.02150487,"teacher_disagreement_score":0.29828626,"about_ca_system_score_codex":0.002961465,"about_ca_system_score_gemma":0.0015443978,"threshold_uncertainty_score":0.99994487},"labels":[],"label_agreement":null},{"id":"W2216967333","doi":"10.1002/pds.3924","title":"Conditions for confounding of interactions","year":2015,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University; The Quebec Population Health Research Network; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Confounding; Pharmacoepidemiology; Pharmacology; Internal medicine; Medical prescription","score_opus":0.35547554723151903,"score_gpt":0.5507731981639249,"score_spread":0.19529765093240586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2216967333","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":[0.05381669,0.00027622728,0.9292993,0.0040715854,0.00060351024,0.0007672703,0.0002195574,0.00031073793,0.010635148],"genre_scores_gemma":[0.9334182,0.00009347945,0.0654462,0.00046575133,0.00008395528,0.000101609156,0.000031097145,0.0000119341175,0.00034774654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990032,0.00024705293,0.00040648397,0.00014411534,0.00003605198,0.00016312451],"domain_scores_gemma":[0.9918578,0.007579095,0.0002104515,0.00011103872,0.00014427034,0.000097339274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018336305,0.00009825715,0.0003203751,0.000062049934,0.0000803209,0.0000018748794,0.00007442825,0.00004372156,0.00005478793],"category_scores_gemma":[0.004346306,0.00008768519,0.000052598665,0.000051963736,0.00018401287,0.0001452096,0.00004150824,0.00014218518,0.0000028192508],"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":[0.00014198161,0.000058040674,0.0021635317,0.00006789469,0.00006116744,6.6129934e-7,0.0005005257,0.000021979922,0.0036663641,0.9436489,0.04840564,0.0012633482],"study_design_scores_gemma":[0.00063199946,0.000040738647,0.00012412941,0.000033704968,0.00007034331,0.000018769531,0.00035266706,0.0015223161,0.006620852,0.9608363,0.029633565,0.000114615876],"about_ca_topic_score_codex":0.000016694019,"about_ca_topic_score_gemma":0.000011710223,"teacher_disagreement_score":0.87960154,"about_ca_system_score_codex":0.00003394944,"about_ca_system_score_gemma":0.000033613112,"threshold_uncertainty_score":0.5203248},"labels":[],"label_agreement":null},{"id":"W2242307981","doi":"10.1002/sim.6818","title":"The missing cause approach to unmeasured confounding in pharmacoepidemiology","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Université de Montréal; Bruyère; University of Ottawa; McGill University; Ottawa Public Health; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Confounding; Pharmacoepidemiology; Spurious relationship; Statistics; Observational study; Missing data; Econometrics; Medicine; Instrumental variable; Average treatment effect; Variance (accounting); Mathematics; Propensity score matching; Medical prescription","score_opus":0.2739779879782596,"score_gpt":0.5135117581148383,"score_spread":0.23953377013657867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2242307981","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":[0.0020755273,0.00010243481,0.989832,0.003354589,0.00021039299,0.00043269497,0.000017935521,0.0000765446,0.0038978711],"genre_scores_gemma":[0.37677744,0.00036675102,0.62099206,0.00094307953,0.0001999915,0.00014635213,0.000006484426,0.000048355916,0.0005194894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980557,0.00034951261,0.0006622752,0.00025606962,0.00024534558,0.00043110567],"domain_scores_gemma":[0.990234,0.009102212,0.00015110247,0.00031815784,0.00008889699,0.00010562343],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033512677,0.00016621586,0.00041151507,0.00016109514,0.000068085916,0.000006415013,0.00026218905,0.00007031633,0.000032307405],"category_scores_gemma":[0.025932798,0.00008845701,0.000010857695,0.0002510189,0.0003294943,0.00004693848,0.000059001395,0.0002625448,0.000006692476],"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":[0.00005569847,0.0000438532,0.0022511801,0.000051820658,0.000014909547,0.00003613747,0.0009805382,0.0000056078757,0.00978998,0.9317049,0.017100181,0.03796519],"study_design_scores_gemma":[0.0008402463,0.000089972535,0.0007938003,0.0004395252,0.000017108518,0.0000123329255,0.00030421442,0.00053284166,0.0006782817,0.992992,0.0031397492,0.00015993681],"about_ca_topic_score_codex":0.000057418165,"about_ca_topic_score_gemma":0.00014501835,"teacher_disagreement_score":0.3747019,"about_ca_system_score_codex":0.00026696385,"about_ca_system_score_gemma":0.000047428613,"threshold_uncertainty_score":0.9822722},"labels":[],"label_agreement":null},{"id":"W2246264012","doi":"10.82308/26320","title":"Flexible marginal structural models for survival analysis","year":2012,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Marginal structural model; Proportional hazards model; Estimator; Covariate; Econometrics; Inverse probability weighting; Weighting; Statistics; Hazard; Confounding; Computer science; Hazard ratio; Truncation (statistics); Mathematics; Confidence interval; Medicine","score_opus":0.15421599477603773,"score_gpt":0.3743980072475583,"score_spread":0.22018201247152056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246264012","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":[0.9353178,0.00015983716,0.012289195,0.000040228537,0.0006901296,0.0015429431,0.0019651891,0.0020830007,0.04591164],"genre_scores_gemma":[0.8646095,0.00001795747,0.13354345,0.00010836296,0.00008213746,0.0002175096,0.00007871679,0.00012696272,0.001215409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962949,0.0002472815,0.0008122955,0.0006722597,0.0006861362,0.0012871],"domain_scores_gemma":[0.996742,0.00095319824,0.0004126325,0.0010067052,0.000412864,0.0004726109],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016055817,0.0006043732,0.0009305702,0.0004798768,0.0007723659,0.00006645545,0.0006574208,0.00036027856,0.00032659323],"category_scores_gemma":[0.00096607767,0.00057939405,0.00059276074,0.0010537038,0.00011207025,0.0023451932,0.00028107624,0.0006398658,0.000044602388],"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":[0.00009018334,0.0001034681,0.0002772585,0.00008989655,0.00048692842,0.0000029279443,0.000006945211,0.00024685162,0.0059710895,0.9797939,0.000008600827,0.012921943],"study_design_scores_gemma":[0.0005264217,0.000110116016,0.000305633,0.000031990243,0.000822153,0.000014319352,0.000073169074,0.0013840315,0.06685768,0.92453796,0.0045490647,0.00078743714],"about_ca_topic_score_codex":0.00007196769,"about_ca_topic_score_gemma":0.000116694624,"teacher_disagreement_score":0.12125425,"about_ca_system_score_codex":0.000562542,"about_ca_system_score_gemma":0.00002096674,"threshold_uncertainty_score":0.99966574},"labels":[],"label_agreement":null},{"id":"W2256970024","doi":"","title":"Les effets du cancer sur l'emploi et les gains des survivants du cancer","year":2014,"lang":"fr","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Humanities; Political science; Gynecology; Medicine; Art","score_opus":0.19047221043256038,"score_gpt":0.44995255628912134,"score_spread":0.259480345856561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256970024","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":[0.95276374,0.0018873914,0.0017023818,0.0020424584,0.0009663428,0.002430756,0.0007115172,0.00042492885,0.03707046],"genre_scores_gemma":[0.7368902,0.24306516,0.009844125,0.00016761654,0.0007969111,0.0023173436,0.0000761517,0.0004172526,0.006425219],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910722,0.0022049681,0.0018025935,0.0019652022,0.00069519796,0.002259877],"domain_scores_gemma":[0.9883709,0.007172344,0.00084577134,0.0020653277,0.0009840445,0.0005616003],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0065186117,0.0011954667,0.0019879437,0.0006869594,0.00062175,0.00034305028,0.0019584289,0.001617857,0.0014240913],"category_scores_gemma":[0.005317758,0.0012889421,0.00045359196,0.000282881,0.0020621943,0.0004508628,0.0025472483,0.004382265,0.00004518102],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002662591,0.0007534975,0.28106624,0.0027722365,0.0005246582,0.000097157186,0.0022122527,0.020581948,0.0009932682,0.037243173,0.00048716072,0.65300214],"study_design_scores_gemma":[0.006131801,0.0011786025,0.3591372,0.02832114,0.00037857212,0.00012894903,0.002756225,0.06756398,0.015983175,0.29626375,0.21344766,0.008708929],"about_ca_topic_score_codex":0.02269666,"about_ca_topic_score_gemma":0.07828294,"teacher_disagreement_score":0.64429325,"about_ca_system_score_codex":0.005134407,"about_ca_system_score_gemma":0.0015998227,"threshold_uncertainty_score":0.99967825},"labels":[],"label_agreement":null},{"id":"W2258095781","doi":"10.1089/end.2015.0653","title":"Editorial Comment for Wiener <i>et al.</i>","year":2015,"lang":"es","type":"editorial","venue":"Journal of Endourology","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":"St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Download; Library science; World Wide Web; Computer science","score_opus":0.09450927870251402,"score_gpt":0.4365783207313075,"score_spread":0.34206904202879346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258095781","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":[0.000037384918,0.00042708113,0.037648983,0.013544062,0.9465523,0.00070496846,0.00037533493,0.00007334341,0.0006365573],"genre_scores_gemma":[0.000085105195,0.0011282108,0.03985864,0.006313894,0.95208776,0.00007332267,0.0000748282,0.00018273399,0.0001955218],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939753,0.0006536962,0.0023644657,0.00044653064,0.0017224146,0.00083759037],"domain_scores_gemma":[0.98029125,0.009108253,0.0047406373,0.0006487711,0.0047995597,0.00041152266],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005573155,0.00077800034,0.0023172626,0.00044764928,0.000106632724,0.00011497258,0.0012315856,0.0015413152,0.00007528155],"category_scores_gemma":[0.015210024,0.00065651507,0.00071401737,0.00013558753,0.00027469534,0.00043478716,0.0003176653,0.0033423507,0.000017664164],"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":[0.0021354912,0.00045581374,0.0000050765866,0.00012499375,0.00041327183,0.000048720543,0.00017022902,0.000030209647,0.00063944946,0.008158709,0.9875111,0.0003069391],"study_design_scores_gemma":[0.003767836,0.0063776625,1.5905742e-7,0.00020951545,0.00049350015,0.00010511601,0.000041372314,0.000010479417,0.00045204113,0.15068147,0.83742917,0.00043170725],"about_ca_topic_score_codex":0.000013349281,"about_ca_topic_score_gemma":0.000015635509,"teacher_disagreement_score":0.15008195,"about_ca_system_score_codex":0.0005376278,"about_ca_system_score_gemma":0.0017955826,"threshold_uncertainty_score":0.9997549},"labels":[],"label_agreement":null},{"id":"W2262143275","doi":"10.1093/aje/kwv152","title":"The Impact of Sparse Follow-up on Marginal Structural Models for Time-to-Event Data","year":2015,"lang":"en","type":"review","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"McGill University","funders":"Université de Montréal; Health Canada; Centre Hospitalier Universitaire de Québec; Canadian Institutes of Health Research; University of Ottawa; McGill University; Institute for Clinical Evaluative Sciences; McGill University Health Centre; McMaster University; Ottawa Hospital Research Institute; Natural Sciences and Engineering Research Council of Canada; Faculty of Medicine, McGill University","keywords":"Missing data; Covariate; Hazard ratio; Statistics; Confounding; Marginal structural model; Medicine; Imputation (statistics); Confidence interval; Proportional hazards model; Event (particle physics); Econometrics; Mathematics","score_opus":0.4973999321594651,"score_gpt":0.5646419536567407,"score_spread":0.06724202149727565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262143275","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":[0.00009691592,0.8025415,0.19370978,0.0003627031,0.00035301488,0.0016727088,0.0009824763,0.00004291206,0.00023799954],"genre_scores_gemma":[0.00011742966,0.8468226,0.1520757,0.00010011494,0.0004242795,0.00004650471,0.000085135594,0.00011461474,0.00021362158],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99404603,0.001965996,0.0027049526,0.0003961154,0.0002468621,0.00064002676],"domain_scores_gemma":[0.97054887,0.020186557,0.006869353,0.0015302211,0.0005334385,0.00033156204],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009139792,0.00054999656,0.0054770345,0.00026292284,0.000066639404,0.000008521361,0.0022281513,0.0001861715,0.000038017566],"category_scores_gemma":[0.019218197,0.0002788093,0.0011232106,0.00026499355,0.0005294699,0.00015170047,0.0003465122,0.00079779886,0.000011674192],"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":[0.00030566132,0.000027415956,0.000002982878,0.00031445402,0.0007105618,0.0000053194435,0.000027484391,0.0004313392,4.607239e-7,0.0083283475,0.054962512,0.9348835],"study_design_scores_gemma":[0.0003260727,0.006946135,0.0000021479007,0.0040116827,0.0010098276,0.0005161324,0.000037580667,0.0021684528,5.3567624e-7,0.5687595,0.4157759,0.00044605468],"about_ca_topic_score_codex":0.000045332254,"about_ca_topic_score_gemma":0.0000035782568,"teacher_disagreement_score":0.9344374,"about_ca_system_score_codex":0.0004633561,"about_ca_system_score_gemma":0.00090100913,"threshold_uncertainty_score":0.9999664},"labels":[],"label_agreement":null},{"id":"W2263960472","doi":"10.1287/orsc.2015.1034","title":"Bridging Qualitative and Quantitative Methods in Organizational Research: Applications of Synthetic Control Methodology in the U.S. Automobile Industry","year":2016,"lang":"en","type":"article","venue":"Organization Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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":"Counterfactual thinking; Bridging (networking); Context (archaeology); Bridge (graph theory); Empirical research; Control (management); Econometrics; Computer science; Economics; Operations management; Business; Psychology; Mathematics; Statistics; Artificial intelligence","score_opus":0.542484474409773,"score_gpt":0.6232486399900531,"score_spread":0.0807641655802801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2263960472","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":[0.06099042,0.000019553207,0.9364999,0.0016726316,0.000011784873,0.00052637985,0.000008913531,0.000038236594,0.00023216406],"genre_scores_gemma":[0.7060255,0.00001128547,0.29382685,0.000043187552,0.000005633067,0.00006000381,6.8769793e-7,0.000010319136,0.000016532582],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962068,0.0023890324,0.0004131854,0.00032849994,0.0004244983,0.00023798864],"domain_scores_gemma":[0.9842203,0.014092573,0.00020826793,0.00031109728,0.001127462,0.00004026086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015685864,0.00008977083,0.00020840771,0.0005759299,0.00014432338,0.000027817838,0.00045589262,0.00010292332,0.000088874025],"category_scores_gemma":[0.040051833,0.00005772131,0.000007480781,0.005462369,0.0015335499,0.00037321963,0.00011314829,0.0002614619,0.00000357922],"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":[0.0000034161492,0.00005525575,0.004546868,0.000013051819,0.0000019121776,4.825551e-7,0.015007014,0.0000066227212,0.1412901,0.8364158,0.000019330546,0.0026400953],"study_design_scores_gemma":[0.00032165356,0.00007095659,0.007584674,0.00009844469,0.0000061175374,0.000012152296,0.014052075,0.0003395965,0.118033804,0.85932094,0.000026051805,0.0001335658],"about_ca_topic_score_codex":0.00002016643,"about_ca_topic_score_gemma":0.000018216768,"teacher_disagreement_score":0.6450351,"about_ca_system_score_codex":0.00013575004,"about_ca_system_score_gemma":0.00026893735,"threshold_uncertainty_score":0.9680342},"labels":[],"label_agreement":null},{"id":"W2264767503","doi":"10.1161/circulationaha.115.017719","title":"Introduction to the Analysis of Survival Data in the Presence of Competing Risks","year":2016,"lang":"en","type":"article","venue":"Circulation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2536,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Medicine; Proportional hazards model; Survival analysis; Cumulative incidence; Incidence (geometry); Survival function; Event (particle physics); Statistics; Hazard ratio; Outcome (game theory); Hazard; Demography; Accelerated failure time model; Econometrics; Confidence interval; Internal medicine; Cohort; Mathematics","score_opus":0.2664686297936992,"score_gpt":0.44262911585399767,"score_spread":0.1761604860602985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2264767503","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":[0.5953732,0.0000073602887,0.402934,0.0012924009,0.000031427502,0.0002026053,0.000017230195,0.00001723244,0.00012451004],"genre_scores_gemma":[0.99614125,0.000004387137,0.003749407,0.000006660375,0.00007023314,0.000007703508,0.000013646336,0.0000036087397,0.0000031182215],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99915147,0.00018543248,0.00025812403,0.00013582467,0.00020475338,0.00006439219],"domain_scores_gemma":[0.9978166,0.0010174405,0.00018869618,0.0008795899,0.00009084983,0.0000067838378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015846164,0.00004413999,0.00013726088,0.00010388003,0.000021498961,0.0000048654933,0.00034662941,0.000023091225,0.000022327915],"category_scores_gemma":[0.0025292381,0.00002228824,0.00002377733,0.00065604906,0.000040634535,0.00013591505,0.00007476932,0.000041952164,0.0000011601019],"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":[0.00005264811,0.00021236813,0.48926064,0.00010508606,0.00031570683,5.923145e-7,0.0075677144,0.010283276,0.13842009,0.2885939,0.0009820153,0.06420599],"study_design_scores_gemma":[0.00011818816,0.000018185392,0.90542746,0.000074437274,0.00030399076,7.5566106e-7,0.0008910385,0.014461553,0.005933315,0.07231374,0.00034930528,0.00010805458],"about_ca_topic_score_codex":0.00007646727,"about_ca_topic_score_gemma":0.00022806102,"teacher_disagreement_score":0.4161668,"about_ca_system_score_codex":0.000020539024,"about_ca_system_score_gemma":0.000008219667,"threshold_uncertainty_score":0.3027917},"labels":[],"label_agreement":null},{"id":"W2267083177","doi":"10.2139/ssrn.2266821","title":"Program Quality and Treatment Completion for Youth Training Programs","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Training (meteorology); Quality (philosophy); Completion (oil and gas wells); Medical education; Psychology; Operations management; Political science; Medicine; Engineering; Geography","score_opus":0.4143963875844185,"score_gpt":0.4623795294929555,"score_spread":0.04798314190853703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2267083177","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":[0.7575586,0.00025141065,0.2384774,0.0005270359,0.000036783626,0.0024153595,0.0000047763897,0.00043989392,0.0002887406],"genre_scores_gemma":[0.9344058,0.00033887953,0.06440023,0.000019186473,0.000116901974,0.0004996531,0.00001472242,0.0000302897,0.00017435076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978654,0.00007271137,0.00034904192,0.00017660677,0.00014457625,0.0013916588],"domain_scores_gemma":[0.999291,0.00012447634,0.00022899295,0.00013196995,0.00013749156,0.0000860932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010280779,0.00017525197,0.00027815462,0.000049822447,0.00017304799,0.00009876191,0.00009652449,0.00007104158,0.000007638531],"category_scores_gemma":[0.00012879098,0.00013266227,0.000092461305,0.000064582055,0.00006394643,0.00021402548,0.00001431161,0.00043268438,0.0000021325486],"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":[0.000018673925,0.00018362145,0.0002987759,0.000010817056,0.0000707715,1.4158252e-7,0.0012497691,1.7475911e-7,0.00019882817,0.33950686,0.000007568121,0.658454],"study_design_scores_gemma":[0.000654259,0.002472374,0.00018626681,0.000029762188,0.000047358677,0.00007007568,0.007931758,0.00009930028,0.000115827104,0.98788136,0.00034583526,0.00016584591],"about_ca_topic_score_codex":0.000066896195,"about_ca_topic_score_gemma":0.00030648813,"teacher_disagreement_score":0.6582881,"about_ca_system_score_codex":0.00068017683,"about_ca_system_score_gemma":0.00031752101,"threshold_uncertainty_score":0.54098105},"labels":[],"label_agreement":null},{"id":"W2278177624","doi":"10.1515/ijb-2015-0017","title":"Variable Selection for Confounder Control, Flexible Modeling and Collaborative Targeted Minimum Loss-Based Estimation in Causal Inference","year":2015,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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; Polytechnique Montréal","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Causal inference; Propensity score matching; Estimator; Computer science; Covariate; Inverse probability weighting; Inverse probability; Average treatment effect; Econometrics; Marginal structural model; Inference; Statistics; Nonparametric statistics; Weighting; Selection bias; Machine learning; Artificial intelligence; Mathematics; Posterior probability","score_opus":0.10003523274824203,"score_gpt":0.4231658834685216,"score_spread":0.3231306507202796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278177624","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":[0.012231027,0.000044141125,0.98636687,0.00063631637,0.00022149157,0.00027981028,0.00011990714,0.000024583538,0.0000758387],"genre_scores_gemma":[0.5997656,0.0000066415273,0.399994,0.00014248895,0.000046661244,0.00001068298,0.000010044875,0.000009859188,0.000014052348],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874467,0.00007787067,0.00055431534,0.000097977485,0.00039066066,0.00013452333],"domain_scores_gemma":[0.99525934,0.0016889344,0.00048096242,0.00006815406,0.0024407664,0.00006185321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010052448,0.000124703,0.00022531093,0.0001714735,0.00004363562,0.000090929665,0.00020590064,0.000065983666,0.000008461917],"category_scores_gemma":[0.004449593,0.000096480726,0.000020807733,0.00015452987,0.00008082453,0.0002641035,0.000022261767,0.00018342196,5.810971e-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":[0.0014468145,0.00016780247,0.00081311184,0.000038729384,0.00017112067,0.00001282841,0.0007538931,0.2061673,0.0033581334,0.7843611,0.001497768,0.0012113728],"study_design_scores_gemma":[0.0011024503,0.00019701413,0.000013684062,0.00006404777,0.000026849744,0.000018136,0.0001349463,0.5023753,0.0014605802,0.4944896,0.00005250771,0.000064872795],"about_ca_topic_score_codex":0.000032360207,"about_ca_topic_score_gemma":0.000035537574,"teacher_disagreement_score":0.58753455,"about_ca_system_score_codex":0.00025678665,"about_ca_system_score_gemma":0.0005617192,"threshold_uncertainty_score":0.53269},"labels":[],"label_agreement":null},{"id":"W2278756228","doi":"10.1093/ije/dyv135","title":"Imputation approaches for potential outcomes in causal inference","year":2015,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":71,"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 Institutes of Health","keywords":"Causal inference; Inference; Imputation (statistics); Missing data; Computer science; Intuition; Causal model; Causal structure; Machine learning; Econometrics; Data science; Artificial intelligence; Psychology; Mathematics; Statistics; Cognitive science","score_opus":0.49969905682162113,"score_gpt":0.5278363928453237,"score_spread":0.028137336023702553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278756228","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":[0.14216733,0.00006938051,0.85331506,0.003330898,0.00073297886,0.00014438339,0.000011444888,0.000023183193,0.0002053416],"genre_scores_gemma":[0.75525385,0.000022976123,0.24418695,0.00025798441,0.00020277727,0.000016136884,0.000007981185,0.000010353758,0.00004096704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981574,0.00027102427,0.0010484186,0.00013016145,0.00019704193,0.00019595781],"domain_scores_gemma":[0.9940715,0.004231693,0.00085922214,0.00009601103,0.00065358,0.000088032066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033318785,0.00012025375,0.00047984644,0.0002794299,0.000010621699,0.000008961891,0.00036794273,0.0001233132,0.000012224754],"category_scores_gemma":[0.026022512,0.00009480282,0.00012582015,0.00004865871,0.00007993295,0.00028649182,0.00006165135,0.00022718326,0.0000022427218],"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":[0.0005674434,0.00037576494,0.11260554,0.000020484664,0.00027495122,0.00007264058,0.0007175435,0.0075906464,0.00027504918,0.84004444,0.0044384333,0.03301709],"study_design_scores_gemma":[0.0008140318,0.00024662228,0.006011794,0.00003228695,0.000014153848,0.000102719365,0.000089628804,0.004048487,0.0001621389,0.98797375,0.0004135179,0.000090880356],"about_ca_topic_score_codex":0.00002221935,"about_ca_topic_score_gemma":0.000019424986,"teacher_disagreement_score":0.6130865,"about_ca_system_score_codex":0.00020515152,"about_ca_system_score_gemma":0.00014118264,"threshold_uncertainty_score":0.9821817},"labels":[],"label_agreement":null},{"id":"W2284187917","doi":"10.1186/s12874-016-0119-1","title":"Head to head comparison of the propensity score and the high-dimensional propensity score matching methods","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":50,"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. Joseph’s Healthcare Hamilton; University of British Columbia; Centre Hospitalier de l’Université de Montréal; McGill University; McMaster University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Confounding; Medicine; Matching (statistics); Cohort; Context (archaeology); Confidence interval; Cohort study; Internal medicine; Statistics; Mathematics; Pathology; Biology","score_opus":0.8646910788517377,"score_gpt":0.6556494814906167,"score_spread":0.20904159736112093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284187917","genre_codex":"empirical","genre_gemma":"methods","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":[0.503865,0.00009819942,0.48806724,0.006489794,0.00011545069,0.0011994423,0.000004123753,0.000055464472,0.00010526153],"genre_scores_gemma":[0.3814385,0.000029406718,0.6176556,0.00034665395,0.00009682463,0.00014191498,6.4712776e-7,0.000029021727,0.00026145906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95408076,0.040948227,0.0010054029,0.0007242552,0.002323078,0.00091828214],"domain_scores_gemma":[0.88438785,0.112810455,0.00028751278,0.0012232964,0.0008272503,0.00046363476],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07210784,0.00026121578,0.0013160573,0.00016898446,0.00041193617,0.000023765158,0.0012131133,0.0003558075,0.00023886168],"category_scores_gemma":[0.22236341,0.000104261286,0.00013339115,0.00052644825,0.0038925437,0.00010635567,0.002790788,0.0014110282,0.00001401488],"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":[0.0033911911,0.00035310007,0.02721664,0.0006163572,0.000109065404,0.000023755205,0.0016743842,0.000005585768,0.07140673,0.6145967,0.003108137,0.27749833],"study_design_scores_gemma":[0.0014347014,0.00041791142,0.027950937,0.0011441691,0.00003213374,0.00008739744,0.0001255658,0.00018127407,0.06975344,0.89831555,0.00035288237,0.00020405729],"about_ca_topic_score_codex":0.0009765957,"about_ca_topic_score_gemma":0.0027650609,"teacher_disagreement_score":0.2837188,"about_ca_system_score_codex":0.00012543848,"about_ca_system_score_gemma":0.00087313063,"threshold_uncertainty_score":0.9988183},"labels":[],"label_agreement":null},{"id":"W2284501626","doi":"10.1093/ije/dyv295","title":"Using observational data to emulate a randomized trial of dynamic treatment-switching strategies: an application to antiretroviral therapy","year":2015,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"AIDS Vancouver; Simon Fraser University; University of Calgary","funders":"National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; Department for International Development; National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health; Medical Research Council; National Institute for Health and Care Research","keywords":"Medicine; Observational study; Randomized controlled trial; Hazard ratio; Regimen; Confidence interval; Cohort; Cohort study; Internal medicine","score_opus":0.6825081891066951,"score_gpt":0.5939492754641644,"score_spread":0.08855891364253066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284501626","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":[0.4687175,0.00003198447,0.529958,0.0005413595,0.0002637388,0.00041996653,0.000026242378,0.00001653314,0.0000246695],"genre_scores_gemma":[0.6566855,0.00004458555,0.34263092,0.00028612476,0.00027116897,0.000016616832,0.000043340468,0.0000149471725,0.0000068277755],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967694,0.0008414721,0.001616012,0.00025300457,0.00033407178,0.00018599018],"domain_scores_gemma":[0.9943077,0.0027172144,0.0014621513,0.00044244828,0.00089790253,0.00017255785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057428973,0.0001783433,0.0009717693,0.00031828246,0.000023011286,0.000020273777,0.000935066,0.000102766506,0.000011808557],"category_scores_gemma":[0.010240316,0.00013348354,0.00013978092,0.00011992026,0.00006498255,0.00070642406,0.00011754129,0.0001463304,0.00000189689],"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":[0.58481574,0.0011828679,0.0013255841,0.000012185518,0.0011840587,0.000024220213,0.0020370877,0.015042572,0.047519207,0.27124354,0.0004089003,0.075204074],"study_design_scores_gemma":[0.17672744,0.0032796045,0.00014728884,0.0000877668,0.00007004425,0.000077444354,0.00026310707,0.0719634,0.00031248177,0.74651015,0.00035880375,0.00020245457],"about_ca_topic_score_codex":0.00023947943,"about_ca_topic_score_gemma":0.00004111147,"teacher_disagreement_score":0.47526664,"about_ca_system_score_codex":0.00032644472,"about_ca_system_score_gemma":0.0003454132,"threshold_uncertainty_score":0.9980968},"labels":[],"label_agreement":null},{"id":"W2288430971","doi":"10.1093/aje/kwv060","title":"Invited Commentary: Boundless Science—Putting Natural Direct and Indirect Effects in a Clearer Empirical Context: Figure 1.","year":2015,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"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":"McGill University","keywords":"Context (archaeology); Natural (archaeology); Psychology; History","score_opus":0.16087419727058952,"score_gpt":0.4625113059421708,"score_spread":0.30163710867158133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288430971","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":[0.9767298,0.00078058726,0.0034082963,0.018567447,0.0002010419,0.00018127338,0.0000017394539,0.000049603692,0.00008019292],"genre_scores_gemma":[0.904276,0.0000394456,0.076186016,0.01937943,0.00009001047,0.000006789862,0.0000010650612,0.000019035044,0.0000021670994],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964228,0.0016144691,0.00091289595,0.0002804711,0.00022264743,0.0005467075],"domain_scores_gemma":[0.9878246,0.010288663,0.00110542,0.00021512283,0.00024969867,0.00031645605],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007742271,0.00021633363,0.0012902339,0.00046780694,0.00007637023,0.000017075883,0.00035691634,0.000075649186,0.0000021488079],"category_scores_gemma":[0.031742275,0.00016266361,0.00008032195,0.00068061094,0.001894484,0.0003249696,0.00016123055,0.0007719503,8.055294e-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":[0.00048354396,0.0002570002,0.7835737,0.000061057115,0.00013591966,0.0002460346,0.0048893485,0.000027346945,0.0017916128,0.002825149,0.053666476,0.15204282],"study_design_scores_gemma":[0.0047072987,0.010570621,0.1285009,0.0017152051,0.00021378562,0.0020057627,0.008248229,0.002816649,0.005809839,0.8188799,0.015180255,0.0013515494],"about_ca_topic_score_codex":0.00019558388,"about_ca_topic_score_gemma":0.00007682853,"teacher_disagreement_score":0.81605476,"about_ca_system_score_codex":0.0003697378,"about_ca_system_score_gemma":0.000086742235,"threshold_uncertainty_score":0.9764138},"labels":[],"label_agreement":null},{"id":"W2292670616","doi":"10.1177/2168479015604183","title":"Defining Regions in Multiregional Clinical Trials: An Analytical Approach to Considering Impact of Intrinsic and Extrinsic Factors","year":2015,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"inVentiv Health Clinical","funders":"","keywords":"Sample size determination; Medicine; Intervention (counseling); Epidemiology; Cluster (spacecraft); Ethnic group; Checklist; Psychology; Family medicine; Computer science; Cognitive psychology; Statistics; Pathology; Political science; Psychiatry","score_opus":0.6558268703743527,"score_gpt":0.5578808159228008,"score_spread":0.09794605445155191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292670616","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":[0.94265246,0.00003235679,0.05631784,0.000056771525,0.000062238614,0.00044334817,0.0000031034135,0.000104243874,0.00032765104],"genre_scores_gemma":[0.95669794,0.0000024132398,0.04313192,0.00009517932,0.000027284677,0.000015028388,0.0000034332745,0.000017283164,0.000009511485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966537,0.0005093887,0.0014079993,0.00049800874,0.00058726734,0.00034368306],"domain_scores_gemma":[0.9966305,0.0014115828,0.00053465785,0.0005380595,0.0006727382,0.00021249922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015546337,0.00021427913,0.0006631599,0.0010196612,0.000089721616,0.00005181807,0.00032444892,0.0001298201,0.0000045517263],"category_scores_gemma":[0.008220889,0.00017053643,0.000067638204,0.0029471284,0.0011371677,0.00068671035,0.000121895995,0.0002910882,0.0000010643043],"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":[0.00008506846,0.00021608127,0.046330094,0.000011364551,0.00002093163,9.210282e-7,0.0014959825,0.00013258356,0.002849273,0.9205565,0.000029026622,0.028272172],"study_design_scores_gemma":[0.0016244389,0.0009248865,0.44360942,0.00015418869,0.00004772408,0.000038604558,0.0028050293,0.02097246,0.0031451434,0.52598757,0.00005814593,0.00063239486],"about_ca_topic_score_codex":0.000029605779,"about_ca_topic_score_gemma":0.00000566047,"teacher_disagreement_score":0.39727932,"about_ca_system_score_codex":0.0002666306,"about_ca_system_score_gemma":0.00083663553,"threshold_uncertainty_score":0.9841766},"labels":[],"label_agreement":null},{"id":"W2293988153","doi":"10.1002/pds.3923","title":"Confounding by drug formulary restriction in pharmacoepidemiologic research","year":2015,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":true,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Formulary; Salmeterol; Fluticasone; Confounding; Confidence interval; Hazard ratio; Pharmacoepidemiology; Rate ratio; COPD; Cohort study; Medical prescription; Asthma; Pediatrics; Internal medicine; Family medicine; Pharmacology","score_opus":0.45341142571709747,"score_gpt":0.5628320553648178,"score_spread":0.10942062964772037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293988153","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":[0.85581493,0.009085155,0.08442396,0.02147373,0.0013125214,0.002724473,0.00010617565,0.0014660435,0.023593027],"genre_scores_gemma":[0.9714686,0.007120983,0.018339474,0.0017881251,0.00024196619,0.00022678681,0.00006350279,0.0000467441,0.0007037904],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99042535,0.0063432604,0.0011954502,0.00071528874,0.0002815146,0.0010391301],"domain_scores_gemma":[0.9796217,0.019114548,0.0003101332,0.0003334078,0.00021635753,0.00040383099],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03324977,0.00034552644,0.00085184607,0.00037232894,0.00026798484,0.000013562302,0.00037156322,0.00023890259,0.00006880184],"category_scores_gemma":[0.015981693,0.0003013337,0.00007643928,0.00053948205,0.0004915319,0.00051708263,0.0003160383,0.001686428,0.000033770113],"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":[0.00086603354,0.0002745974,0.08172174,0.00014268029,0.00006388198,0.000059939674,0.0011456846,0.00009004073,0.005657465,0.21369664,0.6885642,0.0077171377],"study_design_scores_gemma":[0.0019367908,0.00009018891,0.00067199895,0.000096079544,0.00003670752,0.00002841156,0.000916031,0.0042087752,0.003757447,0.93463796,0.053129457,0.0004901228],"about_ca_topic_score_codex":0.00050974684,"about_ca_topic_score_gemma":0.000049408285,"teacher_disagreement_score":0.72094136,"about_ca_system_score_codex":0.00039677348,"about_ca_system_score_gemma":0.00010333527,"threshold_uncertainty_score":0.99994385},"labels":[],"label_agreement":null},{"id":"W2294745036","doi":"10.1177/2158244015625445","title":"Two Cross-Platform Programs for Inferences and Interval Estimation About Indirect Effects in Mediational Models","year":2016,"lang":"en","type":"article","venue":"SAGE Open","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":95,"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":"","keywords":"Resampling; Confidence interval; Posterior probability; Statistics; Bayesian probability; Computer science; Mathematics; Algorithm; Regression; Credible interval","score_opus":0.16955858983009428,"score_gpt":0.4589606541649033,"score_spread":0.289402064334809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294745036","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":[0.39912418,0.000054145312,0.5959384,0.000088999375,0.000061451006,0.00261537,0.000025382706,0.00014639068,0.001945715],"genre_scores_gemma":[0.791752,0.000015721214,0.2070531,0.00002525639,0.000021421805,0.00094019325,0.000015772113,0.000016564481,0.00015997478],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990799,0.000030356441,0.00029354388,0.0002332712,0.0001468929,0.00021607293],"domain_scores_gemma":[0.9985762,0.0009912465,0.00015146294,0.00016171756,0.00006771301,0.000051619358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006380253,0.00014250092,0.00025665312,0.00007851011,0.00005585078,0.00017956295,0.00028234845,0.00007884472,0.000029076773],"category_scores_gemma":[0.0007736455,0.000096877746,0.000026272111,0.00008789855,0.000091590555,0.001519609,0.00020673295,0.00007235922,0.0000048581187],"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":[0.000103433216,0.000111085654,0.012778812,0.00019418393,0.0000246146,0.0000032120518,0.00095144036,0.000019143885,0.0006379962,0.21603014,0.00006435867,0.7690816],"study_design_scores_gemma":[0.0011052431,0.00015677385,0.0030369586,0.0006412983,0.00000851284,0.0000022219515,0.000017386257,0.005069925,0.005134362,0.98463213,0.00003313105,0.00016207815],"about_ca_topic_score_codex":0.000035996556,"about_ca_topic_score_gemma":0.00042501197,"teacher_disagreement_score":0.7689195,"about_ca_system_score_codex":0.0000784818,"about_ca_system_score_gemma":0.000055899312,"threshold_uncertainty_score":0.395056},"labels":[],"label_agreement":null},{"id":"W2302088160","doi":"10.1016/j.jtcvs.2016.01.002","title":"It's not what you put in that is important, it's what you take out","year":2016,"lang":"en","type":"letter","venue":"Journal of Thoracic and Cardiovascular Surgery","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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 Toronto","funders":"","keywords":"Medicine; MEDLINE; Law","score_opus":0.13748950557913775,"score_gpt":0.369904981765231,"score_spread":0.23241547618609326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302088160","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076953038,0.23310591,0.035626438,0.7111045,0.009753795,0.0015253049,0.0001322844,0.00031000632,0.0007464309],"genre_scores_gemma":[0.0068779443,0.6353396,0.005904619,0.33635956,0.01105533,0.000102614336,0.0000398074,0.0006324552,0.0036880479],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927303,0.00080747734,0.0023327724,0.0007981606,0.002299939,0.0010313377],"domain_scores_gemma":[0.99362123,0.0018031148,0.0020882334,0.0016890612,0.00054635014,0.0002520079],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.008136348,0.0009952092,0.003866703,0.0010772523,0.000111350695,0.0008479846,0.0006679678,0.0015880307,0.00016531318],"category_scores_gemma":[0.0008320639,0.0007427107,0.0042860988,0.0002668963,0.00025873334,0.004309518,0.0002512128,0.0029657444,0.000020131945],"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":[0.00010806504,0.000044728407,0.0006833244,0.0010307599,0.0033276007,0.008953694,0.0006663354,0.0000010695346,0.000032350243,0.000017531658,0.74578834,0.2393462],"study_design_scores_gemma":[0.00023541806,0.00005735807,0.000041751395,0.0102077,0.0015462085,0.001838565,0.00096190115,0.0000026122857,0.0025626898,0.012468829,0.9689878,0.0010891359],"about_ca_topic_score_codex":0.000013392774,"about_ca_topic_score_gemma":0.00000927583,"teacher_disagreement_score":0.40223372,"about_ca_system_score_codex":0.00028310769,"about_ca_system_score_gemma":0.0003641011,"threshold_uncertainty_score":0.9997081},"labels":[],"label_agreement":null},{"id":"W2304863478","doi":"10.1136/eb-2015-102294","title":"Control or overcontrol for covariates?","year":2016,"lang":"en","type":"article","venue":"Evidence-Based Mental Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"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":"Covariate; Baseline (sea); Outcome (game theory); Statistics; Variance (accounting); Econometrics; Medicine; Psychology; Demography; Mathematics; Economics; Biology","score_opus":0.2714903255851573,"score_gpt":0.4785412563800963,"score_spread":0.20705093079493903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2304863478","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":[0.0029882477,0.00032008465,0.9623134,0.029159846,0.00029315817,0.0038532212,0.00032976747,0.00064172834,0.00010051081],"genre_scores_gemma":[0.8663113,0.0001586606,0.12415322,0.007631052,0.00019590929,0.00085404154,0.0000076240462,0.00006366908,0.000624519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977213,0.00016459996,0.0006446564,0.00043092188,0.000358812,0.00067969284],"domain_scores_gemma":[0.99382067,0.0048868577,0.00041629854,0.00048608068,0.00012081778,0.00026929035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014151934,0.00028055426,0.0005526961,0.000101252175,0.00022484112,0.000028863506,0.00028200966,0.00010220468,0.0003934317],"category_scores_gemma":[0.0017902062,0.000167387,0.00013242057,0.00013134362,0.00010897353,0.00046621475,0.000027780934,0.000106557636,0.000041607647],"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":[0.010230263,0.00090328406,0.0011259568,0.0017261682,0.00013391403,0.0000121059675,0.00040931464,0.000005822453,0.04801857,0.6964183,0.09744338,0.14357296],"study_design_scores_gemma":[0.031193327,0.0125659425,0.0006694293,0.015211161,0.00015041573,0.00003703047,0.00024676204,0.0014381354,0.114571586,0.7781399,0.04379858,0.0019777634],"about_ca_topic_score_codex":0.00005423136,"about_ca_topic_score_gemma":0.00007445053,"teacher_disagreement_score":0.86332303,"about_ca_system_score_codex":0.00091183704,"about_ca_system_score_gemma":0.0007623987,"threshold_uncertainty_score":0.68258435},"labels":[],"label_agreement":null},{"id":"W2312181596","doi":"10.1111/spc3.12237","title":"On the (In)Validity of Tests of Simple Mediation: Threats and Solutions","year":2016,"lang":"en","type":"article","venue":"Social and Personality Psychology Compass","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":104,"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":"National Institute on Drug Abuse","keywords":"Mediation; Conceptualization; Simple (philosophy); Psychology; Context (archaeology); Social psychology; Epistemology; Computer science; Sociology; Social science; Artificial intelligence","score_opus":0.4013222090578177,"score_gpt":0.48602044924771803,"score_spread":0.08469824018990035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312181596","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":[0.9851204,0.00004306043,0.0024123723,0.010504439,0.000030187879,0.00013039201,0.00006716832,0.000022017302,0.0016699292],"genre_scores_gemma":[0.99934,0.000056403023,0.00034745169,0.000184288,0.000034507593,0.000014328283,0.0000010223957,0.000003928322,0.000018090175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99928975,0.00018125804,0.0001896881,0.0001262931,0.000096609205,0.0001163957],"domain_scores_gemma":[0.99797034,0.0017144566,0.00012584984,0.00011414516,0.000055333985,0.000019894293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005410876,0.00007170068,0.0002063602,0.000026448692,0.00007726053,0.0000020442553,0.00007270766,0.00008468881,0.000077673314],"category_scores_gemma":[0.0002599835,0.00004287781,0.000031791675,0.00007038737,0.0005247855,0.000035632063,0.000029872697,0.0000826862,6.1214075e-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":[0.000044363387,0.00014371134,0.054091386,0.000034332817,0.000019666006,5.347862e-7,0.0018908214,1.6415514e-8,0.002767731,0.93412614,0.0029474732,0.0039338474],"study_design_scores_gemma":[0.00021914914,0.00006443057,0.23373836,0.000015205589,0.0000061353817,0.0000012337525,0.00008658127,0.00000187396,0.00016378796,0.7655743,0.000087496956,0.000041475545],"about_ca_topic_score_codex":0.000019459307,"about_ca_topic_score_gemma":0.00018494946,"teacher_disagreement_score":0.17964698,"about_ca_system_score_codex":0.00001373607,"about_ca_system_score_gemma":0.0000126977275,"threshold_uncertainty_score":0.19335939},"labels":[],"label_agreement":null},{"id":"W2312523744","doi":"10.1371/journal.pmed.1001987","title":"Risk of Bias in Systematic Reviews of Non-Randomized Studies of Adverse Cardiovascular Effects of Thiazolidinediones and Cyclooxygenase-2 Inhibitors: Application of a New Cochrane Risk of Bias Tool","year":2016,"lang":"en","type":"article","venue":"PLoS Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":61,"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; Public Health Ontario","funders":"","keywords":"Medicine; Randomized controlled trial; Systematic review; Meta-analysis; Publication bias; Population; Confounding; Information bias; Internal medicine; MEDLINE; Selection bias; Pathology; Environmental health","score_opus":0.11158745063136817,"score_gpt":0.3768265426239632,"score_spread":0.26523909199259504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312523744","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":[0.9277117,0.032758746,0.033385642,0.000027798393,0.000041796124,0.005991852,0.000027827276,0.000025194096,0.000029403602],"genre_scores_gemma":[0.923761,0.06418984,0.011676688,0.000002269264,0.00004189562,0.00029398603,0.0000018997675,0.000024243636,0.000008175795],"study_design_codex":"systematic_review","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99465185,0.0011731422,0.0030514142,0.00024118982,0.0007392305,0.00014316296],"domain_scores_gemma":[0.9794596,0.014471776,0.0044311187,0.0009099992,0.0006764968,0.000051044408],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064630634,0.00028444073,0.0058231195,0.00036510112,0.000010752644,2.8895434e-7,0.00018280544,0.00012035841,0.0000043389464],"category_scores_gemma":[0.07479571,0.00015278521,0.00041952138,0.00044567735,0.00075278356,0.00009483357,0.00008314618,0.00010545836,3.641798e-7],"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":[0.0032403702,0.0008189533,0.0049200584,0.556855,0.004962036,0.000003418943,0.01109771,0.000019028286,0.413661,0.0015307199,0.00017429524,0.0027173774],"study_design_scores_gemma":[0.032870695,0.0008705506,0.0004699579,0.16815995,0.006216662,0.0000031794218,0.0010851189,0.0001801378,0.77063835,0.019311316,0.000002451397,0.00019166325],"about_ca_topic_score_codex":0.0003770927,"about_ca_topic_score_gemma":0.00002515501,"teacher_disagreement_score":0.38869506,"about_ca_system_score_codex":0.000029672578,"about_ca_system_score_gemma":0.00004793305,"threshold_uncertainty_score":0.9329977},"labels":[],"label_agreement":null},{"id":"W2312871991","doi":"10.1097/ede.0000000000000015","title":"Estimating Causal Effect with RCTs","year":2013,"lang":"en","type":"letter","venue":"Epidemiology","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":true,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Randomized controlled trial; Context (archaeology); Medicine; Covert; Deception; Physical therapy; Psychology; Internal medicine; Social psychology","score_opus":0.19768131595661156,"score_gpt":0.4445952550901146,"score_spread":0.24691393913350304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312871991","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":[0.0016787292,0.00020838842,0.49318364,0.49125513,0.00086956547,0.0020823795,0.000025538864,0.0022609304,0.008435698],"genre_scores_gemma":[0.0002602724,0.000006747539,0.6146403,0.37840265,0.0035327568,0.0006703187,0.00015289568,0.00018424951,0.0021498445],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950999,0.0019280369,0.00090329093,0.0008013058,0.00018957134,0.0010778967],"domain_scores_gemma":[0.9642178,0.033539865,0.0009736113,0.0010558498,0.000122124,0.00009075713],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0021286826,0.0007342067,0.0021213826,0.00017340189,0.00009551922,0.0000137494635,0.00052051287,0.00178523,0.00040228668],"category_scores_gemma":[0.018568652,0.0004938292,0.00015785875,0.00011891776,0.0003662303,0.00012946974,0.00016984713,0.0035340795,0.00034867958],"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":[0.0000071402073,0.000006786652,0.0006214978,0.000448618,0.00008611777,0.00019274754,0.000021604927,0.00001506666,0.000012095393,0.005772407,0.991409,0.0014069285],"study_design_scores_gemma":[0.00025655967,0.0010394341,0.000067159825,0.0006825472,0.00017396786,0.0003435629,0.0000017501067,0.0010840796,0.00015961245,0.839795,0.15551095,0.00088536774],"about_ca_topic_score_codex":0.00011941943,"about_ca_topic_score_gemma":0.000009262822,"teacher_disagreement_score":0.83589804,"about_ca_system_score_codex":0.00016738981,"about_ca_system_score_gemma":0.00006738799,"threshold_uncertainty_score":0.9997513},"labels":[],"label_agreement":null},{"id":"W2314210616","doi":"10.7202/1035914ar","title":"Le score de propension : un guide méthodologique pour les recherches expérimentales et quasi expérimentales en éducation","year":2016,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Humanities; Psychology; Political science; Art","score_opus":0.45761709353281127,"score_gpt":0.5102915203679868,"score_spread":0.05267442683517548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314210616","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":[0.34318608,0.0010158152,0.5942543,0.053488497,0.0007157511,0.0018785986,0.000036322414,0.0005039754,0.004920646],"genre_scores_gemma":[0.6457616,0.0015524346,0.34020284,0.00037862445,0.00027873195,0.0005582776,0.00021568392,0.00012196973,0.010929867],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9722238,0.024342813,0.0012416419,0.0008971019,0.00069975614,0.00059487706],"domain_scores_gemma":[0.9893198,0.007900444,0.000983598,0.0008881229,0.0007546342,0.00015339768],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037670333,0.00060872704,0.00055493717,0.0003093311,0.00028989586,0.0001306291,0.0004709626,0.0008340129,0.0005797191],"category_scores_gemma":[0.017648479,0.00053566316,0.00018286043,0.00033182628,0.00025425522,0.0016003272,0.00018251585,0.00056956755,0.00023064479],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084248444,0.0020902168,0.0042569963,0.0003668075,0.00013365508,0.000004091404,0.09248869,0.000059579397,0.47642103,0.3016685,0.01875858,0.103667594],"study_design_scores_gemma":[0.00086040015,0.00035126565,0.031037325,0.0018321406,0.00018982637,0.00007926088,0.010717786,0.00023194039,0.5586616,0.39242417,0.0028697345,0.0007445874],"about_ca_topic_score_codex":0.0008508465,"about_ca_topic_score_gemma":0.0010439521,"teacher_disagreement_score":0.3025755,"about_ca_system_score_codex":0.0042627957,"about_ca_system_score_gemma":0.0056175156,"threshold_uncertainty_score":0.9997095},"labels":[],"label_agreement":null},{"id":"W2314463908","doi":"10.1515/ijb-2012-0039","title":"The Effect of Error-in-Confounders on the Estimation of the Causal Parameter When Using Marginal Structural Models and Inverse Probability-of-Treatment Weights: A Simulation Study","year":2014,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"","keywords":"Marginal structural model; Econometrics; Weighting; Inverse probability weighting; Statistics; Sign (mathematics); Inverse probability; Confounding; Logistic regression; Mathematics; Empirical research; Empirical likelihood; Estimator; Posterior probability; Bayesian probability; Medicine","score_opus":0.14099169658779223,"score_gpt":0.41563104355077823,"score_spread":0.274639346962986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314463908","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":[0.90160656,0.000007663629,0.0974379,0.00025171196,0.00011340215,0.00054362894,0.00001912588,0.0000031653972,0.00001684589],"genre_scores_gemma":[0.984678,0.00000468713,0.015262262,0.000015198846,0.000021749465,0.000004606842,8.0800305e-7,0.000008838139,0.0000038999674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826086,0.0004522727,0.00062583556,0.000078791585,0.00049433036,0.00008792367],"domain_scores_gemma":[0.9911359,0.0072933654,0.0010109799,0.00022953644,0.00031364517,0.000016592263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011579524,0.00013189319,0.00023665237,0.0000660138,0.000075191325,0.00002738097,0.0003543592,0.00003255865,0.0000039906154],"category_scores_gemma":[0.0017418825,0.000052543317,0.00006574457,0.000060967053,0.0002993143,0.00011099589,0.00006576607,0.00015824125,7.378049e-8],"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":[0.0022100294,0.00031511704,0.016729398,0.00012868167,0.0008899917,0.0000052747832,0.010571672,0.60506034,0.001482506,0.34588888,0.000042362684,0.016675735],"study_design_scores_gemma":[0.00043041425,0.0008114385,0.0011013023,0.00011084526,0.000088867826,0.0000090631265,0.0002214129,0.4728561,0.002396326,0.5219357,0.0000012414566,0.00003727943],"about_ca_topic_score_codex":0.0000908678,"about_ca_topic_score_gemma":0.000098710305,"teacher_disagreement_score":0.17604682,"about_ca_system_score_codex":0.00020459986,"about_ca_system_score_gemma":0.000059326576,"threshold_uncertainty_score":0.21426544},"labels":[],"label_agreement":null},{"id":"W2316013226","doi":"10.1097/ede.0b013e3181f56fc0","title":"Accounting for Center Effects in Multicenter Trials","year":2010,"lang":"en","type":"letter","venue":"Epidemiology","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":"BC Studies","funders":"Canadian Institutes of Health Research","keywords":"Confounding; Medicine; Randomized controlled trial; Population; MEDLINE; Observational study; Sample size determination; Clinical trial; Family medicine; Internal medicine; Statistics; Environmental health","score_opus":0.3682306560980438,"score_gpt":0.5170263155245894,"score_spread":0.14879565942654566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316013226","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":[0.0012332165,0.00023892353,0.3475026,0.638438,0.003914948,0.006755554,0.00019587704,0.0007212744,0.0009996287],"genre_scores_gemma":[0.00032709457,0.000033782075,0.35487494,0.6363853,0.005529074,0.0017902104,0.00030063017,0.00016064571,0.0005983106],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933364,0.0025018742,0.0021644079,0.0007816156,0.00011153072,0.0011041813],"domain_scores_gemma":[0.8846862,0.11295677,0.0014763449,0.0007270515,0.00010938566,0.000044280583],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.010782855,0.00055301376,0.0032107078,0.00033302244,0.000048335394,0.0000120830155,0.000546094,0.0043986253,0.00010780465],"category_scores_gemma":[0.17062625,0.00044433417,0.0005045647,0.00007597254,0.00014782354,0.00011385211,0.00016242964,0.005322157,0.00003800307],"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":[0.00003725061,0.000040172188,0.0016342348,0.0008541528,0.000055307995,0.00003830583,0.000040873198,3.5360222e-7,0.00023166087,0.006289556,0.9886306,0.0021475353],"study_design_scores_gemma":[0.00072185934,0.00006127125,0.00006325126,0.0003100412,0.00005206452,0.0000074141285,0.0000018211299,0.00008950428,0.0002738444,0.51016027,0.4879483,0.00031036933],"about_ca_topic_score_codex":0.00003039455,"about_ca_topic_score_gemma":0.00006490166,"teacher_disagreement_score":0.5038707,"about_ca_system_score_codex":0.00013755613,"about_ca_system_score_gemma":0.00004196425,"threshold_uncertainty_score":0.99980086},"labels":[],"label_agreement":null},{"id":"W2316188450","doi":"10.9778/cmajo.20150036","title":"Current use of routinely collected health data to complement randomized controlled trials: a meta-epidemiological survey","year":2016,"lang":"en","type":"article","venue":"CMAJ Open","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Epidemiology; Randomized controlled trial; Complement (music); Medicine; Environmental health; Internal medicine; Biology","score_opus":0.9025846780532691,"score_gpt":0.6125923435989659,"score_spread":0.2899923344543033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316188450","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":[0.005421582,0.0006277115,0.953148,0.0058944393,0.00021346318,0.030510198,0.0037393526,0.00026345567,0.00018179772],"genre_scores_gemma":[0.3312789,0.001445268,0.6565381,0.001653878,0.000117506774,0.0069593363,0.0006683755,0.00010379042,0.0012348217],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.971487,0.02193644,0.004866547,0.0007369371,0.00043765982,0.000535446],"domain_scores_gemma":[0.8899136,0.1045975,0.0028633552,0.0018444697,0.000513236,0.00026782052],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08152683,0.00039582571,0.012688917,0.00013370921,0.00008725864,0.000083209816,0.0016860826,0.00007867317,0.001013559],"category_scores_gemma":[0.31322098,0.00016879883,0.0005951107,0.00030026012,0.00014249753,0.00033840974,0.0018642901,0.00014502072,0.00001602711],"study_design_candidate":"randomized_trial","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":[0.29211578,0.0012865106,0.0013405762,0.00013413322,0.008137899,0.000003144251,0.00029795247,0.0000069069133,0.00088064437,0.13594614,0.5484458,0.01140447],"study_design_scores_gemma":[0.71379256,0.0012300739,0.0032640316,0.0011690609,0.0044694706,0.0000055750606,0.000049940994,0.0009934767,0.0008116418,0.23528185,0.037674308,0.0012580167],"about_ca_topic_score_codex":0.0020917726,"about_ca_topic_score_gemma":0.0024346872,"teacher_disagreement_score":0.5107715,"about_ca_system_score_codex":0.0001342102,"about_ca_system_score_gemma":0.0003320012,"threshold_uncertainty_score":0.9998996},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2316976792","doi":"10.1097/ede.0000000000000160","title":"The Parametric g-Formula for Time-to-event Data","year":2014,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":189,"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 for Occupational Safety and Health; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Cancer Institute","keywords":"Event (particle physics); Event data; Parametric statistics; Statistics; Computer science; Mathematics; Econometrics; Physics; Covariate","score_opus":0.4063686748368892,"score_gpt":0.5184250915114785,"score_spread":0.11205641667458932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316976792","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":[0.0011444514,0.0000881383,0.9890667,0.006650461,0.0001112638,0.00066585327,0.000028904533,0.00025231732,0.0019919036],"genre_scores_gemma":[0.052375518,0.000064883774,0.9363266,0.004901119,0.00049707957,0.00048712653,0.00009661186,0.000068807516,0.0051822616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811065,0.00044295285,0.0005421318,0.0003602478,0.000064538144,0.00047949134],"domain_scores_gemma":[0.95573354,0.04235786,0.00022694223,0.0015182492,0.00006815044,0.0000952654],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074183918,0.00014306467,0.00043386884,0.0000662433,0.00015246318,0.000007012512,0.0009533236,0.00012384895,0.000054722997],"category_scores_gemma":[0.11100886,0.00008990727,0.00006209509,0.00015905063,0.000093349656,0.00006807144,0.0003760299,0.00015557007,0.00031707398],"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":[0.000024177063,0.000024742372,0.00013916432,0.000016977296,0.000023261266,1.6831564e-7,0.000013673896,0.00004079781,0.00007396904,0.60430783,0.32411948,0.07121576],"study_design_scores_gemma":[0.00006509141,0.00013000172,0.00009348307,0.000007681253,0.000011144183,0.000002719172,0.0000029598252,0.013537786,0.0001083806,0.64801383,0.3379431,0.00008380311],"about_ca_topic_score_codex":0.000006820209,"about_ca_topic_score_gemma":0.0000095843925,"teacher_disagreement_score":0.103590466,"about_ca_system_score_codex":0.000040952633,"about_ca_system_score_gemma":0.000019677369,"threshold_uncertainty_score":0.8964795},"labels":[],"label_agreement":null},{"id":"W2319214962","doi":"10.1097/ede.0000000000000188","title":"Time at Risk and Intention-to-treat Analyses","year":2014,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"National Institutes of Health","keywords":"Causal inference; Inference; Population; Medicine; Randomized controlled trial; Psychology; Actuarial science; Surgery; Computer science; Economics; Environmental health","score_opus":0.2919902481500145,"score_gpt":0.4978836412572379,"score_spread":0.20589339310722338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319214962","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":[0.5240996,0.00011649368,0.46814314,0.0010988101,0.000046150584,0.00020065063,0.000010543696,0.00039455606,0.0058900523],"genre_scores_gemma":[0.6584345,0.00016098612,0.33409002,0.0018228001,0.000111029985,0.00006716304,0.000016470687,0.000039215116,0.005257762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983781,0.000662584,0.00036619525,0.00028905438,0.000039938583,0.00026413763],"domain_scores_gemma":[0.9922995,0.006999599,0.00018731697,0.00035013416,0.000049468563,0.00011400738],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015023459,0.00014109767,0.00050286244,0.00009191392,0.00007890206,0.0000025667748,0.00011098376,0.000120620716,0.00026870324],"category_scores_gemma":[0.02269115,0.000109369,0.00006052524,0.00008089258,0.00015641926,0.00004707238,0.00016206528,0.00013227617,0.000351685],"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":[0.00015589023,0.00015045785,0.2063843,0.0001547855,0.00017107268,0.000008297724,0.0006319583,0.00011835008,0.035496287,0.51295257,0.18010002,0.06367601],"study_design_scores_gemma":[0.0001134241,0.00018256235,0.0054448075,0.000022725912,0.000053402997,0.000015442438,0.000011134911,0.0014413426,0.0022834514,0.98443615,0.005838385,0.00015714431],"about_ca_topic_score_codex":0.00006669531,"about_ca_topic_score_gemma":0.00004220402,"teacher_disagreement_score":0.47148362,"about_ca_system_score_codex":0.000048160673,"about_ca_system_score_gemma":0.0000036249937,"threshold_uncertainty_score":0.98554116},"labels":[],"label_agreement":null},{"id":"W2319338665","doi":"10.1111/caje.12249","title":"Viewpoint: The human capital approach to inference","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Inference; Context (archaeology); Computer science; Artificial intelligence; Machine learning; Causal inference; Econometrics; Economics","score_opus":0.4020192808062404,"score_gpt":0.3037138214272396,"score_spread":0.09830545937900076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319338665","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":[0.98264515,0.00004280097,0.0021798345,0.0039720526,0.00051957933,0.0004556738,0.00007789684,0.000016492997,0.010090511],"genre_scores_gemma":[0.98948914,0.000022974044,0.00837455,0.0009106138,0.0005483655,0.000043890526,0.0000035217188,0.00006541344,0.0005415264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978778,0.0000653051,0.0009081659,0.00034275613,0.000004989081,0.00080102665],"domain_scores_gemma":[0.9951728,0.00026776633,0.0011567094,0.0013816735,0.00028624764,0.0017347955],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001154025,0.00033681447,0.0006829021,0.00038686552,0.0009038128,0.00045697426,0.0022620426,0.00018191183,0.00011894284],"category_scores_gemma":[0.0018408262,0.00030864452,0.00022561438,0.000054005708,0.00038263106,0.0006940932,0.000093987364,0.00060630793,0.000022310029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068645245,0.00001096378,0.0010543094,0.000023858494,0.000059249138,0.00003270051,0.0015898676,0.00020978645,0.000032477466,0.994668,0.00087359163,0.0014383111],"study_design_scores_gemma":[0.00023709933,0.00020490735,0.0012686729,0.0001088299,0.000037677968,0.0002695076,0.00048216086,0.00010649205,0.0003569755,0.98973477,0.0068008713,0.00039200785],"about_ca_topic_score_codex":0.08049142,"about_ca_topic_score_gemma":0.9428544,"teacher_disagreement_score":0.862363,"about_ca_system_score_codex":0.0014906215,"about_ca_system_score_gemma":0.0013212026,"threshold_uncertainty_score":0.9999366},"labels":[],"label_agreement":null},{"id":"W2322253843","doi":"10.1097/ede.0000000000000053","title":"Constructing Inverse Probability Weights for Continuous Exposures","year":2014,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":139,"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":"Heteroscedasticity; Homoscedasticity; Mathematics; Statistics; Probability distribution; Quantile","score_opus":0.266417665166968,"score_gpt":0.4377748148809384,"score_spread":0.17135714971397037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322253843","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":[0.21658862,0.000023846847,0.77532494,0.0010551603,0.00023541604,0.00075142656,0.000010978606,0.00056004676,0.005449575],"genre_scores_gemma":[0.21970765,0.0000033528813,0.7790392,0.00065048656,0.00019927611,0.0002091274,0.000009194968,0.00002163245,0.00016007095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781597,0.00067347067,0.0006667675,0.00036795504,0.000046779674,0.00042905804],"domain_scores_gemma":[0.98101366,0.01793308,0.00038319544,0.0004483358,0.00013753344,0.000084193874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034867437,0.00017683675,0.00071591913,0.000048507332,0.00008492949,0.0000038432418,0.00019090026,0.00021256601,0.000051882613],"category_scores_gemma":[0.05429586,0.00014478549,0.000117514246,0.000050704093,0.00034078315,0.00008000354,0.00006568544,0.000186863,0.000010703535],"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":[0.00001790415,0.00002165878,0.028926425,0.00006791781,0.000013817557,3.0951833e-7,0.00006154238,0.000001451966,0.00020173326,0.9563742,0.005699419,0.008613566],"study_design_scores_gemma":[0.00023420663,0.0001921026,0.00026010053,0.00002560023,0.0000161339,0.00001390648,0.000059619568,0.0007779596,0.002765299,0.9889675,0.006530158,0.0001574497],"about_ca_topic_score_codex":0.00001908797,"about_ca_topic_score_gemma":0.000094508105,"teacher_disagreement_score":0.050809115,"about_ca_system_score_codex":0.00007040641,"about_ca_system_score_gemma":0.000023541614,"threshold_uncertainty_score":0.9536702},"labels":[],"label_agreement":null},{"id":"W2322636499","doi":"10.1097/mlr.0000000000000464","title":"Adjustment for Variable Adherence Under Hierarchical Structure","year":2016,"lang":"en","type":"article","venue":"Medical Care","topic":"Advanced Causal Inference Techniques","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":"Institute of Infection and Immunity","funders":"National Heart, Lung, and Blood Institute; U.S. Department of Veterans Affairs","keywords":"Confounding; Statistics; Econometrics; Random effects model; Instrumental variable; Randomized controlled trial; Multilevel model; Mathematics; Nonparametric statistics; Observational study; Categorical variable; Medicine; Meta-analysis; Internal medicine","score_opus":0.0889677207723866,"score_gpt":0.4064756191708927,"score_spread":0.3175078983985061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322636499","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":[0.009289263,0.00021794623,0.98545575,0.0017159783,0.0003127508,0.0005959323,0.00016261471,0.00041853634,0.0018312199],"genre_scores_gemma":[0.77689534,0.000031259493,0.22047153,0.0010398313,0.00044858234,0.00019240344,0.000024298502,0.00004845482,0.0008482787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985893,0.00004514127,0.00024323624,0.000276613,0.000513669,0.0003320577],"domain_scores_gemma":[0.99825,0.0009725295,0.000058613692,0.00032934424,0.00015664297,0.00023288743],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014536669,0.00015675437,0.00023443419,0.00003188154,0.00005534642,0.000008437063,0.00030140756,0.00025209412,0.0025805882],"category_scores_gemma":[0.0019157866,0.00009022427,0.000057597692,0.00007692819,0.00013650798,0.000071637456,0.00010290787,0.00018987509,0.000009836422],"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":[0.000039283215,0.00004182411,0.00010465559,0.00020955628,0.000024442512,0.000006494054,0.0002929065,4.149449e-7,0.002915959,0.88050365,0.015644504,0.100216284],"study_design_scores_gemma":[0.0005936246,0.0002551146,0.00008580876,0.00025568236,0.00002284209,0.00000936366,0.00014967122,0.000020572505,0.006177125,0.9793632,0.012885251,0.00018173168],"about_ca_topic_score_codex":0.000005333069,"about_ca_topic_score_gemma":0.000041452146,"teacher_disagreement_score":0.7676061,"about_ca_system_score_codex":0.0001444932,"about_ca_system_score_gemma":0.00018273058,"threshold_uncertainty_score":0.9983312},"labels":[],"label_agreement":null},{"id":"W2324021236","doi":"10.1097/ede.0000000000000237","title":"Variable Selection for Propensity Score Estimation via Balancing Covariates","year":2015,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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 Waterloo","funders":"","keywords":"Covariate; Propensity score matching; Statistics; Confounding; Average treatment effect; Estimator; Outcome (game theory); Matching (statistics); Causal inference; Inverse probability weighting; Poisson distribution; Econometrics; Mathematics","score_opus":0.35843125810130666,"score_gpt":0.43624797812403504,"score_spread":0.07781672002272838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324021236","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":[0.00005098451,0.000050730232,0.9242165,0.07246182,0.00046994057,0.0014385433,0.000039813523,0.00072777906,0.0005438622],"genre_scores_gemma":[0.0001361219,0.0000043347345,0.85230035,0.1431154,0.001932633,0.0005615551,0.00073847873,0.00009838311,0.00111273],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99672204,0.0007955206,0.0009505282,0.0006706942,0.00014476576,0.00071646925],"domain_scores_gemma":[0.9894828,0.008326659,0.0010271221,0.00049548433,0.0006017964,0.000066138346],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004506626,0.00044106197,0.0014489864,0.00016241318,0.00013763741,0.000013817143,0.00028910692,0.0017207053,0.00007143147],"category_scores_gemma":[0.029535443,0.00038880008,0.00012249187,0.00016949688,0.00010591828,0.00019251902,0.00010062295,0.0014806322,0.000033263546],"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":[0.000023163553,0.000015320433,0.00035442688,0.000430991,0.000057208985,0.0000030585388,0.000023069111,0.00017878505,0.00013701136,0.06527231,0.93279153,0.000713123],"study_design_scores_gemma":[0.00015263908,0.0002057985,0.000015833672,0.00014628515,0.00010714273,0.00006390759,9.590617e-7,0.019262195,0.00022861412,0.8566715,0.12280571,0.0003393864],"about_ca_topic_score_codex":0.00019230612,"about_ca_topic_score_gemma":0.000023205155,"teacher_disagreement_score":0.8099858,"about_ca_system_score_codex":0.0004791608,"about_ca_system_score_gemma":0.00022838285,"threshold_uncertainty_score":0.9998564},"labels":[],"label_agreement":null},{"id":"W2326057587","doi":"10.1371/journal.pone.0153010","title":"Quantification of Treatment Effect Modification on Both an Additive and Multiplicative Scale","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"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 Laval","funders":"","keywords":"Hazard ratio; Context (archaeology); Medicine; Multiplicative function; Observational study; Propensity score matching; Proportional hazards model; Absolute risk reduction; Relative risk; Survival analysis; Randomized controlled trial; Additive model; Internal medicine; Statistics; Confidence interval; Mathematics; Biology","score_opus":0.2446653644634531,"score_gpt":0.39605357708173533,"score_spread":0.15138821261828223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326057587","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":[0.97818846,0.0000082928755,0.020259924,0.000091938266,0.0000029774242,0.0007857095,0.00009772789,0.0001573791,0.00040760933],"genre_scores_gemma":[0.9702815,0.000095191055,0.02907185,0.0000056646463,0.000016581707,0.00037082293,0.00001666065,0.00001783442,0.00012392117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926853,0.00009659916,0.00017459769,0.00023833294,0.00012546887,0.00009647281],"domain_scores_gemma":[0.998446,0.00084025064,0.00018119054,0.00038961446,0.00009672419,0.000046231773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012911661,0.000121598634,0.00023015436,0.000059114067,0.000034108976,0.0000052928785,0.00006432237,0.00005637901,0.000020564894],"category_scores_gemma":[0.0002923721,0.00007514528,0.000021006997,0.000055173536,0.00009666152,0.00014348673,0.000011262002,0.000031719108,0.000012664817],"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":[0.000108676024,0.0015858542,0.000633792,0.000042621687,0.000063826184,1.3429027e-7,0.000566768,1.701141e-7,0.93143964,0.02511627,0.0000101549795,0.040432118],"study_design_scores_gemma":[0.00035255007,0.0018047836,0.002298035,0.00024612443,0.00006602746,1.8993654e-7,0.000033881388,0.0002853945,0.96327275,0.0315417,0.000005675303,0.00009289725],"about_ca_topic_score_codex":0.000011883816,"about_ca_topic_score_gemma":0.000009505112,"teacher_disagreement_score":0.04033922,"about_ca_system_score_codex":0.0001305797,"about_ca_system_score_gemma":0.000010633513,"threshold_uncertainty_score":0.30643356},"labels":[],"label_agreement":null},{"id":"W2326293200","doi":"10.1097/ede.0000000000000221","title":"The Quasi-cohort Approach in Pharmacoepidemiology","year":2014,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":62,"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":"Pharmacoepidemiology; Medicine; Cohort; Cohort study; Observational study; Nested case-control study; Pneumonia; Covariate; Intensive care medicine; Statistics; Internal medicine","score_opus":0.2639147808630067,"score_gpt":0.48437447309761084,"score_spread":0.22045969223460415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326293200","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":[0.03051328,0.00045262976,0.9358088,0.006460108,0.0003519557,0.0006944522,0.0000026152022,0.00049070024,0.02522546],"genre_scores_gemma":[0.7520624,0.00058783044,0.24059549,0.00501994,0.00042691236,0.0006860095,0.000016237256,0.00005901415,0.00054620043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99273604,0.0046653072,0.001145651,0.0005154917,0.00007940145,0.00085812033],"domain_scores_gemma":[0.9544321,0.044315986,0.0003847727,0.00071854744,0.000050222243,0.00009840017],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018705474,0.0002474625,0.00092178746,0.00009138786,0.00013878662,0.000003974025,0.00056874915,0.00028845307,0.000034300836],"category_scores_gemma":[0.047172118,0.00016009764,0.00011538125,0.00018147026,0.00044487766,0.00007484234,0.00014987287,0.0006951029,0.00004939913],"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":[0.000019281646,0.00006259968,0.07604744,0.000014743372,0.000018868768,9.646025e-7,0.000041507566,0.000039876715,0.00006207292,0.89690703,0.017561583,0.009224003],"study_design_scores_gemma":[0.00018507846,0.000091269525,0.008634643,0.00000934429,0.000011806333,0.00002220008,0.000028003507,0.009531736,0.000078713405,0.9522046,0.029026529,0.00017606447],"about_ca_topic_score_codex":0.00006886704,"about_ca_topic_score_gemma":0.000048450853,"teacher_disagreement_score":0.7215491,"about_ca_system_score_codex":0.00009487778,"about_ca_system_score_gemma":0.00002448208,"threshold_uncertainty_score":0.96085393},"labels":[],"label_agreement":null},{"id":"W2327805644","doi":"10.3233/jem-160423","title":"Model specification tests and the estimation of treatment effects: An application with random and non-random administrative records","year":2016,"lang":"en","type":"article","venue":"Journal of Economic and Social Measurement","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":"University of Waterloo","funders":"","keywords":"Bounding overwatch; Test (biology); Econometrics; Nonparametric statistics; Earnings; Computer science; Estimation; Limiting; Random effects model; Statistics; Economics; Mathematics; Accounting; Engineering; Artificial intelligence; Medicine","score_opus":0.16290518276954313,"score_gpt":0.3770801067298768,"score_spread":0.21417492396033366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2327805644","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":[0.6168128,0.00006645341,0.38203695,0.00037156235,0.000015679809,0.0005507277,0.0000034200546,0.000006071992,0.00013630986],"genre_scores_gemma":[0.9881797,0.00024838076,0.011443372,0.000007855933,0.000060570103,0.00004591443,3.4302204e-7,0.0000070492683,0.000006838282],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993464,0.000076594595,0.00033791582,0.00009120365,0.000088481305,0.000059433176],"domain_scores_gemma":[0.99882084,0.00033490025,0.00058258453,0.00007169842,0.00015531419,0.000034688757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087472197,0.00009540224,0.00031057888,0.00003166485,0.00007356838,0.00001744399,0.000037396374,0.00003745695,9.862437e-7],"category_scores_gemma":[0.00010927899,0.0000479127,0.000027722379,0.000011391195,0.00015715141,0.00020052468,0.0000058587048,0.000037498958,1.0499021e-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":[0.021971183,0.00081644935,0.0049484144,0.00044816465,0.0011436582,0.000002001228,0.023175864,0.00044715812,0.039202936,0.23233351,0.000251048,0.67525965],"study_design_scores_gemma":[0.0412344,0.0041725184,0.0071496745,0.0004528566,0.000692589,0.000028931723,0.0012786681,0.02375892,0.024043905,0.89675504,0.00005903958,0.00037344542],"about_ca_topic_score_codex":0.000008525075,"about_ca_topic_score_gemma":0.000058486345,"teacher_disagreement_score":0.67488617,"about_ca_system_score_codex":0.00021991182,"about_ca_system_score_gemma":0.00008492533,"threshold_uncertainty_score":0.19538233},"labels":[],"label_agreement":null},{"id":"W2337894698","doi":"10.2139/ssrn.2692274","title":"Sharp Instrumental Inequalities: Testing IV Independence Assumption","year":2015,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"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 Toronto","funders":"","keywords":"Independence (probability theory); Inequality; Instrumental variable; Econometrics; Mathematics; Statistics; Mathematical analysis","score_opus":0.28188118066557294,"score_gpt":0.4112924642807069,"score_spread":0.129411283615134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337894698","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":[0.7594542,0.00040564148,0.23259786,0.00024415224,0.00021844998,0.00027837782,0.000005196771,0.00050944556,0.0062866886],"genre_scores_gemma":[0.98099405,0.00014160943,0.017734874,0.000063852414,0.00026359656,0.000015397929,0.0000032167436,0.000040090028,0.00074332673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969007,0.00013104155,0.00046963678,0.00020545331,0.0006070433,0.0016861643],"domain_scores_gemma":[0.99877095,0.00021979527,0.00035490567,0.00021591298,0.00028301412,0.00015542372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003302862,0.00020852858,0.00023686312,0.00013775667,0.00014278504,0.00008256638,0.00035716573,0.00013511634,0.000031925356],"category_scores_gemma":[0.0019068669,0.00019008805,0.0000599956,0.00022225855,0.00005686639,0.00074752996,0.00009732322,0.0022489831,0.000039391376],"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":[0.000044031676,0.00010209444,0.0043406705,0.000019207646,0.00006502758,0.000011271428,0.00067289907,0.0000132501555,0.0017969771,0.9608724,0.0002616797,0.031800482],"study_design_scores_gemma":[0.0004437005,0.00047663847,0.000043202785,0.000077832374,0.000019797888,0.0009104848,0.003955381,0.00021242758,0.0012072991,0.99226743,0.00016008715,0.00022573481],"about_ca_topic_score_codex":0.00006565724,"about_ca_topic_score_gemma":0.0002533004,"teacher_disagreement_score":0.22153984,"about_ca_system_score_codex":0.0022688415,"about_ca_system_score_gemma":0.0019056014,"threshold_uncertainty_score":0.97708374},"labels":[],"label_agreement":null},{"id":"W2340048191","doi":"10.1097/ede.0000000000000487","title":"Targeted Maximum Likelihood Estimation for Pharmacoepidemiologic Research","year":2016,"lang":"en","type":"article","venue":"Epidemiology","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":"Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Estimation; Statistics; Maximum likelihood; Mathematics; Economics","score_opus":0.5866250288778323,"score_gpt":0.5867883144975042,"score_spread":0.0001632856196719379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340048191","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":[0.011369058,0.00026036403,0.9700657,0.015390548,0.00023505437,0.0010435833,0.000040046547,0.000690811,0.00090481807],"genre_scores_gemma":[0.23801635,0.00023993441,0.7584376,0.0012745721,0.00033749297,0.0011524274,0.00002280999,0.000056337136,0.00046251962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946898,0.002377995,0.000987607,0.00061587716,0.00013490938,0.0011938094],"domain_scores_gemma":[0.9335082,0.065036446,0.00034632554,0.00056411733,0.00037181692,0.00017305536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0175623,0.00024401069,0.0007822244,0.00022725986,0.00018893853,0.0000039994266,0.0004354063,0.00036524047,0.00030267128],"category_scores_gemma":[0.13885301,0.00015099642,0.00015680696,0.00021492675,0.0004096844,0.00019957114,0.0001510042,0.00034718457,0.00016657518],"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":[0.00012625506,0.00008855154,0.0019175309,0.00007787569,0.000043833694,0.0000030281103,0.000045842702,0.000008056349,0.020312186,0.62536037,0.1879143,0.16410214],"study_design_scores_gemma":[0.0004388774,0.0003436161,0.00026334435,0.00006518081,0.000014459439,0.000009389303,0.000016684713,0.0013700374,0.009391158,0.977539,0.010346678,0.0002015535],"about_ca_topic_score_codex":0.000016364496,"about_ca_topic_score_gemma":0.0000074441828,"teacher_disagreement_score":0.35217863,"about_ca_system_score_codex":0.00022324147,"about_ca_system_score_gemma":0.000070025344,"threshold_uncertainty_score":0.8684008},"labels":[],"label_agreement":null},{"id":"W2342168697","doi":"10.1002/hec.3342","title":"The Long-Term Effects of Cancer on Employment and Earnings","year":2016,"lang":"en","type":"article","venue":"Health Economics","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Statistics Canada","funders":"Pennsylvania State University","keywords":"Microdata (statistics); Earnings; Census; Demography; History; Medicine; Gerontology; Sociology; Economics; Accounting; Population","score_opus":0.08672492711953217,"score_gpt":0.42082808021937634,"score_spread":0.3341031530998442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342168697","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":[0.9941954,0.00036579656,0.002414991,0.0023400234,0.00010636166,0.00041041008,0.0000045910797,0.000058466347,0.00010393571],"genre_scores_gemma":[0.9802528,0.016256923,0.002021219,0.00072533067,0.00006410625,0.00016685187,4.4168104e-7,0.000036034387,0.00047627045],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993615,0.00003343632,0.00024902998,0.00013121935,0.000031795265,0.00019299997],"domain_scores_gemma":[0.99829584,0.0011289486,0.00026744537,0.00022258429,0.00001795642,0.000067198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022156652,0.000087234315,0.00018349105,0.00002326341,0.000078356505,0.0000073299316,0.00008374028,0.000035561563,0.000009241951],"category_scores_gemma":[0.00012289885,0.000050561564,0.000020746744,0.00001441574,0.00007567152,0.000047545753,0.00004016913,0.000061333216,0.0000041556827],"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":[0.00007921191,0.00007843525,0.07864646,0.0007427654,0.000052126532,0.0000012255488,0.00064712117,0.0000022719773,0.0003016307,0.21154463,0.000925693,0.70697844],"study_design_scores_gemma":[0.0028503295,0.0031839875,0.45723826,0.003234527,0.000048763297,0.000010615862,0.00006273457,0.0000981142,0.09485533,0.42097026,0.016587786,0.00085928285],"about_ca_topic_score_codex":0.000032226926,"about_ca_topic_score_gemma":0.00031320815,"teacher_disagreement_score":0.7061191,"about_ca_system_score_codex":0.00017372314,"about_ca_system_score_gemma":0.00006162228,"threshold_uncertainty_score":0.20618409},"labels":[],"label_agreement":null},{"id":"W2342351145","doi":"10.2139/ssrn.2748490","title":"Stress-Testing with Parametric Models and Flexible Probabilities","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Université de Sherbrooke; HEC Montréal","funders":"","keywords":"Stress testing (software); Stress (linguistics); Parametric statistics; Structural engineering; Computer science; Reliability engineering; Engineering; Mathematics; Statistics","score_opus":0.163380266897334,"score_gpt":0.3589149930101895,"score_spread":0.19553472611285547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342351145","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":[0.35601607,0.00072245614,0.64108187,0.00025105558,0.000013274511,0.00021012721,0.0000030264482,0.00026295663,0.00143915],"genre_scores_gemma":[0.95075256,0.0008685704,0.04724235,0.000012190675,0.000059948612,0.000020858986,1.9345121e-7,0.00003521558,0.0010081436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978178,0.000055461704,0.00025346194,0.00019861577,0.0002406857,0.001433967],"domain_scores_gemma":[0.9986753,0.00068290863,0.00019281563,0.00019341437,0.00017824404,0.000077312754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090117106,0.00017560329,0.00021478873,0.00015101979,0.00013324886,0.000047863792,0.00016466856,0.000061531944,0.000009140638],"category_scores_gemma":[0.0006536822,0.000099293495,0.000028607477,0.00025173553,0.00012323257,0.00055695,0.000043703018,0.00067443046,0.0000019509787],"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":[0.000032251533,0.000040467992,0.00228751,0.000023791587,0.000047066547,0.00000247607,0.000069742746,0.000030301871,0.00032994652,0.96030796,0.000013214634,0.036815297],"study_design_scores_gemma":[0.00032791376,0.0006356744,0.00003459522,0.00019223409,0.000024116438,0.0004532667,0.00041579534,0.00014109735,0.0019001187,0.995686,0.000015163814,0.00017404577],"about_ca_topic_score_codex":0.000013249305,"about_ca_topic_score_gemma":0.00011104675,"teacher_disagreement_score":0.59473646,"about_ca_system_score_codex":0.00051389314,"about_ca_system_score_gemma":0.00071571686,"threshold_uncertainty_score":0.40490714},"labels":[],"label_agreement":null},{"id":"W2345813927","doi":"","title":"Event History Analysis in Longitudinal Cohort Studies with Intermittent Inspection Times","year":2016,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Event (particle physics); History; Cohort; Aeronautics; Statistics; Engineering; Mathematics; Physics","score_opus":0.0530679014943403,"score_gpt":0.3110483358790242,"score_spread":0.2579804343846839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345813927","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":[0.9970446,0.00028388956,0.0008471758,0.0001052247,0.000120045486,0.0003875243,0.0000117300015,0.00020488676,0.0009948928],"genre_scores_gemma":[0.6433251,0.00072463317,0.006530123,0.000004116767,0.000023266224,0.0000057507136,0.000113925336,0.000039911418,0.3492332],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99871695,0.0000700466,0.00021709948,0.00044716417,0.00032898036,0.00021976864],"domain_scores_gemma":[0.99858475,0.00010510302,0.00053108926,0.0003953757,0.0003345674,0.000049095594],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021928054,0.00029124232,0.0008343859,0.0009442968,0.00007032511,0.000004274559,0.0002502684,0.00019606111,0.00021816054],"category_scores_gemma":[0.000048396894,0.0002539666,0.00020434594,0.00030110517,0.0001744669,0.00025140357,0.00006198037,0.00023811786,0.000010622044],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040114126,0.0018737165,0.38410795,0.004758181,0.034173224,0.0011858884,0.48933837,0.0001111465,0.0045241266,0.0435741,0.02075445,0.011587423],"study_design_scores_gemma":[0.0029429558,0.0019477091,0.40744385,0.0069344165,0.017434394,0.0000188074,0.47674507,0.0002406703,0.008567027,0.07396456,0.0005816027,0.003178934],"about_ca_topic_score_codex":0.0050917375,"about_ca_topic_score_gemma":0.111464806,"teacher_disagreement_score":0.35371956,"about_ca_system_score_codex":0.0013936232,"about_ca_system_score_gemma":0.0000814247,"threshold_uncertainty_score":0.99999124},"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":"W2378268168","doi":"10.1002/sim.6979","title":"A flexible parametric approach for estimating continuous‐time inverse probability of treatment and censoring weights","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Cancer Care Ontario; Public Health Ontario; University of Toronto","funders":"","keywords":"Inverse probability; Censoring (clinical trials); Marginal structural model; Inverse probability weighting; Parametric statistics; Statistics; Weighting; Event (particle physics); Computer science; Marginal distribution; Proportional hazards model; Confounding; Parametric model; Econometrics; Mathematics; Posterior probability; Medicine; Estimator; Random variable","score_opus":0.13772868312824896,"score_gpt":0.40989090075438367,"score_spread":0.2721622176261347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2378268168","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":[0.030613244,0.000030315412,0.96743536,0.00004777326,0.000031314365,0.00097552227,0.00011596638,0.00008133832,0.0006691497],"genre_scores_gemma":[0.044040788,0.00003456295,0.955419,0.000007991401,0.000042598745,0.00015423546,0.000011243853,0.00001938531,0.00027020773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882144,0.000055402325,0.0005085285,0.00025810758,0.0001309219,0.00022558574],"domain_scores_gemma":[0.99594,0.0033595215,0.00023840241,0.00025632943,0.00014005473,0.00006567089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006184448,0.00016699906,0.0005381357,0.00017004421,0.00003162282,0.0000032962605,0.00007980157,0.00006134546,0.00002568682],"category_scores_gemma":[0.0062149963,0.000099697936,0.000017589546,0.00016964358,0.00031454716,0.000056475816,0.00003068544,0.000058269336,5.738456e-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":[0.00019196831,0.00051968347,0.0075698425,0.0017211791,0.00009150749,0.0000075923517,0.002018473,0.00003412476,0.008836021,0.8458502,0.0013440968,0.13181525],"study_design_scores_gemma":[0.0016457463,0.0010882235,0.00013153793,0.000404662,0.000064017084,0.0000044535755,0.00009328488,0.016926,0.0038904236,0.9755436,0.00006697378,0.0001410766],"about_ca_topic_score_codex":0.00004468844,"about_ca_topic_score_gemma":0.000007684099,"teacher_disagreement_score":0.13167419,"about_ca_system_score_codex":0.00020595247,"about_ca_system_score_gemma":0.000038803595,"threshold_uncertainty_score":0.744038},"labels":[],"label_agreement":null},{"id":"W2400611004","doi":"10.1515/ijb-2015-0015","title":"Influence Re-weighted G-Estimation","year":2015,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Estimator; Weighting; Estimation; Parametric statistics; Computer science; Robust statistics; Marginal structural model; Average treatment effect; Econometrics; Mathematical optimization; Inverse probability weighting; Outcome (game theory); Mathematics; Parametric model; Statistics; Causal inference; Medicine; Economics","score_opus":0.14528751352761418,"score_gpt":0.43528432890430363,"score_spread":0.2899968153766894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400611004","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":[0.18779936,0.000054247677,0.8074397,0.0028496669,0.0005134274,0.00011057459,0.00004034986,0.00005626744,0.0011364244],"genre_scores_gemma":[0.71744144,0.000028479399,0.28198382,0.00030871195,0.00014315407,0.0000016017735,0.0000036357335,0.000011730446,0.00007745501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984917,0.000061154635,0.00052059756,0.00006237298,0.00076238386,0.00010178128],"domain_scores_gemma":[0.9966414,0.00077780534,0.0006551127,0.00015365613,0.0016933373,0.000078719015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080859667,0.00009773357,0.00014449905,0.0001070136,0.000029446042,0.000060339757,0.0006504969,0.000040303745,0.000023562368],"category_scores_gemma":[0.0042263353,0.000064066146,0.000038505088,0.00009412574,0.00010163408,0.00026421132,0.00007746007,0.00021472588,0.00001681094],"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":[0.0003394343,0.00020639111,0.0005891185,0.00001867397,0.00026472934,0.0003007232,0.0024545745,0.0023250005,0.002696852,0.8793716,0.08583302,0.025599904],"study_design_scores_gemma":[0.0003078086,0.00014169044,0.00017798682,0.000084769694,0.000032135355,0.00025190017,0.00019470569,0.0034003323,0.007648514,0.98571175,0.0019612373,0.00008715169],"about_ca_topic_score_codex":0.0000101047635,"about_ca_topic_score_gemma":0.0000066293537,"teacher_disagreement_score":0.52964205,"about_ca_system_score_codex":0.00017292675,"about_ca_system_score_gemma":0.00015064448,"threshold_uncertainty_score":0.5059624},"labels":[],"label_agreement":null},{"id":"W2403763108","doi":"10.1097/sla.0000000000001797","title":"Potential Pitfalls of Reporting and Bias in Observational Studies With Propensity Score Analysis Assessing a Surgical Procedure","year":2016,"lang":"en","type":"review","venue":"Annals of Surgery","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":141,"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":"","keywords":"Observational study; Propensity score matching; Medicine; Sample size determination; Randomized controlled trial; Covariate; Selection bias; Missing data; Meta-analysis; MEDLINE; Study heterogeneity; Medical physics; Statistics; Surgery; Internal medicine; Pathology","score_opus":0.9070000380051212,"score_gpt":0.5712733601569768,"score_spread":0.33572667784814436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403763108","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":[0.14817555,0.85074335,0.00033969188,0.000067127134,0.00001994009,0.00053020584,0.00003131301,0.000054424534,0.000038402814],"genre_scores_gemma":[0.0187449,0.97861767,0.0024325985,0.000008703551,0.00003989289,0.00006001916,0.000028069648,0.00003603752,0.000032121872],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99563503,0.000254863,0.0029213838,0.00043506883,0.00048277233,0.00027090445],"domain_scores_gemma":[0.98797995,0.003581533,0.0070819766,0.00035765255,0.0009467933,0.000052088682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039160848,0.00036021209,0.004460107,0.0006863823,0.000039003044,0.000022064378,0.00011151167,0.00021349202,0.000008387319],"category_scores_gemma":[0.007970725,0.00021621014,0.0005305051,0.0010727306,0.00026270238,0.0003545445,0.00014820555,0.0002397836,1.6859028e-7],"study_design_candidate":"systematic_review","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":[0.00012306879,0.00060243934,0.31191152,0.16223449,0.0077603585,0.0012236846,0.00022592564,0.0000051147267,0.000017469094,0.004550861,0.00072127755,0.5106238],"study_design_scores_gemma":[0.0005585258,0.0003085582,0.0689358,0.81006116,0.011465661,0.0009580747,0.000346716,0.00002520148,0.0010111055,0.086519,0.015906157,0.0039040314],"about_ca_topic_score_codex":0.000012570698,"about_ca_topic_score_gemma":0.000021576643,"teacher_disagreement_score":0.6478267,"about_ca_system_score_codex":0.00002745984,"about_ca_system_score_gemma":0.0005179391,"threshold_uncertainty_score":0.95422786},"labels":[],"label_agreement":null},{"id":"W2404984931","doi":"10.1016/j.jclinepi.2016.04.014","title":"Specifying a target trial prevents immortal time bias and other self-inflicted injuries in observational analyses","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":974,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Observational study; Emulation; Randomized controlled trial; Computer science; Medical physics; Research design; Simple (philosophy); Clinical trial; Medicine; Psychology; Statistics; Social psychology; Surgery; Mathematics","score_opus":0.8894193828691276,"score_gpt":0.6870352047744127,"score_spread":0.20238417809471487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404984931","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":[0.003012915,0.9862737,0.007548017,0.00036454308,0.0008503029,0.0013860472,0.000101514735,0.00011033787,0.0003526204],"genre_scores_gemma":[0.000016092663,0.8535389,0.14412016,0.0003103035,0.0017534263,0.000035214023,0.000008386639,0.00006459206,0.00015293695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97504103,0.011262129,0.012413562,0.00048284128,0.00032223488,0.00047819968],"domain_scores_gemma":[0.8614943,0.12497122,0.012658596,0.0004081633,0.00022181176,0.00024588263],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032090116,0.0005453135,0.010913036,0.0004618366,0.000038502294,0.000014097905,0.00055900286,0.0012738105,0.00034934023],"category_scores_gemma":[0.18174127,0.00032214777,0.0016486503,0.0002685804,0.00032376955,0.00025514598,0.00020181989,0.0018237003,0.000020038871],"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":[0.009361404,0.0028692256,0.027385067,0.010510357,0.006798446,0.00026273678,0.00016540814,0.000006508214,0.0000036831493,0.0641276,0.016626935,0.8618826],"study_design_scores_gemma":[0.0051443237,0.0011304753,0.0004353772,0.011559692,0.0007072682,0.00010619022,0.0000034108807,0.000037645346,6.229564e-7,0.36574528,0.61469245,0.0004372375],"about_ca_topic_score_codex":0.0000042738816,"about_ca_topic_score_gemma":0.0000030270407,"teacher_disagreement_score":0.86144537,"about_ca_system_score_codex":0.00013675189,"about_ca_system_score_gemma":0.00064357667,"threshold_uncertainty_score":0.99992305},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2405799747","doi":"10.13063/2327-9214.1221","title":"Observational Studies of Drug Safety in Multi-Database Studies: Methodological Challenges and Opportunities","year":2016,"lang":"en","type":"article","venue":"eGEMs (Generating Evidence & Methods to improve patient outcomes)","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":true,"ca_institutions":"University of Manitoba; University of British Columbia; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Observational study; Drug; Database; Data science; Medicine; Computer science; Pharmacology; Internal medicine","score_opus":0.8874851599926737,"score_gpt":0.6117314557646698,"score_spread":0.27575370422800394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405799747","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":[0.3098503,0.023032034,0.65680337,0.0074401386,0.00064541027,0.0018228546,0.000078474615,0.00029262147,0.000034755212],"genre_scores_gemma":[0.024443006,0.010959655,0.962942,0.00071401213,0.00004266947,0.0005538304,0.0000015912502,0.000042631866,0.0003005731],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9935343,0.002902666,0.0017042733,0.0008234908,0.000531986,0.00050325674],"domain_scores_gemma":[0.95853823,0.03902686,0.00077788386,0.00072881836,0.00076020404,0.00016800291],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010795242,0.0004982851,0.0014794194,0.00027779047,0.00013342436,0.000017189275,0.00032902148,0.00012018449,0.000013659624],"category_scores_gemma":[0.10466236,0.0003116666,0.00013045638,0.00018867079,0.00037089302,0.0007304662,0.00085557916,0.00024774123,0.0000015183675],"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":[0.00015001331,0.00024091637,0.003745587,0.0009884203,0.0002771609,0.00001925437,0.01658337,0.000029853249,0.22263636,0.06591194,0.00020729356,0.6892098],"study_design_scores_gemma":[0.0038709168,0.0035229945,0.0125542935,0.017369777,0.0004320471,0.000028238812,0.05211221,0.0016238458,0.59214485,0.30979583,0.0026590244,0.0038860203],"about_ca_topic_score_codex":0.000016552262,"about_ca_topic_score_gemma":0.00008656098,"teacher_disagreement_score":0.68532383,"about_ca_system_score_codex":0.00028380536,"about_ca_system_score_gemma":0.00008391202,"threshold_uncertainty_score":0.99993354},"labels":[],"label_agreement":null},{"id":"W2409841663","doi":"","title":"Illustration of time-dependent bias using individual patient data from the Canadian study","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Econometrics; Statistics; Psychology; Mathematics","score_opus":0.5698719868315746,"score_gpt":0.43072566136371876,"score_spread":0.13914632546785582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409841663","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":[0.9655921,0.000008493466,0.031316504,0.0002025647,0.000046065576,0.00077414414,0.0006300155,0.00009978833,0.0013303563],"genre_scores_gemma":[0.9840862,0.0000013157498,0.015695984,0.00005267125,0.000026995296,0.000006816922,0.000024345596,0.000013540419,0.00009208615],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892825,0.00010984534,0.00029328064,0.00019462143,0.00032488198,0.0001491364],"domain_scores_gemma":[0.9982532,0.0005448398,0.00015410113,0.00090518774,0.00008371707,0.000058927744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045130748,0.000098373464,0.00013270257,0.000043162887,0.000083178355,0.000027837055,0.00048506501,0.00005147561,0.00058382086],"category_scores_gemma":[0.00057167705,0.00005017977,0.0000137650995,0.00006750624,0.000052216972,0.00024006414,0.00022697459,0.000065038475,0.000022015282],"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":[0.00020557745,0.0047737975,0.31415337,0.00006839879,0.0027538287,0.00013435946,0.03630334,0.00013124275,0.08872517,0.10966019,0.0988579,0.34423283],"study_design_scores_gemma":[0.0029168895,0.0022060808,0.02748968,0.00069661345,0.0012743957,0.000020723905,0.016631061,0.0039313193,0.1587428,0.781613,0.0024531968,0.0020242757],"about_ca_topic_score_codex":0.12952799,"about_ca_topic_score_gemma":0.5778593,"teacher_disagreement_score":0.6719528,"about_ca_system_score_codex":0.00009525183,"about_ca_system_score_gemma":0.00015634859,"threshold_uncertainty_score":0.87626857},"labels":[],"label_agreement":null},{"id":"W2413921790","doi":"","title":"Causal inference under directed acyclic graphs","year":2015,"lang":"en","type":"dissertation","venue":"Memorial University Research Repository (Memorial University)","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":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Directed acyclic graph; Censoring (clinical trials); Inference; Phenotype; Causal inference; Genetic marker; Genetics; Statistics; Mathematics; Biology; Computer science; Algorithm; Artificial intelligence; Gene","score_opus":0.12514192518061737,"score_gpt":0.3894251269416274,"score_spread":0.26428320176101006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2413921790","genre_codex":"empirical","genre_gemma":"other","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":[0.5472199,0.00010374401,0.0008507969,0.00009986848,0.018279321,0.0032482361,0.00022097766,0.0035374765,0.42643973],"genre_scores_gemma":[0.46424958,0.0007283957,0.0058955797,0.000015307483,0.0077425446,0.000008293751,0.0015243377,0.00044723108,0.51938874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99079657,0.0024654835,0.0006356635,0.001724693,0.002846679,0.0015309205],"domain_scores_gemma":[0.9904293,0.0022034387,0.00072152395,0.0016762216,0.0039717956,0.0009977277],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0016102226,0.00097068335,0.0013936776,0.003181499,0.0017192147,0.0002774962,0.0029647783,0.001851332,0.00018141206],"category_scores_gemma":[0.0021623676,0.0011917097,0.0005170727,0.0037046904,0.00081772916,0.0014066573,0.0008755234,0.0034180419,0.00010532374],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021212962,0.0019618075,0.00034003126,0.001260733,0.001983225,0.012328418,0.005298957,0.000070204245,0.0573583,0.7360246,0.15942605,0.0027347086],"study_design_scores_gemma":[0.012001033,0.0030029651,0.0006816552,0.0019400587,0.0020724866,0.00009032362,0.039315205,0.00018217663,0.047106605,0.58872837,0.29895332,0.005925818],"about_ca_topic_score_codex":0.002882182,"about_ca_topic_score_gemma":0.0031683042,"teacher_disagreement_score":0.14729626,"about_ca_system_score_codex":0.003861324,"about_ca_system_score_gemma":0.0038914992,"threshold_uncertainty_score":0.9999627},"labels":[],"label_agreement":null},{"id":"W2414683219","doi":"10.1016/j.athoracsur.2014.04.038","title":"Reply","year":2014,"lang":"en","type":"letter","venue":"The Annals of Thoracic Surgery","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":"University of Toronto","funders":"","keywords":"Propensity score matching; Confounding; Medicine; Observational study; Sample size determination; Scopus; Randomized controlled trial; Internal medicine; Cardiology; Publication bias; Odds ratio; MEDLINE; Statistics; Mathematics","score_opus":0.46050029952635,"score_gpt":0.4922971498443505,"score_spread":0.0317968503180005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414683219","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":[0.0008675255,0.0004444456,0.004893547,0.9859068,0.00035178274,0.00037228377,0.000035382924,0.0005559007,0.0065723243],"genre_scores_gemma":[0.0022258402,0.00045426353,0.0029912968,0.98708105,0.002572814,0.00008787553,0.00007306485,0.0001713503,0.0043424247],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969159,0.00067516597,0.00089168915,0.0003590435,0.00062503095,0.00053320185],"domain_scores_gemma":[0.9847863,0.011493181,0.0012307267,0.0020701373,0.0003779224,0.000041787305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037477075,0.00040940865,0.0011326062,0.00025780412,0.00007510587,0.000030863437,0.0007693457,0.00052359165,0.00023510278],"category_scores_gemma":[0.004026072,0.000275942,0.00059849303,0.00025153966,0.0002824736,0.000110112334,0.0001717477,0.0014187687,0.00007300438],"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":[0.000020909616,0.000015109338,0.000010857807,0.000540911,0.00007728436,0.000047038357,0.000035483914,2.1359824e-7,0.000020519976,0.0007066031,0.98928326,0.009241822],"study_design_scores_gemma":[0.0000032856394,0.000014864679,0.0000015962864,0.0004762963,0.000041516345,0.000021491716,0.000005014578,0.000003080262,0.013405762,0.3629243,0.6228752,0.00022754227],"about_ca_topic_score_codex":0.00003175571,"about_ca_topic_score_gemma":8.760361e-7,"teacher_disagreement_score":0.36640802,"about_ca_system_score_codex":0.000014925348,"about_ca_system_score_gemma":0.00008702541,"threshold_uncertainty_score":0.9999693},"labels":[],"label_agreement":null},{"id":"W2414768697","doi":"10.1097/ede.0000000000000117","title":"Commentary","year":2014,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Counterfactual thinking; Argument (complex analysis); Meaning (existential); Psychological intervention; Causal inference; Race (biology); Sociology; Psychology; Epistemology; Social psychology; Econometrics; Gender studies; Mathematics; Medicine; Philosophy","score_opus":0.37566383627024375,"score_gpt":0.48119846562411694,"score_spread":0.1055346293538732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414768697","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":[0.00000818666,0.00010301003,0.11922873,0.8738457,0.00033095537,0.0002480815,0.000017744896,0.00060444226,0.005613165],"genre_scores_gemma":[0.00002430395,0.00003616745,0.12996781,0.86355656,0.0046590175,0.00010985559,0.0002923206,0.00008064447,0.0012733385],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962782,0.0016373304,0.0008150687,0.0004982752,0.00009859459,0.00067248003],"domain_scores_gemma":[0.9781051,0.020227473,0.0005775296,0.0009894731,0.000049991584,0.000050402312],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0018491889,0.0003976909,0.0013498488,0.00012021471,0.00005496914,0.00000320688,0.0005482881,0.0016013783,0.0004966549],"category_scores_gemma":[0.0068753236,0.00034060105,0.00019996632,0.000052074083,0.00025916545,0.000039598093,0.00016797813,0.0027882422,0.00021625555],"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":[0.0000019027993,0.000006609086,0.00014748826,0.00011969729,0.00003055761,0.000048829006,0.00000873874,1.8999323e-7,0.0000024862302,0.02536697,0.97374785,0.0005186705],"study_design_scores_gemma":[0.00003766377,0.000045286248,0.000002666258,0.0000294262,0.000022092641,0.000025710136,6.6861696e-7,0.00001287067,0.00001365304,0.48495436,0.51468736,0.00016827039],"about_ca_topic_score_codex":0.000047029705,"about_ca_topic_score_gemma":0.0000052175997,"teacher_disagreement_score":0.4595874,"about_ca_system_score_codex":0.00012343298,"about_ca_system_score_gemma":0.000016261385,"threshold_uncertainty_score":0.9999046},"labels":[],"label_agreement":null},{"id":"W2417381186","doi":"10.1097/ede.0000000000000485","title":"Commentary","year":2016,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec; McGill University Health Centre; Canadian Institutes of Health Research","funders":"","keywords":"Medicine","score_opus":0.3637801306346827,"score_gpt":0.4849162716428969,"score_spread":0.12113614100821424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417381186","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":[0.000005714811,0.0001508095,0.0785396,0.9139309,0.00044965258,0.00026544274,0.00007671199,0.00060431514,0.0059768716],"genre_scores_gemma":[0.0000075358344,0.000098753015,0.07873099,0.90965104,0.0072485665,0.00013179603,0.00013218472,0.00008285162,0.003916297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666303,0.0011963454,0.000773389,0.00050173694,0.000096183234,0.0007693271],"domain_scores_gemma":[0.97720927,0.02121151,0.0005327619,0.00094474124,0.000051959087,0.000049752667],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001440706,0.00038718703,0.0011665991,0.00012231621,0.00005024454,0.000002343875,0.0005355965,0.0015102196,0.0010276678],"category_scores_gemma":[0.005627349,0.00026823347,0.00019506483,0.000042706004,0.0003005613,0.000060436483,0.00020814307,0.001871998,0.0003100494],"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":[0.0000026755972,0.0000042009824,0.00013484307,0.00007112411,0.000035689827,0.00007961894,0.0000068462473,1.1325816e-8,0.000008986513,0.024545955,0.972728,0.0023820482],"study_design_scores_gemma":[0.000045796063,0.000034088956,0.0000022704041,0.00005261883,0.000016082282,0.000016919379,5.4581665e-7,7.88512e-7,0.000030602394,0.49107733,0.50856286,0.0001600807],"about_ca_topic_score_codex":0.000022005725,"about_ca_topic_score_gemma":0.0000036997496,"teacher_disagreement_score":0.4665314,"about_ca_system_score_codex":0.00017637027,"about_ca_system_score_gemma":0.000022962056,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W2425980697","doi":"10.1111/biom.12468","title":"Model Assessment in Dynamic Treatment Regimen Estimation via Double Robustness","year":2016,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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 Center for Advancing Translational Sciences; University of California, Los Angeles; University of Pittsburgh; Northwestern University","keywords":"Robustness (evolution); Regimen; Mathematics; Computer science; Statistics; Medicine; Econometrics; Internal medicine; Biology","score_opus":0.20103595473419972,"score_gpt":0.4506263431265718,"score_spread":0.24959038839237208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2425980697","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":[0.078086056,0.000032117234,0.92009443,0.0002344024,0.00004721116,0.00043344786,0.000011775182,0.00026063557,0.0007999374],"genre_scores_gemma":[0.6031792,0.0000820797,0.39589426,0.000005940617,0.0000061501632,0.0001166665,0.0000067180104,0.000022164555,0.0006868105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879676,0.000027461452,0.00034387407,0.00027784912,0.0002753877,0.00027865794],"domain_scores_gemma":[0.99891216,0.0003356781,0.00016842697,0.0004330775,0.000084987085,0.000065656386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031167627,0.00019021779,0.00025717952,0.0011963459,0.000036225534,0.000023169256,0.00016873349,0.00012728355,0.000021973186],"category_scores_gemma":[0.00013906618,0.00012828113,0.000047295416,0.0017028062,0.000041008665,0.00028108107,0.000057788202,0.000061743085,0.00001125763],"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":[0.00012935705,0.0023041416,0.0020160354,0.00018264302,0.000092499315,0.000043596356,0.0002925809,0.010756189,0.047138028,0.16970168,0.0006516819,0.76669157],"study_design_scores_gemma":[0.0018545588,0.00029735305,0.00043710426,0.00010254926,0.00003166988,0.000006075489,0.000019161143,0.70065904,0.009435426,0.28669542,0.00009096956,0.00037071007],"about_ca_topic_score_codex":0.000022411547,"about_ca_topic_score_gemma":0.00003026992,"teacher_disagreement_score":0.7663208,"about_ca_system_score_codex":0.0015967258,"about_ca_system_score_gemma":0.00008777387,"threshold_uncertainty_score":0.5231153},"labels":[],"label_agreement":null},{"id":"W246160853","doi":"10.1080/07350015.2015.1044008","title":"Treatment Effects With Unobserved Heterogeneity: A Set Identification Approach","year":2015,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Econometrics; Average treatment effect; Identification (biology); Outcome (game theory); Covariate; Set (abstract data type); Panel data; Treatment effect; Statistics; Mathematics; Computer science; Medicine; Estimator; Mathematical economics","score_opus":0.19657782441177,"score_gpt":0.3694869541265559,"score_spread":0.17290912971478592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W246160853","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":[0.4045969,0.000067893765,0.5950016,0.000032660286,0.000077255645,0.00011569679,0.000034091885,0.000013281436,0.000060664122],"genre_scores_gemma":[0.7308292,0.00013919717,0.268856,0.000011000323,0.00007878059,0.000010542047,0.0000109783705,0.000019549201,0.00004480746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993117,0.00003210901,0.00036912638,0.000103520935,0.00007706555,0.00010647879],"domain_scores_gemma":[0.99883705,0.00018971977,0.00052129186,0.0001369426,0.00021761142,0.00009739744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020919848,0.00012675743,0.0003247855,0.000068875765,0.000030675215,0.00006188246,0.000069702925,0.000039286613,0.0000023974692],"category_scores_gemma":[0.00013815163,0.00009031326,0.000018110522,0.000042482145,0.000049874758,0.00020495379,0.00001633941,0.000052813102,0.000001969515],"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":[0.003827522,0.003386592,0.12440998,0.0042435764,0.0033832828,0.0009935114,0.009726357,0.014537335,0.003831784,0.5949838,0.025380315,0.21129595],"study_design_scores_gemma":[0.012110561,0.004701368,0.07541793,0.00046748552,0.0014833855,0.003466565,0.001439867,0.03205607,0.012620227,0.85193,0.0028113287,0.0014951826],"about_ca_topic_score_codex":0.000026561414,"about_ca_topic_score_gemma":0.000026116582,"teacher_disagreement_score":0.32623225,"about_ca_system_score_codex":0.00020045969,"about_ca_system_score_gemma":0.000117896154,"threshold_uncertainty_score":0.3682868},"labels":[],"label_agreement":null},{"id":"W2466391332","doi":"10.1002/sim.7012","title":"Martingale residual‐based method to control for confounders measured only in a validation sample in time‐to‐event analysis","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Residual; Confounding; Computer science; Econometrics; Control chart; Event (particle physics); Sample (material); Sample size determination; Martingale (probability theory); Mathematics; Algorithm; Chromatography","score_opus":0.1189508705834617,"score_gpt":0.47092695879781293,"score_spread":0.3519760882143512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466391332","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":[0.002987596,0.0000052108003,0.99195147,0.0030833385,0.000024731116,0.0013711643,0.0004189697,0.00005618663,0.000101349804],"genre_scores_gemma":[0.16111888,0.000001664468,0.83754647,0.0007338543,0.000031915304,0.00030578807,0.000058087433,0.00002818352,0.00017513099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99750555,0.00037879977,0.00090642937,0.00036218896,0.000476616,0.00037039135],"domain_scores_gemma":[0.9886385,0.010446747,0.00021399514,0.0003465413,0.00023633885,0.000117843854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004717727,0.00019256257,0.0007224172,0.0009460287,0.000023714842,0.000010074417,0.00020257487,0.000083148865,0.00035432357],"category_scores_gemma":[0.026184538,0.00014947775,0.00003226524,0.00090110494,0.000059175447,0.00005151264,0.000026729827,0.00012548637,0.000009491867],"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":[0.005090242,0.0016520254,0.07342194,0.0010422568,0.0008975516,0.00016461371,0.00995247,0.011248651,0.14142866,0.5175306,0.061785195,0.17578575],"study_design_scores_gemma":[0.0057086926,0.0008067351,0.0054316004,0.0008176804,0.000317794,7.858217e-7,0.00025631976,0.010319468,0.006528274,0.9687545,0.00065250456,0.00040567474],"about_ca_topic_score_codex":0.0003929376,"about_ca_topic_score_gemma":0.0032017021,"teacher_disagreement_score":0.45122385,"about_ca_system_score_codex":0.00047709193,"about_ca_system_score_gemma":0.00012672582,"threshold_uncertainty_score":0.98201835},"labels":[],"label_agreement":null},{"id":"W2468938072","doi":"10.1093/aje/kww068","title":"Correcting for Measurement Error in Time-Varying Covariates in Marginal Structural Models","year":2016,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Covariate; Marginal structural model; Statistics; Estimator; Confounding; Observational error; Econometrics; Inverse probability weighting; Errors-in-variables models; Lasso (programming language); Regression; Mathematics; Medicine; Computer science","score_opus":0.27974429685642044,"score_gpt":0.44757565314153613,"score_spread":0.1678313562851157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468938072","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":[0.37346897,0.00009410947,0.6249066,0.0011514773,0.000100906866,0.00019403643,0.000003663228,0.000022553177,0.000057718804],"genre_scores_gemma":[0.7094395,0.00001727448,0.29026428,0.0001812976,0.000057008478,0.000014729152,2.7125566e-7,0.000016625838,0.000008979087],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971537,0.000739905,0.0012798671,0.00019691247,0.00015691489,0.00047267842],"domain_scores_gemma":[0.9896351,0.008501148,0.0013731259,0.00016178454,0.00024541997,0.00008341424],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070959474,0.00017260366,0.0010082036,0.0002773148,0.000026851445,0.0000033818294,0.0002888899,0.000065389344,0.000030404677],"category_scores_gemma":[0.016913772,0.00011235501,0.00011404129,0.00016679797,0.0002050238,0.00023832357,0.00004659745,0.0002691002,0.0000012060483],"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":[0.0038992872,0.00030917235,0.2757181,0.00014803177,0.00033389524,0.000113934795,0.0021777235,0.009077168,0.037197515,0.15260097,0.0017063715,0.51671785],"study_design_scores_gemma":[0.0008640366,0.0008383681,0.0019448135,0.00052091124,0.000018916859,0.00022593573,0.0001579075,0.00560478,0.0008391683,0.9887615,0.00003279359,0.00019087487],"about_ca_topic_score_codex":0.000084863095,"about_ca_topic_score_gemma":0.00004669506,"teacher_disagreement_score":0.83616054,"about_ca_system_score_codex":0.00045040052,"about_ca_system_score_gemma":0.00010031095,"threshold_uncertainty_score":0.99136716},"labels":[],"label_agreement":null},{"id":"W2469474306","doi":"10.6000/1929-6029.2016.05.02.3","title":"Intention-to-Treat Analysis but for Treatment Intention: How should Consumer Product Randomized Controlled Trials be Analyzed?","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Philip Morris International","keywords":"Blinding; Randomized controlled trial; Randomization; Protocol (science); Product (mathematics); De facto; Population; Intention-to-treat analysis; Marketing; Medicine; Psychology; Business; Alternative medicine; Mathematics; Surgery","score_opus":0.4179813978358019,"score_gpt":0.5845818989366804,"score_spread":0.16660050110087854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469474306","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":[0.009199073,0.0002492641,0.964109,0.023417534,0.0003823691,0.0019998404,0.00041612904,0.000021433088,0.0002053426],"genre_scores_gemma":[0.8170145,0.005722709,0.17134322,0.00017243811,0.00049464003,0.0009296395,0.000039400755,0.000043593212,0.0042398674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98974395,0.0027588138,0.0027671466,0.0003545445,0.0039323983,0.00044314234],"domain_scores_gemma":[0.9143762,0.076126434,0.0012264671,0.00026716423,0.0075770933,0.00042664036],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038205586,0.00026047882,0.0033474439,0.0020492852,0.000063334075,0.00014943264,0.00081737956,0.00015081387,0.0013525829],"category_scores_gemma":[0.37192747,0.00013122828,0.0010246213,0.0005418512,0.00057392474,0.00019393011,0.00012602254,0.00037482954,0.0000058382752],"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":[0.24356763,0.0022112078,0.0016855476,0.00011206663,0.020610241,0.0012522617,0.000516924,0.000009542282,0.00590165,0.36599886,0.026148943,0.33198512],"study_design_scores_gemma":[0.26205656,0.001047817,0.00010578842,0.0011752202,0.0024451828,0.00009521524,0.00042976337,0.00262378,0.0061498242,0.7208835,0.0026379488,0.0003494364],"about_ca_topic_score_codex":0.00008661853,"about_ca_topic_score_gemma":0.00020624642,"teacher_disagreement_score":0.80781543,"about_ca_system_score_codex":0.0009197876,"about_ca_system_score_gemma":0.00054030435,"threshold_uncertainty_score":0.9995603},"labels":[],"label_agreement":null},{"id":"W2469842794","doi":"10.1097/ede.0000000000000521","title":"Sufficient Cause Representation of the Four-way Decomposition for Mediation and Interaction","year":2016,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Jewish General Hospital","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases","keywords":"Outcome (game theory); Counterfactual thinking; Mediation; Context (archaeology); Set (abstract data type); Consistency (knowledge bases); Representation (politics); Computer science; Decomposition; Component (thermodynamics); Psychology; Social psychology; Mathematics; Chemistry; Sociology; Physics; Political science; Artificial intelligence; History; Mathematical economics","score_opus":0.34802142461126384,"score_gpt":0.5045439834955416,"score_spread":0.1565225588842778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469842794","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007718674,0.000047786547,0.549559,0.44033355,0.00083697727,0.0011460688,0.0000838303,0.000103044775,0.00017108604],"genre_scores_gemma":[0.14705437,0.0011234316,0.25128758,0.57975805,0.013521325,0.0029588602,0.0013212141,0.0003661424,0.0026090092],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99787736,0.0007568382,0.000709795,0.00032546697,0.000098093304,0.00023244479],"domain_scores_gemma":[0.98248166,0.015712246,0.0011965712,0.00041752774,0.00017336439,0.000018618794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010153825,0.00017817803,0.00052888476,0.000109709064,0.000061146166,0.0000035131388,0.00014825113,0.0005607277,0.000021705382],"category_scores_gemma":[0.009554515,0.00011167044,0.00012791519,0.00006171631,0.00014972164,0.00010076963,0.00007312225,0.0004308588,0.000002014093],"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":[0.000046706282,0.000015765067,0.0010312026,0.00025617523,0.00007289001,0.00000170283,0.00016813417,0.000008281557,0.0016939358,0.024085047,0.9683077,0.0043124687],"study_design_scores_gemma":[0.00023863208,0.00016406573,0.0009697106,0.00027320674,0.00012276608,0.000036167512,0.000021097254,0.00050035876,0.0057718456,0.94020265,0.051497355,0.00020213053],"about_ca_topic_score_codex":0.000016062948,"about_ca_topic_score_gemma":0.000015652802,"teacher_disagreement_score":0.91681033,"about_ca_system_score_codex":0.00013295813,"about_ca_system_score_gemma":0.000020493842,"threshold_uncertainty_score":0.9987884},"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":"W2492495737","doi":"10.1016/j.jcrc.2016.07.017","title":"Immortal time bias in observational studies of time-to-event outcomes","year":2016,"lang":"en","type":"article","venue":"Journal of Critical Care","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":180,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Observational study; Proportional hazards model; Medicine; Logistic regression; Hazard ratio; Survival analysis; Statistics; Regression analysis; Econometrics; Internal medicine; Confidence interval; Mathematics","score_opus":0.4412060308633293,"score_gpt":0.5311251808301917,"score_spread":0.08991914996686234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492495737","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":[0.98097026,0.00048460747,0.008607192,0.008621409,0.00013103438,0.00021584237,0.00006190002,0.000043876065,0.0008638497],"genre_scores_gemma":[0.9703083,0.0000048116826,0.029189209,0.00014639892,0.000060164562,0.0000052478777,4.3161666e-7,0.000015023026,0.00027039132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984242,0.00007979557,0.000763859,0.00009224378,0.00046291796,0.0001769922],"domain_scores_gemma":[0.9957649,0.002718354,0.00017658446,0.00013934319,0.0011090703,0.00009170868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00046687148,0.00012330174,0.00052182254,0.00014820123,0.000017422026,0.000006297457,0.00017404025,0.00006078814,0.00033254706],"category_scores_gemma":[0.012766157,0.00007375356,0.00014185955,0.000106751206,0.00013530358,0.00022430677,0.000075725315,0.00013265325,0.000030728246],"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":[0.0009052608,0.0028199195,0.19016679,0.004277844,0.00070117606,0.0012163521,0.011091891,0.00012102233,0.14530863,0.5778861,0.02708752,0.03841747],"study_design_scores_gemma":[0.0013586277,0.0017765505,0.037442572,0.0018918065,0.00020643277,0.00008601726,0.0021935152,0.000031578227,0.03568683,0.9182685,0.000528015,0.00052954635],"about_ca_topic_score_codex":6.32583e-7,"about_ca_topic_score_gemma":0.0000027473088,"teacher_disagreement_score":0.3403824,"about_ca_system_score_codex":0.00016262438,"about_ca_system_score_gemma":0.00006926907,"threshold_uncertainty_score":0.99554974},"labels":[],"label_agreement":null},{"id":"W249493256","doi":"10.1515/ijb-2014-0037","title":"Double Bias: Estimation of Causal Effects from Length-Biased Samples in the Presence of Confounding","year":2015,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Estimator; Statistics; Econometrics; Hazard ratio; Causal inference; Sample size determination; Proportional hazards model; Sampling bias; Survival analysis; Estimation; Information bias; Mathematics; Selection bias; Point estimation; Data set; Pooling; Confidence interval; Computer science; Economics","score_opus":0.24735357801031266,"score_gpt":0.4444989250048111,"score_spread":0.19714534699449843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W249493256","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":[0.5802997,0.000081544735,0.41836533,0.00042082398,0.00036002827,0.00019778969,0.0001084546,0.000009290727,0.00015706844],"genre_scores_gemma":[0.8878138,0.00003232187,0.112001054,0.00004692243,0.000077166915,0.0000032726953,0.0000099381705,0.00000885194,0.0000066649663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998096,0.00017290821,0.0007267277,0.0000673302,0.0008402273,0.00009679366],"domain_scores_gemma":[0.9905207,0.007465536,0.0010943383,0.00018341866,0.000703831,0.000032178978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014990823,0.00010393613,0.0002533886,0.00013005841,0.000017785462,0.000033231863,0.0007414512,0.000043399617,0.00000959512],"category_scores_gemma":[0.006737386,0.00006248528,0.00004767459,0.00011363165,0.00016527495,0.00017374192,0.0000661576,0.00021194926,0.0000012382183],"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":[0.00162481,0.00070645806,0.004854632,0.00018700668,0.0005315774,0.00017198185,0.024492852,0.0057913084,0.024798065,0.91251254,0.007957573,0.016371194],"study_design_scores_gemma":[0.0013578088,0.00031314095,0.0013477269,0.0006313584,0.00008360719,0.000056721998,0.0017686695,0.006158302,0.09024844,0.8978259,0.00010449572,0.00010383237],"about_ca_topic_score_codex":0.00031966044,"about_ca_topic_score_gemma":0.00006840954,"teacher_disagreement_score":0.30751416,"about_ca_system_score_codex":0.00009089945,"about_ca_system_score_gemma":0.0001421564,"threshold_uncertainty_score":0.80657667},"labels":[],"label_agreement":null},{"id":"W2495538325","doi":"10.1177/1740774516656583","title":"A practical Bayesian stepped wedge design for community-based cluster-randomized clinical trials: The British Columbia Telehealth Trial","year":2016,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"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":"National Cancer Institute","keywords":"Telehealth; Sample size determination; Clinical trial; Cluster randomised controlled trial; Medicine; Randomized controlled trial; Type I and type II errors; Research design; Confidence interval; Cluster (spacecraft); Health care; Computer science; Telemedicine; Physical therapy; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.7739321541510332,"score_gpt":0.6354475128676494,"score_spread":0.13848464128338378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2495538325","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":[0.0044717467,0.000056055775,0.9481192,0.010375011,0.002703149,0.033089813,0.00026025934,0.00074740493,0.00017733726],"genre_scores_gemma":[0.06804207,0.001092693,0.899104,0.008349849,0.0085388515,0.012043417,0.00006508829,0.0003673825,0.0023966364],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.63895345,0.338857,0.019036872,0.0011114856,0.000883298,0.001157886],"domain_scores_gemma":[0.27332234,0.7174484,0.0061237416,0.0018838187,0.00062860694,0.00059308804],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6255638,0.0005357578,0.00972651,0.00007194043,0.0013270746,0.0011405182,0.0012891515,0.0015063117,0.00045014397],"category_scores_gemma":[0.90325695,0.00037040128,0.0044260845,0.00029544707,0.002263676,0.00032947527,0.00027088964,0.0022703696,0.000047150843],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.57437325,0.0029718021,0.00003737518,0.00012153185,0.00061253866,0.00001073563,0.000023261304,4.6436756e-7,0.000018531577,0.0035485092,0.32323438,0.09504765],"study_design_scores_gemma":[0.55516535,0.0032588434,0.0000058930927,0.0005015245,0.0011984049,0.000009944143,0.00005434469,0.0004917097,0.000051750376,0.42113283,0.01768893,0.0004405007],"about_ca_topic_score_codex":0.0004667656,"about_ca_topic_score_gemma":0.0018398887,"teacher_disagreement_score":0.4175843,"about_ca_system_score_codex":0.0001602245,"about_ca_system_score_gemma":0.0018366982,"threshold_uncertainty_score":0.99997306},"labels":[],"label_agreement":null},{"id":"W2501992360","doi":"10.1080/00273171.2016.1200454","title":"Using Marginal Structural Modeling for Grade Retention Effects","year":2016,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Simon Fraser University; Fordham University","keywords":"Equating; Covariate; Confounding; Propensity score matching; Statistics; Analysis of covariance; Marginal structural model; Econometrics; Missing data; Psychology; Computer science; Mathematics","score_opus":0.8116577974541808,"score_gpt":0.63032002163345,"score_spread":0.18133777582073074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501992360","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":[0.57328385,0.000009714624,0.42543882,0.000057503607,0.00008088311,0.000926318,0.000021023881,0.00016333624,0.000018520941],"genre_scores_gemma":[0.7467204,0.0000034355262,0.25270474,0.0000023045902,0.000089697,0.00019779902,0.0000054473658,0.000053984983,0.00022220722],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973812,0.00030241295,0.00035046387,0.00046769518,0.00066685356,0.00083134143],"domain_scores_gemma":[0.9978091,0.00094019703,0.00008646807,0.00043593647,0.0005814821,0.00014679767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013844261,0.00021661779,0.000281446,0.00027342315,0.00034190062,0.00007069901,0.00032340526,0.00019197447,0.000042681397],"category_scores_gemma":[0.0011407434,0.00014942054,0.00011873147,0.00023041993,0.00013626863,0.00045816595,0.00019897328,0.00032993604,0.0000086661],"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":[0.00019549142,0.00010840206,0.0005724303,0.00012631217,0.000012359812,0.00001622927,0.0001731036,0.000020283602,0.93255454,0.046556674,0.00005315394,0.019611012],"study_design_scores_gemma":[0.001727473,0.00051986956,0.00041855176,0.0005417242,0.000055764503,0.0000126990635,0.00008738741,0.08192774,0.13661636,0.7776322,0.00003661941,0.0004236273],"about_ca_topic_score_codex":0.0002977833,"about_ca_topic_score_gemma":0.00001942627,"teacher_disagreement_score":0.7959382,"about_ca_system_score_codex":0.00048741826,"about_ca_system_score_gemma":0.00008043144,"threshold_uncertainty_score":0.60931927},"labels":[],"label_agreement":null},{"id":"W2505126815","doi":"10.1016/s0731-9053(07)00004-7","title":"Instrumental variables estimation of the average treatment effect in the correlated random coefficient model","year":2008,"lang":"en","type":"book-chapter","venue":"Advances in econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":87,"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":"University of British Columbia; Michigan State University","keywords":"Instrumental variable; Tobit model; Mathematics; Variables; Econometrics; Statistics; Random variable; Estimation; Random effects model; Variable (mathematics); Economics; Mathematical analysis","score_opus":0.066085663606183,"score_gpt":0.3263762946920296,"score_spread":0.2602906310858466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505126815","genre_codex":"other","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":[0.048446495,0.012988096,0.3262498,0.00010272707,0.0012484996,0.011811415,0.00073903706,0.00031123235,0.5981027],"genre_scores_gemma":[0.9591344,0.018013306,0.015571564,0.000077706005,0.00002934778,0.00031809066,0.00009857682,0.000104296676,0.0066527235],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981479,0.00008338257,0.0008872736,0.00035206001,0.00028222828,0.00024713002],"domain_scores_gemma":[0.9957972,0.0027446966,0.0007565542,0.0006378453,0.000037051155,0.000026639626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005605478,0.00043005467,0.0007830454,0.0007031163,0.00007173267,0.000016757742,0.00049410557,0.0002701814,0.00003574364],"category_scores_gemma":[0.00058967195,0.00025903256,0.00018442216,0.00044203893,0.00021300788,0.00027126208,0.00009856498,0.00042791382,0.0000048973343],"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":[0.00017116664,0.00036400673,0.00068622746,0.00022291044,0.0000641086,0.000018513438,0.0011514134,0.71280414,0.0000027206738,0.2113538,0.00009537335,0.073065616],"study_design_scores_gemma":[0.003966788,0.0007243332,0.000047364858,0.0007697571,0.00012953073,0.000032987326,0.000041563828,0.30993342,0.00069479056,0.6797532,0.0032461695,0.0006600866],"about_ca_topic_score_codex":0.000011274928,"about_ca_topic_score_gemma":0.0000625794,"teacher_disagreement_score":0.91068786,"about_ca_system_score_codex":0.00084969477,"about_ca_system_score_gemma":0.000082196755,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W2507759746","doi":"10.1007/s00228-016-2118-x","title":"Performance of the high-dimensional propensity score in adjusting for unmeasured confounders","year":2016,"lang":"en","type":"article","venue":"European Journal of Clinical Pharmacology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":48,"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; McMaster University; McGill University; Centre Hospitalier de l’Université de Montréal; Programs for Assessment of Technology in Health Research Institute","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Confounding; Medicine; Statistics; Econometrics; Internal medicine; Psychology; Mathematics","score_opus":0.4570305638231168,"score_gpt":0.4816920596247215,"score_spread":0.024661495801604705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507759746","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":[0.9923963,0.000015882952,0.0045982054,0.0011841129,0.0011033592,0.0003253765,0.000003850644,0.000016719274,0.0003562174],"genre_scores_gemma":[0.9891948,0.00003853084,0.009793291,0.00047060277,0.00038378642,0.000002101218,1.2519747e-7,0.000024430774,0.00009234646],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99657154,0.0011684169,0.0016627416,0.00014632812,0.0002363314,0.00021465248],"domain_scores_gemma":[0.99467236,0.0029981409,0.0015707924,0.00015754394,0.0005169816,0.00008419486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062090205,0.00012407698,0.00054824835,0.000063285814,0.00004649117,0.0000031792895,0.00045643287,0.000049870672,0.000063475556],"category_scores_gemma":[0.004288101,0.00006439395,0.00019077389,0.00009432574,0.00040409263,0.00014757704,0.00013875349,0.00044390207,0.0000036030779],"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":[0.013389224,0.0024660036,0.24251348,0.00069586746,0.0007489439,0.0003195572,0.00039992953,0.0006842929,0.46881017,0.010714956,0.053939413,0.20531818],"study_design_scores_gemma":[0.037520174,0.010370982,0.6516096,0.004207346,0.0008362848,0.0004095596,0.000068903704,0.0012797937,0.21879508,0.06762523,0.006202213,0.0010748559],"about_ca_topic_score_codex":5.151466e-7,"about_ca_topic_score_gemma":0.0000019300273,"teacher_disagreement_score":0.4090961,"about_ca_system_score_codex":0.000045164452,"about_ca_system_score_gemma":0.00018252582,"threshold_uncertainty_score":0.51335675},"labels":[],"label_agreement":null},{"id":"W2509712226","doi":"10.1016/j.jclinepi.2016.05.017","title":"Propensity score model overfitting led to inflated variance of estimated odds ratios","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Children's Hospital; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Overfitting; Propensity score matching; Statistics; Type I and type II errors; Confounding; Logistic regression; Inference; Econometrics; Mathematics; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.7352681527672233,"score_gpt":0.5929485520547376,"score_spread":0.14231960071248573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509712226","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":[0.44984898,0.000014221449,0.54743916,0.002209001,0.00014431072,0.00017622429,0.0000039174856,0.000041097668,0.00012309123],"genre_scores_gemma":[0.664886,0.000080209655,0.33401164,0.00077098655,0.00013679589,0.000003902759,3.011436e-7,0.000018733424,0.00009142064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913012,0.0018983019,0.0059232046,0.00028198137,0.00021703998,0.000378317],"domain_scores_gemma":[0.9560752,0.03664692,0.0053940583,0.000473656,0.0011087565,0.00030139892],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02035982,0.0002156485,0.0028135653,0.000121938014,0.000038112612,0.0000038020085,0.00044800888,0.00042034997,0.000051201692],"category_scores_gemma":[0.3299714,0.00012513877,0.00036467917,0.0001779435,0.0002680591,0.00028903666,0.00017032473,0.00065080065,0.000010427107],"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":[0.0034685757,0.00093006156,0.3937571,0.00027308942,0.0005713835,0.00009571953,0.00022032646,0.010148808,0.06193904,0.46026155,0.010958249,0.05737609],"study_design_scores_gemma":[0.001397083,0.0013919319,0.0363523,0.0013372255,0.00009173963,0.00006794747,0.0000046534133,0.015072365,0.0052794777,0.9386689,0.00009463787,0.00024174388],"about_ca_topic_score_codex":0.0000045877246,"about_ca_topic_score_gemma":0.0000056710164,"teacher_disagreement_score":0.47840735,"about_ca_system_score_codex":0.000063106294,"about_ca_system_score_gemma":0.00031468377,"threshold_uncertainty_score":0.7056348},"labels":[],"label_agreement":null},{"id":"W2513257670","doi":"10.1002/cjs.11301","title":"Survey estimation of domain means that respect natural orderings","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Estimator; Estimation; Mathematics; Bootstrapping (finance); Domain (mathematical analysis); Statistics; Pooling; Econometrics; Computer science; Economics; Artificial intelligence; Mathematical analysis","score_opus":0.11370152141497193,"score_gpt":0.35557705279460516,"score_spread":0.24187553137963325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513257670","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":[0.06085909,0.00007358612,0.9378251,0.00016517185,0.00020329827,0.00008608369,0.00056997646,0.00001250667,0.00020520834],"genre_scores_gemma":[0.662882,0.000015881731,0.3369467,0.000017094831,0.000018998182,6.526931e-7,0.0000032622715,0.000016682134,0.0000987524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988867,0.00010599336,0.00046703388,0.00007941513,0.00023162708,0.000229246],"domain_scores_gemma":[0.9972691,0.0012497556,0.00054104096,0.00017412705,0.0005162057,0.00024975397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079993595,0.00011909432,0.00028543657,0.00022971486,0.000048371956,0.000019956771,0.00022050012,0.000057358782,0.0001305929],"category_scores_gemma":[0.0043900106,0.00008569132,0.00003646216,0.00012615242,0.00017284797,0.00019030632,0.000010085461,0.00015692695,0.0000029186917],"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":[0.00013605582,0.00005154786,0.020576745,0.00024827296,0.0002173453,0.0005724389,0.0022526144,0.000076948134,0.0038673738,0.78833246,0.07347301,0.1101952],"study_design_scores_gemma":[0.00043139406,0.00023530633,0.017099762,0.00041889472,0.000033745302,0.00010230836,0.000108517816,0.00016339685,0.0045666513,0.97565293,0.00096896995,0.00021812422],"about_ca_topic_score_codex":0.0010285657,"about_ca_topic_score_gemma":0.035861213,"teacher_disagreement_score":0.6020229,"about_ca_system_score_codex":0.00026757133,"about_ca_system_score_gemma":0.00062525575,"threshold_uncertainty_score":0.98173183},"labels":[],"label_agreement":null},{"id":"W2514070870","doi":"10.6339/jds.201604_14(2).0002","title":"Comparing Pre-Post Change Across Groups: Guidelines for Choosing between Difference Scores, ANCOVA, and Residual Change Scores","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":60,"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":"Analysis of covariance; Residual; Statistics; Significant difference; Psychology; Mathematics","score_opus":0.732100748033184,"score_gpt":0.5505718425854673,"score_spread":0.18152890544771672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514070870","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":[0.9079538,0.0012290069,0.08835369,0.0013561689,0.00018859477,0.00040302964,0.00045280685,0.00005559841,0.0000073283904],"genre_scores_gemma":[0.6879482,0.0005213979,0.31016865,0.00027050357,0.0010131341,0.000016188449,0.00003118515,0.000020696067,0.000010015403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973553,0.000052430434,0.00082772836,0.0004925734,0.0007447835,0.00052721746],"domain_scores_gemma":[0.9959034,0.0006640108,0.00076882495,0.00072143256,0.0017286022,0.00021373235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029668652,0.00021629126,0.0005489197,0.00016101132,0.0003989036,0.00037794985,0.0015865645,0.00007019262,0.0000028475483],"category_scores_gemma":[0.0063472423,0.00017372421,0.00004289964,0.0004975356,0.00064790697,0.004406527,0.0015209322,0.00029914785,5.524422e-7],"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":[0.0003279537,0.00050902483,0.4392118,0.001786777,0.00017111636,0.00020049427,0.012501156,0.000003955518,0.17716405,0.023382071,0.005195928,0.3395457],"study_design_scores_gemma":[0.0027998954,0.0015441752,0.6957232,0.009362725,0.00035919074,0.0010939627,0.003352721,0.0059393556,0.09026293,0.18566373,0.0021834124,0.0017147146],"about_ca_topic_score_codex":0.000045947396,"about_ca_topic_score_gemma":0.0002020703,"teacher_disagreement_score":0.33783096,"about_ca_system_score_codex":0.00008516822,"about_ca_system_score_gemma":0.000196058,"threshold_uncertainty_score":0.75987005},"labels":[],"label_agreement":null},{"id":"W2516296618","doi":"10.1016/j.jclinepi.2016.08.006","title":"A simple method for analyzing matched designs with double controls: McNemar's test can be extended","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"McNemar's test; Logistic regression; Computer science; Matching (statistics); Statistics; Simple (philosophy); Null hypothesis; Score test; Data mining; Statistical hypothesis testing; Mathematics","score_opus":0.5988744036316583,"score_gpt":0.6051541069230387,"score_spread":0.00627970329138039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516296618","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":[0.010653904,0.0000628275,0.97476095,0.013725772,0.00012277112,0.00046569805,0.000021103946,0.0000782776,0.000108719425],"genre_scores_gemma":[0.22025989,0.00014292878,0.776887,0.0019876224,0.00047632717,0.000049030743,0.0000013438732,0.00004543777,0.00015044179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99194795,0.002218369,0.0046333703,0.00037786624,0.00018941335,0.00063304417],"domain_scores_gemma":[0.7725844,0.22146818,0.0044752536,0.00043129607,0.0006921171,0.00034875234],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032105908,0.00029486342,0.0036546676,0.0001420718,0.0000737586,0.000009681666,0.0004724964,0.0004295582,0.00008576868],"category_scores_gemma":[0.18692222,0.00015200922,0.0006890934,0.00013190882,0.00030937803,0.00019622763,0.00006461781,0.0006199208,0.0000018988642],"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":[0.015508815,0.0022651537,0.22219451,0.00036399235,0.0025737109,0.00021252564,0.0002641547,0.0002111788,0.02253634,0.5718504,0.043648828,0.11837036],"study_design_scores_gemma":[0.005798382,0.004118728,0.0025292,0.0002353951,0.00032861196,0.00015956302,0.000060253493,0.0004906542,0.0018195047,0.98121774,0.002977385,0.00026457445],"about_ca_topic_score_codex":0.000022649736,"about_ca_topic_score_gemma":0.00012155121,"teacher_disagreement_score":0.40936732,"about_ca_system_score_codex":0.0000983149,"about_ca_system_score_gemma":0.00032952864,"threshold_uncertainty_score":0.99665064},"labels":[],"label_agreement":null},{"id":"W2517555654","doi":"10.1111/caje.12217","title":"Viewpoint: Estimating the causal effects of policies and programs","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Credibility; Interpretation (philosophy); Causal inference; Identification (biology); Context (archaeology); Internal validity; Positive economics; Inference; Estimation; Economics; Epistemology; Econometrics; Computer science","score_opus":0.21164262474422046,"score_gpt":0.26770295389089455,"score_spread":0.05606032914667408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517555654","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":[0.9923886,0.00019628908,0.0032045753,0.003210436,0.00039172216,0.0003683318,0.000026464037,0.000012872347,0.00020072085],"genre_scores_gemma":[0.98384285,0.00008004937,0.015363991,0.00025161734,0.00027874875,0.000024765826,6.7648216e-7,0.00004591677,0.00011141367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839693,0.0000751925,0.00079941977,0.00018988842,0.0000036673755,0.0005349064],"domain_scores_gemma":[0.996743,0.0010744418,0.00087775534,0.00036500525,0.00018186601,0.00075792463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070211507,0.00023380932,0.00058197667,0.0002944271,0.000117055395,0.000052337342,0.00042845216,0.00012383862,0.000026698977],"category_scores_gemma":[0.0014507077,0.00016483289,0.00012449245,0.000078752244,0.00044942342,0.00033957863,0.0000333221,0.00021314526,0.0000017009168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013162311,0.000008551821,0.0019752493,0.00016436445,0.00009680163,0.000039714992,0.0013799444,0.00002798559,0.00025684768,0.9622783,0.00019733103,0.03356171],"study_design_scores_gemma":[0.000367443,0.00044633218,0.00037537725,0.0007313611,0.000057740654,0.00047099954,0.00016670524,0.00017433158,0.0028327957,0.992852,0.0012862522,0.0002387073],"about_ca_topic_score_codex":0.025554655,"about_ca_topic_score_gemma":0.79879665,"teacher_disagreement_score":0.773242,"about_ca_system_score_codex":0.00069970044,"about_ca_system_score_gemma":0.0007863698,"threshold_uncertainty_score":0.98093426},"labels":[],"label_agreement":null},{"id":"W2519327609","doi":"10.3982/ecta16437","title":"Model Selection for Treatment Choice: Penalized Welfare Maximization","year":2021,"lang":"en","type":"preprint","venue":"Econometrica","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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 Calgary","funders":"Shanxi Scholarship Council of China; Northwestern University","keywords":"Oracle; Regret; Maximization; Selection (genetic algorithm); Covariate; Mathematical optimization; Class (philosophy); Computer science; Mathematics; Econometrics; Machine learning; Artificial intelligence","score_opus":0.3036878530973369,"score_gpt":0.437126187165306,"score_spread":0.13343833406796907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519327609","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":[0.013592391,0.0002649079,0.97928596,0.00046278845,0.0001954886,0.0018425707,0.00016072068,0.0006350172,0.0035601768],"genre_scores_gemma":[0.4447298,0.00038697926,0.5497348,0.000041858646,0.00016695182,0.0023355302,0.00064078503,0.00010718734,0.0018561294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983374,0.00004183951,0.00055044604,0.00066400645,0.00011508941,0.000291209],"domain_scores_gemma":[0.998327,0.00040194922,0.00036050408,0.0005317274,0.00029065376,0.00008812114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017218634,0.0003726005,0.00071859924,0.0007094871,0.00013468375,0.00015060657,0.00021712774,0.00038889443,0.00041238184],"category_scores_gemma":[0.0011328184,0.0003820271,0.0002991658,0.00047385276,0.000020069625,0.00017255114,0.00018522126,0.00017172607,0.0000042904844],"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":[0.00044600046,0.0057345,0.0048163347,0.006112207,0.003562187,0.000011934521,0.003072286,0.19173531,0.001114533,0.56133956,0.017376188,0.204679],"study_design_scores_gemma":[0.0013846254,0.00035510302,0.00013813058,0.00012188302,0.00037794164,0.0000057486304,0.000084464926,0.42103907,0.0065698754,0.56038076,0.008519404,0.0010229975],"about_ca_topic_score_codex":0.00004884343,"about_ca_topic_score_gemma":0.00006974644,"teacher_disagreement_score":0.4311374,"about_ca_system_score_codex":0.0012584861,"about_ca_system_score_gemma":0.00018052274,"threshold_uncertainty_score":0.99986315},"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":"W2522161560","doi":"10.1186/s12874-016-0225-0","title":"The use of relative incidence ratios in self-controlled case series studies: an overview","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; Children's Hospital of Eastern Ontario; Ottawa Hospital; Manitoba Beekeepers' Association; University of Ottawa","funders":"Canadian Institutes of Health Research; Crohn's and Colitis Canada; Ontario Ministry of Health and Long-Term Care; Canadian Association of Gastroenterology; Institute for Clinical Evaluative Sciences","keywords":"Context (archaeology); Medicine; Subgroup analysis; Incidence (geometry); Covariate; Vaccination; Statistics; Mathematics; Meta-analysis; Internal medicine; Immunology","score_opus":0.920688573393072,"score_gpt":0.6823189290759659,"score_spread":0.23836964431710606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522161560","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":[0.26643342,0.004237265,0.72153896,0.0045178253,0.00016933336,0.002716503,0.000010371353,0.00024181919,0.00013448458],"genre_scores_gemma":[0.04224757,0.01756074,0.93828934,0.00010530288,0.00009017234,0.00094356114,5.0083077e-7,0.000034892597,0.0007279109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9607515,0.035881035,0.0010588905,0.00040719556,0.0012420514,0.0006593478],"domain_scores_gemma":[0.5761961,0.4214779,0.00026866337,0.0008107908,0.0010024138,0.00024413754],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053492635,0.00017627345,0.00097386923,0.00022419883,0.000186293,0.000015349986,0.00053917046,0.0002874657,0.00013867879],"category_scores_gemma":[0.669033,0.00008343782,0.00008833467,0.00049714674,0.0019281341,0.00061884394,0.000513784,0.00070359564,0.0000075814696],"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":[0.0014742316,0.00017219724,0.0010071323,0.0002854177,0.00013275482,0.0010293709,0.0033708748,9.041681e-7,0.0013582081,0.96160406,0.00072121597,0.028843615],"study_design_scores_gemma":[0.0017228905,0.000801851,0.00006399803,0.00059420464,0.000020395813,0.00052923465,0.0021537186,0.00021583865,0.0021737625,0.9904248,0.0011700001,0.0001293127],"about_ca_topic_score_codex":0.00013772631,"about_ca_topic_score_gemma":0.010806753,"teacher_disagreement_score":0.6155404,"about_ca_system_score_codex":0.0002192929,"about_ca_system_score_gemma":0.00092766783,"threshold_uncertainty_score":0.9746285},"labels":[],"label_agreement":null},{"id":"W2525074234","doi":"10.1097/ede.0000000000000562","title":"Re","year":2016,"lang":"war","type":"letter","venue":"Epidemiology","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":true,"ca_institutions":"Carleton University; McGill University; McGill University Health Centre; University of New Brunswick","funders":"","keywords":"Confounding; Causality (physics); Medicine; Demography; Regression analysis; Statistics; Environmental health; Psychology; Mathematics","score_opus":0.3826505297407446,"score_gpt":0.48573912331077257,"score_spread":0.10308859357002798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525074234","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":[0.000034080975,0.0009992666,0.24531384,0.7175723,0.0014824404,0.00078814256,0.00021182,0.00089498924,0.03270314],"genre_scores_gemma":[0.00034236585,0.0021410733,0.16654374,0.7666696,0.015163647,0.00038882764,0.00020121434,0.00035135588,0.048198197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900521,0.0035887065,0.0024484424,0.0015160731,0.0002364536,0.0021582425],"domain_scores_gemma":[0.9494765,0.045695677,0.0019269455,0.0024543863,0.00023681275,0.00020969249],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0048023444,0.0011169832,0.0033488998,0.0003144296,0.00015920226,0.000009891753,0.0013298397,0.004528131,0.00794587],"category_scores_gemma":[0.037868243,0.0008111624,0.00061770325,0.00015722607,0.0009879946,0.00016935164,0.0005762814,0.0035299028,0.0059464034],"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":[0.000016246853,0.00001840825,0.00036852603,0.0003237601,0.00013427206,0.00016295668,0.00007212165,3.2939084e-7,0.00007289332,0.08768851,0.9038805,0.007261489],"study_design_scores_gemma":[0.000117143056,0.00014244686,0.000015731503,0.0004821474,0.000066177934,0.000026159069,0.000011531699,0.00000873892,0.00012345816,0.49152324,0.50699204,0.00049120217],"about_ca_topic_score_codex":0.000035737175,"about_ca_topic_score_gemma":0.000021968432,"teacher_disagreement_score":0.40383473,"about_ca_system_score_codex":0.0004547055,"about_ca_system_score_gemma":0.0001566313,"threshold_uncertainty_score":0.99943393},"labels":[],"label_agreement":null},{"id":"W2528615349","doi":"10.1093/ije/dyw195","title":"Strategies for evaluating the assumptions of the regression discontinuity design: a case study using a human papillomavirus vaccination programme","year":2016,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; McGill University; Queen's University","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Regression discontinuity design; Psychological intervention; Causal inference; Context (archaeology); Confounding; Popularity; Computer science; Instrumental variable; Variable (mathematics); Econometrics; Intervention (counseling); Inference; Clinical study design; Medicine; Actuarial science; Risk analysis (engineering); Psychology; Statistics; Social psychology; Economics; Machine learning; Mathematics; Clinical trial; Artificial intelligence","score_opus":0.7044133549907624,"score_gpt":0.6179033162114459,"score_spread":0.08651003877931651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528615349","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":[0.5649836,0.0000371635,0.43347713,0.000796791,0.00017426921,0.0005042383,0.0000061233823,0.000010799485,0.000009886275],"genre_scores_gemma":[0.9100944,0.000007689625,0.0896265,0.000040750616,0.00014198628,0.000050474686,3.3743729e-7,0.0000118362495,0.00002607121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966834,0.0015902049,0.0011434895,0.00013523661,0.0002631367,0.0001844915],"domain_scores_gemma":[0.98773354,0.008624725,0.002277468,0.00023567046,0.0010972933,0.000031310345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007839717,0.00012799271,0.0003594486,0.00009930206,0.0001568936,0.000017451499,0.0005191318,0.00007191302,0.00002444981],"category_scores_gemma":[0.013086138,0.00005241483,0.00018989206,0.00006619304,0.0001251621,0.00030894222,0.00011915498,0.0001822728,1.5333711e-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":[0.00086802087,0.0017761847,0.06911225,0.000069083704,0.0013466033,0.00019819102,0.0060747135,0.0008515386,0.21111003,0.5131738,0.0009794699,0.19444008],"study_design_scores_gemma":[0.0009517246,0.0009968036,0.0027785702,0.00032543723,0.00013846256,0.0012139056,0.0030371062,0.0012412766,0.002061177,0.98713505,0.000029763687,0.00009072782],"about_ca_topic_score_codex":0.00008351937,"about_ca_topic_score_gemma":0.00017260143,"teacher_disagreement_score":0.4739612,"about_ca_system_score_codex":0.0001913462,"about_ca_system_score_gemma":0.00013535042,"threshold_uncertainty_score":0.99522704},"labels":[],"label_agreement":null},{"id":"W2531513535","doi":"10.3945/ajcn.115.123315","title":"Best (but oft-forgotten) practices: intention-to-treat, treatment adherence, and missing participant outcome data in the nutrition literature","year":2016,"lang":"en","type":"article","venue":"American Journal of Clinical Nutrition","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":37,"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; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Missing data; Randomization; Medicine; Randomized controlled trial; Outcome (game theory); Clinical trial; Intervention (counseling); Intention-to-treat analysis; Family medicine; Surgery; Internal medicine; Nursing; Statistics","score_opus":0.5813004497897212,"score_gpt":0.5783115260801194,"score_spread":0.0029889237096017984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531513535","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":[0.9569428,0.00049441925,0.0245793,0.016892463,0.00013459193,0.0007313799,0.000106292704,0.00003791836,0.00008084996],"genre_scores_gemma":[0.9221007,0.0039005233,0.073139966,0.00043683004,0.00030446937,0.00005184874,0.00001264581,0.00001844719,0.000034526456],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966633,0.00071673084,0.0016995427,0.00031374505,0.0003453301,0.00026136526],"domain_scores_gemma":[0.9915525,0.0052055996,0.0021603731,0.00058200245,0.00031179987,0.00018772611],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021886078,0.00020488797,0.0007451444,0.00017382491,0.000066049215,0.00010357308,0.0004261101,0.00009470367,0.000013439051],"category_scores_gemma":[0.008393142,0.0001067327,0.00013834791,0.00036137784,0.00030151138,0.0009937778,0.00007185395,0.00036992776,0.000006541881],"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":[0.0030595032,0.011883046,0.06345184,0.00044532947,0.00019879804,0.00047772255,0.0013842493,2.0215943e-7,0.0056639053,0.0064687235,0.0022529336,0.90471375],"study_design_scores_gemma":[0.020958968,0.050428014,0.027421525,0.03097169,0.0020470312,0.0023059626,0.021436725,0.00015949835,0.003030098,0.81177175,0.027904512,0.0015642087],"about_ca_topic_score_codex":0.000044873115,"about_ca_topic_score_gemma":0.00004686812,"teacher_disagreement_score":0.90314955,"about_ca_system_score_codex":0.0000746129,"about_ca_system_score_gemma":0.000058274258,"threshold_uncertainty_score":0.9999596},"labels":[],"label_agreement":null},{"id":"W2536203341","doi":"10.1016/j.jalz.2016.06.1674","title":"P3‐017: The Impact of Central Rating Review Programs on ADAS‐COG Error Variance","year":2016,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","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":"inVentiv Health Clinical","funders":"","keywords":"Medicine; Cog; Clinical trial; Standard error; Sample size determination; Cohort; Statistics; Computer science; Internal medicine; Mathematics; Artificial intelligence","score_opus":0.17279656204449148,"score_gpt":0.424872197208631,"score_spread":0.25207563516413956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536203341","genre_codex":"review","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":[0.036668256,0.6309731,0.2678286,0.010631519,0.0013100713,0.01902548,0.00023187607,0.0033161975,0.030014856],"genre_scores_gemma":[0.9673154,0.0011613318,0.030983211,0.00021465117,0.000073696276,0.00017422726,0.000005849243,0.00004683513,0.000024831259],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99821806,0.00015104341,0.0005543579,0.00028146003,0.0003140537,0.00048102922],"domain_scores_gemma":[0.9982259,0.00032619317,0.0004766743,0.00075508154,0.00013380781,0.00008233187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005382768,0.00026468287,0.00037293122,0.000028886552,0.00008887392,0.00002046041,0.0004353308,0.000064611406,0.00048816582],"category_scores_gemma":[0.00030746197,0.0001321897,0.00022255187,0.00018308537,0.00013146478,0.00021906628,0.000101847,0.00014757905,0.000037716494],"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":[0.000094036564,0.00077448477,0.002501294,0.00024102998,0.012179119,0.000015041343,0.00041731025,0.0000040157947,0.01164311,0.09272488,0.041977055,0.8374286],"study_design_scores_gemma":[0.0031739504,0.0058032526,0.00801325,0.028375814,0.04574839,0.00009211872,0.00018279513,0.00039706475,0.26770666,0.6046065,0.032539733,0.0033604652],"about_ca_topic_score_codex":0.000044572313,"about_ca_topic_score_gemma":0.000012918491,"teacher_disagreement_score":0.93064713,"about_ca_system_score_codex":0.000017708933,"about_ca_system_score_gemma":0.00007215852,"threshold_uncertainty_score":0.539054},"labels":[],"label_agreement":null},{"id":"W2541915084","doi":"10.1007/978-3-319-41259-7_6","title":"Propensity Score Modeling and Evaluation","year":2016,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Waterloo","funders":"","keywords":"Propensity score matching; Causal inference; Covariate; Categorical variable; Observational study; Inference; Statistics; Nonparametric statistics; Econometrics; Average treatment effect; Parametric statistics; Mathematics; Computer science; Artificial intelligence","score_opus":0.307241050441393,"score_gpt":0.4090020091499489,"score_spread":0.1017609587085559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2541915084","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":[0.00017505615,0.000799623,0.5759096,0.00007418103,0.00018782308,0.0017752352,0.0008664421,0.00027536516,0.41993663],"genre_scores_gemma":[0.0045098485,0.0072993278,0.5344152,0.00021628215,0.00030026655,0.00020836198,0.00020575302,0.00039920752,0.45244578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981733,0.000041720083,0.0006065627,0.00042633704,0.0004987274,0.00025334547],"domain_scores_gemma":[0.99824196,0.00034208267,0.00033327471,0.0004946477,0.0005181886,0.00006985559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005555012,0.000400333,0.0005691962,0.00013753946,0.00007599999,0.00004211331,0.0001565837,0.00034479695,0.00037232335],"category_scores_gemma":[0.00067067036,0.00035405482,0.00002917541,0.000016526605,0.00027940836,0.00040455832,0.00020337159,0.00040455052,0.000013731658],"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":[0.00003270139,0.0000072248695,0.000012248609,0.0001994372,0.00001884449,0.000028069288,0.00013972152,0.00001190828,0.00001871515,0.9844409,0.0009356647,0.014154529],"study_design_scores_gemma":[0.00019178724,0.00009528795,0.0000029157075,0.0009118199,0.000086928056,0.000019221647,0.000008619723,0.0024584339,0.000064158485,0.9867905,0.008938777,0.00043157642],"about_ca_topic_score_codex":0.000005448713,"about_ca_topic_score_gemma":0.00021702923,"teacher_disagreement_score":0.041494463,"about_ca_system_score_codex":0.00030300356,"about_ca_system_score_gemma":0.0001857203,"threshold_uncertainty_score":0.99989116},"labels":[],"label_agreement":null},{"id":"W2545262557","doi":"10.1002/sim.7153","title":"Goodness‐of‐fit test for monotone proportional subdistribution hazards assumptions based on weighted residuals","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"University of Waterloo","funders":"Institute of Cancer Research; Institut National Du Cancer","keywords":"Goodness of fit; Mathematics; Monotone polygon; Statistics; Regression analysis; Monte Carlo method; Regression; Proportional hazards model; Applied mathematics","score_opus":0.11451533146660954,"score_gpt":0.4452264803293031,"score_spread":0.3307111488626936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545262557","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":[0.0043833065,0.000011938921,0.9894035,0.0014515637,0.00009137557,0.00080341945,0.0033107225,0.000105109924,0.0004390994],"genre_scores_gemma":[0.5963473,0.000032871016,0.40245184,0.000067223235,0.000107089254,0.0003092917,0.00033193207,0.000030281568,0.00032222705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982867,0.00005645357,0.00070634315,0.00024811758,0.0004548991,0.00024748218],"domain_scores_gemma":[0.9936077,0.0051780352,0.00035024693,0.0003349553,0.00045769467,0.00007138254],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008859973,0.00017635089,0.000391523,0.00019555826,0.00005419342,0.0000033942981,0.00013737791,0.00010592101,0.00031416045],"category_scores_gemma":[0.01227056,0.00011726486,0.000026384376,0.00020432427,0.00032935996,0.00005796542,0.000018189809,0.00012479506,0.00000472818],"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":[0.00013081847,0.00040276902,0.0037603842,0.00023463923,0.000014078767,0.0000102310105,0.000047364818,0.0000042106158,0.011329438,0.9550577,0.023157384,0.005850992],"study_design_scores_gemma":[0.0016272047,0.00096955895,0.0047143754,0.00090857537,0.000052409374,0.0000018358293,0.000030307041,0.0024143867,0.01857009,0.96993923,0.0005972322,0.00017477527],"about_ca_topic_score_codex":0.000013042643,"about_ca_topic_score_gemma":0.000039499286,"teacher_disagreement_score":0.59196395,"about_ca_system_score_codex":0.00021075738,"about_ca_system_score_gemma":0.00014683073,"threshold_uncertainty_score":0.9960495},"labels":[],"label_agreement":null},{"id":"W2547225625","doi":"10.1097/ede.0000000000000586","title":"An R Package for G-estimation of Structural Nested Mean Models","year":2016,"lang":"en","type":"letter","venue":"Epidemiology","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":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Heart, Lung, and Blood Institute","keywords":"Confounding; Nested case-control study; Statistics; Estimation; Structural equation modeling; Nested set model; R package; Econometrics; Computer science; Generalized estimating equation; Random effects model; Mathematics; Medicine; Confidence interval; Data mining; Meta-analysis; Internal medicine; Engineering","score_opus":0.34084432123626573,"score_gpt":0.4867982272452088,"score_spread":0.1459539060089431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547225625","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":[0.0007255994,0.00004593608,0.89959323,0.09772703,0.00020578143,0.0008252952,0.00032454025,0.00034269644,0.0002098679],"genre_scores_gemma":[0.01706685,0.000021108159,0.82265687,0.15583995,0.0022938852,0.00037932044,0.0010815673,0.0001762475,0.00048419964],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99689764,0.000778844,0.0011238654,0.00051614,0.00011230849,0.0005712047],"domain_scores_gemma":[0.9867833,0.010736302,0.0011999473,0.0010089448,0.00021713444,0.000054344702],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013555062,0.00039053735,0.0014156331,0.00016883487,0.00004847549,0.0000035903288,0.0004882197,0.0013844363,0.000065012566],"category_scores_gemma":[0.0048534297,0.00028109792,0.00020376731,0.000054785145,0.00024822465,0.00026620782,0.000054034612,0.00063572574,0.000004516702],"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":[0.000031333137,0.000008346667,0.000030867493,0.00056095084,0.00007003911,0.0000064667756,0.00015113055,0.00016196736,0.00053694245,0.29801473,0.6922968,0.008130413],"study_design_scores_gemma":[0.00016215294,0.0002461537,0.000010615423,0.00014230963,0.00006227097,0.000013998375,0.0000047412905,0.012552859,0.00088256027,0.98069483,0.0049310233,0.0002965015],"about_ca_topic_score_codex":0.000021368196,"about_ca_topic_score_gemma":0.000008549896,"teacher_disagreement_score":0.6873658,"about_ca_system_score_codex":0.00010288823,"about_ca_system_score_gemma":0.00005451124,"threshold_uncertainty_score":0.9999641},"labels":[],"label_agreement":null},{"id":"W2550362301","doi":"10.1093/ije/dyw278","title":"The epidemiology of two things considered together. Commentary on:<i>Explanation in Causal Inference: Developments in Mediation and Interaction</i>, by Tyler J. VanderWeele","year":2016,"lang":"en","type":"letter","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"","keywords":"Causal inference; Mediation; Inference; Epidemiology; Causal model; Psychology; Medicine; Epistemology; Sociology; Philosophy; Internal medicine; Social science; Pathology","score_opus":0.1624964604773908,"score_gpt":0.47211000467438774,"score_spread":0.30961354419699694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550362301","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":[0.013417838,0.00070258323,0.02519985,0.9574698,0.0021396389,0.00047481974,0.000104683655,0.000027088327,0.00046367772],"genre_scores_gemma":[0.17051338,0.006367078,0.029354889,0.7907941,0.002245568,0.00011240224,0.00033141917,0.000090990965,0.00019017553],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99315095,0.0026651558,0.003074089,0.0003294355,0.00035281162,0.00042753448],"domain_scores_gemma":[0.93198305,0.06367698,0.0035724263,0.00020738992,0.0005060482,0.000054087643],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074091284,0.00033350705,0.0011784045,0.0006289148,0.00004029554,0.000008045831,0.0006294115,0.0005966615,0.00006606387],"category_scores_gemma":[0.027825918,0.00022156075,0.000114558046,0.000086182095,0.00036295538,0.00038091096,0.00014870692,0.0019805494,0.000003370187],"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":[0.00031036334,0.000080622274,0.0724538,0.00003626349,0.00036513907,0.00009113375,0.00044276778,0.00003437312,0.00015573243,0.018563433,0.89562166,0.011844737],"study_design_scores_gemma":[0.0016382708,0.00027412045,0.0019744823,0.0009794631,0.000026001115,0.00014549935,0.00009502507,0.00013181458,0.00032104726,0.85238266,0.14174306,0.00028854818],"about_ca_topic_score_codex":0.0002127799,"about_ca_topic_score_gemma":0.00024337112,"teacher_disagreement_score":0.8338192,"about_ca_system_score_codex":0.0006742193,"about_ca_system_score_gemma":0.00015163637,"threshold_uncertainty_score":0.98036313},"labels":[],"label_agreement":null},{"id":"W2552901719","doi":"10.1016/j.je.2016.09.003","title":"A typology of four notions of confounding in epidemiology","year":2016,"lang":"en","type":"review","venue":"Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"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":"Japan Society for the Promotion of Science; University of California, San Francisco; McGill University","keywords":"Medicine; Typology; Confounding; Epidemiology; Internal medicine; Anthropology","score_opus":0.7065898224638333,"score_gpt":0.611025391161835,"score_spread":0.09556443130199832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552901719","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":[0.000043130363,0.8975076,0.1002121,0.00036194807,0.00055262,0.00039970622,0.00004216945,0.000018315328,0.00086238794],"genre_scores_gemma":[0.00018322238,0.89363945,0.105721034,0.00008375633,0.00023284179,0.000023279166,0.0000036969536,0.00004704391,0.00006570144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9833609,0.0068979883,0.008576945,0.00034187996,0.00011328895,0.0007090288],"domain_scores_gemma":[0.88738364,0.09784744,0.013603392,0.00059431134,0.00043633435,0.00013486572],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.019384118,0.0004676667,0.0108328955,0.0012916084,0.000021261305,6.3722825e-7,0.0008174471,0.0013015073,0.00019353804],"category_scores_gemma":[0.16270337,0.00029743358,0.0012380579,0.0003268123,0.00082160067,0.00011270103,0.00018179826,0.0013186613,0.000011129389],"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":[0.00004270589,0.00012857403,0.0010105998,0.0072696283,0.00043086457,0.000042148662,0.000040692797,0.0000037768598,0.000016207741,0.74470097,0.0024077292,0.24390608],"study_design_scores_gemma":[0.00024440323,0.00054494914,0.00003433808,0.017535603,0.00034240124,0.0009576044,0.000016947708,0.0000025732545,0.00000467091,0.73448616,0.24562745,0.0002029073],"about_ca_topic_score_codex":0.000021491234,"about_ca_topic_score_gemma":0.000023093628,"teacher_disagreement_score":0.24370319,"about_ca_system_score_codex":0.00030570023,"about_ca_system_score_gemma":0.0005446148,"threshold_uncertainty_score":0.999995},"labels":[],"label_agreement":null},{"id":"W2557277836","doi":"10.1515/ijb-2015-0034","title":"Effect Estimation in Point-Exposure Studies with Binary Outcomes and High-Dimensional Covariate Data – A Comparison of Targeted Maximum Likelihood Estimation and Inverse Probability of Treatment Weighting","year":2016,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","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 Health Centre; Université de Montréal; McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Inverse probability weighting; Estimator; Statistics; Marginal structural model; Average treatment effect; Inverse probability; Econometrics; Weighting; Computer science; Causal inference; Mathematics; Medicine; Bayesian probability","score_opus":0.10122401502630411,"score_gpt":0.4121929389408524,"score_spread":0.3109689239145483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557277836","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":[0.8809781,0.00010860622,0.11766705,0.0007077931,0.00006539503,0.00025831454,0.0002029454,0.000009692081,0.0000020761486],"genre_scores_gemma":[0.7159647,0.000054807206,0.28394124,0.000007869368,0.0000069951207,0.0000031891798,0.000012571003,0.0000069515663,0.0000016878724],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853796,0.00016099363,0.0007275989,0.00012963008,0.00035445587,0.00008938744],"domain_scores_gemma":[0.99513984,0.0031199483,0.0010418325,0.00019577885,0.00047207033,0.000030560754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010170378,0.00014686595,0.00044381004,0.00013782032,0.000028210721,0.0000116130705,0.00020283139,0.000037617327,0.0000040484024],"category_scores_gemma":[0.0023473706,0.00007150096,0.000019978132,0.000066246896,0.00023624557,0.00027096536,0.0001480878,0.000084830295,1.7159061e-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":[0.0071126875,0.0023402679,0.3030027,0.0013027407,0.0041766576,0.00013962612,0.008414017,0.0036484434,0.04894218,0.06783859,0.00064626837,0.5524358],"study_design_scores_gemma":[0.0051680775,0.0063844905,0.026993869,0.0020471693,0.00046835694,0.0001244142,0.00035264835,0.07806754,0.03755126,0.84258676,0.000003845118,0.00025157887],"about_ca_topic_score_codex":0.000042589665,"about_ca_topic_score_gemma":0.00007949206,"teacher_disagreement_score":0.77474815,"about_ca_system_score_codex":0.00015493174,"about_ca_system_score_gemma":0.00008276525,"threshold_uncertainty_score":0.29157245},"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":"W2560696316","doi":"10.1016/j.jclinepi.2016.12.001","title":"Criteria for use of composite end points for competing risks—a systematic survey of the literature with recommendations","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":56,"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; McMaster University Medical Centre","funders":"","keywords":"CINAHL; MEDLINE; Systematic review; Medicine; Event (particle physics); Point (geometry); Computer science; Psychological intervention; Mathematics; Nursing","score_opus":0.8235246654930325,"score_gpt":0.6620055426811549,"score_spread":0.16151912281187764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560696316","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014466817,0.4902066,0.5006692,0.0008769692,0.0011686187,0.0044331476,0.002462747,0.000025116142,0.000012930401],"genre_scores_gemma":[0.00011617419,0.59546506,0.4038821,0.00012567753,0.00019896922,0.00008568482,0.000042398136,0.000055793236,0.000028149905],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9693179,0.017693548,0.012185124,0.00030000356,0.00017935377,0.00032408006],"domain_scores_gemma":[0.6370753,0.33873174,0.021860719,0.00056641374,0.001673365,0.00009247061],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049563184,0.00040693322,0.012028036,0.00017906429,0.00006309884,0.000013123444,0.00079146173,0.00075579947,0.000015099085],"category_scores_gemma":[0.3249552,0.00017983314,0.0020166126,0.00021343552,0.00037050425,0.00016341342,0.00012984237,0.00097116956,4.6202027e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012129032,0.00094431103,0.0035166293,0.762769,0.004694654,0.0000049855266,0.0001639143,0.000004055874,0.000005300879,0.051945213,0.01387756,0.16086146],"study_design_scores_gemma":[0.0012399147,0.0020492205,0.00046913954,0.80525744,0.0032321296,0.00027476248,0.000014392759,0.00009253559,0.0000074476625,0.13671131,0.050212897,0.00043877566],"about_ca_topic_score_codex":0.0000066005214,"about_ca_topic_score_gemma":0.000018449913,"teacher_disagreement_score":0.3322426,"about_ca_system_score_codex":0.000061753555,"about_ca_system_score_gemma":0.00033822967,"threshold_uncertainty_score":0.9786747},"labels":[],"label_agreement":null},{"id":"W2560833249","doi":"10.1056/nejmra1510065","title":"Interpreting Geographic Variations in Results of Randomized, Controlled Trials","year":2016,"lang":"en","type":"article","venue":"New England Journal of Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Randomized controlled trial; MEDLINE; Surgery","score_opus":0.08639357282908044,"score_gpt":0.4075397463559389,"score_spread":0.3211461735268585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560833249","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":[0.089867406,0.0016799622,0.8793791,0.020860823,0.00075711135,0.0016190531,0.00001097024,0.0000547229,0.005770871],"genre_scores_gemma":[0.97684646,0.00094006525,0.021285394,0.000053206375,0.000719012,0.000008765854,4.192208e-7,0.000010371077,0.00013629816],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9941248,0.0015734013,0.0036715756,0.00008655669,0.0004059475,0.00013770227],"domain_scores_gemma":[0.95158845,0.044283584,0.0034800174,0.00016754172,0.0003841371,0.00009624984],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03383323,0.00013241444,0.0035646283,0.0005709852,0.000012459848,0.0000039009255,0.00016323732,0.0000694919,0.00010918572],"category_scores_gemma":[0.2055742,0.00005417341,0.00032979532,0.00016000363,0.0001416745,0.00011664231,0.00001766098,0.00019982131,3.2542113e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.63103163,0.00023661091,0.0010853059,0.00007878034,0.0013428114,0.00008930288,0.005149804,0.0000128208785,0.045337193,0.14605166,0.0044098943,0.1651742],"study_design_scores_gemma":[0.59792864,0.00029959,0.000021901511,0.0021805419,0.000262711,0.00003539433,0.000046482175,0.000026881498,0.0008939859,0.39808878,0.0001705676,0.000044546472],"about_ca_topic_score_codex":0.000044903965,"about_ca_topic_score_gemma":0.000029024653,"teacher_disagreement_score":0.88697904,"about_ca_system_score_codex":0.000030364869,"about_ca_system_score_gemma":0.00008618119,"threshold_uncertainty_score":0.99487203},"labels":[],"label_agreement":null},{"id":"W2588316907","doi":"10.1093/aje/163.suppl_11.s222-c","title":"Bayesian Propensity Score Analysis for Observational Data","year":2006,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":"University of British Columbia","funders":"","keywords":"Propensity score matching; Observational study; Confidence interval; Confounding; Statistics; Medicine; Bayesian probability; Markov chain Monte Carlo; Credible interval; Odds ratio; Outcome (game theory); Econometrics; Mathematics","score_opus":0.5585941002671695,"score_gpt":0.4887832849630621,"score_spread":0.06981081530410738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588316907","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":[0.10589323,0.00006399867,0.8917662,0.0019076909,0.000043089316,0.00013861347,0.0000514988,0.000030034402,0.00010568168],"genre_scores_gemma":[0.47046417,0.000016981845,0.528662,0.0005339371,0.00019874363,0.0000055001246,0.00006817017,0.000011961468,0.000038522205],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99766374,0.00048338878,0.0011814444,0.00025002772,0.00012039795,0.00030101562],"domain_scores_gemma":[0.98945,0.0073747863,0.00205174,0.0006130096,0.0004278774,0.00008258605],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043867324,0.00014467645,0.0011789625,0.00021706632,0.000059297054,0.000005460222,0.00062855746,0.00005547854,0.000039231756],"category_scores_gemma":[0.011952689,0.00010952564,0.00021614222,0.00047538822,0.00037931112,0.00024243102,0.00010640666,0.00021749102,7.960415e-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":[0.00015480987,0.00012138378,0.7957034,0.000016987464,0.00057956623,0.000009578552,0.000017224556,0.00084758346,0.0002267438,0.17518076,0.019487636,0.007654325],"study_design_scores_gemma":[0.00019245513,0.00052555924,0.106968395,0.00002333564,0.0005431077,0.000059504688,0.000026621055,0.003501514,0.00008679023,0.88461095,0.0032943934,0.00016736804],"about_ca_topic_score_codex":0.00016636556,"about_ca_topic_score_gemma":0.00015642932,"teacher_disagreement_score":0.7094302,"about_ca_system_score_codex":0.00006907225,"about_ca_system_score_gemma":0.000106870866,"threshold_uncertainty_score":0.9963701},"labels":[],"label_agreement":null},{"id":"W2588941913","doi":"10.1097/ede.0000000000000445","title":"The Authors Respond","year":2016,"lang":"en","type":"letter","venue":"Epidemiology","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":true,"ca_institutions":"McGill University; Jewish General Hospital","funders":"National Institute of Environmental Health Sciences","keywords":"Homogeneity (statistics); Odds ratio; Statistics; Statistic; Mathematics; Econometrics; Sample size determination; Statistical hypothesis testing; Type I and type II errors; Medicine; Psychology","score_opus":0.4243224623500017,"score_gpt":0.5097027519094776,"score_spread":0.08538028955947585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588941913","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":[0.000011181209,0.00040554017,0.053264957,0.93682116,0.0008931349,0.00035139383,0.000035638055,0.00054761005,0.007669383],"genre_scores_gemma":[0.00001385769,0.0005213335,0.04071286,0.8541332,0.008277253,0.00032646256,0.00003365335,0.00014020104,0.0958412],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944194,0.0028486617,0.0009834531,0.00055483414,0.00015122221,0.0010424589],"domain_scores_gemma":[0.9231808,0.07449665,0.0007461375,0.0013831344,0.0001373269,0.00005592078],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0056967326,0.0004029308,0.00096276705,0.000105038635,0.00021439709,0.000009339308,0.00094673753,0.0019076021,0.00024529724],"category_scores_gemma":[0.061016083,0.00020237328,0.00019999212,0.00010404503,0.0006413289,0.00005268513,0.00023489055,0.002624723,0.00035830814],"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":[0.000008631722,0.0000013232677,0.000022105625,0.000020216456,0.000031900003,0.000041405023,0.000011353566,1.8463343e-8,0.000011492491,0.14677265,0.8489879,0.004090995],"study_design_scores_gemma":[0.000025356245,0.000033579257,0.000006696705,0.000045252982,0.000012224722,0.0000178303,0.0000014587483,0.0000010156801,0.000024451436,0.49480516,0.5048928,0.00013413615],"about_ca_topic_score_codex":0.00000796447,"about_ca_topic_score_gemma":0.000008061026,"teacher_disagreement_score":0.3480325,"about_ca_system_score_codex":0.00015817332,"about_ca_system_score_gemma":0.00009352081,"threshold_uncertainty_score":0.9996763},"labels":[],"label_agreement":null},{"id":"W2591072037","doi":"10.1186/s12874-017-0304-x","title":"Estimation of treatment preference effects in clinical trials when some participants are indifferent to treatment choice","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"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":"Preference; Test (biology); Clinical trial; Medicine; Randomized controlled trial; Treatment effect; Psychological intervention; Treatment and control groups; Research design; Psychology; Statistics; Surgery; Psychiatry; Mathematics","score_opus":0.9639534187192589,"score_gpt":0.7552924577096153,"score_spread":0.2086609610096436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591072037","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":[0.76412773,0.00009900045,0.23221545,0.00075649243,0.00020913465,0.0024079075,0.000013821989,0.00006715124,0.00010329842],"genre_scores_gemma":[0.67490613,0.00044112807,0.32231295,0.000047846577,0.00022746545,0.0017919685,0.000005918428,0.00003105556,0.00023555254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95186496,0.0423804,0.0023575807,0.0008584771,0.0013526909,0.0011859093],"domain_scores_gemma":[0.74146223,0.25478414,0.00092924555,0.0016757511,0.00022389492,0.0009247428],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058668025,0.0003041794,0.002344364,0.00040480483,0.00016297304,0.000040815215,0.00093275384,0.0005840863,0.00020287716],"category_scores_gemma":[0.70189774,0.00020146236,0.00023152994,0.00012549253,0.00071443367,0.00015898277,0.00046849516,0.0005935897,0.000037543607],"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":[0.0010819105,0.002044104,0.04886312,0.0005214944,0.00017512227,0.00007449433,0.0014325066,0.000019554314,0.0009919881,0.04446522,0.00026583878,0.90006465],"study_design_scores_gemma":[0.004697363,0.007891436,0.13237977,0.0013528968,0.00011184705,0.000004259579,0.00014778682,0.0040475414,0.035418414,0.8134112,0.00024562725,0.00029185798],"about_ca_topic_score_codex":0.0010908821,"about_ca_topic_score_gemma":0.005053068,"teacher_disagreement_score":0.89977276,"about_ca_system_score_codex":0.00068712933,"about_ca_system_score_gemma":0.0011642769,"threshold_uncertainty_score":0.9692994},"labels":[],"label_agreement":null},{"id":"W2594198997","doi":"10.1002/cjs.11311","title":"Nested case‐control study designs for left‐truncated survival data","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"National Cancer Institute; National Institutes of Health; National Science Council","keywords":"Covariate; Nested case-control study; Context (archaeology); Cohort; Cohort study; Medicine; Proportional hazards model; Hazard ratio; Statistics; Demography; Survival analysis; Cumulative incidence; Confidence interval; Surgery; Internal medicine; Mathematics; Geography","score_opus":0.49695850643656436,"score_gpt":0.4503157207576387,"score_spread":0.04664278567892566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594198997","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":[0.012910041,0.00003258025,0.9787338,0.00016716578,0.00047800213,0.0007393122,0.00676111,0.000022279824,0.0001557083],"genre_scores_gemma":[0.7848858,0.0000033609726,0.21474764,0.00003258565,0.0001580712,0.000004215051,0.000017026652,0.00004192723,0.00010935163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984539,0.00011794781,0.0006417524,0.00018874946,0.00020143158,0.0003962111],"domain_scores_gemma":[0.99516296,0.0013269989,0.0009030111,0.0011669177,0.0008829471,0.0005571529],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001461022,0.00019408147,0.00047981058,0.00016615716,0.00059595704,0.00026027518,0.0011667378,0.00008029063,0.00009974948],"category_scores_gemma":[0.010117161,0.000180225,0.00003842802,0.00003727877,0.0001638925,0.00042211002,0.000043279968,0.00027492756,0.0000024343806],"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":[0.0006171082,0.0008941684,0.121311,0.0006336952,0.0030201213,0.09526378,0.006527125,0.000132591,0.0006922739,0.40940768,0.2537049,0.10779556],"study_design_scores_gemma":[0.007938886,0.0037332464,0.026482308,0.000312205,0.002331489,0.007125706,0.004684025,0.008227945,0.00024174486,0.93068886,0.006785217,0.0014483448],"about_ca_topic_score_codex":0.0025487866,"about_ca_topic_score_gemma":0.18472134,"teacher_disagreement_score":0.7719758,"about_ca_system_score_codex":0.00016104356,"about_ca_system_score_gemma":0.0013048816,"threshold_uncertainty_score":0.99822104},"labels":[],"label_agreement":null},{"id":"W2599145178","doi":"10.2139/ssrn.2861669","title":"Testing the IV Zero-Covariance Assumption and Identification with an Invalid Instrument","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"University of Toronto","funders":"","keywords":"Covariance; Zero (linguistics); Identification (biology); Mathematics; Econometrics; Statistics; Applied mathematics; Philosophy","score_opus":0.13935600021998235,"score_gpt":0.35867747474161726,"score_spread":0.21932147452163492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599145178","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":[0.4647917,0.00007622356,0.5340299,0.0007561707,0.000022156028,0.000156865,7.886267e-7,0.00008302483,0.00008320079],"genre_scores_gemma":[0.9831954,0.0004540866,0.015989115,0.000032834043,0.000079652,0.000021579814,5.431006e-7,0.000023065584,0.00020372192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99845755,0.000117604526,0.00027060107,0.00017568575,0.00022963466,0.00074892316],"domain_scores_gemma":[0.99900323,0.00023073883,0.0003322766,0.000251337,0.00013577062,0.000046642977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020678642,0.00012619047,0.000114613766,0.000049499846,0.00024190063,0.00008902697,0.00020099831,0.000046865793,0.000005804371],"category_scores_gemma":[0.00041280958,0.00006383889,0.000016999384,0.00011694749,0.00008606801,0.0006260213,0.000028102451,0.0005396976,0.000004629859],"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":[0.000044768636,0.00004037486,0.0017660849,0.000007876429,0.000040304083,0.0000011647937,0.00012512163,0.0000023064247,0.052291837,0.7480345,0.000013682354,0.19763197],"study_design_scores_gemma":[0.00028321243,0.0003931721,0.0018079877,0.00009071704,0.000028778997,0.00045900262,0.00019998178,0.000055848242,0.004402737,0.9921114,0.000051614315,0.00011554965],"about_ca_topic_score_codex":0.000010957381,"about_ca_topic_score_gemma":0.000144581,"teacher_disagreement_score":0.5184037,"about_ca_system_score_codex":0.00048482692,"about_ca_system_score_gemma":0.00034363553,"threshold_uncertainty_score":0.26032743},"labels":[],"label_agreement":null},{"id":"W2599388927","doi":"10.1007/978-3-662-53994-1_11","title":"Statistical Analysis in the Identification of Pain Biomarkers","year":2017,"lang":"en","type":"book-chapter","venue":"","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":"Jewish General Hospital; McGill University","funders":"","keywords":"Identification (biology); Context (archaeology); Data science; Construct (python library); Intervention (counseling); Computer science; Medicine; Psychiatry; Geography","score_opus":0.14548699693747963,"score_gpt":0.42092076791410576,"score_spread":0.27543377097662614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599388927","genre_codex":"methods","genre_gemma":"other","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":[0.000013955633,0.00001784676,0.64402354,0.00008255247,0.000011627054,0.00029431868,0.00007844469,0.00004822843,0.3554295],"genre_scores_gemma":[0.32877183,0.00029055704,0.19605137,0.0001721277,0.000074864634,0.00013518332,0.00047516046,0.00012907383,0.47389984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863786,0.00008490598,0.00066083984,0.00021301977,0.0002996158,0.000103781225],"domain_scores_gemma":[0.99668306,0.0015476999,0.00066228554,0.0009960739,0.000092215756,0.000018657269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023823006,0.00016648739,0.0004153627,0.000299467,0.00003371731,0.000031008196,0.00045026874,0.0001895703,0.00048536528],"category_scores_gemma":[0.0012820314,0.0001138076,0.00012916162,0.000036561363,0.00019791829,0.000053727323,0.000042858115,0.0001812701,0.0000103156635],"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":[0.000004418035,0.000015911299,0.000052753774,0.000052093153,0.00023292066,0.0000055690066,0.000068099725,3.0619915e-7,0.000054293843,0.9914201,0.0023617689,0.00573179],"study_design_scores_gemma":[0.000031385614,0.000021540873,0.00025464818,0.000046107198,0.00043463777,5.221773e-7,0.000032898286,0.00022089908,0.00015032371,0.9970649,0.0016117783,0.00013035834],"about_ca_topic_score_codex":0.0000422775,"about_ca_topic_score_gemma":0.00040141476,"teacher_disagreement_score":0.44797218,"about_ca_system_score_codex":0.000044065644,"about_ca_system_score_gemma":0.000026193742,"threshold_uncertainty_score":0.5314409},"labels":[],"label_agreement":null},{"id":"W2600361628","doi":"10.1016/j.jclinepi.2017.02.017","title":"Quasi-experimental study designs series—paper 7: assessing the assumptions","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":150,"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":"Economic and Social Research Council","keywords":"Causal inference; Regression discontinuity design; Instrumental variable; Series (stratigraphy); Inference; Randomized experiment; Research design; Popularity; Computer science; Econometrics; Clinical study design; Interrupted time series; Quasi-experiment; Management science; Medicine; Statistics; Mathematics; Psychology; Machine learning; Artificial intelligence; Clinical trial; Social psychology; Engineering; Environmental health","score_opus":0.8002265442453002,"score_gpt":0.6851954560928973,"score_spread":0.11503108815240282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600361628","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":[0.8052911,0.00018250846,0.17678455,0.013010122,0.001601323,0.00048296418,0.0000024137685,0.00007574673,0.002569286],"genre_scores_gemma":[0.8908494,0.00010078387,0.1070785,0.0009099212,0.0008488764,0.000013770692,2.422668e-7,0.000023040275,0.0001754403],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98943037,0.0057687284,0.003954417,0.00024493135,0.00024605865,0.00035549217],"domain_scores_gemma":[0.9528551,0.03987134,0.0057885773,0.0010122862,0.00028452656,0.00018818623],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03530513,0.00020553719,0.0018884782,0.000051670722,0.0005913767,0.00007089138,0.0011077526,0.0002718698,0.00018693748],"category_scores_gemma":[0.17091827,0.00011740878,0.0005268463,0.000035620407,0.0007518805,0.0009206443,0.00026324947,0.0014329442,0.000015378417],"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":[0.0003820795,0.01534256,0.64099383,0.000030801675,0.0008287163,0.00024004075,0.00075882935,0.000034643996,0.00093286496,0.3084839,0.020465646,0.011506104],"study_design_scores_gemma":[0.0010168446,0.007328543,0.17821041,0.000103274935,0.0001759602,0.00025273612,0.0015243429,0.000116236886,0.00020703809,0.80735964,0.0034802167,0.00022479192],"about_ca_topic_score_codex":0.000017387012,"about_ca_topic_score_gemma":0.000025734727,"teacher_disagreement_score":0.4988757,"about_ca_system_score_codex":0.00005797222,"about_ca_system_score_gemma":0.00016202312,"threshold_uncertainty_score":0.99335635},"labels":[],"label_agreement":null},{"id":"W2600481469","doi":"10.1016/j.jclinepi.2017.03.012","title":"Quasi-experimental study designs series—paper 4: uses and value","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":247,"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; Impact; University of Ottawa","funders":"World Health Organization","keywords":"Internal validity; Causal inference; External validity; Intervention (counseling); Rivalry; Randomized experiment; Causal model; Randomized controlled trial; Psychology; Causality (physics); Econometrics; Cognitive psychology; Medicine; Social psychology; Economics; Microeconomics; Psychiatry","score_opus":0.7297338715489702,"score_gpt":0.6445861734780254,"score_spread":0.0851476980709448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600481469","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":[0.9616152,0.00026408426,0.03288112,0.0032765307,0.0006975695,0.00030390156,0.0000022471218,0.00004749204,0.0009118628],"genre_scores_gemma":[0.8619483,0.00027445232,0.13645542,0.00067861244,0.00048623176,0.0000068687627,1.3416827e-7,0.00002135328,0.00012862151],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926119,0.003279465,0.0033639027,0.00026670753,0.00017385618,0.00030421268],"domain_scores_gemma":[0.9701868,0.024741696,0.003988941,0.00063656043,0.00018482331,0.0002611188],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02015364,0.00020580206,0.0022666974,0.00005752243,0.00021150614,0.000027342589,0.0005664715,0.00028253987,0.00009023375],"category_scores_gemma":[0.1508935,0.00014378125,0.0002978525,0.000020813077,0.00067006564,0.0006129379,0.00025365993,0.0008484474,0.00000582763],"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":[0.0010379573,0.008414693,0.6378926,0.000041413557,0.00047835114,0.00025894286,0.0005128309,0.0000068459753,0.0005948855,0.3372663,0.007652337,0.0058428445],"study_design_scores_gemma":[0.0014407858,0.018275138,0.08830191,0.00009345131,0.000117553274,0.00029424162,0.00060674484,0.000047761616,0.0004598145,0.8881149,0.002020244,0.00022743377],"about_ca_topic_score_codex":0.000024064928,"about_ca_topic_score_gemma":0.000017582846,"teacher_disagreement_score":0.5508486,"about_ca_system_score_codex":0.000030183652,"about_ca_system_score_gemma":0.0000898047,"threshold_uncertainty_score":0.85625887},"labels":[],"label_agreement":null},{"id":"W2602609302","doi":"10.1007/s00068-017-0786-6","title":"A systematic review of propensity score methods in the acute care surgery literature: avoiding the pitfalls and proposing a set of reporting guidelines","year":2017,"lang":"en","type":"review","venue":"European Journal of Trauma and Emergency Surgery","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Propensity score matching; Observational study; Medicine; Matching (statistics); Confounding; MEDLINE; Data extraction; Intensive care medicine; Statistics; Internal medicine; Mathematics; Pathology","score_opus":0.6400521993009686,"score_gpt":0.5400017519275301,"score_spread":0.10005044737343849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602609302","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":[0.00081731007,0.9965049,0.00090039027,0.00007802579,0.0002922361,0.0012713635,0.00001696699,0.00001361003,0.000105176405],"genre_scores_gemma":[0.0004391838,0.99200034,0.007281523,0.000021297234,0.0001487729,0.000016880182,0.0000073126143,0.00006829225,0.000016374861],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9805829,0.00839041,0.009917936,0.00030207433,0.0005201796,0.00028649313],"domain_scores_gemma":[0.9715562,0.0036469372,0.02267729,0.0009074091,0.0011405866,0.000071576294],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05243057,0.0005093011,0.0054232236,0.00036907961,0.0002099406,0.000074097334,0.0006002843,0.000092304916,0.0000040433974],"category_scores_gemma":[0.040073138,0.00023875773,0.0012791703,0.00044131314,0.00014489918,0.0003009497,0.00017565065,0.0009783907,1.5318024e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063356383,0.000018034563,0.000120955716,0.8536204,0.0003247669,0.00042651288,0.0014043074,3.0396038e-8,0.000006181941,0.000058596368,0.00110602,0.14290786],"study_design_scores_gemma":[0.00002723701,0.00004161002,0.00004314495,0.9887004,0.0027634792,0.002712268,0.00026953663,5.8198685e-7,0.000023665612,0.0005242915,0.0046219314,0.0002718579],"about_ca_topic_score_codex":0.000004100241,"about_ca_topic_score_gemma":0.0000022031452,"teacher_disagreement_score":0.142636,"about_ca_system_score_codex":0.000031221483,"about_ca_system_score_gemma":0.00021220728,"threshold_uncertainty_score":0.97572213},"labels":[],"label_agreement":null},{"id":"W2602905072","doi":"10.1097/ede.0000000000000657","title":"Treatment Prediction, Balance, and Propensity Score Adjustment","year":2017,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Propensity score matching; Covariate; Confounding; Causal inference; Statistics; Logistic regression; Econometrics; National Health and Nutrition Examination Survey; Medicine; Inverse probability weighting; Average treatment effect; Weighting; Mathematics; Population; Environmental health","score_opus":0.39520376771656374,"score_gpt":0.43289861150205045,"score_spread":0.03769484378548671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602905072","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":[0.002838887,0.0031397184,0.023296896,0.94657916,0.0020211302,0.0041653933,0.0006370756,0.0017043657,0.015617364],"genre_scores_gemma":[0.0026863038,0.010825318,0.14890274,0.75831604,0.02183788,0.0032221123,0.0018110299,0.0004422435,0.05195635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997241,0.00058827735,0.00068079744,0.00078364334,0.00010991525,0.0005963451],"domain_scores_gemma":[0.99507594,0.0025676547,0.0008565296,0.0013093153,0.0001062704,0.000084300096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065627735,0.00051727577,0.0016329158,0.00009745953,0.00019358142,0.000011863783,0.00031473816,0.0012374505,0.00007583234],"category_scores_gemma":[0.0038718518,0.00037454648,0.00013362654,0.000024258443,0.00045568545,0.00010456777,0.00018126631,0.001051859,0.000031103747],"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":[0.0000106883645,0.000028706181,0.0062120245,0.00013841697,0.0001136381,0.00013003957,0.000032556065,2.8749406e-7,0.0000059144063,0.005951621,0.9844074,0.0029687076],"study_design_scores_gemma":[0.00023462264,0.00046529848,0.0026061395,0.00014160364,0.00013075204,0.00020252663,0.0000017307294,0.000040131443,0.00003453473,0.37154788,0.6243186,0.00027616194],"about_ca_topic_score_codex":0.00007676673,"about_ca_topic_score_gemma":0.000015648715,"teacher_disagreement_score":0.36559626,"about_ca_system_score_codex":0.00031199987,"about_ca_system_score_gemma":0.00008556622,"threshold_uncertainty_score":0.99987066},"labels":[],"label_agreement":null},{"id":"W2604427595","doi":"10.1016/j.jclinepi.2017.03.016","title":"Quasi-experimental study designs series—paper 13: realizing the full potential of quasi-experiments for health research","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"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; Bruyère","funders":"","keywords":"Quasi-experiment; Management science; Work (physics); Computer science; Medicine; Engineering; Environmental health","score_opus":0.8447639045687289,"score_gpt":0.7027608747233955,"score_spread":0.1420030298453333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604427595","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":[0.67811036,0.0008941181,0.29191786,0.023983013,0.0016078111,0.0028126128,0.000026008629,0.000062850915,0.00058538065],"genre_scores_gemma":[0.8998708,0.00034729502,0.098163456,0.00059376936,0.0008178002,0.00006447732,0.0000012143859,0.000042531152,0.0000986347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.980445,0.011232547,0.0064323773,0.00043566307,0.0006326981,0.0008216967],"domain_scores_gemma":[0.95550734,0.034754965,0.007264376,0.0012566091,0.00088995614,0.00032673893],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08946948,0.00026283096,0.0029706256,0.00013569245,0.00072386,0.000033486336,0.0015769969,0.00033711913,0.00006132949],"category_scores_gemma":[0.13135146,0.00016600858,0.0007070382,0.00007505078,0.0012292945,0.00045101836,0.0004287782,0.0015014807,0.000003371198],"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":[0.027018461,0.085186236,0.074252926,0.00069048,0.0031905065,0.00020796817,0.007859512,0.00011060813,0.017946148,0.63289493,0.122626685,0.028015532],"study_design_scores_gemma":[0.0049492586,0.12914595,0.011974079,0.0004504731,0.00013351829,0.00021050927,0.010356981,0.00040884723,0.00334961,0.83529997,0.0033135235,0.0004073129],"about_ca_topic_score_codex":0.0001759062,"about_ca_topic_score_gemma":0.00009634545,"teacher_disagreement_score":0.22176048,"about_ca_system_score_codex":0.00013709614,"about_ca_system_score_gemma":0.0004732574,"threshold_uncertainty_score":0.9375828},"labels":[],"label_agreement":null},{"id":"W2604738972","doi":"10.1111/ectj.12092","title":"Oracle and adaptive false discovery rate controlling methods for one‐sided testing: theory and application in treatment effect evaluation","year":2017,"lang":"en","type":"article","venue":"Econometrics Journal","topic":"Advanced Causal Inference Techniques","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 Toronto","funders":"Connaught Fund; Simon Fraser University; Deutsche Forschungsgemeinschaft; Royal Economic Society; Royal Society","keywords":"False discovery rate; Oracle; Multiple comparisons problem; Computer science; Monte Carlo method; Parametric statistics; Econometrics; Sample size determination; Deconvolution; Statistics; Machine learning; Mathematics; Algorithm","score_opus":0.4302061907665916,"score_gpt":0.515759728347448,"score_spread":0.08555353758085638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604738972","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":[0.29377505,0.00056149083,0.7044788,0.00004452781,0.000034126082,0.000906991,0.0000058454993,0.000017242613,0.00017590223],"genre_scores_gemma":[0.73797804,0.00017767768,0.26152208,0.0000085657275,0.000053753905,0.0002236918,0.0000012289079,0.000016004991,0.000018986808],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871874,0.00045869293,0.00036284124,0.00021804964,0.00006819437,0.00017349793],"domain_scores_gemma":[0.9865258,0.012323063,0.00069995073,0.00022503007,0.0001562499,0.00006993856],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010381358,0.0001499045,0.00038214438,0.00039839867,0.0003109863,0.00033493317,0.00010581771,0.00006884779,0.0000028156694],"category_scores_gemma":[0.023490004,0.00012173618,0.000042304906,0.00012367193,0.00006606363,0.0007404799,0.000040686555,0.00013714522,4.067335e-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":[0.00031354974,0.00009787371,0.008371863,0.000031741278,0.000088358385,0.0000012236311,0.00022275705,0.00011012551,0.0022435654,0.047411878,0.0000025332267,0.94110453],"study_design_scores_gemma":[0.0021937205,0.0007300368,0.009472446,0.000066933775,0.00013463547,0.00001481086,0.000068489615,0.041972592,0.005708011,0.9394673,0.000021025793,0.0001499829],"about_ca_topic_score_codex":0.00000930358,"about_ca_topic_score_gemma":0.000011865601,"teacher_disagreement_score":0.94095457,"about_ca_system_score_codex":0.00031048214,"about_ca_system_score_gemma":0.00005142415,"threshold_uncertainty_score":0.98473555},"labels":[],"label_agreement":null},{"id":"W2605813800","doi":"10.23889/ijpds.v1i1.171","title":"Modelling Diagnostic Validity Estimates from Administrative Health Data","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","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":"University of Manitoba","funders":"","keywords":"Statistics; Univariate; Bivariate analysis; Confidence interval; Youden's J statistic; Mean squared error; Mathematics; Sensitivity (control systems); Complement (music); Variance (accounting); Regression; Correlation; Regression analysis; Standard error; Econometrics; Multivariate statistics","score_opus":0.7832932054931357,"score_gpt":0.6179929298057897,"score_spread":0.16530027568734607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605813800","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":[0.029593306,0.000027869859,0.9625064,0.00207427,0.0014638181,0.00027002665,0.00390987,0.00007081097,0.00008362346],"genre_scores_gemma":[0.5981053,0.00007848651,0.40030065,0.000059195754,0.00032285674,0.0000051705974,0.0011025469,0.000010128926,0.000015632444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977028,0.000031978925,0.00055529183,0.000548188,0.0009019346,0.00025981487],"domain_scores_gemma":[0.9945029,0.0015811666,0.0011776845,0.0020281863,0.00054236985,0.0001676782],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023893092,0.00014158523,0.0001992809,0.00011888701,0.0013008631,0.001231976,0.0074309236,0.00003699463,0.0000352872],"category_scores_gemma":[0.021910366,0.00012656435,0.000028105002,0.00005268513,0.0002537233,0.007617014,0.0015528578,0.00020619346,0.0000047221206],"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":[0.0003532912,0.0010457603,0.115113236,0.00009431956,0.00036188125,0.00011428579,0.0013028315,0.012339638,0.0010337587,0.685202,0.04415702,0.13888197],"study_design_scores_gemma":[0.00018124729,0.00004511238,0.0038997438,0.00016143266,0.00001417534,0.000025525957,0.000034369878,0.41493323,0.0002261905,0.57942027,0.000923451,0.00013526203],"about_ca_topic_score_codex":0.00079240167,"about_ca_topic_score_gemma":0.00022570406,"teacher_disagreement_score":0.568512,"about_ca_system_score_codex":0.00019729321,"about_ca_system_score_gemma":0.00036811281,"threshold_uncertainty_score":0.9999993},"labels":[],"label_agreement":null},{"id":"W2605897081","doi":"10.1186/s41512-017-0012-3","title":"Validation of prediction models: examining temporal and geographic stability of baseline risk and estimated covariate effects","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Covariate; Baseline (sea); Stability (learning theory); Statistics; Econometrics; Computer science; Mathematics; Machine learning; Biology","score_opus":0.3648981795435242,"score_gpt":0.46175307836447255,"score_spread":0.09685489882094833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605897081","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":[0.93515944,0.0005370146,0.06290278,0.000027299122,0.000021878705,0.0010899826,0.00011160939,0.00005495192,0.00009505711],"genre_scores_gemma":[0.9773926,0.0018790788,0.020540627,0.0000012247704,0.000016374892,0.00012565446,0.000024310759,0.000017866123,0.000002235954],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979902,0.00055726303,0.000431078,0.0003516714,0.0004080942,0.00026168948],"domain_scores_gemma":[0.9757554,0.022831064,0.00032843524,0.00045584622,0.00051153655,0.00011773791],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004795097,0.00015350227,0.00036717692,0.00019216901,0.00032686285,0.00007590359,0.00013979526,0.00013043654,0.000006768288],"category_scores_gemma":[0.06939388,0.0001329962,0.00001898451,0.00012626403,0.00093281886,0.00036683565,0.0002622754,0.0003111243,1.913777e-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":[0.000073417315,0.00014127449,0.97402495,0.0012169824,0.000035914978,0.0000064739925,0.00050338946,0.000008449945,0.0010462529,0.0063626855,0.00001445471,0.016565753],"study_design_scores_gemma":[0.00076933595,0.0010925214,0.46232662,0.0012304472,0.00013266876,0.0000068632417,0.00015505872,0.033756606,0.018784143,0.4815931,0.0000015730642,0.00015106634],"about_ca_topic_score_codex":0.00056067813,"about_ca_topic_score_gemma":0.000016112432,"teacher_disagreement_score":0.5116983,"about_ca_system_score_codex":0.000012344181,"about_ca_system_score_gemma":0.000050421375,"threshold_uncertainty_score":0.93844503},"labels":[],"label_agreement":null},{"id":"W2606149955","doi":"10.1016/j.jclinepi.2017.04.001","title":"Magnitude and direction of missing confounders had different consequences on treatment effect estimation in propensity score analysis","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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; Population Health Research Institute","funders":"Cancer Research UK","keywords":"Confounding; Propensity score matching; Medicine; Inverse probability weighting; Observational study; Statistics; Population; Odds ratio; Internal medicine; Mathematics; Environmental health","score_opus":0.6695902067594982,"score_gpt":0.6039816511912118,"score_spread":0.06560855556828638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606149955","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":[0.95345324,0.000056175573,0.04474183,0.0012617554,0.00012617258,0.0002013535,0.0000013811205,0.00001100759,0.00014707133],"genre_scores_gemma":[0.9820866,0.00036185863,0.01742035,0.000071390015,0.00003843857,0.0000043015075,9.2555024e-7,0.0000057409043,0.000010406335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99496305,0.0023222275,0.0022421388,0.00019511892,0.00011986873,0.00015761788],"domain_scores_gemma":[0.96770144,0.027525734,0.0042448486,0.0002964021,0.0001287211,0.00010288479],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007437641,0.00016856757,0.0026704243,0.0001874321,0.00008031584,0.000014716736,0.00014864991,0.00020373278,0.000009038361],"category_scores_gemma":[0.081290096,0.00009568697,0.0003541601,0.00005108016,0.00067738496,0.00014056913,0.00003417674,0.00036238317,3.6167737e-7],"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":[0.0005402254,0.00024387125,0.9058064,0.00005605015,0.0004032229,0.000027907654,0.000038346785,0.00017268748,0.00021848071,0.005293669,0.000014570751,0.08718453],"study_design_scores_gemma":[0.00077685405,0.0026570093,0.74960625,0.00026089337,0.00043922942,0.00002231701,0.0000061290198,0.002491938,0.0011998648,0.2424615,0.0000042829793,0.00007375008],"about_ca_topic_score_codex":0.0001406778,"about_ca_topic_score_gemma":0.00026801162,"teacher_disagreement_score":0.23716784,"about_ca_system_score_codex":0.000099574645,"about_ca_system_score_gemma":0.000061181025,"threshold_uncertainty_score":0.9264486},"labels":[],"label_agreement":null},{"id":"W2607186425","doi":"10.1002/cjs.11317","title":"Estimating treatment effects in observational studies with both prevalent and incident cohorts","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Propensity score matching; Observational study; Medicine; Selection bias; Cohort; Cohort study; Population; Cancer registry; Demography; Internal medicine; Environmental health","score_opus":0.2298392366367948,"score_gpt":0.42379400865753053,"score_spread":0.19395477202073572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607186425","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":[0.8074983,0.00062599056,0.19072786,0.0002922449,0.00019547385,0.0004265476,0.00009518302,0.000010273836,0.00012814699],"genre_scores_gemma":[0.5491589,0.000054238975,0.4506712,0.000021758131,0.000035408342,0.000008453075,0.0000011710558,0.000010696781,0.00003821892],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992233,0.000034663688,0.00032073716,0.000090369555,0.00015033442,0.00018057696],"domain_scores_gemma":[0.99820095,0.00067329145,0.00052477914,0.0001680808,0.00022192064,0.00021096606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002764827,0.00012807858,0.00032971913,0.0001051541,0.00019111842,0.000075117816,0.00011323786,0.000029754605,0.000006050825],"category_scores_gemma":[0.0025174788,0.00009691302,0.00001343462,0.000024005078,0.00018089356,0.00018969359,0.000014243765,0.0001124221,2.6243987e-7],"study_design_candidate":"observational","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":[0.000043679793,0.00007526646,0.75614434,0.0007098287,0.0003152608,0.0038255567,0.004791437,0.00041048392,0.00004388188,0.19918433,0.0025070435,0.031948872],"study_design_scores_gemma":[0.00095181965,0.0010985661,0.4073564,0.0015822661,0.0001588316,0.0002480698,0.00023478853,0.0012331356,0.00019318104,0.5865549,0.00014661095,0.00024141524],"about_ca_topic_score_codex":0.0007942487,"about_ca_topic_score_gemma":0.045347378,"teacher_disagreement_score":0.3873706,"about_ca_system_score_codex":0.00048429496,"about_ca_system_score_gemma":0.0005172635,"threshold_uncertainty_score":0.97207254},"labels":[],"label_agreement":null},{"id":"W2608829643","doi":"10.1177/0081175017701180","title":"Estimating Moderated Causal Effects with Time-varying Treatments and Time-varying Moderators: Structural Nested Mean Models and Regression with Residuals","year":2017,"lang":"en","type":"article","venue":"Sociological Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"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","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Regression analysis; Statistics; Econometrics; Regression; Mathematics; Psychology","score_opus":0.28897851064091584,"score_gpt":0.46085075050692603,"score_spread":0.1718722398660102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608829643","genre_codex":"empirical","genre_gemma":"methods","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":[0.72828114,0.00010426119,0.27019268,0.00011901495,0.000023622992,0.00063315145,0.000007645885,0.00036220156,0.00027628124],"genre_scores_gemma":[0.4887484,0.000008176534,0.51099896,0.000049619164,0.000037817863,0.00006406435,0.000011054148,0.00003441815,0.000047513986],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961439,0.0018550442,0.0003939154,0.00081080955,0.00021351522,0.0005828226],"domain_scores_gemma":[0.99338824,0.005141824,0.0005769568,0.00056588295,0.00014160946,0.00018546922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011452319,0.0005398002,0.0011567831,0.00007866862,0.0011133896,0.00013555324,0.00024509127,0.0005250738,0.000018249228],"category_scores_gemma":[0.0024511088,0.00031214004,0.00004136708,0.0000593121,0.0009637549,0.00055907696,0.0003048199,0.0005399786,0.0000013671341],"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":[0.01354507,0.00076215185,0.035898685,0.0026444206,0.0044477894,0.002493509,0.03383261,0.02633142,0.60587525,0.17917424,0.00033489882,0.094659925],"study_design_scores_gemma":[0.00143216,0.0012567575,0.0007594342,0.0004015887,0.0001919622,0.00021191905,0.000053941974,0.22867924,0.009672447,0.7568776,1.1907894e-7,0.00046284468],"about_ca_topic_score_codex":0.00003987052,"about_ca_topic_score_gemma":0.0000029865155,"teacher_disagreement_score":0.59620285,"about_ca_system_score_codex":0.000076176424,"about_ca_system_score_gemma":0.000046702382,"threshold_uncertainty_score":0.99993306},"labels":[],"label_agreement":null},{"id":"W2609185034","doi":"10.1186/s12874-017-0338-0","title":"Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"University of Oxford; Cancer Research UK","keywords":"Covariate; Propensity score matching; Confounding; Statistics; Residual; Matching (statistics); Logistic regression; Regression; Mathematics; Regression analysis; Econometrics; Medicine","score_opus":0.8896096151371321,"score_gpt":0.6436425630183503,"score_spread":0.24596705211878178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609185034","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":[0.39532194,0.0001911004,0.6014486,0.0008138763,0.00010317587,0.0011657444,0.0000043447076,0.00010862676,0.0008426167],"genre_scores_gemma":[0.37699646,0.00012543866,0.62187684,0.00008545961,0.00020854383,0.0005257433,0.000005235831,0.00003314762,0.00014314277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930576,0.0028071294,0.00078562397,0.000777531,0.0014094921,0.0011625884],"domain_scores_gemma":[0.9699904,0.027565664,0.0003175496,0.0013668399,0.0003975896,0.0003619612],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042841017,0.00023788527,0.0011410471,0.00057748234,0.00053838396,0.00011859877,0.0012160272,0.00042111467,0.00012745187],"category_scores_gemma":[0.10085806,0.00019675477,0.00016239504,0.00034404694,0.0009582182,0.00026173465,0.0010800585,0.0014114397,0.0000053518006],"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":[0.0037872123,0.0005952665,0.14929408,0.0022556984,0.0007084965,0.0005073908,0.0026770516,0.00015959605,0.013009514,0.8007784,0.0020105364,0.024216767],"study_design_scores_gemma":[0.0020142405,0.00020917128,0.030842185,0.0006806706,0.00010476349,0.000029077473,0.0004129297,0.0018470479,0.012631017,0.9508296,0.00009583295,0.00030343974],"about_ca_topic_score_codex":0.00079586287,"about_ca_topic_score_gemma":0.012711878,"teacher_disagreement_score":0.15005122,"about_ca_system_score_codex":0.00031799285,"about_ca_system_score_gemma":0.00087638944,"threshold_uncertainty_score":0.9855966},"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":"W261013088","doi":"10.3138/cjpe.24.002","title":"A Promising New Approach to Eliminating Selection Bias","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Variance (accounting); Computer science; Process (computing); Selection bias; Transformation (genetics); Econometrics; Data science; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics; Economics","score_opus":0.5436381024989055,"score_gpt":0.5032713346008978,"score_spread":0.04036676789800775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261013088","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":[0.26686925,0.00016839053,0.71183276,0.002117949,0.00022395902,0.004496273,0.0000015617634,0.00021685808,0.014072976],"genre_scores_gemma":[0.5259823,6.6250095e-7,0.4736697,0.00008503246,0.00015766684,0.00002144471,0.0000019754798,0.0000112662665,0.00006991254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857527,0.00014144016,0.00045421388,0.00013607349,0.00041497612,0.00027803276],"domain_scores_gemma":[0.998089,0.000064215084,0.00037241052,0.00011871015,0.0008626112,0.00049302436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002432738,0.00012039761,0.00018898965,0.00042703544,0.00011500697,0.00013266821,0.00015399713,0.00008096838,0.00005146261],"category_scores_gemma":[0.003924836,0.00011504136,0.00006313545,0.0005149436,0.00001506762,0.0003301929,0.0000035042772,0.00023088304,0.000004511462],"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":[0.000009009568,0.000051991425,0.00013685621,0.000011446013,0.000011997054,0.0000021330688,0.0013225864,0.0003566021,0.0008058513,0.0067985253,0.0034901705,0.98700285],"study_design_scores_gemma":[0.0011553556,0.0029469137,0.004345908,0.0006695044,0.00035158175,0.0004962102,0.0008937954,0.033354,0.010259695,0.9380491,0.006851304,0.0006266586],"about_ca_topic_score_codex":0.00022765363,"about_ca_topic_score_gemma":0.0012893153,"teacher_disagreement_score":0.98637617,"about_ca_system_score_codex":0.0006920162,"about_ca_system_score_gemma":0.001741407,"threshold_uncertainty_score":0.46986786},"labels":[],"label_agreement":null},{"id":"W2611759197","doi":"10.1093/aje/kwx027","title":"Tools for the Precision Medicine Era: How to Develop Highly Personalized Treatment Recommendations From Cohort and Registry Data Using Q-Learning","year":2017,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"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 Allergy and Infectious Diseases; National Cancer Institute; Office of Naval Research; National Heart, Lung, and Blood Institute; Department of Internal Medicine, University of Utah; Juno Therapeutics; Sanofi Genzyme; Takeda Oncology; U.S. Navy; Kite Pharma; Janssen Scientific Affairs; Health Resources and Services Administration; Otsuka Pharmaceutical; Center for International Blood and Marrow Transplant Research; Astellas Pharma; Swedish Orphan Biovitrum; U.S. Department of Health and Human Services; Miltenyi Biotec; National Institutes of Health; Seattle Genetics; Telomere Diagnostics; Pharmacyclics; bluebird bio; Atara Biotherapeutics; Meso Scale Diagnostics; Cerus Corporation; Novartis Pharmaceuticals Canada; Jazz Pharmaceuticals; Sunesis; Department of Epidemiology, Biostatistics and Occupational Health, McGill University; Medac; Actinium Pharmaceuticals; Chimerix; U.S. Department of Defense; Medical College of Wisconsin; McGill University; Karyopharm Therapeutics; University of Minnesota; Fred Hutchinson Cancer Research Center; Division of Intramural Research, National Institute of Allergy and Infectious Diseases; Faculty of Medicine, McGill University; Celgene; Merck; Spectrum Pharmaceuticals; Patient-Centered Outcomes Research Institute; Incyte; Pfizer; Angiocrine Bioscience; Astellas Pharma US; Bristol-Myers Squibb; Be The Match Foundation; Shire; Novartis Pharmaceuticals Corporation; Amgen; Gilead Sciences; HistoGenetics; MedImmune; Moffitt Cancer Center; Sanofi; National Marrow Donor Program","keywords":"Medicine; Randomized controlled trial; Personalized medicine; Population; Precision medicine; Cohort; Clinical trial; Medical physics; Machine learning; Computer science; Bioinformatics; Surgery; Internal medicine; Pathology","score_opus":0.4737298912114096,"score_gpt":0.5235393196854121,"score_spread":0.04980942847400249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611759197","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":[0.09857394,0.00032151787,0.8457789,0.05471374,0.00015221932,0.0003466483,0.00005486177,0.000019064271,0.000039137554],"genre_scores_gemma":[0.18596435,0.0017646699,0.81118804,0.000574299,0.00034537548,0.00002079968,0.000033214827,0.000020945266,0.00008830623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99817395,0.00058870245,0.0006426346,0.00026897425,0.00009406925,0.00023166809],"domain_scores_gemma":[0.96600163,0.030480338,0.0022466392,0.0008189209,0.00032553187,0.00012693115],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040567834,0.00016527188,0.00089677505,0.00006206347,0.00043495078,0.000037307254,0.0006729105,0.000053395175,0.000023869574],"category_scores_gemma":[0.11641321,0.00009512521,0.00004642178,0.00006792353,0.0006073721,0.00034189777,0.00021049878,0.00025281322,3.359715e-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":[0.0005094047,0.000055916003,0.04271001,0.000011147047,0.0007925116,0.000012662769,0.0012369236,0.000053023745,0.0020620094,0.010185498,0.021749774,0.9206211],"study_design_scores_gemma":[0.004000198,0.008717661,0.06538531,0.0018012469,0.002215882,0.00073589984,0.011560958,0.011563544,0.0005810893,0.3753362,0.5170748,0.0010271985],"about_ca_topic_score_codex":0.00040461228,"about_ca_topic_score_gemma":0.00005630758,"teacher_disagreement_score":0.91959393,"about_ca_system_score_codex":0.00014154852,"about_ca_system_score_gemma":0.000116026706,"threshold_uncertainty_score":0.8910296},"labels":[],"label_agreement":null},{"id":"W2611803101","doi":"10.1089/end.2017.0290","title":"Editorial Comment on Tay <i>et al</i> .","year":2017,"lang":"he","type":"editorial","venue":"Journal of Endourology","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":"Western University","funders":"","keywords":"Medicine; Chin; Library science; Anatomy; Computer science","score_opus":0.07674665673909771,"score_gpt":0.4266599938582919,"score_spread":0.3499133371191942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611803101","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":[0.000051826344,0.00019026977,0.003502425,0.027360385,0.9628279,0.00047323754,0.00019571903,0.00007555926,0.0053226654],"genre_scores_gemma":[0.0003388286,0.0027404332,0.0061030793,0.0111933015,0.97889364,0.000022950337,0.000034509398,0.00019003982,0.00048323342],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992386,0.001147832,0.0025075474,0.00058575574,0.0023832552,0.00098964],"domain_scores_gemma":[0.9773843,0.009963539,0.008612263,0.0015766418,0.0020416009,0.00042160795],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0048514595,0.0010274793,0.002749195,0.000547111,0.0003379224,0.0002234137,0.0024743173,0.0021938253,0.000491471],"category_scores_gemma":[0.01817954,0.00086314266,0.0008601129,0.000078665755,0.0004746751,0.00043770275,0.0005027528,0.008351999,0.00018156027],"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":[0.0020308192,0.0006814401,0.000008263088,0.000079130514,0.00046007428,0.00042030375,0.00016846675,0.000018269428,0.0004991003,0.004797027,0.9904043,0.00043280044],"study_design_scores_gemma":[0.0031042385,0.008538494,0.0000014543128,0.0005810904,0.00040188857,0.00017246371,0.000024392712,0.0000029126204,0.000735753,0.053926833,0.93194246,0.00056803133],"about_ca_topic_score_codex":0.000026672673,"about_ca_topic_score_gemma":0.00002791632,"teacher_disagreement_score":0.05846186,"about_ca_system_score_codex":0.0005613494,"about_ca_system_score_gemma":0.0014585429,"threshold_uncertainty_score":0.99938196},"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":"W2617884986","doi":"10.1016/j.jclinepi.2017.02.015","title":"Quasi-experimental study designs series—paper 6: risk of bias assessment","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":95,"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":"Economic and Social Research Council","keywords":"Unobservable; Regression discontinuity design; Selection bias; Confounding; Econometrics; Internal validity; Computer science; Selection (genetic algorithm); Instrumental variable; Information bias; Systematic review; External validity; Discontinuity (linguistics); Statistics; Machine learning; MEDLINE; Mathematics","score_opus":0.9095861097698986,"score_gpt":0.7252836017000012,"score_spread":0.18430250806989745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617884986","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":[0.00034072826,0.96273655,0.03256837,0.00012737734,0.0016346031,0.0015982641,0.000050558512,0.000058966558,0.00088460837],"genre_scores_gemma":[0.00043619424,0.8474958,0.15092862,0.000067397945,0.0007919939,0.000049093203,0.000003630155,0.000079691,0.00014759276],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95211166,0.029281978,0.016956873,0.0005905764,0.0005091406,0.00054975436],"domain_scores_gemma":[0.8534884,0.10581419,0.038377225,0.001477971,0.0004984558,0.00034379508],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07801521,0.0007406387,0.020036748,0.0002803919,0.00012823807,0.00001687271,0.0017278205,0.001338477,0.00023826845],"category_scores_gemma":[0.23854804,0.00046708007,0.0038570135,0.00011133906,0.00074798334,0.0003630315,0.0004463081,0.004117944,0.00001326825],"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":[0.00030361078,0.02249234,0.010724006,0.0053137257,0.0055402108,0.00030782892,0.0001335151,0.0000033742185,8.134067e-7,0.04298305,0.008376871,0.90382063],"study_design_scores_gemma":[0.0012117581,0.036479328,0.00047619938,0.009971759,0.0046464093,0.0004367,0.0002294493,0.0000072907114,0.0000028670736,0.25231305,0.69351095,0.00071425544],"about_ca_topic_score_codex":0.000024429763,"about_ca_topic_score_gemma":0.0000141590035,"teacher_disagreement_score":0.9031064,"about_ca_system_score_codex":0.00020164157,"about_ca_system_score_gemma":0.0012142354,"threshold_uncertainty_score":0.999958},"labels":[],"label_agreement":null},{"id":"W2621147310","doi":"10.1016/j.jclinepi.2017.05.016","title":"A systematic survey of the methods literature on the reporting quality and optimal methods of handling participants with missing outcome data for continuous outcomes in randomized controlled trials","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":48,"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 Toronto; McMaster University; Impact","funders":"","keywords":"Missing data; Ranking (information retrieval); Imputation (statistics); Randomized controlled trial; Data quality; Statistics; Type I and type II errors; Data collection; Systematic review; Meta-analysis; Computer science; Medicine; MEDLINE; Mathematics; Machine learning; Operations management","score_opus":0.968639756689589,"score_gpt":0.7980095567593587,"score_spread":0.17063019993023032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621147310","genre_codex":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003398626,0.5540548,0.43769246,0.0006074865,0.00046163867,0.006731784,0.00009425921,0.000008928881,0.000008750528],"genre_scores_gemma":[0.00035039856,0.31441927,0.68473303,0.000113869704,0.000098008684,0.00021029222,0.0000058920796,0.000043351924,0.000025910642],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.29487222,0.58540446,0.117477775,0.0008937427,0.0005952978,0.00075650256],"domain_scores_gemma":[0.013057432,0.7838216,0.20000406,0.002064429,0.0009392761,0.00011323368],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8710616,0.0006082608,0.10341462,0.00020691965,0.000098593555,0.00004392958,0.0016517774,0.000927988,0.000002414012],"category_scores_gemma":[0.99384177,0.00019447153,0.0051356535,0.00015308066,0.0008856465,0.0001275021,0.0003717663,0.0021439097,2.8520068e-8],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14344642,0.0012323171,0.021461377,0.40884727,0.039944213,0.000048950256,0.00059724954,0.000044319495,0.0000057537045,0.034095634,0.000118596006,0.35015792],"study_design_scores_gemma":[0.13090718,0.0012359197,0.0014522647,0.6181777,0.03741901,0.0002459508,0.00012849133,0.0029176879,0.000009837252,0.20616162,0.0004994708,0.0008448384],"about_ca_topic_score_codex":0.000036412664,"about_ca_topic_score_gemma":0.000020325242,"teacher_disagreement_score":0.34931308,"about_ca_system_score_codex":0.000037457427,"about_ca_system_score_gemma":0.00063211244,"threshold_uncertainty_score":0.931434},"labels":[],"label_agreement":null},{"id":"W2624445525","doi":"10.1016/j.jclinepi.2017.06.003","title":"Graphic report of the results from propensity score method analyses","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"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-Société et Culture; Jewish General Hospital","keywords":"Propensity score matching; Statistics; Medicine; Computer science; Medical physics; Mathematics","score_opus":0.8981984549665861,"score_gpt":0.6914254145489367,"score_spread":0.20677304041764943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624445525","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":[0.7713411,0.00009362227,0.21531941,0.0100140255,0.0011201099,0.00024363495,0.000025202786,0.000027862301,0.0018150182],"genre_scores_gemma":[0.6371338,0.00018751316,0.36173943,0.00040569936,0.00042145627,0.0000013370669,0.0000010112135,0.000011733175,0.00009807732],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863395,0.0054048146,0.007411581,0.00031668038,0.000282919,0.0002444925],"domain_scores_gemma":[0.8930169,0.07620493,0.027355067,0.0023084802,0.00092894066,0.00018573074],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049155854,0.0001700011,0.0030372287,0.000065002445,0.00014356192,0.000009105475,0.001252941,0.00039708804,0.000019422821],"category_scores_gemma":[0.6426695,0.00008714458,0.0011145257,0.00007288212,0.000855386,0.00019120784,0.00036438144,0.0013065004,0.0000012187977],"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":[0.0013311765,0.00045690636,0.9238691,0.000050378236,0.00083534094,0.00041112216,0.00008165767,0.00006839066,0.0014590524,0.039690014,0.0152229285,0.016523937],"study_design_scores_gemma":[0.00040549325,0.00019902427,0.34864807,0.00019031663,0.00016096001,0.00015421599,0.000008193909,0.00006888537,0.001475221,0.6481234,0.0004993673,0.000066872504],"about_ca_topic_score_codex":0.00018884262,"about_ca_topic_score_gemma":0.00008841261,"teacher_disagreement_score":0.60843337,"about_ca_system_score_codex":0.000018146508,"about_ca_system_score_gemma":0.00021363387,"threshold_uncertainty_score":0.97909415},"labels":[],"label_agreement":null},{"id":"W2626910779","doi":"10.1111/bju.13930","title":"Critical appraisal of the application of propensity score methods in the urology literature","year":2017,"lang":"en","type":"article","venue":"British Journal of Urology","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Health Sciences Centre","funders":"","keywords":"Critical appraisal; Propensity score matching; Urology; Medicine; Psychology; Internal medicine; Alternative medicine; Pathology","score_opus":0.13348753793058846,"score_gpt":0.4717279809260477,"score_spread":0.3382404429954592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626910779","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":[0.5602758,0.001711328,0.4302472,0.005399066,0.0004573283,0.0005333081,0.000021645088,0.000017100405,0.0013372598],"genre_scores_gemma":[0.9500483,0.00007953674,0.049592666,0.00017627307,0.00008048358,0.000009038234,4.1429092e-7,0.000009831888,0.0000034529555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980714,0.0008561022,0.0006074002,0.0001177835,0.00018071102,0.000166657],"domain_scores_gemma":[0.99604934,0.0020368593,0.00091127434,0.00050073327,0.00047504308,0.000026753136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002268796,0.00008925966,0.00041857967,0.000055863162,0.00009677181,0.000032276745,0.001002854,0.00020185123,0.00000832094],"category_scores_gemma":[0.014020476,0.000060961702,0.000115116,0.000088457426,0.00074323104,0.00018877625,0.00015847904,0.0007921747,2.0587758e-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":[0.0005916019,0.0013038825,0.03346221,0.00044246297,0.00011957809,0.0005342404,0.0024752384,0.00003729502,0.04521474,0.71308666,0.0023376797,0.2003944],"study_design_scores_gemma":[0.0005385962,0.00061689544,0.13061689,0.00014748277,0.0001094865,0.008959935,0.000052792642,0.00013785026,0.004863754,0.8523928,0.0014478258,0.00011568579],"about_ca_topic_score_codex":0.000025307729,"about_ca_topic_score_gemma":0.000075001306,"teacher_disagreement_score":0.38977253,"about_ca_system_score_codex":0.000009626501,"about_ca_system_score_gemma":0.000058073852,"threshold_uncertainty_score":0.99428487},"labels":[],"label_agreement":null},{"id":"W2683857909","doi":"10.22237/jmasm/1209614460","title":"Confidence Intervals for the Squared Multiple Semipartial Correlation Coefficient","year":2008,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Advanced Causal Inference Techniques","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":"University of Manitoba","funders":"","keywords":"Mathematics; Confidence interval; Statistics; Correlation coefficient; Coverage probability; Mean squared error; CDF-based nonparametric confidence interval; Correlation; Robust confidence intervals; Fisher transformation; Linear regression; Correlation ratio; Population; Medicine","score_opus":0.2641471578532747,"score_gpt":0.49408629685120936,"score_spread":0.22993913899793467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2683857909","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":[0.00052300707,0.00009149179,0.99808556,0.0001206532,0.00022184053,0.0005995921,0.000038728587,0.000053514523,0.00026561745],"genre_scores_gemma":[0.41270986,0.000016913598,0.58704007,0.000066508255,0.00007890011,0.00004240833,0.0000014953844,0.00001911376,0.000024713538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794006,0.00026630447,0.0009359595,0.00017792439,0.00040998493,0.00026977042],"domain_scores_gemma":[0.97223544,0.026365258,0.0006542984,0.00025210905,0.0003704753,0.00012239914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024600506,0.00018337024,0.00048938446,0.00006754585,0.00018878558,0.000026819198,0.00030837298,0.000109395405,0.000059406353],"category_scores_gemma":[0.009819233,0.00012174208,0.0001187861,0.000096452284,0.0002613004,0.00008317961,0.000055994464,0.00041883858,0.00000234926],"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":[0.00077377446,0.00023247945,0.000027259686,0.00006778351,0.00009895034,0.000015718066,0.001554751,0.0026769007,0.023400104,0.83078074,0.0038419636,0.1365296],"study_design_scores_gemma":[0.00053943,0.00020130254,0.00009248124,0.000033551543,0.000088928275,0.00008312136,0.00007539301,0.25142196,0.012371014,0.7345299,0.00044371432,0.00011922369],"about_ca_topic_score_codex":0.0000018882799,"about_ca_topic_score_gemma":0.0000014643791,"teacher_disagreement_score":0.41218683,"about_ca_system_score_codex":0.00010247077,"about_ca_system_score_gemma":0.00009406028,"threshold_uncertainty_score":0.9985215},"labels":[],"label_agreement":null},{"id":"W2713091059","doi":"10.1093/ije/dyx023","title":"Assessing the impact of unmeasured confounding for binary outcomes using confounding functions","year":2017,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":32,"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":"Confounding; Causal inference; Econometrics; Observational study; Statistics; Inference; Instrumental variable; Odds; Information bias; Computer science; Selection bias; Mathematics; Logistic regression; Artificial intelligence","score_opus":0.593533639452308,"score_gpt":0.6345018749151049,"score_spread":0.04096823546279693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2713091059","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":[0.49278462,0.00005284829,0.5045115,0.0009901648,0.0011410521,0.00012842585,0.000017418875,0.000013498445,0.0003605247],"genre_scores_gemma":[0.92493993,0.000019772524,0.07456344,0.00007932155,0.00033074172,0.00000472123,0.0000024662766,0.000016931055,0.000042669533],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980164,0.00029743742,0.0011384259,0.00011825501,0.00020188394,0.00022756291],"domain_scores_gemma":[0.9841308,0.010725419,0.0036222704,0.00031493037,0.001148295,0.000058278296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0052306447,0.00015151635,0.0006411425,0.00019956866,0.00027954899,0.00007430003,0.0008274083,0.00010766484,0.000043625343],"category_scores_gemma":[0.048004173,0.00009258302,0.00048100032,0.000027880762,0.00034273052,0.0007266121,0.000108574095,0.00029305622,6.177134e-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":[0.0002964194,0.00021749052,0.651545,0.000042562915,0.0027155625,0.000030883264,0.0003375467,0.0036196823,0.051832736,0.27916154,0.0026196386,0.00758096],"study_design_scores_gemma":[0.001005492,0.00035740813,0.105909236,0.00044876736,0.00017254648,0.00045802185,0.0004173295,0.007994843,0.0009761463,0.88164973,0.00040949116,0.00020101151],"about_ca_topic_score_codex":0.00010881003,"about_ca_topic_score_gemma":0.0000057829575,"teacher_disagreement_score":0.60248816,"about_ca_system_score_codex":0.00033969694,"about_ca_system_score_gemma":0.00020376526,"threshold_uncertainty_score":0.9600149},"labels":[],"label_agreement":null},{"id":"W2726070247","doi":"10.1093/geroni/igx004.4107","title":"NONRANDOMIZED STUDIES: THE HAZARDOUS PRACTICE OF TESTING FOR BASELINE IMBALANCES","year":2017,"lang":"en","type":"article","venue":"Innovation in Aging","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; Jewish General Hospital","funders":"","keywords":"Observational study; Baseline (sea); Confounding; Medicine; False positive paradox; Psychological intervention; Strengthening the reporting of observational studies in epidemiology; Randomization; Randomized controlled trial; Medical physics; Computer science; Surgery; Nursing; Political science","score_opus":0.2968175987650567,"score_gpt":0.509430155691871,"score_spread":0.2126125569268143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726070247","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":[0.14487883,0.0002181545,0.8394803,0.007346851,0.0003524195,0.0017974607,0.000011100808,0.00020496808,0.005709936],"genre_scores_gemma":[0.65946066,0.0000123963555,0.3400714,0.00016717342,0.00006906707,0.00015688007,0.00000136595,0.000010447467,0.00005059929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989021,0.00006815519,0.00063949206,0.00012603238,0.00013614299,0.00012808575],"domain_scores_gemma":[0.987877,0.009294384,0.0012350125,0.0003926125,0.0011957207,0.000005231421],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0045795827,0.00008927704,0.00025914217,0.00010054852,0.00020956527,0.00004101225,0.00023742473,0.000029731393,0.0000020768741],"category_scores_gemma":[0.12152934,0.0000629053,0.000020208772,0.00026685875,0.0001075579,0.00038347833,0.00006830557,0.00012342067,4.2245662e-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":[0.0009309732,0.0003709444,0.016635777,0.0011143117,0.00027074694,0.000012206248,0.008675806,0.00021122381,0.052927,0.7955175,0.004239728,0.11909378],"study_design_scores_gemma":[0.004746003,0.0001269723,0.00037856115,0.0010278622,0.000057781595,0.000009487173,0.0042765355,0.0053718565,0.039238233,0.9426599,0.0018568091,0.00024997685],"about_ca_topic_score_codex":0.000021545207,"about_ca_topic_score_gemma":0.000009653925,"teacher_disagreement_score":0.51458186,"about_ca_system_score_codex":0.00004034474,"about_ca_system_score_gemma":0.000030529245,"threshold_uncertainty_score":0.8858704},"labels":[],"label_agreement":null},{"id":"W2729335696","doi":"10.48550/arxiv.1707.01473","title":"Machine-Learning Tests for Effects on Multiple Outcomes","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Booth University College","funders":"","keywords":"Intuition; Computer science; Machine learning; Randomized experiment; Inference; Artificial intelligence; Outcome (game theory); Data collection; Set (abstract data type); Data science; Psychology; Statistics; Mathematics","score_opus":0.2748012721513939,"score_gpt":0.32440054044851513,"score_spread":0.049599268297121246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2729335696","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":[0.48654172,0.000051868814,0.4997722,0.00013680955,0.0007417083,0.0032043767,0.00014534949,0.002261891,0.007144108],"genre_scores_gemma":[0.98296964,0.000073267234,0.011284742,0.000051940595,0.00007678977,0.000017171478,0.000041751446,0.00008541342,0.0053992597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983272,0.000117176445,0.00020917773,0.00084437267,0.000090790054,0.0004113078],"domain_scores_gemma":[0.99357533,0.0041942983,0.00058868364,0.0013476274,0.00016066358,0.00013339806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029209442,0.0004935603,0.000683658,0.00021688791,0.00033978646,0.000071662085,0.00094404136,0.00044974222,0.000015386488],"category_scores_gemma":[0.005401638,0.00050297956,0.0003602041,0.0000657588,0.00009657982,0.00015716992,0.0008012332,0.0009609989,0.00003309691],"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":[0.00044504652,0.00058244425,0.19115508,0.0030013684,0.000688975,0.0005684405,0.00037058772,0.019612318,0.00046311144,0.7761603,0.0018596802,0.0050926665],"study_design_scores_gemma":[0.0011144199,0.00028323685,0.0021060836,0.0006057587,0.00022875905,0.0000014141782,0.00002276135,0.03878415,0.002869917,0.9517873,0.0013932234,0.0008029641],"about_ca_topic_score_codex":0.00006483563,"about_ca_topic_score_gemma":0.0000968577,"teacher_disagreement_score":0.49642795,"about_ca_system_score_codex":0.00025393607,"about_ca_system_score_gemma":0.00006558439,"threshold_uncertainty_score":0.9997422},"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":"W2731112398","doi":"10.1016/j.jclinepi.2017.02.020","title":"Quasi-experimental study designs series—paper 1: introduction: two historical lineages","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":74,"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":"Causal inference; Counterfactual conditional; Computer science; Inference; Contrast (vision); Management science; Data science; Clinical study design; Operations research; Clinical trial; Medicine; Psychology; Econometrics; Counterfactual thinking; Artificial intelligence; Mathematics; Social psychology; Engineering","score_opus":0.6842402606492697,"score_gpt":0.6275217179570611,"score_spread":0.05671854269220855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731112398","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":[0.65934443,0.0009262021,0.25325584,0.07086098,0.012546332,0.0009848091,0.0000041149656,0.00027041734,0.0018068909],"genre_scores_gemma":[0.77272415,0.00021445498,0.21602917,0.0007068618,0.009203254,0.000016540218,5.5760205e-7,0.000039749873,0.0010652636],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898663,0.0039459574,0.0050914115,0.00041043627,0.00028631403,0.00039953922],"domain_scores_gemma":[0.9763878,0.015851112,0.0059143635,0.0010942206,0.00042820134,0.00032428672],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024652515,0.00027539328,0.0029778664,0.000092956456,0.0002817593,0.000025887206,0.00092736573,0.00032099776,0.00033227218],"category_scores_gemma":[0.18636869,0.00020124545,0.00060469256,0.00004686257,0.00046583812,0.00071791385,0.00024952102,0.0015388266,0.000019257744],"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":[0.0038731995,0.036865167,0.32504213,0.000072804694,0.0011698117,0.0007191029,0.00073901314,0.000059739803,0.0014481881,0.29082152,0.31987768,0.019311637],"study_design_scores_gemma":[0.0041020457,0.0431849,0.021361321,0.00008569825,0.00031310337,0.00085470336,0.00060697296,0.00008888919,0.0010994936,0.8470494,0.080623075,0.00063038047],"about_ca_topic_score_codex":0.000036312256,"about_ca_topic_score_gemma":0.000026302701,"teacher_disagreement_score":0.5562279,"about_ca_system_score_codex":0.00027375564,"about_ca_system_score_gemma":0.00013870538,"threshold_uncertainty_score":0.8544119},"labels":[],"label_agreement":null},{"id":"W2732843100","doi":"10.1136/bmjopen-2017-016018","title":"Methods, applications, interpretations and challenges of interrupted time series (ITS) data: protocol for a scoping review","year":2017,"lang":"en","type":"review","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":44,"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; St. Michael's Hospital; University of Toronto; McMaster University; Impact","funders":"","keywords":"Medicine; Data science; Psychological intervention; Protocol (science); Interrupted Time Series Analysis; Transparency (behavior); Interrupted time series; Intervention (counseling); Outcome (game theory); MEDLINE; Research design; Data collection; Computer science; Data mining; Alternative medicine; Pathology; Statistics","score_opus":0.8927701739897943,"score_gpt":0.7420679777621761,"score_spread":0.15070219622761816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732843100","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":[1.31895085e-11,0.5097192,0.04230443,0.00007834712,0.0000050804397,0.4461009,0.00014778238,0.000047255486,0.0015970223],"genre_scores_gemma":[5.2674094e-11,0.3756787,0.25510776,0.0000067516403,0.000015318381,0.3689421,0.00005728006,0.00002733608,0.00016474492],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736094,0.0004562534,0.001329985,0.00057186506,0.000117063326,0.00016388824],"domain_scores_gemma":[0.99313474,0.0014633852,0.0024436798,0.0026640866,0.00024198253,0.000052140527],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037287264,0.00035814467,0.0027217993,0.00009115869,0.00010839625,0.000120640434,0.0024794596,0.00017445562,0.000051748757],"category_scores_gemma":[0.004755562,0.00028102455,0.0001335463,0.0000766282,0.00010772517,0.00081207376,0.0026123573,0.00017711084,0.0000106187],"study_design_candidate":"systematic_review","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":[0.000005023586,0.000018158427,5.143841e-9,0.4178005,0.000055099346,1.5329016e-7,0.00001703598,7.7655926e-10,1.4553797e-7,0.01171657,0.00064745586,0.5697399],"study_design_scores_gemma":[0.00006287838,0.000045393554,5.450307e-9,0.46259958,0.00027326713,0.000014947842,0.0000057437856,0.0000035784744,0.00000447215,0.014796928,0.5220171,0.0001760701],"about_ca_topic_score_codex":0.000001820638,"about_ca_topic_score_gemma":0.000013711972,"teacher_disagreement_score":0.5695638,"about_ca_system_score_codex":0.00003440538,"about_ca_system_score_gemma":0.00046175037,"threshold_uncertainty_score":0.9999642},"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":"W2740759698","doi":"","title":"Deep IV: a flexible approach for counterfactual prediction","year":2017,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":154,"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":"","keywords":"Counterfactual thinking; Artificial intelligence; Computer science; Machine learning; Deep learning; Artificial neural network; Conditional independence; Function (biology); Outcome (game theory); Mathematics","score_opus":0.43680739955367165,"score_gpt":0.43826711998452905,"score_spread":0.001459720430857403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740759698","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":[0.12539057,0.000030200768,0.8701706,0.00046875174,0.00004256963,0.0012435042,0.000025114225,0.00018497468,0.0024436966],"genre_scores_gemma":[0.9340941,0.00010245975,0.06531249,0.000008662588,0.00008065506,0.000018252751,0.000012031565,0.000026225125,0.00034514713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985771,0.000117890966,0.00014268339,0.00028281298,0.0004970318,0.00038248333],"domain_scores_gemma":[0.99769884,0.00059393444,0.00016670403,0.0010491275,0.000410657,0.00008073487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013733417,0.00012276394,0.0002194891,0.00012325926,0.0009940716,0.000061710896,0.0011618559,0.00010958913,0.00005151984],"category_scores_gemma":[0.00063925644,0.000106449945,0.00009994367,0.00007052195,0.0007970849,0.0005840826,0.00045373297,0.00032315447,0.00001605453],"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":[0.0055159903,0.0032855025,0.010303453,0.0050634905,0.0012581452,0.000065026186,0.3450935,0.00058320863,0.024394918,0.4081173,0.12630199,0.070017494],"study_design_scores_gemma":[0.00466791,0.0022094878,0.008592997,0.0006087305,0.0002253877,0.00002500179,0.12694727,0.05316315,0.043655097,0.71323854,0.045726586,0.0009398413],"about_ca_topic_score_codex":0.000008707174,"about_ca_topic_score_gemma":0.0000028705717,"teacher_disagreement_score":0.8087035,"about_ca_system_score_codex":0.00015975491,"about_ca_system_score_gemma":0.000059224734,"threshold_uncertainty_score":0.7645695},"labels":[],"label_agreement":null},{"id":"W2742688241","doi":"10.3389/feduc.2017.00039","title":"Is Difference in Measurement Outcome between Groups Differential Responding, Bias or Disparity? A Methodology for Detecting Bias and Impact from an Attributional Stance","year":2017,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Advanced Causal Inference Techniques","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 British Columbia","funders":"","keywords":"Propensity score matching; Matching (statistics); Differential (mechanical device); Outcome (game theory); Confounding; Test (biology); Covariate; Psychology; Selection bias; Closing (real estate); Differential effects; Differential item functioning; Computer science; Econometrics; Cognitive psychology; Social psychology; Applied psychology; Statistics; Psychometrics; Mathematics; Engineering; Developmental psychology; Political science; Item response theory","score_opus":0.5655473824026596,"score_gpt":0.5239767990681791,"score_spread":0.04157058333448049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742688241","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":[0.5867121,0.00006912255,0.4120451,0.00016677358,0.00042289775,0.00044897493,0.00009327158,0.00003522342,0.0000064961487],"genre_scores_gemma":[0.75489473,0.000021930666,0.24458653,0.000026056025,0.00015652292,0.00020756702,0.000039122224,0.00002261782,0.000044943343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99779725,0.00041942886,0.0006040966,0.0005034708,0.00029390168,0.00038186897],"domain_scores_gemma":[0.9975303,0.0010114375,0.0005841339,0.0006000066,0.00016380842,0.00011034596],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019795976,0.00025961574,0.00059237744,0.0003873127,0.00024050112,0.00013101587,0.000393751,0.00021301927,0.000023738172],"category_scores_gemma":[0.0104921665,0.00022393705,0.00006668187,0.00013461933,0.00012591848,0.00047757613,0.00009740433,0.00031333163,3.1899432e-7],"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":[0.00028430086,0.0001570293,0.9623867,0.000060726747,0.00003148694,5.018712e-7,0.0012172662,4.997922e-7,0.0008642455,0.0017282857,0.0002581387,0.03301081],"study_design_scores_gemma":[0.00045387406,0.00012651132,0.65431327,0.00016139676,0.00003559459,7.1751197e-7,0.0004943576,0.00033141763,0.0023488381,0.34150022,0.000032736993,0.00020107752],"about_ca_topic_score_codex":0.00059372035,"about_ca_topic_score_gemma":0.0013193283,"teacher_disagreement_score":0.33977193,"about_ca_system_score_codex":0.0008860241,"about_ca_system_score_gemma":0.00023264132,"threshold_uncertainty_score":0.99784285},"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":"W2745537878","doi":"","title":"Power Analysis for a Proposed Group Randomized Control Trial (GRCT) on the Road to Mental Readiness (R2MP) Program","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Intraclass correlation; Mental health; Data collection; Statistical power; Sample size determination; Randomized controlled trial; Sample (material); Population; Psychology; Test (biology); Statistics; Control (management); Applied psychology; Medicine; Computer science; Mathematics; Environmental health; Psychiatry; Psychometrics; Artificial intelligence","score_opus":0.06832250445262944,"score_gpt":0.40222322890821416,"score_spread":0.3339007244555847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745537878","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":[0.073309265,0.000003235699,0.89211136,0.0023125277,0.00013949999,0.02296273,0.000019997198,0.0009856913,0.008155667],"genre_scores_gemma":[0.9261526,0.0000010348705,0.06549407,0.0007394741,0.00009796693,0.0064981915,0.00001626784,0.000039299004,0.00096110656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9979083,0.00040947352,0.0006076445,0.0003657188,0.00034928296,0.00035959837],"domain_scores_gemma":[0.99588495,0.0029857918,0.00024269559,0.0006179762,0.00016630892,0.000102288046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026113524,0.0002812449,0.0010767045,0.00017357725,0.00012807205,0.0000926271,0.00033050906,0.00010615975,0.0002612097],"category_scores_gemma":[0.0037210034,0.0001464155,0.0005683562,0.00040812534,0.00010709726,0.00008736085,0.00004197257,0.00012529969,0.000016477921],"study_design_candidate":"randomized_trial","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":[0.40564537,0.0008835258,0.000007926176,0.000018725335,0.0011109328,5.507961e-7,0.00035380202,0.0000062011413,0.0006618437,0.58158714,0.0033887888,0.0063351723],"study_design_scores_gemma":[0.7171053,0.003397512,0.000009751627,0.000040456165,0.0011922908,9.05785e-7,0.00016983434,0.009931301,0.0053274683,0.25861943,0.0037009693,0.0005047684],"about_ca_topic_score_codex":0.000024164217,"about_ca_topic_score_gemma":0.000053059506,"teacher_disagreement_score":0.85284334,"about_ca_system_score_codex":0.000075732,"about_ca_system_score_gemma":0.000017134193,"threshold_uncertainty_score":0.59706515},"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":"W2752219857","doi":"10.1007/s10729-017-9415-5","title":"Population-level intervention and information collection in dynamic healthcare policy","year":2017,"lang":"en","type":"article","venue":"Health Care Management Science","topic":"Advanced Causal Inference Techniques","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":"Western University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Centers for Disease Control and Prevention","keywords":"Health informatics; Health administration; Health care; Markov decision process; Population; Actuarial science; Health policy; Computer science; Intervention (counseling); Medicine; Econometrics; Partially observable Markov decision process; Markov process; Public health; Mathematical optimization; Mathematics; Statistics; Economics; Environmental health; Nursing","score_opus":0.09169459837060301,"score_gpt":0.48229282230643256,"score_spread":0.39059822393582955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752219857","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":[0.6222847,0.00044778435,0.30312863,0.042663258,0.0014105123,0.008780713,0.000068617395,0.0011250948,0.020090643],"genre_scores_gemma":[0.969612,0.00020398608,0.029608874,0.00039573247,0.00000917118,0.00007604817,0.00001269441,0.00000584579,0.0000756399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99870455,0.000039968367,0.00038762286,0.00022208702,0.0003360094,0.0003097693],"domain_scores_gemma":[0.99893713,0.000022358765,0.00041022786,0.00043518387,0.00010685184,0.000088243825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009269478,0.00010197807,0.00014842913,0.0006848981,0.0008792409,0.00019908493,0.00028886413,0.00003428709,0.000002484189],"category_scores_gemma":[0.00039261684,0.00010618428,0.000018262548,0.00041035665,0.00013392589,0.0023570247,0.0002508822,0.000104720486,0.0000031993254],"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":[0.000016310238,0.00002829503,0.012563773,0.0015282664,0.000002462218,0.0000013277769,0.0025730263,0.00000791108,0.0000034082962,0.6008629,0.00014008902,0.38227218],"study_design_scores_gemma":[0.0004750686,0.00015558476,0.8485035,0.00048735627,0.0000031285604,0.0000035833789,0.0024190028,0.0020171965,0.000020404039,0.14536554,0.0003726368,0.00017700756],"about_ca_topic_score_codex":0.003553798,"about_ca_topic_score_gemma":0.0040620756,"teacher_disagreement_score":0.8359397,"about_ca_system_score_codex":0.0013050815,"about_ca_system_score_gemma":0.00008581302,"threshold_uncertainty_score":0.6762499},"labels":[],"label_agreement":null},{"id":"W275349574","doi":"10.1007/978-1-4614-7428-9_3","title":"Statistical Reinforcement Learning","year":2013,"lang":"en","type":"book-chapter","venue":"Statistics in the health sciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Sequence (biology); Machine learning; Reinforcement; Engineering","score_opus":0.22600644500450368,"score_gpt":0.46972514238981633,"score_spread":0.24371869738531265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W275349574","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":[0.0000028926179,0.00016927188,0.57570535,0.00052549294,0.0001609335,0.00096838496,0.00010475393,0.00011551672,0.4222474],"genre_scores_gemma":[0.0035886622,0.0016078751,0.7999181,0.0017295748,0.00016443356,0.00015623553,0.00010365921,0.00007754377,0.19265391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967949,0.0001545123,0.0009235309,0.00044367925,0.0010687312,0.000614665],"domain_scores_gemma":[0.99487084,0.0038435159,0.0006814955,0.0003770291,0.00011200053,0.00011511587],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029450047,0.00034099104,0.00052541867,0.00020390519,0.0004516656,0.00011648966,0.0007444819,0.00014656966,0.0014282546],"category_scores_gemma":[0.0012010457,0.0002344931,0.000031939973,0.00009086296,0.00096234604,0.00010146392,0.00013669877,0.0010649825,0.0001855055],"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":[0.0000026293096,0.00000876783,0.0000057478255,0.00016246058,0.0000039268725,0.000010762217,0.00055638823,0.000044174547,1.6444938e-7,0.9560194,0.033884715,0.009300883],"study_design_scores_gemma":[0.000062275074,0.00063693983,0.00001273758,0.00029804974,0.000008921369,0.000010395206,0.00017200374,0.0011701997,9.678351e-7,0.96718615,0.030197416,0.00024391845],"about_ca_topic_score_codex":0.00015205343,"about_ca_topic_score_gemma":0.00013585424,"teacher_disagreement_score":0.2295935,"about_ca_system_score_codex":0.00024029755,"about_ca_system_score_gemma":0.0004946066,"threshold_uncertainty_score":0.9994846},"labels":[],"label_agreement":null},{"id":"W2760941800","doi":"10.1002/pds.4325","title":"Comparison of the ability of double‐robust estimators to correct bias in propensity score matching analysis. <scp>A M</scp>onte <scp>C</scp>arlo simulation study","year":2017,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Propensity score matching; Covariate; Confounding; Estimator; Statistics; Matching (statistics); Logistic regression; Econometrics; Observational study; Residual; Mathematics; Average treatment effect; Medicine; Algorithm","score_opus":0.39422076301799786,"score_gpt":0.5000812465376048,"score_spread":0.10586048351960692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760941800","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":[0.9378129,0.00007227751,0.059464004,0.00014252837,0.00017294523,0.0017551851,0.000029369776,0.000090974485,0.00045978412],"genre_scores_gemma":[0.99353117,0.00002209055,0.006181067,0.00010070758,0.000030002664,0.00005410005,0.000007133969,0.00002342028,0.00005033824],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99491686,0.0020227414,0.0016896174,0.0006411564,0.00027539954,0.00045423466],"domain_scores_gemma":[0.9779405,0.018622383,0.0018884207,0.001126186,0.00028142982,0.00014106113],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009412443,0.00038028965,0.001882565,0.00023920117,0.00042131287,0.000020446372,0.0007471359,0.00017326277,0.000007091343],"category_scores_gemma":[0.023376418,0.00027704725,0.0002311378,0.00044241323,0.00047317432,0.00032608426,0.00068192946,0.000713593,0.0000019321735],"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":[0.00009216906,0.0005128333,0.89441234,0.0001386079,0.00020187178,0.0000018397665,0.004854703,0.0972332,0.0008396426,0.0009586822,0.00032416984,0.0004299451],"study_design_scores_gemma":[0.0011093926,0.000102027116,0.93369967,0.00013035542,0.0005996154,0.000001519673,0.0012706195,0.039899662,0.0058283177,0.017207636,0.00005889872,0.00009227506],"about_ca_topic_score_codex":0.0011103518,"about_ca_topic_score_gemma":0.0011582756,"teacher_disagreement_score":0.05733354,"about_ca_system_score_codex":0.00010121363,"about_ca_system_score_gemma":0.00006420211,"threshold_uncertainty_score":0.9999682},"labels":[],"label_agreement":null},{"id":"W2766207844","doi":"10.1136/bmj.j4587","title":"Handling time varying confounding in observational research","year":2017,"lang":"en","type":"review","venue":"BMJ","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":346,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Confounding; Observational study; Weighting; Marginal structural model; Statistics; Econometrics; Parametric statistics; Inverse probability weighting; Estimation; Causal inference; Medicine; Computer science; Mathematics; Propensity score matching; Engineering","score_opus":0.8963818942939966,"score_gpt":0.6776851293144192,"score_spread":0.21869676497957746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766207844","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":[0.0000024443445,0.96291584,0.0017476127,0.000071974784,0.00012198564,0.0019385584,0.000016095779,0.0001968692,0.0329886],"genre_scores_gemma":[0.00000279723,0.9457101,0.04813024,0.0000084350795,0.00042048373,0.0005476066,0.00005586049,0.00007727404,0.005047185],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974645,0.00035781236,0.0008457888,0.00036164842,0.0005358509,0.0004344214],"domain_scores_gemma":[0.9944647,0.003920513,0.0005552822,0.0008088139,0.00019535367,0.000055358243],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005131851,0.00026439497,0.0012802689,0.0004151467,0.00022668405,0.000145736,0.00068728917,0.00035541726,0.00015290205],"category_scores_gemma":[0.009013413,0.00023641098,0.00016216931,0.00022599299,0.000107727625,0.00023880402,0.00031593742,0.0010418742,0.00027104307],"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":[0.0000038393387,0.00004592575,0.000009756267,0.014362096,0.00005695825,0.000096670745,0.000094583425,5.691294e-7,0.000004834371,0.11544466,0.008779071,0.86110103],"study_design_scores_gemma":[0.00005485341,0.000012998702,8.0043714e-7,0.03599876,0.000032628606,0.000019587873,0.000003328673,0.000045382014,0.0000026114249,0.16997203,0.7936146,0.00024239544],"about_ca_topic_score_codex":0.00001747862,"about_ca_topic_score_gemma":0.000007682411,"teacher_disagreement_score":0.8608586,"about_ca_system_score_codex":0.00041534583,"about_ca_system_score_gemma":0.00055177236,"threshold_uncertainty_score":0.9993341},"labels":[],"label_agreement":null},{"id":"W2766219675","doi":"10.1002/sim.7527","title":"Collaborative targeted learning using regression shrinkage","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Université de Montréal","keywords":"Covariate; Causal inference; Propensity score matching; Estimator; Statistics; Regression; Regression analysis; Inference; Computer science; Stepwise regression; Mean squared error; Model selection; Outcome (game theory); Econometrics; Mathematics; Artificial intelligence","score_opus":0.11734741745116913,"score_gpt":0.4830962113690352,"score_spread":0.3657487939178661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766219675","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":[0.034637213,0.00014522833,0.95516336,0.00026169128,0.0003031296,0.00040988057,0.000048919446,0.00017529096,0.008855278],"genre_scores_gemma":[0.41122296,0.0001229522,0.58793604,0.00003440642,0.000115003975,0.0000128425545,0.000018556777,0.000031407628,0.0005058172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987165,0.00011713724,0.0003732885,0.00022679541,0.00031392393,0.00025237116],"domain_scores_gemma":[0.9980329,0.00071699923,0.00047520633,0.00047169032,0.00023209862,0.00007105491],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006804601,0.00017738824,0.00039801883,0.00012079759,0.00032625988,0.000026586886,0.0002700661,0.00009004935,0.00021222775],"category_scores_gemma":[0.014082884,0.00013832765,0.000010240207,0.00011377334,0.00039689126,0.00014488178,0.000118848366,0.00045476216,0.0000040534733],"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":[0.00013271089,0.0001317737,0.01668538,0.00036287206,0.000052783616,0.00084948906,0.007268868,0.0001223152,0.049524385,0.8863316,0.014836272,0.02370156],"study_design_scores_gemma":[0.0009297723,0.00025462924,0.0022800965,0.001278945,0.00003641454,0.0000074887525,0.0012931516,0.006878219,0.0049367305,0.98079675,0.0010364199,0.0002713956],"about_ca_topic_score_codex":0.00008229046,"about_ca_topic_score_gemma":0.00008219129,"teacher_disagreement_score":0.37658575,"about_ca_system_score_codex":0.00011970517,"about_ca_system_score_gemma":0.000060165523,"threshold_uncertainty_score":0.9942219},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2766434410","doi":"10.1002/sim.7522","title":"Weighted estimation for confounded binary outcomes subject to misclassification","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Covariate; Estimator; Statistics; Logistic regression; Confounding; Computer science; Estimation; Inverse probability; Econometrics; Inverse probability weighting; Consistency (knowledge bases); Identification (biology); Mathematics; Artificial intelligence; Posterior probability","score_opus":0.19441443568362424,"score_gpt":0.500652691376323,"score_spread":0.3062382556926987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766434410","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":[0.009126054,0.000007642056,0.98479486,0.002928382,0.00024169683,0.0009816721,0.00010567234,0.00011968516,0.0016943433],"genre_scores_gemma":[0.27810165,0.000011705452,0.72071,0.00016040241,0.00005220443,0.00020258677,0.00008735901,0.000024880525,0.00064919976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882066,0.00003361659,0.00045256317,0.00023201758,0.0002446101,0.00021651875],"domain_scores_gemma":[0.9971729,0.0015693638,0.0003128475,0.00064956845,0.00021770642,0.000077649944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00066054787,0.00016159439,0.00037540332,0.00016114692,0.00017957644,0.000029070008,0.00030148454,0.00007503601,0.000063129395],"category_scores_gemma":[0.012009269,0.00013210725,0.000017171473,0.000063858606,0.00018197832,0.000111768895,0.000043184707,0.00012344276,0.000010215016],"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":[0.000060272992,0.00006172657,0.0017863736,0.0001557388,0.00001687499,0.000010519982,0.00057047757,0.000004536176,0.0024047054,0.9578194,0.015994104,0.021115271],"study_design_scores_gemma":[0.0008515369,0.0003061075,0.016018009,0.00020324407,0.00003610973,0.0000016530705,0.0001101054,0.010771705,0.0010747315,0.9697453,0.0007157731,0.00016575168],"about_ca_topic_score_codex":0.00006618059,"about_ca_topic_score_gemma":0.00017028273,"teacher_disagreement_score":0.26897562,"about_ca_system_score_codex":0.00014255312,"about_ca_system_score_gemma":0.00004525783,"threshold_uncertainty_score":0.996313},"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":"W2773073055","doi":"10.22374/1710-6222.24.3.6","title":"Development and validation of an index score to adjust for healthy user bias in observational studies","year":2017,"lang":"en","type":"article","venue":"Journal of Population Therapeutics and Clinical Pharmacology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Observational study; Logistic regression; Index (typography); Medicine; Confounding; Cohort; Cohort study; Statistic; Statistics; Vaccination; Internal medicine; Computer science; Mathematics; Immunology","score_opus":0.8034101812282828,"score_gpt":0.641222978353865,"score_spread":0.1621872028744178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773073055","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":[0.99241006,0.000080884514,0.005288585,0.0016781475,0.00025618385,0.00027606313,0.0000029238845,0.0000048673755,0.0000023059943],"genre_scores_gemma":[0.9294018,0.00026313757,0.06939227,0.00078359497,0.000131791,0.000008973944,0.0000025336997,0.000008325332,0.0000075788384],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985854,0.00010541027,0.0009948307,0.000103624174,0.00011767251,0.00009303303],"domain_scores_gemma":[0.99760664,0.0008499175,0.0010501556,0.00007949848,0.00034697194,0.00006679503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017115697,0.00008006809,0.00035761466,0.000093669776,0.00009403978,0.000014542483,0.00010444777,0.000087130415,0.0000038354005],"category_scores_gemma":[0.0005810989,0.00006558883,0.000032450043,0.000031393156,0.00006944051,0.00022625196,0.000043868844,0.00014350358,5.5784657e-8],"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":[0.0018680599,0.0007453201,0.8593945,0.00022206194,0.00037281707,0.000003682693,0.0013251086,0.00014292514,0.0021162045,0.02192761,0.0002016578,0.111680046],"study_design_scores_gemma":[0.0024853775,0.0012556086,0.8297891,0.00010496519,0.00012242112,0.000006209104,0.00023515943,0.0008889812,0.0028382132,0.16018651,0.0019439466,0.0001435294],"about_ca_topic_score_codex":0.00000397027,"about_ca_topic_score_gemma":0.000063364714,"teacher_disagreement_score":0.1382589,"about_ca_system_score_codex":0.00004125759,"about_ca_system_score_gemma":0.000054233264,"threshold_uncertainty_score":0.26746348},"labels":[],"label_agreement":null},{"id":"W2778295401","doi":"10.1177/0098858817723659","title":"Statistics, Adjusted Statistics, and Maladjusted Statistics","year":2017,"lang":"en","type":"article","venue":"American Journal of Law & Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":72,"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 Canada","funders":"","keywords":"Mistake; Statistics; The Imaginary; Statistical inference; Psychology; Econometrics; Economics; Law; Mathematics; Political science","score_opus":0.10561203037843124,"score_gpt":0.4254545307045736,"score_spread":0.31984250032614236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778295401","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":[0.011991411,0.00018830999,0.98331195,0.0011424938,0.0003827321,0.00022491532,0.0006317428,0.00006284465,0.0020636187],"genre_scores_gemma":[0.36152014,0.00046486166,0.6369737,0.00040975987,0.00030757982,0.0000030891256,0.000016157,0.000052548992,0.0002521825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99757737,0.00014608749,0.0010475862,0.00021614923,0.00063908845,0.0003737487],"domain_scores_gemma":[0.99366045,0.0016628073,0.0026770027,0.0006289655,0.000990467,0.00038033148],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00080379104,0.0003008889,0.0010498569,0.00012462029,0.0002709739,0.000058774072,0.0005051068,0.000055164695,0.00024763582],"category_scores_gemma":[0.004938366,0.0002320589,0.000030321306,0.00006771872,0.0031581544,0.00026358938,0.000088293935,0.0005208268,0.000004553822],"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":[0.00016931498,0.000087964865,0.0015764773,0.000130444,0.000168845,0.000573194,0.00091879145,0.0000011763124,0.00075844,0.8629379,0.034238618,0.09843879],"study_design_scores_gemma":[0.0034320375,0.0069825123,0.013250926,0.0013308012,0.000996563,0.0010395726,0.0021903566,0.00045493655,0.0009381063,0.95638365,0.01221322,0.00078730984],"about_ca_topic_score_codex":0.0005811583,"about_ca_topic_score_gemma":0.00026669365,"teacher_disagreement_score":0.34952873,"about_ca_system_score_codex":0.000085244086,"about_ca_system_score_gemma":0.000106990075,"threshold_uncertainty_score":0.9995547},"labels":[],"label_agreement":null},{"id":"W2785275695","doi":"10.1016/j.cjca.2018.01.013","title":"Accounting for Selection Bias in Studies of Acute Cardiac Events","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Censoring (clinical trials); Selection bias; Statistics; Confidence interval; Dyslipidemia; Demography; Internal medicine; Disease; Mathematics","score_opus":0.22038827112810347,"score_gpt":0.43670359222566657,"score_spread":0.2163153210975631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785275695","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":[0.9436952,0.00038961935,0.05328564,0.0002042429,0.0009940153,0.0003196906,0.000040111416,0.000014217585,0.0010572915],"genre_scores_gemma":[0.9854945,0.000066445384,0.013753857,0.00002534716,0.00060649303,0.000009471093,7.203936e-7,0.000014273523,0.000028869154],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990302,0.000106880645,0.0004560274,0.000084804284,0.00006893447,0.00025317742],"domain_scores_gemma":[0.9982699,0.00037770628,0.00036125808,0.0000958145,0.00080969045,0.00008558626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010248743,0.00009298555,0.0005956468,0.00034938884,0.00004971167,0.0000035911473,0.00013504596,0.00010201995,0.0000027500832],"category_scores_gemma":[0.0016225994,0.00008353572,0.00014707354,0.00016396325,0.00014680572,0.00011713829,0.000011069054,0.00014414787,6.6501656e-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":[0.00042856613,0.00001730754,0.75243896,0.00050774455,0.007111284,0.000098624536,0.006486323,0.00038520547,0.027708394,0.0744064,0.09797675,0.032434456],"study_design_scores_gemma":[0.0011607234,0.0021741185,0.025296401,0.0005505544,0.00066255964,0.00031491372,0.0016277909,0.000036393638,0.031247335,0.9030521,0.033410437,0.00046665344],"about_ca_topic_score_codex":0.00012123099,"about_ca_topic_score_gemma":0.0017041337,"teacher_disagreement_score":0.8286457,"about_ca_system_score_codex":0.00023739607,"about_ca_system_score_gemma":0.00040974148,"threshold_uncertainty_score":0.34064877},"labels":[],"label_agreement":null},{"id":"W2789124538","doi":"10.1016/j.rdc.2018.01.001","title":"Alternative Design and Analytical Techniques for Longitudinal Rheumatology Studies","year":2018,"lang":"en","type":"review","venue":"Rheumatic Disease Clinics of North America","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Toronto; University of Manitoba","funders":"","keywords":"Medicine; Covariate; Longitudinal data; Accrual; Missing data; Longitudinal study; Clinical study design; Research design; Data collection; Cohort study; Statistical power; Cohort; Statistics; Medical physics; Clinical trial; Data mining; Internal medicine; Computer science","score_opus":0.3730737574498898,"score_gpt":0.5254522191495213,"score_spread":0.15237846169963154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789124538","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":[0.000039352544,0.6748477,0.32172132,0.000016414011,0.00010034836,0.0027389415,0.00026770635,0.00025108323,0.000017102764],"genre_scores_gemma":[0.000052115065,0.78668535,0.21183221,0.000016929544,0.000035160403,0.0011661783,0.00007065383,0.00010871505,0.000032670603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950633,0.0004744497,0.0026222076,0.0009218569,0.00038054315,0.00053762284],"domain_scores_gemma":[0.97900045,0.015964067,0.002897912,0.0010514562,0.00073149294,0.00035463957],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009338628,0.00085498794,0.005081672,0.000381391,0.00012413405,0.000029501938,0.0006919704,0.00022011541,0.000019744266],"category_scores_gemma":[0.014748733,0.0006751518,0.0007640672,0.00038401393,0.0017883097,0.00016215707,0.00041397565,0.00035896164,0.000011531778],"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":[0.00008603258,0.0003089079,0.00013917744,0.053990927,0.0015637001,0.000011819035,0.000095227566,6.9704515e-7,9.997722e-10,0.006278122,0.0029890412,0.93453634],"study_design_scores_gemma":[0.0006159862,0.0027558305,0.00002086348,0.08997283,0.010803308,0.00005888474,0.0001124745,0.003876767,8.518121e-7,0.66841954,0.22097842,0.0023842566],"about_ca_topic_score_codex":0.0000050680183,"about_ca_topic_score_gemma":0.0000034401987,"teacher_disagreement_score":0.9321521,"about_ca_system_score_codex":0.00012463216,"about_ca_system_score_gemma":0.00052025233,"threshold_uncertainty_score":0.99956995},"labels":[],"label_agreement":null},{"id":"W2789415476","doi":"10.1007/978-981-10-8743-1_17","title":"Open Research and Observational Study for 21st Century Learning","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in educational technology","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":"Athabasca University","funders":"","keywords":"Notice; Formative assessment; Computer science; Observational study; Context (archaeology); Data science; Mathematics education; Psychology; Political science; Mathematics; Statistics","score_opus":0.4145621311745445,"score_gpt":0.5172044997028824,"score_spread":0.10264236852833791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789415476","genre_codex":"other","genre_gemma":"methods","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":[0.06875006,0.009686795,0.12027929,0.14620036,0.0036544541,0.06836033,0.00068567554,0.0039350516,0.578448],"genre_scores_gemma":[0.32295525,0.00067318924,0.5831763,0.0004054713,0.0016482893,0.005335303,0.00063131197,0.00046929685,0.0847056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798816,0.000048614562,0.00048825485,0.00075609883,0.0003400413,0.00037884834],"domain_scores_gemma":[0.99408346,0.004178275,0.00026502673,0.00053267943,0.00089594704,0.000044623528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009892413,0.00032464793,0.00049385085,0.00094381004,0.0002610389,0.00007517676,0.00094493927,0.0008684468,0.0005848728],"category_scores_gemma":[0.006417492,0.0003239311,0.000035154815,0.00023641168,0.00060250185,0.00011982897,0.0008082534,0.0015578459,0.000017934071],"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":[0.000032164135,0.00021995309,0.0015548093,0.00006062689,0.000044616347,0.0000012620663,0.0003615579,0.0000016895816,0.00006173922,0.9902059,0.0007418291,0.006713879],"study_design_scores_gemma":[0.0002461867,0.00069332164,0.00014500791,0.00019236769,0.000016375823,0.000013529827,0.00016940238,0.0000075947605,0.0001682256,0.95226866,0.045803074,0.00027625632],"about_ca_topic_score_codex":0.000013326189,"about_ca_topic_score_gemma":0.00029839447,"teacher_disagreement_score":0.49374238,"about_ca_system_score_codex":0.00035389743,"about_ca_system_score_gemma":0.00047221035,"threshold_uncertainty_score":0.99992126},"labels":[],"label_agreement":null},{"id":"W2791760629","doi":"10.1093/bjps/axx015","title":"The Confounding Question of Confounding Causes in Randomized Trials","year":2017,"lang":"en","type":"article","venue":"The British Journal for the Philosophy of Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":60,"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":"Canadian Institutes of Health Research; University of Johannesburg; W. Garfield Weston Foundation; Università degli Studi di Genova; University of Toronto; King's College London","keywords":"Confounding; Causal inference; Randomized controlled trial; Ideal (ethics); Randomization; Inference; Balance (ability); Psychology; Medicine; Statistics; Computer science; Mathematics; Philosophy; Epistemology; Internal medicine; Artificial intelligence","score_opus":0.30365044426729587,"score_gpt":0.4922772733783582,"score_spread":0.18862682911106232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791760629","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":[0.69991195,0.0076047173,0.23290518,0.024935715,0.0066442345,0.010928192,0.00009431988,0.00016436802,0.01681134],"genre_scores_gemma":[0.9941514,0.0023005912,0.0031733639,0.000027846827,0.00021449756,0.000051514933,1.1609832e-7,0.00001177356,0.00006888811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971934,0.00055168336,0.0011787766,0.00014212665,0.0006230974,0.00031093383],"domain_scores_gemma":[0.9789589,0.01736954,0.0025674358,0.0005199648,0.00053475646,0.00004941285],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.055319346,0.00012307147,0.00079638505,0.00009124715,0.0051118005,0.00089573814,0.0021806634,0.00004039209,0.000004506482],"category_scores_gemma":[0.07926231,0.00006400896,0.00028858546,0.00016135906,0.007184381,0.0006700579,0.00016106504,0.00034928223,4.4089248e-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":[0.0020483537,0.000032832566,0.000021140446,0.000037896156,0.000056647328,0.000003934448,0.000515139,0.000027304817,0.0073613524,0.97648394,0.000073515854,0.013337919],"study_design_scores_gemma":[0.0063298815,0.000052457966,0.000085587504,0.0010567054,0.00008209474,0.00022730631,0.00027857602,0.00041522793,0.011239737,0.9800929,0.00005857315,0.00008095938],"about_ca_topic_score_codex":0.0002387626,"about_ca_topic_score_gemma":0.00008787976,"teacher_disagreement_score":0.29423946,"about_ca_system_score_codex":0.00007772028,"about_ca_system_score_gemma":0.00015905013,"threshold_uncertainty_score":0.9961834},"labels":[],"label_agreement":null},{"id":"W2791924225","doi":"10.1002/sim.7615","title":"Assessing the performance of the generalized propensity score for estimating the effect of quantitative or continuous exposures on binary outcomes","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":85,"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 Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Confounding; Mathematics; Ordinary least squares; Medicine","score_opus":0.215693518484249,"score_gpt":0.4913806844402001,"score_spread":0.2756871659559511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791924225","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":[0.8471548,0.000021146489,0.15088344,0.00029613377,0.00021314235,0.001265712,0.000034650908,0.00002246565,0.000108538334],"genre_scores_gemma":[0.7409655,0.0000051489533,0.25872532,0.00010096638,0.000048774447,0.00007636656,0.0000030391104,0.000017385053,0.000057512243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984256,0.00034904666,0.00055570115,0.00014553833,0.00034602208,0.00017808944],"domain_scores_gemma":[0.98858196,0.010085502,0.00059881806,0.0004434255,0.00027484866,0.000015434618],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021940824,0.00017102456,0.00055051007,0.000046419413,0.00018597778,0.000009728106,0.00035846664,0.000042703417,0.000014956632],"category_scores_gemma":[0.014820239,0.00005881996,0.000032979362,0.00019334696,0.0011623912,0.00006186778,0.000085301435,0.00021251156,3.0369324e-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":[0.0034606275,0.0003759703,0.38690004,0.0059718615,0.0004779983,0.000023744888,0.024422543,0.00082843174,0.045712028,0.4650874,0.018922761,0.047816586],"study_design_scores_gemma":[0.0077026365,0.03643276,0.17109728,0.0101885265,0.00084748573,0.000027952816,0.0029249575,0.15874153,0.28071278,0.33045095,0.000115859635,0.00075727777],"about_ca_topic_score_codex":0.00003983119,"about_ca_topic_score_gemma":0.00006123195,"teacher_disagreement_score":0.23500076,"about_ca_system_score_codex":0.000033705688,"about_ca_system_score_gemma":0.000048769256,"threshold_uncertainty_score":0.99347836},"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":"W2792491629","doi":"10.1007/s12561-018-9213-8","title":"Estimation of Causal Effect Measures in the Presence of Measurement Error in Confounders","year":2018,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"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","keywords":"Confounding; Estimator; Statistics; Context (archaeology); Odds ratio; Econometrics; Biostatistics; Estimation; Causal inference; Mathematics; Medicine; Epidemiology; Engineering; Geography; Internal medicine","score_opus":0.21513680053283413,"score_gpt":0.4531936732303652,"score_spread":0.23805687269753106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792491629","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":[0.5394073,0.000058826852,0.45754632,0.000108449305,0.00018538976,0.0010305817,0.000049756323,0.00002785628,0.0015854967],"genre_scores_gemma":[0.9233811,0.000008428652,0.07655532,0.000011847717,0.0000055560954,0.000030262789,8.0262015e-7,0.000004118643,0.000002597038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798477,0.00029722595,0.00050654355,0.0001832596,0.000824117,0.00020408344],"domain_scores_gemma":[0.99787056,0.0014902856,0.00023919788,0.00022715436,0.00015590423,0.000016918015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039351997,0.00010932136,0.00023893436,0.00021905208,0.000029405934,0.000014310413,0.00040269035,0.000047193455,0.00000914722],"category_scores_gemma":[0.0072292415,0.00007499477,0.000013343803,0.0006100002,0.001043704,0.00012734243,0.000037348436,0.0001193779,7.261515e-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":[0.0001340309,0.00050946395,0.042947646,0.0006546474,0.000011290938,0.000015182778,0.016798014,0.0006103955,0.025347324,0.88736016,0.00065016944,0.02496165],"study_design_scores_gemma":[0.0003682535,0.0009021262,0.024523905,0.0005288508,0.000010485511,0.0000021048418,0.0016522717,0.017761545,0.0603406,0.8937307,0.000008562374,0.00017059612],"about_ca_topic_score_codex":0.00047762124,"about_ca_topic_score_gemma":0.007380168,"teacher_disagreement_score":0.38397375,"about_ca_system_score_codex":0.00008667788,"about_ca_system_score_gemma":0.00011959341,"threshold_uncertainty_score":0.86546},"labels":[],"label_agreement":null},{"id":"W2793831746","doi":"10.1002/pds.4440","title":"Assumptions made when preparing drug exposure data for analysis have an impact on results: <scp>A</scp>n unreported step in pharmacoepidemiology studies","year":2018,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":66,"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":"Medical Research Council; National Institute for Health and Care Research; Canadian Institutes of Health Research; Manchester Biomedical Research Centre; Versus Arthritis; Arthritis Research UK","keywords":"Pharmacoepidemiology; Medicine; Comparability; Observational study; Hazard ratio; Data mining; Confidence interval; Medical prescription; Drug; Consistency (knowledge bases); Hazard; Prescription drug; Statistics; Computer science; Pharmacology; Internal medicine; Mathematics","score_opus":0.3673463826858171,"score_gpt":0.5450930492236101,"score_spread":0.17774666653779303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793831746","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":[0.71015286,0.0038103396,0.2686715,0.004686298,0.00084781426,0.003984747,0.0037332915,0.0014949471,0.0026181696],"genre_scores_gemma":[0.9107015,0.0028064456,0.08140614,0.0019304733,0.00063726207,0.00037792578,0.0013979422,0.00008120234,0.000661103],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99021775,0.004079607,0.002545333,0.0017960897,0.00019507989,0.0011661181],"domain_scores_gemma":[0.9486557,0.04724628,0.0014614403,0.0018778461,0.00038630498,0.00037241165],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020016009,0.0007235496,0.0022515706,0.0006622584,0.0004605539,0.000019528317,0.0009241204,0.00032367045,0.000035350942],"category_scores_gemma":[0.03825361,0.0005777191,0.00028944635,0.00047538732,0.00078984123,0.00076890696,0.0006583591,0.0008995609,0.000008429465],"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":[0.0046239323,0.0016524201,0.26102385,0.0005458711,0.012337299,0.00007329854,0.014978219,0.0046497257,0.0031831632,0.01983783,0.66229385,0.014800509],"study_design_scores_gemma":[0.010975983,0.0016636346,0.052463613,0.000491364,0.008070523,0.00011535249,0.0069907457,0.3120841,0.005941196,0.5522815,0.047197316,0.0017246926],"about_ca_topic_score_codex":0.00041787987,"about_ca_topic_score_gemma":0.0018614561,"teacher_disagreement_score":0.61509657,"about_ca_system_score_codex":0.0002635096,"about_ca_system_score_gemma":0.00009801383,"threshold_uncertainty_score":0.9996674},"labels":[],"label_agreement":null},{"id":"W2795791984","doi":"10.1016/j.rdc.2018.01.002","title":"Propensity Score Methods for Bias Reduction in Observational Studies of Treatment Effect","year":2018,"lang":"en","type":"review","venue":"Rheumatic Disease Clinics of North America","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University Health Network; University of Toronto; Toronto General Hospital; Hospital for Sick Children; Public Health Ontario; Toronto Western Hospital; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Observational study; Propensity score matching; Reduction (mathematics); Statistics; Medicine; Econometrics; Mathematics","score_opus":0.7393426480676626,"score_gpt":0.599232833209911,"score_spread":0.14010981485775154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795791984","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":[0.006304866,0.96842587,0.017350757,0.000012113909,0.0002570291,0.007096022,0.00042308157,0.00011396622,0.000016286915],"genre_scores_gemma":[0.000069170914,0.7955375,0.20254043,0.000003821725,0.000034621517,0.0014558361,0.00026091302,0.00005959231,0.000038160208],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955232,0.00093397294,0.0025179526,0.0005183379,0.00024073306,0.00026580447],"domain_scores_gemma":[0.9834367,0.011461788,0.0035170582,0.00089252123,0.000565287,0.0001266717],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014569961,0.00057753257,0.004492113,0.0002670473,0.000050362734,0.000007888222,0.00033582604,0.00012484696,0.0000098188675],"category_scores_gemma":[0.018379891,0.00039766924,0.00092842226,0.00054685323,0.00053589686,0.0001253323,0.00013119927,0.00015560447,0.0000032416451],"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":[0.0000898869,0.0004322605,0.0006461604,0.059558257,0.000590095,8.1425696e-7,0.00010268218,0.000003865743,4.7801677e-8,0.0003191989,0.0001644924,0.93809223],"study_design_scores_gemma":[0.0034813338,0.018719088,0.0022128883,0.3239091,0.024059767,0.000016851622,0.00019135678,0.0013027777,0.000033029035,0.3517338,0.2704966,0.0038433808],"about_ca_topic_score_codex":0.000012598434,"about_ca_topic_score_gemma":0.00001157699,"teacher_disagreement_score":0.93424886,"about_ca_system_score_codex":0.00037084598,"about_ca_system_score_gemma":0.0008488005,"threshold_uncertainty_score":0.99984753},"labels":[],"label_agreement":null},{"id":"W2800148206","doi":"10.1093/fampra/cmy005","title":"Daring to draw causal claims from non-randomized studies of primary care interventions","year":2018,"lang":"en","type":"article","venue":"Family Practice","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":132,"is_retracted":false,"has_abstract":false,"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":"Medicine; Primary care; Psychological intervention; Randomized controlled trial; Primary health care; MEDLINE; Family medicine; Nursing; Environmental health; Internal medicine","score_opus":0.2966887458985632,"score_gpt":0.5001152720724805,"score_spread":0.20342652617391732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800148206","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":[0.34790158,0.0021553594,0.56801945,0.0004563125,0.00092931575,0.0022217073,0.000109790664,0.0006094247,0.07759705],"genre_scores_gemma":[0.47641128,0.0001777839,0.52198887,0.0005992862,0.0001953902,0.00018121251,0.000018825924,0.00004366311,0.00038371718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811584,0.00030563786,0.0007091903,0.00031722157,0.00031963625,0.00023249972],"domain_scores_gemma":[0.9923132,0.0054668514,0.0005247282,0.00058582943,0.0010356106,0.000073783405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009316225,0.00021376261,0.0007993893,0.0001252341,0.00012900906,0.000032697906,0.00028181486,0.00009544355,0.00002688277],"category_scores_gemma":[0.007807446,0.00018952666,0.00023900259,0.00022411984,0.0003751624,0.00063676614,0.00039336545,0.0002551596,0.00006659108],"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":[0.06849815,0.0030440744,0.0004762403,0.006895249,0.0097136665,0.00022147488,0.24818341,0.000048540933,0.24344952,0.29080352,0.08192043,0.046745725],"study_design_scores_gemma":[0.05645491,0.00263874,0.0010352528,0.0092291925,0.005024371,0.000026794276,0.11899816,0.00012446169,0.0956331,0.68597275,0.022807257,0.0020549784],"about_ca_topic_score_codex":0.00033215916,"about_ca_topic_score_gemma":0.0001322652,"teacher_disagreement_score":0.39516926,"about_ca_system_score_codex":0.00020567454,"about_ca_system_score_gemma":0.000079503145,"threshold_uncertainty_score":0.93468064},"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":"W2801485033","doi":"10.3386/w22892","title":"Bounds on Treatment Effects in Regression Discontinuity Designs with a Manipulated Running Variable","year":2016,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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","funders":"National Science Foundation","keywords":"Regression discontinuity design; Variable (mathematics); Discontinuity (linguistics); Regression; Statistics; Mathematics; Computer science; Mathematical analysis","score_opus":0.6752177241422713,"score_gpt":0.6085671321910054,"score_spread":0.06665059195126588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801485033","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":[0.03024572,0.00032441877,0.0032059823,0.0002992061,0.00029907285,0.004783787,0.00013349162,0.00022768189,0.96048063],"genre_scores_gemma":[0.94071466,0.00070596917,0.02375418,0.000008784157,0.00048330135,0.0013480203,0.00029488336,0.00019671342,0.032493517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966454,0.00025691412,0.0007029667,0.00063217554,0.0012515145,0.0005110368],"domain_scores_gemma":[0.9938019,0.004245907,0.0005095187,0.0005062945,0.00084224605,0.00009417034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036384678,0.00037816432,0.0008590484,0.0010115807,0.00009961985,0.000051217754,0.00035017505,0.00045535865,0.0001570261],"category_scores_gemma":[0.0018655944,0.00023839939,0.00009581078,0.00020998104,0.00019842085,0.0001997133,0.00011477015,0.0006125132,0.00002665776],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000700986,0.0006550501,0.001957788,0.0007178512,0.00034348542,0.000077914636,0.00015631816,0.00014490384,0.0015069065,0.976393,0.011775063,0.0055707633],"study_design_scores_gemma":[0.0009826004,0.0011024553,0.00028547243,0.0042229705,0.000020882937,0.00001779335,0.000012890071,0.00012522725,0.0055866227,0.9860234,0.0013330448,0.00028659162],"about_ca_topic_score_codex":0.00084664393,"about_ca_topic_score_gemma":0.0003173862,"teacher_disagreement_score":0.9279871,"about_ca_system_score_codex":0.008384121,"about_ca_system_score_gemma":0.0035679692,"threshold_uncertainty_score":0.99542254},"labels":[],"label_agreement":null},{"id":"W2802284801","doi":"10.1002/sim.7628","title":"Targeted maximum likelihood estimation for a binary treatment: A tutorial","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":134,"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","funders":"Instituto de Salud Carlos III; Canadian Institutes of Health Research; Cancer Research UK","keywords":"Computer science; Outcome (game theory); Nonparametric statistics; Contrast (vision); Propensity score matching; Code (set theory); Parametric statistics; Binary number; Estimation; Specification; Statistics; Machine learning; Artificial intelligence; Programming language; Mathematics","score_opus":0.08412398744132396,"score_gpt":0.43726232599602827,"score_spread":0.35313833855470433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802284801","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":[0.0032846145,0.00004301249,0.9936074,0.00025056483,0.0006474024,0.0008557629,0.00021809136,0.00019996708,0.00089318835],"genre_scores_gemma":[0.06632053,0.00003650641,0.9320358,0.000078183184,0.0008941125,0.0002510759,0.00018681452,0.00004011645,0.00015687045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876165,0.000044402,0.00044001365,0.00023992622,0.00020867428,0.00030532407],"domain_scores_gemma":[0.9981365,0.001135008,0.00015869693,0.0002782453,0.00021758268,0.00007392601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037924206,0.00019326626,0.0003663975,0.0001661189,0.00007145414,0.0000076830775,0.00011311107,0.00009363888,0.00018988756],"category_scores_gemma":[0.0034552873,0.00015356664,0.000019771338,0.00019767015,0.0002476707,0.00007209341,0.000022202412,0.00009219329,0.0000120741515],"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":[0.00055065675,0.0004527057,0.0001593507,0.00028915956,0.00007478885,0.00006172775,0.0048281723,0.0000048881484,0.007323329,0.771125,0.062431876,0.15269832],"study_design_scores_gemma":[0.0018123838,0.0031541423,0.000066221626,0.00015550107,0.00006208035,0.0000041644325,0.00010921532,0.01039346,0.0022401768,0.9793828,0.002469064,0.00015079985],"about_ca_topic_score_codex":0.0000599916,"about_ca_topic_score_gemma":0.00012141805,"teacher_disagreement_score":0.20825778,"about_ca_system_score_codex":0.00023088453,"about_ca_system_score_gemma":0.00007590844,"threshold_uncertainty_score":0.62622654},"labels":[],"label_agreement":null},{"id":"W2802314382","doi":"10.1177/0049124118769087","title":"Regression-based Adjustment for Time-varying Confounders","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"","keywords":"Marginal structural model; Econometrics; Estimator; Inverse probability; Regression; Average treatment effect; Statistics; Propensity score matching; Matching (statistics); Regression analysis; Computer science; Conditional expectation; Observational study; Outcome (game theory); Confounding; Estimation; Mathematics; Economics; Bayesian probability","score_opus":0.6894510924192692,"score_gpt":0.6691776798557132,"score_spread":0.02027341256355597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802314382","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":[0.0045693624,0.00016351555,0.9798696,0.0013019772,0.000120046934,0.0014715707,0.0000105119425,0.000532043,0.011961352],"genre_scores_gemma":[0.031138452,0.000021047843,0.9663354,0.00036224254,0.00041331432,0.0007049002,0.000009226991,0.000038133116,0.0009772744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947033,0.0029645322,0.000390741,0.00055025064,0.0004974925,0.0008936751],"domain_scores_gemma":[0.9737692,0.02452296,0.00011739842,0.0005431314,0.0008627854,0.00018450714],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011814191,0.00022109419,0.00046134493,0.00014593122,0.00056135457,0.00003757104,0.0005285004,0.00043286395,0.0011196815],"category_scores_gemma":[0.017558932,0.00014713235,0.00017021562,0.0002951738,0.0018173736,0.00007463795,0.00023751312,0.0007416842,0.000097134085],"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":[0.0005713783,0.0004225386,0.00007951002,0.00021529866,0.000091709866,0.000008418156,0.0009364871,0.0000017881388,0.16948475,0.56532615,0.02650374,0.23635821],"study_design_scores_gemma":[0.00035614692,0.001115901,0.00002712683,0.00008066962,0.000011006682,0.0000010587625,0.00038557602,0.0021944756,0.055565476,0.93608606,0.003984477,0.00019202329],"about_ca_topic_score_codex":0.000005698633,"about_ca_topic_score_gemma":5.8692063e-7,"teacher_disagreement_score":0.37075987,"about_ca_system_score_codex":0.000305177,"about_ca_system_score_gemma":0.00016900866,"threshold_uncertainty_score":0.9997934},"labels":[],"label_agreement":null},{"id":"W280240657","doi":"","title":"Commentary on Reed & Walton","year":2007,"lang":"en","type":"article","venue":"","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":"University of Windsor","funders":"","keywords":"History","score_opus":0.1483875117826421,"score_gpt":0.44081826809666524,"score_spread":0.29243075631402315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W280240657","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":[0.067371786,0.0000070594233,0.5463699,0.004128015,0.00010639775,0.0003702238,0.0000024511296,0.0014968821,0.38014725],"genre_scores_gemma":[0.7056577,0.000006989453,0.2771116,0.0146310255,0.0001180764,0.000008657284,0.000005433481,0.000029389823,0.0024311072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940604,0.000011662509,0.00016538578,0.00010696051,0.00012916498,0.00018077705],"domain_scores_gemma":[0.99922884,0.00039601498,0.000040376068,0.00026172076,0.000024256267,0.000048789538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033948335,0.00008561461,0.00009946162,0.000052031413,0.0000340511,0.000005856112,0.00010128755,0.00004615629,0.00031177967],"category_scores_gemma":[0.00009462737,0.000068431735,0.000026665524,0.00007099236,0.00002693534,0.000059920392,0.000034440207,0.000114176015,0.00005118166],"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":[0.0000365807,0.00015075733,0.00027093297,0.000013468633,0.000009094265,0.000016433985,0.00010279247,2.9976368e-7,0.004349696,0.70783395,0.2734917,0.013724292],"study_design_scores_gemma":[0.00014701695,0.00019145847,0.00014098457,0.00002914349,0.0000053121403,0.000002571395,0.000100570884,0.000015820853,0.23361596,0.7434401,0.022172078,0.00013898652],"about_ca_topic_score_codex":0.000021542799,"about_ca_topic_score_gemma":0.000054512857,"teacher_disagreement_score":0.63828593,"about_ca_system_score_codex":0.00006679276,"about_ca_system_score_gemma":0.0000029578673,"threshold_uncertainty_score":0.34137687},"labels":[],"label_agreement":null},{"id":"W2803815837","doi":"10.1007/s10985-018-9430-y","title":"The effect of omitted covariates in marginal and partially conditional recurrent event analyses","year":2018,"lang":"en","type":"article","venue":"Lifetime Data Analysis","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":"University of Waterloo","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Marginal model; Econometrics; Covariate; Censoring (clinical trials); Statistics; Causal inference; Conditional probability distribution; Event (particle physics); Multiplicative function; Inference; Marginal structural model; Confounding; Semiparametric regression; Mathematics; Computer science; Regression analysis; Nonparametric statistics; Artificial intelligence","score_opus":0.12705361535163198,"score_gpt":0.4741786875827103,"score_spread":0.34712507223107836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803815837","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":[0.5339058,0.00087592745,0.46029985,0.00082361116,0.00009160454,0.00093059096,0.0024274504,0.0002073746,0.00043777854],"genre_scores_gemma":[0.9878514,0.00009091255,0.011007632,0.00001712248,0.000057409317,0.000030259944,0.00089892413,0.000010342353,0.000036036272],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825764,0.00036074885,0.00052638847,0.00034709234,0.00029991425,0.00020819037],"domain_scores_gemma":[0.9965875,0.0020025666,0.00029321364,0.0009612173,0.000099238896,0.000056236055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014472189,0.00016638484,0.00049387844,0.0002398289,0.00010188353,0.00004017398,0.0004989242,0.000059816986,0.0002180972],"category_scores_gemma":[0.0015057501,0.0001080607,0.00008895931,0.00088210474,0.00031779887,0.00018361871,0.00032310185,0.00012445262,0.00000894417],"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":[0.004534765,0.0015188237,0.67022014,0.0008528221,0.030882103,0.000095529176,0.0013096126,0.00092202815,0.022971436,0.1644729,0.051443268,0.050776567],"study_design_scores_gemma":[0.0035186603,0.0037010394,0.19182856,0.0004730018,0.020387717,0.000021327469,0.00028757626,0.30782947,0.090047434,0.3735875,0.0066287364,0.0016889871],"about_ca_topic_score_codex":0.000112434675,"about_ca_topic_score_gemma":0.0007369372,"teacher_disagreement_score":0.4783916,"about_ca_system_score_codex":0.000027179818,"about_ca_system_score_gemma":0.000027374632,"threshold_uncertainty_score":0.44065875},"labels":[],"label_agreement":null},{"id":"W2804738343","doi":"10.1515/jci-2016-0029","title":"A Kernel-Based Metric for Balance Assessment","year":2018,"lang":"en","type":"article","venue":"RePEc: Research Papers in Economics","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":"University of Waterloo","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Kernel (algebra); Covariate; Causal inference; Metric (unit); Mathematics; Statistics; Matching (statistics); Balance (ability); Econometrics; Psychology","score_opus":0.1431727040585479,"score_gpt":0.47568054090603085,"score_spread":0.332507836847483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804738343","genre_codex":"other","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":[0.34177092,0.000086840315,0.18301705,0.001665271,0.00064293534,0.0069750347,0.00016580262,0.0010788972,0.46459725],"genre_scores_gemma":[0.77592695,0.00015480783,0.22192934,0.00012757,0.00016378971,0.00063928124,0.000008023647,0.00005690737,0.0009933332],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981153,0.000117736796,0.0004234249,0.00046863855,0.00020001248,0.0006749116],"domain_scores_gemma":[0.99634206,0.0024604525,0.00012374095,0.0007020801,0.00025167587,0.00012000465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021038812,0.00016991145,0.00032760174,0.0004425632,0.00014102724,0.00005592571,0.00044179047,0.00014093569,0.00011508499],"category_scores_gemma":[0.0021831684,0.00017107475,0.00008772898,0.00031361528,0.00031681152,0.00013648432,0.00012351047,0.00036548913,0.000009125017],"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":[0.00047759028,0.0013001953,0.019092778,0.000632814,0.00015496899,0.000028777584,0.00035794664,0.0003849142,0.00714618,0.33754826,0.0030744062,0.62980115],"study_design_scores_gemma":[0.0029109225,0.002135499,0.0037572482,0.0003201524,0.000020165007,0.000008978773,0.0004935649,0.11238024,0.036430057,0.75310856,0.08740533,0.0010293031],"about_ca_topic_score_codex":0.0000071362488,"about_ca_topic_score_gemma":0.000074847885,"teacher_disagreement_score":0.62877184,"about_ca_system_score_codex":0.0008504025,"about_ca_system_score_gemma":0.0003218557,"threshold_uncertainty_score":0.6976226},"labels":[],"label_agreement":null},{"id":"W2805084035","doi":"10.1007/s10985-018-9434-7","title":"New approaches for censored longitudinal data in joint modelling of longitudinal and survival data, with application to HIV vaccine studies","year":2018,"lang":"en","type":"review","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"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 British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Bill and Melinda Gates Foundation","keywords":"Censoring (clinical trials); Proportional hazards model; Survival analysis; Longitudinal data; Human immunodeficiency virus (HIV); Statistics; Longitudinal study; Econometrics; Event data; Computer science; Medicine; Immunology; Covariate; Mathematics; Data mining","score_opus":0.5447526708032592,"score_gpt":0.46424108354286475,"score_spread":0.08051158726039442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805084035","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":[0.0000036031429,0.32908922,0.6598668,0.000047565925,0.0000098316805,0.0012229254,0.009694809,0.0000570655,0.000008179521],"genre_scores_gemma":[0.000034535562,0.4684706,0.49301308,0.0000026758282,0.00016169866,0.000111425215,0.03808874,0.000064406,0.00005283092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99473864,0.00017447295,0.0016671881,0.0024787176,0.00050622254,0.00043477432],"domain_scores_gemma":[0.9872429,0.0011442362,0.0012047105,0.010037449,0.0001978407,0.00017288489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025822858,0.0007141553,0.004280349,0.000858486,0.00008498586,0.00007438095,0.003639852,0.00022482839,0.000014267074],"category_scores_gemma":[0.0009319131,0.000544951,0.00013530941,0.0018688401,0.000104633174,0.0007929017,0.0048534973,0.00029664073,0.0000059490517],"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":[0.0007422461,0.0014233382,0.0034835385,0.09730958,0.061065596,0.0000348455,0.0007086735,0.0030715703,0.0000017152322,0.018147618,0.049032815,0.76497847],"study_design_scores_gemma":[0.0016189931,0.0005820494,0.00010381083,0.019223675,0.13795978,0.00004252868,0.0005663578,0.54132354,0.000013539976,0.020002857,0.2745245,0.0040383195],"about_ca_topic_score_codex":0.0003011184,"about_ca_topic_score_gemma":0.0020258932,"teacher_disagreement_score":0.76094013,"about_ca_system_score_codex":0.00009190981,"about_ca_system_score_gemma":0.0001874134,"threshold_uncertainty_score":0.9997002},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"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":"W2806520546","doi":"10.1002/bimj.201700322","title":"Reward ignorant modeling of dynamic treatment regimes","year":2018,"lang":"en","type":"article","venue":"Biometrical Journal","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":"McGill University; University of Waterloo","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Personalized medicine; Outcome (game theory); Causal inference; Inference; Computer science; Covariate; Precision medicine; Variety (cybernetics); Identification (biology); Observational study; Machine learning; Data science; Risk analysis (engineering); Data mining; Artificial intelligence; Econometrics; Medicine; Bioinformatics; Statistics; Mathematics","score_opus":0.32878468985498016,"score_gpt":0.4667132777993857,"score_spread":0.13792858794440555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806520546","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":[0.26877755,0.0004059781,0.72825736,0.00019692647,0.00016658304,0.00015444751,0.000008560047,0.0001374944,0.0018950821],"genre_scores_gemma":[0.8107076,0.00025640734,0.18872082,0.000013926474,0.00012970204,0.0000033126792,6.607053e-7,0.000018562618,0.0001489811],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986645,0.00005987923,0.0005073077,0.00015321575,0.0003493965,0.00026568543],"domain_scores_gemma":[0.9987615,0.00025867944,0.0002566266,0.00025151827,0.0003279188,0.00014378088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036995386,0.00015096298,0.00033752416,0.0009545927,0.00009253006,0.000026175536,0.00021725493,0.00010020002,0.00006247729],"category_scores_gemma":[0.00081592804,0.000104962775,0.00014299159,0.0012961887,0.00011861741,0.00012391686,0.000046947636,0.00014095471,0.000014813916],"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":[0.00072719326,0.0034686804,0.0010750829,0.00017475638,0.0008932305,0.00028250733,0.001974831,0.00003888231,0.14577873,0.07554569,0.005032659,0.76500773],"study_design_scores_gemma":[0.0013234568,0.004778571,0.00015117225,0.00026432858,0.00016802878,0.0005525076,0.00029543598,0.03658842,0.03279003,0.9207314,0.0018462748,0.000510376],"about_ca_topic_score_codex":0.0000106706475,"about_ca_topic_score_gemma":0.0000018213269,"teacher_disagreement_score":0.8451857,"about_ca_system_score_codex":0.0003032992,"about_ca_system_score_gemma":0.00006780647,"threshold_uncertainty_score":0.42802578},"labels":[],"label_agreement":null},{"id":"W2809710353","doi":"10.1111/1475-6773.12993","title":"Matching and Regression to the Mean in Difference‐in‐Differences Analysis","year":2018,"lang":"en","type":"article","venue":"Health Services Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":258,"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; National Institute on Aging; National Institutes of Health","keywords":"Covariate; Statistics; Matching (statistics); Estimator; Average treatment effect; Regression toward the mean; Regression analysis; Difference in differences; Propensity score matching; Mathematics; Correlation; Regression; Econometrics; Outcome (game theory); Linear regression","score_opus":0.2801946559073915,"score_gpt":0.5611277229491156,"score_spread":0.2809330670417241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809710353","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":[0.99361813,0.00021724745,0.0019226269,0.0029251764,0.0000245713,0.00071206636,0.000005161656,0.00006707666,0.000507926],"genre_scores_gemma":[0.99141777,0.0003371233,0.0074201394,0.0004844488,0.00006396363,0.00012473878,0.0000027275307,0.00001569542,0.00013339284],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99682105,0.00079600606,0.0004694088,0.00045211823,0.0007050698,0.00075637543],"domain_scores_gemma":[0.9977547,0.0011382294,0.00013420146,0.0005892147,0.00018526356,0.00019839642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036984128,0.00015955945,0.0004286778,0.00095168967,0.00032284373,0.00009592628,0.00057975994,0.000090246474,0.00006211845],"category_scores_gemma":[0.00008180007,0.00009749101,0.00002816289,0.0025965245,0.00013380013,0.0001236308,0.00045027558,0.0005789522,0.000018224591],"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":[0.00043326043,0.0005475301,0.45752835,0.0030395885,0.0001177292,0.000036699977,0.31905124,0.000013957563,0.0013744162,0.116008036,0.0003132026,0.10153599],"study_design_scores_gemma":[0.00024466455,0.00048404917,0.43007976,0.0015375022,0.0000102717695,0.0000024384549,0.019251376,0.0028986642,0.00043320522,0.54461044,0.00021488043,0.00023272856],"about_ca_topic_score_codex":0.011090653,"about_ca_topic_score_gemma":0.19483243,"teacher_disagreement_score":0.42860243,"about_ca_system_score_codex":0.00017108207,"about_ca_system_score_gemma":0.000090852576,"threshold_uncertainty_score":0.9954946},"labels":[],"label_agreement":null},{"id":"W2809826847","doi":"10.1080/13645579.2018.1488449","title":"Natural experiment methodology for research: a review of how different methods can support real-world research","year":2018,"lang":"en","type":"review","venue":"International Journal of Social Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":335,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Public Health Agency of Canada","keywords":"Randomized experiment; Research design; Randomized controlled trial; Natural experiment; Natural (archaeology); Intervention (counseling); Management science; Psychological intervention; Computer science; Risk analysis (engineering); Psychology; Sociology; Engineering; Medicine; Social science; Mathematics; Statistics","score_opus":0.967881105314908,"score_gpt":0.8051552063693992,"score_spread":0.16272589894550882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809826847","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":[0.0000087214285,0.92266935,0.06362435,0.0054965788,0.0026581187,0.0037249732,0.000204309,0.000049588878,0.0015640139],"genre_scores_gemma":[0.0000045118363,0.5702764,0.4248542,0.00004365169,0.0022407547,0.00066443434,0.000044750755,0.00012120029,0.0017501131],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8331965,0.15126374,0.0046666306,0.0012491778,0.0071724155,0.002451516],"domain_scores_gemma":[0.77572757,0.19067138,0.0032030945,0.00091690995,0.029056642,0.0004244125],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26533318,0.000741149,0.006401347,0.006479979,0.0004944086,0.0001385376,0.0056077577,0.0010546233,0.0006229974],"category_scores_gemma":[0.22647308,0.0005581453,0.002137033,0.0021644474,0.0039841207,0.00025627032,0.0023936187,0.007838514,0.000007852007],"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":[0.00051291,0.0003721368,6.494667e-7,0.034273673,0.0020094458,0.0001251629,0.0017235436,1.065723e-8,0.0007309207,0.27597138,0.11470113,0.569579],"study_design_scores_gemma":[0.0003331226,0.0012906226,9.399966e-7,0.022641359,0.00022569738,0.00013892436,0.00074928993,7.3286134e-7,0.0023969738,0.358943,0.6129946,0.00028473284],"about_ca_topic_score_codex":0.00014636756,"about_ca_topic_score_gemma":0.00018528527,"teacher_disagreement_score":0.5692943,"about_ca_system_score_codex":0.00339235,"about_ca_system_score_gemma":0.0044858083,"threshold_uncertainty_score":0.99977237},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2811159429","doi":"10.1108/s0731-905320190000039003","title":"Wild Bootstrap Randomization Inference for Few Treated Clusters","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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; Queen's University","funders":"","keywords":"Estimator; Inference; Cluster (spacecraft); Variance (accounting); Randomization; Statistics; Mathematics; Algorithm; Computer science; Artificial intelligence; Randomized controlled trial; Medicine","score_opus":0.16679452841082418,"score_gpt":0.39838990841661104,"score_spread":0.23159538000578686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811159429","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009693685,0.000033259235,0.49583697,0.000063466665,0.000085697066,0.0022617471,0.00005904443,0.00066544325,0.50098467],"genre_scores_gemma":[0.0024863146,0.00025654715,0.060750924,0.00024118247,0.00010762586,0.00015921726,0.00028906084,0.00020273273,0.9355064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983111,0.000018095761,0.00064855895,0.00047755303,0.00025146085,0.00029322875],"domain_scores_gemma":[0.99704134,0.0014421038,0.00050104765,0.0006412265,0.00029533976,0.00007891819],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023451053,0.0005380887,0.0008986532,0.00020914593,0.00005865914,0.00005145514,0.00027901225,0.0006495362,0.0008252165],"category_scores_gemma":[0.00036191195,0.0004588175,0.0002704201,0.000030097266,0.00008519414,0.00019673294,0.00007256809,0.0002939231,0.000090998365],"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":[0.00023928411,0.000016809016,0.000003949563,0.00025209974,0.00009666623,0.0000015035217,0.00003400962,0.0000108938675,0.000060065144,0.9861871,0.009574865,0.003522772],"study_design_scores_gemma":[0.002744458,0.00023098197,6.693221e-7,0.00060061837,0.00023692481,0.0000038629346,0.000008561743,0.0006267626,0.0012869246,0.9556957,0.037860755,0.00070382096],"about_ca_topic_score_codex":0.0000079428055,"about_ca_topic_score_gemma":0.00004544359,"teacher_disagreement_score":0.43508604,"about_ca_system_score_codex":0.00015211919,"about_ca_system_score_gemma":0.00011755071,"threshold_uncertainty_score":0.9997864},"labels":[],"label_agreement":null},{"id":"W2855200104","doi":"10.1136/bmjebm-2018-110972","title":"‘Depletion of the susceptibles’ taught through a story, a table and basic arithmetic","year":2018,"lang":"en","type":"letter","venue":"BMJ evidence-based medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"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":"Phrase; Arithmetic; Table (database); Psychology; Statistics; Computer science; Natural language processing; Mathematics; Data mining","score_opus":0.22595200651833938,"score_gpt":0.4243785418092606,"score_spread":0.19842653529092122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2855200104","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":[0.0014916816,0.0036351627,0.06693821,0.9218978,0.00088837766,0.0036899184,0.00006057312,0.0003867279,0.0010115537],"genre_scores_gemma":[0.0134111615,0.0022761251,0.14332668,0.80982095,0.017700333,0.0016964495,0.0001552734,0.00055454246,0.011058461],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956594,0.00069767394,0.0009647865,0.0007135736,0.0013984048,0.0005661416],"domain_scores_gemma":[0.99141824,0.0047840676,0.0013293632,0.0017403663,0.0006493857,0.00007857469],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022455496,0.00062247575,0.0012502141,0.00025182473,0.00017567522,0.000022306023,0.0007671597,0.0007838411,0.0005944971],"category_scores_gemma":[0.010686773,0.00039230715,0.00015685175,0.0006573657,0.0019134827,0.0003090438,0.00018829943,0.0018290598,0.000012117687],"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":[0.000045521625,0.000030220506,0.0001951014,0.0024408526,0.00004402883,0.00005014249,0.00027029437,6.9208227e-7,0.0013063778,0.0012940608,0.9938762,0.00044646108],"study_design_scores_gemma":[0.0014769841,0.0021004046,0.00018005868,0.057147834,0.0010264975,0.0001366508,0.00022322031,0.0001232521,0.011447509,0.2506336,0.6744613,0.0010427306],"about_ca_topic_score_codex":0.0002332983,"about_ca_topic_score_gemma":0.000057711084,"teacher_disagreement_score":0.31941497,"about_ca_system_score_codex":0.00027191226,"about_ca_system_score_gemma":0.0005506938,"threshold_uncertainty_score":0.9998529},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2888204156","doi":"10.1016/j.jclinepi.2018.08.012","title":"Don't forget about the “R” in cmRCT: reply to Groenwold and van Smeden","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; Jewish General Hospital","funders":"","keywords":"Randomization; Clinical trial; Medicine; Randomized controlled trial; Cohort; Physical therapy; Psychology; Internal medicine","score_opus":0.5280353855673746,"score_gpt":0.5820072379877822,"score_spread":0.053971852420407584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888204156","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":[0.007840662,0.0003584901,0.023231508,0.9654577,0.0013240064,0.0005484612,0.000015826914,0.000052720996,0.001170642],"genre_scores_gemma":[0.00097331713,0.0012345549,0.100953974,0.88482827,0.010864774,0.000026878863,0.0000044527983,0.000077648416,0.001036136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98398703,0.006093337,0.0081614405,0.0005897047,0.00036301994,0.0008054484],"domain_scores_gemma":[0.87965333,0.1125214,0.006095117,0.0009856961,0.0004808806,0.00026355954],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04036906,0.0004606791,0.004634917,0.00030093858,0.000063733285,0.000020432042,0.001197415,0.0018207886,0.00009218304],"category_scores_gemma":[0.26896647,0.00026963148,0.00069884886,0.00017919969,0.00077967823,0.00015472808,0.00039601958,0.007471483,0.000019048006],"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":[0.0001148694,0.00004079585,0.010164313,0.000084747444,0.00009804412,0.00023058036,0.000071366434,0.000001445446,0.0000015043764,0.00392711,0.98092055,0.0043446915],"study_design_scores_gemma":[0.00023751921,0.00080337585,0.0030920652,0.000387709,0.000060806888,0.00020562985,0.0000127156,0.000012021236,0.000003455999,0.49707183,0.49795103,0.00016182574],"about_ca_topic_score_codex":0.00004315332,"about_ca_topic_score_gemma":0.00008148095,"teacher_disagreement_score":0.49314472,"about_ca_system_score_codex":0.0000963897,"about_ca_system_score_gemma":0.00020016891,"threshold_uncertainty_score":0.99997556},"labels":[],"label_agreement":null},{"id":"W2888601585","doi":"10.1007/s10654-018-0434-4","title":"Individually-matched etiologic studies: classical estimators made new again","year":2018,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"","keywords":"Calculator; Statistics; Estimator; Matching (statistics); Econometrics; Statistician; Regression; Multinomial logistic regression; Regression analysis; Computer science; Medicine; Mathematics","score_opus":0.4704787764606337,"score_gpt":0.4991463389490607,"score_spread":0.028667562488427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888601585","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":[0.14989927,0.0015558555,0.83064264,0.008445714,0.000988608,0.00024935158,0.000004800865,0.0003156917,0.007898057],"genre_scores_gemma":[0.25112385,0.0004497934,0.7428286,0.0031322148,0.0017894309,0.0000019039701,0.0000019780455,0.00007093,0.0006013234],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99275666,0.0041833883,0.0020243912,0.00030355563,0.00016949551,0.00056250056],"domain_scores_gemma":[0.9887346,0.008236725,0.0018902882,0.00043591735,0.00038083334,0.00032161138],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011796259,0.00030470316,0.0012491099,0.00020283618,0.00009851508,0.000009171505,0.000712277,0.000118736854,0.00017246848],"category_scores_gemma":[0.06842178,0.0002123482,0.00022786797,0.00018363753,0.00082455383,0.00016830725,0.00026702855,0.00081425323,0.00017113907],"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":[0.0002703489,0.00023049965,0.009176493,0.00008266546,0.0007831749,0.00071140646,0.0031924364,0.000077032935,0.0032937536,0.22470294,0.718649,0.03883023],"study_design_scores_gemma":[0.0006456751,0.0025916556,0.0032401804,0.00029423993,0.00010663784,0.00056603097,0.00037717915,0.000063568084,0.000600166,0.960425,0.030771798,0.00031785265],"about_ca_topic_score_codex":0.0000011952015,"about_ca_topic_score_gemma":0.0000025954473,"teacher_disagreement_score":0.73572206,"about_ca_system_score_codex":0.00011432121,"about_ca_system_score_gemma":0.0001038,"threshold_uncertainty_score":0.9394253},"labels":[],"label_agreement":null},{"id":"W2889374799","doi":"10.1007/s10742-018-0187-2","title":"Causal inference for multi-level treatments with machine-learned propensity scores","year":2018,"lang":"en","type":"article","venue":"Health Services and Outcomes Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Propensity score matching; Causal inference; Inverse probability; Inverse probability weighting; Multinomial logistic regression; Statistics; Econometrics; Observational study; Logistic regression; Matching (statistics); Computer science; Estimator; Bayesian probability; Average treatment effect; Mathematics; Posterior probability","score_opus":0.8430232517073458,"score_gpt":0.6674423948286655,"score_spread":0.1755808568786803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889374799","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":[0.38473985,0.00041499274,0.60554564,0.0036865657,0.00014687181,0.0046970434,0.00016604959,0.00040019536,0.00020280125],"genre_scores_gemma":[0.12829962,0.00033274305,0.8690109,0.0010862064,0.00006530526,0.00035590093,0.0000207615,0.000049924274,0.00077860383],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99539524,0.0020753676,0.000472133,0.0006361449,0.00038761157,0.0010335002],"domain_scores_gemma":[0.9914651,0.0066294493,0.00024503283,0.00056216755,0.0007680294,0.00033021282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005621462,0.00029425768,0.0008783351,0.0002641275,0.00063232024,0.00005721104,0.00036365332,0.00017751129,0.000043576583],"category_scores_gemma":[0.0013167503,0.00018855344,0.00004765381,0.00028894388,0.0005269377,0.00020445495,0.0003460993,0.00042974766,0.00001009565],"study_design_candidate":"observational","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":[0.004189607,0.001126212,0.51874465,0.009331476,0.000660153,0.00004884437,0.019416839,0.0000019611962,0.0016515582,0.20192942,0.00039096377,0.2425083],"study_design_scores_gemma":[0.007504054,0.015066066,0.44238496,0.00092372147,0.00010098736,0.000094870375,0.0033074557,0.0050029624,0.0065349336,0.51517767,0.0028260106,0.0010762962],"about_ca_topic_score_codex":0.0037740627,"about_ca_topic_score_gemma":0.018598486,"teacher_disagreement_score":0.31324828,"about_ca_system_score_codex":0.00012548227,"about_ca_system_score_gemma":0.0002785505,"threshold_uncertainty_score":0.99930954},"labels":[],"label_agreement":null},{"id":"W2889955345","doi":"10.23889/ijpds.v3i4.611","title":"Estimating the effect of referral for nephrology care on the survival of adults with advanced chronic kidney disease in a real-world clinical setting","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","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":true,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Medicine; Hazard ratio; Proportional hazards model; Referral; Nephrology; Confounding; Kidney disease; Internal medicine; Survival analysis; Cohort; Randomized controlled trial; Confidence interval; Clinical trial; Selection bias; Marginal structural model; Emergency medicine; Family medicine; Pathology","score_opus":0.1553901981825603,"score_gpt":0.515340847866065,"score_spread":0.35995064968350476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889955345","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":[0.933122,0.000007641648,0.063711226,0.0010213247,0.0007274828,0.0009811857,0.00034712141,0.000022021733,0.00006002408],"genre_scores_gemma":[0.9469567,0.000003951381,0.05250069,0.00007117439,0.0003241033,0.000041894167,0.00008476528,0.000011235852,0.0000054759425],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981901,0.00014058012,0.00065723166,0.00026940744,0.0005499978,0.00019268315],"domain_scores_gemma":[0.9954121,0.0025207757,0.0008340264,0.0004854971,0.00067802216,0.00006956804],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003265491,0.00011052272,0.00020091684,0.00015610487,0.00020583921,0.000039771156,0.0014268429,0.000026212263,0.000007914425],"category_scores_gemma":[0.010444571,0.000059245824,0.000053995886,0.0002361947,0.00046981277,0.00059374596,0.00019820408,0.00018835838,2.5131465e-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":[0.017142756,0.00030187596,0.50339514,0.0006079206,0.00021566215,0.000010245548,0.0025296551,0.011012125,0.003054095,0.2921275,0.001979013,0.16762401],"study_design_scores_gemma":[0.006842019,0.0076784734,0.19603553,0.00489583,0.00016864971,0.000024727906,0.00047679598,0.64622784,0.005574865,0.13072678,0.000806955,0.0005415283],"about_ca_topic_score_codex":0.000058957674,"about_ca_topic_score_gemma":0.0006087406,"teacher_disagreement_score":0.6352157,"about_ca_system_score_codex":0.00016088258,"about_ca_system_score_gemma":0.0002545311,"threshold_uncertainty_score":0.9978909},"labels":[],"label_agreement":null},{"id":"W2891367027","doi":"10.1513/annalsats.201808-564ps","title":"Control of Confounding and Reporting of Results in Causal Inference Studies. Guidance for Authors from Editors of Respiratory, Sleep, and Critical Care Journals","year":2018,"lang":"en","type":"article","venue":"Annals of the American Thoracic Society","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":722,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McGill University; Queen's University","funders":"","keywords":"Confounding; Causal inference; Fallacy; Medicine; Statistics; Econometrics; Computer science; Mathematics; Linguistics","score_opus":0.40907458202425123,"score_gpt":0.5752142049379743,"score_spread":0.16613962291372303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891367027","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":[0.9862588,0.0011631002,0.011329544,0.0004897464,0.00015584007,0.000350454,0.00020594089,0.000017885255,0.000028700819],"genre_scores_gemma":[0.96446425,0.0001322245,0.035067365,0.00011441988,0.00018548814,0.00001730054,5.7315077e-7,0.000016381096,0.0000019810893],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996946,0.0002322928,0.0020080772,0.00025258484,0.00032516345,0.00023592655],"domain_scores_gemma":[0.9878831,0.0045517515,0.005291191,0.00042417247,0.0017914944,0.000058297683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032445865,0.00016789605,0.0010875458,0.000053167547,0.00007526111,0.000007802851,0.00022184622,0.00008316092,0.0000011149014],"category_scores_gemma":[0.03851728,0.00012837262,0.00016807787,0.0002962493,0.002606359,0.00013161197,0.00016330455,0.00018962244,2.0632232e-8],"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":[0.00314799,0.00050161907,0.37771973,0.0066741602,0.001763653,0.000007256651,0.100585334,0.000039285158,0.41892815,0.013818143,0.010646875,0.06616782],"study_design_scores_gemma":[0.0009826,0.0021727064,0.040064044,0.00449541,0.00030232422,0.0000035410435,0.042754743,0.0006633901,0.7377562,0.17015377,0.00019563937,0.00045563796],"about_ca_topic_score_codex":0.00018179609,"about_ca_topic_score_gemma":0.00002942735,"teacher_disagreement_score":0.3376557,"about_ca_system_score_codex":0.000025416235,"about_ca_system_score_gemma":0.00008959942,"threshold_uncertainty_score":0.9695817},"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":"W2892038960","doi":"10.1145/3287560.3287564","title":"Fairness through Causal Awareness","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":105,"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":"","keywords":"Replicate; Computer science; Outcome (game theory); Causal model; Observational study; Machine learning; Artificial intelligence; Generative grammar; Confounding; Intervention (counseling); Causal structure; Affect (linguistics); Econometrics; Cognitive psychology; Psychology; Statistics; Mathematics","score_opus":0.17918138593962896,"score_gpt":0.44090865532862894,"score_spread":0.261727269389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892038960","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":[0.29234833,0.0000139476515,0.5691824,0.00013473858,0.00029449497,0.00042300622,0.000004134936,0.0013736523,0.13622534],"genre_scores_gemma":[0.8815256,0.000007253183,0.11030875,0.00019377528,0.000055969733,0.000033907298,0.0000037548612,0.000034123237,0.007836896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999104,0.000026522357,0.0002041226,0.00023077012,0.00019074082,0.00024380899],"domain_scores_gemma":[0.99903953,0.0002586337,0.00006585012,0.00049567106,0.000104824176,0.00003549881],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012316629,0.00014956344,0.00023224049,0.000028900398,0.000033871198,0.000021605996,0.0002119792,0.00009397951,0.001636677],"category_scores_gemma":[0.00014488105,0.00011942389,0.000046952267,0.00012874424,0.000036647565,0.0003466714,0.000096778276,0.00012292471,0.00047293038],"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":[0.000005557004,0.000044815348,0.003224573,0.000053741027,0.00000997425,0.0000034066404,0.00018350482,0.0000029022624,0.00202069,0.99026763,0.0036810015,0.00050218025],"study_design_scores_gemma":[0.00016010542,0.00005622449,0.00016695933,0.000033763074,0.000007699331,0.000006026986,0.00022862412,0.00008278948,0.057501,0.93686885,0.004662724,0.00022525013],"about_ca_topic_score_codex":0.000063331376,"about_ca_topic_score_gemma":0.000029842788,"teacher_disagreement_score":0.58917725,"about_ca_system_score_codex":0.000046379264,"about_ca_system_score_gemma":0.000039479975,"threshold_uncertainty_score":0.999276},"labels":[],"label_agreement":null},{"id":"W2892362469","doi":"10.3386/t0337","title":"Regression Discontinuity Designs: A Guide to Practice","year":2007,"lang":"en","type":"preprint","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":52,"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":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Regression discontinuity design; Regression; Discontinuity (linguistics); Computer science; Statistics; Mathematics","score_opus":0.6921272203478509,"score_gpt":0.6760656725899765,"score_spread":0.016061547757874384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892362469","genre_codex":"other","genre_gemma":"methods","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":[0.0068622986,0.00037049508,0.13291076,0.00662549,0.00064410345,0.0046986304,0.00018343449,0.00034710186,0.8473577],"genre_scores_gemma":[0.19031021,0.000281791,0.7980414,0.00018948308,0.00079203764,0.0005894189,0.00013400253,0.00011438282,0.009547254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958477,0.00046897453,0.0010814463,0.0007326461,0.0013477245,0.00052148744],"domain_scores_gemma":[0.98738545,0.008495501,0.0005921366,0.00079634815,0.0025352717,0.00019528842],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01318045,0.0002884894,0.00059720763,0.0009996603,0.00010765007,0.00009217789,0.0010297128,0.00051134697,0.00025000557],"category_scores_gemma":[0.025561497,0.00027155387,0.0001509457,0.00020126197,0.0002167277,0.00032900818,0.0016291708,0.0015080083,0.0001262962],"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":[0.00018877018,0.00015917374,0.00003147038,0.00015873474,0.000076104494,0.000008059188,0.00022779453,0.00020679102,0.0011086694,0.8811581,0.11335178,0.0033245666],"study_design_scores_gemma":[0.00015864147,0.000106853884,0.000023624738,0.00051124213,0.000012980664,0.000007651561,0.00015256723,0.00020106183,0.010819648,0.9756509,0.012113967,0.00024087529],"about_ca_topic_score_codex":0.00042562778,"about_ca_topic_score_gemma":0.00016722873,"teacher_disagreement_score":0.83781046,"about_ca_system_score_codex":0.0021964961,"about_ca_system_score_gemma":0.0012986579,"threshold_uncertainty_score":0.99997365},"labels":[],"label_agreement":null},{"id":"W2893335949","doi":"10.1007/s40471-018-0172-x","title":"The Curse of the Perinatal Epidemiologist: Inferring Causation Amidst Selection","year":2018,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":50,"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 Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Causation; Outcome (game theory); Selection bias; Selection (genetic algorithm); Epidemiology; Pregnancy; Medicine; Psychology; Computer science; Biology; Economics; Epistemology","score_opus":0.29643878629705167,"score_gpt":0.49660026095631526,"score_spread":0.2001614746592636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893335949","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":[0.8373464,0.0013599623,0.15078773,0.0016870797,0.0046145283,0.0013227949,0.000007792229,0.00073125755,0.0021424873],"genre_scores_gemma":[0.99389255,0.00020209895,0.005160856,0.000079781086,0.00036337573,0.00012121161,0.0000054901575,0.000022868711,0.00015177767],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963755,0.000985428,0.0015547998,0.00043664247,0.00015585992,0.0004917881],"domain_scores_gemma":[0.99187636,0.0047943206,0.0019648096,0.0009075672,0.00039124556,0.000065720975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056553897,0.00024198109,0.00055546645,0.000056690475,0.00048720776,0.0000066187413,0.0002985867,0.00020189845,0.00002894881],"category_scores_gemma":[0.051307555,0.00013460976,0.00019325664,0.00026546797,0.0015483695,0.00014140608,0.00025180756,0.00053675415,0.0000055117584],"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":[0.000026475273,0.000075109056,0.624076,0.00009222129,0.00005717578,0.000003637375,0.00021716405,0.000054765304,0.0012457159,0.33081904,0.012759878,0.030572798],"study_design_scores_gemma":[0.00007191696,0.00014221792,0.06465615,0.00016487976,0.000052306452,0.00031814747,0.000034810022,0.0010195909,0.0067190155,0.900803,0.025800232,0.00021768932],"about_ca_topic_score_codex":0.000071962204,"about_ca_topic_score_gemma":0.000116675925,"teacher_disagreement_score":0.569984,"about_ca_system_score_codex":0.00018674818,"about_ca_system_score_gemma":0.000103400394,"threshold_uncertainty_score":0.9566837},"labels":[],"label_agreement":null},{"id":"W2893874018","doi":"10.1097/olq.0000000000000911","title":"Risk Factor Reversal in Studies of Infectious Disease: Making Counterintuitive Results Intuitive Again","year":2018,"lang":"en","type":"letter","venue":"Sexually Transmitted Diseases","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":"","keywords":"Counterintuitive; Medicine; Abstinence; Sexual abstinence; Disease; Internal medicine; Psychiatry; Population; Environmental health; Epistemology; Family planning; Research methodology","score_opus":0.08965879946146911,"score_gpt":0.39388591544713614,"score_spread":0.30422711598566704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893874018","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":[0.45889005,0.020144697,0.10328093,0.08179431,0.005113631,0.022786405,0.2907909,0.010243512,0.0069555766],"genre_scores_gemma":[0.9274228,0.0036617198,0.005400984,0.056513805,0.0029942621,0.0010456595,0.0015134523,0.00065732806,0.00078999304],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99441,0.00087041873,0.0016360974,0.0012472607,0.00097552955,0.0008607224],"domain_scores_gemma":[0.992144,0.004421811,0.0013280767,0.0010641363,0.00088083895,0.00016115572],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000370079,0.0010618105,0.0017101929,0.00073034654,0.00013146787,0.00005379006,0.00065225863,0.0006711775,0.00010511262],"category_scores_gemma":[0.0060944837,0.0009974404,0.00037594364,0.0005760304,0.0011080767,0.0003854009,0.00018170393,0.001795606,0.00001375154],"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":[0.006023292,0.0022755573,0.011879975,0.015367209,0.0064824075,0.005327907,0.024461502,0.000033129956,0.00019774116,0.00315454,0.90946114,0.015335594],"study_design_scores_gemma":[0.00589243,0.0027392183,0.019714143,0.01610848,0.0038212908,0.000016998145,0.0026769147,0.00010277273,0.00069457345,0.9110518,0.03250569,0.0046756933],"about_ca_topic_score_codex":0.00006617973,"about_ca_topic_score_gemma":0.00021934265,"teacher_disagreement_score":0.90789723,"about_ca_system_score_codex":0.0005647092,"about_ca_system_score_gemma":0.00041159062,"threshold_uncertainty_score":0.9992476},"labels":[],"label_agreement":null},{"id":"W2894669578","doi":"10.1002/sta4.205","title":"A doubly robust weighting estimator of the average treatment effect on the treated","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Causal Inference Techniques","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; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Weighting; Mathematics; Statistics; Matching (statistics); Inverse probability weighting; Minimum-variance unbiased estimator; Estimation; Sampling (signal processing); Inverse; Computer science; Medicine; Engineering","score_opus":0.12477632230546995,"score_gpt":0.3810167172586393,"score_spread":0.2562403949531693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894669578","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":[0.977063,0.000010678646,0.008185042,0.0002815078,0.000074502226,0.0008922032,0.000029944162,0.00021783116,0.013245311],"genre_scores_gemma":[0.9916885,0.000002832741,0.007258102,0.000047318747,0.000047609137,0.000080365644,0.0000016964207,0.000025859606,0.0008477222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918205,0.00012922907,0.00018430472,0.00015052347,0.00016677489,0.00018712632],"domain_scores_gemma":[0.9981143,0.0010998733,0.00014982153,0.0005510425,0.00005846914,0.000026527137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021414932,0.00017232534,0.00020659862,0.000026429205,0.00015926597,0.000015981854,0.00019541931,0.000045552562,0.00014652562],"category_scores_gemma":[0.00034684685,0.00007003453,0.000086147025,0.00014165997,0.00016519752,0.00004227021,0.00004981589,0.00008891736,0.000026779153],"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":[0.0011478803,0.0014996572,0.010876544,0.0004198199,0.000843125,0.000060825616,0.010713373,0.00024017712,0.10072147,0.7723602,0.022155672,0.07896125],"study_design_scores_gemma":[0.00054026925,0.002043269,0.0002445573,0.00024025801,0.000072549716,0.000005891992,0.00004943638,0.0011639032,0.90785325,0.086502805,0.0011227935,0.00016101701],"about_ca_topic_score_codex":0.000046720368,"about_ca_topic_score_gemma":0.000041404182,"teacher_disagreement_score":0.80713177,"about_ca_system_score_codex":0.000115354465,"about_ca_system_score_gemma":0.000022451333,"threshold_uncertainty_score":0.28559253},"labels":[],"label_agreement":null},{"id":"W2895514839","doi":"10.1186/s41073-018-0053-3","title":"Protocol for the development of a CONSORT extension for RCTs using cohorts and routinely collected health data","year":2018,"lang":"en","type":"article","venue":"Research Integrity and Peer Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Multiple Sclerosis Society of Canada; Jewish General Hospital; University of Ottawa; Dalhousie University; McMaster University; Western University; Children's Hospital of Eastern Ontario; Impact; Ottawa Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; Wellcome Trust","keywords":"Consolidated Standards of Reporting Trials; Checklist; Observational study; Generalizability theory; Guideline; Protocol (science); Randomized controlled trial; Medicine; Systematic review; Strengthening the reporting of observational studies in epidemiology; Research design; MEDLINE; Family medicine; Alternative medicine; Psychology; Statistics; Political science; Surgery","score_opus":0.9111252944079001,"score_gpt":0.6940410504859482,"score_spread":0.2170842439219519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895514839","genre_codex":"protocol","genre_gemma":"methods","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":[0.0010772392,0.0051980834,0.40026963,0.011964654,0.000031927833,0.5808006,0.00030717824,0.000103378596,0.0002472988],"genre_scores_gemma":[0.0015936255,0.0024175001,0.8560075,0.0003719965,0.00008686716,0.13899139,0.000058736503,0.000038776463,0.00043358665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99811053,0.00026605916,0.0005622095,0.00029414016,0.0004705448,0.0002964861],"domain_scores_gemma":[0.99445206,0.002219833,0.00020585331,0.0005344789,0.0024962393,0.000091514135],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015612672,0.000114058406,0.00045026361,0.00005104553,0.00044349616,0.000034816432,0.0002652231,0.00006105638,0.000018696543],"category_scores_gemma":[0.015611298,0.000067304405,0.000023709743,0.00021796588,0.00031845798,0.000100394864,0.0003323881,0.0003186277,3.3794842e-7],"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":[0.00086474203,0.00056813523,0.00045258412,0.11872195,0.0002278434,0.0000016789928,0.0022413586,3.442658e-8,0.0017171201,0.076899126,0.45043314,0.3478723],"study_design_scores_gemma":[0.0008019062,0.000825253,0.0002530557,0.02502936,0.000044842833,0.000034734,0.00016477909,0.0027586035,0.0031817097,0.0810976,0.8855781,0.00023008324],"about_ca_topic_score_codex":0.00006470225,"about_ca_topic_score_gemma":0.00029169733,"teacher_disagreement_score":0.4557379,"about_ca_system_score_codex":0.000062001745,"about_ca_system_score_gemma":0.0008026611,"threshold_uncertainty_score":0.9926806},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2896610735","doi":"10.1515/jci-2018-0015","title":"Learning Heterogeneity in Causal Inference Using Sufficient Dimension Reduction","year":2018,"lang":"en","type":"article","venue":"Journal of Causal Inference","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","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Causal inference; Dimensionality reduction; Inference; Outcome (game theory); Sufficient dimension reduction; Dimension (graph theory); Econometrics; Regression; Regression analysis; Feature selection; Statistics; Computer science; Mathematics; Machine learning; Artificial intelligence","score_opus":0.1798803548296694,"score_gpt":0.4531881813150275,"score_spread":0.2733078264853581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896610735","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":[0.87265104,0.00005744631,0.1262081,0.000055787208,0.00048597512,0.0001804287,0.0000018465151,0.00008934021,0.0002700184],"genre_scores_gemma":[0.9598108,0.00008311571,0.039640762,0.000032397496,0.00035120832,0.000004262395,0.0000013628382,0.00003796948,0.000038138252],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99671924,0.0003616447,0.0013233704,0.00033621283,0.00071411656,0.0005454217],"domain_scores_gemma":[0.9964039,0.0005971469,0.0012566942,0.00036517804,0.0011736406,0.00020347393],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015988051,0.000348818,0.0006517969,0.00054774754,0.00017939939,0.000089724206,0.00037712528,0.00024041525,0.000095794116],"category_scores_gemma":[0.0033700743,0.00030926068,0.00012623197,0.0006380949,0.0003359,0.0008850986,0.00020852438,0.0010956932,0.000013988743],"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":[0.00071106275,0.001225616,0.06129897,0.00021713789,0.00014652991,0.00031601635,0.006686428,0.006765086,0.87117815,0.039658334,0.00036276766,0.011433891],"study_design_scores_gemma":[0.0025846933,0.008548438,0.018025553,0.0038522268,0.00028069195,0.0019153561,0.0022869662,0.027538802,0.7074581,0.22458367,0.00082710746,0.0020984346],"about_ca_topic_score_codex":0.00007941319,"about_ca_topic_score_gemma":0.00009699307,"teacher_disagreement_score":0.18492533,"about_ca_system_score_codex":0.0004813804,"about_ca_system_score_gemma":0.00035074278,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W2896981660","doi":"10.1002/sim.8008","title":"Propensity‐score matching with competing risks in survival analysis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Covariate; Observational study; Matching (statistics); Hazard ratio; Confounding; Sample size determination; Medicine; Absolute risk reduction; Confidence interval; Econometrics; Mathematics","score_opus":0.23846640406203207,"score_gpt":0.45839961939779816,"score_spread":0.2199332153357661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896981660","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":[0.38420707,0.000008850707,0.6120987,0.00008011199,0.000044554603,0.0002167269,0.000017417951,0.00007107168,0.0032555084],"genre_scores_gemma":[0.679157,0.000011427326,0.32061887,0.000051219322,0.00007424379,0.0000116385445,0.000021102493,0.000019138935,0.000035383302],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99836195,0.00015036904,0.0005061423,0.0002815475,0.00039681102,0.00030318016],"domain_scores_gemma":[0.99803936,0.0011553087,0.00021065355,0.000337415,0.0001971812,0.00006005298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013563909,0.00018286984,0.00063992233,0.0004041283,0.00005302934,0.000011069621,0.00018335029,0.00005705481,0.0001815781],"category_scores_gemma":[0.0015280439,0.00013422075,0.0000132893265,0.000995813,0.00039171067,0.00006452746,0.00007041612,0.00037852555,0.00000458181],"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":[0.00016463545,0.00015496157,0.594779,0.00023501359,0.0001877082,0.00047011403,0.0077371476,0.00012661873,0.00086593,0.3898057,0.0003330047,0.005140123],"study_design_scores_gemma":[0.0010501617,0.000599377,0.16653928,0.00085788534,0.0002909161,0.000009614103,0.0020042001,0.0027997028,0.0004367973,0.82500684,0.000037977577,0.00036726694],"about_ca_topic_score_codex":0.0012856661,"about_ca_topic_score_gemma":0.012935031,"teacher_disagreement_score":0.4352011,"about_ca_system_score_codex":0.00010829275,"about_ca_system_score_gemma":0.000036770347,"threshold_uncertainty_score":0.7218051},"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":"W2899570500","doi":"10.1017/pan.2018.53","title":"A Regression-with-Residuals Method for Estimating Controlled Direct Effects","year":2018,"lang":"en","type":"article","venue":"Political Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"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","funders":"","keywords":"Moderation; Respondent; Econometrics; Regression analysis; Regression; Causal inference; Confounding; Estimation; Mediation; Statistics; Outcome (game theory); Psychology; Computer science; Social psychology; Mathematics; Economics; Political science","score_opus":0.07879243387603321,"score_gpt":0.4727019433909369,"score_spread":0.39390950951490367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899570500","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":[0.0022826293,0.000015805112,0.98998165,0.00047418618,0.000026355403,0.0006266782,0.000017631019,0.0003836687,0.0061913757],"genre_scores_gemma":[0.35250252,2.31753e-7,0.64637244,0.00022270923,0.00017331334,0.0003250134,0.000005144189,0.000022860417,0.0003757586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979505,0.00025950078,0.00045751256,0.00039177886,0.0002952223,0.00064546254],"domain_scores_gemma":[0.986616,0.012128261,0.00019265088,0.00047429884,0.0003505063,0.00023824198],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008781113,0.0002546968,0.0011883178,0.0002676949,0.00017399018,0.00004987064,0.00018657405,0.0001101512,0.000112603455],"category_scores_gemma":[0.010896387,0.00015524916,0.00038288874,0.0006017996,0.00017351817,0.00009024348,0.000060233717,0.00011382543,0.000007476159],"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":[0.00033137476,0.00018068093,0.000440386,0.00020650426,0.0026581092,0.000010361705,0.00014359066,0.00002350861,0.0010192407,0.990243,0.00080876873,0.00393446],"study_design_scores_gemma":[0.0012425921,0.00035790663,0.000034065688,0.0001247305,0.0045092194,0.0000029364462,0.000034548953,0.21520813,0.035277445,0.7428864,0.00004984348,0.0002721476],"about_ca_topic_score_codex":0.00007147643,"about_ca_topic_score_gemma":0.00004697497,"teacher_disagreement_score":0.3502199,"about_ca_system_score_codex":0.00007719282,"about_ca_system_score_gemma":0.00003609211,"threshold_uncertainty_score":0.9974353},"labels":[],"label_agreement":null},{"id":"W2900917686","doi":"10.1038/s41562-018-0466-5","title":"Quasi-experimental causality in neuroscience and behavioural research","year":2018,"lang":"en","type":"review","venue":"Nature Human Behaviour","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":109,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Causality (physics); Psychology; Behavioural sciences; Neuroscience; Cognitive psychology; Cognitive science; Psychotherapist; Physics","score_opus":0.603559070223279,"score_gpt":0.6178682674572226,"score_spread":0.014309197233943527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900917686","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":[0.011063863,0.9858197,0.000016531805,0.000012175859,0.0002753321,0.0019234227,0.00008433807,0.0003186386,0.00048598708],"genre_scores_gemma":[0.04991768,0.94393456,0.0033414196,0.000050603187,0.00032252356,0.0007957895,0.000096587944,0.00027240426,0.001268402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951203,0.0008258925,0.0009405638,0.0012375837,0.0009974316,0.0008782556],"domain_scores_gemma":[0.9976958,0.00039907574,0.00037956025,0.0010854634,0.00022556585,0.00021452614],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0023822924,0.00067093724,0.0015905397,0.0007755197,0.00036941998,0.00017277051,0.0010367538,0.0016398717,0.000072832925],"category_scores_gemma":[0.0006249785,0.0005782276,0.00022026342,0.0007842017,0.0009562161,0.00029574835,0.0007827607,0.005350333,0.000012819637],"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":[0.00007085201,0.023561705,0.018346747,0.0315634,0.00008620998,0.003413053,0.004160825,1.609851e-8,0.000635991,0.7197909,0.040741846,0.15762846],"study_design_scores_gemma":[0.0017398898,0.008321161,0.004669488,0.05309156,0.0012522229,0.0013222347,0.00060031546,0.0000031812197,0.001203714,0.16598234,0.7546674,0.007146505],"about_ca_topic_score_codex":0.00014316944,"about_ca_topic_score_gemma":0.00029621055,"teacher_disagreement_score":0.71392554,"about_ca_system_score_codex":0.0006339248,"about_ca_system_score_gemma":0.00019095506,"threshold_uncertainty_score":0.9996669},"labels":[],"label_agreement":null},{"id":"W2900937465","doi":"10.1097/mlr.0000000000001014","title":"Lasso Regression for the Prediction of Intermediate Outcomes Related to Cardiovascular Disease Prevention Using the TRANSIT Quality Indicators","year":2018,"lang":"en","type":"article","venue":"Medical Care","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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; Sanofi (Canada); Université de Montréal","funders":"","keywords":"Dyslipidemia; Medicine; Population; Diabetes mellitus; Disease; Physical therapy; Internal medicine; Environmental health","score_opus":0.14898389659221287,"score_gpt":0.460383819457116,"score_spread":0.31139992286490314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900937465","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":[0.7013197,0.0003277,0.29589498,0.0005625968,0.00033830764,0.0012587666,0.00008503987,0.00015870019,0.000054218977],"genre_scores_gemma":[0.99783003,0.000022166574,0.0017758737,0.000084942505,0.00009099796,0.00012317378,0.000016932383,0.000020767156,0.000035131812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998105,0.0002639535,0.0004470417,0.00020943448,0.00080216146,0.00017243427],"domain_scores_gemma":[0.99828535,0.00062881847,0.00015182496,0.0006020335,0.00019420154,0.00013774438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012945671,0.00013014808,0.00028390807,0.000058910584,0.0001671646,0.000009334053,0.00031341222,0.00014825839,0.00004927892],"category_scores_gemma":[0.0032302798,0.000064749904,0.00032015544,0.00021430168,0.00026802617,0.00006793677,0.00008373921,0.00021231199,0.000001123698],"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":[0.0014645115,0.00081857806,0.13253014,0.0039345743,0.004373427,0.00003060744,0.09572712,0.00022669333,0.0018563422,0.047826603,0.004623463,0.7065879],"study_design_scores_gemma":[0.007564753,0.0026991472,0.45439702,0.007929379,0.007333917,0.000020779842,0.027027855,0.012558056,0.03438332,0.41023165,0.034068428,0.0017856949],"about_ca_topic_score_codex":0.000018271205,"about_ca_topic_score_gemma":0.000023769526,"teacher_disagreement_score":0.7048022,"about_ca_system_score_codex":0.000086772416,"about_ca_system_score_gemma":0.00009701269,"threshold_uncertainty_score":0.386718},"labels":[],"label_agreement":null},{"id":"W2902725358","doi":"10.1097/jcp.0000000000000991","title":"Statistics Commentary Series","year":2018,"lang":"en","type":"editorial","venue":"Journal of Clinical Psychopharmacology","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":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Library science; Series (stratigraphy); Psychiatry; Psychology; Medicine; Gerontology; Computer science; Biology","score_opus":0.1918737897963293,"score_gpt":0.5953596048181747,"score_spread":0.40348581502184544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902725358","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":[0.00031193072,0.00017297361,0.018172203,0.0017156954,0.9781323,0.00027238808,0.00044686173,0.000080139616,0.00069548184],"genre_scores_gemma":[0.000024874402,0.0038072008,0.1778741,0.0017874418,0.8154986,0.000009357072,0.000034631434,0.00009727813,0.0008664986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99262387,0.0010365925,0.004561777,0.00037357607,0.00096365734,0.0004405173],"domain_scores_gemma":[0.9705317,0.020904943,0.0055870567,0.0004519743,0.0021596062,0.00036474183],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00475262,0.00047011336,0.0022884388,0.00023069931,0.000078041005,0.00003350797,0.0011432081,0.0017191209,0.0015669453],"category_scores_gemma":[0.014463462,0.0003910562,0.00051728816,0.00013545797,0.0008353678,0.00027327167,0.00018961717,0.004656846,0.000054751945],"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":[0.0025860213,0.00054470473,0.000032558088,0.00014274222,0.00056357734,0.00025506917,0.00002543886,1.6334322e-7,0.000028728697,0.00039479852,0.9927035,0.002722695],"study_design_scores_gemma":[0.0021799176,0.002774611,0.000006026945,0.00014159943,0.00046949476,0.000030508274,0.000012194787,0.0000017928021,0.00004851082,0.268303,0.72578466,0.00024769112],"about_ca_topic_score_codex":0.000001849359,"about_ca_topic_score_gemma":0.000016228882,"teacher_disagreement_score":0.26790822,"about_ca_system_score_codex":0.00013592788,"about_ca_system_score_gemma":0.00060991605,"threshold_uncertainty_score":0.99985415},"labels":[],"label_agreement":null},{"id":"W2902926083","doi":"10.1002/sim.8048","title":"Using a monotone single‐index model to stabilize the propensity score in missing data problems and causal inference","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"University of Waterloo","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Causal inference; Propensity score matching; Inference; Missing data; Index (typography); Statistics; Monotone polygon; Computer science; Econometrics; Causal model; Mathematics; Artificial intelligence","score_opus":0.5427102071927957,"score_gpt":0.4837563441874663,"score_spread":0.0589538630053294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902926083","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":[0.15992899,0.000038081624,0.8382942,0.00040207457,0.000044168006,0.00089211826,0.00007884918,0.000051359304,0.00027013393],"genre_scores_gemma":[0.6315691,0.000017574359,0.36811656,0.00016416573,0.0000620922,0.000016220463,0.000012410615,0.000024011893,0.00001788538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998078,0.00011668192,0.00058974756,0.00046709087,0.0003758602,0.00037261503],"domain_scores_gemma":[0.997662,0.00094737276,0.00017021043,0.00089408114,0.0002192062,0.000107129155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014590839,0.00022627211,0.0004492509,0.00015964631,0.0000996256,0.000032499593,0.0004398406,0.000079599515,0.000021578759],"category_scores_gemma":[0.0072930283,0.00015626173,0.0000047272283,0.0003878123,0.0007195962,0.00019185744,0.00054739707,0.00038204962,9.455881e-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":[0.0008643889,0.0014559898,0.09131154,0.0028304541,0.00011203265,0.00042335354,0.07840657,0.0055215294,0.23451008,0.47285503,0.005642075,0.10606696],"study_design_scores_gemma":[0.000416172,0.00025499877,0.0010065957,0.0010776033,0.00002385539,0.000011712851,0.00024072482,0.37267357,0.00052510615,0.6235296,0.000037812162,0.00020222788],"about_ca_topic_score_codex":0.00063935854,"about_ca_topic_score_gemma":0.004915824,"teacher_disagreement_score":0.47164008,"about_ca_system_score_codex":0.00016668245,"about_ca_system_score_gemma":0.00013011499,"threshold_uncertainty_score":0.8730963},"labels":[],"label_agreement":null},{"id":"W2903123620","doi":"10.3386/w25307","title":"Treatment Effects with Multiple Outcomes","year":2018,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Queen's University; Queen's University Belfast; University of Wisconsin-Madison; University of Chicago; Università degli studi di Bergamo; Robert Wood Johnson Foundation","keywords":"Econometrics; Statistics; Mathematics","score_opus":0.6441062607732273,"score_gpt":0.6258726786431317,"score_spread":0.018233582130095627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903123620","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":[0.012768827,0.00022769524,0.0005960676,0.0003778424,0.0003848519,0.0033975649,0.00023901634,0.00024555784,0.9817626],"genre_scores_gemma":[0.8919181,0.0009856964,0.05204285,0.000015895266,0.0012569777,0.001802884,0.0005087466,0.00025605955,0.05121277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967612,0.00015418926,0.00059737015,0.00052319485,0.0015424468,0.00042158764],"domain_scores_gemma":[0.9892777,0.0073215254,0.00042446345,0.0005620662,0.0023101517,0.000104102015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019849727,0.00033453823,0.0008443945,0.00066327583,0.000101324185,0.00003641435,0.0004102701,0.00037477125,0.00024575597],"category_scores_gemma":[0.0045731533,0.0002429251,0.00016827554,0.00011634305,0.00041513753,0.00013494171,0.00013169069,0.0004148491,0.00012103374],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029074648,0.0009356834,0.018610535,0.0014799355,0.0018693383,0.000047689526,0.00022030201,0.00002463359,0.00026568928,0.8339923,0.13554072,0.0067224116],"study_design_scores_gemma":[0.0007851609,0.0012475637,0.0006477222,0.00027792997,0.000041216997,0.000027925007,0.000017598451,0.00007623245,0.0061673215,0.9775175,0.012887326,0.00030653315],"about_ca_topic_score_codex":0.0007641357,"about_ca_topic_score_gemma":0.0006509701,"teacher_disagreement_score":0.9305498,"about_ca_system_score_codex":0.0042171683,"about_ca_system_score_gemma":0.003208197,"threshold_uncertainty_score":0.9996055},"labels":[],"label_agreement":null},{"id":"W2905572727","doi":"10.2139/ssrn.3249910","title":"Methods Matter: P-Hacking and Causal Inference in Economics","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"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":"Causal inference; Hacker; Regression discontinuity design; Randomized experiment; Credibility; Instrumental variable; Identification (biology); Randomized controlled trial; Inference; Statistical inference; Econometrics; Psychology; Statistical hypothesis testing; Statistics; Economics; Computer science; Medicine; Epistemology; Mathematics; Artificial intelligence; Philosophy; Computer security; Internal medicine","score_opus":0.10364846881948976,"score_gpt":0.4459160187302236,"score_spread":0.3422675499107338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905572727","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":[0.434291,0.00029393626,0.5627362,0.0002631711,0.000089112655,0.00012655082,9.4490855e-7,0.000069520895,0.002129556],"genre_scores_gemma":[0.88580334,0.0020402714,0.11157938,0.000121658195,0.00016961394,0.00000818581,4.4202147e-7,0.000033486944,0.00024360981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977183,0.00016049924,0.0003969193,0.00021547869,0.00007267501,0.001436124],"domain_scores_gemma":[0.99896705,0.000472155,0.00021188767,0.00020802204,0.000073597905,0.00006727601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025868963,0.00017777536,0.00027336445,0.00017589399,0.00010700392,0.0000628505,0.00022337526,0.00010260427,0.00005732285],"category_scores_gemma":[0.00046441774,0.00016662558,0.000037125606,0.00011467112,0.00013414798,0.0003522952,0.00009879829,0.0013431321,0.000016123142],"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":[0.000025433394,0.000033607466,0.008680234,0.000009563889,0.000039512383,0.0000024937144,0.00040647908,0.00000262067,0.0010774488,0.8954537,0.000028992104,0.09423989],"study_design_scores_gemma":[0.00023182757,0.00021416166,0.0005028707,0.000039552328,0.000012973985,0.00024294939,0.00036655398,0.00026844838,0.0021151763,0.995404,0.00041259572,0.00018890182],"about_ca_topic_score_codex":0.000034795827,"about_ca_topic_score_gemma":0.0014060362,"teacher_disagreement_score":0.45151234,"about_ca_system_score_codex":0.00067572796,"about_ca_system_score_gemma":0.0005394201,"threshold_uncertainty_score":0.6794794},"labels":[],"label_agreement":null},{"id":"W2906156120","doi":"10.1093/aje/kwy275","title":"Point: Risk Ratio Equations for Natural Direct and Indirect Effects in Causal Mediation Analysis of a Binary Mediator and a Binary Outcome—A Fresh Look at the Formulas","year":2018,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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; Centre Hospitalier de l’Université de Montréal; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Mediation; Binary number; Outcome (game theory); Mediator; Econometrics; Mathematics; Binomial (polynomial); Statistics; Medicine; Mathematical economics; Internal medicine; Sociology","score_opus":0.06949414447764476,"score_gpt":0.4023079516010788,"score_spread":0.332813807123434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906156120","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":[0.8560026,0.0036060372,0.05956032,0.078016534,0.0005312318,0.0016958832,0.00049682526,0.000061410756,0.000029121209],"genre_scores_gemma":[0.7371412,0.0032972055,0.18105471,0.075126074,0.0019759648,0.00046334034,0.00058488076,0.00020211704,0.00015449143],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943051,0.0026760774,0.001945406,0.0003799637,0.00024024383,0.0004532373],"domain_scores_gemma":[0.919533,0.07467665,0.0050308467,0.00038274346,0.00029134945,0.00008537244],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0057997713,0.0003913512,0.0028096049,0.0012585259,0.00011696541,0.000008207022,0.00029751394,0.00038008144,0.000020730058],"category_scores_gemma":[0.04483698,0.00025332932,0.00038729052,0.0006953212,0.0012155861,0.00018130882,0.00015845429,0.0012580224,5.1393437e-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":[0.0012806582,0.00023026831,0.52479064,0.0010520562,0.010677512,0.0002339903,0.0047742887,0.0003880597,0.0018186923,0.0027034618,0.44121316,0.010837189],"study_design_scores_gemma":[0.0075073373,0.030290848,0.20547505,0.0019426765,0.03500497,0.0006352052,0.0020275665,0.077376895,0.0019793422,0.61234444,0.021139368,0.004276329],"about_ca_topic_score_codex":0.00014154079,"about_ca_topic_score_gemma":0.0006191453,"teacher_disagreement_score":0.60964096,"about_ca_system_score_codex":0.00025715932,"about_ca_system_score_gemma":0.000108523025,"threshold_uncertainty_score":0.9999919},"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":"W2906741671","doi":"10.1002/sim.8075","title":"Should a propensity score model be super? The utility of ensemble procedures for causal adjustment","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Covariate; Logistic regression; Statistics; Inverse probability weighting; Overfitting; Weighting; Regression; Matching (statistics); Mean squared error; Econometrics; Mathematics; Confounding; Computer science; Artificial intelligence; Medicine","score_opus":0.352053424871457,"score_gpt":0.4614552599099146,"score_spread":0.10940183503845757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906741671","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":[0.03792845,0.000066547014,0.9578023,0.000717934,0.00010097333,0.0016394295,0.0002672915,0.000072129515,0.0014049538],"genre_scores_gemma":[0.71152884,0.000040389456,0.2876122,0.00033202916,0.000113911585,0.00014931646,0.000022509294,0.000023288903,0.00017750659],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984712,0.000055640066,0.0005338228,0.00025788584,0.0003939316,0.00028750132],"domain_scores_gemma":[0.99778336,0.0009606837,0.00018022518,0.00047436167,0.0005441268,0.00005726732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009891925,0.00018680502,0.00044723361,0.00006447617,0.00007758097,0.000003991475,0.00025380932,0.00008410043,0.00008509209],"category_scores_gemma":[0.0056880265,0.00011361413,0.000022098746,0.0001450924,0.0008366736,0.000050803945,0.0000892793,0.0002079182,6.1175564e-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":[0.00032906758,0.00027674492,0.0012475343,0.0011620892,0.000043999513,0.0000064817436,0.005485426,0.000011079367,0.006251137,0.85309273,0.1263668,0.00572694],"study_design_scores_gemma":[0.0005562737,0.0007355502,0.0009763699,0.00030166106,0.00007748333,0.0000052359387,0.0003506729,0.032210447,0.011374189,0.95315444,0.00012361161,0.00013408318],"about_ca_topic_score_codex":0.00008929595,"about_ca_topic_score_gemma":0.0014791677,"teacher_disagreement_score":0.6736004,"about_ca_system_score_codex":0.000058171794,"about_ca_system_score_gemma":0.00018566572,"threshold_uncertainty_score":0.680951},"labels":[],"label_agreement":null},{"id":"W2908053812","doi":"10.1146/annurev-publhealth-040218-043735","title":"Commentary: Causal Inference for Social Exposures","year":2019,"lang":"en","type":"review","venue":"Annual Review of Public Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":47,"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":"Causal inference; Observational study; Confounding; Epidemiology; Inference; Social epidemiology; Causal model; Causality (physics); Causal structure; Psychology; Task (project management); Marginal structural model; Cognitive psychology; Medicine; Computer science; Public health; Social determinants of health; Pathology; Artificial intelligence","score_opus":0.48796161388773407,"score_gpt":0.5757151415730767,"score_spread":0.08775352768534261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908053812","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":[4.7874614e-8,0.9723339,0.013764289,0.005517629,0.00019630778,0.005640544,0.0019576116,0.00018999253,0.00039966928],"genre_scores_gemma":[5.598209e-7,0.9775318,0.013595918,0.0064419587,0.00029011746,0.0010269835,0.0008485269,0.000118278185,0.00014586501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939857,0.0012374726,0.0027117154,0.0005813634,0.0005736133,0.0009101131],"domain_scores_gemma":[0.9921856,0.0029333069,0.0030457503,0.00086984166,0.0006851278,0.00028040988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0058148606,0.0006856787,0.0057086833,0.00023941256,0.0001429619,0.000031031595,0.0009706599,0.00035889682,0.0001247585],"category_scores_gemma":[0.004555187,0.0005397749,0.00093318924,0.00052237074,0.00015097065,0.0003535655,0.00028422003,0.000635021,0.000024385845],"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":[3.3346655e-7,0.00006103977,3.1597904e-7,0.31402674,0.000053976364,2.3362114e-7,0.00008631831,2.9886893e-10,3.4669598e-9,0.045242947,0.15032463,0.49020347],"study_design_scores_gemma":[0.00009372936,0.0003768558,2.9048496e-7,0.11306615,0.0002367792,0.000005379542,0.000049129165,1.5768244e-7,1.1146603e-7,0.008128629,0.8776798,0.00036297317],"about_ca_topic_score_codex":0.000053318035,"about_ca_topic_score_gemma":0.00001941668,"teacher_disagreement_score":0.7273552,"about_ca_system_score_codex":0.00051155314,"about_ca_system_score_gemma":0.0027736165,"threshold_uncertainty_score":0.9997054},"labels":[],"label_agreement":null},{"id":"W2908350920","doi":"10.1002/sim.8073","title":"Weighted causal inference methods with mismeasured covariates and misclassified outcomes","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Causal inference; Inverse probability weighting; Logistic regression; Econometrics; Computer science; Statistics; Weighting; Inference; Observational error; Regression; Estimation; Mathematics; Estimator; Artificial intelligence; Medicine","score_opus":0.1192263844432153,"score_gpt":0.4720951276343318,"score_spread":0.3528687431911165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908350920","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":[0.021505298,0.00008063695,0.9740934,0.0005481802,0.00014046257,0.0005619024,0.000057847257,0.00016704378,0.0028452307],"genre_scores_gemma":[0.14073057,0.000054381777,0.8582744,0.00016923471,0.000022188608,0.000034422235,0.000026228186,0.00003483178,0.00065373007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825877,0.00021541415,0.000490331,0.0003469413,0.00037618235,0.0003123894],"domain_scores_gemma":[0.9942502,0.0048211515,0.00021052854,0.0004117168,0.00019702029,0.000109380264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010253247,0.00027822106,0.0007241584,0.00017856013,0.00003642367,0.000015124726,0.0001691058,0.00011383705,0.0003188261],"category_scores_gemma":[0.0031876734,0.00018497772,0.000010848578,0.00024136719,0.0003150186,0.00008465518,0.000058671012,0.00038293944,0.0000065166964],"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":[0.000094895244,0.00007129945,0.057178196,0.00027195993,0.000075679316,0.000053268024,0.0012055368,0.0000018743847,0.0059905313,0.92565906,0.0010032993,0.008394423],"study_design_scores_gemma":[0.0018175808,0.00056055083,0.025049895,0.00041570625,0.00007948749,0.0000134714855,0.00038647806,0.001647307,0.0014873203,0.96785986,0.00035188123,0.00033044835],"about_ca_topic_score_codex":0.00010122991,"about_ca_topic_score_gemma":0.00016276025,"teacher_disagreement_score":0.11922528,"about_ca_system_score_codex":0.000067623936,"about_ca_system_score_gemma":0.00008154057,"threshold_uncertainty_score":0.7543173},"labels":[],"label_agreement":null},{"id":"W2910054248","doi":"10.1002/pds.4708","title":"Extreme restriction design as a method for reducing confounding by indication in pharmacoepidemiologic research","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"University of Manitoba; Manitoba Health; University of British Columbia; McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research; Pfizer; McGill University; Amgen","keywords":"Medicine; Confounding; Propensity score matching; Hazard ratio; Cohort study; Confidence interval; Internal medicine; Proportional hazards model; Population; Observational study; Cohort; Environmental health","score_opus":0.456338404685651,"score_gpt":0.5781146390572948,"score_spread":0.12177623437164375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910054248","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":[0.076224856,0.0009930391,0.91357577,0.004181371,0.00029104622,0.0029228006,0.000024302735,0.0003000137,0.0014867708],"genre_scores_gemma":[0.53863984,0.004759904,0.45340714,0.00137945,0.0001679606,0.00090625486,0.00006893747,0.000057917023,0.0006126309],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891122,0.007901257,0.0011208489,0.00084566907,0.00018050896,0.0008395133],"domain_scores_gemma":[0.941381,0.05751852,0.0004673884,0.0003093651,0.0001663164,0.00015741852],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043889344,0.0002920131,0.00079283904,0.00041859894,0.0002733724,0.000012895287,0.00029610682,0.00029424077,0.00015013441],"category_scores_gemma":[0.017515257,0.0002659492,0.00008179253,0.00045956226,0.00018005451,0.00035030718,0.00013097968,0.0010612065,0.000028464925],"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":[0.0029890118,0.00037200213,0.019178644,0.00058856624,0.00016136377,0.000009219175,0.0015518552,0.0009824523,0.32507637,0.46415642,0.113577105,0.07135701],"study_design_scores_gemma":[0.0018185686,0.00024656922,0.00051659724,0.0001714757,0.0000554058,0.000027181213,0.00041072626,0.046170626,0.022183482,0.9190595,0.008901854,0.0004379733],"about_ca_topic_score_codex":0.00025461696,"about_ca_topic_score_gemma":0.000004805885,"teacher_disagreement_score":0.46241495,"about_ca_system_score_codex":0.00031423874,"about_ca_system_score_gemma":0.000099353805,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W2911416111","doi":"10.1136/bmjebm-2018-111069","title":"Causal inference for clinicians","year":2019,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Inference; Causal inference; Psychology; Computer science; Artificial intelligence; Econometrics; Mathematics","score_opus":0.38310932339326553,"score_gpt":0.5368590741435255,"score_spread":0.15374975075025998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911416111","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":[0.06182809,0.0006471072,0.907122,0.018764209,0.001098521,0.006100208,0.000025563117,0.0011780029,0.0032362845],"genre_scores_gemma":[0.8122418,0.00017710114,0.17842782,0.0046340786,0.0009998265,0.00090931804,0.00002463204,0.00009867409,0.0024867489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99726003,0.00013580067,0.0009326602,0.000532308,0.0006118934,0.0005272892],"domain_scores_gemma":[0.9847475,0.013070645,0.00047348117,0.001016879,0.00050100713,0.00019044743],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025014584,0.00034193037,0.0007692828,0.0002030403,0.000073682604,0.000017086964,0.00048044682,0.00020654273,0.00092239474],"category_scores_gemma":[0.022172503,0.00026197097,0.00013067221,0.0003309873,0.0002545741,0.00038117904,0.00006178846,0.0003216556,0.00012596506],"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":[0.0017396545,0.00051348284,0.034875836,0.0043877535,0.00016023061,0.000081535996,0.0011179311,0.00017833029,0.045344085,0.7144293,0.14765911,0.04951271],"study_design_scores_gemma":[0.0042881025,0.006458261,0.0015504012,0.01726535,0.00033256348,0.000020932426,0.00061019225,0.0044600773,0.031403635,0.9084217,0.023936585,0.0012521981],"about_ca_topic_score_codex":0.000050150524,"about_ca_topic_score_gemma":0.00003784749,"teacher_disagreement_score":0.7504137,"about_ca_system_score_codex":0.00014736774,"about_ca_system_score_gemma":0.00040754306,"threshold_uncertainty_score":0.9999909},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","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":"low"}],"label_agreement":"split"},{"id":"W2912071366","doi":"10.1136/bmjopen-2018-024096","title":"Design characteristics and statistical methods used in interrupted time series studies evaluating public health interventions: protocol for a review","year":2019,"lang":"en","type":"review","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council; Monash University","keywords":"Medicine; Research design; Clinical study design; Observational study; Public health; Psychological intervention; Sample size determination; Interrupted Time Series Analysis; Protocol (science); Interrupted time series; Stratified sampling; Sample (material); Data science; Management science; Computer science; Statistics; Alternative medicine; Clinical trial; Engineering; Nursing","score_opus":0.9469505657783722,"score_gpt":0.779869026220801,"score_spread":0.1670815395575712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912071366","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8020601e-9,0.25512904,0.3136237,0.00013654892,0.000021080376,0.4309221,0.00008322418,0.00006250131,0.000021819336],"genre_scores_gemma":[4.450422e-10,0.26261398,0.36996278,0.000049704548,0.000011547654,0.3670398,0.00005155156,0.000045604138,0.00022503574],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9898665,0.005648197,0.0030817157,0.0006668445,0.00025900497,0.0004777401],"domain_scores_gemma":[0.98931646,0.006786163,0.0026193303,0.0007889933,0.0003791373,0.00010991474],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02445023,0.0005746709,0.0054241354,0.00022029689,0.00009141449,0.00023178138,0.00074422645,0.00018140847,0.0001409093],"category_scores_gemma":[0.030725699,0.0004376477,0.00023735005,0.00031416636,0.000117566364,0.00047313023,0.0012164372,0.0004296865,0.000018183664],"study_design_candidate":"systematic_review","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":[0.00002049611,0.000055134144,2.5113792e-7,0.37142888,0.000121828234,0.000001585847,0.00010970294,4.660869e-9,1.0396156e-7,0.003706378,0.0021062614,0.6224494],"study_design_scores_gemma":[0.0005412267,0.001407035,6.23602e-7,0.6636161,0.00042575152,0.000047945654,0.000059614234,0.00009213034,5.8974837e-7,0.050603107,0.28260556,0.0006003166],"about_ca_topic_score_codex":0.0000036267934,"about_ca_topic_score_gemma":0.000006509945,"teacher_disagreement_score":0.62184906,"about_ca_system_score_codex":0.00046613143,"about_ca_system_score_gemma":0.0011817717,"threshold_uncertainty_score":0.99980754},"labels":[],"label_agreement":null},{"id":"W2912909587","doi":"10.2139/ssrn.1133595","title":"Assessing Racial Discrimination in Parole Release in the U.S.: An Approach Based on Outcome Tests","year":2008,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Dalhousie University; HEC Montréal","funders":"","keywords":"Outcome (game theory); Psychology; Criminology; Political science; Social psychology; Economics; Mathematical economics","score_opus":0.2069318959140339,"score_gpt":0.4347749968915277,"score_spread":0.2278431009774938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912909587","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":[0.8597067,0.000056653374,0.13765806,0.00044379762,0.000026393498,0.00027734085,6.514034e-7,0.000069544774,0.0017608696],"genre_scores_gemma":[0.99052536,0.00005772414,0.009005217,0.00021778933,0.00009187985,0.000033948334,0.000005911524,0.000026811984,0.000035380195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737036,0.00040416187,0.0004679785,0.00020349544,0.00041729677,0.001136713],"domain_scores_gemma":[0.99910414,0.00030154042,0.00021711738,0.00027396795,0.000059732087,0.000043499393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030430863,0.00017853141,0.00022606686,0.00025995864,0.00017742696,0.000064072476,0.0003425863,0.00009722025,0.000004588618],"category_scores_gemma":[0.00094898354,0.00012702998,0.000061493476,0.00032049042,0.00005483509,0.00065893494,0.000014641995,0.00229134,0.0000020627253],"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":[0.0002956149,0.0044170776,0.08648485,0.00007010044,0.000023896704,0.000195621,0.0060503534,0.0026458243,0.0012184553,0.8408733,0.00007411391,0.05765082],"study_design_scores_gemma":[0.00091030385,0.00042389444,0.023084247,0.00006128812,0.000015800084,0.00029955732,0.003875983,0.010236347,0.00018952672,0.96061784,0.00001820728,0.00026700567],"about_ca_topic_score_codex":0.00003604137,"about_ca_topic_score_gemma":0.00070995535,"teacher_disagreement_score":0.13081865,"about_ca_system_score_codex":0.0010119975,"about_ca_system_score_gemma":0.00074045756,"threshold_uncertainty_score":0.99548596},"labels":[],"label_agreement":null},{"id":"W2913795110","doi":"","title":"My Friend Far Far Away: Asymptotic Properties of Pairwise Stable Networks","year":2013,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; University of Cambridge; Université Laval","keywords":"Pairwise comparison; Homophily; Estimator; Set (abstract data type); Computer science; Mathematics; Mathematical optimization; Theoretical computer science; Statistics; Combinatorics; Artificial intelligence","score_opus":0.13140597674026105,"score_gpt":0.3698184686459345,"score_spread":0.23841249190567343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913795110","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":[0.88903356,0.0021461388,0.0047687404,0.0004396694,0.00075719255,0.008304058,0.00015186601,0.00093525037,0.093463525],"genre_scores_gemma":[0.95160383,0.017964622,0.024812477,0.000060839633,0.00021945522,0.0015266864,0.000041918196,0.00026388324,0.0035063038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99538994,0.00045131918,0.0013877017,0.001071044,0.0004418133,0.0012582076],"domain_scores_gemma":[0.9954907,0.0010821847,0.0005925511,0.0021376857,0.00045548193,0.00024143292],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002435703,0.00057875336,0.0012662396,0.00055080163,0.0001346313,0.00015352295,0.0012851339,0.00086960394,0.00023805752],"category_scores_gemma":[0.0021871075,0.000552828,0.00024556855,0.00018585085,0.0007656954,0.00029221817,0.0023345957,0.0026825133,0.000014846275],"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":[0.00082855136,0.0032300442,0.0072494387,0.012033485,0.0017031762,0.00014814967,0.0080299135,0.13004798,0.0070146266,0.18598303,0.004025314,0.6397063],"study_design_scores_gemma":[0.0018495615,0.0010261473,0.0007063274,0.0064613107,0.00013047292,0.00003381248,0.0061128894,0.22492065,0.025073756,0.6956677,0.03413783,0.003879588],"about_ca_topic_score_codex":0.00026126465,"about_ca_topic_score_gemma":0.0002342059,"teacher_disagreement_score":0.6358267,"about_ca_system_score_codex":0.0011422413,"about_ca_system_score_gemma":0.0006521937,"threshold_uncertainty_score":0.9996923},"labels":[],"label_agreement":null},{"id":"W2913892683","doi":"10.1513/annalsats.201901-070le","title":"Reply: More on Causal Inference Studies","year":2019,"lang":"en","type":"letter","venue":"Annals of the American Thoracic Society","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":"Université de Montréal; Western University","funders":"","keywords":"Medicine; Causal inference; Inference; MEDLINE; Intensive care medicine; Artificial intelligence; Pathology","score_opus":0.42315660559657453,"score_gpt":0.5451764451784764,"score_spread":0.12201983958190188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913892683","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":[0.021900002,0.000523009,0.0011592044,0.97265196,0.00048773817,0.0012353365,0.00026208212,0.00060189806,0.0011787685],"genre_scores_gemma":[0.0074997195,0.0020240506,0.0133136315,0.9716757,0.00090537965,0.00012002241,0.000022288126,0.00016638616,0.0042728246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966119,0.00037939948,0.000711519,0.0006713374,0.0009732386,0.0006525836],"domain_scores_gemma":[0.9903412,0.004074163,0.0024285465,0.0024607475,0.0006562392,0.000039131748],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00073544803,0.0006528112,0.0015718542,0.00006720808,0.00014115561,0.000027234486,0.0013541513,0.00032561133,0.000019362675],"category_scores_gemma":[0.002635431,0.00043787362,0.0010196391,0.00059363694,0.0018387387,0.000117495314,0.0006454211,0.002413335,0.000028691242],"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":[0.00002183168,0.000040451396,0.00013087782,0.00049425755,0.0005365977,0.0000074833865,0.0010517631,0.000005279997,0.00007483722,0.00040274402,0.99375916,0.003474706],"study_design_scores_gemma":[0.00015935514,0.001231625,0.00039769654,0.0035498505,0.00051650504,0.000017682438,0.0037942554,0.00005939165,0.028135711,0.33474764,0.6254271,0.0019631272],"about_ca_topic_score_codex":0.00008232454,"about_ca_topic_score_gemma":0.000001698439,"teacher_disagreement_score":0.36833203,"about_ca_system_score_codex":0.000111484216,"about_ca_system_score_gemma":0.00017218727,"threshold_uncertainty_score":0.9998881},"labels":[],"label_agreement":null},{"id":"W2914109878","doi":"10.1289/isee.2014.p1-263","title":"Case: Control Matching Strategies on Associations between Cellular Telephone Use and Glioma Risk in the INTERPHONE Study","year":2014,"lang":"en","type":"article","venue":"ISEE Conference Abstracts","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":true,"ca_institutions":"Université de Montréal; Université du Québec; BC Cancer Agency; University of Ottawa","funders":"","keywords":"Library science; Agency (philosophy); History; Sociology; Computer science; Social science","score_opus":0.1253507366700997,"score_gpt":0.36936287307082266,"score_spread":0.24401213640072297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914109878","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":[0.9697596,0.000008034171,0.028234106,0.000109837296,0.00003723543,0.00092441624,0.0001032476,0.00017577858,0.0006477677],"genre_scores_gemma":[0.99796695,0.000006956084,0.0017627578,0.000059947506,0.00007327773,0.000079517595,0.000008510174,0.000029259583,0.00001280378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765867,0.00059685356,0.00064034516,0.00037521342,0.00035719364,0.00037171913],"domain_scores_gemma":[0.99299866,0.0057326057,0.00047643724,0.0005582635,0.00015263485,0.00008138444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018943504,0.00030475642,0.0004891016,0.00017183519,0.0002113197,0.00048745683,0.00031167013,0.00014884632,0.000020365227],"category_scores_gemma":[0.0018994285,0.00023251283,0.00004810893,0.00019127181,0.00010023781,0.0006533482,0.000058516718,0.0007149299,0.000018361656],"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":[0.00063954137,0.010580247,0.18125771,0.00051141693,0.0019397008,0.013852612,0.2074634,0.01155328,0.056022655,0.45315242,0.0016161111,0.06141089],"study_design_scores_gemma":[0.0019017145,0.0008801788,0.47547147,0.00019450313,0.00023289393,0.00009907299,0.014448553,0.00012341495,0.0026064825,0.5033752,0.000033400935,0.0006331332],"about_ca_topic_score_codex":0.0013571129,"about_ca_topic_score_gemma":0.002526158,"teacher_disagreement_score":0.29421377,"about_ca_system_score_codex":0.00006450806,"about_ca_system_score_gemma":0.0000548997,"threshold_uncertainty_score":0.9481598},"labels":[],"label_agreement":null},{"id":"W2914649162","doi":"10.4324/9781315755649-2","title":"Analysis of Variance","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Manitoba","funders":"","keywords":"Observational study; Repeated measures design; Variance (accounting); Research design; Statistics; Sample size determination; Analysis of variance; Clinical study design; Psychology; Design of experiments; Sample (material); Econometrics; Variable (mathematics); Mathematics; Computer science; Medicine; Clinical trial","score_opus":0.17167256795051344,"score_gpt":0.4059815696570885,"score_spread":0.23430900170657504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914649162","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007697325,0.000020348149,0.22964516,0.0000087803155,0.000020870479,0.000105629566,0.000034902485,0.00019059534,0.769966],"genre_scores_gemma":[0.0006661942,0.000057917634,0.15226391,0.000045340876,0.00004804918,0.000005373974,0.000017934177,0.000041756695,0.84685355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990078,0.0000059830904,0.0004163732,0.000239012,0.0002195709,0.00011122334],"domain_scores_gemma":[0.9983061,0.00026457128,0.00040970155,0.000740334,0.0002441792,0.000035115947],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015567584,0.00021291203,0.00071971724,0.0003488219,0.000013657226,0.0000056384365,0.00023478798,0.00028020563,0.018322885],"category_scores_gemma":[0.000108345455,0.00018270066,0.00026028775,0.00008859941,0.00013746931,0.000044944398,0.0000857673,0.00014108435,0.00006977831],"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":[0.000002748981,0.00000783432,0.0000031477846,0.000031792504,0.0008764621,0.0000017907138,0.000034244305,2.9088372e-7,0.000034332515,0.9932449,0.0051965187,0.00056592474],"study_design_scores_gemma":[0.000021747603,0.00004698053,0.0000029124365,0.00007226998,0.0015835946,4.955631e-7,0.000002756371,0.000060992366,0.00073420774,0.9729003,0.024383066,0.00019069934],"about_ca_topic_score_codex":0.000005069169,"about_ca_topic_score_gemma":0.000053482774,"teacher_disagreement_score":0.07738126,"about_ca_system_score_codex":0.0000408443,"about_ca_system_score_gemma":0.000027196253,"threshold_uncertainty_score":0.9825745},"labels":[],"label_agreement":null},{"id":"W2915065822","doi":"10.1007/s40471-019-0180-5","title":"Immortal Time Bias in Epidemiology","year":2019,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":47,"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 British Columbia; McGill University; Jewish General Hospital; McGill University Health Centre","funders":"","keywords":"Epidemiology; Context (archaeology); Pharmacoepidemiology; Medicine; Pathology; Biology; Pharmacology","score_opus":0.45766667753120593,"score_gpt":0.5141528458328342,"score_spread":0.056486168301628226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915065822","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":[0.9761837,0.0031758184,0.00989285,0.0010763375,0.0019549876,0.0012939995,0.000007944757,0.0007526179,0.005661742],"genre_scores_gemma":[0.9645037,0.00029001624,0.03290696,0.0005930429,0.00024611945,0.00025058415,0.0001089399,0.000082983584,0.0010176632],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930895,0.0018007087,0.0028459402,0.0010426182,0.0001188248,0.001102436],"domain_scores_gemma":[0.9830673,0.013740892,0.0016250215,0.001275827,0.00009834069,0.00019265662],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012155114,0.0004216154,0.0019932878,0.00027965606,0.000039875147,0.0000026873734,0.0002649176,0.00044316487,0.00081450824],"category_scores_gemma":[0.049397755,0.00035773768,0.00026966928,0.0002663641,0.00026237703,0.00019232818,0.00022994992,0.00090583396,0.0004059419],"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":[0.000016959479,0.00014415212,0.90967816,0.00009025387,0.000025082447,0.000115091905,0.00004727661,0.000109605884,0.00019518092,0.07310773,0.010872907,0.0055975937],"study_design_scores_gemma":[0.00016993147,0.000113883354,0.029546104,0.000173054,0.000020947962,0.0005490571,0.000010312234,0.0017377392,0.00010691879,0.95962435,0.007542963,0.00040474455],"about_ca_topic_score_codex":0.00004167317,"about_ca_topic_score_gemma":0.000011503206,"teacher_disagreement_score":0.88651663,"about_ca_system_score_codex":0.00017569057,"about_ca_system_score_gemma":0.00009120487,"threshold_uncertainty_score":0.99988747},"labels":[],"label_agreement":null},{"id":"W2915181725","doi":"10.48550/arxiv.1902.07343","title":"Estimation and Inference for Synthetic Control Methods with Spillover Effects","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Booth University College","funders":"","keywords":"Spillover effect; Estimator; Inference; Econometrics; Estimation; Control (management); Computer science; Statistics; Mathematics; Economics; Artificial intelligence","score_opus":0.15216136572999706,"score_gpt":0.33093074034018455,"score_spread":0.1787693746101875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915181725","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":[0.09358088,0.000028776865,0.90352535,0.000018287847,0.00008691339,0.0017095977,0.000025263575,0.00028140197,0.0007435429],"genre_scores_gemma":[0.77505285,0.00003438169,0.22446978,0.000032441327,0.000013792138,0.000014472883,0.000007460629,0.00003761715,0.00033720498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859196,0.00018215684,0.00018231594,0.00070742646,0.00006311504,0.00027301206],"domain_scores_gemma":[0.99531704,0.0033237787,0.00036110755,0.00072479376,0.00018221767,0.00009106879],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040759533,0.00036586422,0.0005942292,0.00016169579,0.000067983194,0.00004505518,0.0003003767,0.00032208016,0.00001080726],"category_scores_gemma":[0.0008907677,0.00034275727,0.0000886002,0.00012581379,0.00015697032,0.00020754141,0.00026423426,0.00038219002,0.0000066486173],"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":[0.00035419528,0.00011661675,0.0013361438,0.0027792212,0.0002876086,0.00003648109,0.00016161574,0.050277222,0.00049108156,0.93500125,0.00007801359,0.009080574],"study_design_scores_gemma":[0.00078833854,0.00024635662,0.00013180946,0.00054160954,0.00041158087,0.0000030206083,0.000016986409,0.32506028,0.0021717225,0.67018974,0.00004233577,0.00039625785],"about_ca_topic_score_codex":0.000017308297,"about_ca_topic_score_gemma":0.0000075985527,"teacher_disagreement_score":0.68147194,"about_ca_system_score_codex":0.00015252442,"about_ca_system_score_gemma":0.00009979805,"threshold_uncertainty_score":0.9999024},"labels":[],"label_agreement":null},{"id":"W2918520331","doi":"10.1002/cjs.11490","title":"When exposure is subject to nondifferential misclassification, are validation data helpful in testing for an exposure–disease association?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":true,"ca_institutions":"Centre for Advancing Health Outcomes; Providence Health Care; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Variable (mathematics); Statistics; Surrogate endpoint; Disease; Research design; Variables; Clinical study design; Medicine; Econometrics; Computer science; Mathematics; Clinical trial; Pathology","score_opus":0.22232079577962238,"score_gpt":0.378983718950411,"score_spread":0.15666292317078861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918520331","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":[0.38552836,0.00005583964,0.6037573,0.0012267178,0.00048174628,0.0011218217,0.0076785395,0.00003716114,0.00011249994],"genre_scores_gemma":[0.7012986,0.0000023647226,0.2977944,0.00019322957,0.0001556541,0.000014020816,0.00021515782,0.000038663056,0.00028789055],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982879,0.00010634675,0.0007054292,0.0002475881,0.00031243343,0.00034031132],"domain_scores_gemma":[0.99596745,0.0009082579,0.0008164525,0.0005433006,0.0011749227,0.0005895934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008720829,0.0001649361,0.00031832096,0.00033607098,0.00008656376,0.00013736787,0.0005418571,0.00009655248,0.0001409567],"category_scores_gemma":[0.008394836,0.00017545323,0.000029085308,0.00019343183,0.000018677143,0.0004535988,0.000024830159,0.0002193253,0.000009358039],"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":[0.00010924534,0.00015723605,0.8507121,0.00037437544,0.00009869759,0.000062221436,0.003402254,0.00013341686,0.001610489,0.016467715,0.11892258,0.007949651],"study_design_scores_gemma":[0.0022990787,0.0016654249,0.2742557,0.0010012101,0.0003577846,0.000024611836,0.0018584072,0.0043926714,0.0016452849,0.7047157,0.00670695,0.0010771207],"about_ca_topic_score_codex":0.00040552687,"about_ca_topic_score_gemma":0.01332685,"teacher_disagreement_score":0.68824804,"about_ca_system_score_codex":0.0005947306,"about_ca_system_score_gemma":0.0011615532,"threshold_uncertainty_score":0.99995786},"labels":[],"label_agreement":null},{"id":"W2920887687","doi":"10.1093/aje/kwy280","title":"A Future for Observational Epidemiology: Clarity, Credibility, Transparency","year":2018,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":30,"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":"Observational study; Epidemiology; CLARITY; Credibility; Transparency (behavior); Psychological intervention; Medicine; Causal inference; Population; Environmental health; Computer science; Pathology; Psychiatry; Biology","score_opus":0.45769032009790966,"score_gpt":0.5216762008091765,"score_spread":0.06398588071126687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920887687","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":[0.09634319,0.00035473474,0.88164324,0.020313738,0.0006206014,0.00030918294,0.00005036313,0.00008755892,0.00027738098],"genre_scores_gemma":[0.2321302,0.00020903998,0.75994515,0.005136382,0.0024528282,0.00004959051,0.000010620439,0.000032002845,0.000034176675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99452335,0.0019004967,0.0023858114,0.00038073215,0.00013056015,0.00067904626],"domain_scores_gemma":[0.96576476,0.02965064,0.0027864887,0.0004958791,0.0010463034,0.0002559381],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013287928,0.00028162086,0.001867929,0.0001775444,0.00012886286,0.0000030803276,0.00062824145,0.00023731102,0.00017509404],"category_scores_gemma":[0.051996652,0.00021700127,0.00044469722,0.00028293597,0.0018255477,0.00022034385,0.000059142305,0.0006292797,0.000005089624],"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":[0.00053154904,0.00018503278,0.14751211,0.00005613771,0.00020600625,0.0000048087036,0.0003077882,0.000014342424,0.00026721947,0.76745653,0.046115562,0.03734288],"study_design_scores_gemma":[0.00032439738,0.003498533,0.02304215,0.00005508409,0.00008015497,0.00016608491,0.00017632359,0.0002779449,0.00009096762,0.94775176,0.02433563,0.00020097775],"about_ca_topic_score_codex":0.000034363933,"about_ca_topic_score_gemma":0.000055591412,"teacher_disagreement_score":0.1802952,"about_ca_system_score_codex":0.00013942491,"about_ca_system_score_gemma":0.00020968463,"threshold_uncertainty_score":0.95598876},"labels":[],"label_agreement":null},{"id":"W2921058067","doi":"10.5539/mas.v13n4p40","title":"A Weighted Covariate Balancing Method of Estimating Causal Effects in Case-Control Studies","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Observational study; Mahalanobis distance; Statistics; Weighting; Computer science; Econometrics; Mathematics; Propensity score matching; Monte Carlo method; Rank (graph theory); Medicine","score_opus":0.08025093776596098,"score_gpt":0.41369464480832424,"score_spread":0.33344370704236326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921058067","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":[0.1983541,0.000039458613,0.7998121,0.00001417818,0.00008090774,0.0007624567,0.00000274539,0.00014371125,0.00079036667],"genre_scores_gemma":[0.53481907,5.0757006e-7,0.4650595,0.000028914561,0.00000807653,0.000060994094,1.12385415e-7,0.000011578856,0.0000112370635],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804986,0.000076770586,0.00046311782,0.00049936696,0.00044746092,0.00046340207],"domain_scores_gemma":[0.99674964,0.002261075,0.0002918721,0.00047596474,0.00015823198,0.000063198255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027448342,0.00021116063,0.0005992919,0.00025227186,0.000102585174,0.000028943778,0.0003417845,0.000067364235,0.0000064452147],"category_scores_gemma":[0.0010069492,0.0001799175,0.000034106182,0.0006677581,0.00023927273,0.00026392,0.00017655261,0.00023442991,0.0000074402046],"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":[0.000031242016,0.000062139945,0.00056364934,0.00043034717,0.000027043572,0.00009009051,0.0039642532,0.001733807,0.85344434,0.12751655,0.000006425305,0.01213009],"study_design_scores_gemma":[0.00046861623,0.00004446025,0.00009807897,0.00014104503,0.000019466326,0.000054995257,0.00015858325,0.50802267,0.047840595,0.4429991,3.528556e-7,0.00015202673],"about_ca_topic_score_codex":0.000033473403,"about_ca_topic_score_gemma":0.000025658923,"teacher_disagreement_score":0.80560374,"about_ca_system_score_codex":0.00019632798,"about_ca_system_score_gemma":0.00010835009,"threshold_uncertainty_score":0.7336823},"labels":[],"label_agreement":null},{"id":"W2921476564","doi":"10.1002/sim.8132","title":"A test for the correct specification of marginal structural models","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Université Laval; The Quebec Population Health Research Network","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation du CHUM","keywords":"Marginal structural model; Inverse probability; Computer science; Estimator; Econometrics; Outcome (game theory); Confounding; Statistics; Causal model; Mathematics; Bayesian probability; Posterior probability","score_opus":0.14322652898192254,"score_gpt":0.43763620167038475,"score_spread":0.2944096726884622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921476564","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":[0.004598652,0.000057962035,0.99262446,0.00015854002,0.00017922364,0.0007133747,0.00012582027,0.000027493512,0.0015144958],"genre_scores_gemma":[0.6003874,0.000040327883,0.3991096,0.000039349346,0.000064378895,0.000026648308,0.000023962057,0.000014787921,0.00029356536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991457,0.000015809395,0.0003573952,0.000118922515,0.00021548127,0.00014668232],"domain_scores_gemma":[0.99332535,0.0060129617,0.00018821003,0.00027801655,0.0001753538,0.000020122761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006120349,0.00009182165,0.00022985524,0.00006961256,0.000019669298,0.0000025176175,0.0001649659,0.000038202903,0.00013444114],"category_scores_gemma":[0.0020250594,0.000057793222,0.000012559815,0.0001208029,0.00015138803,0.0000413263,0.000019176792,0.00013472102,0.0000015466587],"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":[0.00004773906,0.000014791609,0.00091203256,0.00014117188,0.0000069583366,0.000001005645,0.0006118622,0.000065456494,0.002149118,0.9845564,0.0036105237,0.007882976],"study_design_scores_gemma":[0.0004212525,0.00026725882,0.0010776997,0.00011514956,0.0000218586,0.0000033152132,0.00049166655,0.046359062,0.001115285,0.94989413,0.0001665446,0.00006680133],"about_ca_topic_score_codex":0.000027036096,"about_ca_topic_score_gemma":0.000042731343,"teacher_disagreement_score":0.5957887,"about_ca_system_score_codex":0.0000495966,"about_ca_system_score_gemma":0.000023616882,"threshold_uncertainty_score":0.24243316},"labels":[],"label_agreement":null},{"id":"W2921943956","doi":"10.1002/sim.8121","title":"Bayesian estimation of the average treatment effect on the treated using inverse weighting","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Vanderbilt University","keywords":"Confounding; Statistics; Marginal structural model; Context (archaeology); Bayesian probability; Weighting; Posterior probability; Inverse probability; Econometrics; Estimation; Sample size determination; Average treatment effect; Inverse probability weighting; Marginal likelihood; Mathematics; Computer science; Medicine; Propensity score matching; Economics","score_opus":0.06999270852247445,"score_gpt":0.4013656679853423,"score_spread":0.3313729594628678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921943956","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":[0.7370871,0.000011303437,0.25857228,0.00019035139,0.000145477,0.001240707,0.00005318046,0.000052721625,0.0026469256],"genre_scores_gemma":[0.9428543,0.000008496715,0.056851145,0.000074668336,0.000023934132,0.000018939778,0.0000124568305,0.000019563124,0.00013649193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989089,0.00021441207,0.00032339443,0.0001359486,0.00027348418,0.00014388483],"domain_scores_gemma":[0.9963242,0.002980392,0.00022911892,0.00040434444,0.000040119376,0.000021823938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053626695,0.00015751408,0.00030326823,0.00007201183,0.000050061935,0.0000042754177,0.0001413995,0.000047724843,0.00018352299],"category_scores_gemma":[0.00165445,0.00007075814,0.000023947268,0.00020861463,0.00013275207,0.000028676346,0.000027764274,0.00015312279,0.0000039565725],"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":[0.0002115603,0.00029823376,0.015452353,0.0006258549,0.00016799447,0.000049474405,0.007002827,0.0072336956,0.027194133,0.8987626,0.0018074131,0.04119388],"study_design_scores_gemma":[0.0016736015,0.002029034,0.0010270971,0.0018096413,0.00018508719,0.000008053805,0.00029015966,0.34909418,0.056478586,0.587155,0.000042860534,0.00020672021],"about_ca_topic_score_codex":0.00015791987,"about_ca_topic_score_gemma":0.00005813417,"teacher_disagreement_score":0.34186047,"about_ca_system_score_codex":0.00020008071,"about_ca_system_score_gemma":0.000024911935,"threshold_uncertainty_score":0.2885433},"labels":[],"label_agreement":null},{"id":"W2927518299","doi":"10.1007/s43441-019-00061-x","title":"Choosing Estimands in Clinical Trials: Putting the ICH E9(R1) Into Practice","year":2020,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Generalizability theory; Clinical trial; Psychology; Causal inference; Management science; Medical education; Medicine","score_opus":0.5758803589607833,"score_gpt":0.5856898343720771,"score_spread":0.009809475411293844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2927518299","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":[0.5466914,0.00021684877,0.41279104,0.03474186,0.0005151551,0.0015407293,0.000001363432,0.0007284888,0.002773073],"genre_scores_gemma":[0.88898224,0.0000091767315,0.10435019,0.006377676,0.00020004458,0.00003236815,0.0000011274616,0.000023048628,0.000024115241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954539,0.0009007247,0.0018455525,0.000558808,0.0008481397,0.00039286926],"domain_scores_gemma":[0.9926205,0.0045540542,0.0012562501,0.0006600938,0.0008292894,0.00007979347],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03536164,0.00021332946,0.00046119952,0.0002612498,0.00039819788,0.00018526582,0.00082031457,0.00012475361,0.000031871772],"category_scores_gemma":[0.035240993,0.00015391433,0.00006264205,0.004774657,0.0010017138,0.0013534316,0.00017968663,0.0006815781,0.00001601032],"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":[0.0000881728,0.000093664385,0.0011705911,0.000030875097,0.000020055175,0.0000037912705,0.003277313,0.000054338474,0.050504163,0.6770023,0.00022838412,0.26752636],"study_design_scores_gemma":[0.0009888692,0.00039629306,0.011234181,0.00018938562,0.00007346073,0.000022288492,0.0020506242,0.023740586,0.022435755,0.92904437,0.009332173,0.0004920014],"about_ca_topic_score_codex":0.000007731719,"about_ca_topic_score_gemma":0.000002937383,"teacher_disagreement_score":0.34229082,"about_ca_system_score_codex":0.00019481014,"about_ca_system_score_gemma":0.00054820656,"threshold_uncertainty_score":0.9932982},"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":"W2938511274","doi":"10.1002/sim.8162","title":"One‐step validation method for surrogate endpoints using data from multiple randomized cancer clinical trials with failure‐time endpoints","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"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":"Secrétariat Général pour les Affaires Régionales, Etat en Région Aquitaine; Institute of Cancer Research; Institut National de la Santé et de la Recherche Médicale; Institut National Du Cancer; Association pour la Recherche sur le Cancer","keywords":"Surrogate endpoint; Context (archaeology); Estimator; Statistics; Clinical trial; Computer science; Random effects model; Medicine; Mathematics; Meta-analysis; Internal medicine","score_opus":0.5056720796718315,"score_gpt":0.5934294578687577,"score_spread":0.0877573781969262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938511274","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":[0.008674682,0.00006543881,0.98321193,0.0002588361,0.00036523913,0.0037530356,0.0034531339,0.000117483716,0.00010018657],"genre_scores_gemma":[0.009027208,0.00014624234,0.98827046,0.00014100746,0.0003703814,0.00017962439,0.0016350873,0.000081272316,0.000148707],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99316514,0.0027091394,0.0023809366,0.0007614055,0.00059596414,0.0003874288],"domain_scores_gemma":[0.9275372,0.06955206,0.0013660586,0.0010782535,0.00034269594,0.00012370858],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022163842,0.00033612957,0.002905911,0.00016992536,0.00004933805,0.000025383879,0.0005118045,0.00020562031,0.0011935224],"category_scores_gemma":[0.0743396,0.0002497468,0.00007389974,0.00019030688,0.00027239785,0.0002342483,0.00016969896,0.000428399,0.000017897644],"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":[0.32549828,0.0028162913,0.012474903,0.0038952997,0.007217983,0.00017332606,0.0064442195,0.0010041313,0.13839394,0.22446536,0.07344032,0.20417595],"study_design_scores_gemma":[0.14817172,0.00033913465,0.00006276125,0.0017789834,0.0012984836,0.000003050709,0.00024917175,0.33452493,0.005741051,0.50684845,0.00047788772,0.00050436164],"about_ca_topic_score_codex":0.0007644644,"about_ca_topic_score_gemma":0.00075253565,"teacher_disagreement_score":0.3335208,"about_ca_system_score_codex":0.00013887166,"about_ca_system_score_gemma":0.00019030483,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W2939670107","doi":"10.1093/aje/kwz100","title":"Effect Estimates in Randomized Trials and Observational Studies: Comparing Apples With Apples","year":2019,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":115,"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 Hip and Knee Clinic; University of Calgary","funders":"Cilag; National Institute of Allergy and Infectious Diseases; Instituto de Salud Carlos III; National Center for Advancing Translational Sciences; Medical Research Council; University of North Carolina at Chapel Hill; National Institutes of Health; U.S. Department of Defense; Université de Bordeaux; Center for AIDS Research, University of Washington; Uniformed Services University of the Health Sciences; Universiteit van Amsterdam; Gilead Sciences; University of Bristol; Uniwersytet Warszawski; University College London; Harvard T.H. Chan School of Public Health; National Institute for Health and Care Research; Rowan University; Rigshospitalet; National and Kapodistrian University of Athens; Bill and Melinda Gates Foundation; ViiV Healthcare; Universität Basel; Centre Hospitalier Universitaire de Bordeaux; Stichting HIV Monitoring; Warszawski Uniwersytet Medyczny; Harvard University Center for AIDS Research; Harvard University; Yale University; Sorbonne Université; Institut National de la Santé et de la Recherche Médicale; University of Minnesota","keywords":"Observational study; Randomized controlled trial; Medicine; Internal medicine","score_opus":0.4249577462813197,"score_gpt":0.5321859369904708,"score_spread":0.10722819070915107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939670107","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":[0.9167379,0.0015161044,0.08047653,0.00054705434,0.000049217986,0.0005917512,0.0000015249271,0.000027843638,0.00005203103],"genre_scores_gemma":[0.72840565,0.0005712792,0.2707321,0.00018787199,0.000041748008,0.0000419884,0.0000014595838,0.000013761429,0.000004150479],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934264,0.004239902,0.0017755023,0.00018395617,0.00011524443,0.0002590272],"domain_scores_gemma":[0.8023826,0.1944261,0.002805879,0.00015819617,0.00015784771,0.0000694055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028749196,0.00021008699,0.0055406024,0.0001874483,0.000024225921,0.0000050802155,0.00015190062,0.000045800665,0.000013186543],"category_scores_gemma":[0.08452943,0.00011907315,0.00016307701,0.00015747074,0.00081299874,0.00013160503,0.00005116058,0.00030076306,0.0000013135075],"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":[0.02346482,0.00007193026,0.80860573,0.00023797918,0.0012311813,0.000015380818,0.00068651594,0.0012915212,0.0008829699,0.15098073,0.00040059755,0.012130661],"study_design_scores_gemma":[0.05856125,0.004686662,0.01029998,0.0014369918,0.00059132226,0.00038845825,0.0015727573,0.0024410465,0.0011114114,0.91827226,0.00014590826,0.00049197447],"about_ca_topic_score_codex":0.00003255494,"about_ca_topic_score_gemma":0.000017104823,"teacher_disagreement_score":0.79830575,"about_ca_system_score_codex":0.00006416466,"about_ca_system_score_gemma":0.00004517345,"threshold_uncertainty_score":0.99639547},"labels":[],"label_agreement":null},{"id":"W2939937326","doi":"10.1017/s026646662200024x","title":"A DECOMPOSITION ANALYSIS OF DIFFUSION OVER A LARGE NETWORK","year":2022,"lang":"en","type":"article","venue":"Econometric Theory","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 British Columbia","funders":"","keywords":"Diffusion; Inference; Mathematics; Covariate; Measure (data warehouse); Decomposition; Econometrics; Statistics; Diffusion process; Preprint; Statistical physics; Computer science; Data mining; Innovation diffusion; Artificial intelligence","score_opus":0.050236692760370495,"score_gpt":0.37410826264417407,"score_spread":0.32387156988380356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939937326","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":[0.81453204,0.00032955178,0.17725661,0.000012418919,0.000084396655,0.00020244879,0.00010201763,0.00014564247,0.007334855],"genre_scores_gemma":[0.99268204,0.000022276108,0.0068057175,0.00009154317,0.000029905095,0.00007056456,0.000038916158,0.000016413385,0.00024261854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893194,0.00020667493,0.0003420007,0.00018853633,0.00012771442,0.00020314133],"domain_scores_gemma":[0.99801123,0.0012763096,0.0003002518,0.00035014848,0.000024032277,0.000038036254],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013717985,0.00009888974,0.0003558685,0.0012759204,0.00013524765,0.000008118952,0.00020121092,0.000032785847,0.00731634],"category_scores_gemma":[0.00021907038,0.000102440164,0.0001893353,0.0041260496,0.000024213434,0.000092084316,0.00026822672,0.00014018953,0.000003490893],"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":[0.00005006912,0.0002564218,0.0059644748,0.00001058119,0.0003886419,0.0000021525782,0.00020665071,0.0006376722,0.000081181985,0.98780227,0.00057478395,0.0040251194],"study_design_scores_gemma":[0.00025297233,0.00014069036,0.011851133,0.000005874111,0.00047993,0.0000016705238,0.0002511676,0.0042537423,0.00016388462,0.98091877,0.0015001015,0.00018009346],"about_ca_topic_score_codex":0.0000057514962,"about_ca_topic_score_gemma":0.000006956587,"teacher_disagreement_score":0.17815,"about_ca_system_score_codex":0.00023120029,"about_ca_system_score_gemma":0.0000127128405,"threshold_uncertainty_score":0.9935911},"labels":[],"label_agreement":null},{"id":"W2943292425","doi":"10.30834/kjp.31.1.2018.153","title":"Common errors in reporting of statistical analyses","year":2019,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Computer science; Econometrics; Statistics; Mathematics","score_opus":0.6765648551574031,"score_gpt":0.696991294786385,"score_spread":0.02042643962898194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943292425","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":[0.98011136,0.0009328746,0.010030324,0.00003188969,0.00012419993,0.0005712773,0.00003342056,0.00006492829,0.00809972],"genre_scores_gemma":[0.97761357,0.0005491721,0.02156264,0.000047387213,0.000023762528,0.000022751301,0.000008038901,0.00004962449,0.00012308096],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950557,0.00030118827,0.0032170198,0.0003650732,0.0006988668,0.00036215328],"domain_scores_gemma":[0.9921809,0.0017147744,0.0049442644,0.00069933827,0.00032269224,0.00013803778],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029582987,0.0002810584,0.0015866574,0.0008015208,0.000051364637,0.00019159152,0.0015671952,0.00012777213,0.005984484],"category_scores_gemma":[0.0050460813,0.00024751003,0.00015467484,0.0009013546,0.00014541479,0.0014030904,0.0007550433,0.00052708137,0.0000072793587],"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":[0.00011057603,0.0003333396,0.8212739,0.00034090065,0.00010966097,0.000087495166,0.00019269923,0.00016095595,0.16210234,0.006662762,0.003967122,0.0046582026],"study_design_scores_gemma":[0.00031719243,0.000026355923,0.35298577,0.001112331,0.000078240366,0.000018714549,0.00021936724,0.00027754522,0.14868997,0.49569893,0.00018730671,0.00038831154],"about_ca_topic_score_codex":0.0009769239,"about_ca_topic_score_gemma":0.00016649233,"teacher_disagreement_score":0.48903614,"about_ca_system_score_codex":0.00012092431,"about_ca_system_score_gemma":0.00012125103,"threshold_uncertainty_score":0.99999774},"labels":[],"label_agreement":null},{"id":"W2949045795","doi":"10.1097/ede.0000000000001015","title":"Causal Mediation Analysis for Standardized Mortality Ratios","year":2019,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"","keywords":"Mediation; Estimator; Health care; Causal model; Medicine; Intervention (counseling); Outcome (game theory); Standardized mortality ratio; Econometrics; Psychology; Statistics; Cancer; Internal medicine; Nursing; Mathematics","score_opus":0.2800238229706258,"score_gpt":0.5032093866688059,"score_spread":0.2231855636981801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949045795","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":[0.19840597,0.000029110151,0.79949087,0.00045434656,0.00016449994,0.00060721027,0.00006139308,0.00022204043,0.0005645443],"genre_scores_gemma":[0.7871942,0.00002099441,0.21148899,0.00052245415,0.00015144961,0.00013913706,0.00014466236,0.000019770177,0.00031834617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819046,0.00043462723,0.000644593,0.00032686454,0.00009695503,0.0003064717],"domain_scores_gemma":[0.99067026,0.008190101,0.0003851894,0.0004871667,0.00020678467,0.000060472317],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034313204,0.00014454906,0.000862625,0.00013075893,0.000041670577,0.0000038084208,0.00013617943,0.00018693673,0.00038483518],"category_scores_gemma":[0.017267972,0.00012261145,0.0002229714,0.00023222447,0.000057973382,0.00011027499,0.000035578927,0.00012619268,0.000022689877],"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":[0.00006761851,0.00003926317,0.3342063,0.00006459427,0.0007553243,6.569373e-7,0.00014917314,0.00042385547,0.0012526191,0.6546005,0.007817975,0.00062214315],"study_design_scores_gemma":[0.00034541485,0.00012463912,0.018201042,0.0000040744394,0.00025062982,5.375157e-7,0.00003249769,0.0049513956,0.0012114794,0.9729888,0.0017206739,0.00016882754],"about_ca_topic_score_codex":0.0000242651,"about_ca_topic_score_gemma":0.00012608428,"teacher_disagreement_score":0.5887882,"about_ca_system_score_codex":0.00009668799,"about_ca_system_score_gemma":0.000043775482,"threshold_uncertainty_score":0.99101},"labels":[],"label_agreement":null},{"id":"W2949052936","doi":"10.1007/s10654-019-00529-y","title":"A descriptive review of variable selection methods in four epidemiologic journals: there is still room for improvement","year":2019,"lang":"en","type":"review","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; The Quebec Population Health Research Network","funders":"Fonds de Recherche du Québec - Santé; Centre Hospitalier Universitaire de Québec","keywords":"Medicine; Observational study; Univariate; Confounding; Epidemiology; Selection (genetic algorithm); Selection bias; Descriptive statistics; Variable (mathematics); Statistics; Multivariate statistics; Computer science; Pathology; Machine learning; Mathematics","score_opus":0.6514226894111171,"score_gpt":0.5780220217195277,"score_spread":0.07340066769158948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949052936","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":[5.1625466e-7,0.54374284,0.45435065,0.00012344407,0.0002499795,0.0011008421,0.000030935484,0.000018325614,0.00038247774],"genre_scores_gemma":[3.960081e-7,0.5334583,0.46550512,0.00062011054,0.00018429947,0.00003301721,0.000004026125,0.00008152104,0.00011322708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9586874,0.029677982,0.009880893,0.0006667691,0.0002204036,0.0008665246],"domain_scores_gemma":[0.9495524,0.032084577,0.016427796,0.0006587997,0.0010931611,0.00018323465],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09972129,0.0007748823,0.009477704,0.00064728357,0.000042139603,0.000008033718,0.0011327048,0.00039030472,0.0003066881],"category_scores_gemma":[0.117132686,0.00051309046,0.00173033,0.0005798515,0.00011622612,0.0002188551,0.00022562411,0.0021092023,0.000010230507],"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":[0.000050094277,0.00011056985,0.000030346251,0.08974177,0.00065704295,0.000023431485,0.000052033964,0.000013179542,0.000036183672,0.011890563,0.017663557,0.87973124],"study_design_scores_gemma":[0.0002965342,0.001815133,0.0000056669146,0.16739647,0.0013242373,0.00045064208,0.00001728179,0.000042445954,0.000010431491,0.19128451,0.636991,0.00036561425],"about_ca_topic_score_codex":0.000007505427,"about_ca_topic_score_gemma":0.0000010282802,"teacher_disagreement_score":0.8793656,"about_ca_system_score_codex":0.0005947526,"about_ca_system_score_gemma":0.00049089186,"threshold_uncertainty_score":0.9997321},"labels":[],"label_agreement":null},{"id":"W2949392217","doi":"10.1111/jgs.16022","title":"Investigating and Remediating Selection Bias in Geriatrics Research: The Selection Bias Toolkit","year":2019,"lang":"en","type":"review","venue":"Journal of the American Geriatrics Society","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":86,"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 on Aging","keywords":"Geriatrics; Selection bias; Selection (genetic algorithm); Context (archaeology); Medicine; Publication bias; Gerontology; Computer science; Psychiatry; Meta-analysis; Machine learning; Pathology","score_opus":0.5513045905054362,"score_gpt":0.5063414029643264,"score_spread":0.04496318754110984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949392217","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":[0.024173873,0.96636873,0.004317906,0.00079778663,0.0010277064,0.0029494409,0.000022802345,0.0001685919,0.00017316059],"genre_scores_gemma":[0.0005306814,0.9449468,0.053071912,0.00011685644,0.0010681261,0.00003872457,0.0000015962851,0.000118359756,0.00010689113],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929143,0.0026459142,0.0020166363,0.00041051547,0.0013470016,0.0006655927],"domain_scores_gemma":[0.98194134,0.009225268,0.0073488774,0.00051124854,0.00084240094,0.00013088765],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.012776762,0.0005061333,0.0020044537,0.00044214015,0.00049556274,0.00025155503,0.001034581,0.00034739712,0.0000045319334],"category_scores_gemma":[0.01544025,0.00029533263,0.0009765765,0.0062857913,0.0005190901,0.00033567287,0.00052801304,0.0045196246,0.0000027330398],"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":[0.000028779568,0.00025768793,0.0059155687,0.015241236,0.0008123025,0.000006886902,0.006061745,0.00019988394,0.00019768534,0.0029594558,0.035665955,0.93265283],"study_design_scores_gemma":[0.0013750443,0.0023898713,0.00086439704,0.021324212,0.004817038,0.0020870417,0.007963223,0.003184817,0.00016907579,0.13884777,0.8138562,0.0031213206],"about_ca_topic_score_codex":0.00013012218,"about_ca_topic_score_gemma":0.000028870145,"teacher_disagreement_score":0.9295315,"about_ca_system_score_codex":0.0015594704,"about_ca_system_score_gemma":0.0014891183,"threshold_uncertainty_score":0.9999499},"labels":[],"label_agreement":null},{"id":"W2950335439","doi":"10.1111/biom.13104","title":"Model Selection for G-Estimation of Dynamic Treatment Regimes","year":2019,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","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":"McGill University; University of Waterloo","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; National Institute of Mental Health; University of Waterloo","keywords":"Selection (genetic algorithm); Computer science; Model selection; Identification (biology); Variety (cybernetics); Function (biology); Information Criteria; Estimation; Quadratic equation; Maximum likelihood; Mathematical optimization; Machine learning; Data mining; Econometrics; Artificial intelligence; Mathematics; Statistics; Biology","score_opus":0.17582160060611435,"score_gpt":0.43713139605817636,"score_spread":0.261309795452062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950335439","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":[0.19518492,0.000035379395,0.803598,0.000018917222,0.000035807836,0.00054408005,0.000021193424,0.00013837204,0.00042334216],"genre_scores_gemma":[0.58263624,0.000025871283,0.41621366,0.0000032394344,0.000003682877,0.000037746708,0.000011423772,0.000012210014,0.0010559505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994271,0.000008439156,0.00019716196,0.00013309337,0.000120784796,0.00011345482],"domain_scores_gemma":[0.9991851,0.00032493798,0.00016820074,0.00017404533,0.00012695446,0.000020803796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013173763,0.0000918463,0.00017593145,0.0006463495,0.000019041443,0.0000071725035,0.00006367852,0.00007857674,0.000007777582],"category_scores_gemma":[0.00036685434,0.000079376514,0.00005664662,0.0010497952,0.0000140875645,0.00010423052,0.0000114865015,0.000023220557,0.000005358916],"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":[0.00014967418,0.0010727673,0.0011157972,0.000965185,0.00015007809,2.5733786e-7,0.00048385843,0.0073735598,0.11301652,0.47453204,0.0016597667,0.3994805],"study_design_scores_gemma":[0.00026134716,0.0005027898,0.000044116325,0.000017893799,0.000028235065,0.0000010095132,0.000013471149,0.7041599,0.037873305,0.2568855,0.00011988783,0.00009252648],"about_ca_topic_score_codex":0.0000057492543,"about_ca_topic_score_gemma":0.0000020640846,"teacher_disagreement_score":0.69678634,"about_ca_system_score_codex":0.00024544235,"about_ca_system_score_gemma":0.00003689285,"threshold_uncertainty_score":0.32368803},"labels":[],"label_agreement":null},{"id":"W2951994252","doi":"10.1002/cjs.11509","title":"New perspective on the benefits of the gene–environment independence in case–control studies","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Independence (probability theory); Econometrics; Bridging (networking); Logistic regression; Computer science; Maximum likelihood; Statistics; Perspective (graphical); Estimation; Mathematical optimization; Mathematics; Artificial intelligence; Economics","score_opus":0.08972304379449776,"score_gpt":0.33465631020641035,"score_spread":0.2449332664119126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951994252","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":[0.8482973,0.003646429,0.13671161,0.005682213,0.0008008203,0.0017550514,0.0012778863,0.000013345685,0.0018153231],"genre_scores_gemma":[0.9746445,0.00008225597,0.0248899,0.00017018603,0.000036451318,0.000002205104,9.7695676e-8,0.00001386731,0.0001605845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990194,0.00009170597,0.00036017963,0.00008695042,0.00025501562,0.00018674984],"domain_scores_gemma":[0.99793184,0.0010832545,0.00039156788,0.00025509554,0.00021361063,0.00012464974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042603334,0.00011473167,0.00025465016,0.00009726098,0.000057776106,0.000011651322,0.00027689603,0.000048552105,0.00013031324],"category_scores_gemma":[0.0012900896,0.00006801393,0.000041864234,0.00009300369,0.00011554847,0.00005582518,0.000018508335,0.00038492717,0.000004589439],"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":[0.000020284184,0.000019616786,0.0062784227,0.000024522584,0.00015483671,0.00045156927,0.005409975,0.0021146024,0.00009412118,0.97836435,0.0038601945,0.0032075269],"study_design_scores_gemma":[0.0006326126,0.00048206298,0.01082296,0.00040418305,0.00012329749,0.00068869843,0.010249944,0.00010992541,0.0018641796,0.9742163,0.00020333745,0.0002025081],"about_ca_topic_score_codex":0.001732517,"about_ca_topic_score_gemma":0.023309028,"teacher_disagreement_score":0.12634714,"about_ca_system_score_codex":0.00062500767,"about_ca_system_score_gemma":0.00057425175,"threshold_uncertainty_score":0.99451303},"labels":[],"label_agreement":null},{"id":"W2952566994","doi":"10.1214/19-ejs1566","title":"Empirical likelihood inference for non-randomized pretest-posttest studies with missing data","year":2019,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"","keywords":"Empirical likelihood; Mathematics; Statistics; Confidence interval; Wald test; Missing data; Score test; Inference; Propensity score matching; Randomized experiment; Statistic; Coverage probability; Likelihood-ratio test; Test statistic; Restricted maximum likelihood; Statistical hypothesis testing; Econometrics; Maximum likelihood; Artificial intelligence; Computer science","score_opus":0.14204327335502406,"score_gpt":0.4623509266687351,"score_spread":0.320307653313711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952566994","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":[0.017227644,0.0007989149,0.9804284,0.00038216938,0.000090242196,0.00082019006,0.000109395136,0.00004340102,0.000099627425],"genre_scores_gemma":[0.37351292,0.0007546894,0.62532884,0.000112083515,0.00010342446,0.000017078431,0.00002224277,0.000051364175,0.00009735628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997672,0.00012217693,0.00087375095,0.00025613682,0.00042707782,0.0006488167],"domain_scores_gemma":[0.9870908,0.010198621,0.0010451964,0.0005452095,0.001020815,0.00009934375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020339284,0.0002696242,0.0010848579,0.000114114286,0.000075067546,0.00005027169,0.0006036561,0.000076339544,0.00002056544],"category_scores_gemma":[0.008417116,0.0001843846,0.000067498644,0.00014628282,0.00022415248,0.00039436476,0.00012242283,0.00061354216,0.0000037605748],"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":[0.057464104,0.0015802095,0.0059977006,0.0034769361,0.0070701567,0.00017935345,0.007834412,0.00016628006,0.0056898636,0.80085444,0.0557649,0.05392166],"study_design_scores_gemma":[0.018962663,0.0022827098,0.00002343141,0.00054906675,0.0004939142,0.0001235444,0.00036394878,0.0037513971,0.0011167345,0.97140664,0.000617695,0.0003082765],"about_ca_topic_score_codex":0.0000018693125,"about_ca_topic_score_gemma":0.00002716641,"teacher_disagreement_score":0.35628527,"about_ca_system_score_codex":0.00024500725,"about_ca_system_score_gemma":0.0010813371,"threshold_uncertainty_score":0.9999354},"labels":[],"label_agreement":null},{"id":"W2954516837","doi":"10.1016/j.jval.2019.04.1375","title":"PNS9 PROPENSITY SCORE MATCHING AND REWEIGHTING TO ASSESS COMPARATIVE EFFICACY OF SINGLE-ARM TRIALS: A GENERAL FRAMEWORK AND SIMULATION STUDY","year":2019,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Propensity score matching; Replicate; Observational study; Computer science; Inverse probability weighting; Matching (statistics); Weighting; Sample size determination; Flexibility (engineering); Comparative effectiveness research; Average treatment effect; Data mining; Statistics; Mathematics; Medicine","score_opus":0.6619148956200791,"score_gpt":0.5295113976503267,"score_spread":0.13240349796975237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954516837","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":[0.95531976,0.00006179417,0.041388724,0.00007162307,0.00005233121,0.0029852039,0.0000036469157,0.0000718584,0.000045084173],"genre_scores_gemma":[0.85476637,0.0000059911376,0.14510389,0.00005041783,0.000034499797,0.000016548576,0.0000010256059,0.000015579948,0.000005679755],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974153,0.0009803588,0.0008429017,0.0003191022,0.00022511088,0.00021721786],"domain_scores_gemma":[0.9942899,0.0047660666,0.00051210646,0.00025638856,0.00009040966,0.00008515083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034615928,0.00015745057,0.0008707635,0.00013819219,0.00006562525,0.000034069108,0.00008075501,0.00007296328,0.0000046429777],"category_scores_gemma":[0.0019555998,0.00013415665,0.00002276932,0.0002250413,0.000027028496,0.00014637578,0.00011447411,0.00026315433,9.3487995e-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":[0.0015416569,0.006352987,0.41290593,0.0037391041,0.00015621768,0.000016472988,0.16606463,0.23384668,0.012085475,0.14215101,0.000024363893,0.021115445],"study_design_scores_gemma":[0.0038563088,0.008224488,0.15855628,0.007040023,0.000068532245,0.0000095584455,0.006075658,0.060223028,0.005166908,0.74983484,0.000028733708,0.0009156266],"about_ca_topic_score_codex":0.00045568577,"about_ca_topic_score_gemma":0.000036882073,"teacher_disagreement_score":0.60768384,"about_ca_system_score_codex":0.00012540357,"about_ca_system_score_gemma":0.00006598604,"threshold_uncertainty_score":0.5470749},"labels":[],"label_agreement":null},{"id":"W2954560470","doi":"10.5539/ijsp.v8n4p60","title":"Medical Intervention for Disease Stages Using Game Theory, Markov Chains, and Bayesian Inference","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","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":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Markov chain; Bayesian probability; Inference; Mathematics; Bayesian inference; Bayesian game; Computer science; Markov process; Artificial intelligence; Game theory; Econometrics; Mathematical economics; Mathematical optimization; Machine learning; Statistics; Sequential game","score_opus":0.05640725535649568,"score_gpt":0.4160866617305908,"score_spread":0.3596794063740951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954560470","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":[0.22699744,0.00007644504,0.7721286,0.00021108415,0.00015114844,0.00020437955,0.00020090959,0.000009146663,0.000020858653],"genre_scores_gemma":[0.81415164,0.00010456486,0.18558986,0.000043467615,0.000056309196,0.0000045639717,0.000006853806,0.00000845405,0.000034281067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988061,0.00009692524,0.0004799957,0.00013409794,0.00038245728,0.00010043026],"domain_scores_gemma":[0.99742466,0.0013976671,0.00036890668,0.00009108986,0.00057821465,0.00013943168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013589342,0.000102473074,0.00019712791,0.00006938072,0.000022607548,0.00005923055,0.00016518286,0.00004881585,0.00013400012],"category_scores_gemma":[0.0035506058,0.000083691615,0.00004555581,0.000021930131,0.00012435982,0.00018165019,0.0000870954,0.00015020205,1.9134737e-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":[0.00050696085,0.00017997813,0.028267285,0.00037140626,0.00009496899,0.000018206592,0.00019111932,0.000008379118,0.00008582697,0.88105744,0.000065499175,0.089152955],"study_design_scores_gemma":[0.00054488407,0.00018233387,0.00466874,0.00031918663,0.000031650296,0.000024934792,0.000035002588,0.012926463,0.000057430272,0.9810141,0.00010508544,0.000090235844],"about_ca_topic_score_codex":0.0000058835794,"about_ca_topic_score_gemma":0.000009963762,"teacher_disagreement_score":0.5871542,"about_ca_system_score_codex":0.00006855093,"about_ca_system_score_gemma":0.00009620232,"threshold_uncertainty_score":0.42506632},"labels":[],"label_agreement":null},{"id":"W2956147361","doi":"10.1002/sim.8741","title":"Formulating causal questions and principled statistical answers","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Lorentz Center; Medical Research Council; Vetenskapsrådet","keywords":"Causal inference; Covariate; Outcome (game theory); Computer science; Observational study; Set (abstract data type); Confounding; Variable (mathematics); Code (set theory); Statistical inference; Inference; Propensity score matching; Econometrics; Data science; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.15779582121857488,"score_gpt":0.47360673047319685,"score_spread":0.31581090925462196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956147361","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":[0.0021058293,0.00012000726,0.9925022,0.00094264717,0.00026779695,0.00086211617,0.001014806,0.00032277536,0.0018618025],"genre_scores_gemma":[0.13508885,0.00025226164,0.86355793,0.00019363037,0.00023013008,0.00011863205,0.00040046146,0.00007719625,0.00008088875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718845,0.00017377583,0.001048257,0.0006434751,0.00052911456,0.00041692235],"domain_scores_gemma":[0.9952785,0.0034119803,0.00039031974,0.00047594588,0.00018599343,0.00025727777],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007486402,0.00044975846,0.0009982962,0.0002137727,0.00007591005,0.000028612834,0.00025316334,0.00029991806,0.00017873751],"category_scores_gemma":[0.015417589,0.0004138553,0.000020601714,0.00016081573,0.0005229243,0.000052844098,0.0006034048,0.0016406201,0.000003798752],"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":[0.000026828158,0.000037611382,0.0007638199,0.0010288322,0.00003695592,0.00023419962,0.0013883208,0.000029959894,0.00018265912,0.98748386,0.0043160557,0.0044709146],"study_design_scores_gemma":[0.00049839006,0.00023628818,0.0016686633,0.0011126985,0.00012724631,0.000013537302,0.00022249627,0.01612188,0.000032816384,0.9792541,0.0003408405,0.0003710386],"about_ca_topic_score_codex":0.00023957875,"about_ca_topic_score_gemma":0.0003322673,"teacher_disagreement_score":0.13298301,"about_ca_system_score_codex":0.00022755709,"about_ca_system_score_gemma":0.00018712974,"threshold_uncertainty_score":0.9998313},"labels":[],"label_agreement":null},{"id":"W2957839981","doi":"10.2139/ssrn.3272396","title":"Estimating Average Treatment Effects With Propensity Scores Estimated With Four Machine Learning Procedures: Simulation Results in High Dimensional Settings and With Time to Event Outcomes","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Propensity score matching; Event (particle physics); Statistics; Computer science; Econometrics; Machine learning; Artificial intelligence; Psychology; Mathematics","score_opus":0.033983390593026554,"score_gpt":0.33123923631771407,"score_spread":0.2972558457246875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957839981","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":[0.8965924,0.000028641465,0.101991154,0.00029185653,0.0000068458958,0.0009058329,0.0000027616734,0.0001569705,0.000023578983],"genre_scores_gemma":[0.9082769,0.0000064074147,0.09113317,0.000040735704,0.000038182025,0.000035286484,0.000009895578,0.00005506898,0.00040433978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976131,0.00013216652,0.00036465534,0.00038875043,0.0003995012,0.0011018704],"domain_scores_gemma":[0.9985998,0.0004896042,0.00039497876,0.00017156993,0.00022980288,0.000114238705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090511004,0.00036277153,0.00046645824,0.0001813005,0.0003089496,0.00006987271,0.000099774734,0.0000623225,0.00000626276],"category_scores_gemma":[0.0007950747,0.00020700137,0.000022601631,0.0002529149,0.00008357967,0.00029289266,0.000047021993,0.0007808627,0.0000065730023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020580636,0.0013916956,0.23461556,0.00054373103,0.0014983051,0.0005675007,0.0055819303,0.6756209,0.004621679,0.007010468,0.00003590739,0.047931693],"study_design_scores_gemma":[0.021261267,0.071313016,0.045365553,0.009279387,0.0006071301,0.00431118,0.00020350187,0.6573976,0.009306774,0.17855051,0.000022667142,0.0023813704],"about_ca_topic_score_codex":0.00012468574,"about_ca_topic_score_gemma":0.0022993179,"teacher_disagreement_score":0.18925,"about_ca_system_score_codex":0.0008992053,"about_ca_system_score_gemma":0.000714535,"threshold_uncertainty_score":0.8441271},"labels":[],"label_agreement":null},{"id":"W2962931983","doi":"10.1097/mcc.0000000000000642","title":"Defining standard of practice: pros and cons of the usual care arm","year":2019,"lang":"en","type":"review","venue":"Current Opinion in Critical Care","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Generalizability theory; Medicine; Protocol (science); Randomization; Clinical equipoise; Randomized controlled trial; Selection bias; MEDLINE; Standard of care; Alternative medicine; Surgery; Psychology","score_opus":0.45607620734391213,"score_gpt":0.602160831643227,"score_spread":0.14608462429931485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962931983","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":[0.000003093887,0.9951066,0.0005477731,0.000033244116,0.0011851519,0.0012828221,0.0010865285,0.000037836748,0.000716984],"genre_scores_gemma":[0.0016985993,0.9925646,0.005366828,0.0000034743261,0.00006761785,0.00016863045,0.000077737954,0.00005080429,0.0000016799821],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976676,0.00033586935,0.0009233148,0.00035930387,0.00046262392,0.00025125023],"domain_scores_gemma":[0.99450684,0.003705287,0.00042865193,0.00054967817,0.00074924284,0.000060312446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002625607,0.00032596014,0.0014686103,0.000116168914,0.000039521645,0.000020578384,0.0003006407,0.00028859705,0.00001801899],"category_scores_gemma":[0.008330809,0.00023093642,0.00023512206,0.00023284025,0.00041112225,0.000121621546,0.00035028337,0.0008550023,0.0000015042176],"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":[0.000009597554,0.00006209046,0.000048688264,0.25703305,0.000013068468,4.041932e-7,0.0011889148,8.7872706e-8,9.868467e-8,0.45337486,0.00020276518,0.2880664],"study_design_scores_gemma":[0.00032795308,0.00051993656,0.0000029169041,0.1596603,0.00063242717,0.000025897074,0.0061298367,0.000001319604,0.00004213547,0.023361435,0.8087988,0.00049704977],"about_ca_topic_score_codex":0.000002268249,"about_ca_topic_score_gemma":0.000001578275,"teacher_disagreement_score":0.808596,"about_ca_system_score_codex":0.00020064187,"about_ca_system_score_gemma":0.00056989695,"threshold_uncertainty_score":0.9973358},"labels":[],"label_agreement":null},{"id":"W2963624793","doi":"10.1515/jci-2017-0010","title":"Variable Selection in Causal Inference using a Simultaneous Penalization Method","year":2018,"lang":"en","type":"article","venue":"RePEc: Research Papers in Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"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":"Causal inference; Estimator; Spurious relationship; Econometrics; Confounding; Statistics; Lasso (programming language); Outcome (game theory); Variance inflation factor; Feature selection; Average treatment effect; Variable (mathematics); Mathematics; Inflation (cosmology); Regression analysis; Computer science; Multicollinearity; Artificial intelligence","score_opus":0.1427988771873353,"score_gpt":0.47745571021162403,"score_spread":0.3346568330242887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963624793","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":[0.44838765,0.000014919035,0.49704534,0.00006140799,0.00015189042,0.0015555414,0.000013344149,0.0003560775,0.052413836],"genre_scores_gemma":[0.5808794,0.00008215927,0.4184679,0.00003135383,0.000093239265,0.000053038813,0.000003356085,0.00004009388,0.00034945481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978074,0.00039774698,0.00051922025,0.0004712788,0.00019201107,0.0006123871],"domain_scores_gemma":[0.9966745,0.0025177205,0.0001349342,0.0003091178,0.00027829126,0.000085463704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022892037,0.00017400715,0.0003095783,0.0005005617,0.0001347774,0.00006695364,0.00025364375,0.0002141502,0.00017908057],"category_scores_gemma":[0.0056843287,0.00019256688,0.000028217706,0.00058606715,0.00016949199,0.0003100689,0.00016077267,0.00053767924,0.0000059763897],"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":[0.00055471784,0.00091247726,0.017920949,0.0003728536,0.000092799186,0.00009423816,0.0033146266,0.07857443,0.10574411,0.5022466,0.000058243186,0.29011396],"study_design_scores_gemma":[0.00037187483,0.00024826825,0.00015966328,0.0001714056,0.0000053851413,0.000030208048,0.0002585872,0.6209293,0.00983629,0.36653143,0.0011569434,0.00030063046],"about_ca_topic_score_codex":0.0002491758,"about_ca_topic_score_gemma":0.0013243564,"teacher_disagreement_score":0.5423549,"about_ca_system_score_codex":0.0012043121,"about_ca_system_score_gemma":0.00034901573,"threshold_uncertainty_score":0.78526497},"labels":[],"label_agreement":null},{"id":"W2964028530","doi":"10.1111/sjos.12398","title":"Novel criteria to exclude the surrogate paradox and their optimalities","year":2019,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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":"University of Alberta; Harvard University; University of Minnesota; University of Wisconsin-Madison","keywords":"Surrogate endpoint; Surrogate data; Surrogate model; Outcome (game theory); Mathematics; Clinical endpoint; Econometrics; Statistics; Mathematical economics; Medicine; Internal medicine; Clinical trial","score_opus":0.11013643131589221,"score_gpt":0.390690188280301,"score_spread":0.28055375696440876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964028530","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":[0.20841298,0.00012143942,0.7895127,0.00047406883,0.00028011834,0.00028367876,0.00034790477,0.000030365052,0.00053678255],"genre_scores_gemma":[0.6705364,0.00006400978,0.32885772,0.00014009001,0.000072078175,0.0000035125888,0.0000016115283,0.000024915105,0.00029969076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988894,0.000058354784,0.00047420568,0.00011611724,0.0002162861,0.00024566607],"domain_scores_gemma":[0.99808526,0.0009106006,0.00034623366,0.00024202083,0.00027548315,0.00014042853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000619053,0.00018056978,0.00036296638,0.00009298789,0.00007790655,0.000095564945,0.00027739728,0.000045795958,0.00014128382],"category_scores_gemma":[0.00045397246,0.000109898174,0.000043931625,0.00010588617,0.000120844605,0.00017094032,0.00008135901,0.00025214133,0.0000082333],"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":[0.00043788797,0.00022340403,0.006044186,0.0004609697,0.00026973107,0.00009540299,0.017795006,0.00006839363,0.02896848,0.90025836,0.028123042,0.017255146],"study_design_scores_gemma":[0.00083683385,0.0012665716,0.004636066,0.0007192518,0.000073882686,0.00080491306,0.004918066,0.00038433346,0.0059134914,0.97755545,0.0024726614,0.00041849],"about_ca_topic_score_codex":0.0000069586595,"about_ca_topic_score_gemma":0.0000064059273,"teacher_disagreement_score":0.46212342,"about_ca_system_score_codex":0.000056384106,"about_ca_system_score_gemma":0.000042360407,"threshold_uncertainty_score":0.44815174},"labels":[],"label_agreement":null},{"id":"W2964417596","doi":"10.1093/bioinformatics/btz602","title":"Non-parametric individual treatment effect estimation for survival data with random forests","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Random forest; Censoring (clinical trials); Computer science; Estimation; Statistics; Parametric statistics; Population; Random effects model; Survival analysis; Average treatment effect; Machine learning; Artificial intelligence; Data mining; Mathematics; Medicine; Propensity score matching; Engineering","score_opus":0.112018737931895,"score_gpt":0.39302598033528546,"score_spread":0.2810072424033905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964417596","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":[0.1851714,0.000012751024,0.80891335,0.000016892367,0.00017987065,0.0037762127,0.0002701334,0.00031489867,0.0013445212],"genre_scores_gemma":[0.3368844,0.000010839663,0.6616674,0.000022289134,0.000053943364,0.00024568182,0.00090553425,0.000045855806,0.00016406835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985863,0.000025097077,0.0004801307,0.00019979489,0.00037554093,0.00033315824],"domain_scores_gemma":[0.99636173,0.001982547,0.00035239634,0.0010888953,0.00013571058,0.00007872725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007355984,0.0003041165,0.00052687887,0.00020000411,0.000073964155,0.00009599676,0.00047089832,0.00012037239,0.000016299966],"category_scores_gemma":[0.0009647264,0.0001934859,0.00006412326,0.00029850466,0.00004346644,0.0008075175,0.00013346043,0.00009099999,0.00006549839],"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":[0.0078123184,0.0023698346,0.11891598,0.0136947045,0.0034959791,0.000019007644,0.0075799115,0.007511971,0.00014313118,0.070370354,0.037251245,0.73083556],"study_design_scores_gemma":[0.016943535,0.007909044,0.0023892622,0.00041563768,0.0007379927,0.000023330536,0.00028976102,0.92900187,0.007831642,0.030692903,0.0026814444,0.0010835706],"about_ca_topic_score_codex":0.000008807459,"about_ca_topic_score_gemma":0.000031663323,"teacher_disagreement_score":0.9214899,"about_ca_system_score_codex":0.000115666786,"about_ca_system_score_gemma":0.00008935427,"threshold_uncertainty_score":0.7890126},"labels":[],"label_agreement":null},{"id":"W2966416868","doi":"10.1002/sim.8690","title":"Measurement error and precision medicine: Error‐prone tailoring covariates in dynamic treatment regimes","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Precision medicine; Observational error; Context (archaeology); Accuracy and precision; Simple (philosophy); Error detection and correction","score_opus":0.1879669184940262,"score_gpt":0.4346654424349814,"score_spread":0.2466985239409552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966416868","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":[0.022346389,0.0023968427,0.96076477,0.010050589,0.00026375448,0.0018217592,0.000055414286,0.00029318966,0.0020073133],"genre_scores_gemma":[0.7302101,0.0010282397,0.2681422,0.00023247849,0.00010407578,0.000117874,0.000026383244,0.000048330283,0.00009032342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768335,0.00013488372,0.00077517837,0.0004409079,0.00064225873,0.000323402],"domain_scores_gemma":[0.99836516,0.0008345584,0.0002172045,0.000287465,0.00013724001,0.00015835243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010335967,0.0003074815,0.0007313319,0.0002033822,0.000042808235,0.0000067471005,0.0001576621,0.00009108647,0.0001164754],"category_scores_gemma":[0.006007818,0.00022679383,0.000013026143,0.0003204973,0.0002822428,0.0000813186,0.000071810166,0.00028313106,0.0000035865428],"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":[0.0013315574,0.0009402325,0.012384607,0.0030857108,0.00029374025,0.0014223973,0.061173156,0.00025824338,0.03851622,0.66496325,0.019748103,0.1958828],"study_design_scores_gemma":[0.0060657347,0.004224642,0.006306378,0.0040491843,0.00018481897,0.000018938881,0.0044184714,0.021666583,0.0011974889,0.95001185,0.0012693058,0.0005866056],"about_ca_topic_score_codex":0.00024267257,"about_ca_topic_score_gemma":0.00065059465,"teacher_disagreement_score":0.70786375,"about_ca_system_score_codex":0.0004814413,"about_ca_system_score_gemma":0.00006157911,"threshold_uncertainty_score":0.92483836},"labels":[],"label_agreement":null},{"id":"W2968938401","doi":"10.1111/biom.13135","title":"Data‐adaptive longitudinal model selection in causal inference with collaborative targeted minimum loss‐based estimation","year":2019,"lang":"en","type":"article","venue":"Biometrics","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":true,"ca_institutions":"Statistics Canada; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Causal inference; Confounding; Counterfactual thinking; Statistics; Marginal structural model; Observational study; Inverse probability weighting; Computer science; Population; Econometrics; Outcome (game theory); Mathematics; Medicine; Propensity score matching; Psychology; Environmental health","score_opus":0.18956229312117323,"score_gpt":0.41666249240000175,"score_spread":0.22710019927882852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968938401","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":[0.19076088,0.00003156749,0.807662,0.000036233698,0.000035606226,0.0007241657,0.00022265573,0.00022530538,0.000301553],"genre_scores_gemma":[0.64304787,0.0000073022366,0.35669354,0.000017474851,0.000009866728,0.00003807553,0.00010852663,0.000024757912,0.00005261405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981061,0.00008094141,0.00039485915,0.00055262615,0.0005218532,0.00034359682],"domain_scores_gemma":[0.9976793,0.00086112175,0.00032777464,0.00049200567,0.0005611337,0.00007864424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004896165,0.00027465046,0.00037053888,0.001591904,0.000054160493,0.000058355825,0.00035836856,0.00018362592,0.00003397009],"category_scores_gemma":[0.0013997696,0.00024384397,0.000019185,0.00791445,0.000094593226,0.0008096364,0.000116364216,0.00027169078,0.000025652693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004312836,0.0055300137,0.29013392,0.0015917396,0.0006024441,0.00020200602,0.0025124478,0.3451632,0.056627277,0.2656639,0.0061301724,0.02153003],"study_design_scores_gemma":[0.00081008504,0.00069420907,0.0023659924,0.00011048361,0.00003667933,0.00000350027,0.00008139931,0.96281755,0.007941643,0.024705395,0.000031054835,0.0004019917],"about_ca_topic_score_codex":0.000039887906,"about_ca_topic_score_gemma":0.00017818205,"teacher_disagreement_score":0.6176544,"about_ca_system_score_codex":0.00038413765,"about_ca_system_score_gemma":0.0004782899,"threshold_uncertainty_score":0.9943669},"labels":[],"label_agreement":null},{"id":"W2969528659","doi":"10.1002/pds.4888","title":"An empirical assessment of immeasurable time bias in the setting of nested case‐control studies: Statins and all‐cause mortality among patients with heart failure","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"Yuhan; McGill University","keywords":"Medicine; Confidence interval; Nested case-control study; Hazard ratio; Pharmacoepidemiology; Odds ratio; Proportional hazards model; Emergency medicine; Weighting; Inverse probability weighting; Statistics; Internal medicine; Propensity score matching; Pharmacology","score_opus":0.16791865048048754,"score_gpt":0.4942670090386634,"score_spread":0.32634835855817584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969528659","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":[0.9960818,0.00008210354,0.002035063,0.0006893958,0.00001609714,0.0009290701,0.00008823951,0.00003719497,0.00004102273],"genre_scores_gemma":[0.98695725,0.0000524636,0.012447083,0.00046229077,0.000008610028,0.000040909297,0.000014469579,0.000013756431,0.0000031751697],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957873,0.0026971623,0.00076880184,0.00031479474,0.00015629525,0.00027564794],"domain_scores_gemma":[0.98957366,0.00940719,0.0004888343,0.00029535583,0.000168926,0.00006604343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060525946,0.0002124706,0.000833587,0.00006334622,0.00006677655,0.000003990338,0.000111774374,0.000083496234,0.00002109713],"category_scores_gemma":[0.0010176795,0.00013078812,0.00003693937,0.00013357117,0.00026836112,0.00026020122,0.000052930973,0.00035699032,3.3465184e-7],"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":[0.00009124819,0.00018916272,0.99652576,0.00016635327,0.00027753707,0.000007760393,0.0012564557,0.00016249898,0.00031608302,0.0005798729,0.00033224755,0.00009502282],"study_design_scores_gemma":[0.0020640101,0.00034592015,0.97934717,0.00012692697,0.0003921762,0.000030006238,0.001756828,0.008530574,0.00021019312,0.0069449507,0.000030753952,0.00022051489],"about_ca_topic_score_codex":0.00017411531,"about_ca_topic_score_gemma":0.00028219097,"teacher_disagreement_score":0.017178612,"about_ca_system_score_codex":0.000033546996,"about_ca_system_score_gemma":0.000036386682,"threshold_uncertainty_score":0.5333384},"labels":[],"label_agreement":null},{"id":"W2969601771","doi":"10.1136/bmjebm-2019-111225","title":"Challenges in interpreting results from ‘multiple regression’ when there is interaction between covariates","year":2019,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Université de Montréal; McGill University; Jewish General Hospital","funders":"","keywords":"Covariate; Observational study; Outcome (game theory); Popularity; Meta-regression; Regression; Population; Econometrics; Regression analysis; Statistics; Regression toward the mean; Pace; Baseline (sea); Medicine; Psychology; Meta-analysis; Mathematics; Geography; Social psychology; Internal medicine","score_opus":0.4058680440234082,"score_gpt":0.4765542601293872,"score_spread":0.07068621610597897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969601771","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":[0.82493377,0.007345703,0.041313242,0.109360084,0.00122254,0.004709174,0.000117770745,0.0013971833,0.00960053],"genre_scores_gemma":[0.9612014,0.0007079788,0.036707304,0.0005507673,0.0004363594,0.000105191495,0.00004208812,0.000051536146,0.00019735683],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681157,0.0004028552,0.0011316132,0.0007002651,0.000589856,0.00036381546],"domain_scores_gemma":[0.98108524,0.016841898,0.00074097834,0.001008542,0.00020410243,0.00011924918],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024196282,0.0003600949,0.00078357203,0.0002774358,0.000043256183,0.000020987338,0.00044445574,0.00024454188,0.00063194335],"category_scores_gemma":[0.018292228,0.00025745152,0.00007915543,0.00019858583,0.00010725446,0.00059465045,0.00012956376,0.00060536474,0.000086890366],"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":[0.010511243,0.0007638501,0.334231,0.0031617326,0.0004765046,0.00034080422,0.06757751,0.00013622353,0.08146612,0.012424841,0.062000524,0.42690966],"study_design_scores_gemma":[0.00886815,0.002479412,0.019818567,0.20964207,0.00024806484,0.000012609002,0.012941478,0.0078865485,0.13955995,0.5905202,0.00642175,0.0016012044],"about_ca_topic_score_codex":0.00077532785,"about_ca_topic_score_gemma":0.00022037746,"teacher_disagreement_score":0.5780954,"about_ca_system_score_codex":0.00026441735,"about_ca_system_score_gemma":0.00009915672,"threshold_uncertainty_score":0.9999878},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","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":"split"},{"id":"W2969619689","doi":"10.1111/rssa.12497","title":"Regression-With-Residuals Estimation of Marginal Effects: A Method of Adjusting for Treatment-Induced Confounders That may also be Effect Modifiers","year":2019,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":25,"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","funders":"","keywords":"Marginal structural model; Confounding; Spurious relationship; Statistics; Marginal model; Econometrics; Regression; Mathematics; Set (abstract data type); Regression analysis; Point estimation; Estimation; Computer science; Engineering","score_opus":0.06958519297076769,"score_gpt":0.4071576483818013,"score_spread":0.3375724554110336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969619689","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":[0.054063246,0.000060773757,0.94369906,0.00019079713,0.00017914014,0.0012646281,0.0004451854,0.00002483274,0.00007235088],"genre_scores_gemma":[0.26044655,0.000047558813,0.73914534,0.000053047665,0.000030356543,0.00004409814,0.000012883296,0.000049017293,0.00017116588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969048,0.00042588168,0.0011139023,0.00027641145,0.00081035035,0.00046868177],"domain_scores_gemma":[0.9813231,0.015953518,0.0018481029,0.00035088076,0.0004068753,0.00011749353],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017221569,0.00041778164,0.0013322433,0.000041179304,0.00014162736,0.000040802202,0.0003786982,0.0002652444,0.000048015976],"category_scores_gemma":[0.0025382391,0.00025730775,0.00050034083,0.00025770825,0.00044425082,0.00019346927,0.00009725742,0.00042154023,2.138313e-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":[0.0059853657,0.0017668306,0.0152714085,0.023032919,0.0052497173,0.000060873277,0.019513303,0.031188803,0.015140833,0.78247184,0.032495376,0.067822754],"study_design_scores_gemma":[0.01109417,0.012603289,0.002303775,0.004483632,0.0025645134,0.00009119827,0.009804784,0.20932983,0.11468151,0.63164425,0.00024072344,0.0011583007],"about_ca_topic_score_codex":0.00007926412,"about_ca_topic_score_gemma":0.00001911015,"teacher_disagreement_score":0.20638332,"about_ca_system_score_codex":0.0005191261,"about_ca_system_score_gemma":0.00024884706,"threshold_uncertainty_score":0.9999879},"labels":[],"label_agreement":null},{"id":"W2969784647","doi":"10.1002/sim.8986","title":"Incorporating partial adherence into the principal stratification analysis framework","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; Providence Health Care; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Estimator; Stratification (seeds); Principal (computer security); Computer science; Principal component analysis; Population; Clinical trial; Monte Carlo method; Statistics; Econometrics; Mathematics; Artificial intelligence; Medicine","score_opus":0.11815568465399728,"score_gpt":0.45816061350439785,"score_spread":0.34000492885040057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969784647","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":[0.009877053,0.00008768438,0.9875905,0.00073592557,0.00010754023,0.0001871475,0.000016892558,0.00007657185,0.0013206906],"genre_scores_gemma":[0.5148438,0.000033879856,0.48474476,0.00010529799,0.0000911576,0.00004551954,0.000053135685,0.000009477344,0.00007294538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99824303,0.00021343082,0.000634998,0.00028747116,0.00042649056,0.00019459626],"domain_scores_gemma":[0.99623495,0.0025342912,0.0002987005,0.0005933136,0.00027999852,0.00005873886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009594523,0.00014966617,0.00035849685,0.000103346574,0.00010512984,0.000024066549,0.0002256524,0.00009251633,0.00035089717],"category_scores_gemma":[0.010450514,0.000106621745,0.00002688973,0.0012010515,0.0002987212,0.00006232775,0.00007161981,0.00047704412,0.000005430158],"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":[0.0000063253183,0.000038137634,0.0028894572,0.00003793825,0.000057917405,0.00004310888,0.002900809,0.00006686141,0.00093498576,0.98541254,0.00030296357,0.0073089674],"study_design_scores_gemma":[0.000108646425,0.00007645727,0.0016745873,0.00012641461,0.00019437674,0.000002072008,0.0014600463,0.004920794,0.0017336897,0.9895154,0.00007222487,0.00011528475],"about_ca_topic_score_codex":0.00011049606,"about_ca_topic_score_gemma":0.0014331164,"teacher_disagreement_score":0.5049668,"about_ca_system_score_codex":0.000086000415,"about_ca_system_score_gemma":0.00011749256,"threshold_uncertainty_score":0.99788487},"labels":[],"label_agreement":null},{"id":"W2970371236","doi":"10.1002/bimj.201600228","title":"Inverse‐probability‐of‐treatment weighted estimation of causal parameters in the presence of error‐contaminated and time‐dependent confounders","year":2019,"lang":"en","type":"article","venue":"Biometrical Journal","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Marginal structural model; Causal inference; Confounding; Estimation; Statistics; Inference; Econometrics; Inverse probability; Mathematics; Observational error; Computer science; Bayesian probability; Artificial intelligence; Economics","score_opus":0.16967966074865296,"score_gpt":0.3903522632045267,"score_spread":0.22067260245587375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970371236","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":[0.98122275,0.00005654222,0.01791855,0.00006793441,0.00003713609,0.0004854132,0.000009361063,0.000012989786,0.0001893332],"genre_scores_gemma":[0.95693624,0.00004296905,0.04297296,0.000007087349,0.000003490543,0.00000587546,0.0000019562224,0.0000070191495,0.000022390032],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984359,0.00023949702,0.0006402054,0.00013850449,0.00038474356,0.00016114349],"domain_scores_gemma":[0.99707305,0.0019541166,0.0005218417,0.00023311155,0.00016283113,0.000055055956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008754287,0.00012991126,0.00039115455,0.00067727384,0.000019021281,0.0000140229495,0.00020084812,0.00009920623,0.000039787992],"category_scores_gemma":[0.0010822929,0.00008280061,0.000066929715,0.0010897614,0.00021748133,0.00015696256,0.00004230605,0.00016079743,0.0000020312434],"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":[0.0030810947,0.0124330195,0.20701604,0.0033956347,0.0021653546,0.00022865912,0.024126034,0.0060255383,0.3378269,0.18989207,0.0013254037,0.21248424],"study_design_scores_gemma":[0.0053598043,0.009961512,0.019188372,0.0008060029,0.00033905817,0.00037060364,0.002601895,0.074807435,0.19979636,0.68606883,0.00004330255,0.0006568262],"about_ca_topic_score_codex":0.00008957506,"about_ca_topic_score_gemma":0.0000064944393,"teacher_disagreement_score":0.49617675,"about_ca_system_score_codex":0.00020033587,"about_ca_system_score_gemma":0.00008140232,"threshold_uncertainty_score":0.3376511},"labels":[],"label_agreement":null},{"id":"W2970689096","doi":"10.32614/rj-2019-029","title":"ipwErrorY: An R Package for Estimation of Average Treatment Effect with Misclassified Binary Outcome","year":2019,"lang":"en","type":"article","venue":"The R Journal","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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"R package; Outcome (game theory); Statistics; Estimation; Binary number; Econometrics; Mathematics; Computer science; Economics; Arithmetic; Mathematical economics","score_opus":0.17842987736422145,"score_gpt":0.42649781193230446,"score_spread":0.24806793456808302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970689096","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":[0.8203621,0.000014306924,0.17842218,0.00008663712,0.000045773035,0.00065892923,0.000010741374,0.000057331777,0.00034201526],"genre_scores_gemma":[0.9578777,0.000008229432,0.04158721,0.00001668974,0.000032848297,0.00002357682,0.0000053140207,0.000028363122,0.00042007334],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99914974,0.00015475473,0.00026708795,0.00008607217,0.00017297379,0.00016935678],"domain_scores_gemma":[0.99858236,0.00062847196,0.00032367758,0.00035155285,0.00006112742,0.000052811472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072018977,0.00015584024,0.00030120256,0.000057395308,0.00009025097,0.00001884767,0.00017132083,0.000048183807,0.00007010842],"category_scores_gemma":[0.00009980337,0.000073874246,0.00007476724,0.00005793208,0.00004247867,0.00020011964,0.000014508868,0.00014310534,0.0000069789508],"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":[0.015816843,0.004378599,0.06762743,0.00287726,0.0022971313,0.00016246304,0.024731463,0.022161921,0.5322436,0.17840384,0.0026561888,0.14664324],"study_design_scores_gemma":[0.010612761,0.04598211,0.008654716,0.00093028264,0.0010990343,0.00097396935,0.0010413013,0.047522295,0.4314014,0.45031565,0.00038853122,0.0010779392],"about_ca_topic_score_codex":0.000003576248,"about_ca_topic_score_gemma":0.000004382721,"teacher_disagreement_score":0.27191183,"about_ca_system_score_codex":0.000111693895,"about_ca_system_score_gemma":0.000034215966,"threshold_uncertainty_score":0.30125043},"labels":[],"label_agreement":null},{"id":"W2970862519","doi":"10.1016/j.ahj.2019.08.017","title":"Variations in stepped-wedge cluster randomized trial design: Insights from the Patient-Centered Care Transitions in Heart Failure trial","year":2019,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Population Health Research Institute; McMaster University; University of Ottawa","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Sample size determination; Randomized controlled trial; Cluster randomised controlled trial; Research design; Statistical power; Clinical study design; Cluster (spacecraft); Psychological intervention; Computer science; Clinical trial; Statistics; Nursing; Surgery","score_opus":0.08799311841661227,"score_gpt":0.362863905260655,"score_spread":0.2748707868440427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970862519","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":[0.93260723,0.00012634839,0.055006534,0.0043312926,0.00058521243,0.007104057,0.000037112368,0.00009310934,0.0001091042],"genre_scores_gemma":[0.9313574,0.000020600823,0.06712436,0.00079420605,0.00029063624,0.00034623683,0.000014513216,0.00004088184,0.000011200053],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99499494,0.00275358,0.0011408553,0.00029816065,0.00042199215,0.00039049995],"domain_scores_gemma":[0.99508107,0.0038344827,0.00039524553,0.00042323596,0.00014671597,0.00011924678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074861903,0.00027524983,0.0011039574,0.0002565104,0.00015760049,0.00011651731,0.00024897323,0.00011178971,0.00019528028],"category_scores_gemma":[0.0008773557,0.00019315066,0.00034277022,0.000495706,0.00020021143,0.0003660865,0.000045354434,0.0009363051,0.000032847784],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9739765,0.0006402743,0.00043718392,0.000010047583,0.00010752314,0.00001615439,0.016493568,0.0002281561,0.0010038327,0.0013815538,0.0049103773,0.0007948311],"study_design_scores_gemma":[0.9497733,0.0016184092,0.000118692624,0.00024561118,0.00008518694,0.000029720433,0.006239443,0.0005447672,0.00024728358,0.03933676,0.0014032624,0.00035753727],"about_ca_topic_score_codex":0.00026738705,"about_ca_topic_score_gemma":0.0006164411,"teacher_disagreement_score":0.037955206,"about_ca_system_score_codex":0.00025224467,"about_ca_system_score_gemma":0.00026896354,"threshold_uncertainty_score":0.7876455},"labels":[],"label_agreement":null},{"id":"W2972232169","doi":"10.1002/pds.4876","title":"Multiple imputation for systematically missing confounders within a distributed data drug safety network: A simulation study and real‐world example","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University Health Centre; University of British Columbia; McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Missing data; Imputation (statistics); Confounding; Medicine; Hazard ratio; Statistics; Confidence interval; Univariate; Multivariate statistics; Data mining; Computer science; Internal medicine; Mathematics","score_opus":0.2291901691434829,"score_gpt":0.4677311089516778,"score_spread":0.2385409398081949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972232169","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":[0.08968506,0.0001579208,0.9039998,0.0007923485,0.00023205265,0.0042885044,0.00028957767,0.000388236,0.0001664993],"genre_scores_gemma":[0.9368599,0.00006884744,0.06177662,0.0003113158,0.00010919569,0.00009094783,0.000646458,0.000040290044,0.000096406526],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99553496,0.0016351938,0.001391613,0.0007924179,0.00015031503,0.0004955239],"domain_scores_gemma":[0.9664193,0.031917546,0.0007286598,0.00061174127,0.00015936086,0.00016344317],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009922968,0.00035195562,0.0009890748,0.0000829728,0.00037503647,0.000034993303,0.00027011085,0.00010997809,0.000025115676],"category_scores_gemma":[0.004211456,0.0003045048,0.000051669642,0.000186699,0.00015387894,0.000494754,0.00031833292,0.00032081304,0.0000031387756],"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":[0.01037132,0.001571704,0.49514216,0.0085435705,0.0021684186,0.000026471589,0.014745646,0.14240795,0.0012910648,0.28298596,0.016261192,0.024484538],"study_design_scores_gemma":[0.0027802475,0.000084717976,0.004886784,0.00024040927,0.0002982061,0.0000067991746,0.00094441144,0.84856087,0.00002787345,0.14091334,0.00085898454,0.0003973418],"about_ca_topic_score_codex":0.0003971186,"about_ca_topic_score_gemma":0.00067344104,"teacher_disagreement_score":0.8471749,"about_ca_system_score_codex":0.00010889005,"about_ca_system_score_gemma":0.000062477295,"threshold_uncertainty_score":0.9999407},"labels":[],"label_agreement":null},{"id":"W2972461329","doi":"10.1002/cjs.11634","title":"Synthetic estimation for the complier average causal effect","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health","keywords":"Estimator; Minimum-variance unbiased estimator; Mean squared error; Variance (accounting); Robustness (evolution); Efficiency; Efficient estimator; Bias of an estimator; Statistics; Robust statistics; Mathematics; Econometrics; Computer science; Economics","score_opus":0.10320913308488103,"score_gpt":0.3740226324498933,"score_spread":0.2708134993650123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972461329","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":[0.0020309787,0.0004043109,0.9943484,0.00027695735,0.0009826162,0.0006429922,0.0011190242,0.000018844948,0.00017585333],"genre_scores_gemma":[0.41735366,0.00006013058,0.5818827,0.00008079438,0.00022053736,0.00005338258,0.000081434824,0.000078482146,0.00018888226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983571,0.00014253835,0.00070348394,0.00018553108,0.00026947283,0.0003418272],"domain_scores_gemma":[0.9929422,0.004633114,0.0008219756,0.00047497574,0.00078965485,0.00033809335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009406353,0.00029025794,0.0006055812,0.00018440967,0.00020442213,0.00023561329,0.00048518833,0.00021773114,0.00022179227],"category_scores_gemma":[0.005805405,0.00022232623,0.00015898571,0.00007412878,0.00017925179,0.0000705526,0.000060072525,0.0009202911,0.0000023037483],"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":[0.00013866629,0.00010982133,0.0004884174,0.006035041,0.0018439447,0.0016375559,0.005538271,0.043534465,0.00022315752,0.577163,0.21880871,0.14447898],"study_design_scores_gemma":[0.00041862074,0.00039193907,0.00024516322,0.0016563741,0.0008947812,0.0003977841,0.00015072891,0.035171483,0.0009516344,0.955302,0.0038938234,0.0005256655],"about_ca_topic_score_codex":0.0005786603,"about_ca_topic_score_gemma":0.007120892,"teacher_disagreement_score":0.41532266,"about_ca_system_score_codex":0.0004850016,"about_ca_system_score_gemma":0.0019868375,"threshold_uncertainty_score":0.90662},"labels":[],"label_agreement":null},{"id":"W2974998223","doi":"10.1080/00273171.2019.1660605","title":"New Recommendations on the Use of R-Squared Differences in Multilevel Model Comparisons","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Mean squared error; Measure (data warehouse); Multilevel model; Computer science; Class (philosophy); Confusion; Data mining; Statistics; Mathematics; Artificial intelligence; Psychology","score_opus":0.8895675119762272,"score_gpt":0.598556855129321,"score_spread":0.2910106568469062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974998223","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":[0.91486007,0.0000037399902,0.08191853,0.0009828269,0.000058022193,0.0016695551,0.0000923396,0.00010659088,0.00030832668],"genre_scores_gemma":[0.8461451,0.000008022908,0.1517225,0.00001497995,0.000009021197,0.00012451792,0.000010886719,0.000030141704,0.0019348158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973423,0.00052397395,0.0005311266,0.0003664297,0.0007194459,0.00051676197],"domain_scores_gemma":[0.9947316,0.0039047145,0.00014524866,0.0008042339,0.00030621473,0.0001079645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010124882,0.00020190667,0.00039246096,0.00035967078,0.00011292621,0.000071910225,0.0005792105,0.0001539666,0.0004624518],"category_scores_gemma":[0.0010961405,0.0001405288,0.000075156786,0.00045941796,0.00012736456,0.000286912,0.00028006427,0.0009658849,0.00006070297],"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":[0.00084094895,0.0058165663,0.08593088,0.00012944717,0.00006213273,0.000017817883,0.010963871,0.0015445789,0.08654626,0.7056209,0.037178073,0.06534856],"study_design_scores_gemma":[0.003450614,0.0016446717,0.08137008,0.0016649317,0.000051878807,0.0000028401762,0.0028698714,0.5402603,0.042095184,0.3240141,0.0013799479,0.0011955395],"about_ca_topic_score_codex":0.003337477,"about_ca_topic_score_gemma":0.00043624075,"teacher_disagreement_score":0.5387158,"about_ca_system_score_codex":0.00018505403,"about_ca_system_score_gemma":0.00018605358,"threshold_uncertainty_score":0.57305986},"labels":[],"label_agreement":null},{"id":"W2975824420","doi":"10.1016/j.apmr.2019.04.007","title":"Comparative Effectiveness of Inpatient Rehabilitation Interventions for Traumatic Brain Injury: Introduction","year":2019,"lang":"en","type":"article","venue":"Archives of Physical Medicine and Rehabilitation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Medical Rehabilitation Research; National Institutes of Health; National Institute on Disability, Independent Living, and Rehabilitation Research; Ontario Neurotrauma Foundation; Patient-Centered Outcomes Research Institute","keywords":"Observational study; Rehabilitation; Propensity score matching; Traumatic brain injury; Causal inference; Psychological intervention; Comparative effectiveness research; Confounding; Randomized controlled trial; Medicine; Physical therapy; Physical medicine and rehabilitation; Marginal structural model; Consistency (knowledge bases); Psychiatry; Computer science; Alternative medicine; Surgery","score_opus":0.07253782938070465,"score_gpt":0.44738257168161294,"score_spread":0.3748447423009083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975824420","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":[0.9379284,0.000026384445,0.058742758,0.0012186639,0.000057899895,0.0017857555,0.000014027883,0.000031952866,0.00019418418],"genre_scores_gemma":[0.9449726,0.000002024621,0.054742124,0.0000045829893,0.00005434893,0.00017925553,0.000023848863,0.000009564087,0.000011684845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987151,0.00035742068,0.00046961568,0.00021808922,0.00014858221,0.00009120481],"domain_scores_gemma":[0.966593,0.03273286,0.0002979999,0.0001992378,0.00014672097,0.000030178058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055944937,0.00011805913,0.0005804615,0.00022986827,0.000025563166,0.0000016957429,0.000061049956,0.000027580772,0.0000056373633],"category_scores_gemma":[0.0050758757,0.00009024834,0.00016910897,0.00015479399,0.00055989274,0.00015634549,0.000023908804,0.000081642225,4.1915968e-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":[0.0006946627,0.0008336925,0.00070569466,0.014874351,0.000067561865,1.1620847e-8,0.040306736,0.000055112334,0.24176101,0.68497974,0.00024438178,0.015477072],"study_design_scores_gemma":[0.0007981322,0.017353794,0.013567136,0.0036216937,0.000061979445,1.8803681e-7,0.004883974,0.0016416472,0.010805787,0.9471429,0.000029104298,0.00009364709],"about_ca_topic_score_codex":0.0000114974655,"about_ca_topic_score_gemma":0.0000031095667,"teacher_disagreement_score":0.26216322,"about_ca_system_score_codex":0.00001971498,"about_ca_system_score_gemma":0.000012692391,"threshold_uncertainty_score":0.6076664},"labels":[],"label_agreement":null},{"id":"W2976627433","doi":"10.1093/biomet/asz048","title":"Causal inference with confounders missing not at random","year":2019,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; Institute of Education Sciences","keywords":"Confounding; Causal inference; Missing data; Estimator; Statistics; Econometrics; Observational study; Mathematics; Nonparametric statistics; Outcome (game theory); Inference; Causal model; Computer science; Artificial intelligence","score_opus":0.14942930539156363,"score_gpt":0.4019501723183518,"score_spread":0.25252086692678816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976627433","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":[0.7792824,0.00008800064,0.20233697,0.00030865258,0.00019758745,0.0009217556,0.000018800287,0.00082392123,0.016021943],"genre_scores_gemma":[0.94473094,0.000017415274,0.052176327,0.00018310046,0.000033946006,0.00002147532,0.000009089984,0.000043073782,0.0027846433],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984994,0.00005022429,0.0003013826,0.0003425975,0.00042679708,0.00037961823],"domain_scores_gemma":[0.99751997,0.0014780152,0.00020544484,0.00053076673,0.00014306698,0.00012273164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003659976,0.00024305895,0.00040445232,0.00048681512,0.00008590462,0.00006632032,0.00024276585,0.00013284718,0.0006367023],"category_scores_gemma":[0.00075351517,0.0001875047,0.000058479905,0.0010085918,0.00014361045,0.00022952148,0.00011630745,0.0001642935,0.00026590147],"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":[0.003461652,0.0006554827,0.047951743,0.0011377687,0.00059697375,0.00016482102,0.00279586,0.000025824576,0.5715082,0.31538916,0.007590286,0.04872222],"study_design_scores_gemma":[0.013152491,0.0021582232,0.0038350525,0.0009111728,0.00022206722,0.00016537642,0.00067224225,0.0008689055,0.73098654,0.19783522,0.046492446,0.0027002746],"about_ca_topic_score_codex":0.00003552566,"about_ca_topic_score_gemma":0.000020212748,"teacher_disagreement_score":0.16544856,"about_ca_system_score_codex":0.00031288236,"about_ca_system_score_gemma":0.000084986335,"threshold_uncertainty_score":0.764622},"labels":[],"label_agreement":null},{"id":"W2977740587","doi":"10.1016/j.jclinepi.2019.08.012","title":"Calculation of absolute risk for important outcomes in patients with and without a prognostic factor of interest","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"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; University Health Network; Toronto General Hospital; Impact; Ted Rogers Centre for Heart Research","funders":"","keywords":"Absolute risk reduction; Medicine; Risk factor; Relative risk; Guideline; Odds ratio; Outcome (game theory); Risk assessment; Statistics; Actuarial science; Confidence interval; Internal medicine; Mathematics; Computer science; Pathology","score_opus":0.43000849667316116,"score_gpt":0.5486397522909624,"score_spread":0.11863125561780125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977740587","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":[0.96048915,0.00002742609,0.03878891,0.00011328028,0.00008561307,0.0004659468,0.00001944988,0.0000054838733,0.000004751154],"genre_scores_gemma":[0.90328,0.000052386913,0.09659501,0.00003488115,0.000015512076,0.000003719213,0.0000010517483,0.000011144047,0.000006254799],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952375,0.00058486004,0.0037974368,0.00013657154,0.00008959296,0.00015399598],"domain_scores_gemma":[0.9699448,0.023491085,0.0059792334,0.00016712591,0.00034747424,0.000070302114],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005233057,0.00011680042,0.0020368008,0.00010278073,0.000006023241,0.0000010714473,0.00011357249,0.00018380665,0.000007643689],"category_scores_gemma":[0.07242015,0.00006926243,0.00018509357,0.00004638712,0.00014515241,0.00009969693,0.00003543688,0.0003643799,1.8962675e-7],"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":[0.00061779696,0.00023005148,0.99284333,0.00009802633,0.00008867015,3.011967e-7,0.000039186492,0.000008501031,0.000010938566,0.0044418583,0.000012328203,0.0016089916],"study_design_scores_gemma":[0.001666978,0.002901012,0.85152835,0.0002498159,0.00005468323,0.0000015716295,0.000009385207,0.0004455352,0.000021744723,0.14305401,0.000008487287,0.00005841194],"about_ca_topic_score_codex":0.000010229815,"about_ca_topic_score_gemma":0.00003326157,"teacher_disagreement_score":0.14131498,"about_ca_system_score_codex":0.000016623111,"about_ca_system_score_gemma":0.000056693094,"threshold_uncertainty_score":0.9353933},"labels":[],"label_agreement":null},{"id":"W2978101249","doi":"10.1017/s0140525x18000912","title":"Holding replication studies to mainstream standards of evidence","year":2018,"lang":"en","type":"letter","venue":"Behavioral and Brain Sciences","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":"Queen's University","funders":"","keywords":"Replication (statistics); Mainstream; Psychology; Value (mathematics); Cognitive psychology; Social psychology; Statistics; Mathematics; Political science; Law","score_opus":0.6873896146597199,"score_gpt":0.582156676757374,"score_spread":0.10523293790234589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978101249","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45795995,0.0010726318,0.006668281,0.5309865,0.00040161842,0.0016732513,0.0003035244,0.00048283965,0.00045140306],"genre_scores_gemma":[0.23142685,0.0014175653,0.49781016,0.25770003,0.003430949,0.0008416025,0.00003306912,0.00016165542,0.007178125],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99764884,0.00008446374,0.00042198438,0.0006740251,0.0008701744,0.00030051995],"domain_scores_gemma":[0.9977544,0.0008056098,0.00035124176,0.0005283803,0.00051249156,0.000047867932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002183551,0.00023872967,0.00045529832,0.00021357588,0.00019835161,0.00007000818,0.00048023334,0.00020708996,0.000023322355],"category_scores_gemma":[0.0026219743,0.00015589959,0.000055673292,0.00042160202,0.0012089567,0.00033603923,0.00027674052,0.00027051842,0.000001696694],"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":[0.0000060336606,0.000022909519,0.00053020683,0.00022219097,0.000007988399,0.000012238305,0.00085742766,1.4500824e-7,0.0032058202,0.00089041656,0.97463787,0.019606752],"study_design_scores_gemma":[0.0002548174,0.0065405834,0.0005723937,0.011297289,0.00035945693,0.000086946544,0.0029199787,0.00001984069,0.08199249,0.51852286,0.37536955,0.002063822],"about_ca_topic_score_codex":0.000037357582,"about_ca_topic_score_gemma":0.00002636396,"teacher_disagreement_score":0.5992683,"about_ca_system_score_codex":0.0001043096,"about_ca_system_score_gemma":0.0001291743,"threshold_uncertainty_score":0.63574004},"labels":[],"label_agreement":null},{"id":"W2978569536","doi":"10.1002/pds.4890","title":"Estimation of high‐dimensional propensity scores with multiple exposure levels","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Covariate; Propensity score matching; Pairwise comparison; Bupropion; Multinomial distribution; Varenicline; Statistics; Confounding; Cohort; Smoking cessation; Internal medicine; Nicotine; Mathematics","score_opus":0.1076302195864092,"score_gpt":0.38881148004335414,"score_spread":0.2811812604569449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978569536","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":[0.9311089,0.000105039064,0.0672713,0.00052009907,0.000072606155,0.0005406434,0.000037126356,0.00013015007,0.00021416863],"genre_scores_gemma":[0.90108186,0.00002808882,0.098426454,0.00027497965,0.000019867688,0.000018854711,0.00001732062,0.000014661736,0.00011789832],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99848425,0.00043327844,0.00044965587,0.00029901887,0.00011372131,0.00022008429],"domain_scores_gemma":[0.9957598,0.0035253866,0.00031364142,0.0002276727,0.00010620321,0.00006731558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015191428,0.00018395556,0.00055760285,0.000054694843,0.00007105051,0.000002280519,0.0001032506,0.00009050652,0.00014444931],"category_scores_gemma":[0.0010140907,0.00012945801,0.000036274938,0.00007801507,0.00020471124,0.00020780422,0.00009408713,0.00024667915,0.000011627133],"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":[0.0033384254,0.0004576319,0.6200065,0.0010090462,0.00033863116,0.000018917202,0.0008679029,0.013009548,0.03085809,0.28388363,0.004291587,0.041920114],"study_design_scores_gemma":[0.0048954263,0.00061486993,0.25356516,0.00051544746,0.00021743905,0.00011682481,0.00006574679,0.04766934,0.16725755,0.52388304,0.00031910057,0.0008800751],"about_ca_topic_score_codex":0.00007413472,"about_ca_topic_score_gemma":0.000021146374,"teacher_disagreement_score":0.36644134,"about_ca_system_score_codex":0.00002345731,"about_ca_system_score_gemma":0.00004012449,"threshold_uncertainty_score":0.52791446},"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":"W2980305249","doi":"10.1093/aje/kwz233","title":"The Critical Importance of Asking Good Questions: The Role of Epidemiology Doctoral Training Programs","year":2019,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":"National Institute of Allergy and Infectious Diseases; University of North Carolina at Chapel Hill; National Institutes of Health; McGill University","keywords":"Coursework; Curriculum; Process (computing); Focus (optics); Computer science; Space (punctuation); Medical education; Data science; Management science; Engineering ethics; Mathematics education; Psychology; Medicine; Pedagogy","score_opus":0.19970712353999379,"score_gpt":0.47289733371775317,"score_spread":0.27319021017775935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980305249","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":[0.8158301,0.008230625,0.15925454,0.013440058,0.00057729846,0.0007737008,0.000013657925,0.000097861244,0.0017821824],"genre_scores_gemma":[0.84416974,0.00029245988,0.15496372,0.0004048063,0.00011817815,0.000017497796,0.0000010025449,0.000021598962,0.0000110042365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928477,0.0034513257,0.00266057,0.00022825887,0.00016235115,0.00064979045],"domain_scores_gemma":[0.9306767,0.06422624,0.0039211935,0.00060517027,0.00045218036,0.00011849723],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.015084539,0.00021695261,0.0016843977,0.00008990945,0.000088256806,0.000003783948,0.0007451949,0.0001215441,0.000033440367],"category_scores_gemma":[0.07321082,0.00011694479,0.0003456224,0.00027091373,0.002867779,0.00014529555,0.000099755,0.0008774907,0.000001948145],"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":[0.000078207806,0.000057993082,0.19251382,0.000020344904,0.000091172005,0.0000022303957,0.0004222194,0.000046563,0.00047586573,0.7341898,0.00007801178,0.072023764],"study_design_scores_gemma":[0.00012856656,0.0019474481,0.00400571,0.0002008978,0.000074077274,0.00026571145,0.003545425,0.00037262528,0.00015853965,0.9855881,0.003586367,0.00012652972],"about_ca_topic_score_codex":0.00009600674,"about_ca_topic_score_gemma":0.000031002124,"teacher_disagreement_score":0.2513983,"about_ca_system_score_codex":0.000068286216,"about_ca_system_score_gemma":0.0001769094,"threshold_uncertainty_score":0.99984586},"labels":[],"label_agreement":null},{"id":"W2980883791","doi":"10.1002/cpt.1698","title":"Reproducing Protocol‐Based Studies Using Parameterizable Tools—Comparison of Analytic Approaches Used by Two Medical Product Surveillance Networks","year":2019,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Canadian Society of Nephrology; Institut universitaire en santé mentale de Montréal; Jewish General Hospital; McGill University","funders":"Canadian Institutes of Health Research; U.S. Food and Drug Administration","keywords":"Protocol (science); Medicine; Observational study; Hazard; Acute pancreatitis; Emergency medicine; Pharmacology; Computer science; Internal medicine; Pathology; Alternative medicine","score_opus":0.7218767300534139,"score_gpt":0.6223373168771107,"score_spread":0.09953941317630322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980883791","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":[0.87542593,0.00082613365,0.076602176,0.0020155434,0.0013376322,0.04296837,0.00001845388,0.0006546961,0.00015104315],"genre_scores_gemma":[0.9558219,0.000055937388,0.036455125,0.0022479256,0.00043739963,0.00478056,0.000014033553,0.00010702936,0.00008012955],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942008,0.0013768129,0.0021472871,0.0010849574,0.000543113,0.000647025],"domain_scores_gemma":[0.9908715,0.0063187657,0.0012755312,0.0010591759,0.00031295465,0.0001620753],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0048748655,0.00044561416,0.0017913489,0.00009124795,0.00010101897,0.00002620893,0.0006934214,0.00034675805,0.00015467171],"category_scores_gemma":[0.0010284636,0.00037311882,0.00026120292,0.00047115155,0.00092609756,0.00018475603,0.0002523658,0.0011754198,0.000006583374],"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":[0.00465493,0.015134899,0.7404344,0.0037155987,0.00948135,0.00004857138,0.0017252958,0.037388805,0.1131882,0.0010469942,0.020004027,0.053176947],"study_design_scores_gemma":[0.008931776,0.002709807,0.0006281814,0.00054718356,0.0014722664,0.000014576376,0.0004435981,0.8253336,0.14146426,0.011162648,0.00561908,0.0016730492],"about_ca_topic_score_codex":0.0000048689703,"about_ca_topic_score_gemma":0.000005814567,"teacher_disagreement_score":0.7879448,"about_ca_system_score_codex":0.00012687365,"about_ca_system_score_gemma":0.00028469396,"threshold_uncertainty_score":0.9998721},"labels":[],"label_agreement":null},{"id":"W2981744747","doi":"10.1503/cmaj.190085","title":"Testing group differences for confounder selection in nonrandomized studies: flawed practice","year":2019,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Observational study; Confounding; Random assignment; Selection (genetic algorithm); Medicine; Key (lock); Selection bias; Intervention (counseling); Computer science; Family medicine; Pathology; Machine learning; Computer security; Nursing","score_opus":0.1467618169955665,"score_gpt":0.41679078570413347,"score_spread":0.27002896870856696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981744747","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":[0.8457897,0.0005921072,0.09075265,0.034782887,0.0034405035,0.00474467,0.000034436394,0.0004567224,0.019406375],"genre_scores_gemma":[0.9264741,0.00011709709,0.06599211,0.0057377606,0.00093109475,0.00014768244,0.0000038819317,0.00004181492,0.0005544889],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977017,0.0003538546,0.0006077392,0.00016628091,0.00072671124,0.00044370338],"domain_scores_gemma":[0.9869367,0.011122461,0.00053318497,0.00005864773,0.00096915796,0.000379867],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004960869,0.00013630863,0.00043487857,0.00018338865,0.00016026296,0.0000790748,0.00015870002,0.00028396695,0.0003417404],"category_scores_gemma":[0.07677388,0.0001182959,0.00006651554,0.00028847688,0.000026567819,0.00037012267,0.000011877452,0.0007502997,0.000018236622],"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":[0.0017681713,0.0010842881,0.36582437,0.0008169887,0.0033476716,0.00046849807,0.012309477,0.000042089938,0.003317118,0.31269962,0.14707516,0.15124655],"study_design_scores_gemma":[0.038458362,0.0016816444,0.021162048,0.0021516832,0.00036673193,0.00090745353,0.019997628,0.010089265,0.00019211759,0.7958429,0.10748076,0.0016694044],"about_ca_topic_score_codex":0.0006109552,"about_ca_topic_score_gemma":0.014349434,"teacher_disagreement_score":0.48314327,"about_ca_system_score_codex":0.001813983,"about_ca_system_score_gemma":0.0010704824,"threshold_uncertainty_score":0.93100286},"labels":[],"label_agreement":null},{"id":"W2981913938","doi":"10.1016/b978-0-12-811316-5.00008-2","title":"Detailed Treatment Plan","year":2019,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","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":"Université Laval; Centre for Interdisciplinary Research in Rehabilitation","funders":"","keywords":"Plan (archaeology); Computer science; Geography; Archaeology","score_opus":0.11963435797991798,"score_gpt":0.35094809074189165,"score_spread":0.23131373276197367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981913938","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004381067,0.00025318848,0.0001614694,0.000019785315,0.00017930228,0.0013454829,0.0000696351,0.00059014227,0.99733716],"genre_scores_gemma":[0.00028521483,0.0001296366,0.011214679,0.00010478334,0.00020410358,0.00010082812,0.000036508518,0.00021166058,0.98771256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982421,0.000023579798,0.0005398584,0.00052384334,0.0003140041,0.00035663892],"domain_scores_gemma":[0.9979138,0.00031340471,0.00040605583,0.0011589428,0.0000888682,0.00011892088],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013048775,0.00068451447,0.00095995533,0.00015305383,0.00005972864,0.000033988406,0.00031705527,0.000518923,0.00078014744],"category_scores_gemma":[0.000036105208,0.0005577883,0.0003250783,0.000006643942,0.00010022965,0.000043235796,0.00011489356,0.0003880271,0.0009408467],"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":[0.000013980345,0.000014033239,0.0000047841118,0.00008923419,0.00014230028,0.00004016207,0.00012152962,6.6601636e-8,0.000043973305,0.293839,0.00027732502,0.70541364],"study_design_scores_gemma":[0.00017696474,0.00019115704,7.594869e-7,0.00030364012,0.00013354674,0.000012970189,0.0000029979897,0.0000012915466,0.00047662397,0.44310492,0.5552243,0.00037079342],"about_ca_topic_score_codex":2.0142575e-7,"about_ca_topic_score_gemma":0.00005856003,"teacher_disagreement_score":0.70504284,"about_ca_system_score_codex":0.0004045656,"about_ca_system_score_gemma":0.00018116801,"threshold_uncertainty_score":0.99983704},"labels":[],"label_agreement":null},{"id":"W2982005826","doi":"10.1016/j.jamcollsurg.2019.10.003","title":"Use of Propensity Score Methodology in Contemporary High-Impact Surgical Literature","year":2019,"lang":"en","type":"article","venue":"Journal of the American College of Surgeons","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; McGill University Health Centre; University of Ottawa","funders":"","keywords":"Propensity score matching; Medicine; Covariate; Confounding; Observational study; Odds ratio; Univariate; Odds; Selection bias; Meta-analysis; Study heterogeneity; Multivariate statistics; Univariate analysis; Multivariate analysis; Internal medicine; Statistics; Logistic regression; Pathology","score_opus":0.37125641664828146,"score_gpt":0.42437729479580066,"score_spread":0.0531208781475192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982005826","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":[0.9983136,0.00009690802,0.0003294914,0.00048814242,0.00013036179,0.00034951768,0.00014485935,0.000011553257,0.00013555212],"genre_scores_gemma":[0.97379375,0.00006927963,0.025842646,0.000043222048,0.00001915639,0.0000017923807,7.6568665e-7,0.000021067865,0.00020831251],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972912,0.0010156698,0.000984695,0.00013145816,0.00036644915,0.00021049519],"domain_scores_gemma":[0.99289405,0.0035421655,0.0024815688,0.0004898321,0.00051258475,0.00007977716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016682565,0.0001855292,0.0014481638,0.0003095273,0.000020172558,0.00000784452,0.00041694276,0.000082339,0.000040201245],"category_scores_gemma":[0.0017724661,0.000108571716,0.0003950161,0.0009533399,0.0003871583,0.00032192035,0.00015844125,0.000573222,5.3653383e-7],"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":[0.004044996,0.0009414407,0.9139185,0.0002604109,0.00045951188,0.00077862927,0.00055790955,0.0002360022,0.03411027,0.03207768,0.011752435,0.0008622074],"study_design_scores_gemma":[0.004014041,0.006104739,0.615186,0.005975905,0.00027866528,0.0037833778,0.0011792639,0.00014011007,0.11374951,0.24450587,0.003945149,0.0011374145],"about_ca_topic_score_codex":0.0003140133,"about_ca_topic_score_gemma":0.00004108524,"teacher_disagreement_score":0.29873255,"about_ca_system_score_codex":0.00009562799,"about_ca_system_score_gemma":0.00037366818,"threshold_uncertainty_score":0.44274262},"labels":[],"label_agreement":null},{"id":"W2982251593","doi":"10.1093/eurheartj/ehz746.0648","title":"P5707An evaluation of the use of propensity scores in cardiovascular literature: a systematic review and recommendations","year":2019,"lang":"en","type":"review","venue":"European Heart Journal","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":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Medicine; Observational study; Systematic review; MEDLINE; Medical literature; Randomized controlled trial; Psychological intervention; New england; Family medicine; Internal medicine; Pathology; Psychiatry","score_opus":0.6694194216818972,"score_gpt":0.4876004993261666,"score_spread":0.18181892235573055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982251593","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":[0.00001678207,0.9955821,0.00019170437,0.000038618513,0.000079037614,0.0039825696,0.00002195447,0.00001246593,0.000074764735],"genre_scores_gemma":[0.000045329165,0.995472,0.0042854655,0.000035801335,0.000028533663,0.00003035768,0.000006120538,0.000048252507,0.00004810646],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9890282,0.008558785,0.001464799,0.00020443236,0.0006048066,0.00013896235],"domain_scores_gemma":[0.9964068,0.0005610391,0.0014323338,0.000955774,0.00060043694,0.000043616394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009857075,0.00026198366,0.00275691,0.00018720188,0.000053376676,0.00006187663,0.0003008261,0.00006687392,0.000015159803],"category_scores_gemma":[0.005948734,0.0001478305,0.00073078106,0.00044358388,0.000058121692,0.00025277858,0.00018763868,0.000760049,0.000003988072],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8059755e-7,0.00004101379,0.000016899783,0.974505,0.00034986186,0.000004313827,0.00012378099,0.0000026154116,6.9402375e-7,0.00023684243,0.0015005224,0.023217592],"study_design_scores_gemma":[0.000103186576,0.0000343103,0.000033491207,0.9546854,0.007490671,0.00074674963,0.0000038119806,0.0000067789533,0.0000017435427,0.00055367075,0.036181778,0.00015839924],"about_ca_topic_score_codex":0.0000015343104,"about_ca_topic_score_gemma":0.00000179174,"teacher_disagreement_score":0.034681257,"about_ca_system_score_codex":0.00011529901,"about_ca_system_score_gemma":0.00019914751,"threshold_uncertainty_score":0.71216196},"labels":[],"label_agreement":null},{"id":"W2982419922","doi":"10.1080/07350015.2019.1684300","title":"Sharp Bounds on Functionals of the Joint Distribution in the Analysis of Treatment Effects","year":2019,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","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":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Mathematical optimization; Identification (biology); Computer science; Joint (building); Focus (optics); Distribution (mathematics); Selection (genetic algorithm); Upper and lower bounds; Joint probability distribution; Econometrics; Applied mathematics; Mathematics; Statistics; Machine learning; Engineering","score_opus":0.07145711777495668,"score_gpt":0.3386223486793442,"score_spread":0.26716523090438754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982419922","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":[0.9558604,0.00003353588,0.043440066,0.000101361904,0.00011036788,0.0001301099,0.0002446754,0.000001508567,0.000078008605],"genre_scores_gemma":[0.99805236,0.00012638117,0.0017487945,0.000017316757,0.000018868517,0.0000026738285,0.000009065302,0.000004032058,0.00002049905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9993174,0.000043757056,0.00044391485,0.00005591223,0.00007696255,0.000062074294],"domain_scores_gemma":[0.99827886,0.000787672,0.00067289977,0.0001467278,0.00010178658,0.000012062985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031495394,0.00007462017,0.00036869652,0.00009159527,0.000018761697,0.000012068433,0.00007644575,0.00002876498,0.00003920178],"category_scores_gemma":[0.00019309545,0.000039557533,0.00006770808,0.00013933018,0.000047199643,0.00005576653,0.000014081005,0.000059407957,5.6572503e-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":[0.00044981504,0.00096045644,0.13293517,0.000724293,0.0021393402,0.000011025005,0.0014483102,0.025916446,0.0021092284,0.80990744,0.0032441167,0.020154348],"study_design_scores_gemma":[0.00064210047,0.0004694569,0.8632458,0.00018298958,0.000726406,0.000011510963,0.00015033394,0.0042111077,0.0012340215,0.12881535,0.00022111228,0.000089802816],"about_ca_topic_score_codex":0.00005024737,"about_ca_topic_score_gemma":0.00005029512,"teacher_disagreement_score":0.7303106,"about_ca_system_score_codex":0.00016355354,"about_ca_system_score_gemma":0.000060648188,"threshold_uncertainty_score":0.16131094},"labels":[],"label_agreement":null},{"id":"W2983970670","doi":"10.1920/wp.cem.2019.2119","title":"Optimal Data Collection for Randomized Control Trials","year":2019,"lang":"en","type":"report","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"York University; Economic and Social Research Council; University of Pennsylvania; Princeton University","keywords":"Randomized controlled trial; Data collection; Geography; Computer science; Statistics; Mathematics; Medicine","score_opus":0.5368749035102747,"score_gpt":0.5423176930024491,"score_spread":0.005442789492174471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983970670","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":[0.000004931953,0.00025307277,0.9104407,0.00011561556,0.0011470558,0.013892767,0.0007857999,0.00068648346,0.07267358],"genre_scores_gemma":[0.0006273887,0.0020435485,0.8049439,0.00009668406,0.001299647,0.004075114,0.0019159311,0.0002358239,0.18476191],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9955288,0.0006283988,0.0020976197,0.0007034945,0.00070326414,0.0003383983],"domain_scores_gemma":[0.96800774,0.026806861,0.0021444529,0.0018974434,0.0010794307,0.00006409349],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024172267,0.00046438575,0.0049244137,0.00021986324,0.00007038718,0.00008101349,0.000684076,0.0007217363,0.0006584662],"category_scores_gemma":[0.09989295,0.0003251771,0.0006479129,0.00010476395,0.00008245611,0.0002188914,0.0001843425,0.00034606183,0.000019697773],"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":[0.029954268,0.00008276113,6.8588145e-7,0.0007067798,0.0010514451,0.0000017493613,0.00001461906,0.000005625436,0.00006853866,0.0169624,0.9495446,0.0016065311],"study_design_scores_gemma":[0.38057527,0.0003126165,1.399494e-7,0.0005931064,0.004869559,0.000054470474,0.000036852547,0.01188219,0.0015573706,0.28789657,0.31103754,0.0011843303],"about_ca_topic_score_codex":0.00009240893,"about_ca_topic_score_gemma":0.000024464907,"teacher_disagreement_score":0.63850707,"about_ca_system_score_codex":0.00031692558,"about_ca_system_score_gemma":0.0015300252,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W2991051464","doi":"10.23889/ijpds.v4i3.1319","title":"High-dimensional propensity score adjustment in HIV research using linked administrative health data","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","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":true,"ca_institutions":"AIDS Vancouver","funders":"","keywords":"Observational study; Medicine; Confounding; Context (archaeology); Propensity score matching; Population; Environmental health; Geography","score_opus":0.8021241040371514,"score_gpt":0.6189031968739147,"score_spread":0.1832209071632367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991051464","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":[0.94085234,0.000046272562,0.051955357,0.0024754796,0.0018022333,0.0015344152,0.001226942,0.000055800185,0.000051130053],"genre_scores_gemma":[0.7738064,0.000018777568,0.22479345,0.00012316699,0.0002355371,0.0000069273765,0.00090660714,0.0000141840965,0.00009495925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960469,0.0001642741,0.00074392377,0.0006907917,0.0019338753,0.00042025856],"domain_scores_gemma":[0.9966174,0.0004262547,0.00051854906,0.0011258905,0.0011585519,0.00015336943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077383826,0.0001391526,0.00024939273,0.0005554735,0.00032375395,0.0002466645,0.0033820025,0.000051423518,0.00007328224],"category_scores_gemma":[0.0029854525,0.00011999827,0.00002220676,0.0004798673,0.00020244086,0.004156637,0.0018046848,0.00049342896,0.00001196906],"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":[0.0012038779,0.001637172,0.111018725,0.00018536845,0.00014585031,0.000086350075,0.0009342891,0.006022052,0.017185263,0.7966037,0.021534352,0.043443013],"study_design_scores_gemma":[0.002219895,0.0005777281,0.11429386,0.0016472734,0.00001676368,0.00041119725,0.00034015343,0.38927305,0.0011167715,0.48779306,0.0016677957,0.0006424575],"about_ca_topic_score_codex":0.000405912,"about_ca_topic_score_gemma":0.00036494766,"teacher_disagreement_score":0.38325098,"about_ca_system_score_codex":0.0009163146,"about_ca_system_score_gemma":0.0012089484,"threshold_uncertainty_score":0.62846583},"labels":[],"label_agreement":null},{"id":"W2992485813","doi":"10.1080/02664763.2021.1911966","title":"Confounding adjustment methods for multi-level treatment comparisons under lack of positivity and unknown model specification","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Causal Inference Techniques","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 Laval","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Covariate; Estimator; Observational study; Context (archaeology); Specification; Confounding; Matching (statistics); Variance (accounting); Propensity score matching","score_opus":0.6386904553834739,"score_gpt":0.5704813769769004,"score_spread":0.06820907840657353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992485813","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":[0.0017960095,0.00010400932,0.9971441,0.000053665066,0.000051192124,0.00030055753,0.0002519497,0.000013429598,0.00028509658],"genre_scores_gemma":[0.055501755,0.00025251115,0.9440225,0.000032648386,0.00003167101,0.000016012273,0.000015532454,0.000020894173,0.000106478175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887884,0.00005651694,0.0006385508,0.00013096648,0.00015105591,0.00014405343],"domain_scores_gemma":[0.9971383,0.0013983244,0.0007419564,0.00016292119,0.0004782935,0.00008017684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045887366,0.00015157711,0.0005128953,0.000066595196,0.000055333247,0.000019808818,0.000067472865,0.00006713826,0.000008265273],"category_scores_gemma":[0.00020527815,0.00013186959,0.00005455872,0.000064680964,0.000076310156,0.00005488545,0.000028913639,0.000118635966,2.1909722e-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":[0.000094927374,0.00041253938,0.0000065489858,0.000099132725,0.00013071213,0.0000020528473,0.00039924833,0.00086071325,0.039383594,0.92862886,0.0005285514,0.029453136],"study_design_scores_gemma":[0.0013769043,0.00025533032,0.00025043977,0.00006321583,0.00033710516,0.000018053046,0.00056223024,0.08824231,0.11205124,0.796358,0.0003212281,0.00016394557],"about_ca_topic_score_codex":0.0000013457395,"about_ca_topic_score_gemma":0.000013331956,"teacher_disagreement_score":0.13227084,"about_ca_system_score_codex":0.00023795872,"about_ca_system_score_gemma":0.00016026325,"threshold_uncertainty_score":0.5377486},"labels":[],"label_agreement":null},{"id":"W2993516287","doi":"10.1093/neuros/nyz509","title":"Comparing Effects of Treatment: Controlling for Confounding","year":2019,"lang":"en","type":"review","venue":"Neurosurgery","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Confounding; Medicine; Propensity score matching; Sample size determination; Causal inference; Matching (statistics); Research design; Statistics; Surgery; Internal medicine; Mathematics","score_opus":0.3940133581819556,"score_gpt":0.47494344151657364,"score_spread":0.08093008333461804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993516287","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":[0.000063556174,0.97664976,0.01815293,0.0000011006086,0.00096453854,0.003432119,0.000032174237,0.00029681428,0.00040700633],"genre_scores_gemma":[0.00029303817,0.99543995,0.002992028,0.000010827811,0.00013696111,0.00064015074,0.00002891859,0.00015100207,0.0003071393],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797493,0.00014935367,0.000972328,0.00039987525,0.0001354985,0.00036804206],"domain_scores_gemma":[0.9802346,0.017969051,0.0011086022,0.000558213,0.00007228893,0.00005722741],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027319393,0.0005087004,0.003988381,0.00026043114,0.00004891336,0.000031515898,0.00020202379,0.00024878263,0.0000041654926],"category_scores_gemma":[0.001283425,0.00040800322,0.0009782276,0.00014835493,0.000049010174,0.00008722551,0.000047762598,0.00019782035,0.000008534124],"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":[0.000033054257,0.00019836763,0.00003733104,0.25059536,0.00047546814,0.00002713356,0.00005077938,0.000006108477,0.00011827278,0.04677808,0.00048908585,0.70119095],"study_design_scores_gemma":[0.0006055977,0.00042798088,3.027749e-7,0.036374837,0.0024080155,0.000025347112,0.0000023694615,0.00016334202,0.0005468966,0.01439596,0.9444253,0.00062407786],"about_ca_topic_score_codex":0.0000027164824,"about_ca_topic_score_gemma":5.3813187e-7,"teacher_disagreement_score":0.94393617,"about_ca_system_score_codex":0.00020795339,"about_ca_system_score_gemma":0.00016781157,"threshold_uncertainty_score":0.99983716},"labels":[],"label_agreement":null},{"id":"W2993745637","doi":"10.1002/sim.8419","title":"Causal inference with noisy data: Bias analysis and estimation approaches to simultaneously addressing missingness and misclassification in binary outcomes","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Missing data; Estimator; Inference; Causal inference; Computer science; Statistics; Estimation; Statistical inference; Econometrics; Binary number; Artificial intelligence; Mathematics; Machine learning","score_opus":0.43835106484182346,"score_gpt":0.46189622136305486,"score_spread":0.023545156521231403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993745637","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":[0.34406757,0.000039872793,0.6547899,0.0004369936,0.000018299688,0.00041761936,0.00006805732,0.00004475009,0.00011690544],"genre_scores_gemma":[0.6164043,0.000019410916,0.38332173,0.000036838497,0.0000066972093,0.000014050903,0.00014110075,0.000013146657,0.00004272461],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998489,0.00009799332,0.00046027612,0.00045119374,0.0003012502,0.0002002488],"domain_scores_gemma":[0.9964012,0.002725663,0.00020103701,0.0005187763,0.00006759108,0.000085748135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007350849,0.0002026343,0.0005546054,0.0005182182,0.000038929873,0.000036242687,0.00016592098,0.00007419361,0.000019274536],"category_scores_gemma":[0.0034897944,0.0001525067,0.0000049203236,0.00068964326,0.00019450224,0.00020322886,0.000111785,0.00021396684,0.0000011971075],"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":[0.00022229642,0.00027906316,0.81923914,0.0013891842,0.00020236496,0.0001755462,0.009297228,0.005981404,0.0016246923,0.08281299,0.000227177,0.07854892],"study_design_scores_gemma":[0.0011725515,0.0004491683,0.23300417,0.0011046678,0.00038965588,0.000013262447,0.0017481911,0.6685987,0.00012358067,0.09289869,0.000024815576,0.00047254405],"about_ca_topic_score_codex":0.00024843347,"about_ca_topic_score_gemma":0.0013018639,"teacher_disagreement_score":0.6626173,"about_ca_system_score_codex":0.00007010633,"about_ca_system_score_gemma":0.000046846533,"threshold_uncertainty_score":0.62190425},"labels":[],"label_agreement":null},{"id":"W2995122033","doi":"","title":"Learning Disentangled Representations for CounterFactual Regression","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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 Alberta","funders":"","keywords":"Counterfactual thinking; Leverage (statistics); Computer science; Observational study; Selection bias; Covariate; Machine learning; Selection (genetic algorithm); Econometrics; Population; Model selection; Regression; Artificial intelligence; Statistics; Mathematics; Psychology","score_opus":0.279971621243436,"score_gpt":0.48483052989203934,"score_spread":0.20485890864860334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995122033","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":[0.18985574,0.00002436405,0.6462003,0.03767588,0.0009152503,0.0025203591,0.00018286117,0.0031302287,0.11949501],"genre_scores_gemma":[0.9781236,0.000051485087,0.015434331,0.0003079081,0.00031105668,0.00037462532,0.0003079486,0.00006205786,0.0050269603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99767816,0.00019478648,0.00056015566,0.00065204664,0.00060743163,0.00030743645],"domain_scores_gemma":[0.99681425,0.0016087723,0.00043725743,0.00026832975,0.00068372354,0.00018767553],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022989268,0.0002813541,0.0003031041,0.00017324653,0.00041167316,0.00020898871,0.00048118635,0.00011355768,0.0011758658],"category_scores_gemma":[0.007471581,0.0002710768,0.0001751348,0.00023654167,0.000123843,0.00045821525,0.00013919761,0.0006730023,0.00010094175],"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":[0.000807004,0.00037573642,0.014420477,0.000091227404,0.00033401433,0.000035201832,0.014887475,0.006120584,0.041218244,0.89101,0.018440971,0.012259071],"study_design_scores_gemma":[0.0049834005,0.0027256901,0.0032880728,0.00084232446,0.00026488962,0.00004452811,0.031201864,0.34150648,0.039805204,0.5321841,0.041088037,0.002065397],"about_ca_topic_score_codex":0.000020547714,"about_ca_topic_score_gemma":0.000008112226,"teacher_disagreement_score":0.7882679,"about_ca_system_score_codex":0.00011496853,"about_ca_system_score_gemma":0.00009060157,"threshold_uncertainty_score":0.99997413},"labels":[],"label_agreement":null},{"id":"W2995591168","doi":"10.1111/bmsp.12194","title":"The danger of conflating level‐specific effects of control variables when primary interest lies in level‐2 effects","year":2019,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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":"","keywords":"Conflation; Cluster (spacecraft); Variable (mathematics); Control variable; Econometrics; Multilevel model; Estimation; Control (management); Statistics; Variables; Psychology; Computer science; Mathematics; Economics; Epistemology; Artificial intelligence","score_opus":0.0946494624905834,"score_gpt":0.3728073056028315,"score_spread":0.2781578431122481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995591168","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":[0.24508308,0.0013477345,0.75057316,0.00017615265,0.00018568957,0.0005992572,0.000061029965,0.000016108555,0.0019578058],"genre_scores_gemma":[0.8198214,0.0003071079,0.17961766,0.000097947406,0.000037441438,0.000013369056,0.0000013606509,0.00002621757,0.0000775019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751294,0.0004115092,0.0013015794,0.00018898622,0.00028388933,0.00030107476],"domain_scores_gemma":[0.9803374,0.018528147,0.000617507,0.0002062128,0.00021328108,0.00009747048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013515154,0.00018054536,0.0010396453,0.00009086921,0.000038353686,0.000033077704,0.0002819761,0.00016066621,0.000093910414],"category_scores_gemma":[0.0045233136,0.00013711648,0.00008190862,0.00008160687,0.0005658722,0.00011040391,0.00007150819,0.0005222717,0.0000037333568],"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":[0.00034782675,0.0006039984,0.00049879286,0.0029505307,0.00014843392,0.00029669618,0.00039229996,6.829562e-7,0.013759762,0.8922089,0.002383933,0.086408146],"study_design_scores_gemma":[0.0020557626,0.00083272986,0.0110242525,0.0023903248,0.00005654746,0.00075175596,0.00006212022,0.00006425487,0.0010620115,0.98141754,0.00013496322,0.00014774792],"about_ca_topic_score_codex":0.0000050560843,"about_ca_topic_score_gemma":0.000007836086,"teacher_disagreement_score":0.5747383,"about_ca_system_score_codex":0.000026718737,"about_ca_system_score_gemma":0.000031981555,"threshold_uncertainty_score":0.5591448},"labels":[],"label_agreement":null},{"id":"W2995714276","doi":"10.1016/j.annepidem.2019.12.006","title":"Visualization tool of variable selection in bias–variance tradeoff for inverse probability weights","year":2019,"lang":"en","type":"article","venue":"Annals of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University Health Centre; McGill University; Jewish General Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Confounding; Propensity score matching; Statistics; Inverse probability; Estimator; Medicine; Variance (accounting); Econometrics; Mathematics","score_opus":0.44819868361695125,"score_gpt":0.49089526374425557,"score_spread":0.04269658012730432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995714276","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":[0.5338122,0.00003795334,0.46405667,0.00028645885,0.000061621846,0.0011051606,0.00001988497,0.00006700343,0.00055299356],"genre_scores_gemma":[0.5208591,0.000076778226,0.4782502,0.00045450148,0.00003356661,0.00014113609,0.000021238775,0.000021441907,0.00014200248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99779254,0.0005384472,0.0010163132,0.0002862492,0.000065476685,0.0003009978],"domain_scores_gemma":[0.9933215,0.005404715,0.0006995724,0.00025172599,0.00029372558,0.00002876023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004694317,0.00012837241,0.00070918095,0.00012813583,0.000014506424,0.0000010336269,0.00013242473,0.0002393319,0.00007737267],"category_scores_gemma":[0.018245934,0.000116658055,0.000084658255,0.0002902237,0.00008752063,0.0001972689,0.000026938666,0.00010698725,0.0000021866085],"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":[0.00011484208,0.00015967588,0.036992513,0.0004419882,0.000017748707,4.8592728e-8,0.00008274695,0.0003500944,0.0054979925,0.9548353,0.0012176563,0.00028941224],"study_design_scores_gemma":[0.00022160284,0.0003964965,0.0034539546,0.000110750756,0.000008226985,0.0000010331039,0.000009465416,0.008354883,0.024492642,0.96198803,0.0008595845,0.00010331756],"about_ca_topic_score_codex":0.000101470316,"about_ca_topic_score_gemma":0.00005010185,"teacher_disagreement_score":0.033538558,"about_ca_system_score_codex":0.000030997806,"about_ca_system_score_gemma":0.00007169339,"threshold_uncertainty_score":0.9900238},"labels":[],"label_agreement":null},{"id":"W2995768992","doi":"10.1002/sim.8410","title":"Safety surveillance and the estimation of risk in select populations: Flexible methods to control for confounding while targeting marginal comparisons via standardization","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"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 Institutes of Health; U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Center for Advancing Translational Sciences; U.S. Department of Health and Human Services","keywords":"Covariate; Causal inference; Confounding; Computer science; Inference; Statistics; Context (archaeology); Econometrics; Machine learning; Mathematics; Artificial intelligence","score_opus":0.07507788337893141,"score_gpt":0.472539222786533,"score_spread":0.3974613394076016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995768992","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":[0.0032829049,0.000100498735,0.99453866,0.00019798243,0.00009746074,0.001394282,0.00023269306,0.000032601532,0.00012291793],"genre_scores_gemma":[0.4542689,0.000021410184,0.5455739,0.000020949494,0.000012919779,0.000038359492,0.00004815819,0.000009450818,0.0000059402523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983531,0.00042172323,0.00069000834,0.00016678235,0.00019680735,0.00017154163],"domain_scores_gemma":[0.9910642,0.00817221,0.00036160438,0.00015941296,0.00021303871,0.000029528926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005230301,0.000117764284,0.00054442434,0.00015811225,0.0000595177,0.000008235054,0.00008115865,0.000045683973,0.00002853169],"category_scores_gemma":[0.01230327,0.000088933266,0.000012101783,0.0003037251,0.00011824283,0.000060704617,0.000020321762,0.00016486328,3.430373e-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":[0.0007212511,0.000026349466,0.034991454,0.000256933,0.00001927734,3.3726843e-7,0.0015918955,0.02522703,0.0006877421,0.92537236,0.0006852843,0.010420085],"study_design_scores_gemma":[0.002845278,0.00012675002,0.008870582,0.00019946219,0.000026160955,8.1074387e-7,0.000282687,0.36605728,0.00018584997,0.6212421,0.0000737618,0.0000892472],"about_ca_topic_score_codex":0.00016585254,"about_ca_topic_score_gemma":0.0002795341,"teacher_disagreement_score":0.450986,"about_ca_system_score_codex":0.000117289725,"about_ca_system_score_gemma":0.00003179164,"threshold_uncertainty_score":0.9960165},"labels":[],"label_agreement":null},{"id":"W2996569227","doi":"10.1257/aer.20171634","title":"A Theory of Experimenters: Robustness, Randomization, and Balance","year":2020,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":78,"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":"","keywords":"Robustness (evolution); Ambiguity; Quantile; Economics; Econometrics; Decision maker; SAFER; Computer science; Balance (ability); Randomization; Sample size determination; Preference; Microeconomics; Mathematics; Statistics; Randomized controlled trial; Psychology; Management science; Medicine","score_opus":0.09297531679658333,"score_gpt":0.3749022126952344,"score_spread":0.28192689589865105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996569227","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":[0.045065768,0.11089894,0.8249138,0.0062576085,0.00007534933,0.0029380976,0.000035238478,0.00052067236,0.009294541],"genre_scores_gemma":[0.6274177,0.2488807,0.11679302,0.006419587,0.00008407182,0.00026938578,0.000009139896,0.00006910056,0.000057294044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992343,0.00009943769,0.0003807817,0.00016877301,0.000029803037,0.00008691331],"domain_scores_gemma":[0.9990807,0.00025967858,0.00039818554,0.00018986824,0.000018682396,0.000052872096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023502458,0.00010541777,0.00060780527,0.000012841447,0.000012135658,0.0000051802244,0.00011803793,0.000010781286,0.00014638422],"category_scores_gemma":[0.000328685,0.000092037175,0.00005233344,0.000057639252,0.0002066793,0.00010449516,0.00004554018,0.000042951655,0.000006643728],"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":[0.00045285307,0.0001297643,0.0019716262,0.009798198,0.00037511502,0.000005866975,0.0017363848,0.00018605658,0.0010957397,0.56427896,0.045934804,0.37403464],"study_design_scores_gemma":[0.020525035,0.003954346,0.0004429795,0.034296196,0.00217679,0.00018683933,0.006295675,0.03144783,0.040148564,0.6276455,0.22626463,0.0066156145],"about_ca_topic_score_codex":0.000004200127,"about_ca_topic_score_gemma":4.828307e-7,"teacher_disagreement_score":0.70812076,"about_ca_system_score_codex":0.000021747928,"about_ca_system_score_gemma":0.00002148152,"threshold_uncertainty_score":0.3753167},"labels":[],"label_agreement":null},{"id":"W2997303312","doi":"10.1146/annurev-publhealth-040119-094027","title":"Essential Ingredients and Innovations in the Design and Analysis of Group-Randomized Trials","year":2019,"lang":"en","type":"review","venue":"Annual Review of Public Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Randomized controlled trial; Research design; Clinical study design; Alternative medicine; Medical physics; Medicine; Management science; Computer science; Clinical trial; Engineering; Surgery; Mathematics; Pathology; Statistics","score_opus":0.5427499544596217,"score_gpt":0.5734347809793503,"score_spread":0.030684826519728592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997303312","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":[0.0000025588806,0.9247206,0.06873261,0.000451092,0.000032112577,0.00578251,0.00020121492,0.000018736951,0.000058590173],"genre_scores_gemma":[0.000015079017,0.98163414,0.017384253,0.00031075973,0.000020480617,0.00041644505,0.00018826204,0.000021914027,0.000008680501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9814898,0.012265454,0.0049822317,0.00039914742,0.0005169201,0.00034644862],"domain_scores_gemma":[0.9747961,0.018728875,0.00524378,0.0006872869,0.00045446103,0.00008946286],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06583432,0.00034117998,0.0106661245,0.0010390285,0.00003875562,0.000024706998,0.00038457685,0.00017616372,0.00002408076],"category_scores_gemma":[0.035479482,0.00019095953,0.0006108755,0.0031976257,0.00022522254,0.00022194006,0.00012703835,0.0003618605,5.14605e-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":[0.000018091863,0.0000932267,0.0000016163707,0.16141206,0.00066305464,3.2355211e-7,0.00039756967,1.6606535e-8,1.807293e-8,0.080390476,0.00072225096,0.7563013],"study_design_scores_gemma":[0.0069899005,0.000383173,0.000010311483,0.20265643,0.014714719,0.000015517493,0.00027906295,0.00003841843,1.8503682e-7,0.027193744,0.74712133,0.00059722655],"about_ca_topic_score_codex":0.000058210364,"about_ca_topic_score_gemma":0.000010389579,"teacher_disagreement_score":0.7557041,"about_ca_system_score_codex":0.00006847248,"about_ca_system_score_gemma":0.000685256,"threshold_uncertainty_score":0.9726451},"labels":[],"label_agreement":null},{"id":"W2998463403","doi":"10.1002/sim.8481","title":"A threshold‐free summary index for quantifying the capacity of covariates to yield efficient treatment rules","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","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 British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Context (archaeology); Econometrics; Estimator; Index (typography); Computer science; Metric (unit); Statistics; Parametric statistics; Mathematics; Economics","score_opus":0.28486632970212217,"score_gpt":0.4353815638659449,"score_spread":0.15051523416382273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998463403","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":[0.024515169,0.00008484977,0.97012955,0.0029833824,0.00008577672,0.001115744,0.00063639076,0.000070494185,0.0003786718],"genre_scores_gemma":[0.5376779,0.000050548435,0.46145824,0.00049414916,0.00009835386,0.00015392361,0.000018695178,0.000026638234,0.00002159216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987092,0.000037730664,0.00051202864,0.0002222205,0.0002868247,0.00023196408],"domain_scores_gemma":[0.99505097,0.0041686147,0.00016923272,0.0003851589,0.0001376046,0.00008845117],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00048963295,0.00018077524,0.0004653383,0.0000754917,0.0000549405,0.000006299252,0.0002998991,0.000057869845,0.000044665147],"category_scores_gemma":[0.009542333,0.00011234584,0.000029576213,0.00019804917,0.00019621714,0.000017629622,0.00008533753,0.00014231839,0.000001456366],"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":[0.000195176,0.00014470877,0.001108311,0.00038111614,0.000053159725,0.000012253738,0.008471836,0.0003958828,0.005063947,0.9684871,0.01353932,0.0021472212],"study_design_scores_gemma":[0.0012062315,0.0020600818,0.00063430297,0.00082131283,0.0001242457,0.000002482292,0.0017136097,0.0212367,0.009749345,0.96155655,0.00064383587,0.00025131428],"about_ca_topic_score_codex":0.00020591258,"about_ca_topic_score_gemma":0.00030013896,"teacher_disagreement_score":0.5131627,"about_ca_system_score_codex":0.00008992394,"about_ca_system_score_gemma":0.000044698205,"threshold_uncertainty_score":0.9988007},"labels":[],"label_agreement":null},{"id":"W3003482288","doi":"10.1371/journal.pone.0228098","title":"How to use frailtypack for validating failure-time surrogate endpoints using individual patient data from meta-analyses of randomized controlled trials","year":2020,"lang":"en","type":"review","venue":"PLoS ONE","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Institute of Cancer Research; Institut National de la Santé et de la Recherche Médicale; Institut National Du Cancer; Association pour la Recherche sur le Cancer","keywords":"Surrogate endpoint; Context (archaeology); Surrogate model; Computer science; Randomized controlled trial; Clinical endpoint; Surrogate data; Data mining; Machine learning; Medicine; Surgery","score_opus":0.8963449595823894,"score_gpt":0.5377973172268874,"score_spread":0.35854764235550196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003482288","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013354748,0.82445943,0.11057074,0.00016151003,0.000052919273,0.033539157,0.030679483,0.0003878608,0.00001536647],"genre_scores_gemma":[0.000027336288,0.2423152,0.7519042,0.000041484258,0.00017193159,0.0023775583,0.0028783637,0.00020071105,0.000083230785],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.98486036,0.006202863,0.0058955424,0.0011518616,0.0014144692,0.00047487806],"domain_scores_gemma":[0.9039867,0.083560444,0.009427367,0.0021393623,0.0006619564,0.0002241994],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.009336827,0.0011383297,0.0475498,0.00044400778,0.000082292405,0.0003936952,0.0014199901,0.00045625004,0.00033216793],"category_scores_gemma":[0.2715689,0.00070499943,0.0049000615,0.0004177236,0.00009569829,0.00058711524,0.001037641,0.00047246832,0.0000149054495],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022375505,0.0024914804,2.3480413e-7,0.02532306,0.9019181,0.000027437261,0.0007252815,0.0000045462766,0.00749971,0.0009864575,0.0025650058,0.036083188],"study_design_scores_gemma":[0.054385953,0.00020696282,2.5211733e-9,0.015415278,0.8896989,0.0000013003256,0.00005396992,0.00068740116,0.013250086,0.015594531,0.009579709,0.0011258769],"about_ca_topic_score_codex":0.000039759732,"about_ca_topic_score_gemma":0.000009989151,"teacher_disagreement_score":0.64133346,"about_ca_system_score_codex":0.00009731689,"about_ca_system_score_gemma":0.00030317748,"threshold_uncertainty_score":0.9995401},"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":"W3004365348","doi":"10.1097/ede.0000000000001165","title":"A Graphical Description of Partial Exchangeability","year":2020,"lang":"en","type":"review","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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 Institute of Allergy and Infectious Diseases; National Institute of Mental Health","keywords":"Context (archaeology); Graphical model; Identification (biology); Computer science; Mathematics; Artificial intelligence; History; Biology","score_opus":0.6643106012507909,"score_gpt":0.5440173253947438,"score_spread":0.1202932758560471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004365348","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":[0.0000021085334,0.8602052,0.13825187,0.00017101149,0.00014958494,0.00069989107,0.00004114628,0.00024948866,0.0002297134],"genre_scores_gemma":[0.00002194762,0.9461597,0.05309681,0.000085812964,0.00023667676,0.00029627336,0.000040544375,0.00004252054,0.000019686462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99462473,0.0025927084,0.00177348,0.00054757204,0.00009293565,0.00036855793],"domain_scores_gemma":[0.98849577,0.009485689,0.0011898869,0.0006340724,0.00006964233,0.00012493985],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024918735,0.00038437566,0.0044491356,0.00012472467,0.000025274927,0.0000017335882,0.00036057382,0.00083189947,0.00014305982],"category_scores_gemma":[0.028593395,0.00029423187,0.00072803564,0.00028207075,0.00037073,0.00005359871,0.0001875034,0.0007630965,0.000026868776],"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":[0.0000082306,0.00006295852,0.000036327598,0.014268596,0.00009249206,0.0000068357194,0.00003429837,3.6201545e-8,0.0000012637782,0.29314753,0.0037177335,0.6886237],"study_design_scores_gemma":[0.000022846636,0.00009884162,0.0000018593905,0.0012364546,0.00020794608,0.000015021099,0.0000017069386,0.000006866704,0.0000014046273,0.46362954,0.534643,0.00013451702],"about_ca_topic_score_codex":0.000014374781,"about_ca_topic_score_gemma":0.0000061225296,"teacher_disagreement_score":0.6884892,"about_ca_system_score_codex":0.00010092487,"about_ca_system_score_gemma":0.000109671775,"threshold_uncertainty_score":0.999951},"labels":[],"label_agreement":null},{"id":"W3005330424","doi":"10.1515/em-2018-0016","title":"Meeting the Assumptions of Inverse-Intensity Weighting for Longitudinal Data Subject to Irregular Follow-Up: Suggestions for the Design and Analysis of Clinic-Based Cohort Studies","year":2020,"lang":"en","type":"article","venue":"Epidemiologic Methods","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"","keywords":"Conditional independence; Weighting; Cohort; Independence (probability theory); Outcome (game theory); Inverse probability weighting; Cohort study; Medicine; Marginal structural model; Statistics; Psychology; Computer science; Econometrics; Observational study; Mathematics; Propensity score matching","score_opus":0.7908480222615445,"score_gpt":0.5966324160977184,"score_spread":0.19421560616382605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005330424","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":[0.008561352,0.00048279934,0.9843445,0.0043639853,0.000072350595,0.0019157019,0.00015659259,0.00009196794,0.000010785899],"genre_scores_gemma":[0.03690088,0.00015921106,0.9618458,0.0006076645,0.00004312354,0.00037922245,0.000033178123,0.000015679263,0.000015211051],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549365,0.0024217195,0.0011273593,0.0005447176,0.00013485565,0.00027766838],"domain_scores_gemma":[0.7835589,0.2133956,0.001070402,0.0011813005,0.0007091194,0.00008468499],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036141958,0.00021764869,0.0014025519,0.000103904946,0.00032276422,0.000008711077,0.00063664577,0.00011131576,0.000009427833],"category_scores_gemma":[0.2973381,0.00011912531,0.0003180002,0.0006701008,0.00037572815,0.00007013163,0.00036980212,0.00019534967,1.9682115e-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":[0.0034833134,0.0006021259,0.49549055,0.0031362344,0.051904015,0.000005143676,0.007599402,0.07175354,0.034389667,0.17422251,0.10888848,0.048525028],"study_design_scores_gemma":[0.00038630268,0.0005848447,0.00997708,0.00015089432,0.010970115,0.0000011039441,0.0018093765,0.722869,0.011004818,0.24141826,0.0005252136,0.0003030006],"about_ca_topic_score_codex":0.000031134525,"about_ca_topic_score_gemma":0.0000439201,"teacher_disagreement_score":0.6511155,"about_ca_system_score_codex":0.00003225713,"about_ca_system_score_gemma":0.000047663907,"threshold_uncertainty_score":0.9924947},"labels":[],"label_agreement":null},{"id":"W3005979941","doi":"10.1186/s12874-019-0876-8","title":"LEVEL (Logical Explanations &amp; Visualizations of Estimates in Linear mixed models): recommendations for reporting multilevel data and analyses","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"","keywords":"Multilevel model; Computer science; Data science; Statistics; Data mining; Mathematics; Machine learning","score_opus":0.9892096136300748,"score_gpt":0.7711307624025253,"score_spread":0.21807885122754944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005979941","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":[0.006541578,0.000089160305,0.9887838,0.0036293298,0.00003090609,0.00055304694,0.00022282971,0.00008644267,0.00006292356],"genre_scores_gemma":[0.038943388,0.00021153135,0.9600252,0.00010487522,0.00005551145,0.0002039883,0.00040555792,0.000022230457,0.000027748449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99394304,0.0028704104,0.0016050328,0.000550462,0.0006255622,0.0004054841],"domain_scores_gemma":[0.8574357,0.13972789,0.0007559563,0.00078675605,0.00084604014,0.00044763938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018967204,0.00013480321,0.0006591917,0.00031953954,0.0001317418,0.000013181044,0.0005933032,0.00025302963,0.00018624846],"category_scores_gemma":[0.6580242,0.00011427937,0.000048292306,0.00056498195,0.0004546303,0.00020182217,0.0007912337,0.0005188256,0.0000012251234],"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":[0.0005137393,0.0012497732,0.005670229,0.0025377607,0.00025663842,0.000039046725,0.006801959,0.0012167483,0.020307016,0.83557653,0.027941654,0.09788891],"study_design_scores_gemma":[0.00035192634,0.00009570413,0.00015141175,0.00011729355,0.000021821335,0.000008931784,0.00078254833,0.51713604,0.0017388288,0.4790523,0.0004433101,0.0000999],"about_ca_topic_score_codex":0.00014482977,"about_ca_topic_score_gemma":0.0012475887,"teacher_disagreement_score":0.639057,"about_ca_system_score_codex":0.000033951346,"about_ca_system_score_gemma":0.0005248383,"threshold_uncertainty_score":0.6573692},"labels":[],"label_agreement":null},{"id":"W3007145966","doi":"10.1093/biomet/asaa003","title":"Generalized instrumental inequalities: testing the instrumental variable independence assumption","year":2020,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"","keywords":"Instrumental variable; Mathematics; Independence (probability theory); Variable (mathematics); Outcome (game theory); Econometrics; Inference; Intersection (aeronautics); Conditional independence; Binary number; Variables; Statistics; Mathematical economics; Computer science; Artificial intelligence; Arithmetic","score_opus":0.3397669956737207,"score_gpt":0.3936904073599447,"score_spread":0.053923411686224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007145966","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":[0.9266393,0.0001011103,0.06576,0.00075137,0.00023320387,0.00079331006,0.000098378405,0.0010503063,0.0045730234],"genre_scores_gemma":[0.8217898,0.00001542307,0.17706196,0.00075584534,0.00017416383,0.00006287627,0.000019879446,0.000033672295,0.0000863801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981232,0.00012990896,0.00048335944,0.00033799175,0.0005711411,0.0003543802],"domain_scores_gemma":[0.9985582,0.0006226889,0.00026628177,0.00031806916,0.000104797364,0.0001299374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935038,0.00023537803,0.00027461356,0.00020484513,0.00019561079,0.000115489565,0.00046926763,0.00014381752,0.0003259241],"category_scores_gemma":[0.0026299162,0.00017844928,0.000059193622,0.0021520613,0.00012256703,0.00041500278,0.00029706815,0.00031392206,0.000054718003],"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":[0.00014932896,0.00034644225,0.015561728,0.00040489482,0.00020125326,0.000025306677,0.0029697292,0.00001655622,0.40913454,0.49855393,0.005876287,0.06676002],"study_design_scores_gemma":[0.0040703197,0.0018954949,0.0022459726,0.0004267874,0.00020647007,0.00015277485,0.0051079616,0.0082964,0.38643733,0.5615137,0.027427252,0.0022195203],"about_ca_topic_score_codex":0.00011893531,"about_ca_topic_score_gemma":0.0000031646262,"teacher_disagreement_score":0.11130195,"about_ca_system_score_codex":0.00018609248,"about_ca_system_score_gemma":0.00008281251,"threshold_uncertainty_score":0.72769505},"labels":[],"label_agreement":null},{"id":"W3007256858","doi":"10.1016/j.jclinepi.2020.02.006","title":"Design characteristics and statistical methods used in interrupted time series studies evaluating public health interventions: a review","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":143,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research","keywords":"Interrupted time series; Public health; Series (stratigraphy); Psychological intervention; Public health interventions; Interrupted Time Series Analysis; Statistics; Statistical analysis; Time series; Medicine; Computer science; Mathematics; Nursing","score_opus":0.9578941774010222,"score_gpt":0.7853317705012486,"score_spread":0.17256240689977365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007256858","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":[3.5307272e-7,0.5678107,0.42798188,0.0032615112,0.00019402622,0.0007009543,0.000017505614,0.000030292942,0.0000027672056],"genre_scores_gemma":[1.5969415e-7,0.5239828,0.47504222,0.0007330636,0.00013824156,0.000049363287,0.000009703513,0.000033004515,0.000011407961],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84945846,0.119865626,0.02874371,0.00079230586,0.00035477566,0.00078511937],"domain_scores_gemma":[0.6084783,0.36186597,0.027517097,0.0005993773,0.0008546184,0.0006846446],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17475225,0.00058478786,0.02317983,0.00031551014,0.000052247306,0.00001853177,0.00055399287,0.00055946753,0.000104486644],"category_scores_gemma":[0.7437028,0.00039877952,0.0013584157,0.00036671213,0.0006060192,0.00023413212,0.000432117,0.0032774215,0.000010905689],"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":[0.000027762913,0.00009855527,0.000022637749,0.061972175,0.0005690089,0.000045831504,0.000056193618,4.476576e-8,4.601479e-8,0.0052926354,0.0025554628,0.9293597],"study_design_scores_gemma":[0.00046865604,0.005571263,0.000043620752,0.35180485,0.0017599153,0.0008239478,0.000057492613,0.00017135518,4.5205553e-8,0.3539711,0.28480965,0.0005180893],"about_ca_topic_score_codex":0.000001015382,"about_ca_topic_score_gemma":0.0000017722098,"teacher_disagreement_score":0.92884153,"about_ca_system_score_codex":0.00030788712,"about_ca_system_score_gemma":0.0012996162,"threshold_uncertainty_score":0.9998464},"labels":[],"label_agreement":null},{"id":"W3008269149","doi":"10.31235/osf.io/86d2k","title":"Effect Decomposition in the Presence of Treatment-induced Confounding: A Regression-with-residuals Approach","year":2019,"lang":"en","type":"article","venue":"","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":"University of Toronto","funders":"","keywords":"Confounding; Estimator; Statistics; Outcome (game theory); Econometrics; Weighting; Mediation; Regression; Set (abstract data type); Conditional expectation; Inverse probability weighting; Mathematics; Medicine; Computer science","score_opus":0.09187174120657353,"score_gpt":0.42975942178175586,"score_spread":0.3378876805751823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008269149","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":[0.9647886,0.000009344659,0.009625601,0.000037240436,0.000014772676,0.0014527838,0.000001493568,0.0001004575,0.023969688],"genre_scores_gemma":[0.97558236,0.000004548923,0.023920935,0.000017853063,0.0000083595805,0.00018043496,0.000005104652,0.000013916227,0.00026648585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989017,0.00028467338,0.00023381003,0.000198481,0.00020592105,0.00017537575],"domain_scores_gemma":[0.99713546,0.002175966,0.000152502,0.00047602033,0.000037266804,0.000022781198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000561747,0.00016455905,0.00030766396,0.000081224454,0.000026569767,0.000019206773,0.00021294698,0.000073849646,0.000038112365],"category_scores_gemma":[0.00014257304,0.000075544354,0.000042216143,0.00018370156,0.000038664788,0.00015330978,0.000027084725,0.00010300907,0.0000051547718],"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":[0.0008710054,0.0015206776,0.026112985,0.00093990285,0.00014864079,0.000024473364,0.007259762,0.00009025737,0.39875203,0.5520508,0.00069910294,0.011530368],"study_design_scores_gemma":[0.0021267305,0.0067503396,0.00070319587,0.00067219755,0.00007730415,0.00005975122,0.0013850562,0.0022393456,0.87675744,0.10880488,0.00003572387,0.00038800432],"about_ca_topic_score_codex":0.00007282496,"about_ca_topic_score_gemma":0.00001611093,"teacher_disagreement_score":0.47800544,"about_ca_system_score_codex":0.000080933096,"about_ca_system_score_gemma":0.00003159728,"threshold_uncertainty_score":0.30806094},"labels":[],"label_agreement":null},{"id":"W3008905790","doi":"10.1002/sim.8502","title":"Variance estimation when using propensity‐score matching with replacement with survival or time‐to‐event outcomes","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":86,"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; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Event data; Matching (statistics); Variance (accounting); Estimation; Event (particle physics); Survival analysis; Econometrics; Computer science; Mathematics; Covariate","score_opus":0.1810926378835545,"score_gpt":0.4193115110956037,"score_spread":0.2382188732120492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008905790","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":[0.02614024,0.0000041070466,0.9706906,0.0016741647,0.00003212603,0.0009571526,0.000036606452,0.00014880393,0.00031617505],"genre_scores_gemma":[0.06667566,0.0000026672665,0.9321376,0.0006842035,0.000047542842,0.00003817938,0.000028324986,0.000051911808,0.00033386945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818087,0.000096524454,0.00049058936,0.0003559478,0.00060435955,0.00027171796],"domain_scores_gemma":[0.998493,0.0006254167,0.0002578901,0.00031483723,0.00016255744,0.00014630587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005910589,0.0002562921,0.000600415,0.00007947806,0.00006486818,0.000019566165,0.00017122016,0.000042052663,0.000379664],"category_scores_gemma":[0.0016607764,0.00015472376,0.000008179937,0.00025995192,0.00010637538,0.000116137744,0.00008121676,0.00025707128,0.000014631963],"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":[0.019170547,0.0016016299,0.07639881,0.008322908,0.0012905211,0.0058525237,0.10049338,0.06446856,0.017318469,0.62130725,0.036904868,0.046870537],"study_design_scores_gemma":[0.00947685,0.013915588,0.010637649,0.009708902,0.0007855804,0.00018576912,0.0026315239,0.16051297,0.00207904,0.7869579,0.00069253903,0.0024156864],"about_ca_topic_score_codex":0.000091377384,"about_ca_topic_score_gemma":0.00013987625,"teacher_disagreement_score":0.16565067,"about_ca_system_score_codex":0.00017331401,"about_ca_system_score_gemma":0.0001157486,"threshold_uncertainty_score":0.6309452},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3010656855","doi":"10.1142/9789811232701_0019","title":"ParKCa: Causal Inference with Partially Known Causes","year":2020,"lang":"en","type":"article","venue":"","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":"Simon Fraser University","funders":"","keywords":"Computer science; Inference; Causal inference; Artificial intelligence; Econometrics; Mathematics","score_opus":0.19317662007528785,"score_gpt":0.40157336232931395,"score_spread":0.2083967422540261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010656855","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":[0.068764396,0.000031397904,0.89336187,0.0026467526,0.000042123786,0.000589859,0.000012786582,0.0027761715,0.031774636],"genre_scores_gemma":[0.84390604,0.000019595656,0.15449852,0.0009914754,0.00008987599,0.00006159474,0.0000034766238,0.000038517683,0.0003908869],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998728,0.000044460747,0.0002917751,0.00032788163,0.00027429382,0.00033361465],"domain_scores_gemma":[0.9987846,0.0004193038,0.00010999769,0.00032814778,0.00014430982,0.00021366074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009761637,0.00023869945,0.0003125529,0.000030704137,0.000061351144,0.000048405007,0.0002443783,0.00008295576,0.00073414866],"category_scores_gemma":[0.0007380719,0.0001700854,0.00003656379,0.00023904041,0.000118179516,0.00028371115,0.0001133012,0.00022641831,0.00011074593],"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":[0.00013320254,0.00015972074,0.005175521,0.00015333826,0.00009330401,0.00012435784,0.0011581482,0.000053653275,0.0076309275,0.96550125,0.015404787,0.00441178],"study_design_scores_gemma":[0.0014763753,0.0030544235,0.0013200594,0.00028641432,0.00021898755,0.00004802418,0.000701369,0.0019372641,0.3188943,0.6247733,0.045174196,0.0021152487],"about_ca_topic_score_codex":0.000026415457,"about_ca_topic_score_gemma":0.00028242447,"teacher_disagreement_score":0.77514166,"about_ca_system_score_codex":0.000028754403,"about_ca_system_score_gemma":0.000112702655,"threshold_uncertainty_score":0.8038413},"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":"W3011550827","doi":"10.1186/s12874-020-00945-9","title":"Incorporating sampling weights into robust estimation of Cox proportional hazards regression model, with illustration in the Multi-Ethnic Study of Atherosclerosis","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of Manitoba","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute","keywords":"Proportional hazards model; Statistics; Estimation; Regression analysis; Regression; Econometrics; Medicine; Computer science; Mathematics","score_opus":0.8839438527848583,"score_gpt":0.6241169862692942,"score_spread":0.2598268665155641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011550827","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":[0.42148754,0.000012550093,0.5775015,0.00025062842,0.000006510157,0.0006984399,0.0000011794867,0.000026254716,0.000015378384],"genre_scores_gemma":[0.48161143,0.000011041478,0.51819444,0.00001647951,0.000018424567,0.00012870402,0.0000050174813,0.000011344908,0.0000031374097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884811,0.0077164574,0.0010176403,0.0004024742,0.0020771155,0.00030519627],"domain_scores_gemma":[0.9807526,0.017814785,0.0004960207,0.0003665178,0.00042973144,0.00014038205],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017630052,0.00015414425,0.0005361393,0.00020196971,0.00010713597,0.000009172745,0.00050209253,0.00023770066,0.00003193964],"category_scores_gemma":[0.055113465,0.00008992097,0.000040366558,0.0008216958,0.0006071536,0.00015167969,0.00019588087,0.0009311085,5.371348e-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":[0.0044101044,0.007952282,0.037781507,0.00550656,0.00019467185,0.000055038534,0.11550374,0.19386172,0.09690247,0.41522536,0.00017397878,0.12243257],"study_design_scores_gemma":[0.0011571236,0.0020172517,0.0021849696,0.00062429253,0.000021252677,0.00000541175,0.008570662,0.8057726,0.0070821424,0.1724372,5.6335364e-7,0.00012651364],"about_ca_topic_score_codex":0.00012898765,"about_ca_topic_score_gemma":0.0012143563,"teacher_disagreement_score":0.6119109,"about_ca_system_score_codex":0.000058560192,"about_ca_system_score_gemma":0.00083054363,"threshold_uncertainty_score":0.9528457},"labels":[],"label_agreement":null},{"id":"W3011937366","doi":"10.1038/s41390-020-0835-4","title":"Privacy-preserving statistical analyses in Learning Health Systems","year":2020,"lang":"en","type":"letter","venue":"Pediatric Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Statistical learning; Computer science; Internet privacy; Psychology; Data science; Artificial intelligence","score_opus":0.6413351111834622,"score_gpt":0.5988428338972334,"score_spread":0.04249227728622884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011937366","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009659654,0.008591864,0.13197985,0.8419696,0.0004814457,0.005720999,0.00027081327,0.0020533549,0.007966076],"genre_scores_gemma":[0.0894562,0.048223622,0.49656972,0.20837584,0.108862326,0.007473828,0.0046055415,0.0038189024,0.032614004],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.989788,0.0037202004,0.0012279692,0.0009932094,0.002606026,0.0016645825],"domain_scores_gemma":[0.98648953,0.011477999,0.00041704017,0.0009360141,0.00042111383,0.00025827013],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031950334,0.00043054402,0.0012341907,0.0015143082,0.00025293676,0.00027370223,0.0015195258,0.00062124466,0.00019172658],"category_scores_gemma":[0.021888573,0.00040547748,0.00010382154,0.0020725452,0.0001313727,0.0001835837,0.0013644343,0.012034432,0.0001533105],"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":[0.000010127684,0.00003207522,0.0011811223,0.004160469,0.000020460915,0.0009531251,0.00035822918,0.00002636565,0.000008201479,0.0013479522,0.99167603,0.00022585227],"study_design_scores_gemma":[0.0006921944,0.0012628284,0.00024025365,0.0008570581,0.000107414155,0.00004149899,0.0009847486,0.009402599,0.000029880242,0.4037347,0.58092415,0.001722634],"about_ca_topic_score_codex":0.0010742168,"about_ca_topic_score_gemma":0.00001752979,"teacher_disagreement_score":0.6335938,"about_ca_system_score_codex":0.00084907626,"about_ca_system_score_gemma":0.0009833444,"threshold_uncertainty_score":0.9998397},"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":"W3013573462","doi":"10.1515/jci-2021-0023","title":"A generalized double robust Bayesian model averaging approach to causal effect estimation with application to the study of osteoporotic fractures","year":2022,"lang":"en","type":"article","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","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":"Institut National de Santé Publique du Québec; Université Laval; Centre hospitalier de l'Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute on Aging; National Institutes of Health","keywords":"Causal inference; Covariate; Estimator; Confounding; Bayesian probability; Estimation; Shrinkage estimator; Econometrics; Confidence interval; Statistics; Interval estimation; Computer science; Bayes estimator; Selection (genetic algorithm); Mathematics; Machine learning; Bias of an estimator; Engineering; Minimum-variance unbiased estimator","score_opus":0.07273394108806942,"score_gpt":0.382152650539416,"score_spread":0.3094187094513466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013573462","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":[0.39306358,0.000009104537,0.6052242,0.00014146768,0.000030850457,0.0013344514,0.0000049143287,0.000035626497,0.00015580602],"genre_scores_gemma":[0.8282271,0.0000012026181,0.17109151,0.00013116199,0.000046500518,0.0004314251,0.0000042043757,0.000036040754,0.00003083692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972368,0.0002826789,0.00084143446,0.00028401837,0.0010669633,0.00028811736],"domain_scores_gemma":[0.9975028,0.0004285179,0.0009069308,0.0005813182,0.00041854952,0.00016188051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015520896,0.00028981143,0.0006120524,0.00032698084,0.00025825656,0.00006866073,0.00067590066,0.000052372787,0.000020013842],"category_scores_gemma":[0.00031224018,0.00019063697,0.00007314291,0.00065371656,0.00003593007,0.00030464004,0.00024750293,0.00062887237,0.0000012364737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007272851,0.0005154784,0.0005695889,0.000058520654,0.00007738161,0.0000069069874,0.005297154,0.9821613,0.0020936097,0.005883204,0.00033391872,0.0022756632],"study_design_scores_gemma":[0.0049120174,0.012088498,0.0013908651,0.00025239927,0.00065483054,0.00033974144,0.0033386303,0.9078353,0.015557033,0.052542206,0.00012829374,0.00096017245],"about_ca_topic_score_codex":0.00010060372,"about_ca_topic_score_gemma":0.0000663423,"teacher_disagreement_score":0.43516353,"about_ca_system_score_codex":0.0002552059,"about_ca_system_score_gemma":0.00018566851,"threshold_uncertainty_score":0.777395},"labels":[],"label_agreement":null},{"id":"W3016292706","doi":"10.1038/s41598-020-63465-y","title":"Determining organ weight toxicity with Bayesian causal models: Improving on the analysis of relative organ weights","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prioris.ai (Canada)","funders":"","keywords":"Analysis of covariance; Bayesian probability; Covariance; Computer science; Chemical toxicity; Organ system; Interpretation (philosophy); Body weight; Approximate Bayesian computation; Statistics; Toxicity; Medicine; Mathematics; Machine learning; Artificial intelligence; Internal medicine","score_opus":0.08902112929955784,"score_gpt":0.31892822014240263,"score_spread":0.22990709084284477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016292706","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":[0.688729,0.000008416749,0.30743083,0.00032243883,0.00018944277,0.00046718668,0.000008756462,0.0002802771,0.0025636898],"genre_scores_gemma":[0.97481674,7.8171666e-7,0.024768293,0.000068228255,0.000025173445,0.000021510012,0.000015100036,0.000035890513,0.00024826732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971959,0.00011962382,0.0007483657,0.00082764437,0.000781019,0.00032746038],"domain_scores_gemma":[0.99693644,0.00044428572,0.0009791013,0.0011550116,0.00032728593,0.00015785545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011306026,0.00026158345,0.0005214211,0.00028000903,0.00034671067,0.00011634153,0.00029234256,0.00009432301,0.00016319285],"category_scores_gemma":[0.001220183,0.000158882,0.00014265497,0.0023023256,0.00040760607,0.00044810312,0.00013992442,0.00029776088,0.0000020561147],"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":[0.00027794045,0.001383591,0.025131626,0.00050908164,0.005271446,0.0036349124,0.08195697,0.0043954817,0.33357593,0.5269518,0.0067038448,0.010207398],"study_design_scores_gemma":[0.000119164164,0.00028257587,0.0001987659,0.00017808654,0.0009963079,0.000034014156,0.0007384184,0.06649557,0.40349448,0.5269055,0.00009481354,0.00046230483],"about_ca_topic_score_codex":0.0000129229375,"about_ca_topic_score_gemma":0.00011026982,"teacher_disagreement_score":0.28608778,"about_ca_system_score_codex":0.00008710679,"about_ca_system_score_gemma":0.00016586823,"threshold_uncertainty_score":0.647902},"labels":[],"label_agreement":null},{"id":"W3016548487","doi":"10.22237/jmasm/1556669280","title":"Investigating the Performance of Propensity Score Approaches for Differential Item Functioning Analysis","year":2020,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"","keywords":"Covariate; Propensity score matching; Differential item functioning; Statistics; Mathematics; Type I and type II errors; Mean squared error; Econometrics; Missing data; Item response theory; Psychometrics","score_opus":0.46701448305474397,"score_gpt":0.44107681053009584,"score_spread":0.025937672524648125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016548487","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":[0.14235736,0.00001872237,0.85699666,0.00012554748,0.000025436235,0.00031411092,0.000017074122,0.000027117909,0.00011797951],"genre_scores_gemma":[0.4883296,0.0000022718316,0.51153594,0.000037937523,0.00006174974,0.000015311696,0.000002060297,0.00001292456,0.0000021977824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806756,0.00025931382,0.00090366486,0.00019306368,0.00037163077,0.00020478207],"domain_scores_gemma":[0.99344933,0.0050287303,0.00095685764,0.00018839186,0.00023427406,0.00014244014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015862947,0.00018033692,0.0007770875,0.000082420076,0.00013010524,0.000036048885,0.00028263815,0.00008170446,0.000025099409],"category_scores_gemma":[0.0042715482,0.00011414184,0.00016635367,0.00033107516,0.00021262807,0.00009551643,0.00009362556,0.00046021168,1.8805966e-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":[0.0005747387,0.0001667972,0.0031174985,0.00096450833,0.001378507,0.0000017601943,0.0023461855,0.003580997,0.0702959,0.3997948,0.0001601584,0.5176182],"study_design_scores_gemma":[0.00028924076,0.00029294103,0.0022111128,0.000037268997,0.0010810822,0.0000045361135,0.000113891525,0.49667993,0.02806918,0.4710737,0.000011104965,0.00013603631],"about_ca_topic_score_codex":7.527405e-7,"about_ca_topic_score_gemma":6.4455935e-7,"teacher_disagreement_score":0.5174821,"about_ca_system_score_codex":0.000038166356,"about_ca_system_score_gemma":0.00006609465,"threshold_uncertainty_score":0.5113751},"labels":[],"label_agreement":null},{"id":"W3018281085","doi":"10.1111/biom.13285","title":"Weighted regression analysis to correct for informative monitoring times and confounders in longitudinal studies","year":2020,"lang":"en","type":"article","venue":"Biometrics","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":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Confounding; Inverse probability; Outcome (game theory); Statistics; Context (archaeology); Observational study; Marginal structural model; Econometrics; Ordinary least squares; Generalized linear model; Computer science; Mathematics; Bayesian probability","score_opus":0.4591560821512847,"score_gpt":0.5072392278805445,"score_spread":0.04808314572925987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018281085","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":[0.37185323,0.0020505216,0.62340486,0.00061816286,0.00017016602,0.0011117677,0.000040633717,0.0003592883,0.00039134728],"genre_scores_gemma":[0.87021506,0.00044525976,0.12912214,0.000059294758,0.000038457038,0.000064865446,0.00000542914,0.000012944347,0.00003658728],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905497,0.000022270548,0.00032448862,0.00020279473,0.00019973301,0.000195734],"domain_scores_gemma":[0.99809444,0.0013115031,0.00015112071,0.000118892465,0.00022174368,0.00010231644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027172163,0.00015493657,0.0004230805,0.0016236553,0.00006153602,0.000034848887,0.00011016356,0.000068040026,0.0000050888593],"category_scores_gemma":[0.0034800558,0.00012493512,0.00005638261,0.0065896395,0.00004862538,0.00024057331,0.00012240306,0.00008972473,0.0000024611938],"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":[0.0011484938,0.0004266727,0.61616385,0.0029906742,0.0049438635,0.000058211295,0.05692852,0.00015034559,0.004599172,0.041058403,0.01765586,0.25387594],"study_design_scores_gemma":[0.009425896,0.009762967,0.08172026,0.0025605948,0.0057501174,0.000024352916,0.09360167,0.04839812,0.32046053,0.3999169,0.021429406,0.006949217],"about_ca_topic_score_codex":0.000005442308,"about_ca_topic_score_gemma":0.000005320925,"teacher_disagreement_score":0.53444356,"about_ca_system_score_codex":0.00012756579,"about_ca_system_score_gemma":0.000015826137,"threshold_uncertainty_score":0.50947064},"labels":[],"label_agreement":null},{"id":"W301845562","doi":"10.1007/978-0-387-71393-9_13","title":"Missing Data in Longitudinal Studies","year":2007,"lang":"en","type":"book-chapter","venue":"Springer series in statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"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 Waterloo","funders":"","keywords":"Longitudinal data; Missing data; Computer science; Data mining; Machine learning","score_opus":0.5009964620410728,"score_gpt":0.499865245040885,"score_spread":0.0011312170001878674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301845562","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":[0.000076263954,0.011732721,0.6006567,0.00014807064,0.0011835253,0.0013689519,0.0024649038,0.00068094285,0.3816879],"genre_scores_gemma":[0.00041004078,0.0060040304,0.94297266,0.000045815297,0.0001879909,0.000015782918,0.00017416787,0.00019160875,0.049997896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973091,0.000025223446,0.0010419411,0.0006922767,0.00044968238,0.00048179214],"domain_scores_gemma":[0.9965853,0.0012451409,0.000434267,0.0014830431,0.00018494326,0.00006732262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088569947,0.00054084655,0.00095420127,0.00040756364,0.00005683133,0.000042612657,0.00069887633,0.00034444086,0.00015056068],"category_scores_gemma":[0.0020823316,0.0005774245,0.000031490246,0.0000821176,0.0004937478,0.00037981925,0.0010923163,0.0009580084,0.000019324234],"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":[0.000040732422,0.000027110304,0.00040973816,0.000804257,0.000055361244,0.0008869858,0.00034835556,0.0000014177372,0.000004354652,0.9725067,0.0019398789,0.02297511],"study_design_scores_gemma":[0.00014191704,0.00006265827,0.00012402286,0.001445974,0.000053603737,0.000022224272,0.00010819456,0.00002606039,0.00005221424,0.948113,0.049276736,0.00057334907],"about_ca_topic_score_codex":0.000017585999,"about_ca_topic_score_gemma":0.0029370363,"teacher_disagreement_score":0.34231594,"about_ca_system_score_codex":0.00042940406,"about_ca_system_score_gemma":0.00011165718,"threshold_uncertainty_score":0.9996677},"labels":[],"label_agreement":null},{"id":"W3019567365","doi":"10.1002/sim.8541","title":"Doubly robust estimation and causal inference for recurrent event data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Semiparametric regression; Causal inference; Computer science; Statistics; Semiparametric model; Inference; Event (particle physics); Econometrics; Estimating equations; Mathematics; Artificial intelligence","score_opus":0.32461444492443875,"score_gpt":0.5000145513770762,"score_spread":0.17540010645263743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019567365","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":[0.0006317394,0.000114425595,0.9959028,0.0019405468,0.00009781681,0.0005794767,0.0005221176,0.00009119042,0.000119929275],"genre_scores_gemma":[0.12141595,0.000143463,0.87745535,0.0002625817,0.00011955346,0.00005626127,0.00050562806,0.000022051201,0.000019176028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874806,0.000039242404,0.0004601297,0.00032760738,0.00023488404,0.00019009941],"domain_scores_gemma":[0.9975978,0.0016686443,0.0001625998,0.00034750908,0.000110868685,0.00011254758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005265505,0.00015298201,0.00032019915,0.00005698646,0.00003818154,0.000011357668,0.00025021617,0.000054504162,0.00005011987],"category_scores_gemma":[0.012078391,0.00013090442,0.000005702593,0.00013275101,0.00014591617,0.00012685393,0.00016621924,0.00020381084,0.0000018179203],"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":[0.0001713931,0.00008302436,0.00035524604,0.001064719,0.00002469139,0.000025019632,0.0022121363,0.00028045333,0.00028031622,0.79231966,0.07204642,0.13113691],"study_design_scores_gemma":[0.00081000203,0.00070542435,0.00017475717,0.00031036543,0.00005233511,0.0000028831603,0.00014022109,0.31848297,0.00009167954,0.67795146,0.0011133961,0.0001645174],"about_ca_topic_score_codex":0.000018797355,"about_ca_topic_score_gemma":0.000102516155,"teacher_disagreement_score":0.3182025,"about_ca_system_score_codex":0.000045393193,"about_ca_system_score_gemma":0.000051443258,"threshold_uncertainty_score":0.9962433},"labels":[],"label_agreement":null},{"id":"W3021067680","doi":"10.1136/injuryprev-2020-savir.37","title":"107 Can synthetic controls improve causal inference in interrupted time series evaluations of public health interventions?","year":2020,"lang":"en","type":"article","venue":"Oral Presentations","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":"St. Michael's Hospital","funders":"","keywords":"Causal inference; Psychological intervention; Interrupted time series; Observational study; Computer science; Inference; Interrupted Time Series Analysis; Confounding; Risk analysis (engineering); Control (management); Time series; Poison control; Rigour; Management science; Engineering; Machine learning; Econometrics; Artificial intelligence; Psychology; Medicine; Environmental health; Mathematics","score_opus":0.3480507879678849,"score_gpt":0.5051622501842452,"score_spread":0.1571114622163603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021067680","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":[0.1367297,0.00018040926,0.80401605,0.05098235,0.00016034422,0.0037913523,0.00074970495,0.0008564963,0.002533611],"genre_scores_gemma":[0.9741854,0.000016929662,0.024884133,0.00019088994,0.000020167126,0.00028625567,0.00008816061,0.000026532418,0.00030154735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977774,0.00046817682,0.0008853124,0.0002747678,0.00027471886,0.00031963072],"domain_scores_gemma":[0.998006,0.00076176046,0.0004133215,0.00031996073,0.0003160444,0.00018290935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058243447,0.00017795607,0.00046584185,0.00021052538,0.00008372028,0.00005786215,0.0002797296,0.00006520078,0.00052838377],"category_scores_gemma":[0.005984043,0.00017990083,0.00012305872,0.00054984615,0.00019727592,0.0005516659,0.00014047784,0.00024767872,0.000025689007],"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":[0.00017643417,0.0025515137,0.017043684,0.002049212,0.0005243153,0.000025403166,0.030907627,0.00078042015,0.058502454,0.8332411,0.008197149,0.046000704],"study_design_scores_gemma":[0.0046311687,0.0038595032,0.014201417,0.001552811,0.0002936085,0.000020342131,0.010599254,0.03955796,0.024594665,0.89800996,0.001108057,0.0015712848],"about_ca_topic_score_codex":0.00030117363,"about_ca_topic_score_gemma":0.0013351532,"teacher_disagreement_score":0.8374557,"about_ca_system_score_codex":0.00011678273,"about_ca_system_score_gemma":0.00030055133,"threshold_uncertainty_score":0.73361427},"labels":[],"label_agreement":null},{"id":"W3021470514","doi":"10.1002/jrsm.1511","title":"Methods for population adjustment with limited access to individual patient data: A review and simulation study","year":2021,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":57,"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":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Institute of Conservation","keywords":"Covariate; Estimator; Standard error; Sample size determination; Measure (data warehouse); Variance (accounting); Population; Standard deviation; Confidence interval","score_opus":0.7644489907710884,"score_gpt":0.7005175490144144,"score_spread":0.06393144175667398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021470514","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":[0.0050132405,0.0026149096,0.98613596,0.00059553754,0.000027918459,0.005316366,0.00007084741,0.00014024971,0.00008499674],"genre_scores_gemma":[0.009302947,0.0004960551,0.98773247,0.00017035543,0.000039258113,0.0021163626,0.00005186282,0.00005625696,0.000034416153],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891867,0.008292384,0.00056679174,0.0008230278,0.0006777758,0.00045334283],"domain_scores_gemma":[0.95852596,0.03856514,0.00018966645,0.001514981,0.000996898,0.0002073333],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017866848,0.00022867028,0.0006958813,0.00029579987,0.00021692933,0.00017347204,0.00056246296,0.000086965374,0.000055282435],"category_scores_gemma":[0.07395944,0.0001796833,0.00003907243,0.0010477916,0.000047251444,0.0005721345,0.0012488505,0.0002750035,8.146206e-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":[0.000073458374,0.00046870546,0.00034639225,0.0010539461,0.00017918205,0.0000037361021,0.00031950738,0.00006806387,0.00037845655,0.00077766454,0.00048341,0.99584746],"study_design_scores_gemma":[0.003421431,0.011073912,0.0623777,0.017351616,0.008701168,0.000070888666,0.008875056,0.071381,0.20870201,0.5288903,0.07410315,0.0050517675],"about_ca_topic_score_codex":0.000031543477,"about_ca_topic_score_gemma":0.00003793998,"teacher_disagreement_score":0.99079573,"about_ca_system_score_codex":0.00013923807,"about_ca_system_score_gemma":0.00011268176,"threshold_uncertainty_score":0.933841},"labels":[],"label_agreement":null},{"id":"W3022994372","doi":"10.1002/jrsm.1416","title":"Equivalence of entropy balancing and the method of moments for matching‐adjusted indirect comparison","year":2020,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"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":"Medical Research Council; Medical Research Council Canada; Department of Health and Social Care; University of Bristol; National Institute for Health and Care Research; University Hospitals Bristol NHS Foundation Trust; AstraZeneca","keywords":"Covariate; Statistics; Population; Mathematics; Entropy (arrow of time); Nonparametric statistics; Standard error; Econometrics; Computer science","score_opus":0.5557337790460275,"score_gpt":0.6078522747330801,"score_spread":0.052118495687052624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022994372","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":[0.012164115,0.00028065703,0.98515284,0.00079560844,0.000017090788,0.0011029779,0.000026253732,0.00007037951,0.00039005608],"genre_scores_gemma":[0.20482934,0.00010623858,0.7947487,0.000017611786,0.000024920484,0.00022042761,5.398428e-7,0.000027547017,0.000024647978],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99246943,0.0054134447,0.00071293116,0.00033190686,0.0006526681,0.00041961827],"domain_scores_gemma":[0.91546196,0.08327115,0.0003769361,0.00041246953,0.0003633454,0.00011412344],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019007212,0.00016509411,0.0010018506,0.00015841673,0.00011603557,0.000022307811,0.00053992576,0.00010191572,0.0000389273],"category_scores_gemma":[0.056505308,0.00011218386,0.00013046956,0.0004766102,0.00044709045,0.000103659746,0.00035672408,0.00036891765,5.0724174e-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":[0.0010861284,0.00015299364,0.0004906186,0.0029698277,0.0003104686,0.0000012435825,0.0071293707,0.000028081287,0.5667387,0.20353179,0.0004623992,0.21709834],"study_design_scores_gemma":[0.0003036572,0.000121736965,0.00006861035,0.0002038591,0.000058154354,0.000001141139,0.0010929923,0.010980403,0.6814659,0.3054852,0.0001346859,0.000083631894],"about_ca_topic_score_codex":0.00004639043,"about_ca_topic_score_gemma":0.0000016047702,"teacher_disagreement_score":0.2170147,"about_ca_system_score_codex":0.000051166673,"about_ca_system_score_gemma":0.000066953275,"threshold_uncertainty_score":0.9514421},"labels":[],"label_agreement":null},{"id":"W3023009578","doi":"10.1002/9781118445112.stat05236","title":"Drug Utilization Patterns","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Observational study; Nonparametric statistics; Data collection; Drug; Data science; Computer science; Medicine; Econometrics; Pharmacology; Statistics; Economics; Mathematics","score_opus":0.19819524501425995,"score_gpt":0.4350969791750898,"score_spread":0.23690173416082988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023009578","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":[0.000019064228,0.00026816182,0.9063368,0.000046059726,0.00034106345,0.00080768,0.031389188,0.0018188853,0.058973096],"genre_scores_gemma":[0.0004953003,0.00451334,0.6464747,0.00021507197,0.00050144404,0.00010905905,0.012778857,0.0014830183,0.33342916],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962103,0.0002487894,0.0009879475,0.00093967305,0.000856244,0.0007570497],"domain_scores_gemma":[0.9960952,0.00070781214,0.0011929447,0.0013821191,0.00034185333,0.00028011625],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029439316,0.0009459455,0.0011597818,0.0005228796,0.00009289727,0.00008558258,0.0007654452,0.00056935486,0.0069645355],"category_scores_gemma":[0.0009827312,0.00089015515,0.00008104648,0.00026925895,0.00022443588,0.00009321064,0.00024724158,0.00089907594,0.00030244113],"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":[0.000012284358,0.0002449872,0.00007321059,0.00072018575,0.00007331161,0.00002709553,0.00006649509,0.0000016408246,0.00001594904,0.23656416,0.73895854,0.023242118],"study_design_scores_gemma":[0.00042720168,0.00016762348,0.000033576827,0.002033919,0.00017939223,0.00000823753,0.000078819605,0.00048722886,0.00008298758,0.46882755,0.5264817,0.0011917764],"about_ca_topic_score_codex":0.0003177062,"about_ca_topic_score_gemma":0.004703096,"teacher_disagreement_score":0.27445608,"about_ca_system_score_codex":0.00018925262,"about_ca_system_score_gemma":0.00020023917,"threshold_uncertainty_score":0.9993549},"labels":[],"label_agreement":null},{"id":"W3023265660","doi":"10.1016/j.jeconom.2006.07.021","title":"A structural analysis of the correlated random coefficient wage regression model","year":2006,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Center for Interuniversity Research and Analysis on Organizations","funders":"Koç Üniversitesi","keywords":"Econometrics; Mathematics; Monotonic function; Regression; Wage; Regression analysis; Statistics; Function (biology); Economics","score_opus":0.21169313368412038,"score_gpt":0.3561619053662627,"score_spread":0.1444687716821423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023265660","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":[0.8382125,0.00021184058,0.16047987,0.00004351345,0.000114871335,0.000103363556,0.000017887452,0.0000140387165,0.00080209033],"genre_scores_gemma":[0.9845716,0.000032810713,0.015156236,0.000016176678,0.000023345458,8.4801326e-7,0.0000016642211,0.000010942577,0.00018639567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850124,0.000053600288,0.0009506673,0.00009159124,0.00026373315,0.00013915318],"domain_scores_gemma":[0.99695104,0.0006491293,0.0017457684,0.00027668243,0.00033464245,0.000042756015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006552038,0.00012069551,0.0005777046,0.0012900345,0.000053974814,0.00002021108,0.0003268404,0.000089294066,0.00005625049],"category_scores_gemma":[0.0010715816,0.00006948522,0.0004084429,0.002724317,0.000064632906,0.00015294355,0.000064393695,0.00025983606,3.7461092e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000268305,0.0003336293,0.025655115,0.00005277967,0.000988463,0.000012881825,0.0004185459,0.91669744,0.001884074,0.047528964,0.0032675336,0.0028922386],"study_design_scores_gemma":[0.0015055356,0.00013214236,0.008087238,0.00010069687,0.0015155672,0.0000246863,0.000092149065,0.82011116,0.0059962594,0.16216715,0.00005940974,0.00020802357],"about_ca_topic_score_codex":0.0000069039543,"about_ca_topic_score_gemma":0.000007831191,"teacher_disagreement_score":0.14635906,"about_ca_system_score_codex":0.00014989651,"about_ca_system_score_gemma":0.000053597654,"threshold_uncertainty_score":0.2833525},"labels":[],"label_agreement":null},{"id":"W3024135636","doi":"10.1007/s10742-023-00301-6","title":"Hierarchical causal variance decomposition for institution and provider comparisons in healthcare","year":2023,"lang":"en","type":"article","venue":"Health Services and Outcomes Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ontario Institute for Cancer Research","keywords":"Multinomial logistic regression; Multilevel model; Context (archaeology); Variance (accounting); Health administration; Health care; Variation (astronomy); Logistic regression; Medicine; Quality (philosophy); Statistics; Public health; Nursing; Mathematics; Geography","score_opus":0.6102249160260278,"score_gpt":0.6500267204155956,"score_spread":0.03980180438956782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024135636","genre_codex":"empirical","genre_gemma":"methods","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":[0.45888785,0.0014702275,0.41138747,0.121295966,0.00034978797,0.0056895404,0.00012646653,0.00069650804,0.000096178235],"genre_scores_gemma":[0.34328622,0.0015146978,0.65193826,0.0022932617,0.00007251219,0.00072552636,0.000059592534,0.00003465056,0.000075283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955494,0.0023948895,0.0005295997,0.0004613901,0.0002512178,0.0008135064],"domain_scores_gemma":[0.9896802,0.009559924,0.00012036154,0.00023887114,0.0001636182,0.00023706791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008331794,0.00015703621,0.0006194185,0.00047785035,0.00038153515,0.000036555066,0.00014887998,0.00019240534,0.0000032505843],"category_scores_gemma":[0.00074998004,0.00013553842,0.000029428562,0.0005015291,0.00020848692,0.00017542462,0.00022839317,0.00059018424,0.0000024994245],"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":[0.00035183938,0.000095408475,0.08169141,0.008304004,0.000024438115,0.000015739348,0.0039124805,0.000012154344,0.00027529706,0.8742744,0.00046753717,0.030575303],"study_design_scores_gemma":[0.0008602665,0.00063820445,0.1540555,0.00028207156,0.0000044610897,0.000021340635,0.0012598354,0.0059273457,0.00008143209,0.83484304,0.0018588532,0.00016763146],"about_ca_topic_score_codex":0.0030882887,"about_ca_topic_score_gemma":0.0088585345,"teacher_disagreement_score":0.24055077,"about_ca_system_score_codex":0.00013758661,"about_ca_system_score_gemma":0.00019666331,"threshold_uncertainty_score":0.5527096},"labels":[],"label_agreement":null},{"id":"W3024190863","doi":"10.1177/1740774520920893","title":"Adjusting for adherence in randomized trials when adherence is measured as a continuous variable: An application to the Lipid Research Clinics Coronary Primary Prevention Trial","year":2020,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","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":"London Health Sciences Centre; Western University","funders":"Patient-Centered Outcomes Research Institute","keywords":"Medicine; Randomized controlled trial; Primary prevention; Research design; Clinical trial; Secondary prevention; Coronary heart disease; Physical therapy; Internal medicine; Statistics; Disease; Mathematics","score_opus":0.8094234507609317,"score_gpt":0.642819391213717,"score_spread":0.1666040595472147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024190863","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":[0.03747052,0.00037142038,0.8847914,0.005187483,0.0013829739,0.068997055,0.00022255446,0.00066044054,0.0009162001],"genre_scores_gemma":[0.3087069,0.0011002786,0.6253604,0.007642195,0.011838907,0.043548018,0.00025785176,0.00031132335,0.0012341208],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9219942,0.059391,0.014007944,0.0019735538,0.0016033534,0.0010299544],"domain_scores_gemma":[0.49527675,0.4908754,0.0074484334,0.0026889266,0.002719756,0.000990722],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3163549,0.0004391092,0.0060506174,0.00015181565,0.00023694901,0.00019001066,0.001369299,0.00076785934,0.00027805765],"category_scores_gemma":[0.7181277,0.00030911723,0.0011252619,0.00079891086,0.00034821747,0.00037570286,0.00036290992,0.0013344907,0.00006815533],"study_design_candidate":"randomized_trial","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":[0.67727435,0.0010039806,0.000040268846,0.0002106121,0.00022982621,0.0000026877017,0.0011265235,0.000012678837,0.00156227,0.018673925,0.013607456,0.2862554],"study_design_scores_gemma":[0.3112895,0.0068911174,0.000014211085,0.00046740315,0.0004894782,0.0000016149025,0.00032959273,0.0016305497,0.0006905058,0.67106843,0.0067178123,0.00040979157],"about_ca_topic_score_codex":0.00005764678,"about_ca_topic_score_gemma":0.000034565586,"teacher_disagreement_score":0.65239453,"about_ca_system_score_codex":0.00014278578,"about_ca_system_score_gemma":0.0011512112,"threshold_uncertainty_score":0.9999361},"labels":[],"label_agreement":null},{"id":"W3025042862","doi":"10.2147/jmdh.s241085","title":"&lt;p&gt;Methods, Applications and Challenges in the Analysis of Interrupted Time Series Data: A Scoping Review&lt;/p&gt;","year":2020,"lang":"en","type":"article","venue":"Journal of Multidisciplinary Healthcare","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"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; St. Michael's Hospital; University of Toronto; McMaster University; Children's Hospital of Eastern Ontario; Impact","funders":"","keywords":"CINAHL; MEDLINE; Interrupted time series; Descriptive statistics; Computer science; Data science; Research design; Systematic review; Medicine; Web of science; Health care; Psychological intervention; Meta-analysis; Data mining; Statistics; Mathematics; Pathology; Nursing","score_opus":0.40645321681616026,"score_gpt":0.5238091338564785,"score_spread":0.11735591704031828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025042862","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01991655,0.65892124,0.10217168,0.21266668,0.000105864434,0.0052238177,0.00040023815,0.00019786216,0.00039605296],"genre_scores_gemma":[0.06429494,0.3952782,0.53936225,0.00055094005,0.00022450472,0.00014665417,0.0000690777,0.000059075915,0.000014398712],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9969055,0.000796312,0.001411129,0.0003114772,0.0003583022,0.00021729401],"domain_scores_gemma":[0.9963152,0.0011829892,0.0012492096,0.0007410973,0.00036309668,0.00014841108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002924364,0.00020596951,0.00108729,0.00028113404,0.00009999892,0.000015609923,0.0007743985,0.00010341852,0.000018792758],"category_scores_gemma":[0.0012130914,0.00014544821,0.00013748424,0.00096216163,0.00012385914,0.00047725847,0.00045550175,0.00044168707,0.0000010593186],"study_design_candidate":"systematic_review","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":[0.001558982,0.0024209095,0.006502087,0.20160322,0.0037882496,0.00042212493,0.10156961,0.00020146664,0.029221602,0.06072622,0.0051707104,0.5868148],"study_design_scores_gemma":[0.0076554953,0.014459588,0.06410022,0.43230084,0.018571552,0.0025148727,0.06559615,0.045247436,0.0054232883,0.30918854,0.028652206,0.006289825],"about_ca_topic_score_codex":0.000002806741,"about_ca_topic_score_gemma":0.00021014934,"teacher_disagreement_score":0.580525,"about_ca_system_score_codex":0.000055811135,"about_ca_system_score_gemma":0.00015958061,"threshold_uncertainty_score":0.59312063},"labels":[],"label_agreement":null},{"id":"W3025280704","doi":"10.1257/pandp.20201078","title":"A Proposed Specification Check for <i>p</i>-Hacking","year":2020,"lang":"en","type":"article","venue":"AEA Papers and Proceedings","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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 Ottawa","funders":"","keywords":"Hacker; Computer science; Specification; Set (abstract data type); Control (management); Programming language; Computer security; Artificial intelligence; Machine learning","score_opus":0.22378057856440436,"score_gpt":0.3763875279604566,"score_spread":0.15260694939605224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025280704","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":[0.7575182,0.0003860388,0.059634164,0.02556466,0.000134288,0.0059072506,0.000035202098,0.003130731,0.14768952],"genre_scores_gemma":[0.9025334,0.000058106478,0.096402444,0.00063085114,0.00012974217,0.00006880758,0.000002952988,0.000027036755,0.00014666973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993629,0.0000018058101,0.00016172067,0.00022772435,0.0000920467,0.00015383394],"domain_scores_gemma":[0.9996186,0.000064304615,0.000097618664,0.000043779037,0.00009781134,0.00007788498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001185367,0.000112260386,0.0001486927,0.00001772279,0.00008027638,0.00004885948,0.00008411888,0.00005938543,0.000019628089],"category_scores_gemma":[0.00036286633,0.00009751374,0.000032603035,0.00009700018,0.00003967344,0.00016192858,0.000028284101,0.00008289061,0.0000021845874],"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":[0.000096760516,0.000030616273,0.0010406711,0.00062147086,0.000021337157,6.7863175e-7,0.004685815,7.049056e-8,0.45385036,0.51290673,0.008218484,0.018527014],"study_design_scores_gemma":[0.0010799946,0.0007912438,0.00061948114,0.00018528372,0.0000895464,0.000013941128,0.0027011523,0.0008720823,0.30035466,0.57170916,0.12087748,0.0007059729],"about_ca_topic_score_codex":7.8264907e-7,"about_ca_topic_score_gemma":3.8002958e-7,"teacher_disagreement_score":0.15349568,"about_ca_system_score_codex":0.000015082584,"about_ca_system_score_gemma":0.000010438091,"threshold_uncertainty_score":0.3976495},"labels":[],"label_agreement":null},{"id":"W3027809961","doi":"10.1002/bimj.201900277","title":"Propensity score methods for time‐dependent cluster confounding","year":2020,"lang":"en","type":"article","venue":"Biometrical Journal","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":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Propensity score matching; Covariate; Confounding; Matching (statistics); Observational study; Cluster (spacecraft); Statistics; Computer science; Outcome (game theory); Econometrics; Mathematics","score_opus":0.5549064887138153,"score_gpt":0.5202090427054289,"score_spread":0.03469744600838642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027809961","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":[0.0063419575,0.00010320874,0.9906382,0.0014362972,0.00014597214,0.00051167863,0.0000069358166,0.0001837923,0.0006319785],"genre_scores_gemma":[0.05258558,0.000022937102,0.94560665,0.0009342345,0.0005019698,0.000019066209,0.0000022257354,0.00004172957,0.00028563297],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983387,0.0002177375,0.0005138166,0.0002398444,0.000330858,0.00035906112],"domain_scores_gemma":[0.9972105,0.0016319075,0.00030275658,0.0001539775,0.0003205614,0.00038029868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016844332,0.0001819293,0.0004376083,0.00041454978,0.00017122804,0.00016072912,0.00035172052,0.00013481824,0.00021722032],"category_scores_gemma":[0.00934937,0.00013687085,0.00017158853,0.0011115789,0.00006208393,0.0002343427,0.00016421243,0.00042201293,0.00003996964],"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":[0.0009956222,0.0006081967,0.0020224436,0.00047307293,0.0004704231,0.00012796097,0.0008420003,0.0000118899625,0.24328344,0.041048102,0.07270011,0.6374167],"study_design_scores_gemma":[0.0041025653,0.0033755272,0.00038762102,0.00024189147,0.00037895553,0.0015169305,0.00013662362,0.011217462,0.1916907,0.70899194,0.07643979,0.0015200019],"about_ca_topic_score_codex":6.955287e-7,"about_ca_topic_score_gemma":7.885031e-8,"teacher_disagreement_score":0.66794384,"about_ca_system_score_codex":0.00017068235,"about_ca_system_score_gemma":0.00006808329,"threshold_uncertainty_score":0.9989953},"labels":[],"label_agreement":null},{"id":"W3028305733","doi":"10.1016/j.patter.2020.100008","title":"gfoRmula: An R Package for Estimating the Effects of Sustained Treatment Strategies via the Parametric g-formula","year":2020,"lang":"en","type":"article","venue":"Patterns","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":90,"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 Mental Health; National Institute of Allergy and Infectious Diseases; U.S. National Library of Medicine; Fonds de recherche du Québec – Nature et technologies; National Institutes of Health; National Science Foundation","keywords":"R package; Package design; Parametric statistics; Mathematics; Computer science; Econometrics; Statistics; Engineering; Manufacturing engineering","score_opus":0.1078923772644685,"score_gpt":0.398412433487412,"score_spread":0.2905200562229435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028305733","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":[0.32676554,0.000021572127,0.6715502,0.0002789247,0.000031271964,0.0011272542,0.000018798368,0.00014402563,0.000062421925],"genre_scores_gemma":[0.9565141,0.000007730302,0.042841412,0.00013567529,0.00009425614,0.00034786385,0.000011916165,0.00003256788,0.000014461802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990272,0.000074110445,0.0002921941,0.00018170284,0.00016207743,0.00026271906],"domain_scores_gemma":[0.9968726,0.0023297411,0.00022566556,0.00043395476,0.000080901016,0.000057126108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017987376,0.00019930505,0.0002722472,0.000034920497,0.00012879918,0.000055513447,0.0003153644,0.00005262443,0.0000104280625],"category_scores_gemma":[0.00084119604,0.00010047663,0.00010616807,0.00018319661,0.000053453692,0.00019914053,0.00005603383,0.0001023142,0.0000016612388],"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":[0.00045075643,0.0017771913,0.010418677,0.011637456,0.0011131368,0.000087341956,0.07561505,0.0014486669,0.07383946,0.4229848,0.00087460154,0.39975286],"study_design_scores_gemma":[0.0014110428,0.004867263,0.0009808023,0.0001848304,0.00035176388,0.000008690589,0.006194595,0.09338667,0.30301785,0.5889915,0.00010758968,0.00049738085],"about_ca_topic_score_codex":0.000053611646,"about_ca_topic_score_gemma":0.000028576309,"teacher_disagreement_score":0.6297486,"about_ca_system_score_codex":0.000060033293,"about_ca_system_score_gemma":0.000035151203,"threshold_uncertainty_score":0.4097318},"labels":[],"label_agreement":null},{"id":"W3029886377","doi":"10.1111/sjos.12471","title":"Failure time studies with intermittent observation and losses to follow‐up","year":2020,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Parametric statistics; Nonparametric statistics; Econometrics; Mathematics; Sample size determination; Statistics; Parametric model; Joint (building); Engineering","score_opus":0.18056090870356195,"score_gpt":0.39020543207076624,"score_spread":0.2096445233672043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029886377","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":[0.23100065,0.00015530267,0.76520526,0.0030886137,0.0000803126,0.00026615206,0.000101245925,0.000054382177,0.000048082],"genre_scores_gemma":[0.39479694,0.00007834593,0.60447496,0.00035783887,0.00009189951,0.0000040180644,0.000002604726,0.000025766794,0.00016762536],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990063,0.000037865575,0.00041206868,0.0001224494,0.00026730154,0.00015405829],"domain_scores_gemma":[0.9984476,0.0003406015,0.0003713109,0.00009350044,0.0005499488,0.00019701703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016143634,0.00015794802,0.00039334176,0.00006862317,0.000056280416,0.00004396069,0.00013100899,0.00003226955,0.000027675578],"category_scores_gemma":[0.0013235842,0.00011489029,0.000025400428,0.00016276096,0.00009091267,0.00019656765,0.000055181834,0.00018576637,0.00000545111],"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":[0.002968425,0.00032901074,0.07360623,0.002683288,0.0022311085,0.002341179,0.056563668,0.00012345558,0.017744377,0.20498286,0.515553,0.12087337],"study_design_scores_gemma":[0.0044299937,0.01725426,0.012807666,0.005352747,0.0010748811,0.0009387326,0.013864406,0.0005690161,0.012995477,0.92324895,0.005923922,0.0015399483],"about_ca_topic_score_codex":9.0958804e-7,"about_ca_topic_score_gemma":0.000008944836,"teacher_disagreement_score":0.71826607,"about_ca_system_score_codex":0.000067938374,"about_ca_system_score_gemma":0.000039112434,"threshold_uncertainty_score":0.468509},"labels":[],"label_agreement":null},{"id":"W3033114400","doi":"10.1214/22-sts879","title":"The Role of Exchangeability in Causal Inference","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","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":"McGill University; University of Toronto","funders":"","keywords":"Causal inference; Inference; Property (philosophy); Contrast (vision); Bayesian probability; Predictive inference; Bayesian inference; Econometrics; Causal model; Frequentist inference; Computer science; Causal structure; Statistical inference; Mathematics; Artificial intelligence; Epistemology; Statistics; Philosophy","score_opus":0.12924522197799054,"score_gpt":0.4691296344740189,"score_spread":0.33988441249602835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033114400","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":[0.6048015,0.00007308428,0.34320036,0.0007552733,0.00030237884,0.001318288,0.00021311695,0.00089602417,0.04844],"genre_scores_gemma":[0.97739583,0.000017667799,0.022469485,0.000007466938,0.00000749516,0.00003749531,8.818486e-7,0.000004762094,0.000058926442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998578,0.000057891106,0.00027403477,0.00023676486,0.00046312137,0.0003901738],"domain_scores_gemma":[0.9953895,0.004022928,0.00006396997,0.00032960845,0.00011812024,0.00007585051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019334125,0.00007699207,0.0001345626,0.00007839992,0.00012796327,0.00002697176,0.0004584997,0.000028745526,0.0000446387],"category_scores_gemma":[0.013070271,0.00005111047,0.000012123216,0.0012216482,0.0016127657,0.00013659878,0.00022605699,0.00013742417,0.00002272515],"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":[0.0000045722873,0.000018829149,0.0032691874,0.0000100381185,4.818703e-7,0.0000023494306,0.00016613207,0.0000019045751,0.0047685606,0.95010996,0.000055068078,0.041592892],"study_design_scores_gemma":[0.000033356107,0.000048218502,0.02519238,0.000015884762,0.0000013205337,4.9067256e-7,0.00022170837,0.0029598144,0.0071575847,0.9640683,0.00023751086,0.00006340807],"about_ca_topic_score_codex":0.00007425215,"about_ca_topic_score_gemma":0.0002695524,"teacher_disagreement_score":0.37259436,"about_ca_system_score_codex":0.000071993585,"about_ca_system_score_gemma":0.00013895592,"threshold_uncertainty_score":0.9952431},"labels":[],"label_agreement":null},{"id":"W3034619260","doi":"10.1002/pds.5031","title":"Bias in case‐crossover studies of medications due to persistent use: A simulation study","year":2020,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Brigham and Women's Hospital","keywords":"Medicine; Pharmacoepidemiology; Crossover; Crossover study; Intensive care medicine; Pharmacology; Alternative medicine; Medical prescription","score_opus":0.5388691683247122,"score_gpt":0.5460614077403486,"score_spread":0.007192239415636403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034619260","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":[0.95286584,0.00044382794,0.038282905,0.0071313833,0.00005555725,0.000993109,0.00003729933,0.00011525926,0.00007484817],"genre_scores_gemma":[0.98864114,0.0001414866,0.009457573,0.0016177661,0.00003590223,0.000067781184,0.0000031568147,0.00001131189,0.000023876835],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978046,0.00087991176,0.0007249958,0.00030593682,0.00009060866,0.0001939748],"domain_scores_gemma":[0.98798966,0.011388502,0.00021734675,0.00015866481,0.0001240302,0.00012178133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021133432,0.00015452184,0.0006059912,0.00008135122,0.00008958186,0.0000028909596,0.00009189849,0.0000542156,0.000031847463],"category_scores_gemma":[0.009317989,0.00013052697,0.00005712343,0.00023833507,0.00014006709,0.00014778177,0.00016065745,0.0002221529,0.0000032329206],"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":[0.0030165203,0.0027164915,0.5774014,0.0012805783,0.0024491777,0.001572564,0.24059337,0.06759228,0.0024934993,0.06489379,0.017460806,0.018529521],"study_design_scores_gemma":[0.023965247,0.0053748465,0.14572743,0.0012099842,0.0043641226,0.0011580734,0.17608052,0.36400503,0.006990871,0.24890725,0.017386844,0.004829804],"about_ca_topic_score_codex":0.00009156327,"about_ca_topic_score_gemma":0.00014654889,"teacher_disagreement_score":0.43167397,"about_ca_system_score_codex":0.000049081493,"about_ca_system_score_gemma":0.000020881556,"threshold_uncertainty_score":0.99902695},"labels":[],"label_agreement":null},{"id":"W3035052016","doi":"10.1016/j.ijrobp.2020.02.638","title":"Understanding Propensity Score Analyses","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":54,"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 British Columbia","funders":"","keywords":"Propensity score matching; Observational study; Confounding; Medicine; Statistics; Randomized controlled trial; Sample size determination; Internal medicine; Mathematics","score_opus":0.5087663686543212,"score_gpt":0.4766493267535492,"score_spread":0.032117041900772025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035052016","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":[0.11929226,0.00009253168,0.8729871,0.004863222,0.0007505498,0.00020985134,0.000029228415,0.00015742377,0.001617863],"genre_scores_gemma":[0.96910185,0.00017810862,0.027815286,0.0013392215,0.0015000441,0.000004887776,0.0000185756,0.00002919063,0.00001284033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998265,0.00023519991,0.000776776,0.0002133715,0.00030603417,0.0002035703],"domain_scores_gemma":[0.99693453,0.0007379309,0.0013788443,0.00012963549,0.0006736984,0.00014533917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048752842,0.00019904795,0.00052202767,0.000112920294,0.00007697081,0.000041149375,0.00057935226,0.00019137296,0.000085396336],"category_scores_gemma":[0.0016662949,0.00017053762,0.00020886419,0.00021647844,0.0001838699,0.0004997434,0.00011575272,0.0005353749,0.00001792862],"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":[0.00042338495,0.00039193282,0.122848995,0.000028812892,0.0010163201,0.00011628396,0.0014383411,0.000858357,0.031369265,0.799995,0.009392599,0.032120716],"study_design_scores_gemma":[0.0016316822,0.00097490917,0.0011765086,0.00006530025,0.0001409841,0.0000850611,0.00018840088,0.0022144804,0.020328248,0.96761227,0.0052952627,0.00028688755],"about_ca_topic_score_codex":0.0000041237013,"about_ca_topic_score_gemma":0.0000027730084,"teacher_disagreement_score":0.8498096,"about_ca_system_score_codex":0.0008642797,"about_ca_system_score_gemma":0.000324358,"threshold_uncertainty_score":0.6954322},"labels":[],"label_agreement":null},{"id":"W3037840142","doi":"10.1186/s12874-020-01050-7","title":"A conceptual framework for prognostic research","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":192,"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 Tech University; Public Health Ontario; University of Toronto; Canadian Memorial Chiropractic College","funders":"","keywords":"Computer science; Conceptual framework; Data science; MEDLINE; Medicine; Management science; Sociology; Political science","score_opus":0.9537009219251084,"score_gpt":0.7282200696729361,"score_spread":0.2254808522521723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037840142","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":[0.007186115,0.00029856787,0.978814,0.010006688,0.00010932175,0.0020279626,0.000013282311,0.00037804322,0.0011659854],"genre_scores_gemma":[0.04223992,0.00012894672,0.9538759,0.00074875494,0.0010389435,0.0016934247,0.000007775503,0.00007305294,0.00019328856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9695448,0.023279358,0.0007715838,0.00093818974,0.0035345086,0.0019315203],"domain_scores_gemma":[0.4421055,0.5537502,0.00010803941,0.0007215974,0.0018141649,0.0015004653],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06224936,0.00021192933,0.0007753365,0.00029791344,0.00033225864,0.00004074993,0.0014638009,0.0008808991,0.0019376497],"category_scores_gemma":[0.8790135,0.00017415274,0.00014587057,0.0012112757,0.0035464615,0.00009338793,0.0009364445,0.003833684,0.0001617276],"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":[0.0003870403,0.00009540031,0.00024249293,0.00034114724,0.000023382056,0.00004404636,0.0017225594,3.55427e-7,0.0007656477,0.9640669,0.01990509,0.012405896],"study_design_scores_gemma":[0.00043876984,0.0016582089,0.000028937831,0.00022326774,0.000008778,0.000012938573,0.0028360395,0.00081361743,0.004310206,0.97013503,0.019368334,0.0001658704],"about_ca_topic_score_codex":0.000026321131,"about_ca_topic_score_gemma":0.00005883664,"teacher_disagreement_score":0.8167641,"about_ca_system_score_codex":0.00013022296,"about_ca_system_score_gemma":0.0020402446,"threshold_uncertainty_score":0.9991653},"labels":[],"label_agreement":null},{"id":"W3039902043","doi":"10.1016/j.chest.2020.03.011","title":"Using Causal Diagrams to Improve the Design and Interpretation of Medical Research","year":2020,"lang":"en","type":"review","venue":"CHEST Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":142,"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 British Columbia","funders":"Cancer Research UK","keywords":"Causal inference; Observational study; Terminology; Medicine; Confounding; Interpretation (philosophy); Directed acyclic graph; Causal structure; Relation (database); Inference; Selection bias; Outcome (game theory); Computer science; Artificial intelligence; Data mining; Linguistics; Algorithm; Pathology; Mathematics","score_opus":0.6701582115990727,"score_gpt":0.5913517703700976,"score_spread":0.07880644122897518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039902043","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000054349352,0.4895247,0.5095698,0.0001869515,0.00007592635,0.0005738416,0.0000025558252,0.000019451058,0.00004130288],"genre_scores_gemma":[0.00012060497,0.9116507,0.08777693,0.000022716755,0.0003269153,0.00004120711,8.354837e-7,0.00004926329,0.000010825618],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967124,0.0010372701,0.00077045447,0.00021155289,0.0009900521,0.0002783108],"domain_scores_gemma":[0.9950316,0.0037391381,0.00044847364,0.0002485251,0.00025470185,0.0002775506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005419617,0.00022583513,0.0009619244,0.00017424645,0.00013029242,0.00011230635,0.0006421053,0.0002962584,0.000035925186],"category_scores_gemma":[0.008188807,0.00013112056,0.00014367653,0.0003587497,0.00022335946,0.00009710019,0.00033554016,0.0020293586,0.0000044258227],"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":[0.000007543458,0.000017846458,2.43033e-7,0.0038730064,0.000060551512,0.000044553057,0.0005909195,5.3073836e-7,0.000019992964,0.0027702749,0.00045667047,0.9921579],"study_design_scores_gemma":[0.00024397606,0.0009544292,6.2525714e-7,0.06098927,0.00085622526,0.0023548394,0.00051431975,0.0037539355,0.00039424872,0.2448307,0.6844617,0.0006457197],"about_ca_topic_score_codex":0.000004817756,"about_ca_topic_score_gemma":0.000002193431,"teacher_disagreement_score":0.9915121,"about_ca_system_score_codex":0.0002121427,"about_ca_system_score_gemma":0.0007392979,"threshold_uncertainty_score":0.98033583},"labels":[],"label_agreement":null},{"id":"W3047016911","doi":"10.1257/aer.20190687","title":"Methods Matter: p-Hacking and Publication Bias in Causal Analysis in Economics","year":2020,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":333,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Credibility; Regression discontinuity design; Instrumental variable; Publication bias; Hacker; Causal inference; Omitted-variable bias; Economics; Identification (biology); Econometrics; Randomized experiment; Selection bias; Psychology; Statistics; Political science; Computer science; Law; MEDLINE; Mathematics; Computer security","score_opus":0.23393224661412015,"score_gpt":0.47090079454139366,"score_spread":0.2369685479272735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047016911","genre_codex":"empirical","genre_gemma":"methods","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":[0.6903905,0.028079813,0.18371676,0.06497444,0.000119555196,0.004813602,0.00008601895,0.0007152694,0.027104013],"genre_scores_gemma":[0.37214142,0.14368771,0.46690223,0.016701944,0.00005762414,0.00034642717,0.000042894288,0.000080146616,0.00003962178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982673,0.00026435472,0.00084715517,0.00040112782,0.000022742015,0.00019735258],"domain_scores_gemma":[0.99850804,0.00046735106,0.0005791064,0.00034364377,0.000015602389,0.00008623718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010032139,0.00016908081,0.0009806332,0.00020982376,0.000012285832,0.000035866648,0.0001895665,0.000029632325,0.00017282022],"category_scores_gemma":[0.00048534325,0.00017659974,0.00008952247,0.0005069704,0.00009768053,0.00028201,0.00009597202,0.00015245774,0.000044535787],"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":[0.000009077159,0.000040350842,0.17465805,0.00085784256,0.00020251343,0.00000309152,0.00047197164,0.000096471806,0.000035111312,0.023211522,0.0019573946,0.7984566],"study_design_scores_gemma":[0.0024095725,0.000833528,0.25457695,0.0046326476,0.003472651,0.000080598606,0.0018035993,0.0888748,0.0017507711,0.29490465,0.34001583,0.006644421],"about_ca_topic_score_codex":0.0002581341,"about_ca_topic_score_gemma":0.0004109569,"teacher_disagreement_score":0.7918122,"about_ca_system_score_codex":0.00020547627,"about_ca_system_score_gemma":0.000039332488,"threshold_uncertainty_score":0.72015285},"labels":[],"label_agreement":null},{"id":"W3048846123","doi":"10.1002/pds.5083","title":"Time‐related biases in pharmacoepidemiology","year":2020,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":161,"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; Jewish General Hospital","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Medicine; Pharmacoepidemiology; COPD; Lung cancer; Hazard ratio; Observational study; Cohort; Cohort study; Internal medicine; Emergency medicine; Medical prescription; Pharmacology; Confidence interval","score_opus":0.2100696790819873,"score_gpt":0.4555282154921335,"score_spread":0.24545853641014623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048846123","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":[0.79668117,0.0068796715,0.03396694,0.13653451,0.00072038564,0.002714325,0.00021289822,0.0036711143,0.018618999],"genre_scores_gemma":[0.9591199,0.0031994204,0.01766395,0.019289665,0.00023124788,0.000096372525,0.00005681883,0.000064455926,0.00027816716],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99413735,0.002940535,0.0013299942,0.0007235614,0.00009318219,0.0007753804],"domain_scores_gemma":[0.9780281,0.02095677,0.0003702946,0.00021878474,0.000052400166,0.00037364138],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048735207,0.00040183033,0.0011795327,0.00013438755,0.00011722757,0.0000041665094,0.000317242,0.00025418552,0.0012047517],"category_scores_gemma":[0.018792456,0.0003590268,0.00012314218,0.0003582884,0.0005018985,0.00024945172,0.00024757572,0.0009766949,0.00016126725],"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":[0.0034268065,0.00083404017,0.10474702,0.0007639051,0.0007449136,0.00060340774,0.007024547,0.003387529,0.06615439,0.29611087,0.45554546,0.06065709],"study_design_scores_gemma":[0.0071873018,0.00037695904,0.005363306,0.00029609597,0.00036489635,0.00022016079,0.00039523936,0.16918163,0.014362905,0.71925247,0.080798596,0.002200452],"about_ca_topic_score_codex":0.000034059245,"about_ca_topic_score_gemma":0.000007860158,"teacher_disagreement_score":0.42314157,"about_ca_system_score_codex":0.00006802853,"about_ca_system_score_gemma":0.000051296913,"threshold_uncertainty_score":0.99988616},"labels":[],"label_agreement":null},{"id":"W3049285076","doi":"10.1016/j.conctc.2020.100639","title":"An empirical comparison of time-to-event models to analyse a composite outcome in the presence of death as a competing risk","year":2020,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"Fogarty International Center; National Institutes of Health","keywords":"Hazard ratio; Proportional hazards model; Confidence interval; Medicine; Covariate; Observational study; Accelerated failure time model; Demography; Internal medicine; Statistics","score_opus":0.8439229051582652,"score_gpt":0.6493708172970246,"score_spread":0.19455208786124056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049285076","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":[0.6323611,0.00044137932,0.3412807,0.016373,0.000034916357,0.004867527,0.0002713346,0.00026783484,0.00410221],"genre_scores_gemma":[0.85649365,0.000039879098,0.14215551,0.0010856785,0.00003166077,0.00013406704,0.00002915152,0.000023785296,0.000006614547],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98109806,0.012436955,0.00538237,0.00041001098,0.00045471918,0.00021788121],"domain_scores_gemma":[0.9522346,0.04220539,0.0019800402,0.0029417432,0.00032497445,0.0003132286],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015468276,0.00024582676,0.0021155197,0.00015382966,0.00011895433,0.00003428815,0.003124574,0.00016910708,0.000028175338],"category_scores_gemma":[0.032729946,0.00018676718,0.00042699248,0.0008364856,0.00025740315,0.00023588748,0.00087019126,0.0008599858,0.00003171482],"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":[0.0027943528,0.011502406,0.868792,0.00022851852,0.00059591845,0.000009550441,0.04106589,0.010899444,0.0062601543,0.039968405,0.006857287,0.011026067],"study_design_scores_gemma":[0.0061265454,0.008287618,0.026143521,0.0015335593,0.0008965548,0.000003925878,0.011848175,0.5936077,0.004311084,0.34177572,0.0038577348,0.0016078615],"about_ca_topic_score_codex":0.00020207191,"about_ca_topic_score_gemma":0.000049868177,"teacher_disagreement_score":0.8426485,"about_ca_system_score_codex":0.000031179112,"about_ca_system_score_gemma":0.00018794579,"threshold_uncertainty_score":0.9754178},"labels":[],"label_agreement":null},{"id":"W3052338136","doi":"10.1097/bsd.0000000000001055","title":"Propensity Score Matching","year":2020,"lang":"en","type":"article","venue":"Clinical Spine Surgery A Spine Publication","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":"University of Toronto","funders":"","keywords":"Propensity score matching; Observational study; Outcome (game theory); Matching (statistics); Confounding; Medicine; Computer science; Econometrics; Internal medicine; Mathematics; Pathology","score_opus":0.503363480811191,"score_gpt":0.4645952154944371,"score_spread":0.03876826531675387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3052338136","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":[0.56761885,0.00005728796,0.37269947,0.052746087,0.00029501398,0.0011246318,0.000009957479,0.0024435986,0.0030051002],"genre_scores_gemma":[0.91919196,0.00010322686,0.071724586,0.0072595044,0.0010267624,0.00015400288,0.00016174049,0.00008167389,0.00029653462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99697196,0.00021640044,0.0014768986,0.0006330145,0.00033510203,0.00036659598],"domain_scores_gemma":[0.99715996,0.00056781666,0.0006916889,0.00064610795,0.0005493378,0.00038507834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021096675,0.00025416154,0.0007336771,0.00009031547,0.000105386374,0.000101621656,0.00035036902,0.00020109511,0.00029216113],"category_scores_gemma":[0.022721497,0.00022434356,0.0002864097,0.00068217935,0.00013805387,0.0006802808,0.0002447462,0.00055446586,0.00014498184],"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":[0.00014470151,0.0016153333,0.11253389,0.00082506303,0.00017668115,0.000039277984,0.00024912512,0.000006768822,0.006136023,0.33027995,0.22710563,0.32088754],"study_design_scores_gemma":[0.0009535705,0.0007069572,0.46008775,0.00047319834,0.00015353858,0.000032416403,0.00004905591,0.0013050371,0.0077073537,0.42003787,0.10664435,0.0018488972],"about_ca_topic_score_codex":0.000007593153,"about_ca_topic_score_gemma":0.0000037255024,"teacher_disagreement_score":0.3515731,"about_ca_system_score_codex":0.000047709047,"about_ca_system_score_gemma":0.0001500505,"threshold_uncertainty_score":0.9855105},"labels":[],"label_agreement":null},{"id":"W307107294","doi":"10.22237/jmasm/1177992660","title":"Tests for Treatment Group Equality When Data are Nonnormal and Heteroscedastic","year":2007,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Manitoba; York University","funders":"","keywords":"Heteroscedasticity; Mathematics; Nonparametric statistics; Statistics; Type I and type II errors; Econometrics; Monte Carlo method; Group (periodic table)","score_opus":0.49317632282399754,"score_gpt":0.5732767093652745,"score_spread":0.08010038654127699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W307107294","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":[0.0012137754,0.00008923188,0.99746674,0.0000652437,0.0000754186,0.00043490843,0.00029367895,0.000050888793,0.00031010938],"genre_scores_gemma":[0.15772328,0.000017591958,0.8419794,0.00006741177,0.00013461141,0.000015046779,0.00001405912,0.00003459209,0.000014048506],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99780506,0.0001895506,0.0009780871,0.00032044514,0.00030784679,0.00039902906],"domain_scores_gemma":[0.9860723,0.012326056,0.00068024057,0.00049933395,0.0001458203,0.00027624873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044915224,0.00025997017,0.0007475273,0.000099720695,0.00008704324,0.00004910086,0.00034072177,0.00013270523,0.0000193613],"category_scores_gemma":[0.003605969,0.000197372,0.00005369595,0.00005303661,0.00018347625,0.00017400573,0.0001652249,0.0002203019,5.0009726e-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":[0.0005978892,0.00038690012,0.00008352557,0.00017404434,0.000107092324,0.000025747942,0.00030433183,0.000002960143,0.01383378,0.36955377,0.00029344726,0.6146365],"study_design_scores_gemma":[0.0009728435,0.00066738494,0.0006786204,0.000049581107,0.00020479325,0.00006964016,0.00008690981,0.005430682,0.0029469847,0.98802733,0.0006550007,0.0002102051],"about_ca_topic_score_codex":0.0000034401442,"about_ca_topic_score_gemma":0.000021315762,"teacher_disagreement_score":0.6184736,"about_ca_system_score_codex":0.00015718979,"about_ca_system_score_gemma":0.00004186492,"threshold_uncertainty_score":0.8048597},"labels":[],"label_agreement":null},{"id":"W3080867134","doi":"10.1136/bmjopen-2020-036961","title":"Evaluation of propensity score used in cardiovascular research: a cross-sectional survey and guidance document","year":2020,"lang":"en","type":"article","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Medicine; Propensity score matching; Covariate; Data extraction; Impact factor; Matching (statistics); MEDLINE; Family medicine; Internal medicine; Statistics; Pathology","score_opus":0.8584909049281757,"score_gpt":0.6073207296458257,"score_spread":0.25117017528235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080867134","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":[0.9883363,0.00009386848,0.002200943,0.00007499918,0.000016011523,0.008109638,0.000014394446,0.00002589411,0.0011279003],"genre_scores_gemma":[0.9922186,0.000004339409,0.006840739,0.00001857193,0.000020989859,0.0008493368,0.00000723828,0.000013106978,0.000027061547],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99591154,0.0017269728,0.00040019702,0.00033164382,0.0014653862,0.00016424175],"domain_scores_gemma":[0.99793667,0.0003467337,0.000112095724,0.0004254053,0.0011229371,0.000056138964],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03343291,0.00008662233,0.00033560052,0.000052610034,0.000053735137,0.00009884896,0.0003389407,0.000061802806,0.000055781733],"category_scores_gemma":[0.010172111,0.000078779995,0.000040019342,0.0003169412,0.00011997576,0.00035537762,0.0006451338,0.00017731814,0.000004936647],"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":[0.00019926898,0.000051039973,0.99232763,0.00016721817,0.00008029296,0.0000061438714,0.0005056697,0.0002424206,0.0008333424,0.0038895993,0.0002523547,0.0014450024],"study_design_scores_gemma":[0.0007784911,0.00011268638,0.8953805,0.00010100842,0.000010671357,0.0000029190294,0.000026370755,0.00066783,0.0045292526,0.09824374,0.00003659009,0.00010995112],"about_ca_topic_score_codex":0.0006995505,"about_ca_topic_score_gemma":0.00070908613,"teacher_disagreement_score":0.096947156,"about_ca_system_score_codex":0.00014798246,"about_ca_system_score_gemma":0.00032542247,"threshold_uncertainty_score":0.9981656},"labels":[],"label_agreement":null},{"id":"W3081944489","doi":"10.1002/sim.8710","title":"Impact of discretization of the timeline for longitudinal causal inference methods","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"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":"Timeline; Causal inference; Inference; Computer science; Econometrics; Discretization; Statistics; Mathematics; Artificial intelligence","score_opus":0.22839864773798854,"score_gpt":0.5624154422413042,"score_spread":0.3340167945033157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081944489","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":[0.0048893294,0.000032365773,0.9937842,0.0003659722,0.000043814023,0.00041090974,0.00027945245,0.000021387757,0.00017257073],"genre_scores_gemma":[0.4437044,0.000019807349,0.5561584,0.000021652291,0.000037835318,0.000012686959,0.00002232188,0.0000115283265,0.000011364791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883294,0.00011060901,0.00057527045,0.00014004334,0.00021000665,0.00013112338],"domain_scores_gemma":[0.99659026,0.0024698914,0.0003686776,0.00022789095,0.0002967483,0.000046533976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005818945,0.00012150456,0.00042249472,0.000049412687,0.000017198461,0.0000016098173,0.00019789881,0.000049925748,0.00008791131],"category_scores_gemma":[0.018601522,0.00007324496,0.000037999005,0.0003061277,0.00027957352,0.000036625035,0.000057887126,0.00014527433,1.7861827e-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":[0.000148924,0.00008793036,0.022656498,0.00062257063,0.00006000714,0.0000018287922,0.0020817777,0.00027207527,0.025721297,0.936116,0.0036527053,0.008578401],"study_design_scores_gemma":[0.0007419555,0.0012495191,0.0154228825,0.00034820152,0.00010375082,0.0000013089598,0.00011097589,0.022169765,0.010664768,0.9490315,0.000032170712,0.00012322172],"about_ca_topic_score_codex":0.00006180794,"about_ca_topic_score_gemma":0.00002658,"teacher_disagreement_score":0.43881506,"about_ca_system_score_codex":0.000042692624,"about_ca_system_score_gemma":0.00008388684,"threshold_uncertainty_score":0.9896652},"labels":[],"label_agreement":null},{"id":"W3082894717","doi":"10.1002/sim.8722","title":"Multiply robust estimation of causal quantile treatment effects","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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 Waterloo; Roche (Canada)","funders":"","keywords":"Quantile; Causal inference; Estimator; Propensity score matching; Econometrics; Statistics; Inverse probability weighting; Empirical likelihood; Weighting; Average treatment effect; Inference; Computer science; Estimation; Mathematics; Artificial intelligence; Medicine; Economics","score_opus":0.1383377641491244,"score_gpt":0.4358404304734299,"score_spread":0.2975026663243055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082894717","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":[0.014555597,0.000059240123,0.98388314,0.00033506204,0.000072757684,0.00047266923,0.000065534114,0.00010799976,0.00044799145],"genre_scores_gemma":[0.4549971,0.000047201785,0.544736,0.00007122596,0.000042474494,0.000029602108,0.00003628318,0.000017214516,0.000022892584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989106,0.00006624249,0.00044263207,0.0001794728,0.00024049738,0.00016055163],"domain_scores_gemma":[0.9976616,0.0018190348,0.00018153641,0.00018354294,0.000072628354,0.00008165655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016789226,0.00015788947,0.00044944743,0.00007453049,0.00001839943,0.0000025233626,0.000092827584,0.00005560828,0.000078782774],"category_scores_gemma":[0.0046438915,0.00012410898,0.000015266229,0.00018398037,0.00014451898,0.000044774468,0.000023869672,0.00011673,0.000005808932],"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":[0.00019234898,0.00045369918,0.0018824175,0.0020197812,0.00008911126,0.0002892744,0.010243546,0.0038105578,0.013267986,0.8748778,0.012337448,0.08053602],"study_design_scores_gemma":[0.003835686,0.0051033385,0.0018120997,0.0009502524,0.00020288002,0.000007568421,0.0005647121,0.26775646,0.03662734,0.6825323,0.00021168431,0.00039567988],"about_ca_topic_score_codex":0.000097410084,"about_ca_topic_score_gemma":0.000052217514,"teacher_disagreement_score":0.4404415,"about_ca_system_score_codex":0.00008980677,"about_ca_system_score_gemma":0.000034116874,"threshold_uncertainty_score":0.5559507},"labels":[],"label_agreement":null},{"id":"W3083830176","doi":"10.1214/20-sts786","title":"On Nearly Assumption-Free Tests of Nominal Confidence Interval Coverage for Causal Parameters Estimated by Machine Learning","year":2020,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"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":"Shanghai University of Finance and Economics; University of Toronto; Eidgenössische Technische Hochschule Zürich; University of Washington; Office of Naval Research; Harvard University; National Science Foundation","keywords":"Estimator; Mathematics; Smoothness; Statistics; Confidence interval; Null hypothesis; Null (SQL); Algorithm; Computer science; Mathematical analysis","score_opus":0.14827249785666008,"score_gpt":0.42738724172025827,"score_spread":0.2791147438635982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083830176","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":[0.07653661,0.000006662123,0.92188567,0.00029929905,0.000038409013,0.0003351156,0.00052307895,0.00014766985,0.00022751518],"genre_scores_gemma":[0.70495695,0.0000019434008,0.29481432,0.00014980909,0.0000066134608,0.000022502662,0.0000142269455,0.000012204469,0.00002144146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982417,0.00005419803,0.00037730052,0.00043466466,0.0005218887,0.0003702349],"domain_scores_gemma":[0.9954509,0.003709844,0.00019181994,0.00023082805,0.00018039286,0.00023622013],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005505922,0.00017069055,0.00029985374,0.000047339377,0.00013793535,0.00007333191,0.0005515435,0.000048632402,0.000109977685],"category_scores_gemma":[0.026883721,0.00015056331,0.00003382602,0.00028476666,0.00089947035,0.00024337905,0.00014920534,0.0002689288,0.000013084111],"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":[0.0003118929,0.00014888264,0.00079055224,0.00019172934,0.00001195906,0.000017970324,0.0004322147,0.0003183645,0.11568566,0.87005985,0.003989927,0.008041013],"study_design_scores_gemma":[0.00069008284,0.003284235,0.0012172231,0.00017727276,0.00003933303,0.000007445393,0.000040565257,0.16835305,0.0338299,0.79188895,0.000088985245,0.00038294334],"about_ca_topic_score_codex":0.00008126993,"about_ca_topic_score_gemma":0.0000123328355,"teacher_disagreement_score":0.62842035,"about_ca_system_score_codex":0.000082253326,"about_ca_system_score_gemma":0.0001010529,"threshold_uncertainty_score":0.9813132},"labels":[],"label_agreement":null},{"id":"W3085668815","doi":"10.47302/jsr.2018520205","title":"Bootstrap bias correction for average treatment effects with inverse propensity weights","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Research","topic":"Advanced Causal Inference Techniques","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":"Carleton University; Memorial University of Newfoundland","funders":"","keywords":"Propensity score matching; Estimator; Average treatment effect; Endogeneity; Observational study; Econometrics; Statistics; Mathematics; Instrumental variable; Confounding; Inverse; Treatment effect; Medicine","score_opus":0.42776929817582293,"score_gpt":0.5138247682271289,"score_spread":0.08605547005130593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085668815","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":[0.39084458,0.000012700126,0.6059618,0.00012658752,0.00018523171,0.001528408,0.000023086213,0.000032289154,0.0012853465],"genre_scores_gemma":[0.80234814,0.00005926613,0.19510804,0.000017513581,0.00012352158,0.000046098638,0.0000044217863,0.00003392541,0.002259053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812686,0.00026629618,0.00033561242,0.00016719264,0.0007477311,0.0003563072],"domain_scores_gemma":[0.9910959,0.007431467,0.00017890292,0.0001935096,0.00090403407,0.00019615667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013533738,0.00013370227,0.00039098162,0.0002005441,0.00009345216,0.00005368648,0.00013375931,0.00007547336,0.00012368112],"category_scores_gemma":[0.0029953192,0.0000793287,0.000058859583,0.00016461094,0.00013850786,0.00019327166,0.000030065905,0.00045010442,0.000028393228],"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":[0.011587797,0.0033108394,0.010317001,0.00202606,0.00070586253,0.0014885176,0.001513235,0.000085386906,0.019714132,0.7817132,0.056628417,0.11090954],"study_design_scores_gemma":[0.0032330574,0.026260192,0.0028949997,0.00077281083,0.00009118767,0.00024497634,0.00017124976,0.0033898745,0.06877294,0.8908075,0.0030696318,0.00029154902],"about_ca_topic_score_codex":0.000023034985,"about_ca_topic_score_gemma":0.00004017779,"teacher_disagreement_score":0.41150358,"about_ca_system_score_codex":0.000390852,"about_ca_system_score_gemma":0.0002785161,"threshold_uncertainty_score":0.35858932},"labels":[],"label_agreement":null},{"id":"W3087032669","doi":"10.1002/pds.5121","title":"Implementing high‐dimensional propensity score principles to improve confounder adjustment in <scp>UK</scp> electronic health records","year":2020,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"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":"Medical Research Council; Medical Research Council Canada","keywords":"Medicine; Confounding; Propensity score matching; Clopidogrel; Observational study; Hazard ratio; Pharmacoepidemiology; Health records; Internal medicine; Psychological intervention; Confidence interval; Emergency medicine; Myocardial infarction; Medical prescription; Pharmacology; Psychiatry","score_opus":0.18407368460946416,"score_gpt":0.4199496426328565,"score_spread":0.23587595802339234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087032669","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":[0.8902684,0.0016425466,0.07610176,0.026242243,0.0003747298,0.0036724077,0.000112163005,0.00059028575,0.0009955141],"genre_scores_gemma":[0.9516456,0.00095870305,0.024590502,0.02213064,0.00023859879,0.00018322865,0.000053885055,0.00004218942,0.0001566117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995657,0.0009924824,0.0011406031,0.0007709382,0.00016519403,0.0012737688],"domain_scores_gemma":[0.9954449,0.0033578677,0.0004663394,0.00024004099,0.0000966364,0.0003942454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004913152,0.00036410734,0.0009312147,0.00009194717,0.0002354462,0.000008996302,0.00022517993,0.000110762434,0.00009190011],"category_scores_gemma":[0.0034650627,0.00032054578,0.00007440002,0.0002186994,0.0001079055,0.0001509931,0.00055309106,0.0007839932,0.000016615371],"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":[0.0006201983,0.00035803128,0.10039269,0.000832951,0.00031540438,0.000035124205,0.0035641755,0.00041078913,0.011442463,0.7952251,0.03858112,0.04822197],"study_design_scores_gemma":[0.009053921,0.0027323589,0.13986287,0.00063058635,0.00028265122,0.00010844476,0.0014079511,0.01543599,0.031902943,0.64118344,0.15577738,0.0016214676],"about_ca_topic_score_codex":0.00028445126,"about_ca_topic_score_gemma":0.00042955557,"teacher_disagreement_score":0.15404163,"about_ca_system_score_codex":0.00031289784,"about_ca_system_score_gemma":0.00028907182,"threshold_uncertainty_score":0.99992466},"labels":[],"label_agreement":null},{"id":"W3088227231","doi":"10.1177/1536867x20953572","title":"Causal mediation analysis in instrumental-variables regressions","year":2020,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":186,"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","funders":"","keywords":"Instrumental variable; Mediation; Causal inference; Econometrics; Mediator; Psychology; Causal analysis; Causal model; Variables; Estimation; Statistics; Mathematics; Medicine; Sociology; Economics; Social science; Internal medicine","score_opus":0.19406576556761382,"score_gpt":0.43369128149908953,"score_spread":0.2396255159314757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088227231","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":[0.04410705,0.00039765728,0.9339352,0.017200433,0.000055513545,0.0007253061,0.0024212697,0.00014823937,0.0010093354],"genre_scores_gemma":[0.73017955,0.0016946244,0.2675782,0.0002571064,0.000025191619,0.000018812716,0.00020354736,0.000023995013,0.000018960814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979799,0.00056127255,0.00068658375,0.00019553801,0.00032681684,0.00024993924],"domain_scores_gemma":[0.9956335,0.0026187177,0.0005201558,0.0009178163,0.00015055023,0.0001592973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012672431,0.00017832528,0.0003216113,0.00018613687,0.0006177296,0.00017946862,0.00087811594,0.000047808324,0.000067539884],"category_scores_gemma":[0.0027731725,0.00012901131,0.00003787665,0.0006976724,0.00021736757,0.00021613733,0.00046332623,0.0008550542,0.0000031708355],"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":[0.000097089054,0.00044006374,0.008439199,0.000096851785,0.0005589162,0.000033917004,0.01588289,0.0001834527,0.00063849584,0.92674184,0.0066963434,0.040190928],"study_design_scores_gemma":[0.0007797037,0.00041638777,0.0029812714,0.00020662548,0.00040229445,0.000035935518,0.0034741992,0.12886366,0.00015761264,0.86027414,0.0019966918,0.0004114998],"about_ca_topic_score_codex":0.000049249156,"about_ca_topic_score_gemma":0.00027753934,"teacher_disagreement_score":0.6860725,"about_ca_system_score_codex":0.00007991783,"about_ca_system_score_gemma":0.00008836107,"threshold_uncertainty_score":0.5260929},"labels":[],"label_agreement":null},{"id":"W3088839437","doi":"10.1515/jqas-2020-0060","title":"A contextual analysis of crossing the ball in soccer","year":2020,"lang":"en","type":"article","venue":"Journal of Quantitative Analysis in Sports","topic":"Advanced Causal Inference Techniques","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Level crossing; Computer science; Inference; Ball (mathematics); Border crossing; Causal inference; Artificial intelligence; Machine learning; Econometrics; Mathematics; Engineering","score_opus":0.24222184916877643,"score_gpt":0.4724619200366338,"score_spread":0.23024007086785736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088839437","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":[0.8843996,0.00023612885,0.1145349,0.00047995726,0.000013042818,0.00008591907,0.000007421357,0.000008284662,0.00023477282],"genre_scores_gemma":[0.9750471,0.00006741724,0.02464312,0.00020145159,0.0000147122755,0.0000021928215,0.0000021255885,0.000010619963,0.00001124718],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99722064,0.00022591157,0.001616068,0.0001768577,0.0005724922,0.00018804902],"domain_scores_gemma":[0.9963069,0.0011797351,0.0017766652,0.00021755406,0.0004528058,0.000066353154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019404391,0.00016269805,0.0013432666,0.0013609672,0.0000382215,0.00003822815,0.00031232522,0.00007188417,0.00019622403],"category_scores_gemma":[0.0018259102,0.000110495355,0.00069609925,0.006083196,0.00024605307,0.00030944328,0.00005135267,0.0004130411,4.660976e-7],"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":[0.00035030034,0.00038538236,0.89168227,0.000048736474,0.0068942313,0.0003993136,0.02927174,0.020751147,0.0021904772,0.046440747,0.00020586539,0.0013797699],"study_design_scores_gemma":[0.0012002514,0.0006370458,0.76085883,0.00034103543,0.01932315,0.000009254874,0.029171806,0.06347666,0.0025337616,0.12165451,0.00019790468,0.0005958068],"about_ca_topic_score_codex":0.00006749169,"about_ca_topic_score_gemma":0.0009764948,"teacher_disagreement_score":0.13082348,"about_ca_system_score_codex":0.000084656764,"about_ca_system_score_gemma":0.00010156592,"threshold_uncertainty_score":0.45058697},"labels":[],"label_agreement":null},{"id":"W3089978665","doi":"10.1097/ede.0000000000001267","title":"Single-arm Trials with Historical Controls","year":2020,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Long arm; Biology; Genetics","score_opus":0.6572075309335021,"score_gpt":0.4891268965738019,"score_spread":0.16808063435970028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089978665","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":[0.0046232017,0.00040979052,0.949369,0.038544085,0.00012671996,0.00057088374,0.0000071892996,0.0008567095,0.005492379],"genre_scores_gemma":[0.4050654,0.00004409248,0.5776601,0.015532801,0.0008710714,0.00018466222,0.000008880666,0.00006865247,0.0005643596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968465,0.0014020333,0.0009508635,0.00034830114,0.00008587434,0.00036640163],"domain_scores_gemma":[0.9769657,0.021934919,0.00055418734,0.00028153302,0.00007301589,0.00019063092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028279123,0.00019517669,0.0015977089,0.000033191205,0.00003858756,0.0000033879787,0.0002014816,0.0001866036,0.0002931174],"category_scores_gemma":[0.08612362,0.00013265616,0.0001281028,0.00009802385,0.00009997384,0.00006824609,0.000049737246,0.0003027876,0.000048440197],"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":[0.00062322954,0.00029654198,0.0021162576,0.00006316109,0.0001309066,0.000047109297,0.0002965269,0.000019846213,0.0074197357,0.8433286,0.13266844,0.012989681],"study_design_scores_gemma":[0.0007047978,0.0023356257,0.000049756058,0.00002328771,0.00007224637,0.000020580788,0.000021907967,0.00019069227,0.0017749,0.8571756,0.13738255,0.00024805087],"about_ca_topic_score_codex":0.000014982776,"about_ca_topic_score_gemma":0.000004605189,"teacher_disagreement_score":0.40044218,"about_ca_system_score_codex":0.00022395824,"about_ca_system_score_gemma":0.000034043194,"threshold_uncertainty_score":0.92157435},"labels":[],"label_agreement":null},{"id":"W3090620836","doi":"10.1016/j.jclinepi.2020.09.017","title":"GRADE Guidelines: 29. Rating the certainty in time-to-event outcomes—Study limitations due to censoring of participants with missing data in intervention studies","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; McMaster University; Impact","funders":"","keywords":"Censoring (clinical trials); Missing data; Medicine; Survival analysis; Proportional hazards model; Statistics; Mathematics","score_opus":0.9206566054490741,"score_gpt":0.6874685182399085,"score_spread":0.23318808720916562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090620836","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":[0.85119516,0.00009186191,0.099880226,0.04816409,0.00008969928,0.0005453269,0.0000039740917,0.000017717079,0.000011973097],"genre_scores_gemma":[0.835455,0.000034417208,0.16237357,0.0019891353,0.00010853032,0.000015556647,9.312172e-7,0.000014705775,0.000008146907],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98753965,0.003946008,0.007526265,0.00034238878,0.00028548384,0.00036021534],"domain_scores_gemma":[0.93343073,0.062319726,0.0030187636,0.00054862944,0.0004609308,0.00022119796],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030422391,0.00016772017,0.002237061,0.00012757532,0.00003419299,0.000006708512,0.0006865313,0.00008455016,0.000007716994],"category_scores_gemma":[0.49570587,0.0000971071,0.00016431697,0.00033317524,0.00009629064,0.00015889303,0.0004398126,0.0007364105,0.000004059849],"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":[0.00071690214,0.001492201,0.93724257,0.0001428671,0.00047962784,0.00013086075,0.0051168124,0.014171102,0.00013112993,0.0012820996,0.0026376403,0.03645618],"study_design_scores_gemma":[0.0051233335,0.009259594,0.78107727,0.004769521,0.00048951135,0.000041820993,0.021426195,0.02292452,0.00017864612,0.15358134,0.0005432423,0.0005850043],"about_ca_topic_score_codex":0.000028908888,"about_ca_topic_score_gemma":0.00041046506,"teacher_disagreement_score":0.46528348,"about_ca_system_score_codex":0.000057676687,"about_ca_system_score_gemma":0.00007314661,"threshold_uncertainty_score":0.9983842},"labels":[],"label_agreement":null},{"id":"W3090836172","doi":"10.1097/ede.0000000000001253","title":"Postmyocardial Infarction Statin Exposure and the Risk of Stroke with Weighting for Outcome Misclassification","year":2020,"lang":"en","type":"article","venue":"Epidemiology","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":"McGill University; Jewish General Hospital; University of Ottawa","funders":"Biogen; Eli Lilly and Company; Canadian Institutes of Health Research; Mitacs; McGill University; Amgen","keywords":"Medicine; Confidence interval; Confounding; Observational study; Inverse probability weighting; Odds ratio; Randomized controlled trial; Stroke (engine); Statin; Inverse probability; Outcome (game theory); Statistics; Internal medicine; Emergency medicine; Propensity score matching; Mathematics","score_opus":0.22109227161303385,"score_gpt":0.4148833491069785,"score_spread":0.19379107749394464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090836172","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":[0.26917306,0.000103723956,0.7202284,0.009307729,0.000034033947,0.000736922,0.00006334955,0.000109125394,0.000243725],"genre_scores_gemma":[0.77186,0.000053616874,0.2272755,0.000588249,0.000077698314,0.000105770836,0.000008158505,0.000013313457,0.000017659075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984898,0.0005922898,0.00052378094,0.0001879678,0.000053714182,0.00015242676],"domain_scores_gemma":[0.9885832,0.0105003435,0.00061209424,0.00017241662,0.000092246286,0.000039679722],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018393898,0.000106581465,0.0004709863,0.000022369259,0.000067766116,0.0000026369562,0.00008674646,0.00008851709,0.000005756762],"category_scores_gemma":[0.016385676,0.000061192964,0.00006225515,0.00005175954,0.00024113774,0.000055572804,0.000030049623,0.00018739082,6.347686e-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":[0.0010938338,0.000023050556,0.24879116,0.0001665639,0.00019732643,2.1791399e-7,0.0024345277,0.00010662506,0.0035241435,0.7337894,0.0011705896,0.008702572],"study_design_scores_gemma":[0.0025835012,0.0011963869,0.044653513,0.000030945146,0.00027108795,0.000008490707,0.0009836388,0.007826379,0.0021983886,0.9384629,0.0015517335,0.0002330518],"about_ca_topic_score_codex":0.000025216046,"about_ca_topic_score_gemma":0.000010033323,"teacher_disagreement_score":0.502687,"about_ca_system_score_codex":0.000013465046,"about_ca_system_score_gemma":0.000015503321,"threshold_uncertainty_score":0.9918997},"labels":[],"label_agreement":null},{"id":"W3091170675","doi":"10.1093/ije/dyaa127","title":"Bias factor, maximum bias and the E-value: insight and extended applications","year":2020,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Value (mathematics); Statistics; Factor (programming language); Econometrics; Mathematics; Computer science","score_opus":0.3817986940034575,"score_gpt":0.47124402102576,"score_spread":0.08944532702230251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091170675","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":[0.058543906,0.0027824903,0.8538628,0.0822909,0.0002696509,0.0004281138,0.0000311668,0.000078754885,0.0017121716],"genre_scores_gemma":[0.88914037,0.0024556324,0.09995275,0.007844731,0.00051709026,0.00002544346,0.0000032488724,0.000019857287,0.000040895953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982501,0.0005048565,0.00080027664,0.0001512265,0.0001614949,0.00013201007],"domain_scores_gemma":[0.9903955,0.008257218,0.00081629393,0.00011569072,0.00030010307,0.00011521981],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014356391,0.00012430843,0.00043549156,0.000083321785,0.000043297652,0.000017506267,0.0003608522,0.000087485045,0.000051144052],"category_scores_gemma":[0.0142479725,0.00007504874,0.000088163884,0.000061564664,0.0004393496,0.00015105051,0.00014869375,0.00035798157,0.0000032822543],"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":[0.00019239071,0.00003440142,0.0033885883,0.000013073538,0.00017839849,0.000013832212,0.0005932569,0.00000956282,0.00036789387,0.96473163,0.0018468372,0.02863011],"study_design_scores_gemma":[0.0007269317,0.00011047067,0.0019776148,0.00002772487,0.000029474135,0.00028532415,0.00007634824,0.00051197497,0.0002775908,0.96495724,0.030938804,0.00008051735],"about_ca_topic_score_codex":0.000008910151,"about_ca_topic_score_gemma":0.0000027152635,"teacher_disagreement_score":0.83059645,"about_ca_system_score_codex":0.00003555188,"about_ca_system_score_gemma":0.000038456135,"threshold_uncertainty_score":0.99405545},"labels":[],"label_agreement":null},{"id":"W3091744499","doi":"10.1093/ije/dyaa152","title":"Can synthetic controls improve causal inference in interrupted time series evaluations of public health interventions?","year":2020,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"St. Michael's Hospital","funders":"Joyce Foundation","keywords":"Interrupted time series; Causal inference; Counterfactual thinking; Psychological intervention; Interrupted Time Series Analysis; Observational study; Computer science; Inference; Time series; Control (management); Public health; Research design; Confounding; Clinical study design; Series (stratigraphy); Machine learning; Econometrics; Artificial intelligence; Medicine; Psychology; Mathematics; Statistics; Clinical trial","score_opus":0.3983787466085861,"score_gpt":0.5332732795590025,"score_spread":0.13489453295041642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091744499","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":[0.09274219,0.00070478383,0.75165457,0.15298748,0.0006805268,0.0005728636,0.00025292,0.00008633498,0.00031830813],"genre_scores_gemma":[0.95944864,0.00017212992,0.03876806,0.0013906672,0.00012840277,0.000020591657,0.000017466617,0.000017407521,0.000036612044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995081,0.0015068562,0.0026030992,0.00020687835,0.00029495702,0.00030720764],"domain_scores_gemma":[0.9898933,0.0059997514,0.0025465735,0.00018176566,0.0011746767,0.00020393293],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005262359,0.000175569,0.0010028089,0.0003966668,0.000022301027,0.00001369564,0.00067269505,0.0001102211,0.00034944256],"category_scores_gemma":[0.08124021,0.00015346629,0.00027393358,0.00017620191,0.000250352,0.00036454582,0.00015519961,0.00048677396,0.000005923922],"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":[0.0006733926,0.0011568314,0.031869613,0.00038092435,0.0013565568,0.000088534754,0.0049452274,0.0008654793,0.019595016,0.8435213,0.003664886,0.09188222],"study_design_scores_gemma":[0.0018978704,0.0030116474,0.005493934,0.0014276969,0.00006170357,0.00017902661,0.0005941307,0.0052594705,0.0017833811,0.9788219,0.0011445339,0.00032474683],"about_ca_topic_score_codex":0.00006489538,"about_ca_topic_score_gemma":0.00013825674,"teacher_disagreement_score":0.8667065,"about_ca_system_score_codex":0.00032798227,"about_ca_system_score_gemma":0.00043404946,"threshold_uncertainty_score":0.9264989},"labels":[],"label_agreement":null},{"id":"W3092385491","doi":"10.1002/sim.8764","title":"The effect of a constraint on the maximum number of controls matched to each treated subject on the performance of full matching on the propensity score when estimating risk differences","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"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; Matching (statistics); Observational study; Calipers; Constraint (computer-aided design); Statistics; Mathematics; Average treatment effect; Econometrics; Medicine","score_opus":0.09042720693450075,"score_gpt":0.3650431871051201,"score_spread":0.2746159801706194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092385491","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":[0.94325155,0.00000800638,0.05084564,0.0030306135,0.000043836077,0.0019243074,0.00014214954,0.000036837195,0.0007170584],"genre_scores_gemma":[0.98470354,0.000020057914,0.014771525,0.0003115615,0.00003770612,0.00011688391,0.0000042602883,0.000024305886,0.000010170214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972691,0.0008317699,0.0007621628,0.00022546186,0.0006540654,0.00025746907],"domain_scores_gemma":[0.9734361,0.025051797,0.0007456525,0.0005541221,0.000156063,0.000056219287],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002976065,0.0002836324,0.00075902545,0.00003725373,0.00017872412,0.000014244804,0.00054709805,0.00005936608,0.00008729621],"category_scores_gemma":[0.016697058,0.00010147599,0.00004544322,0.00022328911,0.0008113193,0.000022317618,0.00009049935,0.0006916947,0.0000042785305],"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":[0.005154565,0.00025463814,0.04942407,0.0015714526,0.0004564724,0.000027875734,0.033189066,0.0005378201,0.025323585,0.85125405,0.003298048,0.029508347],"study_design_scores_gemma":[0.0026698047,0.016575456,0.01109361,0.008672591,0.00045209634,0.000015542082,0.005641029,0.048944917,0.090592064,0.81481755,0.000011645239,0.0005136946],"about_ca_topic_score_codex":0.00019554925,"about_ca_topic_score_gemma":0.000059635226,"teacher_disagreement_score":0.06526848,"about_ca_system_score_codex":0.000047351798,"about_ca_system_score_gemma":0.00004334094,"threshold_uncertainty_score":0.99158573},"labels":[],"label_agreement":null},{"id":"W3092939691","doi":"10.1101/2020.10.12.20211706","title":"Evaluation of statistical methods used in the analysis of interrupted time series studies: a simulation study","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","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":"Ottawa Hospital; University of Ottawa","funders":"Monash University","keywords":"Autocorrelation; Statistics; Series (stratigraphy); Ordinary least squares; Mathematics; Restricted maximum likelihood; Econometrics; Population; Autocorrelation technique; Maximum likelihood; Demography; Biology","score_opus":0.5710198001624486,"score_gpt":0.6137507411071274,"score_spread":0.042730940944678775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092939691","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":[0.59648794,0.000053443426,0.40177152,0.000059057555,0.00002878989,0.0014273662,0.00005069022,0.000056840516,0.0000643274],"genre_scores_gemma":[0.8730078,0.0000076244737,0.12668951,0.000006903645,0.000010120385,0.00022468514,0.000032283053,0.000017449192,0.0000036425756],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924925,0.0047121723,0.0011640158,0.00038632288,0.0011220605,0.00012290892],"domain_scores_gemma":[0.99152505,0.005880762,0.00080817833,0.00075143494,0.0010129567,0.000021587035],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011576342,0.0002369375,0.0012455202,0.0004244705,0.000018228006,0.000012335635,0.00040134226,0.00012263181,0.00010748395],"category_scores_gemma":[0.020915305,0.00017137734,0.00014353446,0.0009910952,0.00013638537,0.00006823432,0.00037598028,0.00037978627,9.475414e-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":[0.0007655891,0.0061147846,0.11199706,0.003433828,0.039299343,0.000040017258,0.42848825,0.3241511,0.013414905,0.026891707,0.0001499761,0.04525342],"study_design_scores_gemma":[0.0003369732,0.00033718202,0.032818474,0.00017010016,0.011183498,1.5073043e-7,0.0076667373,0.4166011,0.0016405366,0.52902573,0.0000022377294,0.00021728972],"about_ca_topic_score_codex":0.00002588914,"about_ca_topic_score_gemma":0.00014353117,"teacher_disagreement_score":0.502134,"about_ca_system_score_codex":0.0001436833,"about_ca_system_score_gemma":0.00010243021,"threshold_uncertainty_score":0.9873319},"labels":[],"label_agreement":null},{"id":"W3093094898","doi":"10.1101/2020.10.15.20212886","title":"Population attributable fraction for continuously distributed exposures","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","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":"McMaster University; Population Health Research Institute","funders":"","keywords":"Econometrics; Inference; Attributable risk; Statistics; Categorical variable; Population; Estimator; Categorization; Risk factor; Causal inference; Computer science; Mathematics; Medicine; Environmental health; Artificial intelligence","score_opus":0.20869255994259875,"score_gpt":0.4191759803314865,"score_spread":0.21048342038888776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093094898","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":[0.17780937,0.00006254702,0.81789154,0.00058254454,0.00033864102,0.0014140657,0.00060559774,0.0011705144,0.0001251919],"genre_scores_gemma":[0.89787567,0.000026346017,0.09887481,0.000067231646,0.00034595962,0.0007006486,0.0019144787,0.000083635336,0.0001111979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980927,0.00009352819,0.0006355662,0.00056647346,0.0002864339,0.0003253164],"domain_scores_gemma":[0.9977765,0.000607441,0.000644293,0.0005781937,0.00029073693,0.00010284145],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043989834,0.00035949494,0.0008297359,0.00007845159,0.00010521049,0.00008601426,0.00032178787,0.00045448507,0.00005447175],"category_scores_gemma":[0.0032188273,0.00035963109,0.0002087199,0.00012332764,0.00003180616,0.00015228846,0.00028637986,0.0005804834,0.000011147174],"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":[0.0010604357,0.0011265473,0.36095062,0.009707155,0.0010875997,0.000081086895,0.0010582935,0.0010341199,0.050994437,0.42773446,0.12666966,0.018495565],"study_design_scores_gemma":[0.00025399512,0.00010721454,0.009168175,0.00021708038,0.00012489947,0.0000023344362,0.00003170951,0.0013452566,0.016367,0.966679,0.00526512,0.00043823835],"about_ca_topic_score_codex":0.000073671785,"about_ca_topic_score_gemma":0.000033473516,"teacher_disagreement_score":0.7200663,"about_ca_system_score_codex":0.00021832819,"about_ca_system_score_gemma":0.000050107512,"threshold_uncertainty_score":0.99988556},"labels":[],"label_agreement":null},{"id":"W3093632891","doi":"10.1515/em-2019-0021","title":"A comparison of approaches for estimating combined population attributable risks (PARs) for multiple risk factors","year":2020,"lang":"en","type":"article","venue":"Epidemiologic Methods","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 Calgary; McMaster University; Impact; Alberta Health Services","funders":"Canadian Cancer Society","keywords":"Statistics; Econometrics; Population; Estimation; Attributable risk; Risk factor; Relative risk; Risk assessment; Mathematics; Computer science; Medicine; Environmental health; Economics; Confidence interval","score_opus":0.8704649646198399,"score_gpt":0.6146697198316243,"score_spread":0.2557952447882156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093632891","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":[0.08347224,0.00007455648,0.91369945,0.00017032413,0.00009371851,0.0019121123,0.00016010326,0.00038692093,0.00003057296],"genre_scores_gemma":[0.40251473,0.0000019649954,0.59698135,0.00002878369,0.000048050755,0.00028844748,0.00010845676,0.000023315706,0.0000049038804],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961793,0.001481768,0.0013488766,0.00047293556,0.000106389874,0.0004107632],"domain_scores_gemma":[0.9425761,0.055253413,0.0016032538,0.00032317976,0.00013083692,0.00011321899],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006837143,0.00029647187,0.001670911,0.000054133416,0.00017841192,0.000010048409,0.00028534065,0.00027936726,0.0000126802115],"category_scores_gemma":[0.22084069,0.00023199082,0.00029065262,0.00018628188,0.000077141005,0.00012404837,0.00009765008,0.00028019416,4.3301657e-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":[0.0004807586,0.00035635868,0.7591751,0.0015414607,0.00022961383,1.34789e-7,0.0017050877,0.047203127,0.0034434514,0.100411676,0.0031326616,0.08232053],"study_design_scores_gemma":[0.000304018,0.00041709974,0.0020097906,0.000023522769,0.00007887056,1.28802e-7,0.00018826363,0.5540435,0.015196541,0.4275101,0.00007377268,0.00015440113],"about_ca_topic_score_codex":0.00010423697,"about_ca_topic_score_gemma":0.000004560088,"teacher_disagreement_score":0.7571654,"about_ca_system_score_codex":0.000060919105,"about_ca_system_score_gemma":0.000016228641,"threshold_uncertainty_score":0.94603115},"labels":[],"label_agreement":null},{"id":"W3099982168","doi":"10.1214/23-sts889","title":"Causal Inference Methods for Combining Randomized Trials and Observational Studies: A Review","year":2024,"lang":"en","type":"review","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Google (Canada)","funders":"National Institute on Aging; U.S. Food and Drug Administration","keywords":"Observational study; Causal inference; Inference; Randomized controlled trial; Econometrics; Computer science; Statistics; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.85000118132543,"score_gpt":0.7220045213661083,"score_spread":0.12799665995932175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099982168","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":[4.8316657e-9,0.5264271,0.47004446,0.0000688063,0.00018406058,0.0028380489,0.00021037082,0.00011054069,0.00011658328],"genre_scores_gemma":[9.695627e-8,0.5241299,0.4738301,0.00007671751,0.00003762766,0.0018177717,0.0000219868,0.000023340206,0.000062420935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930138,0.0022084746,0.0026463207,0.0010135731,0.0005784366,0.0005393767],"domain_scores_gemma":[0.81605923,0.18155572,0.001057007,0.000458257,0.0006379003,0.00023187713],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045170214,0.0005765579,0.008347887,0.00020825601,0.00023023659,0.00017198206,0.00057429826,0.00015645317,0.000076559714],"category_scores_gemma":[0.44532037,0.0003403054,0.00042910653,0.0009466724,0.0025195752,0.00023268689,0.0004763764,0.0004998031,0.000010464306],"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":[0.00003063781,0.0000073250094,4.9486997e-9,0.044592272,0.000079759375,0.0000016509663,0.000024014596,4.30375e-9,3.0347377e-7,0.5188706,0.001372183,0.43502128],"study_design_scores_gemma":[0.0013545627,0.000059179656,1.6954552e-8,0.05300898,0.0038504296,0.000012825291,0.000008235234,0.00016972848,8.5732574e-7,0.75610656,0.18510321,0.00032541988],"about_ca_topic_score_codex":0.000002775722,"about_ca_topic_score_gemma":0.0000012800932,"teacher_disagreement_score":0.43469587,"about_ca_system_score_codex":0.0002475097,"about_ca_system_score_gemma":0.0011683056,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W3105768632","doi":"10.1002/sim.8857","title":"Conflating marginal and conditional treatment effects: Comments on “Assessing the performance of population adjustment methods for anchored indirect comparisons: A simulation study”","year":2021,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":37,"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":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research","keywords":"Inference; Marginal structural model; Econometrics; Marginal model; Population; Treatment effect; Causal inference; Statistics; Statistical inference; Computer science; Medicine; Mathematics; Artificial intelligence; Regression analysis","score_opus":0.20791701651492495,"score_gpt":0.5391972190249351,"score_spread":0.33128020251001017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105768632","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":[0.02528937,0.0003842018,0.96296674,0.0058144634,0.00035282562,0.004723327,0.0003471894,0.000060958606,0.000060907598],"genre_scores_gemma":[0.18205452,0.00009191077,0.8029771,0.0094282,0.0006415521,0.0008756803,0.0038023205,0.0000752354,0.000053495223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974228,0.0007680154,0.0008253289,0.00034141663,0.00041099553,0.00023145271],"domain_scores_gemma":[0.98069483,0.01800657,0.0007814912,0.0002969542,0.00019428408,0.000025869942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010877764,0.00034088234,0.0009486122,0.00020366881,0.0001325741,0.000019531008,0.0001035343,0.00018078536,0.000018182782],"category_scores_gemma":[0.0019445051,0.00023784324,0.00003045747,0.00014120349,0.00015554996,0.00006168625,0.000037915375,0.0005548222,1.0353288e-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":[0.0010546495,0.004808819,0.08587468,0.024750289,0.0039051115,0.00037986287,0.023584625,0.012282152,0.0012377454,0.04536187,0.30217376,0.49458644],"study_design_scores_gemma":[0.0149786165,0.016785337,0.10890929,0.01372209,0.0032113432,0.000023688348,0.003086333,0.5508689,0.0014174073,0.27462867,0.010790476,0.0015778415],"about_ca_topic_score_codex":0.000054585234,"about_ca_topic_score_gemma":0.000015864274,"teacher_disagreement_score":0.53858674,"about_ca_system_score_codex":0.00040386253,"about_ca_system_score_gemma":0.000042861626,"threshold_uncertainty_score":0.96989655},"labels":[],"label_agreement":null},{"id":"W3107334064","doi":"10.1515/ijb-2020-0073","title":"Doubly robust adaptive LASSO for effect modifier discovery","year":2022,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Counterfactual thinking; Lasso (programming language); Propensity score matching; Outcome (game theory); Observational study; Covariate; Marginal structural model; Set (abstract data type); Conditional expectation","score_opus":0.13319771240494277,"score_gpt":0.3993879005224699,"score_spread":0.26619018811752715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107334064","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":[0.02177048,0.000051889056,0.97455585,0.0012186297,0.0010136158,0.00030430182,0.00070450065,0.000026864374,0.0003538509],"genre_scores_gemma":[0.8545878,0.000019525894,0.14382292,0.00035554465,0.00036604912,0.000049529423,0.000017606351,0.0000338513,0.000747205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984675,0.000116592964,0.00044619027,0.00009463931,0.000730436,0.00014463472],"domain_scores_gemma":[0.99550855,0.003198523,0.0006496213,0.00014315463,0.0004643261,0.00003584484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010792502,0.0001260066,0.00021473592,0.00011127144,0.00013620203,0.00007160407,0.00077759934,0.000025002859,0.000060564573],"category_scores_gemma":[0.0011917577,0.00008586997,0.00012842425,0.00007201898,0.00007657733,0.0001947049,0.00020114117,0.0003354802,0.0000013991316],"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":[0.0020620837,0.00023763807,0.00011210992,0.000024104298,0.000605076,0.00012566669,0.00067867234,0.006260634,0.0032611047,0.8992999,0.078996636,0.008336353],"study_design_scores_gemma":[0.0011415072,0.0015186287,0.000062314975,0.000053425927,0.00013563187,0.00033361663,0.00037353337,0.0046208673,0.009064841,0.97609055,0.0064142263,0.00019088003],"about_ca_topic_score_codex":0.000007240218,"about_ca_topic_score_gemma":0.0000049798014,"teacher_disagreement_score":0.8328173,"about_ca_system_score_codex":0.0003011543,"about_ca_system_score_gemma":0.000101699305,"threshold_uncertainty_score":0.35016757},"labels":[],"label_agreement":null},{"id":"W3108260275","doi":"10.5539/ijsp.v10n1p40","title":"Causal Subclassification Tree Algorithm and Robust Causal Effect Estimation via Subclassification","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Estimator; Propensity score matching; Mathematics; Causal inference; Observational study; Consistency (knowledge bases); Confounding; Statistics; Econometrics; Weighting; Inverse probability weighting; Medicine; Discrete mathematics","score_opus":0.09041582394700515,"score_gpt":0.3658715823730794,"score_spread":0.2754557584260742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108260275","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":[0.036502387,0.00005323692,0.96125555,0.0015056911,0.00015725652,0.000270364,0.00012896355,0.000042661006,0.000083914114],"genre_scores_gemma":[0.5101847,0.00007611169,0.48950532,0.00005255989,0.00012044645,0.00000954815,0.000031902153,0.000013392206,0.000005995327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99828655,0.00015742512,0.00070561445,0.00023482324,0.00048652952,0.0001290803],"domain_scores_gemma":[0.9973392,0.00093790004,0.0006551919,0.00011814125,0.00078692316,0.00016264318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008010352,0.00017930241,0.0002997167,0.00008393561,0.00006269345,0.00010483455,0.00018612547,0.00009196761,0.00002701134],"category_scores_gemma":[0.001992574,0.00015506388,0.00003888928,0.00008730915,0.00017208046,0.00036445443,0.000059896127,0.00027987544,0.0000017642466],"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":[0.00046196772,0.0002462227,0.00692744,0.0003156698,0.00021626188,0.000054418928,0.0009930783,0.00023489397,0.005855576,0.19585271,0.0013811886,0.78746057],"study_design_scores_gemma":[0.000992648,0.0010005371,0.019432092,0.00008840407,0.00013184694,0.0001712207,0.000041588013,0.16069761,0.0035205858,0.8133952,0.00025054786,0.00027773535],"about_ca_topic_score_codex":0.000016913595,"about_ca_topic_score_gemma":0.000013235309,"teacher_disagreement_score":0.7871828,"about_ca_system_score_codex":0.0001352461,"about_ca_system_score_gemma":0.00008030563,"threshold_uncertainty_score":0.63233215},"labels":[],"label_agreement":null},{"id":"W3108536614","doi":"10.1093/ehjci/ehaa946.3551","title":"Effect of immortal time bias on the association between atrial fibrillation ablation and incident stroke: a meta-analysis","year":2020,"lang":"en","type":"article","venue":"European Heart Journal","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":"Montreal Heart Institute","funders":"","keywords":"Medicine; Observational study; Atrial fibrillation; Randomized controlled trial; Stroke (engine); Meta-analysis; Internal medicine; Cardiology; Catheter ablation; Ablation; Subgroup analysis; Cryoablation; Epidemiology; Surgery","score_opus":0.3201336256414198,"score_gpt":0.41296496097908386,"score_spread":0.09283133533766408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108536614","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":[0.9917344,0.00009465709,0.0055655837,0.0014578402,0.000020762012,0.0002987058,0.000028686429,0.000063010244,0.0007363632],"genre_scores_gemma":[0.9978221,0.000011406834,0.0014649966,0.000057984114,0.000510652,6.040575e-7,0.000005851214,0.000020922835,0.00010546155],"study_design_codex":"observational","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99665886,0.0020880024,0.00048073585,0.00014052406,0.00050311483,0.00012877086],"domain_scores_gemma":[0.99589515,0.003073299,0.00071150076,0.00013899883,0.000100519996,0.00008052971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043306737,0.0001402579,0.00058896776,0.00010619615,0.00011830757,0.00007960753,0.00009079065,0.00003902514,0.00017800428],"category_scores_gemma":[0.003331678,0.00008616262,0.00067230343,0.00025272355,0.00002013249,0.00015724049,0.000050363436,0.00029841036,0.000033268785],"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":[0.0009072416,0.000042518193,0.769813,0.00017006382,0.16977423,0.00005269659,0.004016767,0.0084872665,0.017980007,0.0033920654,0.016212402,0.009151709],"study_design_scores_gemma":[0.0036905718,0.012695052,0.4007419,0.00010715312,0.46619892,0.000092219634,0.00012905359,0.022446701,0.07286575,0.0132337,0.0061357794,0.0016631857],"about_ca_topic_score_codex":0.0000018765445,"about_ca_topic_score_gemma":6.9585167e-7,"teacher_disagreement_score":0.3690711,"about_ca_system_score_codex":0.000060568185,"about_ca_system_score_gemma":0.00001173403,"threshold_uncertainty_score":0.39885703},"labels":[],"label_agreement":null},{"id":"W3108711748","doi":"10.1038/s41366-020-00720-2","title":"Selection bias can creep into unselected cohorts and produce counterintuitive findings","year":2020,"lang":"en","type":"letter","venue":"International Journal of Obesity","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"","keywords":"Counterintuitive; Selection bias; Selection (genetic algorithm); Medicine; Demography; Internal medicine; Computer science; Physics; Pathology; Artificial intelligence","score_opus":0.08674983111192126,"score_gpt":0.36616000392843073,"score_spread":0.2794101728165095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108711748","genre_codex":"commentary","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":[0.33906752,0.00014026162,0.06610352,0.5901916,0.0022563988,0.0010304935,0.00019188249,0.0004337634,0.0005846014],"genre_scores_gemma":[0.73353195,0.0005068019,0.057820667,0.19763564,0.009295987,0.000035295343,0.00019718404,0.0002095168,0.0007669382],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975459,0.00015100998,0.00075724756,0.00033221312,0.0009943626,0.00021927842],"domain_scores_gemma":[0.99624854,0.00046924246,0.0010750243,0.00012651835,0.00199124,0.00008945431],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035766006,0.00033722576,0.0006133111,0.0003606994,0.000075657066,0.00014345747,0.00054636557,0.0003261135,0.00009099202],"category_scores_gemma":[0.0018383856,0.00031553817,0.0001432555,0.00016674137,0.00012411576,0.00031047725,0.00014174136,0.0020842408,0.0000040705945],"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":[0.00018621128,0.0001348142,0.0063772704,0.00022756257,0.00094721443,0.0018487835,0.001318645,0.0000017293439,0.003822333,0.0013014498,0.98222226,0.0016117197],"study_design_scores_gemma":[0.0012764109,0.0015929015,0.004813049,0.0023821879,0.00056579086,0.005105372,0.000114686096,0.00019170671,0.062730506,0.6658384,0.25391388,0.0014751141],"about_ca_topic_score_codex":0.0000758486,"about_ca_topic_score_gemma":0.00006584238,"teacher_disagreement_score":0.7283084,"about_ca_system_score_codex":0.0006713095,"about_ca_system_score_gemma":0.00024441667,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W3109567526","doi":"10.48550/arxiv.1907.13323","title":"Identifiability of causal effects with multiple causes and a binary outcome","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"University of Toronto","funders":"","keywords":"Confounding; Outcome (game theory); Causal inference; Identifiability; Econometrics; Observational study; Inference; Latent variable; Probit; Probit model; Instrumental variable; Causal model; Statistics; Computer science; Mathematics; Artificial intelligence","score_opus":0.17387976192086851,"score_gpt":0.2878945172744816,"score_spread":0.1140147553536131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109567526","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":[0.9106993,0.000029264867,0.08756695,0.0000074660375,0.00011058219,0.00096442486,0.000049977727,0.00027349335,0.0002985455],"genre_scores_gemma":[0.9938232,0.000047850495,0.005417163,0.00001076227,0.000014683645,0.000003977155,0.000011672501,0.000044491564,0.0006262057],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983255,0.00016642785,0.00031099154,0.0008097997,0.000110321766,0.0002769324],"domain_scores_gemma":[0.9967197,0.0013001118,0.00048019653,0.0011791541,0.0002128178,0.00010798045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029566753,0.0003922057,0.0007734859,0.00020979559,0.0000535677,0.000021657394,0.0004019014,0.00033139647,0.000018781908],"category_scores_gemma":[0.0004849093,0.0003727993,0.00012207688,0.0002184721,0.00035870535,0.00021836019,0.0010334038,0.0005574981,0.0000074926816],"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":[0.00039293282,0.00049167825,0.8916348,0.0074790777,0.00037822002,0.00043637666,0.0004329595,0.0077127074,0.002108945,0.08872321,0.00013066611,0.000078428144],"study_design_scores_gemma":[0.002762276,0.0010540459,0.08899066,0.0021157535,0.0012686047,0.000022152435,0.00047437692,0.021113658,0.019215794,0.86095583,0.000048973798,0.001977886],"about_ca_topic_score_codex":0.00024246353,"about_ca_topic_score_gemma":0.00018731257,"teacher_disagreement_score":0.80264413,"about_ca_system_score_codex":0.00016585407,"about_ca_system_score_gemma":0.00010076211,"threshold_uncertainty_score":0.9998724},"labels":[],"label_agreement":null},{"id":"W3109871844","doi":"10.1093/ehjci/ehaa946.3010","title":"REDUCE-IT: accumulation of data across prespecified interim analyses to final results","year":2020,"lang":"en","type":"article","venue":"European Heart Journal","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":"Université de Montréal; Montreal Heart Institute","funders":"Amarin Pharma; Amarin Corporation","keywords":"Medicine; Clinical endpoint; Interim analysis; Myocardial infarction; Internal medicine; Randomized controlled trial; Placebo","score_opus":0.9390778783731909,"score_gpt":0.6534559555338757,"score_spread":0.2856219228393152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109871844","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":[0.64888865,0.00010115927,0.3231817,0.013737952,0.00031832804,0.00061520754,0.00047218776,0.00044618262,0.012238667],"genre_scores_gemma":[0.84068817,0.000017496906,0.15797736,0.0005558746,0.00053782127,6.577918e-7,0.000014710519,0.000039617105,0.00016826513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978992,0.0003927893,0.000793965,0.0003144646,0.00034223567,0.0002573736],"domain_scores_gemma":[0.99827313,0.00026129064,0.000362327,0.00067115424,0.00019171298,0.00024039399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013891876,0.00015879361,0.00030410534,0.00006796172,0.00011002526,0.00010916941,0.00077399175,0.000029858391,0.00010926153],"category_scores_gemma":[0.0036369837,0.00013913603,0.00007527715,0.0002656025,0.000050949,0.0005599468,0.000646449,0.00040588688,0.00007217509],"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":[0.0020578892,0.00023933635,0.0004084834,0.00011082412,0.00014615941,0.00023823735,0.010999526,0.0005718147,0.278296,0.0007865125,0.68383574,0.022309506],"study_design_scores_gemma":[0.005847315,0.0054857917,0.046123177,0.0026965055,0.00029677883,0.0012193406,0.004772121,0.0064640096,0.2761006,0.020780599,0.6279903,0.0022234523],"about_ca_topic_score_codex":0.000002248852,"about_ca_topic_score_gemma":0.0000029401465,"teacher_disagreement_score":0.19179957,"about_ca_system_score_codex":0.000030498248,"about_ca_system_score_gemma":0.000041691725,"threshold_uncertainty_score":0.56738025},"labels":[],"label_agreement":null},{"id":"W3109899857","doi":"10.3390/jrfm13110290","title":"Propensity Score Weighting with Mismeasured Covariates: An Application to Two Financial Literacy Interventions","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Propensity score matching; Covariate; Estimator; Inverse probability weighting; Econometrics; Average treatment effect; Statistics; Weighting; Instrumental variable; Causal inference; Kernel density estimation; Kernel (algebra); Computer science; Mathematics; Medicine","score_opus":0.09952639413194576,"score_gpt":0.35829909527204684,"score_spread":0.2587727011401011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109899857","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":[0.25790885,0.00004225136,0.7412747,0.00020298225,0.000033153385,0.00040874447,0.0000062505583,0.000038621063,0.000084434425],"genre_scores_gemma":[0.7888183,0.00006580721,0.21064939,0.00022168412,0.00019661202,0.000021250486,0.0000016375918,0.0000137803845,0.000011574899],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885225,0.00006331732,0.0004956825,0.00019496675,0.00023780073,0.000155995],"domain_scores_gemma":[0.9988725,0.000043030384,0.000498998,0.00015433613,0.00027747566,0.00015362455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005149457,0.00014653178,0.00031093025,0.00011244743,0.0001360567,0.00007037484,0.0001865243,0.00003731459,0.0000057347675],"category_scores_gemma":[0.000404389,0.000114367576,0.00007678227,0.00027794376,0.000028333445,0.000365707,0.00009795491,0.00025115706,0.0000025199479],"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":[0.0012692668,0.0005916267,0.011585187,0.00069736957,0.00005657802,0.00016514966,0.0066482993,0.00022365329,0.00063367287,0.18339543,0.0010937556,0.79364],"study_design_scores_gemma":[0.0057346565,0.00742447,0.1730772,0.0039819083,0.0012212397,0.00011313956,0.00065039477,0.001228272,0.0030995016,0.76066,0.04138426,0.001424987],"about_ca_topic_score_codex":0.000013541049,"about_ca_topic_score_gemma":0.000048302165,"teacher_disagreement_score":0.792215,"about_ca_system_score_codex":0.000043596272,"about_ca_system_score_gemma":0.000035116926,"threshold_uncertainty_score":0.46637747},"labels":[],"label_agreement":null},{"id":"W3111500892","doi":"10.1002/cjs.11685","title":"Better experimental design by hybridizing binary matching with imbalance optimization","year":2022,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"United States-Israel Binational Science Foundation","keywords":"Covariate; Estimator; Matching (statistics); Extant taxon; Statistics; Robustness (evolution); Heuristic; Mathematics; Design of experiments; Mean squared error; Word error rate; Greedy algorithm; Binary number; Set (abstract data type); Computer science; Mathematical optimization; Algorithm; Artificial intelligence","score_opus":0.09052559107560555,"score_gpt":0.33924781787011926,"score_spread":0.24872222679451372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111500892","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":[0.006679718,0.0005207775,0.9909729,0.00012606496,0.00028120514,0.00032116703,0.00090185174,0.00003410828,0.00016223529],"genre_scores_gemma":[0.09648831,0.000052457777,0.9028972,0.00017847984,0.000086080785,0.00002679688,0.0000973523,0.00009595946,0.00007739621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982413,0.00016690529,0.00062998984,0.0002264328,0.00037474625,0.00036060173],"domain_scores_gemma":[0.99773115,0.00034852058,0.0010091135,0.00028797996,0.00024021657,0.00038303228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042360465,0.0003129158,0.00048365697,0.0002719871,0.00020983398,0.00013679992,0.00046098672,0.000109485125,0.0005810488],"category_scores_gemma":[0.00018026358,0.00031148235,0.000051568757,0.00009609519,0.000114033384,0.00016456525,0.00009388663,0.0011195252,8.5548396e-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":[0.0002458019,0.0002423386,0.001401707,0.00080185354,0.00068652956,0.007575378,0.0070598954,0.5833892,0.002329923,0.030925404,0.36329198,0.0020499846],"study_design_scores_gemma":[0.0021328703,0.0035636323,0.00012475299,0.0037829916,0.0007906364,0.0019492988,0.0053493264,0.042941775,0.017135069,0.91293675,0.005426009,0.0038669088],"about_ca_topic_score_codex":0.00069978856,"about_ca_topic_score_gemma":0.00026571285,"teacher_disagreement_score":0.88201135,"about_ca_system_score_codex":0.0010236992,"about_ca_system_score_gemma":0.0015415103,"threshold_uncertainty_score":0.9999337},"labels":[],"label_agreement":null},{"id":"W3112629828","doi":"10.48550/arxiv.2012.05849","title":"The Promises of Parallel Outcomes","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"University of Toronto","funders":"","keywords":"Causal inference; Identifiability; Conditional independence; Observational study; Identification (biology); Key (lock); Computer science; Nonparametric statistics; Inference; Confounding; Set (abstract data type); Contrast (vision); Causal model; Independence (probability theory); Parametric statistics; Econometrics; Machine learning; Instrumental variable; Outcome (game theory); Artificial intelligence; Mathematics; Statistics","score_opus":0.3713705675728355,"score_gpt":0.3073641142223964,"score_spread":0.06400645335043909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112629828","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":[0.30534038,0.000118591575,0.6734003,0.0010580511,0.00035492113,0.0020300762,0.00009132801,0.0013066054,0.016299743],"genre_scores_gemma":[0.98804855,0.00029523278,0.009736638,0.000036989444,0.000024494933,0.0000039591914,0.000005400656,0.000032749485,0.0018159907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881124,0.00010400087,0.0002926754,0.00046655722,0.000092558475,0.00023295797],"domain_scores_gemma":[0.9975054,0.00081318966,0.00049140287,0.0009431947,0.00015929161,0.00008747384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018864045,0.00028374852,0.00049179577,0.000061312676,0.00010444453,0.000024407089,0.0009976544,0.00021779315,0.000029824861],"category_scores_gemma":[0.00061028154,0.00022373218,0.00025700312,0.00017648106,0.00025982308,0.00008915349,0.0010960845,0.0005394757,0.000015922677],"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":[0.000058299614,0.000064167725,0.0031537004,0.00020884797,0.00017236089,0.000046782116,0.00014518923,0.0012345868,0.00006506952,0.99359274,0.0010968591,0.00016141035],"study_design_scores_gemma":[0.00019069987,0.000045504425,0.0004781318,0.0000842162,0.00012139684,5.9965777e-7,0.00016086789,0.0022597432,0.0006920487,0.9952434,0.0004774142,0.00024602446],"about_ca_topic_score_codex":0.00003304458,"about_ca_topic_score_gemma":0.000037222395,"teacher_disagreement_score":0.68270814,"about_ca_system_score_codex":0.00009230528,"about_ca_system_score_gemma":0.00012201217,"threshold_uncertainty_score":0.91235334},"labels":[],"label_agreement":null},{"id":"W3112964578","doi":"10.1161/circulationaha.120.051718","title":"Emulating Randomized Clinical Trials With Nonrandomized Real-World Evidence Studies","year":2020,"lang":"en","type":"article","venue":"Circulation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":297,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; McGill University; National Institute on Aging; Harvard University; Vanderbilt University","keywords":"Medicine; Randomized controlled trial; Confounding; Propensity score matching; Hazard ratio; Placebo; Clinical trial; Clinical endpoint; Research design; Proxy (statistics); Clinical study design; Confidence interval; Internal medicine; Statistics; Alternative medicine","score_opus":0.7113316494914241,"score_gpt":0.5902829400891217,"score_spread":0.12104870940230239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112964578","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":[0.18875723,0.00043876705,0.80321294,0.0015744768,0.00013876571,0.0037472218,0.0000022720756,0.0009689491,0.0011593968],"genre_scores_gemma":[0.91831976,0.00033349328,0.08049316,0.00024559748,0.00033133358,0.00021172903,0.0000047672415,0.000035582496,0.000024550945],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928052,0.0041055605,0.0020685494,0.00042593206,0.00038504452,0.0002097231],"domain_scores_gemma":[0.9411392,0.056490555,0.0014655791,0.00035646715,0.00041796343,0.00013021601],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016517034,0.00024076641,0.002409896,0.000078109144,0.000104761195,0.000045428256,0.0001399689,0.000095165866,0.00005584178],"category_scores_gemma":[0.13342273,0.00016462558,0.00036092068,0.00035785197,0.0002093599,0.00040823294,0.00005641139,0.0002609153,0.000014027586],"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":[0.5219453,0.00042913537,0.0552037,0.0017941624,0.003973176,0.000081361984,0.01334133,0.0036916528,0.011373356,0.33561465,0.0028478503,0.049704347],"study_design_scores_gemma":[0.35259256,0.00023324013,0.0020317172,0.0022567513,0.001954118,0.0000055293162,0.00060937565,0.0691371,0.0024575184,0.56770736,0.000065763146,0.0009489591],"about_ca_topic_score_codex":0.000012313304,"about_ca_topic_score_gemma":0.000020307993,"teacher_disagreement_score":0.7295626,"about_ca_system_score_codex":0.000077466786,"about_ca_system_score_gemma":0.00006774776,"threshold_uncertainty_score":0.8738768},"labels":[],"label_agreement":null},{"id":"W3114661150","doi":"10.1515/em-2019-0037","title":"Population attributable fractions for continuously distributed exposures","year":2020,"lang":"en","type":"article","venue":"Epidemiologic Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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; Population Health Research Institute","funders":"Health Research Board","keywords":"Econometrics; Inference; Categorical variable; Categorization; Population; Statistics; Estimator; Risk factor; Causal inference; Attributable risk; Computer science; Mathematics; Medicine; Environmental health; Artificial intelligence","score_opus":0.580190986490552,"score_gpt":0.5732593142264173,"score_spread":0.006931672264134714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114661150","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":[0.0035757597,0.00013322457,0.9907415,0.0032595606,0.00012308719,0.000757509,0.00013041405,0.000955149,0.00032382313],"genre_scores_gemma":[0.06480539,0.000023613726,0.93319756,0.0011437569,0.00019337176,0.00031973384,0.00020160028,0.000024828383,0.00009016617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99704254,0.0013135959,0.00075573515,0.00040834324,0.00008982687,0.00038998408],"domain_scores_gemma":[0.97982913,0.019085703,0.00046676464,0.0003127914,0.00015766677,0.0001479622],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004073746,0.00022048235,0.0008576443,0.000035424175,0.00016793184,0.000017202598,0.00022038132,0.00023650992,0.00014778858],"category_scores_gemma":[0.12413347,0.00017827054,0.00018471724,0.00023163826,0.000053092615,0.00017363137,0.00007328109,0.0002735491,0.0000071176323],"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":[0.0001754007,0.00014021617,0.026580198,0.00025243897,0.00013267646,0.000004261432,0.00023120035,0.0005563642,0.021393796,0.77494466,0.124423385,0.05116542],"study_design_scores_gemma":[0.00020171866,0.0002379122,0.0025241245,0.000017609958,0.00004977602,0.0000031211373,0.000073227144,0.0056476095,0.008214749,0.95840526,0.024394514,0.00023040915],"about_ca_topic_score_codex":0.00003337165,"about_ca_topic_score_gemma":0.0000031402349,"teacher_disagreement_score":0.1834606,"about_ca_system_score_codex":0.000072014634,"about_ca_system_score_gemma":0.000016918797,"threshold_uncertainty_score":0.88324434},"labels":[],"label_agreement":null},{"id":"W3115153714","doi":"10.1093/ije/dyaa251","title":"Analytical approaches to minimizing immeasurable time bias in cohort studies","year":2020,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"McGill University","keywords":"Medicine; Hazard ratio; Medical prescription; Pharmacoepidemiology; Confidence interval; Proportional hazards model; Cohort study; Gold standard (test); Emergency medicine; Statistics; Internal medicine; Pharmacology; Mathematics","score_opus":0.8518547459120639,"score_gpt":0.5325737713499968,"score_spread":0.31928097456206705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115153714","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":[0.6593816,0.001467734,0.1945508,0.13904475,0.0006768689,0.0005108484,0.000017252674,0.00012123118,0.0042288727],"genre_scores_gemma":[0.75213385,0.00021605904,0.24262485,0.0043663266,0.00051866856,0.0000144013975,0.0000023702535,0.000024415865,0.000099051096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975421,0.00047223546,0.0012927029,0.00020152204,0.00025193047,0.00023949715],"domain_scores_gemma":[0.9923587,0.0064420737,0.000565686,0.00010560081,0.00037154334,0.00015639926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038466803,0.00014459448,0.00080909656,0.00023737893,0.000014557287,0.000007594787,0.00048656896,0.00008945711,0.00007452814],"category_scores_gemma":[0.06132718,0.00011431817,0.00013818844,0.000154032,0.000099856574,0.00016800949,0.00014457999,0.0003668225,0.000031751413],"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":[0.001242866,0.00043980786,0.37534538,0.000087720444,0.0031760575,0.00070530747,0.0032445116,0.0053710323,0.0019108802,0.50602686,0.08531089,0.017138701],"study_design_scores_gemma":[0.0009369474,0.00080828194,0.008460503,0.0004797681,0.00012590644,0.00038317192,0.000791996,0.011536859,0.001927707,0.9660853,0.008024616,0.00043890715],"about_ca_topic_score_codex":0.0000055036135,"about_ca_topic_score_gemma":0.000003863196,"teacher_disagreement_score":0.46005848,"about_ca_system_score_codex":0.00020942597,"about_ca_system_score_gemma":0.000057561774,"threshold_uncertainty_score":0.94657964},"labels":[],"label_agreement":null},{"id":"W3115405644","doi":"10.1515/ijb-2021-0072","title":"Increasing the efficiency of randomized trial estimates via linear adjustment for a prognostic score","year":2021,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":36,"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":"Covariate; Estimator; Statistics; Econometrics; Variance (accounting); Sample size determination; Mathematics; Standard error; Delta method","score_opus":0.09452364034429618,"score_gpt":0.4134439329947414,"score_spread":0.31892029265044525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115405644","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":[0.09994035,0.0003285107,0.89702654,0.0010867554,0.0006680227,0.0008003379,0.00008058122,0.000015503056,0.000053393185],"genre_scores_gemma":[0.5988559,0.00013716253,0.4003884,0.00013109579,0.00039675354,0.000033558084,0.000011218728,0.0000190744,0.000026832944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979863,0.0002136799,0.0009810514,0.00008429911,0.000608883,0.00012579677],"domain_scores_gemma":[0.9811956,0.015570685,0.0011922912,0.00016289401,0.0018456433,0.000032863503],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022759861,0.00012570345,0.00045732042,0.0000693415,0.00006231118,0.000037955055,0.0005165164,0.000038979786,0.00002817915],"category_scores_gemma":[0.0287474,0.0000659788,0.00021631332,0.00009180122,0.00025007632,0.000063231855,0.00009386146,0.00017730088,7.111441e-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":[0.40309605,0.0014019522,0.00011256617,0.00020834625,0.0020984015,0.000119818884,0.002251828,0.0004126198,0.01938669,0.548324,0.002418753,0.020169003],"study_design_scores_gemma":[0.116809525,0.0004223969,0.000020693162,0.00043175468,0.00056804676,0.0004413144,0.00020473098,0.012154571,0.042473402,0.8262741,0.00008211527,0.00011734062],"about_ca_topic_score_codex":0.000010571966,"about_ca_topic_score_gemma":0.000004981918,"teacher_disagreement_score":0.49891555,"about_ca_system_score_codex":0.00006847544,"about_ca_system_score_gemma":0.00022745368,"threshold_uncertainty_score":0.9794339},"labels":[],"label_agreement":null},{"id":"W3116999980","doi":"10.47004/wp.cem.2021.1921","title":"Discordant relaxations of misspecified models","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Mathematics; Econometrics; Environmental science; Statistics","score_opus":0.39898016621774574,"score_gpt":0.4477138834706251,"score_spread":0.04873371725287934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116999980","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":[0.015126373,0.000077083365,0.91009426,0.00014439411,0.000105351544,0.00038562508,0.000028686618,0.0003821454,0.073656105],"genre_scores_gemma":[0.41997206,0.00014494479,0.57787156,0.000017927065,0.000025448202,0.00007920047,0.00004081541,0.00003442579,0.0018136394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985638,0.00005868972,0.0006007494,0.00035244485,0.00026116252,0.00016313627],"domain_scores_gemma":[0.99781835,0.0003165822,0.0004328628,0.0010852022,0.0002933667,0.000053656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017921085,0.00023209471,0.00052554766,0.000094027244,0.000025687432,0.000030406276,0.00033237739,0.00017875897,0.0004280988],"category_scores_gemma":[0.00037483318,0.00020501121,0.00018214337,0.00010022798,0.00007112935,0.00011995434,0.0007412564,0.00048125646,0.000002357621],"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":[0.000004818114,0.00014146618,0.000005418162,0.00029683905,0.00005283106,0.000009371414,0.00042480315,0.0006102159,0.0023354723,0.9943565,0.0012381122,0.00052415626],"study_design_scores_gemma":[0.000049450875,0.000013207286,0.000009926519,0.00031378918,0.000043271662,0.0000036974106,0.00036270803,0.0027902848,0.03583935,0.9603242,0.000035596724,0.00021451262],"about_ca_topic_score_codex":0.0000629632,"about_ca_topic_score_gemma":0.000082221806,"teacher_disagreement_score":0.40484568,"about_ca_system_score_codex":0.000072554205,"about_ca_system_score_gemma":0.00013329525,"threshold_uncertainty_score":0.83601147},"labels":[],"label_agreement":null},{"id":"W3119329857","doi":"10.1002/cjs.11586","title":"An approximate Bayesian inference on propensity score estimation under unit nonresponse","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Frequentist inference; Statistics; Propensity score matching; Bayesian probability; Econometrics; Mathematics; Weighting; Statistical inference; Bayesian inference; Computer science","score_opus":0.23824473122960516,"score_gpt":0.3957939407962062,"score_spread":0.15754920956660107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119329857","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":[0.07165887,0.000016708429,0.9272951,0.00019368115,0.00011389647,0.00012864145,0.00021839282,0.000026729069,0.00034800204],"genre_scores_gemma":[0.6411561,0.00000878019,0.3584374,0.00021322817,0.00003437369,0.000002074994,0.000023390729,0.000025957374,0.00009874315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985278,0.00022849048,0.0004933917,0.0001605454,0.00027485038,0.00031487987],"domain_scores_gemma":[0.9969716,0.0006386766,0.00037647007,0.00037188554,0.0009996609,0.0006416854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053195533,0.00018396213,0.0003213195,0.00023548769,0.00015885274,0.00013593127,0.00024346625,0.000100355195,0.00025480054],"category_scores_gemma":[0.003307865,0.00017542376,0.000035037723,0.00023676941,0.00013835629,0.00029633933,0.00001321952,0.0004292654,0.0000067849805],"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":[0.000099940145,0.00013230975,0.0028268446,0.00013468985,0.00005776259,0.002444037,0.0008742507,0.0024386388,0.001011704,0.97000194,0.0026865858,0.017291328],"study_design_scores_gemma":[0.00032095017,0.00054889696,0.005644633,0.00038630998,0.00006943696,0.00033993184,0.00026515644,0.008151529,0.005446032,0.97827184,0.00022891784,0.0003263675],"about_ca_topic_score_codex":0.00025259927,"about_ca_topic_score_gemma":0.012834179,"teacher_disagreement_score":0.56949717,"about_ca_system_score_codex":0.0002465713,"about_ca_system_score_gemma":0.0026619958,"threshold_uncertainty_score":0.7161773},"labels":[],"label_agreement":null},{"id":"W3121695905","doi":"10.1162/rest_a_00622","title":"Testing Local Average Treatment Effect Assumptions","year":2016,"lang":"en","type":"preprint","venue":"The Review of Economics and Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Toronto","funders":"","keywords":"Intersection (aeronautics); Sign (mathematics); Instrumental variable; Econometrics; Monotonic function; Set (abstract data type); Identification (biology); Computer science; Algorithm; Mathematics; Engineering; Programming language","score_opus":0.15950357126852724,"score_gpt":0.4066505584022922,"score_spread":0.24714698713376496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121695905","genre_codex":"methods","genre_gemma":"review","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":[0.0036221966,0.031407796,0.95425236,0.00038516184,0.00020400362,0.0023324213,0.00419786,0.00009203211,0.0035061683],"genre_scores_gemma":[0.018085046,0.69312036,0.2878047,0.00013917168,0.00013275298,0.00032172183,0.000106478015,0.000077401244,0.0002123524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99879247,0.00013557826,0.0006312415,0.00023843757,0.000042002473,0.00016028507],"domain_scores_gemma":[0.9949546,0.0036368764,0.0006689986,0.0005997132,0.00008723063,0.000052571304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006491777,0.0002929005,0.00088828267,0.000030077781,0.00006367733,0.000020784333,0.00019862867,0.00009297429,0.000044839995],"category_scores_gemma":[0.0007749055,0.00016168212,0.00009353045,0.00002076337,0.00018465696,0.000024142699,0.00026303777,0.00017069606,0.000006829842],"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":[0.0000050379167,0.00003426981,0.000030292766,0.011408275,0.00014077057,0.0000021255307,0.000034592304,0.00003562591,0.0000043608106,0.5802298,0.0008837388,0.4071911],"study_design_scores_gemma":[0.00012744503,0.00022621136,0.000035951667,0.009601934,0.00035125713,0.000011031438,0.000002251905,0.0021177984,0.00012339937,0.98377144,0.0034067926,0.0002245093],"about_ca_topic_score_codex":0.00002204051,"about_ca_topic_score_gemma":0.00001649686,"teacher_disagreement_score":0.6664477,"about_ca_system_score_codex":0.00016393789,"about_ca_system_score_gemma":0.00009767157,"threshold_uncertainty_score":0.65932053},"labels":[],"label_agreement":null},{"id":"W3122218197","doi":"10.1287/ijds.2022.0020","title":"A Robust Approach to Quantifying Uncertainty in Matching Problems of Causal Inference","year":2022,"lang":"en","type":"article","venue":"INFORMS Journal on Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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":"Causal inference; Matching (statistics); Test statistic; Inference; Computer science; Set (abstract data type); Statistical hypothesis testing; Observational study; Type I and type II errors; Randomized experiment; Statistic; Econometrics; Statistics; Mathematics; Artificial intelligence","score_opus":0.4344220118695823,"score_gpt":0.4456203986695917,"score_spread":0.011198386800009397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122218197","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":[0.59824234,0.000023584284,0.3928928,0.00023044764,0.00029718285,0.0009049328,0.00018260039,0.00014077833,0.007085337],"genre_scores_gemma":[0.8683658,0.000017807113,0.13134499,0.0001755557,0.0000195376,0.00003402122,0.000011551531,0.000013459092,0.000017256645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966374,0.000057856792,0.0008772772,0.00040939293,0.0014594245,0.0005586418],"domain_scores_gemma":[0.9976383,0.00036685963,0.00055751315,0.0010635987,0.00017999312,0.00019377413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062496318,0.0001924473,0.00034024537,0.00081529224,0.00047769933,0.0001794319,0.0034766742,0.00003424225,0.000043004282],"category_scores_gemma":[0.0024385382,0.00015208863,0.00003316983,0.0019960848,0.00024403188,0.002867439,0.0022580246,0.0010161808,0.0000037701254],"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":[0.00012542265,0.0006349168,0.0019114565,0.00018946127,0.000015508665,0.00003460755,0.0076901913,0.62015754,0.008990341,0.34549147,0.0006431052,0.01411599],"study_design_scores_gemma":[0.002181892,0.0030068124,0.0034945884,0.0021497938,0.0000429577,0.0015960392,0.019375097,0.22462338,0.0043482534,0.7307053,0.0060995235,0.0023763487],"about_ca_topic_score_codex":0.00013383834,"about_ca_topic_score_gemma":0.00005680242,"teacher_disagreement_score":0.39553416,"about_ca_system_score_codex":0.0004444171,"about_ca_system_score_gemma":0.0006210079,"threshold_uncertainty_score":0.6460584},"labels":[],"label_agreement":null},{"id":"W3122538678","doi":"10.1108/s0731-905320170000038019?utm_campaign=repec&amp;wt.mc_id=repec","title":"The Devil is in the Tails: Regression Discontinuity Design with Measurement Error in the Assignment Variable","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Regression discontinuity design; Covariate; Discontinuity (linguistics); Variable (mathematics); Identification (biology); Observational error; Instrumental variable; Econometrics; Omitted-variable bias; Statistics; Mathematics; Regression; Computer science","score_opus":0.18305358370719607,"score_gpt":0.37218072425919335,"score_spread":0.18912714055199728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122538678","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":[0.015853189,0.0012782005,0.96839446,0.012334313,0.00004310499,0.0011114806,0.000001305651,0.000042071442,0.0009418854],"genre_scores_gemma":[0.99437237,0.0012034797,0.0036364503,0.00022991565,0.000065890046,0.0001725207,1.344776e-7,0.000024731264,0.000294494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99559575,0.0011395991,0.00044855903,0.00020837595,0.0010054337,0.0016022641],"domain_scores_gemma":[0.99795324,0.0010412338,0.00033484632,0.0005276076,0.00011169916,0.00003136377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01770767,0.00022554575,0.00021117095,0.000055413584,0.00033022996,0.000109133674,0.00093295606,0.00007060995,0.00001802512],"category_scores_gemma":[0.00065271696,0.00006832511,0.000053825996,0.0002657821,0.00010826834,0.00025766055,0.0000461497,0.0014719344,0.0000040572772],"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":[0.00043107482,0.0004620167,0.0015605743,0.000014759995,0.00013314847,0.000018214543,0.003938394,0.000019056653,0.004661959,0.9264897,0.0032810958,0.058989987],"study_design_scores_gemma":[0.00059819355,0.00045738876,0.00018771148,0.0004012126,0.00003071539,0.00015588514,0.0046995096,0.00002354568,0.0015739045,0.9903753,0.0013477174,0.00014892752],"about_ca_topic_score_codex":0.000030252635,"about_ca_topic_score_gemma":0.0022438422,"teacher_disagreement_score":0.9785192,"about_ca_system_score_codex":0.0016993323,"about_ca_system_score_gemma":0.0011424165,"threshold_uncertainty_score":0.6394904},"labels":[],"label_agreement":null},{"id":"W3122958054","doi":"10.1016/j.jeconom.2007.05.001","title":"Regression discontinuity designs: A guide to practice","year":2007,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3773,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Regression discontinuity design; Covariate; Econometrics; Discontinuity (linguistics); Regression; Value (mathematics); Regression analysis; Statistics; Mathematics; Computer science; Economics; Psychology","score_opus":0.4194458121712126,"score_gpt":0.48015923405399336,"score_spread":0.06071342188278078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122958054","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":[0.035251174,0.00023266269,0.949561,0.00060577574,0.00033232145,0.00018097178,0.000002401257,0.00004383642,0.013789834],"genre_scores_gemma":[0.1464581,0.00013660292,0.85187066,0.0004220831,0.00026081048,0.0000018236792,2.476488e-7,0.00002596804,0.0008237192],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981894,0.00005674998,0.0010617647,0.00013188236,0.0002849409,0.00027524572],"domain_scores_gemma":[0.9940033,0.00352545,0.0013073492,0.00027799324,0.00063392654,0.00025198382],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005315716,0.00014296535,0.00038051492,0.0011764161,0.000048940994,0.000054958382,0.00034422457,0.00009493118,0.000070267626],"category_scores_gemma":[0.03189541,0.00011099154,0.00011806193,0.0010993336,0.000025361882,0.0008873572,0.000089570145,0.00033795973,0.000016686521],"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":[0.0011726065,0.0019706187,0.007994942,0.00019080627,0.00036357273,0.0010977595,0.0026997658,0.00008320905,0.009012998,0.21185566,0.2899019,0.47365612],"study_design_scores_gemma":[0.0011283422,0.0022055204,0.0023142474,0.0005276523,0.00019860931,0.00096123293,0.0025538902,0.000029204566,0.04869323,0.37535125,0.565304,0.00073287945],"about_ca_topic_score_codex":0.0000034546229,"about_ca_topic_score_gemma":0.0000086607615,"teacher_disagreement_score":0.47292325,"about_ca_system_score_codex":0.00037044246,"about_ca_system_score_gemma":0.000076562115,"threshold_uncertainty_score":0.97625935},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3123542241","doi":"10.1017/bpp.2020.24","title":"Successfully scaled solutions need not be homogenous","year":2020,"lang":"en","type":"article","venue":"Behavioural Public Policy","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Scalability; Temptation; Context (archaeology); Computer science; Psychological intervention; Relevance (law); Intervention (counseling); Open research; Risk analysis (engineering); Data science; Process management; Psychology; Business; Medicine; Political science; World Wide Web; Social psychology; Nursing","score_opus":0.41364885089965364,"score_gpt":0.4161054610316193,"score_spread":0.002456610131965631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123542241","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":[0.6225834,0.00007796484,0.041459378,0.3166929,0.00015947016,0.0015232026,0.00054288976,0.005422304,0.011538494],"genre_scores_gemma":[0.97399545,0.000010970583,0.019293511,0.0054982523,0.00034813583,0.00012813733,0.000049923296,0.00007437817,0.0006012487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975873,0.00010126305,0.0005255329,0.0003968822,0.00045343256,0.000935556],"domain_scores_gemma":[0.99823636,0.00016732067,0.00021656096,0.0005487091,0.00024120405,0.000589857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024514986,0.00033082732,0.00042149745,0.00025038523,0.00031676062,0.00018832172,0.0007181288,0.00020114973,0.0003883929],"category_scores_gemma":[0.0019230943,0.0003175485,0.00018899278,0.00073340716,0.0002214725,0.00068395986,0.00037491648,0.00042949332,0.00007770346],"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":[0.000024461056,0.00030256284,0.0033691938,0.000042453594,0.000037401995,0.00003748325,0.0011477773,9.3031923e-7,0.01049338,0.94679546,0.030700149,0.007048717],"study_design_scores_gemma":[0.004559561,0.0017356698,0.02046967,0.00012955278,0.0005249027,0.00041564918,0.0012573428,0.001010971,0.048740555,0.8401229,0.07656379,0.004469456],"about_ca_topic_score_codex":0.0016481467,"about_ca_topic_score_gemma":0.00016553402,"teacher_disagreement_score":0.35141206,"about_ca_system_score_codex":0.00024589675,"about_ca_system_score_gemma":0.0004195747,"threshold_uncertainty_score":0.99992764},"labels":[],"label_agreement":null},{"id":"W3123549106","doi":"10.1097/ede.0000000000001315","title":"Incremental Propensity Score Effects for Time-fixed Exposures","year":2021,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Waterloo","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; University of California, Irvine; Northwestern University; University of Pittsburgh; University of Pennsylvania; National Institutes of Health; RTI International; Case Western Reserve University; National Science Foundation","keywords":"Propensity score matching; Causal inference; Medicine; Preeclampsia; Average treatment effect; Statistics; Odds ratio; Consistency (knowledge bases); Psychological intervention; Econometrics; Pregnancy; Demography; Mathematics; Internal medicine","score_opus":0.35652440237283917,"score_gpt":0.45002139779034983,"score_spread":0.09349699541751066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123549106","genre_codex":"empirical","genre_gemma":"methods","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":[0.68642807,0.00038307035,0.30719388,0.0014861984,0.0002740105,0.00137329,0.000021288215,0.00063773786,0.0022024657],"genre_scores_gemma":[0.41629803,0.00003164551,0.5783775,0.0028419632,0.0002952404,0.00048601493,0.00007553243,0.000059949263,0.0015341352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980741,0.0006467022,0.00044544987,0.00037175533,0.00006282803,0.00039913505],"domain_scores_gemma":[0.99062556,0.008549745,0.00019878506,0.00040854808,0.00014070846,0.000076645956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001497466,0.00017828793,0.00068934815,0.00003648232,0.00009031044,0.0000048846805,0.00015382255,0.00018146375,0.00012955959],"category_scores_gemma":[0.025046393,0.00015210695,0.00012073083,0.000077363205,0.00011325697,0.00008074859,0.00016085645,0.0001759177,0.00004612522],"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":[0.00015482477,0.0003000477,0.045098152,0.00062536664,0.00017936378,0.00008603344,0.0001695759,0.0000061355418,0.22543329,0.5773771,0.1384866,0.012083525],"study_design_scores_gemma":[0.00034670802,0.00027390587,0.0042550806,0.00007365928,0.000034395795,0.000040388662,0.000009267466,0.00010576579,0.19937539,0.79343873,0.0018501563,0.00019652947],"about_ca_topic_score_codex":0.000009434072,"about_ca_topic_score_gemma":0.00002229483,"teacher_disagreement_score":0.2711836,"about_ca_system_score_codex":0.000070985356,"about_ca_system_score_gemma":0.00005679544,"threshold_uncertainty_score":0.98316604},"labels":[],"label_agreement":null},{"id":"W3124305122","doi":"10.1002/mde.3496","title":"Test Sensitivity for Infection versus Infectiousness of SARS-CoV-2","year":2020,"lang":"en","type":"article","venue":"Managerial and Decision Economics","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":"University of Toronto","funders":"","keywords":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); False positive paradox; Test (biology); Coronavirus disease 2019 (COVID-19); Medicine; 2019-20 coronavirus outbreak; Virology; Statistics; Infectious disease (medical specialty); Biology; Internal medicine; Outbreak; Mathematics","score_opus":0.1855592832765327,"score_gpt":0.3868124033624004,"score_spread":0.2012531200858677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124305122","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":[0.6877411,0.0000026619293,0.31115413,0.00006502115,0.00022810239,0.00024394804,0.000025014553,0.00009209828,0.00044795492],"genre_scores_gemma":[0.9640612,0.00007640179,0.035536785,0.000121101155,0.00015963291,0.00001748267,0.0000041140856,0.00002016981,0.000003131612],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993213,0.000014389199,0.00030087397,0.00021834848,0.00003516857,0.000109932895],"domain_scores_gemma":[0.9977701,0.0018096826,0.0001770196,0.00014703382,0.000059668277,0.000036527716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024498298,0.000119819546,0.00029725002,0.00005327588,0.0000533115,0.000033720407,0.000043054504,0.00008536298,0.000004258722],"category_scores_gemma":[0.0016202705,0.00012051616,0.000066059045,0.00006820365,0.000050300274,0.00019525456,0.000099520774,0.000056842582,0.000003994048],"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":[0.004971766,0.00038972902,0.0022422732,0.0005726946,0.00015866492,0.000009197355,0.00054081,0.00044597246,0.07951605,0.36658102,0.0065502757,0.5380215],"study_design_scores_gemma":[0.0023665985,0.0008576111,0.00048879744,0.000030837655,0.00005959337,0.00000501961,0.00003509113,0.01209365,0.14161842,0.83453584,0.007577497,0.00033104673],"about_ca_topic_score_codex":0.000025601561,"about_ca_topic_score_gemma":0.00013720158,"teacher_disagreement_score":0.53769046,"about_ca_system_score_codex":0.000029071003,"about_ca_system_score_gemma":0.000013553076,"threshold_uncertainty_score":0.49145064},"labels":[],"label_agreement":null},{"id":"W3124523117","doi":"","title":"A Simple, Graphical Approach to Comparing Multiple Treatments","year":2017,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","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":"Carleton University; Toronto Metropolitan University","funders":"","keywords":"Spurious relationship; Graphical model; Resampling; Simple (philosophy); Computer science; Algorithm; Multiple comparisons problem; Zero (linguistics); Jackknife resampling; Mathematics; Machine learning; Statistics","score_opus":0.2667984675321099,"score_gpt":0.4595448809158001,"score_spread":0.1927464133836902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124523117","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":[0.70299464,0.00004112722,0.0019699493,0.00012930296,0.00019777527,0.004069792,0.000121978985,0.00046735586,0.29000804],"genre_scores_gemma":[0.93786955,0.0009171535,0.05840216,0.0000312227,0.0001380336,0.0015732655,0.00008785433,0.0001312658,0.00084951194],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961196,0.00026641082,0.000805551,0.0013186265,0.00038225405,0.0011075137],"domain_scores_gemma":[0.9952915,0.0011370047,0.0003228804,0.0027051787,0.00015597668,0.00038748537],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016770102,0.0005223294,0.0011308868,0.00071124115,0.00030282553,0.0002717705,0.0016679493,0.0006331109,0.000016520118],"category_scores_gemma":[0.0029379919,0.0005415934,0.00024802133,0.0001040878,0.0003576084,0.00014413212,0.0030558247,0.00223363,0.000012316743],"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":[0.0014575527,0.008447743,0.30383328,0.0036490555,0.0021323212,0.00034847506,0.0052412525,0.019298038,0.0016970838,0.13888295,0.0025171598,0.5124951],"study_design_scores_gemma":[0.002094463,0.00036804887,0.015938058,0.0009856434,0.00006353534,0.000027262817,0.0007078615,0.048501622,0.0015753155,0.92029625,0.00738339,0.0020585358],"about_ca_topic_score_codex":0.00016938962,"about_ca_topic_score_gemma":0.00044773964,"teacher_disagreement_score":0.7814133,"about_ca_system_score_codex":0.001294954,"about_ca_system_score_gemma":0.00027867628,"threshold_uncertainty_score":0.9997036},"labels":[],"label_agreement":null},{"id":"W3124873071","doi":"10.1002/jae.2583","title":"Difference‐in‐differences when the treatment status is observed in only one period","year":2017,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Advanced Causal Inference Techniques","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":"Simon Fraser University","funders":"","keywords":"Proxy (statistics); Conditional cash transfer; Estimator; Econometrics; Propensity score matching; Average treatment effect; Treatment effect; Difference in differences; Statistics; Time point; Instrumental variable; Mathematics; Economics; Medicine","score_opus":0.31502552485901403,"score_gpt":0.37108907204825997,"score_spread":0.056063547189245944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124873071","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":[0.99149835,0.00023197242,0.001086826,0.00063026586,0.000114951334,0.0003859808,0.00001679034,0.000018852357,0.006016025],"genre_scores_gemma":[0.98054296,0.00190098,0.017144129,0.00007591495,0.00008819641,0.000030266254,8.513649e-7,0.00002406955,0.00019265097],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99803525,0.00003151733,0.0009868237,0.00023473451,0.00027259582,0.0004391016],"domain_scores_gemma":[0.9969804,0.0006873581,0.0014068777,0.000706993,0.000088748355,0.00012960844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068107946,0.00026219018,0.0007933672,0.00071117235,0.0001414366,0.00025788834,0.0008686096,0.00013955311,0.00019276961],"category_scores_gemma":[0.00048341905,0.00017608044,0.00013830405,0.00027462808,0.00014550956,0.00027864223,0.000100924786,0.0004349662,0.000008613516],"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":[0.00046242488,0.0030472325,0.5854584,0.00013153715,0.00032466662,0.00008599677,0.01721926,0.000026078493,0.00047613648,0.12660146,0.00037002817,0.26579675],"study_design_scores_gemma":[0.0015826868,0.00061321666,0.3628866,0.000089407964,0.000049692422,0.000010108051,0.0012696305,0.00013592174,0.0012433197,0.630863,0.0009642775,0.00029214067],"about_ca_topic_score_codex":0.00008165768,"about_ca_topic_score_gemma":0.00048385505,"teacher_disagreement_score":0.5042615,"about_ca_system_score_codex":0.0006531263,"about_ca_system_score_gemma":0.00018981074,"threshold_uncertainty_score":0.7180352},"labels":[],"label_agreement":null},{"id":"W3124954008","doi":"10.2139/ssrn.3761992","title":"Prison Rehabilitation Programs: Efficiency and Targeting","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"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; Université de Montréal; Center for Interuniversity Research and Analysis on Organizations; Université du Québec; University of Toronto","funders":"Ministry of Public Security of the People's Republic of China","keywords":"Prison; Rehabilitation; Physical medicine and rehabilitation; Psychology; Medicine; Criminology; Physical therapy","score_opus":0.04727063454987291,"score_gpt":0.3631881595415629,"score_spread":0.31591752499169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124954008","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":[0.56798315,0.0030519876,0.42681563,0.0009032103,0.00006206634,0.00023372125,4.0050185e-7,0.00021687373,0.0007329631],"genre_scores_gemma":[0.91808814,0.0010161874,0.08041087,0.00002133772,0.00008801393,0.000014453717,0.0000024282738,0.000025094263,0.0003334949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980726,0.0001173382,0.00030104825,0.00019194624,0.00020431352,0.001112734],"domain_scores_gemma":[0.99917096,0.00027565288,0.00016129714,0.0001356589,0.00020331742,0.000053136795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017741949,0.00011703313,0.00016269978,0.00005390791,0.00015718814,0.000057034093,0.0000938929,0.0000658639,0.000012296452],"category_scores_gemma":[0.0017985215,0.000104715866,0.000054368527,0.00018854256,0.00005616383,0.00021109128,0.00004266215,0.0010438532,0.0000025763886],"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":[0.0000112390635,0.00015081439,0.0019967041,0.000039532035,0.000029362558,0.00000574311,0.00061996514,0.000002394283,0.003572977,0.91935575,0.00007785232,0.07413769],"study_design_scores_gemma":[0.00017947251,0.00043156822,0.000048224432,0.00005516135,0.000017844768,0.00027236788,0.0033933823,0.00009786956,0.0013289362,0.99350333,0.00054742786,0.00012444248],"about_ca_topic_score_codex":0.0000031490015,"about_ca_topic_score_gemma":0.00006509206,"teacher_disagreement_score":0.350105,"about_ca_system_score_codex":0.00043633237,"about_ca_system_score_gemma":0.00069917,"threshold_uncertainty_score":0.45350808},"labels":[],"label_agreement":null},{"id":"W3124998720","doi":"","title":"Population-Level Intervention and Information Collection in Dynamic Healthcare Policy","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Western University","funders":"","keywords":"Markov decision process; Partially observable Markov decision process; Population; Health care; Monotonic function; Actuarial science; Intervention (counseling); Markov process; Computer science; Econometrics; Medicine; Mathematics; Economics; Statistics; Environmental health","score_opus":0.0840389501912132,"score_gpt":0.4337004996604655,"score_spread":0.34966154946925226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124998720","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":[0.7998278,0.0002380272,0.19476905,0.0040464564,0.00013161117,0.0004209696,0.000005326003,0.00010449881,0.0004562671],"genre_scores_gemma":[0.9957182,0.0015101464,0.0024453464,0.000032606476,0.000041435957,0.000013499381,0.000008001061,0.000011070746,0.00021969655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998632,0.00006301614,0.0003795854,0.00008498273,0.00014563858,0.0006947559],"domain_scores_gemma":[0.9991632,0.0000363497,0.00048344184,0.0001811882,0.000094181385,0.00004161206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011409305,0.00010463164,0.00015334951,0.00033438182,0.0003821019,0.00012979525,0.00015044978,0.00009026861,0.0000034171383],"category_scores_gemma":[0.00081794464,0.000102531274,0.000041205465,0.00009683354,0.000027870541,0.0019475075,0.00004577508,0.0008600652,0.000002302319],"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":[0.000038555274,0.000027430659,0.010026963,0.000040142917,0.000015502214,4.951158e-7,0.00023311035,0.0000025096504,0.000028864733,0.8635824,0.000010927784,0.12599313],"study_design_scores_gemma":[0.00045584544,0.00016408473,0.059279248,0.0000966172,0.000005471806,0.00014105144,0.0004123522,0.00061755395,0.000024103294,0.9386835,0.000026603133,0.00009353949],"about_ca_topic_score_codex":0.0017141036,"about_ca_topic_score_gemma":0.020830495,"teacher_disagreement_score":0.1958904,"about_ca_system_score_codex":0.0019776393,"about_ca_system_score_gemma":0.00038820328,"threshold_uncertainty_score":0.9970368},"labels":[],"label_agreement":null},{"id":"W3125018148","doi":"","title":"Program Quality and Treatment Completion for Youth Training Programs","year":2013,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","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":"Carleton University","funders":"","keywords":"Propensity score matching; Quality (philosophy); Training (meteorology); Psychology; Medicine; Physical therapy; Statistics; Mathematics; Geography","score_opus":0.5495414068579555,"score_gpt":0.5181398152830163,"score_spread":0.03140159157493916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125018148","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":[0.97446775,0.00005683437,0.0007159303,0.00029051575,0.000121910365,0.0126075195,0.00019160553,0.0006407435,0.010907162],"genre_scores_gemma":[0.7430214,0.0023419522,0.2394872,0.000021267635,0.00019814487,0.013891963,0.00044373222,0.00013787666,0.00045645316],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969848,0.00028032783,0.0008352908,0.0008965572,0.00019751368,0.0008055349],"domain_scores_gemma":[0.9973545,0.001086457,0.00034077562,0.00082767295,0.00020439425,0.00018619384],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020816326,0.00039582932,0.00086875155,0.00024249489,0.00014044782,0.00022934767,0.00032839953,0.00046019198,0.000013516893],"category_scores_gemma":[0.0008058104,0.00037609588,0.00016932347,0.00006177228,0.00039561637,0.00010923328,0.00044920878,0.00075555226,0.0000012604562],"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":[0.000060153452,0.0004326738,0.0007287873,0.00034338128,0.000079003665,0.0000014810158,0.0031817837,0.000023297847,0.000033299704,0.014395154,0.000006292231,0.9807147],"study_design_scores_gemma":[0.0021393166,0.00275453,0.0019388718,0.001110237,0.000068178415,0.0000090199665,0.013027614,0.010420201,0.00036172578,0.95631534,0.010418751,0.0014362114],"about_ca_topic_score_codex":0.00014839637,"about_ca_topic_score_gemma":0.00036543573,"teacher_disagreement_score":0.9792785,"about_ca_system_score_codex":0.0012022986,"about_ca_system_score_gemma":0.00026382777,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W3125772486","doi":"","title":"Estimating the Impact of an Improvement to a Revenue Management System: An Airline Application.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Counterfactual thinking; Revenue; Econometrics; Computer science; Focus (optics); Value (mathematics); Revenue management; Operations research; Economics; Engineering; Finance; Machine learning","score_opus":0.14320608756952574,"score_gpt":0.3164780128141871,"score_spread":0.17327192524466134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125772486","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":[0.46400404,0.0000044891326,0.534597,0.000009378145,0.000036346293,0.00090526755,0.000046615485,0.00015288554,0.0002439787],"genre_scores_gemma":[0.89159364,0.000006374473,0.1080452,0.000015061766,0.000057035773,0.000027922479,0.000049380247,0.000036755817,0.00016861755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984173,0.00013984641,0.0003649057,0.0007074242,0.000116739575,0.00025377216],"domain_scores_gemma":[0.99700123,0.00008435217,0.00052119466,0.0019834193,0.00026415064,0.00014567682],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052009634,0.00030485002,0.00042637633,0.00015028479,0.00010872981,0.000047734324,0.0009370302,0.00014841564,0.000013459048],"category_scores_gemma":[0.000055086446,0.00026876296,0.00018415652,0.00038343653,0.00005801254,0.00018659772,0.0010132928,0.00033354998,0.000004552028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009255372,0.0007401041,0.00033808904,0.0022895397,0.00054210884,0.00018768334,0.0012557273,0.7948714,0.0027170035,0.18665195,0.00019254905,0.0101212775],"study_design_scores_gemma":[0.00043172372,0.0006160345,0.00061316934,0.0013216102,0.00051845383,0.000009577768,0.0030237355,0.7239728,0.0025516376,0.2661412,0.000020608391,0.0007794562],"about_ca_topic_score_codex":0.0006710875,"about_ca_topic_score_gemma":0.00012669795,"teacher_disagreement_score":0.4275896,"about_ca_system_score_codex":0.00061981863,"about_ca_system_score_gemma":0.00009090872,"threshold_uncertainty_score":0.99997646},"labels":[],"label_agreement":null},{"id":"W3126063643","doi":"10.1093/ectj/utaa013","title":"Two-way exclusion restrictions in models with heterogeneous treatment effects","year":2020,"lang":"en","type":"article","venue":"Econometrics Journal","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":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; National Natural Science Foundation of China","keywords":"Outcome (game theory); Estimator; Latent variable; Instrumental variable; Econometrics; Structural equation modeling; Mathematics; Treatment effect; Monotone polygon; Variable (mathematics); Selection (genetic algorithm); Contrast (vision); Statistics; Applied mathematics; Computer science; Medicine; Mathematical economics; Artificial intelligence; Mathematical analysis","score_opus":0.2922863835589675,"score_gpt":0.3783037642443129,"score_spread":0.08601738068534537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126063643","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":[0.5572631,0.00046358604,0.43702087,0.00047885766,0.00009405726,0.0004366663,0.000007012045,0.0001677626,0.0040681115],"genre_scores_gemma":[0.92291856,0.0005479452,0.07619563,0.00011456061,0.00012332031,0.000029297551,0.0000013696911,0.000033224194,0.000036124766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889165,0.0000667465,0.00039015946,0.00022030824,0.00015232613,0.00027878885],"domain_scores_gemma":[0.9987758,0.000504493,0.00023532707,0.0001779404,0.000061977255,0.00024446886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001839882,0.00019049009,0.00033088666,0.00068418833,0.00011807531,0.00007781029,0.00016810853,0.000062114545,0.000047407906],"category_scores_gemma":[0.00030447074,0.00014926979,0.00007713507,0.0011015936,0.000024406392,0.00036706007,0.000053749613,0.00030302088,0.0000130389935],"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":[0.0011538363,0.004776478,0.044802155,0.0005066234,0.0010449642,0.0067976983,0.011513896,0.37970763,0.0024778794,0.26694024,0.0031134929,0.2771651],"study_design_scores_gemma":[0.0058847596,0.006743892,0.00084197737,0.00021337553,0.00013966199,0.0012866015,0.00024797738,0.050046198,0.012335587,0.9200074,0.0012621388,0.0009904072],"about_ca_topic_score_codex":0.0000136650115,"about_ca_topic_score_gemma":0.00002984968,"teacher_disagreement_score":0.6530672,"about_ca_system_score_codex":0.0005576763,"about_ca_system_score_gemma":0.00006527181,"threshold_uncertainty_score":0.60870457},"labels":[],"label_agreement":null},{"id":"W3126099178","doi":"10.2139/ssrn.1016131","title":"Limited Information Goodness-of-Fit Testing in Multidimensional Contingency Tables","year":2005,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of British Columbia","funders":"","keywords":"Goodness of fit; Contingency table; Econometrics; Statistics; Computer science; Mathematics","score_opus":0.12984033626226146,"score_gpt":0.37228271373172384,"score_spread":0.24244237746946237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126099178","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":[0.88732636,0.0005637935,0.10964441,0.00024787267,0.000058034206,0.00027892675,0.000004287675,0.00014675224,0.0017295678],"genre_scores_gemma":[0.9130286,0.00026616085,0.08647815,0.00003853153,0.00007723902,0.000009100637,0.0000036031781,0.000016223246,0.00008238162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768686,0.000058867805,0.0007270611,0.00009584344,0.00027571176,0.0011556435],"domain_scores_gemma":[0.998597,0.00041107545,0.00051765796,0.00014032757,0.0002883841,0.000045554378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016814553,0.00015438661,0.00024922602,0.00025967837,0.00008013077,0.000018374642,0.00017762974,0.00009503891,0.00002913883],"category_scores_gemma":[0.0019359138,0.00014038723,0.000053365286,0.00034201253,0.000037422145,0.001010499,0.000046405254,0.0011733765,0.0000097576],"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":[0.00006179769,0.0002421133,0.009655653,0.000046348247,0.00005728625,0.0000021264852,0.0006734298,0.0005522335,0.009326138,0.82990867,0.0000942933,0.14937992],"study_design_scores_gemma":[0.00090857263,0.000273629,0.0007973075,0.00024149628,0.000024529276,0.0002332671,0.001170787,0.0043464107,0.007448289,0.98361677,0.0006619649,0.0002769895],"about_ca_topic_score_codex":0.000041068823,"about_ca_topic_score_gemma":0.0004115935,"teacher_disagreement_score":0.1537081,"about_ca_system_score_codex":0.0006315901,"about_ca_system_score_gemma":0.00074696826,"threshold_uncertainty_score":0.5724825},"labels":[],"label_agreement":null},{"id":"W3126812739","doi":"10.1002/env.2668","title":"Causal inference for quantile treatment effects","year":2021,"lang":"en","type":"article","venue":"Environmetrics","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":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Quantile; Estimator; Causal inference; Inference; Statistics; Quantile regression; Econometrics; Population; Mathematics; Computer science; Demography; Artificial intelligence","score_opus":0.14503351945885762,"score_gpt":0.4149983745832314,"score_spread":0.2699648551243738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126812739","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":[0.10014795,0.0005204372,0.8966767,0.00008502373,0.00017993951,0.00061182556,0.000042068747,0.0003061574,0.0014298513],"genre_scores_gemma":[0.61880714,0.0005006585,0.37725827,0.00009585758,0.000101893456,0.00030723395,0.000039519688,0.00005897055,0.0028304674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99887705,0.000055333174,0.00023695863,0.0003289134,0.00018978222,0.00031198774],"domain_scores_gemma":[0.995584,0.0036808555,0.00010315861,0.00050034095,0.000039738687,0.000091915936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013939333,0.00020982265,0.00031605372,0.0001325788,0.00008496977,0.00002820533,0.00012269297,0.00012940311,0.00010041974],"category_scores_gemma":[0.0035551973,0.00019162672,0.000113567556,0.00040732513,0.000053013697,0.00010929602,0.000071386065,0.00009880102,0.000047462927],"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":[0.00005368989,0.0023234005,0.008876722,0.000559129,0.00023830356,0.00028005143,0.00069580897,0.0001002262,0.05123082,0.6879666,0.0059152553,0.24176],"study_design_scores_gemma":[0.0009159291,0.0008834029,0.0018088156,0.000046502122,0.00013335682,0.000015903719,0.000060194187,0.00046796646,0.5605165,0.385532,0.04911001,0.0005094294],"about_ca_topic_score_codex":0.0000058771457,"about_ca_topic_score_gemma":0.000010833448,"teacher_disagreement_score":0.5194185,"about_ca_system_score_codex":0.00022075327,"about_ca_system_score_gemma":0.000052054627,"threshold_uncertainty_score":0.7814311},"labels":[],"label_agreement":null},{"id":"W3127376134","doi":"10.1093/biomet/asab003","title":"Estimation of local treatment effects under the binary instrumental variable model","year":2021,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","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 Toronto","funders":"","keywords":"Instrumental variable; Interpretability; Observational study; Econometrics; Robustness (evolution); Estimation; Outcome (game theory); Imperfect; Confounding; Binary number; Mathematics; Endogeneity; Statistics; Computer science; Machine learning; Economics","score_opus":0.10829330849576933,"score_gpt":0.3882440437363961,"score_spread":0.27995073524062675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127376134","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":[0.19344428,0.00016351613,0.8049915,0.00007627646,0.00004932898,0.00022248203,0.000014939264,0.0000994366,0.00093824154],"genre_scores_gemma":[0.81010926,0.00002949098,0.18948238,0.00003848356,0.000009439766,0.00003958332,0.000016350295,0.000014068062,0.0002609608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924,0.000052022948,0.00020901683,0.00015578324,0.00019434371,0.00014886094],"domain_scores_gemma":[0.99895024,0.0005207419,0.00009801573,0.000339558,0.00005614921,0.000035316032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013730848,0.00012473633,0.00019719712,0.00016778204,0.00005464146,0.000014355465,0.00010062858,0.000076373784,0.00003691746],"category_scores_gemma":[0.00013017624,0.00008448792,0.000056303372,0.000993272,0.000091657006,0.00010524644,0.0000740528,0.000054437904,0.0000069427983],"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":[0.00004507638,0.0013218585,0.000053337088,0.00029880102,0.00020844997,0.000018156772,0.00025582893,0.011764885,0.10940404,0.7108553,0.0008400523,0.16493422],"study_design_scores_gemma":[0.00037991346,0.0002823666,0.000053263248,0.00006252369,0.000060038394,0.000011238471,0.00017091916,0.10256382,0.58607644,0.31016147,0.00006835923,0.000109643275],"about_ca_topic_score_codex":0.000019013614,"about_ca_topic_score_gemma":0.0000022863371,"teacher_disagreement_score":0.61666495,"about_ca_system_score_codex":0.00024090064,"about_ca_system_score_gemma":0.00010776816,"threshold_uncertainty_score":0.34453171},"labels":[],"label_agreement":null},{"id":"W3129669709","doi":"10.48550/arxiv.2111.06486","title":"Variational Auto-Encoder Architectures that Excel at Causal Inference","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"University of Alberta","funders":"","keywords":"Causal inference; Inference; Discriminative model; Generative grammar; Computer science; Artificial intelligence; Machine learning; Generative model; Observational study; Sequence (biology); Causal model; Series (stratigraphy); Econometrics; Mathematics","score_opus":0.2576327158538822,"score_gpt":0.295841922690196,"score_spread":0.03820920683631379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129669709","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":[0.42745993,0.00003679225,0.5668408,0.000056555822,0.00020751602,0.0003535074,0.00006719563,0.00061654544,0.004361171],"genre_scores_gemma":[0.97196645,0.00011265558,0.022995526,0.000109168475,0.00010907513,0.000008041985,0.00012155106,0.00006603767,0.0045114774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99740154,0.00026067276,0.00033471093,0.0012335179,0.00025255152,0.00051700964],"domain_scores_gemma":[0.99659157,0.0010540689,0.00049618876,0.0013303558,0.00031697753,0.00021083526],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028097272,0.0005946792,0.0006528874,0.00028190186,0.0002213074,0.00009678741,0.0009074789,0.00064767106,0.00097058626],"category_scores_gemma":[0.00054330076,0.0006649369,0.00029187993,0.0003206891,0.00024289812,0.00019126057,0.0026312864,0.0012109833,0.000044883807],"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":[0.00015471317,0.00048323517,0.020779783,0.0007135453,0.0005935707,0.0013096288,0.0020811853,0.2154224,0.0011185335,0.75530255,0.00165458,0.0003862515],"study_design_scores_gemma":[0.00035458396,0.000047776568,0.00352165,0.00032949264,0.00021715395,0.000020577761,0.0001435087,0.040213563,0.0024305074,0.9515492,0.00023823713,0.00093377073],"about_ca_topic_score_codex":0.00015477183,"about_ca_topic_score_gemma":0.0004160214,"teacher_disagreement_score":0.54450655,"about_ca_system_score_codex":0.0007108999,"about_ca_system_score_gemma":0.00045168345,"threshold_uncertainty_score":0.99994266},"labels":[],"label_agreement":null},{"id":"W3131939934","doi":"10.48550/arxiv.2102.10003","title":"Treatment effect estimation with Multilevel Regression and Poststratification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"University of Toronto","funders":"","keywords":"Estimator; Causal inference; Covariate; Statistics; Econometrics; Average treatment effect; Population; Small area estimation; Cluster sampling; Inference; Regression; Nonparametric statistics; Computer science; Sampling (signal processing); Statistical inference; Regression analysis; Mathematics; Demography; Artificial intelligence","score_opus":0.21118456809185446,"score_gpt":0.30243442094547507,"score_spread":0.09124985285362061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131939934","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":[0.6511335,0.000023512763,0.3477762,0.000018900464,0.000028051634,0.0005131425,0.000010171429,0.00022780195,0.00026872676],"genre_scores_gemma":[0.9553217,0.0001532496,0.043874424,0.000004134397,0.000013966775,0.000009033171,0.00009796522,0.000027803806,0.00049769855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988233,0.00014262924,0.0001538534,0.00065427995,0.00006706334,0.00015889242],"domain_scores_gemma":[0.9985127,0.0003497829,0.00028676586,0.0006347671,0.00013335168,0.00008265237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001008034,0.00034281472,0.00037480876,0.000113602306,0.00009697965,0.000059484195,0.0001368006,0.00025728333,0.000017239476],"category_scores_gemma":[0.000112763366,0.00026946125,0.00006650687,0.00012119841,0.00009367797,0.00021123834,0.00016576584,0.00024934215,0.0000030311628],"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":[0.0027139445,0.0029084268,0.037581094,0.00611072,0.001960439,0.003914764,0.007982541,0.08542882,0.019209774,0.6056044,0.0002972359,0.22628783],"study_design_scores_gemma":[0.0023080774,0.001626747,0.004579624,0.0024522238,0.0010733961,0.00007053563,0.0005522302,0.63195753,0.060279332,0.2936844,0.000021690235,0.0013942054],"about_ca_topic_score_codex":0.00008486188,"about_ca_topic_score_gemma":0.00006490417,"teacher_disagreement_score":0.54652876,"about_ca_system_score_codex":0.0003244371,"about_ca_system_score_gemma":0.0000914734,"threshold_uncertainty_score":0.99997574},"labels":[],"label_agreement":null},{"id":"W3133445812","doi":"10.2147/rmhp.s275831","title":"Three Statistical Approaches for Assessment of Intervention Effects: A Primer for Practitioners","year":2021,"lang":"en","type":"article","venue":"Risk Management and Healthcare Policy","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; London Health Sciences Centre","funders":"National Cancer Institute; National Institute on Aging; Icahn School of Medicine at Mount Sinai","keywords":"Autoregressive integrated moving average; Medicine; Medicaid; Health care; Emergency medicine; Interrupted Time Series Analysis; Regression toward the mean; Regression analysis; Statistics; Time series; Mathematics","score_opus":0.22271926986229418,"score_gpt":0.5021859580156652,"score_spread":0.27946668815337106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133445812","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":[0.0018818943,0.00019685598,0.9938403,0.0013997762,0.00003400039,0.0017918557,0.00014371873,0.00006866047,0.00064294843],"genre_scores_gemma":[0.19253303,0.00041629947,0.80556905,0.000092799564,0.00007384728,0.0010521164,0.00010571436,0.000023058103,0.00013405521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999062,0.00006847233,0.00031429096,0.00022949834,0.00011986766,0.00020587382],"domain_scores_gemma":[0.9987195,0.0006687846,0.00024260339,0.0001967816,0.00011518301,0.000057160138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004281256,0.000114589515,0.00024442963,0.000109486595,0.000090417714,0.000020391895,0.000054395132,0.000054969503,0.0000047522003],"category_scores_gemma":[0.000382785,0.00010965551,0.00007161615,0.00010092352,0.000041234878,0.00008906559,0.00007169277,0.000083931445,2.0889644e-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":[0.00002623808,0.00013451489,0.00079463643,0.0049986793,0.00008580359,8.275672e-7,0.00006854766,9.1286256e-7,0.000005056196,0.8795416,0.00093383715,0.11340935],"study_design_scores_gemma":[0.00069311773,0.00036384733,0.0044248416,0.00019497558,0.00013836242,0.0000010800654,0.00030057871,0.0017417226,0.0003057062,0.98956835,0.0021577391,0.00010969236],"about_ca_topic_score_codex":0.00019402761,"about_ca_topic_score_gemma":0.00023913958,"teacher_disagreement_score":0.19065113,"about_ca_system_score_codex":0.00010201269,"about_ca_system_score_gemma":0.000051649753,"threshold_uncertainty_score":0.4471622},"labels":[],"label_agreement":null},{"id":"W3133809934","doi":"10.1093/aje/kwab055","title":"Parametric-Regression–Based Causal Mediation Analysis of Binary Outcomes and Binary Mediators: Moving Beyond the Rareness or Commonness of the Outcome","year":2021,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outcome (game theory); Mediation; Binary number; Parametric statistics; Regression analysis; Econometrics; Psychology; Medicine; Clinical psychology; Statistics; Mathematics; Sociology","score_opus":0.13680713593318722,"score_gpt":0.4469185093233275,"score_spread":0.3101113733901403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133809934","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":[0.9738741,0.00053164095,0.021052014,0.004160826,0.0001960475,0.00012435981,0.00003304097,0.000015789115,0.00001220284],"genre_scores_gemma":[0.96632975,0.0001940297,0.032561507,0.00083323516,0.000036445796,0.000009162281,0.000006413933,0.000019040855,0.000010418898],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943171,0.0028247747,0.002020737,0.0002132999,0.00034255578,0.00028148867],"domain_scores_gemma":[0.95185214,0.042371076,0.0045000794,0.000650851,0.00052062474,0.000105218714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004119686,0.00023925283,0.0021799814,0.0005399984,0.000097358876,0.00000501312,0.00054747297,0.00011547114,0.000058114972],"category_scores_gemma":[0.03991159,0.00010965793,0.00043921158,0.0022887026,0.0011336537,0.00013019904,0.00022477868,0.00046302658,1.3674774e-7],"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":[0.00013120759,0.00014521643,0.9891311,0.000055322773,0.00078693964,0.000025851372,0.00030941414,0.0014804024,0.0009926604,0.0036107884,0.00019551064,0.0031356206],"study_design_scores_gemma":[0.00087963586,0.0012420514,0.92373025,0.00022182576,0.0025584316,0.00008927872,0.0040636463,0.00665749,0.0034162216,0.05670286,0.000076727745,0.0003615767],"about_ca_topic_score_codex":0.000088138906,"about_ca_topic_score_gemma":0.00007893003,"teacher_disagreement_score":0.06540081,"about_ca_system_score_codex":0.00007229576,"about_ca_system_score_gemma":0.00024571395,"threshold_uncertainty_score":0.96817565},"labels":[],"label_agreement":null},{"id":"W3134059791","doi":"10.1007/s10985-021-09527-3","title":"Instrumental variable estimation of early treatment effect in randomized screening trials","year":2021,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Institute for Cancer Research","keywords":"Instrumental variable; Randomized controlled trial; Context (archaeology); Lung cancer screening; Estimator; Treatment effect; Estimation; Causal inference; Cancer screening","score_opus":0.1739607699834338,"score_gpt":0.4512018372006999,"score_spread":0.2772410672172661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134059791","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":[0.12766194,0.000114811664,0.87038934,0.00004616136,0.000019197454,0.00066813786,0.0005560919,0.00009383014,0.00045049618],"genre_scores_gemma":[0.49500275,0.000057743116,0.50223035,0.000011598675,0.000018314058,0.000084596206,0.0024656411,0.000014680145,0.000114323775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647504,0.0015300292,0.0011419172,0.00039689936,0.00027652786,0.00017960569],"domain_scores_gemma":[0.99279326,0.005385796,0.0005380899,0.0011795798,0.000053919466,0.000049373342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004554585,0.00020430746,0.002369584,0.0003774353,0.00003275472,0.000044691995,0.00027943056,0.000090893845,0.0004538436],"category_scores_gemma":[0.008358497,0.00015422778,0.00033841588,0.0013175359,0.000055754746,0.00038944723,0.00019888044,0.00008435446,0.000005508563],"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":[0.10083517,0.006820811,0.064681254,0.0016344221,0.10869003,0.00044531352,0.0047308104,0.06316908,0.04218014,0.13733277,0.0024026548,0.46707755],"study_design_scores_gemma":[0.13028698,0.0005609834,0.00061941054,0.000584589,0.033954132,0.0000071579193,0.00017596871,0.5583555,0.14205846,0.13240919,0.00010355552,0.0008840575],"about_ca_topic_score_codex":0.0006887376,"about_ca_topic_score_gemma":0.000078262834,"teacher_disagreement_score":0.49518645,"about_ca_system_score_codex":0.00007857946,"about_ca_system_score_gemma":0.00005809531,"threshold_uncertainty_score":0.9999945},"labels":[],"label_agreement":null},{"id":"W3134225231","doi":"10.1177/0049124121995548","title":"Marginal and Conditional Confounding Using Logits","year":2021,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","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":"Western University","funders":"Medical Research Council; Chief Scientist Office","keywords":"Confounding; Statistics; Weighting; Econometrics; Marginal structural model; Conditional probability; Odds; Conditional probability distribution; Logistic regression; Marginal model; Inverse probability weighting; Conditional logistic regression; Mathematics; Odds ratio; Regression analysis; Medicine; Propensity score matching","score_opus":0.8690128158201307,"score_gpt":0.7315306657257828,"score_spread":0.13748215009434783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134225231","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":[0.20627204,0.0004887863,0.78647,0.00055852596,0.00005303602,0.00023699708,0.000012052937,0.00017405864,0.005734492],"genre_scores_gemma":[0.1845722,0.00009555203,0.81478536,0.000098816294,0.000118162454,0.000036372414,0.000007736904,0.0000138577925,0.00027193932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948002,0.0035674565,0.00026615692,0.00041605675,0.000400684,0.0005494551],"domain_scores_gemma":[0.98743176,0.011598381,0.00005992096,0.00022680013,0.0005403337,0.00014280928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070893536,0.00013793563,0.00033994686,0.000087023385,0.00038790566,0.00006904678,0.00016916257,0.00028471297,0.00080981303],"category_scores_gemma":[0.013113068,0.000111409834,0.00006428956,0.00028051916,0.0011454541,0.000111733105,0.0004275862,0.0010176664,0.000009722043],"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":[0.000014428733,0.00005191367,0.0006259979,0.000045750505,0.000022683664,0.00008487861,0.00015362038,8.8925066e-7,0.09753379,0.893609,0.000193197,0.007663876],"study_design_scores_gemma":[0.00013281239,0.000091503636,0.0007499135,0.00003283257,0.000007778885,0.0000781013,0.0009300018,0.0002863266,0.01638613,0.9802098,0.00096097396,0.0001337968],"about_ca_topic_score_codex":0.000005017172,"about_ca_topic_score_gemma":6.888489e-7,"teacher_disagreement_score":0.086600855,"about_ca_system_score_codex":0.00016305565,"about_ca_system_score_gemma":0.00014874061,"threshold_uncertainty_score":0.9951999},"labels":[],"label_agreement":null},{"id":"W3135053972","doi":"10.1002/sim.8906","title":"The impact of adjusting for pure predictors of exposure, mediator, and outcome on the variance of natural direct and indirect effect estimators","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Université du Québec à Montréal; Université Laval","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Estimator; Confounding; Outcome (game theory); Mediation; Inverse probability weighting; Variance (accounting); Weighting; Econometrics; Mathematics; Linear regression; Regression analysis; Medicine; Economics","score_opus":0.05564411871493614,"score_gpt":0.42065357746469295,"score_spread":0.3650094587497568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135053972","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":[0.9782513,0.0016052483,0.018395577,0.00009682756,0.00021224952,0.0007941514,0.00037901834,0.00002958842,0.00023604235],"genre_scores_gemma":[0.9729033,0.00021214566,0.026760086,0.0000088983425,0.000034162364,0.000035407407,0.000010340495,0.000018972185,0.000016656746],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986122,0.00018041862,0.0005995249,0.00015708654,0.00027973484,0.00017098573],"domain_scores_gemma":[0.9782064,0.020857023,0.0004383598,0.00026847646,0.00019110362,0.000038656675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015876191,0.00016686223,0.0006143028,0.000065265915,0.000050326682,0.0000041513485,0.00012795244,0.0000633686,0.0000061596875],"category_scores_gemma":[0.031428788,0.00008272867,0.000032895015,0.00019929503,0.0004951141,0.000029237324,0.000055623965,0.00022245804,2.105641e-8],"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":[0.00063301966,0.0001838515,0.5842794,0.004236121,0.00051077816,0.00004051386,0.005905292,0.00007277153,0.019920332,0.35830322,0.0040520024,0.02186266],"study_design_scores_gemma":[0.003508002,0.0056302007,0.24449791,0.0036559443,0.00055931025,0.000030516097,0.0013629596,0.0050231796,0.07819267,0.65708286,0.000023137742,0.00043332524],"about_ca_topic_score_codex":0.000022128615,"about_ca_topic_score_gemma":0.000036769226,"teacher_disagreement_score":0.33978152,"about_ca_system_score_codex":0.000033985423,"about_ca_system_score_gemma":0.00005532143,"threshold_uncertainty_score":0.97672987},"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":"W3137325329","doi":"10.11124/jbies-20-00403","title":"Strategies for measuring prescription medication switching with pharmacy claims data: a scoping review protocol","year":2021,"lang":"en","type":"review","venue":"JBI Evidence Synthesis","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":"Toronto Rehabilitation Institute; Centre for Excellence in Mining Innovation; Institute for Work & Health; St. Michael's Hospital; Public Health Ontario; University Health Network; University of Toronto","funders":"","keywords":"Pharmacy; Medical prescription; Protocol (science); Medicine; Family medicine; Alternative medicine; Pharmacology","score_opus":0.43626730247438156,"score_gpt":0.5549240835973895,"score_spread":0.11865678112300798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137325329","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":[2.5617982e-8,0.6579311,0.18997182,0.00009807575,0.00004162072,0.15145159,0.000025816513,0.00038869824,0.00009123496],"genre_scores_gemma":[3.9741747e-7,0.58073276,0.06157525,0.000031801217,0.0001690968,0.3573396,0.000028431665,0.00010446445,0.000018205019],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.994609,0.00085303414,0.0017716298,0.00132128,0.0009093221,0.0005357135],"domain_scores_gemma":[0.9881228,0.0068190107,0.002102065,0.0023872934,0.00043069964,0.00013808331],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0041835387,0.0008058873,0.0030124271,0.00020302125,0.00023950073,0.00031917955,0.0016174932,0.0002382807,0.00012052472],"category_scores_gemma":[0.010593589,0.0005979727,0.00034155758,0.0004946597,0.00008293748,0.003052432,0.00041946024,0.0006114514,0.000010401259],"study_design_candidate":"systematic_review","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":[0.00000775115,0.000034926656,3.1097534e-7,0.47297224,0.0001053119,0.000006346553,0.000022747738,1.8943956e-7,0.000008374749,0.0010054178,0.0009020683,0.5249343],"study_design_scores_gemma":[0.00006562507,0.000034790213,2.9548948e-8,0.8298681,0.0024978463,0.000056605215,0.000045013556,0.000040598392,0.00010845184,0.003208593,0.1634908,0.0005835425],"about_ca_topic_score_codex":0.000023187882,"about_ca_topic_score_gemma":0.000057458634,"teacher_disagreement_score":0.52435076,"about_ca_system_score_codex":0.0003758369,"about_ca_system_score_gemma":0.0026316496,"threshold_uncertainty_score":0.99964714},"labels":[],"label_agreement":null},{"id":"W3137498389","doi":"10.1002/pds.5227","title":"Control yourself: <scp>ISPE‐endorsed</scp> guidance in the application of <scp>self‐controlled</scp> study designs in pharmacoepidemiology","year":2021,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":80,"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 British Columbia; Women's College Hospital; Public Health Ontario; University of Toronto","funders":"Medical Research Council; International Society for Pharmacoepidemiology; Johnson and Johnson; Novartis Pharmaceuticals Corporation; Brigham and Women's Hospital; Eli Lilly and Company","keywords":"Medicine; Pharmacoepidemiology; Pharmacology","score_opus":0.18511305950100923,"score_gpt":0.4859422869113026,"score_spread":0.3008292274102934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137498389","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":[0.00080167747,0.9389441,0.04702273,0.00031327177,0.00036977316,0.010918608,0.00019119262,0.00032711693,0.0011115365],"genre_scores_gemma":[0.012933799,0.9711378,0.007365755,0.0012695417,0.00039750844,0.006484705,0.00012767964,0.00015480927,0.00012839868],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9537731,0.03543594,0.006598724,0.0020261002,0.00044576914,0.0017204067],"domain_scores_gemma":[0.84365475,0.15074137,0.0038084663,0.0012848708,0.00026859975,0.00024192469],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.038669422,0.001576767,0.0105896145,0.0007800696,0.00023450625,0.000021037307,0.0017797446,0.0010357911,0.000021271637],"category_scores_gemma":[0.036169574,0.0011384521,0.0009876369,0.0011523258,0.0005664308,0.0002946279,0.00038654503,0.0034144614,0.000021750002],"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":[0.0005139041,0.015184527,0.04326746,0.032214496,0.007984159,0.0009641265,0.014248988,0.0011690015,0.00021635847,0.3023721,0.07978154,0.50208336],"study_design_scores_gemma":[0.016350284,0.00043674442,0.00066662737,0.0040444313,0.006549048,0.00031926742,0.0020926392,0.0043011424,0.000047343892,0.05805093,0.9064469,0.0006946479],"about_ca_topic_score_codex":0.00020531235,"about_ca_topic_score_gemma":0.00015669221,"teacher_disagreement_score":0.82666534,"about_ca_system_score_codex":0.0003682168,"about_ca_system_score_gemma":0.00048555998,"threshold_uncertainty_score":0.99969804},"labels":[],"label_agreement":null},{"id":"W3138340382","doi":"10.1016/j.ahj.2021.03.008","title":"To Adjust or Not to Adjust: The Role of Different Covariates in Cardiovascular Observational Studies","year":2021,"lang":"en","type":"review","venue":"American Heart Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":101,"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; University of British Columbia","funders":"Cancer Research UK","keywords":"Confounding; Observational study; Covariate; Econometrics; Causal inference; Outcome (game theory); Regression analysis; Variables; Statistics; Psychology; Computer science; Medicine; Mathematics","score_opus":0.47779239218442265,"score_gpt":0.5094929273474985,"score_spread":0.03170053516307586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138340382","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":[0.0006106443,0.9954809,0.0021908842,0.00038354858,0.00015319399,0.001047089,0.000053619835,0.00004589962,0.000034213248],"genre_scores_gemma":[0.00036993704,0.954683,0.043782428,0.00040418564,0.00032030602,0.00027396015,0.0000062465724,0.000078356396,0.00008157757],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961982,0.00080350356,0.0013365714,0.00038912255,0.0008223579,0.00045026248],"domain_scores_gemma":[0.9952301,0.0027549758,0.00056510797,0.00075711723,0.00050329766,0.00018941423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011881688,0.000495854,0.0041272086,0.00030735432,0.00011961892,0.000049553302,0.0005469201,0.000096263866,0.00007703087],"category_scores_gemma":[0.003581925,0.00028392836,0.0010174331,0.0010964369,0.00016967826,0.00008446806,0.00038821195,0.0008854111,0.000011709842],"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":[0.000036181984,0.00017974795,0.0001576687,0.0019316508,0.0021425367,0.00006975392,0.0012785037,0.000053983127,0.000019943769,0.005959882,0.0032911787,0.98487896],"study_design_scores_gemma":[0.00012087719,0.00054331135,0.00040431228,0.019056447,0.0013167963,0.00053839793,0.0034929381,0.000004318463,0.0001250049,0.0062440443,0.9675004,0.0006531384],"about_ca_topic_score_codex":0.00006672047,"about_ca_topic_score_gemma":0.000074144205,"teacher_disagreement_score":0.9842258,"about_ca_system_score_codex":0.0004322126,"about_ca_system_score_gemma":0.0004877683,"threshold_uncertainty_score":0.9999613},"labels":[],"label_agreement":null},{"id":"W3138456065","doi":"10.1093/biomet/asab016","title":"Identifiability of causal effects with multiple causes and a binary outcome","year":2021,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"National Institute of Environmental Health Sciences; National Institute on Aging","keywords":"Identifiability; Confounding; Outcome (game theory); Causal inference; Econometrics; Mathematics; Observational study; Latent variable; Probit; Inference; Probit model; Causal model; Statistics; Instrumental variable; Computer science; Artificial intelligence","score_opus":0.11765876254771182,"score_gpt":0.4010844052541662,"score_spread":0.28342564270645443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138456065","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":[0.98507416,0.00033840482,0.013861342,0.0000383994,0.000060996885,0.00029360826,0.000028807382,0.00017710602,0.00012718714],"genre_scores_gemma":[0.9295497,0.000023346352,0.070157714,0.000019166762,0.00001415924,0.00002814979,0.0000059270214,0.000021834665,0.00017998698],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885595,0.00008619877,0.0003196186,0.00029425617,0.0002481013,0.00019588953],"domain_scores_gemma":[0.9973323,0.001771158,0.00014942423,0.0004618537,0.00020704785,0.00007825817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003117288,0.0001595741,0.0003928135,0.0003127977,0.000040776984,0.000021599859,0.00009666872,0.00008821885,0.00002977193],"category_scores_gemma":[0.0036693485,0.00012699005,0.000045648252,0.001243302,0.00018828154,0.00014456394,0.00014722675,0.00010277503,0.0000028940522],"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":[0.00009186059,0.0007229142,0.6153679,0.0024135064,0.0001496551,0.00023439655,0.00030440532,7.649497e-7,0.36545694,0.010787769,0.00037317091,0.0040967106],"study_design_scores_gemma":[0.0008778913,0.00048433515,0.12230465,0.0001953386,0.00009778187,0.000048993523,0.00014418182,0.000035848723,0.8410888,0.034072626,0.0003195317,0.0003300374],"about_ca_topic_score_codex":0.000041880543,"about_ca_topic_score_gemma":0.00005919905,"teacher_disagreement_score":0.49306327,"about_ca_system_score_codex":0.00004760061,"about_ca_system_score_gemma":0.000046615056,"threshold_uncertainty_score":0.5178504},"labels":[],"label_agreement":null},{"id":"W3139095225","doi":"10.1164/rccm.202008-3238cp","title":"Attention to Immortal Time Bias in Critical Care Research","year":2021,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Critical illness; Intensive care medicine; Critically ill","score_opus":0.25876148731467413,"score_gpt":0.5310246238141766,"score_spread":0.27226313649950246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139095225","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":[0.9854047,0.0043001077,0.0035805316,0.004780174,0.00013194316,0.00013454349,0.000009557712,0.000032663596,0.0016258364],"genre_scores_gemma":[0.9893675,0.000021365593,0.009266379,0.00094989745,0.00034577752,0.000009389035,0.0000014499559,0.000023817125,0.000014423908],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99700665,0.00079882715,0.0006843618,0.00027149028,0.0008249639,0.00041370778],"domain_scores_gemma":[0.99355906,0.0032540841,0.00007772272,0.00025865826,0.0024019913,0.00044845417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014591034,0.00016415451,0.0006221062,0.00037803026,0.000097878146,0.000027350168,0.00017062757,0.00007273881,0.00017659909],"category_scores_gemma":[0.022155818,0.00013282892,0.000071762595,0.0007146736,0.0013636438,0.00016991408,0.000105217776,0.00082768855,0.0000060093535],"study_design_candidate":"qualitative","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":[0.0011597344,0.0007335267,0.048587147,0.0026579725,0.00009810998,0.017122762,0.025739992,0.0000053257327,0.13581365,0.2593062,0.0062552625,0.5025203],"study_design_scores_gemma":[0.0043671993,0.060539737,0.027508454,0.011016487,0.00062809605,0.0025151179,0.633933,0.000043061384,0.037518263,0.20167007,0.018358227,0.0019023115],"about_ca_topic_score_codex":0.000012218488,"about_ca_topic_score_gemma":0.000021833612,"teacher_disagreement_score":0.608193,"about_ca_system_score_codex":0.00015971296,"about_ca_system_score_gemma":0.00019524412,"threshold_uncertainty_score":0.986081},"labels":[],"label_agreement":null},{"id":"W3143149325","doi":"10.6084/m9.figshare.14381684.v1","title":"Confounding adjustment methods for multi-level treatment comparisons under lack of positivity and unknown model specification","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"Centre hospitalier universitaire de Québec; Université Laval","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Estimator; Context (archaeology); Matching (statistics); Observational study; Propensity score matching; Confounding; Specification; Average treatment effect; Variance (accounting); Computer science; Statistics; Econometrics; Outcome (game theory); Contrast (vision); Mathematics; Machine learning; Artificial intelligence","score_opus":0.8348849125377892,"score_gpt":0.5963865798411815,"score_spread":0.2384983326966077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143149325","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":[0.00035041614,0.0003177644,0.9573101,0.000077133234,0.000016364498,0.0006622759,0.040604353,0.00010187577,0.0005597643],"genre_scores_gemma":[0.022996148,0.000022807722,0.9679471,0.00004225902,0.000019683694,0.00040185018,0.007953548,0.000024256644,0.0005923094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924743,0.00007098185,0.00023776575,0.0002243677,0.00007221623,0.00014723865],"domain_scores_gemma":[0.9984848,0.00078969134,0.00017045092,0.00025819347,0.00024467293,0.000052181425],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000084820065,0.00014336187,0.00029344662,0.000034328415,0.000054903434,0.000017903394,0.00006097104,0.00007843193,0.0012706737],"category_scores_gemma":[0.0006423482,0.00013330128,0.00006471534,0.000066561726,0.000012177995,0.00009193405,0.00005956156,0.000056383364,0.0000050532526],"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":[0.000103390674,0.002509951,0.00004059029,0.0021796806,0.0004770409,0.0000058789046,0.0019919644,0.0011753285,0.10007493,0.69593674,0.058886636,0.13661788],"study_design_scores_gemma":[0.0014511693,0.00021844657,0.00095779536,0.0013492979,0.00014842191,0.000009470993,0.00035745473,0.24900323,0.5927926,0.14683159,0.0064040986,0.00047644568],"about_ca_topic_score_codex":0.0000022868014,"about_ca_topic_score_gemma":0.00002709646,"teacher_disagreement_score":0.5491051,"about_ca_system_score_codex":0.00016662315,"about_ca_system_score_gemma":0.00007646453,"threshold_uncertainty_score":0.9996423},"labels":[],"label_agreement":null},{"id":"W3143317772","doi":"10.1080/0886022x.2021.1903928","title":"Survival outcomes and adverse events in patients with chronic kidney disease after coronary artery bypass grafting and percutaneous coronary intervention: a meta-analysis of propensity score-matching studies","year":2021,"lang":"en","type":"article","venue":"Renal Failure","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Propensity score matching; Kidney disease; Conventional PCI; Percutaneous coronary intervention; Adverse effect; Coronary artery disease; Bypass grafting; Artery","score_opus":0.08804451007661503,"score_gpt":0.338607501394673,"score_spread":0.250562991318058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143317772","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":[0.99774754,0.00071581424,0.0007703854,0.00016122645,0.000016483067,0.0004150356,0.0001242857,0.000045499062,0.0000037458717],"genre_scores_gemma":[0.9946994,0.00003332582,0.005005112,0.000051300805,0.0000061608475,0.000055886994,0.000059862414,0.000023243232,0.00006566506],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981906,0.00025719815,0.0005106256,0.0004394233,0.00037517803,0.00022697255],"domain_scores_gemma":[0.9987436,0.00028086174,0.00025479842,0.00033580238,0.0002420752,0.00014287191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002698633,0.0002932096,0.001194878,0.00016460914,0.00006364519,0.000010750289,0.0000865166,0.000057589255,0.000073056624],"category_scores_gemma":[0.00028830592,0.00020974364,0.0002973261,0.00028841585,0.0001286587,0.00031893904,0.00030876417,0.00020614408,4.850247e-7],"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":[0.00037721003,0.00030076999,0.97080034,0.00050391577,0.026282348,0.0006388911,0.0005803711,0.00005091113,0.00008573685,0.00019025391,0.0000074373133,0.0001818338],"study_design_scores_gemma":[0.0008638448,0.00019742479,0.9641866,0.00034779092,0.027892653,0.000038864215,0.0003551974,0.000052929016,0.000033288048,0.0057169925,0.000003791916,0.00031059806],"about_ca_topic_score_codex":0.000018146327,"about_ca_topic_score_gemma":0.0010928146,"teacher_disagreement_score":0.0066136974,"about_ca_system_score_codex":0.00011391829,"about_ca_system_score_gemma":0.00006878291,"threshold_uncertainty_score":0.8553097},"labels":[],"label_agreement":null},{"id":"W3153628378","doi":"10.2139/ssrn.3013430","title":"Sharp Bounds on Functionals of the Joint Distribution in the Analysis of Treatment Effects","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Carleton University","funders":"","keywords":"Nonparametric statistics; Joint (building); Mathematical optimization; Selection (genetic algorithm); Basis (linear algebra); Identification (biology); Joint probability distribution; Computer science; Distribution (mathematics); Focus (optics); Applied mathematics; Upper and lower bounds; Mathematics; Algorithm; Econometrics; Statistics; Artificial intelligence; Mathematical analysis; Engineering; Geometry","score_opus":0.1110620422219345,"score_gpt":0.39481730790946434,"score_spread":0.28375526568752985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153628378","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":[0.96819085,0.00018636243,0.029932186,0.0007179973,0.000058508787,0.0003126324,0.000020720052,0.0000121642315,0.00056859595],"genre_scores_gemma":[0.9993561,0.00035015252,0.00009285954,0.0000149352445,0.000031432886,0.00001924096,0.000004764193,0.0000064010255,0.00012413565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998669,0.0001587348,0.00031446182,0.00009838036,0.00026583063,0.0004935418],"domain_scores_gemma":[0.99842626,0.00031080842,0.0006315578,0.0005391751,0.00007723457,0.000014965743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014797201,0.00011247106,0.00029139363,0.00008970892,0.00021829084,0.000028056591,0.00036889515,0.00005023558,0.000010467076],"category_scores_gemma":[0.00062977517,0.00005598425,0.0002707917,0.00019449671,0.00009814422,0.00008855257,0.000029672552,0.0005136372,6.592841e-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":[0.000055727007,0.000291864,0.004542328,0.000012595585,0.0007793716,9.26811e-7,0.00020838137,0.0001229918,0.0015359698,0.9852689,0.000051219242,0.007129739],"study_design_scores_gemma":[0.0003417602,0.0007159905,0.051772505,0.00006588967,0.00053435273,0.000014667576,0.00019222853,0.00013673998,0.006307873,0.9397875,0.000064710315,0.00006579254],"about_ca_topic_score_codex":0.000083651306,"about_ca_topic_score_gemma":0.0010398118,"teacher_disagreement_score":0.04723018,"about_ca_system_score_codex":0.0011082928,"about_ca_system_score_gemma":0.00038977124,"threshold_uncertainty_score":0.2898147},"labels":[],"label_agreement":null},{"id":"W3153692697","doi":"10.5539/hes.v11n2p155","title":"Program Specific Effects of a Semester Abroad on the Likelihood of Pursuing a PhD","year":2021,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Propensity score matching; Psychology; Higher education; Study abroad; Sample (material); Matching (statistics); German; Mathematics education; Medical education; Pedagogy; Statistics; Political science; Mathematics; Medicine","score_opus":0.19384437347273922,"score_gpt":0.47402357170306214,"score_spread":0.2801791982303229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153692697","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":[0.9802911,0.008286954,0.0003622096,0.0020616371,0.0010019675,0.00096457015,0.0000028299155,0.00021324752,0.0068154726],"genre_scores_gemma":[0.96942025,0.0004387605,0.027001945,0.00017346155,0.00012586605,0.0006133001,0.0000020854966,0.00002346363,0.0022008638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991082,0.00009262405,0.0002836698,0.00017178699,0.00020687058,0.00013686548],"domain_scores_gemma":[0.9977137,0.001085626,0.00021821326,0.0004122157,0.00055035466,0.000019918956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015093738,0.00012988914,0.00028012058,0.000051607687,0.000048149064,0.000011640937,0.00010786368,0.000037544203,0.00004622637],"category_scores_gemma":[0.00020529128,0.00008744023,0.00006782458,0.00027404077,0.00011413358,0.000057808273,0.00007121877,0.00009903664,0.0000053037666],"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":[0.000032584037,0.0039770724,0.0017779057,0.0024154051,0.0005727127,0.0000046579694,0.008394267,6.07765e-7,0.031261843,0.8091873,0.09835571,0.04401995],"study_design_scores_gemma":[0.0002957195,0.00044460478,0.013628717,0.0019807036,0.0001376367,0.000003952503,0.005788594,5.753776e-7,0.4485649,0.4731856,0.05568101,0.0002879884],"about_ca_topic_score_codex":0.000002019193,"about_ca_topic_score_gemma":0.0000019058492,"teacher_disagreement_score":0.41730306,"about_ca_system_score_codex":0.000045543038,"about_ca_system_score_gemma":0.00006798224,"threshold_uncertainty_score":0.3565709},"labels":[],"label_agreement":null},{"id":"W3154094468","doi":"10.1007/978-1-0716-1138-8_6","title":"Longitudinal Studies 1: Determinants of Risk","year":2021,"lang":"en","type":"book-chapter","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Observational study; Confounding; Selection bias; Casual; Randomized controlled trial; Computer science; Risk analysis (engineering); Randomized experiment; Causal inference; Clinical study design; Econometrics; Medicine; Statistics; Clinical trial; Mathematics; Surgery","score_opus":0.28411791574331063,"score_gpt":0.554268203409184,"score_spread":0.2701502876658734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154094468","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":[0.000384919,0.014920894,0.9617522,0.000007562873,0.00021826326,0.00029417395,0.000050059964,0.000074243326,0.022297714],"genre_scores_gemma":[0.00011966632,0.004646781,0.98954314,0.000023825642,0.000031768053,0.000036475267,0.000008916245,0.00007416694,0.005515274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99744254,0.0007163501,0.00087449147,0.0005688397,0.00011258098,0.00028517947],"domain_scores_gemma":[0.9957923,0.0023600326,0.00077400997,0.0007773125,0.00025995658,0.000036386853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015978316,0.00041995337,0.0015548868,0.00028832915,0.000024119021,0.0000035867295,0.0003198708,0.0006956964,0.00009633388],"category_scores_gemma":[0.0053549986,0.00038359506,0.00024732546,0.000065704175,0.0004685125,0.000021701217,0.00045286427,0.0006542176,0.0000024221195],"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":[0.000019408883,0.000036567388,0.0010748042,0.00037095798,0.00024123491,0.00032469028,0.00012957356,0.0000010635569,0.013133853,0.8884832,0.000024304889,0.09616032],"study_design_scores_gemma":[0.00011176609,0.00012286028,0.00001496617,0.00042032695,0.00013416885,0.000024958714,0.000023816321,0.000004753096,0.081869125,0.9148817,0.0020832191,0.00030832028],"about_ca_topic_score_codex":0.0000069142257,"about_ca_topic_score_gemma":0.00007968955,"teacher_disagreement_score":0.095852,"about_ca_system_score_codex":0.000094483876,"about_ca_system_score_gemma":0.00005999788,"threshold_uncertainty_score":0.9998616},"labels":[],"label_agreement":null},{"id":"W3155589879","doi":"10.1007/978-1-0716-1138-8_17","title":"Randomized Controlled Trials 7: On Contamination and Estimating the Actual Treatment Effect","year":2021,"lang":"en","type":"book-chapter","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Memorial University of Newfoundland","funders":"","keywords":"Censoring (clinical trials); Randomized controlled trial; Discontinuation; Treatment effect; Treatment and control groups; Medicine; Sample size determination; Psychological intervention; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.1615683949677094,"score_gpt":0.523665076592925,"score_spread":0.3620966816252157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155589879","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":[0.00018699377,0.0016937697,0.9648629,0.00014103395,0.00021954207,0.0047744703,0.000010060989,0.000082331986,0.028028939],"genre_scores_gemma":[0.0002666336,0.0003564674,0.98842925,0.00015758035,0.00008845772,0.00145908,0.000042161548,0.000068184774,0.0091322055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.983207,0.01449483,0.0014330195,0.0005089475,0.00012646684,0.00022973932],"domain_scores_gemma":[0.91479623,0.08356268,0.0010850963,0.00044477722,0.00007874803,0.000032455155],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.021195378,0.00057510356,0.0062680165,0.0002271488,0.000057265326,0.000030829025,0.000146758,0.0006341871,0.00008251556],"category_scores_gemma":[0.056750916,0.00028319674,0.00077644363,0.000029838333,0.00031270794,0.000013701996,0.00008758226,0.00042741452,0.00000139143],"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":[0.012529816,0.00002303064,4.330512e-7,0.000038418697,0.00083568087,0.00004270529,0.000105895284,0.000005376485,0.009326383,0.8612928,0.0000041958465,0.11579529],"study_design_scores_gemma":[0.1076765,0.0006577808,1.0109644e-7,0.00031045263,0.0010233128,0.000015383788,0.00000704268,0.0008137665,0.024472779,0.8643372,0.00041853896,0.0002671263],"about_ca_topic_score_codex":0.0000068664435,"about_ca_topic_score_gemma":0.0000066932434,"teacher_disagreement_score":0.11552817,"about_ca_system_score_codex":0.000170307,"about_ca_system_score_gemma":0.000055431163,"threshold_uncertainty_score":0.99996203},"labels":[],"label_agreement":null},{"id":"W3156818063","doi":"10.1002/sim.9002","title":"Semiparametric recurrent event vs time‐to‐first‐event analyses in randomized trials: Estimands and model misspecification","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Censoring (clinical trials); Estimator; Econometrics; Proportional hazards model; Event (particle physics); Semiparametric regression; Semiparametric model; Sample size determination; Statistics; Computer science; Mathematics","score_opus":0.30399888459233215,"score_gpt":0.5326979569422585,"score_spread":0.22869907234992637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156818063","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":[0.003815863,0.0014107932,0.9918494,0.001226928,0.00007717582,0.0009881365,0.00006836508,0.00006078296,0.0005025406],"genre_scores_gemma":[0.13555504,0.0024497283,0.8606334,0.00016395761,0.000081312166,0.00030468294,0.00014226652,0.000039902323,0.00062972563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964209,0.00072037335,0.001681793,0.0004277986,0.000478294,0.0002708236],"domain_scores_gemma":[0.9866794,0.012141098,0.00041551885,0.00038879926,0.0002468486,0.0001283497],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054805605,0.00025064594,0.0018828658,0.0006453616,0.000036962756,0.00001727634,0.00013771617,0.00009578299,0.00027705438],"category_scores_gemma":[0.08024328,0.00020095248,0.000059778347,0.00094594236,0.00015526098,0.000054029457,0.0000762885,0.00030292873,0.000009950275],"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":[0.03741564,0.0027353552,0.00034586567,0.002212513,0.0005808708,0.0006603278,0.012861336,0.023880748,0.010500276,0.60433817,0.112186484,0.19228242],"study_design_scores_gemma":[0.020518325,0.00017684058,0.0000861115,0.0008595826,0.00020592134,0.0000072104904,0.00012864865,0.2976755,0.0010106025,0.6789537,0.00015035545,0.00022720179],"about_ca_topic_score_codex":0.000029329492,"about_ca_topic_score_gemma":0.00008249181,"teacher_disagreement_score":0.27379477,"about_ca_system_score_codex":0.0002436914,"about_ca_system_score_gemma":0.000097486314,"threshold_uncertainty_score":0.92750424},"labels":[],"label_agreement":null},{"id":"W3157155409","doi":"10.1002/sim.8997","title":"Using generalized linear models to implement g‐estimation for survival data with time‐varying confounding","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"NIHR Cambridge Biomedical Research Centre; Bijzonder Onderzoeksfonds UGent; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research; UK Research and Innovation","keywords":"Confounding; Computer science; Estimation; Weighting; Statistics; Marginal structural model; Software; Proportional hazards model; Econometrics; Observational study; Data mining; Mathematics; Medicine","score_opus":0.4354915215451955,"score_gpt":0.5352801309584877,"score_spread":0.0997886094132922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157155409","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":[0.0022770013,0.000024028246,0.995827,0.00022172165,0.00010033067,0.0006215482,0.0005584478,0.00007587828,0.00029402066],"genre_scores_gemma":[0.010191941,0.000016613496,0.98828804,0.0001675238,0.0001254355,0.00004064142,0.0010201257,0.000044280216,0.000105388695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984041,0.00007242177,0.0005140862,0.0003523128,0.00036251935,0.0002945558],"domain_scores_gemma":[0.99761903,0.001236371,0.00015583588,0.00058862375,0.0003140868,0.00008607056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010309445,0.00017375189,0.0004386701,0.000111114634,0.00007971234,0.000017258775,0.00021437573,0.000042939777,0.00011714786],"category_scores_gemma":[0.0021455605,0.00014956793,0.000008400108,0.00023604688,0.000048626993,0.00015784804,0.0001618599,0.00012395807,0.000001469926],"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":[0.00014365016,0.00007493454,0.000049591887,0.0004015744,0.00007235792,0.00009083813,0.0014201811,0.01624356,0.015792659,0.9560856,0.0042845663,0.0053404905],"study_design_scores_gemma":[0.00082023395,0.00011142361,0.0000018057476,0.0003296491,0.00006479972,0.000008970192,0.00017464045,0.60636,0.0012841203,0.3905263,0.00017597376,0.00014208526],"about_ca_topic_score_codex":0.000093852985,"about_ca_topic_score_gemma":0.00016304274,"teacher_disagreement_score":0.59011644,"about_ca_system_score_codex":0.0001597454,"about_ca_system_score_gemma":0.00014629192,"threshold_uncertainty_score":0.6099203},"labels":[],"label_agreement":null},{"id":"W3157785707","doi":"10.1186/s12874-021-01306-w","title":"Comparison of six statistical methods for interrupted time series studies: empirical evaluation of 190 published series","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council; Canadian Institutes of Health Research; Monash University","keywords":"Statistics; Series (stratigraphy); Confidence interval; Autocorrelation; Pairwise comparison; Statistical significance; Sample size determination; Point estimation; Statistical hypothesis testing; Mathematics; Computer science; Econometrics","score_opus":0.9326180323716993,"score_gpt":0.7848555400066978,"score_spread":0.1477624923650015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157785707","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":[0.009407206,0.0010164756,0.98614556,0.001602622,0.00018793046,0.0008941239,0.000042047366,0.00008873657,0.0006153174],"genre_scores_gemma":[0.008021544,0.00012485858,0.9907952,0.000038658727,0.00009199267,0.00049610756,0.000061918414,0.000036617155,0.00033312896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9433912,0.050329223,0.0019614007,0.0007085279,0.0028312155,0.00077840843],"domain_scores_gemma":[0.72983086,0.2601709,0.00045202306,0.0008463223,0.008353094,0.00034681903],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10038468,0.0002281455,0.0018937878,0.00033683877,0.00010065618,0.000019779918,0.00057558174,0.000495734,0.002912541],"category_scores_gemma":[0.81620026,0.00018530949,0.00015895528,0.00078686763,0.0024717222,0.00024521726,0.0007530133,0.0008640803,0.000004528746],"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":[0.0028333322,0.001503358,0.0020500075,0.0051970966,0.00089775596,0.000018822659,0.007609781,0.000015787624,0.050759867,0.60593766,0.045629073,0.27754748],"study_design_scores_gemma":[0.0007372991,0.0012424567,0.00015725875,0.00025626004,0.00013572439,0.000026187734,0.0052960766,0.007481461,0.16348195,0.81941926,0.0016157274,0.00015033345],"about_ca_topic_score_codex":0.000014371395,"about_ca_topic_score_gemma":0.00024371417,"teacher_disagreement_score":0.7158156,"about_ca_system_score_codex":0.0002149571,"about_ca_system_score_gemma":0.0028380037,"threshold_uncertainty_score":0.99799895},"labels":[],"label_agreement":null},{"id":"W3158629300","doi":"10.1186/s12893-021-01278-0","title":"Bias estimation in study design: a meta-epidemiological analysis of transcatheter versus surgical aortic valve replacement","year":2021,"lang":"en","type":"article","venue":"BMC Surgery","topic":"Advanced Causal Inference Techniques","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":"St. Michael's Hospital; Women's College Hospital; University of Toronto; Institute for Work & Health; Western University","funders":"University of Toronto; Canadian Institutes of Health Research; University of Ottawa","keywords":"Medicine; Aortic valve replacement; Propensity score matching; Stenosis; Randomized controlled trial; Aortic valve stenosis; Surgery; Aortic valve; Internal medicine; Epidemiology; Cardiology; Meta-analysis","score_opus":0.6141875518604735,"score_gpt":0.4766740758921051,"score_spread":0.13751347596836838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158629300","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":[0.7083968,0.00016307269,0.2907833,0.00003388581,0.000051625837,0.00038953347,0.0000056057324,0.000108183,0.00006800531],"genre_scores_gemma":[0.9282903,0.000030655618,0.07133145,0.00001545347,0.0000076283327,0.0002622665,0.000019814686,0.000015594465,0.000026814007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958096,0.0018705529,0.001233905,0.0004402717,0.0003620416,0.00028360277],"domain_scores_gemma":[0.973603,0.025270384,0.000347872,0.000589661,0.00012509897,0.00006397584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050786473,0.00024355609,0.0017164595,0.00041796037,0.000026005262,0.000013149421,0.000105338775,0.000119069635,0.0005053596],"category_scores_gemma":[0.007827071,0.00018312263,0.0015495423,0.0013205466,0.000054913013,0.0001097858,0.00004870683,0.00015667277,0.0000032745893],"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":[0.0038659219,0.011026831,0.8866314,0.00041658626,0.043199833,0.00029071333,0.0030702122,0.032831103,0.00039204126,0.012031813,0.0009442208,0.0052993004],"study_design_scores_gemma":[0.007409279,0.003181731,0.3450291,0.00045552076,0.1404983,0.000046490193,0.005217322,0.21489352,0.030614765,0.24844484,0.00021037464,0.0039987867],"about_ca_topic_score_codex":0.000026249874,"about_ca_topic_score_gemma":0.0001118249,"teacher_disagreement_score":0.5416024,"about_ca_system_score_codex":0.000094636714,"about_ca_system_score_gemma":0.000099234785,"threshold_uncertainty_score":0.93702996},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3159118220","doi":"10.1371/journal.pone.0250778","title":"Current trends in the application of causal inference methods to pooled longitudinal observational infectious disease studies—A protocol for a methodological systematic review","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Causal Inference Techniques","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","funders":"Institute of Genetics; Horizon 2020; Canadian Institutes of Health Research; European Commission","keywords":"Observational study; Causal inference; Confounding; Pooling; Psychological intervention; CINAHL; Mendelian randomization; Sample size determination; Clinical study design; EconLit; Propensity score matching; Research design; Protocol (science); MEDLINE; Computer science; Psychology; Medicine; Clinical trial; Statistics; Artificial intelligence; Biology; Alternative medicine; Pathology","score_opus":0.7695121858504534,"score_gpt":0.6143971825879464,"score_spread":0.15511500326250705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159118220","genre_codex":"methods","genre_gemma":"protocol","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":[0.001054752,0.0011098137,0.87189317,0.001039071,0.000012260906,0.124695994,0.00003013986,0.00012808996,0.000036688536],"genre_scores_gemma":[0.0034105973,0.00007496895,0.43659154,0.00023727417,0.000029710469,0.559606,0.000019192952,0.000014682586,0.000016014928],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963872,0.0015292098,0.001017607,0.00037333166,0.00047366324,0.00021902831],"domain_scores_gemma":[0.99115044,0.0067236214,0.00049091276,0.0006620905,0.0008972927,0.000075670156],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035766715,0.00022067544,0.0011081776,0.000115998424,0.000057287558,0.000016544634,0.00029159736,0.00005350648,0.000021123404],"category_scores_gemma":[0.033013523,0.00014807472,0.00013084603,0.00091362034,0.000053525513,0.00010620678,0.00013630204,0.00020928094,0.0000019647064],"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":[0.00015090677,0.0066870516,0.0036652226,0.6840803,0.0005686503,0.0000075855405,0.0006035519,0.000016415783,0.0046714344,0.29400688,0.00039277674,0.0051492276],"study_design_scores_gemma":[0.0010232159,0.0006117918,0.0052278033,0.13979919,0.002783718,0.0000069385146,0.00012370516,0.0013772545,0.01023809,0.83808833,0.000086592416,0.00063338823],"about_ca_topic_score_codex":0.0000020999103,"about_ca_topic_score_gemma":0.00002200076,"teacher_disagreement_score":0.5442811,"about_ca_system_score_codex":0.00013461335,"about_ca_system_score_gemma":0.00009655619,"threshold_uncertainty_score":0.9751318},"labels":[],"label_agreement":null},{"id":"W3160551206","doi":"10.1161/circoutcomes.120.007903","title":"Accuracy of Cardiovascular Trial Outcome Ascertainment and Treatment Effect Estimates from Routine Health Data: A Systematic Review and Meta-Analysis","year":2021,"lang":"en","type":"review","venue":"Circulation Cardiovascular Quality and Outcomes","topic":"Advanced Causal Inference Techniques","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":"University of Ottawa; St. Michael's Hospital; University Health Network; University of Toronto; Women's College Hospital; Queen's University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Hazard ratio; Randomized controlled trial; Meta-analysis; Stroke (engine); Clinical trial; Random effects model; Adjudication; Internal medicine; Myocardial infarction; Confidence interval","score_opus":0.5794287875974299,"score_gpt":0.5409709812143217,"score_spread":0.03845780638310814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160551206","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":[0.000026396612,0.9674505,0.021997219,0.0000938096,0.000044555803,0.009288325,0.0009738721,0.00012140586,0.000003928748],"genre_scores_gemma":[0.00033577476,0.9923055,0.0045819073,0.00008377316,0.00003483074,0.0011545757,0.0014169822,0.00007563702,0.000010990988],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.98623925,0.006657225,0.003973714,0.0015956347,0.0011589001,0.00037524605],"domain_scores_gemma":[0.9843416,0.00798615,0.002292925,0.0049682455,0.00017869029,0.0002323888],"candidate_categories":["metaepi_narrow","metaepi_broad"],"consensus_categories":["metaepi_broad"],"category_scores_codex":[0.011451958,0.0012288359,0.037018944,0.00029699365,0.00018084193,0.0001406479,0.00038541734,0.00037229972,0.00002353912],"category_scores_gemma":[0.0067072087,0.00077620597,0.012662814,0.00060760224,0.00014994219,0.00030128457,0.00047220947,0.00030183903,0.0000011128411],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008591012,0.000054946086,0.00006630393,0.42805633,0.5537338,0.000008028695,0.000059715665,0.000010895159,7.0142425e-9,0.0004518034,0.0000027130322,0.017546836],"study_design_scores_gemma":[0.0023583341,0.000080380065,0.00005915006,0.010688389,0.982172,0.000023900337,0.000029020073,0.000020324318,4.5940834e-7,0.0005419276,0.0033667446,0.00065934524],"about_ca_topic_score_codex":0.00097648177,"about_ca_topic_score_gemma":0.000029980285,"teacher_disagreement_score":0.4284382,"about_ca_system_score_codex":0.00029936965,"about_ca_system_score_gemma":0.00016029888,"threshold_uncertainty_score":0.99946886},"labels":[],"label_agreement":null},{"id":"W3164315881","doi":"10.2217/cer-2021-0069","title":"Propensity score matching versus coarsened exact matching in observational comparative effectiveness research","year":2021,"lang":"en","type":"article","venue":"Journal of Comparative Effectiveness Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Physicians' Services Incorporated Foundation","keywords":"Propensity score matching; Observational study; Medicine; Randomized controlled trial; Matching (statistics); Comparative effectiveness research; Clinical trial; Balance (ability); Statistics; Physical therapy; Internal medicine; Mathematics; Alternative medicine; Pathology","score_opus":0.8095129096967779,"score_gpt":0.6082277517660837,"score_spread":0.20128515793069424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164315881","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":[0.9661387,0.00039424532,0.028811453,0.000118128686,0.00033375202,0.0018212904,0.000014281533,0.00005587193,0.0023122574],"genre_scores_gemma":[0.99059767,0.000056019464,0.008770002,0.000007142757,0.00021870434,0.00023070599,0.000013432881,0.000057473197,0.000048824753],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9689988,0.024358248,0.0012552764,0.00077300303,0.0034374173,0.0011772704],"domain_scores_gemma":[0.9334999,0.056171134,0.0005535347,0.0006323943,0.008841533,0.0003015337],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.029281761,0.0004999183,0.0021037946,0.0013478708,0.00072342367,0.00032717007,0.00095902395,0.00027560574,0.00008923419],"category_scores_gemma":[0.0042354017,0.00043745773,0.00028342032,0.0032025075,0.00083918584,0.001529105,0.0007536031,0.0047407947,0.00003412241],"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":[0.0341129,0.005048009,0.049567983,0.0029363255,0.0013463561,0.0042413985,0.017562144,0.0102914255,0.56370646,0.30882704,0.00076701294,0.0015929585],"study_design_scores_gemma":[0.0038412823,0.0015326318,0.2669365,0.0038912785,0.000026945614,0.0001281122,0.0037300983,0.00026303786,0.24985293,0.46924895,0.000098425655,0.00044979042],"about_ca_topic_score_codex":0.0001544799,"about_ca_topic_score_gemma":0.0003936029,"teacher_disagreement_score":0.3138535,"about_ca_system_score_codex":0.0023937686,"about_ca_system_score_gemma":0.0019755869,"threshold_uncertainty_score":0.9998077},"labels":[],"label_agreement":null},{"id":"W3164974682","doi":"10.48550/arxiv.2105.12720","title":"Marginal structural models with Latent Class Growth Modeling of Treatment Trajectories","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Université Laval","funders":"","keywords":"Covariate; Marginal structural model; Confounding; Inverse probability weighting; Observational study; Estimator; Proportional hazards model; Econometrics; Weighting; Statistics; Estimating equations; Latent class model; Computer science; Mathematics; Medicine","score_opus":0.2642149883152034,"score_gpt":0.26888424256902577,"score_spread":0.004669254253822364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164974682","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":[0.5861217,0.00002985464,0.41256928,0.000007900057,0.000047995494,0.00027808134,0.000033937165,0.00017500765,0.00073625427],"genre_scores_gemma":[0.96975785,0.00025146248,0.029589582,0.0000053147824,0.000031026357,0.0000040781347,0.000043308228,0.00005043461,0.00026696446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840873,0.00009174309,0.00030422313,0.00074499537,0.00012109785,0.000329216],"domain_scores_gemma":[0.9981958,0.00011485629,0.00033832795,0.0007547398,0.00048466155,0.000111600675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008088332,0.00048186377,0.00072879676,0.00017424916,0.00007914689,0.000035965553,0.00039737063,0.00029302383,0.000036183785],"category_scores_gemma":[0.000025407797,0.0004313159,0.0002270191,0.00025295024,0.0001476633,0.00033983926,0.00035939578,0.00041439448,6.5284075e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014272363,0.000066694665,0.00078100094,0.00023236501,0.00024694583,0.00014396799,0.00048566613,0.6235194,0.000068333946,0.37427998,0.0000030060344,0.000029924746],"study_design_scores_gemma":[0.0003641767,0.00018969251,0.000015015669,0.00023036054,0.00025663403,0.00000720686,0.0003897725,0.5253837,0.0012293141,0.4716093,5.511458e-7,0.0003242853],"about_ca_topic_score_codex":0.00049550243,"about_ca_topic_score_gemma":0.00027397342,"teacher_disagreement_score":0.38363615,"about_ca_system_score_codex":0.0007375495,"about_ca_system_score_gemma":0.00034383012,"threshold_uncertainty_score":0.99981385},"labels":[],"label_agreement":null},{"id":"W3167041284","doi":"10.1371/journal.pone.0253057","title":"EA3: A softmax algorithm for evidence appraisal aggregation","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"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":"Medizinische Universität Wien; European Research Council; Universität Wien; University of Toronto; Deutsche Forschungsgemeinschaft","keywords":"Softmax function; Inference; Function (biology); Causal inference; Bayesian probability; Computer science; Aggregate (composite); Quality (philosophy); Risk analysis (engineering); Artificial intelligence; Machine learning; Data science; Management science; Medicine; Econometrics; Mathematics; Economics; Artificial neural network; Epistemology","score_opus":0.33230842506662195,"score_gpt":0.42308011353026176,"score_spread":0.09077168846363981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167041284","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":[0.019095633,0.00033135002,0.9784624,0.00048646604,0.000043974043,0.0005139299,0.00002264589,0.0005600943,0.00048348508],"genre_scores_gemma":[0.019975916,0.000113772454,0.97817874,0.00010538333,0.00017182885,0.00035133155,0.000016321483,0.000036545975,0.0010501477],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989441,0.00003998245,0.00024262635,0.0002575213,0.00029787718,0.0002179186],"domain_scores_gemma":[0.9973145,0.0017508944,0.00012034139,0.00035194363,0.0004053023,0.000056995323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022674234,0.00012505199,0.0002491038,0.00003869844,0.00006637638,0.00003732031,0.00013037438,0.000088709196,0.00009471892],"category_scores_gemma":[0.005731788,0.00013046215,0.000057836343,0.00015581015,0.000037771828,0.00029863138,0.00006552258,0.0001241598,0.000025681915],"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":[0.00006838433,0.0056011532,0.0005823464,0.002341131,0.0006508171,0.0000756661,0.0015052408,0.0000024442095,0.3773745,0.19557467,0.0064106327,0.40981302],"study_design_scores_gemma":[0.0001835015,0.00012405687,0.00001935736,0.0010068578,0.0001174337,0.0000054268316,0.00005739937,0.00440939,0.64615613,0.34752157,0.00020031103,0.00019853548],"about_ca_topic_score_codex":0.0000025081572,"about_ca_topic_score_gemma":0.000007624998,"teacher_disagreement_score":0.40961447,"about_ca_system_score_codex":0.000058645168,"about_ca_system_score_gemma":0.000077947356,"threshold_uncertainty_score":0.68618995},"labels":[],"label_agreement":null},{"id":"W3167159522","doi":"10.1016/j.cjca.2021.05.012","title":"Emulating a Randomised Controlled Trial With Observational Data: An Introduction to the Target Trial Framework","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal; McGill University Health Centre; McGill University","funders":"Faculty of Medicine, McGill University","keywords":"Medicine; Observational study; Randomized controlled trial; Physical therapy; Medical physics; Internal medicine","score_opus":0.3421173803111958,"score_gpt":0.45621014785226793,"score_spread":0.11409276754107212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167159522","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":[0.0000443559,0.6182334,0.3653947,0.0017984479,0.004742807,0.009356904,0.0001922283,0.000035892634,0.000201262],"genre_scores_gemma":[0.00024901683,0.5089835,0.34225476,0.0005139226,0.14460729,0.0017740097,0.0010517745,0.000341431,0.00022428767],"study_design_codex":"randomized_trial","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947714,0.0023326748,0.0017156795,0.000436404,0.00032244463,0.00042136176],"domain_scores_gemma":[0.9919472,0.0039379084,0.0016828096,0.0012435297,0.0007367091,0.00045187084],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004463494,0.00040651305,0.004638335,0.00033687285,0.00019551792,0.000110423825,0.0010924948,0.00050129363,0.00006534501],"category_scores_gemma":[0.024725115,0.00023842952,0.00062534225,0.00039536998,0.00012656412,0.00025472062,0.00005666656,0.0013794918,0.0000018890627],"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":false,"study_design_scores_codex":[0.60776514,0.00003809861,0.0000034574407,0.00093128905,0.0064984686,0.00049795385,0.00036135656,0.0022657975,4.6868726e-7,0.060561795,0.10078637,0.22028983],"study_design_scores_gemma":[0.20888855,0.0008416689,1.0286634e-7,0.0009526822,0.001329711,0.00034411481,0.000038939022,0.000007216887,8.44587e-8,0.008587983,0.7787893,0.00021964517],"about_ca_topic_score_codex":0.00003685306,"about_ca_topic_score_gemma":0.00041471262,"teacher_disagreement_score":0.67800295,"about_ca_system_score_codex":0.00034999987,"about_ca_system_score_gemma":0.006359193,"threshold_uncertainty_score":0.99927384},"labels":[],"label_agreement":null},{"id":"W3168529271","doi":"10.1002/9781118445112.stat07475","title":"<scp>J</scp> oint <scp>M</scp> odels","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","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":"Simon Fraser University","funders":"","keywords":"Conditional independence; Independence (probability theory); Computer science; Event (particle physics); Joint (building); Process (computing); Econometrics; Latent growth modeling; Longitudinal data; Artificial intelligence; Statistics; Machine learning; Mathematics; Data mining; Engineering","score_opus":0.11693235072682291,"score_gpt":0.3903701334789807,"score_spread":0.2734377827521578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168529271","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":[0.00011557977,0.000964044,0.71220183,0.000030221488,0.000613897,0.0014857812,0.033464186,0.0028682626,0.24825618],"genre_scores_gemma":[0.00014120553,0.0044641197,0.5674259,0.0003154701,0.00072538736,0.00020503331,0.005760067,0.0017852114,0.4191776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914669,0.00047876788,0.0021248853,0.0019895916,0.0018443317,0.002095556],"domain_scores_gemma":[0.98571134,0.007123863,0.0025986463,0.0028557335,0.00085333287,0.00085711],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.000786622,0.0021571596,0.002738009,0.001073098,0.00022662841,0.00025316514,0.00190564,0.0016192723,0.0011926092],"category_scores_gemma":[0.01242278,0.0020421145,0.00025481015,0.0006830193,0.0007889283,0.00022931317,0.0007394965,0.0025158757,0.0011591649],"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":[0.000003434716,0.00045081438,0.00002227592,0.00085837994,0.0002122974,0.00009974701,0.00025218443,0.000008765187,0.000104480416,0.24391727,0.7492889,0.004781398],"study_design_scores_gemma":[0.0005383082,0.00043661273,0.000013461904,0.0015866008,0.00027552055,0.000026498921,0.00033648653,0.0006623871,0.00017523604,0.38049304,0.61508006,0.0003757861],"about_ca_topic_score_codex":0.00029035416,"about_ca_topic_score_gemma":0.0016408324,"teacher_disagreement_score":0.17092143,"about_ca_system_score_codex":0.00048752272,"about_ca_system_score_gemma":0.00068127946,"threshold_uncertainty_score":0.99978536},"labels":[],"label_agreement":null},{"id":"W3168647111","doi":"10.1214/22-aoas1726","title":"Evaluating the use of generalized dynamic weighted ordinary least squares for individualized HIV treatment strategies","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","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":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Categorical variable; Estimator; Ordinary least squares; Human immunodeficiency virus (HIV); Mathematics; Population; Mathematical optimization; Robustness (evolution); Computer science; Medicine; Statistics; Econometrics; Algorithm; Immunology","score_opus":0.6063138857192424,"score_gpt":0.5398848109691714,"score_spread":0.06642907475007098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168647111","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":[0.2584332,0.00006336772,0.73300606,0.0006746544,0.000051486655,0.0027306478,0.0043538683,0.00034744773,0.00033928722],"genre_scores_gemma":[0.3423781,0.00040893466,0.65547156,0.000091143214,0.00003508144,0.0006953121,0.00043135366,0.00008149737,0.00040701914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982267,0.00014764172,0.00067522627,0.00021315478,0.00039757925,0.00033967485],"domain_scores_gemma":[0.99343157,0.0049599237,0.0006287247,0.00063111266,0.0003125535,0.00003613507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008456055,0.00025865278,0.0005128207,0.00010365302,0.0001868291,0.00004860372,0.00035921164,0.000074087846,0.00003256438],"category_scores_gemma":[0.0004216852,0.0001495634,0.00009924773,0.00032208383,0.00030504767,0.000083270934,0.000108425724,0.00010156575,0.00000476788],"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":[0.000588895,0.00012774931,0.000003103391,0.00020537872,0.000269064,0.0000015354753,0.002267179,0.002369026,0.010364819,0.94649875,0.007348758,0.029955754],"study_design_scores_gemma":[0.00065194094,0.00059579144,0.00006460872,0.000048295016,0.00017528053,9.764441e-7,0.0012171259,0.040148005,0.016048694,0.94013786,0.00074528164,0.00016616542],"about_ca_topic_score_codex":0.000031790576,"about_ca_topic_score_gemma":0.000030326608,"teacher_disagreement_score":0.08394491,"about_ca_system_score_codex":0.000026381913,"about_ca_system_score_gemma":0.00012672764,"threshold_uncertainty_score":0.60990185},"labels":[],"label_agreement":null},{"id":"W3170350666","doi":"10.1186/s12874-021-01452-1","title":"Evaluating the performance of propensity score matching based approaches in individual patient data meta-analysis","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Propensity score matching; Observational study; Confounding; Matching (statistics); Meta-analysis; Random effects model; Statistics; Logistic regression; Medicine; Odds ratio; Internal medicine; Mathematics","score_opus":0.9918079962204878,"score_gpt":0.7322729214567691,"score_spread":0.2595350747637186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170350666","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008313393,0.85266477,0.14391182,0.00008884885,0.000036192727,0.0022465724,0.00011093163,0.00004311447,0.000066390756],"genre_scores_gemma":[0.000126811,0.43989632,0.5585578,0.00003046419,0.0000469961,0.0009064551,0.00036121506,0.000050708044,0.000023220582],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.88493437,0.10443444,0.0027216438,0.001505319,0.0053832955,0.0010209352],"domain_scores_gemma":[0.8104118,0.18421097,0.0010563437,0.0035991417,0.0004954955,0.0002262413],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19373369,0.0004973408,0.0073343106,0.0010373284,0.00017137094,0.000047345915,0.0041459515,0.00081221136,0.00093783264],"category_scores_gemma":[0.25178897,0.00026768266,0.0011575683,0.0032038982,0.0010905877,0.00014052662,0.005057341,0.004111223,0.0000044384],"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":[0.000031034746,0.00027315787,0.000048942755,0.022253279,0.019761553,0.000038415485,0.00034997432,0.00006916745,9.592554e-7,0.004279953,0.000087425455,0.9528061],"study_design_scores_gemma":[0.0012977187,0.0038224347,0.00011449292,0.032105517,0.765369,0.00027814793,0.0023524615,0.06334006,0.00037521217,0.092761196,0.03472661,0.003457181],"about_ca_topic_score_codex":0.00021176443,"about_ca_topic_score_gemma":0.0009479213,"teacher_disagreement_score":0.949349,"about_ca_system_score_codex":0.00014302059,"about_ca_system_score_gemma":0.005600437,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W3171631375","doi":"10.1002/jae.2985","title":"Multiple testing with covariate adjustment in experimental economics","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","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","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Covariate; Null hypothesis; Statistics; Statistical hypothesis testing; Null (SQL); Econometrics; Multiple comparisons problem; Statistical power; Mathematics; Alternative hypothesis; Sample size determination; Computer science; Data mining","score_opus":0.2636212041580691,"score_gpt":0.36247357626277843,"score_spread":0.09885237210470932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171631375","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":[0.98860115,0.000050195307,0.0057570958,0.00003339822,0.00011392124,0.00027400142,0.0000052501823,0.00009499209,0.005070001],"genre_scores_gemma":[0.8589995,0.00007016032,0.14072591,0.000043076026,0.000083608895,0.000023299293,0.0000016775593,0.000034673747,0.000018093957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998697,0.000010462556,0.0007349114,0.00016782392,0.000111864334,0.00027795346],"domain_scores_gemma":[0.99784106,0.001110432,0.0007034379,0.00018071356,0.0000678262,0.00009651255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077030755,0.0001645808,0.00042452544,0.0012407763,0.000034601537,0.00003380708,0.00022785702,0.00007273108,0.000027527218],"category_scores_gemma":[0.00038237008,0.00014575744,0.0000480643,0.0013241846,0.000035685014,0.00023007012,0.00007988081,0.00025626444,0.0000191456],"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":[0.0024426458,0.0040236367,0.080120236,0.000603804,0.0009140751,0.0005422187,0.008704692,0.13843608,0.0232851,0.5881797,0.0048887194,0.1478591],"study_design_scores_gemma":[0.011759831,0.002892072,0.02687521,0.00034773335,0.0001346972,0.0002773722,0.009513497,0.025712809,0.15825945,0.759116,0.0030867434,0.0020245602],"about_ca_topic_score_codex":0.0000038394364,"about_ca_topic_score_gemma":0.0000072909447,"teacher_disagreement_score":0.17093632,"about_ca_system_score_codex":0.00044248035,"about_ca_system_score_gemma":0.00008107865,"threshold_uncertainty_score":0.59438163},"labels":[],"label_agreement":null},{"id":"W3172234771","doi":"","title":"Commentary on Cox et al.","year":2019,"lang":"en","type":"article","venue":"Evidence-Based Mental Health","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":"University of British Columbia","funders":"","keywords":"Psychology","score_opus":0.19573689921768495,"score_gpt":0.47611042619721117,"score_spread":0.2803735269795262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172234771","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21027529,0.00083718076,0.012179796,0.7626587,0.0011102533,0.005381595,0.00015924008,0.0016802727,0.005717637],"genre_scores_gemma":[0.5238831,0.0003619055,0.031875655,0.44342694,0.0000374956,0.00008214238,0.000054068816,0.00005193132,0.00022675244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788624,0.0002617692,0.00044312415,0.00040752176,0.0005409146,0.00046042263],"domain_scores_gemma":[0.997713,0.0011614949,0.00026070583,0.00062699,0.0000351988,0.0002026042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011846322,0.00025660283,0.0003738143,0.0001161702,0.0001292998,0.000027383736,0.00027182096,0.000053366264,0.0005329392],"category_scores_gemma":[0.000103455386,0.00023200999,0.000081873906,0.00016862564,0.00006523428,0.00032207737,0.00007166809,0.00037929337,0.00031351947],"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":[0.00029705826,0.00044808738,0.0015679193,0.00031918962,0.000013621071,0.000004436254,0.0003734042,0.000018128037,0.0016626687,0.03979585,0.9484104,0.007089271],"study_design_scores_gemma":[0.006960241,0.019450374,0.0023670201,0.02787932,0.000044279277,0.000033605742,0.001919283,0.0017642878,0.16255769,0.20888992,0.5651609,0.002973086],"about_ca_topic_score_codex":0.00015327531,"about_ca_topic_score_gemma":0.00004029801,"teacher_disagreement_score":0.38324946,"about_ca_system_score_codex":0.0008229757,"about_ca_system_score_gemma":0.00023425379,"threshold_uncertainty_score":0.9461093},"labels":[],"label_agreement":null},{"id":"W3173229721","doi":"","title":"Methods for Population Adjustment with Limited Access to Individual Patient Data: A Review and Simulation Study","year":2021,"lang":"en","type":"review","venue":"UCL Discovery (University College London)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"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":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Institute of Conservation","keywords":"Computer science; Data collection; Research methodology; Population; Data science; Management science; Statistics; Demography; Sociology","score_opus":0.30749754247377786,"score_gpt":0.4937568482589888,"score_spread":0.18625930578521094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173229721","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":[0.000099296485,0.7783749,0.20403877,0.000051360024,0.00008070399,0.012988928,0.004171036,0.00015670325,0.000038285038],"genre_scores_gemma":[0.0000423955,0.84194016,0.15471494,0.0001474115,0.000035826237,0.00013041178,0.0024272734,0.00008105093,0.00048050363],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969142,0.00082869385,0.0005458618,0.0010415944,0.00036221207,0.00030740164],"domain_scores_gemma":[0.9959419,0.0016343368,0.0007345387,0.0012983405,0.00024807587,0.00014284051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006785065,0.0005568318,0.0022255676,0.00041200378,0.00023702832,0.00011814777,0.0008491235,0.0001915625,0.00002193867],"category_scores_gemma":[0.00059866835,0.00049926376,0.00017278935,0.0012366263,0.000034250883,0.0021013934,0.0017922332,0.0002770552,0.0000011957482],"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":[0.00009163478,0.0007919308,0.000029432036,0.029497705,0.0010657777,0.000057200275,0.00023342075,0.0000519025,5.1559947e-8,0.0062700063,0.003881627,0.9580293],"study_design_scores_gemma":[0.0011681216,0.0015066649,0.00012498646,0.037356015,0.01999087,0.000024475961,0.0010307671,0.00039179792,4.916767e-7,0.0011072118,0.9357353,0.0015632877],"about_ca_topic_score_codex":0.000040140487,"about_ca_topic_score_gemma":0.00018935312,"teacher_disagreement_score":0.956466,"about_ca_system_score_codex":0.00038962465,"about_ca_system_score_gemma":0.00024306387,"threshold_uncertainty_score":0.9997459},"labels":[],"label_agreement":null},{"id":"W3173591338","doi":"10.1136/bmjopen-2020-045410","title":"Simulation study on the validity of the average risk approach in estimating population attributable fractions for continuous exposures","year":2021,"lang":"en","type":"article","venue":"BMJ Open","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":true,"ca_institutions":"University of Calgary; McMaster University; Queen's University; Impact; Alberta Health Services","funders":"Canadian Cancer Society","keywords":"Medicine; Attributable risk; Population; Environmental health; Epidemiology; Statistics; Internal medicine","score_opus":0.4618158466234644,"score_gpt":0.5231943004545682,"score_spread":0.06137845383110374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173591338","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":[0.61942875,0.0000011005894,0.37144446,0.00007659034,0.0000532101,0.008383706,0.000030286004,0.00003268354,0.00054920046],"genre_scores_gemma":[0.9360608,1.6770203e-7,0.06244045,0.000022722657,0.000028328728,0.0013181701,0.000013567327,0.000014314419,0.000101476464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998576,0.0005129154,0.00040485442,0.00017901184,0.0002101307,0.00011712931],"domain_scores_gemma":[0.99573076,0.0030991593,0.00044201556,0.0005633675,0.00015301743,0.000011699371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019559935,0.00009661856,0.00026122676,0.000024184375,0.00021107207,0.000069219794,0.00027168632,0.00004969637,0.000016994138],"category_scores_gemma":[0.008150383,0.000061326915,0.000052184634,0.00020108113,0.000015159547,0.0001971227,0.00020690923,0.00016839811,6.824451e-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":[0.00010246248,0.0018756521,0.3767947,0.00012938611,0.000062382845,0.0000018434699,0.0029839366,0.58258164,0.00035016317,0.03295,0.00041273923,0.0017551249],"study_design_scores_gemma":[0.00093938434,0.00025457802,0.16662912,0.0002492566,0.000079193545,0.0000018856769,0.0031501781,0.37656868,0.00464041,0.4472208,0.000035243884,0.000231262],"about_ca_topic_score_codex":0.00018421959,"about_ca_topic_score_gemma":0.00013889787,"teacher_disagreement_score":0.41427082,"about_ca_system_score_codex":0.00006532965,"about_ca_system_score_gemma":0.00004056023,"threshold_uncertainty_score":0.97573584},"labels":[],"label_agreement":null},{"id":"W3174385715","doi":"10.1214/21-aoas1570","title":"Estimation of the marginal effect of antidepressants on body mass index under confounding and endogenous covariate-driven monitoring times","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Covariate; Endogeneity; Confounding; Statistics; Body mass index; Propensity score matching; Marginal structural model; Econometrics; Selection bias; Index (typography); Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.17584202781014677,"score_gpt":0.41534126538013316,"score_spread":0.2394992375699864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174385715","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":[0.7394337,0.00004247969,0.25655898,0.000047685546,0.00010407305,0.001120252,0.0005312348,0.000057837828,0.0021037802],"genre_scores_gemma":[0.9842955,0.000033853958,0.015562146,0.000012983464,0.000011959605,0.00004183122,0.0000059497615,0.000022490247,0.000013273141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875426,0.00014688916,0.00037257688,0.00012937229,0.00043235035,0.0001645237],"domain_scores_gemma":[0.99680704,0.002164672,0.0005786813,0.0003552394,0.00007218526,0.000022187107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006953872,0.0001460667,0.0003517733,0.00006250304,0.00015791511,0.000009622526,0.0002847149,0.000035488923,0.000023437435],"category_scores_gemma":[0.00021515627,0.000099657904,0.00003355506,0.00013273295,0.00019560009,0.000029801931,0.00018082737,0.00021636234,3.7669207e-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":[0.0006867533,0.00011376923,0.0014723543,0.00054493156,0.00019518043,0.00000320046,0.00079008023,0.037950113,0.0952588,0.85745484,0.00022526878,0.005304724],"study_design_scores_gemma":[0.00036851416,0.0003874432,0.002414512,0.0000937156,0.00009510558,0.000004658931,0.00025717125,0.00963583,0.44123885,0.5453765,0.0000065110835,0.00012122341],"about_ca_topic_score_codex":0.000021664317,"about_ca_topic_score_gemma":4.5187562e-7,"teacher_disagreement_score":0.34598005,"about_ca_system_score_codex":0.000021884438,"about_ca_system_score_gemma":0.00003142979,"threshold_uncertainty_score":0.40639314},"labels":[],"label_agreement":null},{"id":"W3180503092","doi":"10.1016/j.jeconom.2023.02.011","title":"Inference on individual treatment effects in nonseparable triangular models","year":2023,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Japan Society for the Promotion of Science; National Natural Science Foundation of China; National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; Social Sciences and Humanities Research Council of Canada; Renmin University of China; Japan Society for the Promotion of Science London","keywords":"Mathematics; Jackknife resampling; Estimator; Asymptotic distribution; Density estimation; Kernel density estimation; Instrumental variable; Applied mathematics; Inference; Nonparametric statistics; Statistics; Econometrics; Artificial intelligence; Computer science","score_opus":0.5512096984674635,"score_gpt":0.43109320865724554,"score_spread":0.12011648981021794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180503092","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":[0.9695446,0.00021516437,0.026167395,0.00013734585,0.00024671873,0.00040427028,0.000016288128,0.00009980763,0.0031683943],"genre_scores_gemma":[0.9812988,0.00059062697,0.017705234,0.00005453812,0.00007207719,0.000025797042,0.0000025146232,0.000026791211,0.00022363056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856436,0.000081982085,0.00067942013,0.00014800736,0.00023747893,0.0002887404],"domain_scores_gemma":[0.99538964,0.0036702692,0.00050436246,0.00023674789,0.00008754736,0.00011140435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011135134,0.00017814798,0.0005380735,0.0026443028,0.00003220752,0.000046621262,0.00027284084,0.00009331143,0.000027202843],"category_scores_gemma":[0.0026082424,0.00014641932,0.000120043944,0.0019093535,0.000025136387,0.00040820692,0.000045079858,0.00025553606,0.000034333094],"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":[0.0009660871,0.005523957,0.02410845,0.00054324593,0.00087996706,0.0022889061,0.004326137,0.074709386,0.00054067274,0.7075832,0.010544428,0.16798556],"study_design_scores_gemma":[0.0019795275,0.003965594,0.0026205704,0.00018181033,0.000050141858,0.000019899573,0.00009447542,0.0033634622,0.0030674504,0.9839587,0.00046116335,0.0002371609],"about_ca_topic_score_codex":0.0000065413087,"about_ca_topic_score_gemma":0.000008839551,"teacher_disagreement_score":0.27637553,"about_ca_system_score_codex":0.00041874783,"about_ca_system_score_gemma":0.00011808977,"threshold_uncertainty_score":0.59708065},"labels":[],"label_agreement":null},{"id":"W3181564238","doi":"10.29173/cais1219","title":"A Bibliometric Analysis of Race-Related Research in LIS","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University; Western University","funders":"","keywords":"Diversity (politics); Equity (law); Race (biology); Work (physics); Sociology; Political science; Library science; Regional science; Social science; Computer science; Engineering; Gender studies; Anthropology","score_opus":0.1645688386437193,"score_gpt":0.4133993316957991,"score_spread":0.24883049305207983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181564238","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":[0.9885792,0.00032550574,0.00010852174,0.00071778224,0.000039965078,0.00036091232,0.00012459463,0.00006052267,0.009682989],"genre_scores_gemma":[0.9943481,0.00045923048,0.0045588254,0.000023812821,0.00001559235,0.00004426826,0.000005878184,0.000031190422,0.0005131124],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99655455,0.00011871579,0.001174144,0.00045737196,0.001123063,0.0005721352],"domain_scores_gemma":[0.9099807,0.0015881535,0.001135283,0.00048425177,0.086681604,0.00013000777],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0028719741,0.00027403154,0.0011508034,0.027995214,0.00007428173,0.0006718405,0.0016912253,0.00030250015,0.00011883456],"category_scores_gemma":[0.0872266,0.00022722737,0.00035296066,0.12703554,0.00065051107,0.0044684852,0.0010191043,0.00069587305,0.0000013285023],"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":[0.00027936304,0.001456023,0.5107773,0.0018695887,0.0017971419,0.000022388605,0.039871585,0.000028938928,0.16481142,0.25905415,0.0029795093,0.017052619],"study_design_scores_gemma":[0.00086827244,0.00045737086,0.21553113,0.0013042373,0.00082903844,0.000029057275,0.006341272,0.0011902994,0.42785397,0.3424077,0.002640921,0.0005467268],"about_ca_topic_score_codex":0.0002675599,"about_ca_topic_score_gemma":0.000068962516,"teacher_disagreement_score":0.29524612,"about_ca_system_score_codex":0.00012898713,"about_ca_system_score_gemma":0.00042394086,"threshold_uncertainty_score":0.9830216},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3182566191","doi":"10.1016/j.hlpt.2021.100545","title":"Analysing electronic health records: The benefits of target trial emulation","year":2021,"lang":"en","type":"article","venue":"Health Policy and Technology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Horizon 2020; European Commission; Trent University; Kingston University; Nottingham Trent University","keywords":"Observational study; Confounding; Emulation; Selection bias; Information bias; Randomized controlled trial; Medicine; Health records; Clinical trial; Relevance (law); Computer science; Health care; Medical physics; Psychology; Internal medicine","score_opus":0.13086425565288243,"score_gpt":0.4726321239005088,"score_spread":0.3417678682476264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182566191","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":[0.5026249,0.014624069,0.098014206,0.3792725,0.00019965078,0.0025903438,0.00006367077,0.0014578472,0.0011527712],"genre_scores_gemma":[0.96798384,0.0030049041,0.027018514,0.0016575807,0.00014567244,0.000053588894,0.000012416539,0.00002301171,0.00010045738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984775,0.00017051374,0.00054874487,0.00021660974,0.00011115698,0.00047544544],"domain_scores_gemma":[0.9986405,0.00031919865,0.0004667354,0.00040783733,0.00011451004,0.000051268966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069564226,0.000117094314,0.00043673097,0.00030797222,0.00020445247,0.0000073374354,0.00011662377,0.00015445448,0.000011783167],"category_scores_gemma":[0.001216291,0.000094188115,0.00003711414,0.0010334922,0.00012126436,0.000053892392,0.000079846235,0.00033915017,7.711526e-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":[0.00007542372,0.000048210903,0.00008764558,0.0000916733,0.00001667389,2.861908e-7,0.00018044724,0.000004858123,0.000046234374,0.9514106,0.00026010378,0.04777786],"study_design_scores_gemma":[0.0014770715,0.00065255375,0.000060947572,0.00007489952,0.000007274779,0.000024677573,0.00018200396,0.00015953745,0.0024154314,0.98924774,0.0056168437,0.00008103335],"about_ca_topic_score_codex":0.00039252863,"about_ca_topic_score_gemma":0.00080066256,"teacher_disagreement_score":0.46535888,"about_ca_system_score_codex":0.00019446513,"about_ca_system_score_gemma":0.0010662681,"threshold_uncertainty_score":0.384088},"labels":[],"label_agreement":null},{"id":"W3182851625","doi":"10.1097/ede.0000000000001379","title":"To Bound or Not to Bound","year":2021,"lang":"en","type":"letter","venue":"Epidemiology","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":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Columbia university; Statistics; History; Genealogy; Library science; Geography; Demography; Media studies; Mathematics; Sociology; Computer science","score_opus":0.4387032220054125,"score_gpt":0.5088100046339101,"score_spread":0.07010678262849762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182851625","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":[0.00079845503,0.000097705866,0.13891876,0.8545572,0.001067042,0.0009821011,0.00011718603,0.00064982794,0.0028116836],"genre_scores_gemma":[0.000044352226,0.000037850637,0.2253044,0.7450364,0.0035369368,0.00035099697,0.00013017382,0.00013657787,0.025422262],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99464375,0.0012418893,0.0013538428,0.0012101703,0.00023862865,0.001311745],"domain_scores_gemma":[0.97948337,0.017858114,0.00045573208,0.001716799,0.00023664303,0.00024936078],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0020910266,0.0006773199,0.0023149913,0.00031429323,0.00012119896,0.000034208962,0.00086823595,0.0018919939,0.0017881688],"category_scores_gemma":[0.04900494,0.0005610654,0.00026465778,0.00034742613,0.00016999224,0.00007415184,0.0006299757,0.00245721,0.0008342977],"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":[0.000039001,0.000017603954,0.000023384704,0.00016954655,0.00006923452,0.0005362017,0.00012582609,0.0000027327044,0.00018008891,0.014560028,0.98333853,0.00093781686],"study_design_scores_gemma":[0.000054832915,0.00022596863,0.000025418205,0.0001757422,0.00003972323,0.000080401966,0.000013175884,0.0000026440475,0.0003879219,0.3248937,0.6736338,0.00046662454],"about_ca_topic_score_codex":0.000101778314,"about_ca_topic_score_gemma":0.00019790555,"teacher_disagreement_score":0.3103337,"about_ca_system_score_codex":0.00040647038,"about_ca_system_score_gemma":0.0002660385,"threshold_uncertainty_score":0.9999437},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3186631519","doi":"10.1038/s41366-021-00909-z","title":"Errors in the implementation, analysis, and reporting of randomization within obesity and nutrition research: a guide to their avoidance","year":2021,"lang":"en","type":"review","venue":"International Journal of Obesity","topic":"Advanced Causal Inference Techniques","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":"McMaster University; Impact","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Heart, Lung, and Blood Institute","keywords":"Randomized controlled trial; Randomization; Pooling; Randomized experiment; Causal inference; Random assignment; Research design; Statistical power; Psychology; Computer science; Econometrics; Medicine; Statistics; Artificial intelligence; Mathematics","score_opus":0.3229823804839253,"score_gpt":0.569537068589849,"score_spread":0.24655468810592368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186631519","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":[0.07974099,0.8175449,0.09958681,0.0005404419,0.00020869757,0.0021275233,0.000108190856,0.000022538648,0.000119907454],"genre_scores_gemma":[0.025188021,0.9352274,0.0392921,0.000032586653,0.00013431658,0.000050389368,0.000041404677,0.000017846378,0.000015960411],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948523,0.0010497546,0.002963824,0.00021499631,0.0007871456,0.00013199494],"domain_scores_gemma":[0.99176353,0.001621567,0.0046407683,0.00020682978,0.0017156845,0.00005160498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010831334,0.0001780565,0.0013576453,0.0009116094,0.00006311593,0.00008083427,0.00040914636,0.00010118513,0.000015833406],"category_scores_gemma":[0.0067226416,0.0001206707,0.00025777236,0.00080647506,0.00007707234,0.0002390663,0.00016439702,0.00052092155,1.4547058e-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":[0.00078535377,0.0037824092,0.043739792,0.019303966,0.010446952,0.001351173,0.02873522,0.00007448394,0.00038209595,0.10859583,0.007202954,0.7755998],"study_design_scores_gemma":[0.010875978,0.00147586,0.015970558,0.13336127,0.009176598,0.00533884,0.025690231,0.00025856847,0.0048264195,0.587259,0.2033671,0.002399557],"about_ca_topic_score_codex":0.00008418831,"about_ca_topic_score_gemma":0.00049978134,"teacher_disagreement_score":0.7732002,"about_ca_system_score_codex":0.00022287815,"about_ca_system_score_gemma":0.00022514474,"threshold_uncertainty_score":0.80481154},"labels":[],"label_agreement":null},{"id":"W3187148082","doi":"10.1002/cjs.11650","title":"Nested doubly robust estimating equations for causal analysis with an incomplete effect modifier","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Causal inference; Estimator; Inverse probability; Inference; Confounding; Covariate; Estimating equations; Econometrics; Missing data; Mathematics; Causal model; Computer science; Statistics; Artificial intelligence; Posterior probability; Bayesian probability","score_opus":0.17286319533372785,"score_gpt":0.3824992649622621,"score_spread":0.20963606962853426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187148082","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":[0.014740096,0.000023027844,0.98411053,0.00008395957,0.000090044734,0.00019199707,0.00064705743,0.000022320168,0.00009093889],"genre_scores_gemma":[0.24234515,6.4643746e-7,0.7573196,0.000048459766,0.00008532257,0.000011826606,0.00009671979,0.000030695846,0.000061558174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986074,0.00012087108,0.00054309895,0.00016190161,0.000231522,0.0003351902],"domain_scores_gemma":[0.99557865,0.0018354685,0.0004717252,0.00027751416,0.001295497,0.000541134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005182835,0.00018284899,0.0005034046,0.0003830339,0.00022348906,0.00013338058,0.00018327088,0.000072833725,0.00009388048],"category_scores_gemma":[0.0029253685,0.00016084309,0.000081647304,0.00058149785,0.000097353746,0.00024802625,0.000009260307,0.0002452215,8.721412e-7],"study_design_candidate":"theoretical_or_conceptual","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":[0.00019907678,0.00015267413,0.01107384,0.00061333086,0.0031191753,0.0028644619,0.0024513789,0.29760483,0.0006528812,0.65312886,0.007717585,0.02042191],"study_design_scores_gemma":[0.0021227682,0.0027326716,0.0018501203,0.00040772898,0.0054455902,0.000482554,0.00058073224,0.56987876,0.001066453,0.41395313,0.00053207786,0.0009474372],"about_ca_topic_score_codex":0.00067864644,"about_ca_topic_score_gemma":0.06762747,"teacher_disagreement_score":0.27227393,"about_ca_system_score_codex":0.00023993816,"about_ca_system_score_gemma":0.00135226,"threshold_uncertainty_score":0.9493859},"labels":[],"label_agreement":null},{"id":"W3187664365","doi":"10.1002/cjs.11648","title":"Dummy endogenous treatment effect estimation using high‐dimensional instrumental variables","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Instrumental variable; Estimator; Logistic regression; Average treatment effect; Propensity score matching; Econometrics; Statistics; Curse of dimensionality; Ordinary least squares; Mathematics; Estimation; Regression; Variables; Monte Carlo method; Linear regression; Variable (mathematics); Computer science; Economics","score_opus":0.12615962435199574,"score_gpt":0.34170076068560956,"score_spread":0.21554113633361383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187664365","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":[0.38744852,0.00020607155,0.6105075,0.0000581908,0.0005075507,0.00019809706,0.0007541527,0.000022985858,0.00029692153],"genre_scores_gemma":[0.4966895,0.000009310674,0.50313663,0.000029029936,0.000054278375,0.0000016394165,0.00002967506,0.000019031859,0.00003090888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886686,0.00010481301,0.00043750406,0.00011284283,0.00020587676,0.0002721081],"domain_scores_gemma":[0.9983244,0.00053267035,0.00030855028,0.00014974584,0.00031720035,0.00036745626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019642264,0.00017805869,0.00034808012,0.00015501489,0.00015916354,0.00005838549,0.0000877449,0.000071386654,0.00031078618],"category_scores_gemma":[0.0007731336,0.00015572191,0.000054025135,0.00012680453,0.0000750659,0.00014575114,0.0000111034315,0.0001470385,0.000004278794],"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":[0.00012531468,0.00038570244,0.004739466,0.00041025528,0.0010774311,0.021431731,0.0017479829,0.011285805,0.044927355,0.73379433,0.006273804,0.17380083],"study_design_scores_gemma":[0.0022109193,0.0021182632,0.00038526324,0.00059294637,0.00076543906,0.009186055,0.00018485241,0.013194852,0.13939317,0.83043945,0.0008755225,0.0006533031],"about_ca_topic_score_codex":0.0016014178,"about_ca_topic_score_gemma":0.0031521625,"teacher_disagreement_score":0.17314751,"about_ca_system_score_codex":0.0010415044,"about_ca_system_score_gemma":0.0019157747,"threshold_uncertainty_score":0.6350155},"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":"W3189430776","doi":"10.1002/sim.9141","title":"Estimating adjusted risk differences by multiply‐imputing missing control binary potential outcomes following propensity score‐matching","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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 Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Imputation (statistics); Missing data; Confidence interval; Matching (statistics); Mean squared error; Absolute risk reduction; Regression; Mathematics; Econometrics; Medicine","score_opus":0.0927472377061911,"score_gpt":0.39244463014258196,"score_spread":0.2996973924363909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189430776","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":[0.41623697,0.00014778331,0.5824531,0.0001666746,0.00035285283,0.00029245604,0.00007000127,0.00018561193,0.0000945954],"genre_scores_gemma":[0.5691907,0.000010603368,0.43047303,0.00011192243,0.00006646486,0.000013888258,0.000042087766,0.00003633087,0.0000549993],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658054,0.00050112786,0.001087779,0.0005530868,0.00069256127,0.0005849258],"domain_scores_gemma":[0.9946833,0.0039177802,0.0005935268,0.00042580583,0.00022530589,0.00015424012],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001470033,0.00040678107,0.0011314962,0.00014607901,0.00034346138,0.00005968255,0.00026333483,0.00014547621,0.00007844404],"category_scores_gemma":[0.017317304,0.00033271482,0.000075139666,0.00030178743,0.00020341312,0.00018470164,0.0001701676,0.0008405148,0.0000032764692],"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":[0.00012466473,0.00075487694,0.7542516,0.001441243,0.00063079677,0.004698739,0.010366712,0.0013601466,0.101,0.015125105,0.0028981275,0.107348],"study_design_scores_gemma":[0.005219074,0.00033431582,0.09462126,0.0037429444,0.00057393184,0.000054970882,0.0021583345,0.1799359,0.0013243932,0.71099097,0.0000075699213,0.0010363336],"about_ca_topic_score_codex":0.0003825322,"about_ca_topic_score_gemma":0.00008958747,"teacher_disagreement_score":0.69586587,"about_ca_system_score_codex":0.00015309267,"about_ca_system_score_gemma":0.00011154616,"threshold_uncertainty_score":0.9999125},"labels":[],"label_agreement":null},{"id":"W3191068200","doi":"10.1093/ije/dyab157","title":"Causal diagrams for immortal time bias","year":2021,"lang":"en","type":"editorial","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":45,"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 British Columbia","funders":"","keywords":"Medicine; Psychology; Computer science","score_opus":0.2682896299893995,"score_gpt":0.5137249393930979,"score_spread":0.24543530940369845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191068200","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":[0.00027586383,0.0011000839,0.16367574,0.001379798,0.83227116,0.00025329125,0.0005693025,0.000071032715,0.0004037385],"genre_scores_gemma":[0.00019506335,0.0007577826,0.1494991,0.00029607734,0.84693,0.000044589488,0.0006725799,0.00009561457,0.0015091556],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953308,0.0007040825,0.0024405587,0.00037838757,0.0007063498,0.0004398354],"domain_scores_gemma":[0.9354983,0.05654687,0.0036009108,0.0003243158,0.0038737406,0.00015586965],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0057735946,0.0004046484,0.0017403973,0.00034084314,0.000037369475,0.000031776945,0.0012206087,0.001161054,0.00036161146],"category_scores_gemma":[0.19704299,0.0003383709,0.00080678787,0.00006975186,0.00018985214,0.00019995583,0.00021070793,0.0014140218,0.000014724791],"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":[0.0001586907,0.00010591852,0.00006438732,0.00003985262,0.00077820465,0.00017986489,0.000026670636,0.000016687827,0.00010115377,0.016014583,0.97885007,0.003663942],"study_design_scores_gemma":[0.00044516692,0.00032119453,0.000005923419,0.00031455266,0.00012526062,0.0001302373,0.000009384108,0.000107630236,0.00013521346,0.37853023,0.6196478,0.00022737517],"about_ca_topic_score_codex":0.000017172082,"about_ca_topic_score_gemma":0.000024257339,"teacher_disagreement_score":0.36251566,"about_ca_system_score_codex":0.00043968268,"about_ca_system_score_gemma":0.0006243752,"threshold_uncertainty_score":0.99990684},"labels":[],"label_agreement":null},{"id":"W3192788213","doi":"10.1177/0272989x211025525","title":"Testing for a Sweet Spot in Randomized Trials","year":2021,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Advanced Causal Inference Techniques","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":"Health Sciences Centre; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Canada Research Chairs; BrightFocus Foundation","keywords":"Sweet spot; Randomized controlled trial; Risk stratification; Clinical trial; MEDLINE; Blind spot","score_opus":0.39334255561661463,"score_gpt":0.5333925520726709,"score_spread":0.14004999645605626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192788213","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":[0.02951256,0.00018830768,0.966955,0.00033937843,0.00020563297,0.0008351199,0.0000032744117,0.00019139906,0.0017692986],"genre_scores_gemma":[0.27623054,0.000014708679,0.7229354,0.00037485856,0.00014305311,0.00022217153,0.0000022597762,0.000025775147,0.00005123989],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962864,0.0007333465,0.0015627196,0.00033497557,0.00076958747,0.00031296338],"domain_scores_gemma":[0.8261805,0.17254946,0.00043976287,0.00039844235,0.0002994029,0.00013239202],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018058911,0.00016280904,0.0015911025,0.00014842469,0.000056190205,0.000044682372,0.00023611916,0.00021161136,0.0006444852],"category_scores_gemma":[0.66738874,0.0001209333,0.00027064703,0.0004136437,0.00007608331,0.00008584556,0.00016733719,0.0002787021,0.0000074119525],"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":[0.005480124,0.00014055216,0.00008185926,0.00009878188,0.000028781727,0.00031467743,0.00016075342,0.000008318636,0.0013594718,0.11487852,0.002269208,0.87517893],"study_design_scores_gemma":[0.032331876,0.000031075404,0.00001842405,0.0020029491,0.00003262839,0.00003197517,0.000047940932,0.007113601,0.0014170326,0.9563614,0.000469894,0.0001412089],"about_ca_topic_score_codex":0.0000022673391,"about_ca_topic_score_gemma":0.000022925757,"teacher_disagreement_score":0.8750377,"about_ca_system_score_codex":0.00006821318,"about_ca_system_score_gemma":0.0001964019,"threshold_uncertainty_score":0.70566607},"labels":[],"label_agreement":null},{"id":"W3193216897","doi":"10.1002/sim.9151","title":"Estimating the marginal effect of a continuous exposure on an ordinal outcome using data subject to covariate‐driven treatment and visit processes","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Marginal structural model; Outcome (game theory); Confounding; Causal inference; Econometrics; Inference; Statistics; Odds; Generalization; Computer science; Inverse probability weighting; Mathematics; Logistic regression; Artificial intelligence; Propensity score matching","score_opus":0.18254403681751505,"score_gpt":0.48358799182642537,"score_spread":0.30104395500891035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193216897","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":[0.4769054,0.0000951122,0.52183944,0.00014217653,0.00007214857,0.00053174264,0.00028565785,0.000041722866,0.0000866365],"genre_scores_gemma":[0.511941,0.000013131306,0.48781025,0.00004681184,0.000065431064,0.000013975407,0.00007031513,0.000019909303,0.000019167814],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853104,0.00022866907,0.00045727342,0.00032603985,0.00025675245,0.00020021897],"domain_scores_gemma":[0.995956,0.0030051698,0.00019235224,0.0006168436,0.00016227433,0.00006735526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084145187,0.000204739,0.00058426283,0.00008049243,0.00006625619,0.000017506056,0.00022199869,0.000044600696,0.000032232114],"category_scores_gemma":[0.00802841,0.00012486277,0.00000815766,0.00025700874,0.00013208705,0.000071851624,0.00012496812,0.00015491802,4.842209e-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":[0.003091979,0.0020281337,0.37697673,0.01276327,0.00082126464,0.0038692858,0.029512897,0.0049102837,0.043856896,0.20844813,0.0017848113,0.31193632],"study_design_scores_gemma":[0.020480681,0.07203456,0.020389775,0.01647539,0.0037210807,0.0013032315,0.006185708,0.27382204,0.04360831,0.5386402,0.0005478123,0.0027911959],"about_ca_topic_score_codex":0.00015253862,"about_ca_topic_score_gemma":0.00023125244,"teacher_disagreement_score":0.35658696,"about_ca_system_score_codex":0.00008545669,"about_ca_system_score_gemma":0.000093377486,"threshold_uncertainty_score":0.96113366},"labels":[],"label_agreement":null},{"id":"W3193794660","doi":"10.1515/ijb-2020-0144","title":"Quantifying the extent of visit irregularity in longitudinal data","year":2021,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","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":"Institute of Health Services and Policy Research; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Bin; Observational study; Statistics; Longitudinal data; Sample size determination; Longitudinal study; Medicine; Repeated measures design; Mathematics; Demography; Computer science; Data mining","score_opus":0.3671022536769504,"score_gpt":0.48595958555317914,"score_spread":0.11885733187622877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193794660","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":[0.18930541,0.0007500146,0.800524,0.007584577,0.00091342686,0.00016379877,0.0004102841,0.00001791975,0.00033059038],"genre_scores_gemma":[0.89578986,0.00026098744,0.10367376,0.00010604498,0.00011533291,7.2298656e-7,0.000013392894,0.000009780323,0.000030093415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983418,0.000120526434,0.00066864054,0.00010277923,0.00065956626,0.000106685045],"domain_scores_gemma":[0.9963416,0.0017044141,0.0006404115,0.00046125418,0.0008279701,0.00002434104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013417369,0.00009019617,0.00020238591,0.000069745074,0.00003466842,0.000048388076,0.0013506901,0.00003276498,0.000064215776],"category_scores_gemma":[0.0033310226,0.000053385003,0.00004979569,0.000128769,0.00013500474,0.00015868926,0.00045004993,0.0003206368,0.0000014331173],"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":[0.00019653297,0.0005080045,0.011631263,0.000068957095,0.00043468102,0.0008207782,0.00093380944,0.00014017896,0.012495126,0.94197613,0.008337765,0.022456802],"study_design_scores_gemma":[0.00057243905,0.00009883024,0.020871291,0.0005613747,0.00012421861,0.0010400115,0.0010891979,0.0036589452,0.028580388,0.9417871,0.0014478515,0.00016833056],"about_ca_topic_score_codex":0.000028147659,"about_ca_topic_score_gemma":0.00021320155,"teacher_disagreement_score":0.7064845,"about_ca_system_score_codex":0.0000753376,"about_ca_system_score_gemma":0.00015903653,"threshold_uncertainty_score":0.3987786},"labels":[],"label_agreement":null},{"id":"W3196495100","doi":"10.1093/ije/dyab168.399","title":"286Collider-stratification bias when estimating variable importance using Random Forests","year":2021,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Université du Québec à Montréal; McGill University","funders":"","keywords":"Causal inference; Outcome (game theory); Feature selection; Random forest; Inference; Collider; Variable (mathematics); Econometrics; Variables; Statistics; Computer science; Selection bias; Machine learning; Artificial intelligence; Mathematics; Physics","score_opus":0.40156421078467736,"score_gpt":0.49848441269001376,"score_spread":0.0969202019053364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196495100","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":[0.044230282,0.00027667228,0.95227766,0.0014634313,0.0009094103,0.000093503564,0.000007805698,0.00003833113,0.0007028914],"genre_scores_gemma":[0.12773857,0.00003630357,0.8710253,0.00051948347,0.0005448781,0.000006064866,0.000013430256,0.000018881936,0.000097082695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970236,0.00055470155,0.0016757619,0.0002082087,0.0002721423,0.00026559317],"domain_scores_gemma":[0.9891501,0.0069760005,0.0020340225,0.00023895058,0.0015045383,0.000096386095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00413224,0.00015526096,0.00058610085,0.00014360667,0.000053491072,0.000027894166,0.00040540757,0.0001418319,0.00030976642],"category_scores_gemma":[0.053240664,0.00013642767,0.00015734367,0.000103690116,0.00008773223,0.0004079894,0.00007651178,0.0003505091,0.0000030926099],"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":[0.0002699595,0.00025277,0.07405867,0.000058112004,0.00057575083,0.00040496248,0.00036857976,0.015617661,0.013059162,0.874488,0.009218913,0.011627451],"study_design_scores_gemma":[0.00058761786,0.00004523687,0.00046476876,0.00021269933,0.000042232794,0.0012069509,0.000049552247,0.023226494,0.0029313555,0.9700456,0.0010693733,0.00011807534],"about_ca_topic_score_codex":0.000018519882,"about_ca_topic_score_gemma":0.000036717604,"teacher_disagreement_score":0.09555763,"about_ca_system_score_codex":0.00025377798,"about_ca_system_score_gemma":0.00034151733,"threshold_uncertainty_score":0.95473427},"labels":[],"label_agreement":null},{"id":"W3196666600","doi":"10.48550/arxiv.2109.03757","title":"Causal Inference for Quantile Treatment Effects","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Quantile; Estimator; Causal inference; Quantile regression; Statistics; Inference; Econometrics; Population; Average treatment effect; Mathematics; Computer science; Artificial intelligence; Medicine; Environmental health","score_opus":0.2776922142114546,"score_gpt":0.3254229962819759,"score_spread":0.04773078207052128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196666600","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":[0.38412037,0.00005403586,0.61301273,0.000016831056,0.00026345468,0.0010959709,0.00005665109,0.0005227636,0.00085721706],"genre_scores_gemma":[0.97247297,0.00031266705,0.024989853,0.000028997956,0.000082307255,0.000038221937,0.0000958695,0.000063672815,0.0019154648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807614,0.00013198964,0.0002646519,0.0010028218,0.0000777507,0.00044664866],"domain_scores_gemma":[0.9964184,0.0016646666,0.0003242958,0.0011487781,0.00028569644,0.00015812389],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014764401,0.0005201968,0.0007413448,0.00016939767,0.00012497714,0.00007278572,0.0004893436,0.0004745797,0.0000651271],"category_scores_gemma":[0.0005650458,0.00055607513,0.00036715937,0.00022404839,0.000114943105,0.00018621229,0.0005897961,0.0003743985,0.000014656182],"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":[0.00014522072,0.00081238826,0.0016062992,0.0015687417,0.00054945576,0.0007327481,0.0006076856,0.00607605,0.0011590158,0.984174,0.000622702,0.0019456598],"study_design_scores_gemma":[0.0010880544,0.0006152448,0.00016472375,0.0006953535,0.0006449796,0.0000050812578,0.00024932894,0.021043409,0.022925975,0.95096844,0.0005760912,0.0010233182],"about_ca_topic_score_codex":0.00014236396,"about_ca_topic_score_gemma":0.00026980974,"teacher_disagreement_score":0.58835256,"about_ca_system_score_codex":0.0006202952,"about_ca_system_score_gemma":0.00032602568,"threshold_uncertainty_score":0.9996891},"labels":[],"label_agreement":null},{"id":"W3196761963","doi":"10.1212/wnl.0000000000012777","title":"Applying Propensity Score Methods in Clinical Research in Neurology","year":2021,"lang":"en","type":"article","venue":"Neurology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":137,"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; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Observational study; Covariate; Matching (statistics); Medicine; Weighting; Statistics; Internal medicine; Mathematics; Pathology; Radiology","score_opus":0.7483324935008868,"score_gpt":0.6275504623094126,"score_spread":0.12078203119147424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196761963","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":[0.9826672,0.00005640501,0.009445627,0.0033157014,0.00024551357,0.00081217376,9.2242317e-7,0.00014606884,0.0033103984],"genre_scores_gemma":[0.87366104,0.00016347885,0.12027198,0.004987804,0.00014145573,0.00063725543,0.0000035697922,0.00006661178,0.00006683323],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99133253,0.006321528,0.00077943184,0.00072918873,0.00019018224,0.0006471383],"domain_scores_gemma":[0.99270767,0.0062418617,0.00010609641,0.00069721375,0.00017150033,0.00007565598],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0056901057,0.00015142054,0.00060505356,0.00031043665,0.000046252357,0.000013081257,0.0003371523,0.0004687246,0.00006461304],"category_scores_gemma":[0.0060314485,0.00015170079,0.000060605904,0.0007602817,0.00034106176,0.000087355475,0.00063479017,0.002937059,0.000021902619],"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":[0.0012537896,0.0012619591,0.6337569,0.00017216938,0.000017337125,0.009538753,0.00027294777,0.000039266044,0.019992193,0.1936958,0.00092150347,0.13907741],"study_design_scores_gemma":[0.0006841295,0.0011395938,0.08802488,0.000021586064,0.0000049989953,0.00029618517,0.00000859666,0.0005256499,0.0047603785,0.8979106,0.0064314962,0.00019192968],"about_ca_topic_score_codex":0.00007257991,"about_ca_topic_score_gemma":0.0012210747,"teacher_disagreement_score":0.70421475,"about_ca_system_score_codex":0.000021483123,"about_ca_system_score_gemma":0.00016186076,"threshold_uncertainty_score":0.9993632},"labels":[],"label_agreement":null},{"id":"W3197211443","doi":"10.1186/s12874-021-01364-0","title":"Evaluation of statistical methods used in the analysis of interrupted time series studies: a simulation study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":110,"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 Public Health; Ottawa Hospital","funders":"National Health and Medical Research Council; Medical Research Council; Monash University","keywords":"Autocorrelation; Statistics; Series (stratigraphy); Ordinary least squares; Mathematics; Restricted maximum likelihood; Econometrics; Population; Confidence interval; Maximum likelihood; Demography; Biology","score_opus":0.9376995805081113,"score_gpt":0.7822997123750204,"score_spread":0.15539986813309092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197211443","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":[0.21869157,0.00017700957,0.7802029,0.00012773833,0.000023172124,0.0006390743,0.000007722982,0.00001829206,0.000112501904],"genre_scores_gemma":[0.44438154,0.00002953354,0.5553709,0.0000114419645,0.00001332048,0.00015569803,0.00001005673,0.000008483943,0.000018991315],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79594135,0.19655383,0.0015387806,0.00051569357,0.005005406,0.00044496937],"domain_scores_gemma":[0.6449887,0.35028455,0.00025566499,0.00075381337,0.0036306423,0.00008660329],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22855736,0.00012456019,0.0011532047,0.00071749825,0.000043784636,0.000007314886,0.00042679088,0.0001808043,0.0013655312],"category_scores_gemma":[0.71255326,0.00008412467,0.00010535922,0.002900389,0.00079659047,0.000075533615,0.0003294905,0.00059127633,0.0000014321055],"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":[0.002015477,0.00901151,0.025978519,0.0017366784,0.011877075,0.00023823138,0.13118507,0.0104617,0.026018176,0.25491515,0.0005169568,0.5260455],"study_design_scores_gemma":[0.00092925155,0.0008536815,0.009751314,0.00011974012,0.0016902057,0.0000041553594,0.040325556,0.22655338,0.0050430894,0.71459806,0.000013400866,0.00011814424],"about_ca_topic_score_codex":0.00007145682,"about_ca_topic_score_gemma":0.0021441653,"teacher_disagreement_score":0.5259273,"about_ca_system_score_codex":0.00015897359,"about_ca_system_score_gemma":0.0010512241,"threshold_uncertainty_score":0.99954736},"labels":[],"label_agreement":null},{"id":"W3197721016","doi":"10.1002/jrsm.1565","title":"Parametric G‐computation for compatible indirect treatment comparisons with limited individual patient data","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computation; Computer science; Parametric statistics; Econometrics; Statistics; Algorithm; Mathematics","score_opus":0.8280228066436652,"score_gpt":0.6339570443067984,"score_spread":0.1940657623368668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197721016","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":[0.047688764,0.00021580723,0.946629,0.00031299726,0.000056385215,0.0030646168,0.0008853438,0.0004322956,0.0007147834],"genre_scores_gemma":[0.23304045,0.000021588306,0.76370656,0.000013882011,0.000024249008,0.002892051,0.00019957956,0.000059156853,0.000042457723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913964,0.0053967726,0.00050459063,0.00073541177,0.001249973,0.00071683805],"domain_scores_gemma":[0.9394452,0.058547653,0.00028266272,0.0012400714,0.00031482012,0.00016957628],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008945559,0.0002675319,0.0006684144,0.0010665886,0.0009452446,0.00011423979,0.00094912486,0.0000715708,0.00012710779],"category_scores_gemma":[0.011248709,0.00021665804,0.000076546305,0.001993048,0.00017038338,0.00021442708,0.00089384714,0.00047937146,0.0000031527998],"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":[0.0005404515,0.0024616544,0.0010012563,0.00015607134,0.00065893383,0.000017721095,0.0013618439,0.0011823064,0.00076394225,0.006683903,0.01628407,0.96888787],"study_design_scores_gemma":[0.0026997766,0.016703198,0.0019274857,0.00031551236,0.0009838433,0.00009385453,0.012904877,0.27303338,0.2850648,0.30090302,0.10324477,0.0021254884],"about_ca_topic_score_codex":0.00010708099,"about_ca_topic_score_gemma":0.000029192122,"teacher_disagreement_score":0.96676236,"about_ca_system_score_codex":0.00066203024,"about_ca_system_score_gemma":0.00029788815,"threshold_uncertainty_score":0.99707997},"labels":[],"label_agreement":null},{"id":"W3197765782","doi":"10.1101/2021.08.25.21262631","title":"Causal and Associational Language in Observational Health Research: A systematic evaluation","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Advanced Causal Inference Techniques","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; McGill University; AIDS Vancouver; Public Health Ontario; University of Toronto","funders":"","keywords":"Causality (physics); CLARITY; Observational study; Psychology; Interpretation (philosophy); Linguistics; Medicine; Pathology","score_opus":0.6989486828195921,"score_gpt":0.5697149354724764,"score_spread":0.12923374734711568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197765782","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":[0.9882289,0.0021648188,0.004778721,0.001588764,0.00014795663,0.002547894,0.000045825775,0.00014799046,0.00034910176],"genre_scores_gemma":[0.9633488,0.00012153026,0.034414344,0.0001352627,0.000106262276,0.0013496281,0.00029017855,0.000042924097,0.00019107209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9938008,0.0026669917,0.00088080956,0.0005193437,0.0017593328,0.0003727028],"domain_scores_gemma":[0.9951191,0.002953426,0.00050930865,0.00051434303,0.0008121153,0.00009172011],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01580051,0.00021942527,0.00069663004,0.0003387797,0.00009318477,0.00011860717,0.00023616586,0.00027620292,0.00008661358],"category_scores_gemma":[0.018060772,0.00021840936,0.00005906833,0.00034519524,0.00006670851,0.00013882578,0.00049346976,0.0010962276,0.0000039555594],"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":[0.00006259887,0.0018270252,0.19184546,0.24502745,0.00075105386,0.00034027273,0.07492818,0.0006347081,0.0036907787,0.47258964,0.0050858813,0.0032169502],"study_design_scores_gemma":[0.00050999015,0.000073654344,0.09392771,0.023175387,0.000065002394,0.000018802415,0.0034572491,0.012584145,0.00032051172,0.86536074,0.000008941143,0.000497859],"about_ca_topic_score_codex":0.00017528354,"about_ca_topic_score_gemma":0.0011630005,"teacher_disagreement_score":0.3927711,"about_ca_system_score_codex":0.0011682743,"about_ca_system_score_gemma":0.0011361378,"threshold_uncertainty_score":0.99021053},"labels":[],"label_agreement":null},{"id":"W3197852285","doi":"10.1016/j.annepidem.2021.05.028","title":"The reliability of risk of bias tools for nonrandomized studies","year":2021,"lang":"en","type":"article","venue":"Annals of Epidemiology","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":"Université de Montréal","funders":"","keywords":"Medicine; Reliability (semiconductor); Reliability engineering","score_opus":0.7295545469632841,"score_gpt":0.5783653061591613,"score_spread":0.15118924080412288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197852285","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":[0.8438605,0.009727943,0.13845871,0.005740655,0.00019601535,0.0011033888,0.0002774427,0.00006867903,0.00056664104],"genre_scores_gemma":[0.69628334,0.023700366,0.27933162,0.00032734682,0.000052289924,0.00018284678,0.000010692819,0.000020533156,0.00009094073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99587506,0.0020276634,0.00154484,0.00020753495,0.00007663976,0.00026823333],"domain_scores_gemma":[0.75592244,0.24018739,0.0015039924,0.0007060885,0.0016506602,0.000029419902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015874485,0.00012458401,0.0015330159,0.000029787938,0.000047690708,0.0000010974559,0.00020392209,0.00012168935,0.000010834659],"category_scores_gemma":[0.6191733,0.00007514321,0.00039128953,0.00010678062,0.0006512224,0.00006926579,0.00011701798,0.00012171663,3.5678576e-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":[0.0030234854,0.0004450926,0.009295404,0.0010442619,0.0010292666,0.0000010788414,0.0008361646,0.00016989026,0.0035393839,0.9304934,0.026907844,0.023214689],"study_design_scores_gemma":[0.00064176833,0.0002060587,0.0005924449,0.000079263875,0.00006426178,7.858971e-7,0.00033429076,0.000055356333,0.092285834,0.90423423,0.0014474925,0.00005822362],"about_ca_topic_score_codex":0.000022225473,"about_ca_topic_score_gemma":0.000040019433,"teacher_disagreement_score":0.6032988,"about_ca_system_score_codex":0.000007039374,"about_ca_system_score_gemma":0.000056342393,"threshold_uncertainty_score":0.55018115},"labels":[],"label_agreement":null},{"id":"W3198343911","doi":"10.1002/cjs.11772","title":"Optimal multiwave validation of secondary use data with outcome and exposure misclassification","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; University of North Carolina at Chapel Hill; National Institutes of Health; Vanderbilt University; Patient-Centered Outcomes Research Institute","keywords":"Estimator; Computer science; Variance (accounting); Outcome (game theory); Optimal design; Observational study; Data mining; Mathematical optimization; Grid; Resource (disambiguation); Machine learning; Statistics; Mathematics","score_opus":0.31193088679359926,"score_gpt":0.3904439519980124,"score_spread":0.07851306520441315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198343911","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":[0.477311,0.00003069669,0.5199289,0.00014608733,0.000074121825,0.0001584601,0.00226998,0.000022674314,0.0000581268],"genre_scores_gemma":[0.5648977,0.000021721511,0.43482888,0.00001303719,0.000019993871,9.918808e-7,0.00011121616,0.000017340153,0.000089113244],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99908924,0.000040052793,0.00045840742,0.0001038082,0.00016006484,0.0001484182],"domain_scores_gemma":[0.99815226,0.0005096155,0.0004546992,0.00030031792,0.00037082462,0.00021226903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038487362,0.00009395049,0.0002127316,0.00022414413,0.00005104653,0.00004411313,0.0001946884,0.000052273645,0.00003262117],"category_scores_gemma":[0.0014389599,0.00008128312,0.000010704124,0.00014849464,0.0001275735,0.00036230395,0.000021438866,0.0001862632,0.0000012972597],"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":[0.0003197156,0.0001758804,0.44873846,0.0021974812,0.0008225583,0.002548392,0.01193616,0.0017468447,0.0067449505,0.2821741,0.14983898,0.09275646],"study_design_scores_gemma":[0.00793599,0.0053010406,0.5197447,0.0025566928,0.0019070634,0.002083969,0.015787907,0.033737477,0.021785263,0.36242658,0.023639701,0.0030936038],"about_ca_topic_score_codex":0.00027504613,"about_ca_topic_score_gemma":0.0028716652,"teacher_disagreement_score":0.12619929,"about_ca_system_score_codex":0.0000567256,"about_ca_system_score_gemma":0.00047476587,"threshold_uncertainty_score":0.33146295},"labels":[],"label_agreement":null},{"id":"W3198361082","doi":"10.1177/0272989x221121747","title":"A Tutorial on Time-Dependent Cohort State-Transition Models in R using a Cost-Effectiveness Analysis Example","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"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; University of Ottawa; Hospital for Sick Children","funders":"National Institute of Allergy and Infectious Diseases; National Institute on Drug Abuse; National Cancer Institute; Gordon and Betty Moore Foundation","keywords":"Computer science; Probabilistic logic; Transition (genetics); Cohort; Constant (computer programming); Dependency (UML); Code (set theory); State (computer science); Statistics; Algorithm; Mathematics; Artificial intelligence; Programming language","score_opus":0.2636102031350876,"score_gpt":0.304842683778224,"score_spread":0.04123248064313639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198361082","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":[0.52529234,0.0000020224713,0.47391966,0.000001940193,0.000028497707,0.00027597698,0.000016476384,0.00010245421,0.00036065307],"genre_scores_gemma":[0.9978975,0.000017940802,0.0018218199,0.000017707944,0.000021190439,0.000004197183,0.000025681009,0.000023235296,0.0001707299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984523,0.00037063617,0.00019747451,0.0005758958,0.00012491914,0.00027874074],"domain_scores_gemma":[0.9987473,0.0004228122,0.000106257365,0.00045533234,0.00018656295,0.000081768434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045357356,0.00019696819,0.00042036653,0.0003520161,0.00007496864,0.000027826014,0.00014496516,0.00011724584,0.00008551341],"category_scores_gemma":[0.00007428879,0.00023671406,0.00014701358,0.001368719,0.000041735257,0.00040317397,0.00007026645,0.00021633941,0.000012609283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024407782,0.00039593186,0.0024187958,0.00003680346,0.00032193202,0.000633533,0.00024544753,0.9282931,0.0043256073,0.063001,0.0000060120715,0.000077758974],"study_design_scores_gemma":[0.00093718956,0.000078156896,0.00070218486,0.000092141636,0.00056335184,0.00000441984,0.00014799119,0.53224444,0.013761808,0.4510819,0.000007762207,0.00037865798],"about_ca_topic_score_codex":0.0005669805,"about_ca_topic_score_gemma":0.0003601481,"teacher_disagreement_score":0.47260517,"about_ca_system_score_codex":0.00068754936,"about_ca_system_score_gemma":0.00010019114,"threshold_uncertainty_score":0.9652919},"labels":[],"label_agreement":null},{"id":"W3198388524","doi":"10.1093/ije/dyab168.716","title":"465Simplifying the Differences between Causal and Prediction Analyses","year":2021,"lang":"en","type":"article","venue":"International Journal of Epidemiology","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":"Alberta Health Services; University of Calgary","funders":"","keywords":"Presentation (obstetrics); Outcome (game theory); Causal model; Computer science; Regression analysis; Causal inference; Predictive modelling; Process (computing); Multivariable calculus; Variety (cybernetics); Key (lock); Management science; Data science; Econometrics; Artificial intelligence; Machine learning; Medicine; Statistics; Mathematics","score_opus":0.5420566679419827,"score_gpt":0.5551532219223125,"score_spread":0.013096553980329828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198388524","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":[0.6021087,0.0011023101,0.38726074,0.008350365,0.0005859457,0.00005559764,0.000030197838,0.00003570605,0.00047041406],"genre_scores_gemma":[0.9648866,0.0006108419,0.033328336,0.00046492435,0.0006465318,0.0000027981212,0.0000053818358,0.00000750584,0.000047056168],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99821,0.00052978203,0.0007877114,0.0001247838,0.00019076999,0.0001569566],"domain_scores_gemma":[0.9898213,0.008768834,0.00066733547,0.00012162109,0.00055685214,0.0000640506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017981422,0.00009992007,0.00038670996,0.00009849133,0.000052717543,0.000018009234,0.00028505264,0.00008560108,0.000068426714],"category_scores_gemma":[0.014539962,0.00006104074,0.00009744247,0.00006665679,0.0001646906,0.00016505513,0.00011291592,0.00032866347,0.0000010425271],"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":[0.000052388026,0.00006713006,0.7578071,0.000018571867,0.0010624984,0.000116229814,0.0003728691,0.00004297432,0.0044842125,0.19500473,0.0050814953,0.03588985],"study_design_scores_gemma":[0.00017088147,0.00009021039,0.13215087,0.00007857932,0.00008516282,0.0005026479,0.00018119959,0.00013010003,0.0017372285,0.8632761,0.0015307792,0.00006621786],"about_ca_topic_score_codex":0.000012279889,"about_ca_topic_score_gemma":0.000011964293,"teacher_disagreement_score":0.66827136,"about_ca_system_score_codex":0.000059662903,"about_ca_system_score_gemma":0.0000652118,"threshold_uncertainty_score":0.993761},"labels":[],"label_agreement":null},{"id":"W3199775394","doi":"10.1002/sim.9176","title":"Informing power and sample size calculations when using inverse probability of treatment weighting using the propensity score","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":48,"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; Institute of Health Services and Policy Research; 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; Observational study; Weighting; Statistics; Sample size determination; Average treatment effect; Mathematics; Statistic; Homogeneity (statistics); Econometrics; Inverse probability weighting; Medicine","score_opus":0.27352121820347886,"score_gpt":0.4268053675944418,"score_spread":0.15328414939096296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199775394","genre_codex":"empirical","genre_gemma":"methods","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":[0.63930464,0.000026281967,0.35993525,0.00007913205,0.00003506697,0.00039145316,0.00005888864,0.000021099531,0.00014819007],"genre_scores_gemma":[0.290549,0.000014624262,0.70934844,0.00003697678,0.000017523382,0.000005775519,0.0000054238035,0.000010136671,0.000012101364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989145,0.00009439327,0.0004721341,0.00016735637,0.00018598136,0.00016564339],"domain_scores_gemma":[0.99612314,0.0030766635,0.00021925052,0.00030342554,0.00023473619,0.00004278134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00049333076,0.00013290162,0.0003440573,0.00004193483,0.00010841875,0.000008280972,0.000058331796,0.000047212954,0.00008505109],"category_scores_gemma":[0.01181668,0.000087307366,0.000015532449,0.0001764449,0.00034126337,0.00008483298,0.0000903637,0.00013510644,6.9712264e-8],"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":[0.000101631354,0.00046269153,0.22899422,0.001458148,0.000218146,0.00017017948,0.050822597,0.0011626554,0.055536192,0.64835405,0.0002575677,0.012461916],"study_design_scores_gemma":[0.0004726545,0.00014009097,0.002041729,0.00050167285,0.00010731443,0.000029021057,0.0012506566,0.01713863,0.0031151262,0.9750288,0.000047408208,0.00012689961],"about_ca_topic_score_codex":0.0008862511,"about_ca_topic_score_gemma":0.0010572418,"teacher_disagreement_score":0.34941316,"about_ca_system_score_codex":0.00027655053,"about_ca_system_score_gemma":0.0001861297,"threshold_uncertainty_score":0.9965072},"labels":[],"label_agreement":null},{"id":"W3200513035","doi":"10.1161/circoutcomes.121.008040","title":"Physician Network Connections Associated With Faster De-Adoption of Dronedarone for Permanent Atrial Fibrillation","year":2021,"lang":"en","type":"article","venue":"Circulation Cardiovascular Quality and Outcomes","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Tellabs (Canada)","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; Agency for Healthcare Research and Quality; National Heart, Lung, and Blood Institute; U.S. Food and Drug Administration; National Institute on Aging","keywords":"Dronedarone; Medicine; Medicaid; Quarter (Canadian coin); Atrial fibrillation; Emergency medicine; Family medicine; Medicare Part D; Medical emergency; Internal medicine; Amiodarone; Health care; Medical prescription; Nursing; Prescription drug","score_opus":0.1398828730401273,"score_gpt":0.37954967021984265,"score_spread":0.23966679717971534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200513035","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":[0.43819106,0.00037602553,0.5606012,0.00014418788,0.00006487862,0.00039486695,0.000025060082,0.00009798111,0.00010477853],"genre_scores_gemma":[0.98784906,0.00003508342,0.011661962,0.000057171634,0.0001784388,0.00001726932,0.00015437929,0.000020988646,0.000025634616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986056,0.0003172275,0.0003855646,0.00023124658,0.0002832034,0.00017712174],"domain_scores_gemma":[0.9983062,0.0007612934,0.0002275243,0.0003098047,0.00035510378,0.00004005171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010622608,0.00013726635,0.0005426921,0.000036084544,0.00014307274,0.00002586833,0.000033017768,0.000118745906,0.000003501147],"category_scores_gemma":[0.0007259724,0.0001304612,0.0005457621,0.00017096695,0.000057292465,0.00016912234,0.000021029806,0.00007097672,3.4242416e-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":[0.00019073489,0.00013217276,0.3239066,0.00092861487,0.008615407,0.0000062002205,0.001863205,0.15985072,0.0018789391,0.46923214,0.0001195943,0.033275664],"study_design_scores_gemma":[0.0027529907,0.000096136835,0.71035665,0.00021891529,0.001520727,0.000014465335,0.00060228596,0.003423453,0.0013580982,0.27825946,0.00085304334,0.00054376805],"about_ca_topic_score_codex":0.000011039154,"about_ca_topic_score_gemma":0.000027966644,"teacher_disagreement_score":0.549658,"about_ca_system_score_codex":0.00011138461,"about_ca_system_score_gemma":0.000057957644,"threshold_uncertainty_score":0.5320053},"labels":[],"label_agreement":null},{"id":"W3201688646","doi":"10.1257/aer.20230039","title":"Treatment Effects in Market Equilibrium","year":2025,"lang":"en","type":"preprint","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","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":"Booth University College","funders":"","keywords":"Estimator; Economics; Econometrics; Sensitivity (control systems); Consistency (knowledge bases); Market price; Microeconomics; Mathematics; Statistics","score_opus":0.0823559128946701,"score_gpt":0.4248523175273293,"score_spread":0.34249640463265923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201688646","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023544041,0.28780067,0.013142493,0.008366901,0.0022907134,0.028454907,0.00061584054,0.0028459607,0.63293844],"genre_scores_gemma":[0.013456022,0.8390592,0.12825617,0.0029946507,0.00023359273,0.007541097,0.00010563553,0.00017044261,0.008183227],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976938,0.0003154222,0.0008920642,0.0006906391,0.000058351256,0.0003497177],"domain_scores_gemma":[0.99665385,0.0011261324,0.0007824621,0.001342269,0.000018456061,0.00007680939],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036392317,0.0005140038,0.0021240346,0.00015305643,0.000011320471,0.000022915507,0.0004852211,0.00010293543,0.00020063348],"category_scores_gemma":[0.00033297006,0.00046937892,0.00032818023,0.00010600271,0.00014968966,0.00006316212,0.0005459618,0.00034180767,0.00006879492],"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":[0.000022878075,0.0002200532,0.0010063783,0.028282817,0.0002972987,0.000049665505,0.00008081007,0.000022650805,0.000007203402,0.023003167,0.04808217,0.8989249],"study_design_scores_gemma":[0.0007961713,0.0007886507,0.0007933401,0.07135724,0.0009723863,0.000028755756,0.000032682805,0.0011043183,0.00057761354,0.6664294,0.2546656,0.0024538056],"about_ca_topic_score_codex":0.00040251744,"about_ca_topic_score_gemma":0.00013740243,"teacher_disagreement_score":0.8964711,"about_ca_system_score_codex":0.0015290508,"about_ca_system_score_gemma":0.00034991716,"threshold_uncertainty_score":0.99977577},"labels":[],"label_agreement":null},{"id":"W3203445629","doi":"10.1002/sim.9718","title":"Causal inference in survival analysis using longitudinal observational data: Sequential trials and marginal structural models","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"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":"Medical Research Council; Medical Research Council Canada; Norges Forskningsråd; UK Research and Innovation","keywords":"Marginal structural model; Causal inference; Censoring (clinical trials); Observational study; Inverse probability; Econometrics; Computer science; Confounding; Inference; Statistics; Inverse probability weighting; Propensity score matching; Mathematics; Artificial intelligence; Bayesian probability","score_opus":0.7073736049282677,"score_gpt":0.5705797811041333,"score_spread":0.1367938238241344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203445629","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":[0.24767403,0.00004575757,0.7505701,0.00012610527,0.00017927511,0.0002800882,0.0009895056,0.000082205195,0.00005292067],"genre_scores_gemma":[0.7270468,0.00012839466,0.27141932,0.00002097382,0.00015583813,0.000014460527,0.0011592152,0.000021357559,0.00003364898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99695253,0.0003843319,0.0011318417,0.0004999684,0.00065166986,0.00037966174],"domain_scores_gemma":[0.9931491,0.005783044,0.0003308528,0.00048393232,0.00016535996,0.00008769291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004174677,0.00024656198,0.0011087147,0.0007512901,0.000065037435,0.000029606785,0.00032157614,0.00010565278,0.00015450518],"category_scores_gemma":[0.010837155,0.00021329035,0.000023995035,0.0015556748,0.00030651884,0.0003812445,0.0003036279,0.00037010535,9.670483e-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":[0.00014343491,0.000034387773,0.13504769,0.0002164611,0.00031099853,0.00037380782,0.0009862526,0.013103762,0.0008635785,0.8466038,0.0005921561,0.0017236749],"study_design_scores_gemma":[0.00053960714,0.00003869819,0.03018978,0.00008903783,0.00024117329,0.0000031221323,0.00017541413,0.4083308,0.000011053978,0.56023115,0.0000033789806,0.00014674877],"about_ca_topic_score_codex":0.00089562876,"about_ca_topic_score_gemma":0.003204427,"teacher_disagreement_score":0.47937277,"about_ca_system_score_codex":0.0001443739,"about_ca_system_score_gemma":0.00014277278,"threshold_uncertainty_score":0.997495},"labels":[],"label_agreement":null},{"id":"W3204186164","doi":"10.1016/j.simpa.2021.100147","title":"InteractionR: An R package for full reporting of effect modification and interaction","year":2021,"lang":"en","type":"article","venue":"Software Impacts","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Fonds de Recherche du Québec - Santé","keywords":"Bootstrapping (finance); Multiplicative function; Delta method; Percentile; R package; Interaction; Computer science; Confidence interval; Variance (accounting); Scale (ratio); Variance components; Additive model; Simple (philosophy); Econometrics; Statistics; Data mining; Mathematics; Machine learning; Estimator","score_opus":0.20723313807223007,"score_gpt":0.4870284351868094,"score_spread":0.2797952971145793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204186164","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":[0.600921,0.000022709695,0.39845267,0.00004100126,0.000078644145,0.00023128979,0.000010056417,0.00019384199,0.000048786707],"genre_scores_gemma":[0.8694557,0.000011326173,0.13032462,0.000022622718,0.000041574993,0.000044664765,0.00004577154,0.000024168026,0.000029585355],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988163,0.00007140981,0.0006486797,0.00021145963,0.00010403826,0.00014810023],"domain_scores_gemma":[0.9970779,0.0011117578,0.0010998677,0.00033194103,0.00030575955,0.00007281897],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00060352904,0.00012118316,0.00027443215,0.000066143904,0.0000520989,0.000036467834,0.00004687798,0.00007698632,0.000018304252],"category_scores_gemma":[0.022662777,0.0001116486,0.000060521386,0.00009596845,0.000025517003,0.00058308156,0.000031524567,0.00012010663,9.1562606e-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":[0.0003436443,0.00027538004,0.005910903,0.0015448377,0.000093312825,0.000021255672,0.002092017,0.000014328591,0.8532423,0.0056978273,0.001034365,0.12972987],"study_design_scores_gemma":[0.00031158156,0.0006999281,0.002278128,0.00038231618,0.000065545544,0.00014503059,0.00036359773,0.00030974258,0.84785277,0.147233,0.00016319574,0.00019516885],"about_ca_topic_score_codex":0.000011781156,"about_ca_topic_score_gemma":0.000030946525,"teacher_disagreement_score":0.26853466,"about_ca_system_score_codex":0.00007377541,"about_ca_system_score_gemma":0.00004173377,"threshold_uncertainty_score":0.9855698},"labels":[],"label_agreement":null},{"id":"W3204441930","doi":"10.1080/01621459.2023.2216909","title":"An Automated Approach to Causal Inference in Discrete Settings","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"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; Office of Naval Research; University of Pennsylvania; York University; National Institutes of Health; National Science Foundation; Yale University; Carnegie Corporation of New York","keywords":"Causal inference; Computer science; Inference; Range (aeronautics); Algorithm; Causal model; Mathematical optimization; Mathematics; Artificial intelligence; Econometrics; Statistics","score_opus":0.055280762557961514,"score_gpt":0.44274617951837264,"score_spread":0.38746541696041115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204441930","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":[0.6105485,0.0000011263064,0.38654736,0.001743182,0.000101334874,0.0002675848,0.00008411939,0.0003581121,0.00034868286],"genre_scores_gemma":[0.8750437,0.000004263555,0.12452716,0.00026449934,0.000054434688,0.000010707857,0.00000510313,0.000019146093,0.00007101691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99800235,0.0003877178,0.00057644845,0.00013492837,0.00059837935,0.00030016835],"domain_scores_gemma":[0.99611634,0.0023077058,0.0010510221,0.00018840104,0.00022237063,0.00011417412],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014412228,0.00012215176,0.0003943974,0.0001710378,0.000056804023,0.00004945776,0.0003366345,0.000044243152,0.0000053879107],"category_scores_gemma":[0.012434778,0.00008593606,0.00005074092,0.0010696794,0.00006145709,0.00019666179,0.000075515185,0.0003683943,0.000010581613],"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":[0.0006222545,0.0017874946,0.28144467,0.00025039449,0.00046281065,0.000136457,0.010617008,0.0120061375,0.0391029,0.44006005,0.17564507,0.03786475],"study_design_scores_gemma":[0.00047163127,0.0008515734,0.47370815,0.00017004726,0.0000938455,0.000013743128,0.0013208893,0.06992278,0.0010005613,0.4517317,0.00029255432,0.00042249067],"about_ca_topic_score_codex":0.000057617395,"about_ca_topic_score_gemma":0.000018014762,"teacher_disagreement_score":0.26449516,"about_ca_system_score_codex":0.0005731118,"about_ca_system_score_gemma":0.000083064406,"threshold_uncertainty_score":0.9958839},"labels":[],"label_agreement":null},{"id":"W3206008197","doi":"10.1002/pds.5372","title":"A systematic, concept‐based method of developing the exposure measure for drug safety and effectiveness studies","year":2021,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; McGill University; Vancouver Coastal Health; Vancouver Coastal Health Research Institute; International Collaboration On Repair Discoveries; University of British Columbia","funders":"Michael J. Fox Foundation for Parkinson's Research","keywords":"Medicine; Measure (data warehouse); Drug; Pharmacoepidemiology; Risk analysis (engineering); Computer science; Pharmacology; Data mining","score_opus":0.30367479372413136,"score_gpt":0.5431034091767329,"score_spread":0.23942861545260158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206008197","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":[0.000001193133,0.60620046,0.39005092,0.00026050172,0.00015854707,0.0030841348,0.00014228692,0.00008346515,0.00001847188],"genre_scores_gemma":[0.00006733056,0.89045775,0.10754484,0.00022063458,0.00009003375,0.0014636837,0.000051460982,0.00007011849,0.000034130837],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9785978,0.017463727,0.0024538385,0.0008100993,0.00018739875,0.00048712682],"domain_scores_gemma":[0.8485108,0.1486703,0.001737845,0.00049005274,0.00050490827,0.00008608146],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025462594,0.00082329585,0.0075200093,0.00012739172,0.00039474544,0.000011257211,0.00039676423,0.00037931048,0.0000070368433],"category_scores_gemma":[0.022491949,0.00048942387,0.0005840882,0.00027745424,0.00057292584,0.00010392461,0.0003213324,0.00075992115,4.6540524e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018277983,0.000052205774,0.000019658617,0.70391303,0.0035255728,0.0000084566955,0.0011815155,0.000013794436,0.0000066016883,0.13895646,0.0009864974,0.1511534],"study_design_scores_gemma":[0.003667034,0.00019720147,0.000011877178,0.5910025,0.02171068,0.00038462062,0.0022409258,0.00048343473,0.0011325146,0.1267566,0.24962978,0.0027828212],"about_ca_topic_score_codex":0.000008280463,"about_ca_topic_score_gemma":0.000011635861,"teacher_disagreement_score":0.2842573,"about_ca_system_score_codex":0.00018765304,"about_ca_system_score_gemma":0.00034541433,"threshold_uncertainty_score":0.99975574},"labels":[],"label_agreement":null},{"id":"W3206852087","doi":"10.1097/j.pain.0000000000002506","title":"Compliance with telephone-based lifestyle weight loss programs improves low back pain but not knee pain outcomes: complier average causal effects analyses of 2 randomised trials","year":2021,"lang":"en","type":"article","venue":"Pain","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"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":"Medicine; Physical therapy; Osteoarthritis; Confidence interval; Randomized controlled trial; Weight loss; Back pain; Knee pain; Low back pain; Psychological intervention; WOMAC; Body mass index; Obesity; Internal medicine; Alternative medicine","score_opus":0.1410671350934605,"score_gpt":0.39632775365511175,"score_spread":0.2552606185616513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206852087","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":[0.052606814,0.00015778429,0.9427961,0.00029985118,0.000088166,0.0032919783,0.00006363621,0.0004991272,0.00019654859],"genre_scores_gemma":[0.78574723,0.000017561006,0.21115784,0.001268892,0.00010394658,0.00086178165,0.00015331036,0.00014022966,0.0005492316],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9843577,0.011629685,0.0016616865,0.0007915128,0.00076644594,0.0007929805],"domain_scores_gemma":[0.9548109,0.042143486,0.0011418969,0.0011761487,0.0004754042,0.00025213818],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02275058,0.0007467206,0.0026852726,0.00017958027,0.0001344183,0.00010571257,0.00042120373,0.00026998145,0.00018462581],"category_scores_gemma":[0.029146012,0.00054960867,0.0005507914,0.00065750995,0.0003700031,0.00017953476,0.00009789135,0.00043872648,0.00002305671],"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":[0.011335766,0.0072031403,0.040210944,0.023302404,0.0040414818,0.0015019062,0.0012431344,0.0006076891,0.73710054,0.0039128014,0.005537217,0.16400297],"study_design_scores_gemma":[0.034220885,0.0019352419,0.00064228894,0.0042127203,0.00051386916,0.000014855066,0.00024827523,0.028576154,0.9092477,0.017993892,0.00059356645,0.0018005705],"about_ca_topic_score_codex":0.00007976675,"about_ca_topic_score_gemma":0.00009728987,"teacher_disagreement_score":0.7331404,"about_ca_system_score_codex":0.00014900215,"about_ca_system_score_gemma":0.0003011005,"threshold_uncertainty_score":0.99969554},"labels":[],"label_agreement":null},{"id":"W3207022311","doi":"10.1007/978-3-030-72437-5_5","title":"A Review of Multiply Robust Estimation with Missing Data","year":2021,"lang":"en","type":"review","venue":"Emerging topics in statistics and biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Ottawa","funders":"","keywords":"Imputation (statistics); Missing data; Weighting; Propensity score matching; Robustness (evolution); Computer science; Statistics; National Health and Nutrition Examination Survey; Econometrics; Data mining; Mathematics; Medicine; Population","score_opus":0.34760909233140475,"score_gpt":0.5043437967085805,"score_spread":0.1567347043771758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207022311","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":[3.0230193e-8,0.54759234,0.44953266,0.000024899624,0.000049567017,0.00037771746,0.0023364539,0.00002218876,0.000064103995],"genre_scores_gemma":[6.2140465e-8,0.5082614,0.4897445,0.000028859537,0.00002492839,0.000014320646,0.0018648128,0.000035838184,0.000025303978],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971833,0.00021426604,0.0013851771,0.00058614195,0.00033631022,0.00029478595],"domain_scores_gemma":[0.9956074,0.0019400173,0.0010295875,0.001060771,0.00028009986,0.0000821634],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069950754,0.0004713575,0.0020379461,0.00017736245,0.000063712934,0.00004827522,0.00042836287,0.00018341825,0.000053850723],"category_scores_gemma":[0.0047273715,0.00038880252,0.000044191842,0.0004384119,0.00019005926,0.0000970324,0.00039687776,0.00049476465,5.594187e-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":[0.0000011118427,0.000046904923,0.000002801375,0.16397779,0.00005155531,0.000070692055,0.00003482981,0.0000012511521,3.7809865e-8,0.06215988,0.0060015474,0.7676516],"study_design_scores_gemma":[0.0001764363,0.00008840038,0.0000014077863,0.38732356,0.0011866655,0.00008053684,0.000026957323,0.0059211575,9.640601e-7,0.038812824,0.56570905,0.00067205855],"about_ca_topic_score_codex":0.000031240044,"about_ca_topic_score_gemma":0.00005799082,"teacher_disagreement_score":0.7669796,"about_ca_system_score_codex":0.000085280095,"about_ca_system_score_gemma":0.000366301,"threshold_uncertainty_score":0.9998564},"labels":[],"label_agreement":null},{"id":"W3208637463","doi":"10.33137/utjph.v2i2.36827","title":"Evaluating the Impact of Alcohol Control Interventions on Suicide Mortality Rates","year":2021,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","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":"Centre for Addiction and Mental Health; Public Health Ontario; University of Toronto","funders":"","keywords":"Psychological intervention; Demography; Suicide prevention; Medicine; Poison control; Injury prevention; Excise; Intervention (counseling); Unemployment; Mortality rate; Environmental health; Gerontology; Psychiatry; Economics; Surgery","score_opus":0.543377495980509,"score_gpt":0.5646551700270969,"score_spread":0.02127767404658787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208637463","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":[0.88107014,0.0009792458,0.113350876,0.0024336108,0.000097053104,0.00030247838,0.000068460955,0.000025122134,0.0016730422],"genre_scores_gemma":[0.9876107,0.00020543969,0.011993101,0.00004250735,0.000025158686,1.10384136e-7,0.0000019779284,0.000006483396,0.00011449808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9979625,0.00081355317,0.0005576254,0.00009061105,0.00036926815,0.0002064625],"domain_scores_gemma":[0.99624205,0.0007288971,0.0015033638,0.000288246,0.0010814092,0.00015604113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003918121,0.00009666358,0.00045784182,0.000050526636,0.0001122334,0.000012579575,0.0003175105,0.00004635653,0.0006983482],"category_scores_gemma":[0.0019438256,0.00007351696,0.0004614803,0.00007694879,0.000105363935,0.00041342241,0.000056138244,0.00021060141,4.2179383e-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":[0.0015025532,0.013039984,0.1691996,0.0034812673,0.011162376,0.0002915425,0.046797734,0.0034871288,0.029143779,0.43128625,0.043652944,0.24695484],"study_design_scores_gemma":[0.012337447,0.023432534,0.71393573,0.0053526415,0.00083711586,0.00027992428,0.049477316,0.0051544253,0.0030695659,0.18446094,0.00078319485,0.00087913213],"about_ca_topic_score_codex":0.00524531,"about_ca_topic_score_gemma":0.0032373546,"teacher_disagreement_score":0.54473615,"about_ca_system_score_codex":0.0008229732,"about_ca_system_score_gemma":0.0011900052,"threshold_uncertainty_score":0.7929374},"labels":[],"label_agreement":null},{"id":"W3208912526","doi":"10.1002/cjs.11734","title":"Causal inference for multiple treatments using fractional factorial designs","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Division of Graduate Education; NIH Office of the Director; Faculty of Arts and Sciences","keywords":"Fractional factorial design; Factorial experiment; Causal inference; Factorial; Observational study; Plackett–Burman design; Inference; Design of experiments; Statistics; Computer science; Main effect; Mathematics; Regression; Artificial intelligence; Response surface methodology","score_opus":0.33946401693582756,"score_gpt":0.42734990250249033,"score_spread":0.08788588556666277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208912526","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":[0.017601168,0.000022368393,0.97827286,0.000024033418,0.00085407816,0.00023445215,0.0029380254,0.000012298867,0.000040737865],"genre_scores_gemma":[0.5710195,0.0000024846738,0.4286189,0.000034582787,0.00019036127,0.000015140567,0.000026441463,0.000025190559,0.000067397326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998846,0.000070586764,0.000427806,0.000103476996,0.00026040137,0.00029172376],"domain_scores_gemma":[0.9972396,0.001493298,0.0004410626,0.000113665854,0.00038145532,0.00033092962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026239362,0.00013656862,0.00024598732,0.00021499472,0.00040133792,0.00003827287,0.00019028335,0.00004504261,0.00043024326],"category_scores_gemma":[0.002174371,0.00014249141,0.00005731902,0.00010400202,0.000060942293,0.00015287947,0.000016797612,0.00028385688,7.7375523e-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":[0.00065112085,0.00051732577,0.03838066,0.0002017681,0.0010384064,0.0014792227,0.0048607546,0.013041421,0.009476266,0.810068,0.104198605,0.016086424],"study_design_scores_gemma":[0.0014084994,0.0011093597,0.00055523514,0.00003942408,0.00021792807,0.0002473443,0.00048434606,0.0055329306,0.00096633163,0.97422326,0.014847694,0.00036768056],"about_ca_topic_score_codex":0.0013296321,"about_ca_topic_score_gemma":0.0038873358,"teacher_disagreement_score":0.55341834,"about_ca_system_score_codex":0.00104275,"about_ca_system_score_gemma":0.0021205703,"threshold_uncertainty_score":0.5810631},"labels":[],"label_agreement":null},{"id":"W3209944773","doi":"10.1111/rssa.12716","title":"Propensity Score Analysis for a Semi-Continuous Exposure Variable: A Study of Gestational Alcohol Exposure and Childhood Cognition","year":2021,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":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 Waterloo","funders":"Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers; National Institute on Alcohol Abuse and Alcoholism; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Covariate; Statistics; Observational study; Econometrics; Instrumental variable; Regression analysis; Regression; Linear regression; Mathematics","score_opus":0.06640264768141525,"score_gpt":0.33270834563667184,"score_spread":0.2663056979552566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209944773","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":[0.28603074,0.00014874428,0.711301,0.000117078336,0.00009600403,0.00075320766,0.0014971646,0.000021026237,0.00003499184],"genre_scores_gemma":[0.5462708,0.00007308242,0.45327675,0.000094838426,0.000059501217,0.000038655508,0.000038578266,0.000027510145,0.00012029284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970081,0.00028737358,0.001279854,0.00032841275,0.00075179164,0.00034447777],"domain_scores_gemma":[0.9942552,0.0026976287,0.0010474798,0.00028685806,0.0015910161,0.00012183133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011118855,0.00029616893,0.001006358,0.000037929858,0.00025344637,0.00009199169,0.00026159987,0.00019899277,0.000070197384],"category_scores_gemma":[0.0031304788,0.00023124483,0.00034601745,0.0007441374,0.00035978848,0.00017550793,0.00020311869,0.0006499671,1.01222284e-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":[0.0014179696,0.0132322665,0.39195213,0.0035833495,0.017910404,0.00024826394,0.050657682,0.006440209,0.0021916458,0.46499348,0.03987409,0.007498524],"study_design_scores_gemma":[0.0053145015,0.0024132899,0.21173331,0.00041382643,0.0050231824,0.00009311182,0.016462179,0.0046241987,0.00061416737,0.7525219,0.00014581783,0.0006405475],"about_ca_topic_score_codex":0.000021955715,"about_ca_topic_score_gemma":0.00013911765,"teacher_disagreement_score":0.2875284,"about_ca_system_score_codex":0.0001537253,"about_ca_system_score_gemma":0.00035348034,"threshold_uncertainty_score":0.94298905},"labels":[],"label_agreement":null},{"id":"W3210110199","doi":"10.1111/biom.13776","title":"Combining Parametric and Nonparametric Models to Estimate Treatment Effects in Observational Studies","year":2022,"lang":"en","type":"article","venue":"Biometrics","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observational study; Nonparametric statistics; Econometrics; Parametric statistics; Statistics; Semiparametric model; Semiparametric regression; Mathematics; Computer science","score_opus":0.49491503928947006,"score_gpt":0.49405273154595414,"score_spread":0.0008623077435159221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210110199","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":[0.9339429,0.0024910886,0.061567083,0.00015181361,0.00017376828,0.001116273,0.000029844621,0.0002703312,0.00025688118],"genre_scores_gemma":[0.7752811,0.00018123945,0.22367875,0.00009743234,0.000009694009,0.0006205888,0.000008580881,0.000026883887,0.00009577777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983234,0.00011508668,0.0003890773,0.00037125463,0.00047073502,0.00033047248],"domain_scores_gemma":[0.99395853,0.005424869,0.00014631909,0.00026811485,0.00010199698,0.00010016684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000666517,0.0002249587,0.00047360637,0.0051299287,0.00016613005,0.000034153567,0.00017914924,0.00004925158,0.0000056036247],"category_scores_gemma":[0.003812195,0.00021288838,0.00004405224,0.016580185,0.00004034791,0.00016297908,0.00036779096,0.00014932526,0.0000028081638],"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":[0.00015367355,0.0029272693,0.054997817,0.000650696,0.00035723083,0.0002497906,0.004265597,0.02300282,0.0009735962,0.68780404,0.0017157466,0.2229017],"study_design_scores_gemma":[0.0015501796,0.0029587904,0.011118283,0.000070737915,0.000084624226,0.000025197307,0.00051574386,0.03484055,0.0015000816,0.94572663,0.00091734255,0.00069181906],"about_ca_topic_score_codex":0.000033845274,"about_ca_topic_score_gemma":0.0000064022574,"teacher_disagreement_score":0.2579226,"about_ca_system_score_codex":0.0009260611,"about_ca_system_score_gemma":0.00004467998,"threshold_uncertainty_score":0.8681336},"labels":[],"label_agreement":null},{"id":"W3212311571","doi":"10.1136/bmjopen-2021-052969","title":"Current trends in the application of causal inference methods to pooled longitudinal non-randomised data: a protocol for a methodological systematic review","year":2021,"lang":"en","type":"article","venue":"BMJ Open","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"Institute of Genetics; Canadian Institutes of Health Research; European Commission","keywords":"Causal inference; Medicine; Protocol (science); Causality (physics); Observational study; Data science; MEDLINE; Medical education; Management science; Alternative medicine; Computer science; Pathology","score_opus":0.7630757976314549,"score_gpt":0.6992870156665126,"score_spread":0.06378878196494231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212311571","genre_codex":"methods","genre_gemma":"protocol","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":[0.0000045580155,0.00004928964,0.64840454,0.00034870827,0.000009917263,0.3508818,0.000023824283,0.000022905657,0.0002544887],"genre_scores_gemma":[0.00014684987,0.0000054747134,0.46765837,0.00013168287,0.00001470312,0.5319798,0.00003121319,0.000010412819,0.000021477521],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99475735,0.0027276748,0.0014127084,0.000536422,0.00032224756,0.00024362144],"domain_scores_gemma":[0.990135,0.006583721,0.0007544227,0.002144069,0.00032333157,0.00005942072],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018096456,0.00022825535,0.0014885878,0.000088680215,0.000047036177,0.000072368355,0.0018668353,0.00007469039,0.000039802184],"category_scores_gemma":[0.023513589,0.00013792448,0.0001128232,0.0007975276,0.00003795551,0.0002384277,0.001009784,0.00019603017,0.0000030937708],"study_design_candidate":"systematic_review","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":[0.0027274885,0.001942306,0.00016258835,0.7411922,0.00026855056,0.000023582405,0.0012678779,0.0000140460925,0.0039317473,0.15626533,0.009915384,0.082288876],"study_design_scores_gemma":[0.022112124,0.0014816627,0.00088952255,0.38063017,0.002673445,0.00017763031,0.0006453336,0.010029528,0.018276194,0.5562574,0.004765237,0.0020617386],"about_ca_topic_score_codex":0.000020085687,"about_ca_topic_score_gemma":0.0000791417,"teacher_disagreement_score":0.39999208,"about_ca_system_score_codex":0.000054973654,"about_ca_system_score_gemma":0.00017275664,"threshold_uncertainty_score":0.98471177},"labels":[],"label_agreement":null},{"id":"W3213398770","doi":"10.33137/utjph.v2i2.36762","title":"Performance of statistical methods to address treatment non-adherence in pragmatic clinical trials with point-treatment settings: a simulation study","year":2021,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Instrumental variable; Confounding; Statistics; Inverse probability weighting; Mean squared error; Confidence interval; Marginal structural model; Nonparametric statistics; Average treatment effect; Inverse probability; Econometrics; Mathematics; Propensity score matching; Bayesian probability; Posterior probability","score_opus":0.36324283547822495,"score_gpt":0.5572104845341386,"score_spread":0.19396764905591363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213398770","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":[0.56829363,0.00008444397,0.42983383,0.00047379415,0.000046797675,0.0010028782,0.000030442174,0.000014038024,0.00022013728],"genre_scores_gemma":[0.59788585,0.000178009,0.40185133,0.00001667111,0.000015899814,9.661495e-7,0.0000022584215,0.0000070564092,0.000041964977],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.994292,0.0034154803,0.0014575568,0.00020765756,0.00036776357,0.00025953352],"domain_scores_gemma":[0.9924488,0.0044156048,0.0018245762,0.00029735078,0.0007018136,0.00031186323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009770507,0.00016376899,0.0013934709,0.00011082997,0.000055412966,0.000012124766,0.00018787585,0.000067043875,0.00020283063],"category_scores_gemma":[0.00327963,0.00012875702,0.00011602154,0.00013997464,0.000066816094,0.00044204248,0.00005463229,0.0001328396,4.464286e-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":[0.002517287,0.018680776,0.09211125,0.0008870681,0.0013135263,0.00028185325,0.07031024,0.0022332259,0.00025142074,0.0025000167,0.00041196568,0.80850136],"study_design_scores_gemma":[0.055250067,0.31197846,0.28351426,0.006432959,0.0018379817,0.00021577705,0.28208843,0.0419615,0.0023590648,0.005883963,0.006647068,0.0018304647],"about_ca_topic_score_codex":0.0015318515,"about_ca_topic_score_gemma":0.0051828744,"teacher_disagreement_score":0.8066709,"about_ca_system_score_codex":0.0015875865,"about_ca_system_score_gemma":0.0016955382,"threshold_uncertainty_score":0.5250559},"labels":[],"label_agreement":null},{"id":"W3213843957","doi":"10.3390/e24020179","title":"Normalized Augmented Inverse Probability Weighting with Neural Network Predictions","year":2022,"lang":"en","type":"article","venue":"Entropy","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":"University of Toronto","funders":"","keywords":"Estimator; Weighting; Regularization (linguistics); Computer science; Artificial neural network; Stochastic gradient descent; Parametric statistics; Mathematical optimization; Mathematics; Normalization (sociology); Robustness (evolution); Algorithm; Artificial intelligence; Statistics","score_opus":0.0720494997390497,"score_gpt":0.326328666726839,"score_spread":0.2542791669877893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213843957","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":[0.81747246,0.00004702797,0.17341542,0.0005951963,0.00035799295,0.0017111655,0.000051420688,0.0023578936,0.0039914353],"genre_scores_gemma":[0.8270693,0.0000042675365,0.17139642,0.00019597722,0.000150065,0.0006381273,0.000027114667,0.000040017814,0.0004787115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867254,0.00018227575,0.00025980084,0.00023938176,0.0003084929,0.00033749855],"domain_scores_gemma":[0.9991715,0.00017623712,0.00016479423,0.00036073514,0.000054903638,0.000071849536],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002960871,0.00014810184,0.00019038752,0.000039348375,0.0004220091,0.000018441959,0.00017866043,0.000026692544,0.0010326295],"category_scores_gemma":[0.000121814,0.00012723276,0.000052310486,0.00032102634,0.00007297816,0.00015546,0.00019639505,0.00035518224,0.0000047085846],"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":[0.0010792803,0.001239581,0.05021143,0.00017893668,0.0002956119,0.00012841867,0.002452448,0.052247234,0.005668598,0.81597257,0.06906089,0.0014650099],"study_design_scores_gemma":[0.0022224488,0.0011774914,0.0009850117,0.00007230799,0.00017037576,0.00010571999,0.0006250835,0.068370916,0.0024885645,0.90585226,0.01724799,0.00068182615],"about_ca_topic_score_codex":0.000019272871,"about_ca_topic_score_gemma":0.000028378294,"teacher_disagreement_score":0.0898797,"about_ca_system_score_codex":0.00022943733,"about_ca_system_score_gemma":0.000043061576,"threshold_uncertainty_score":0.99988055},"labels":[],"label_agreement":null},{"id":"W3214335189","doi":"10.33137/utjph.v2i2.36761","title":"Comparisons of Propensity Score Methods for Time to Event Outcomes: Evaluation through Simulations and Oral Squamous Cell Carcinoma Case Study","year":2021,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","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":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"","keywords":"Covariate; Propensity score matching; Confounding; Inverse probability weighting; Statistics; Hazard ratio; Proportional hazards model; Observational study; Population; Medicine; Mathematics; Confidence interval","score_opus":0.4349740173307456,"score_gpt":0.5034382312175022,"score_spread":0.06846421388675661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214335189","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":[0.57315767,0.00013845999,0.42528954,0.0005426131,0.000023713374,0.00073653145,0.000022846341,0.00000852856,0.000080066755],"genre_scores_gemma":[0.66721386,0.0000034226348,0.33267227,0.000024278599,0.0000058633086,2.8965545e-7,0.0000022142544,0.000005686313,0.00007212391],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.997957,0.00092507905,0.0005057843,0.0001436504,0.0002905969,0.00017787205],"domain_scores_gemma":[0.99620533,0.00074238545,0.0008136204,0.00023350629,0.001813428,0.00019172723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031720812,0.000108373766,0.00062092644,0.00006327721,0.00014932039,0.000011202266,0.00014199494,0.00004778856,0.00018507587],"category_scores_gemma":[0.0010814887,0.00010640922,0.00009500809,0.00008623026,0.000043845994,0.000485421,0.000112448106,0.00010594442,1.8842331e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009810084,0.02939796,0.34136245,0.004151323,0.0014153685,0.00090596185,0.350855,0.00409258,0.0055482807,0.012968922,0.026118709,0.22220245],"study_design_scores_gemma":[0.041859772,0.04369218,0.2627742,0.0007682733,0.004010024,0.0024988826,0.51340485,0.065612145,0.0058066235,0.038597733,0.018319553,0.0026557487],"about_ca_topic_score_codex":0.003611618,"about_ca_topic_score_gemma":0.007843037,"teacher_disagreement_score":0.2195467,"about_ca_system_score_codex":0.0006764065,"about_ca_system_score_gemma":0.0010118517,"threshold_uncertainty_score":0.545971},"labels":[],"label_agreement":null},{"id":"W40055348","doi":"","title":"Predicting treatment outcome in chemically dependent women: A test of Marlatt and Gordon's Relapse Model.","year":2000,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"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":"Outcome (game theory); Test (biology); Internal medicine; Computer science; Oncology; Medicine; Mathematics; Biology; Mathematical economics","score_opus":0.06697021376643184,"score_gpt":0.30746608093270705,"score_spread":0.24049586716627522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W40055348","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":[0.99674976,0.0000405712,0.00026874326,0.0001393514,0.00001064189,0.00040100492,0.00007478563,0.00012778329,0.0021873727],"genre_scores_gemma":[0.9761597,0.00009991186,0.020706192,0.000022324226,0.000009599447,0.0000036495055,0.0000066033317,0.000030922347,0.0029610833],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982222,0.00008362719,0.00043441678,0.00045048035,0.0003762616,0.00043304835],"domain_scores_gemma":[0.9984655,0.00044430332,0.00029335718,0.0005135601,0.00009445083,0.00018882196],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005959477,0.00028528387,0.0006293455,0.00024274368,0.00012275731,0.000012547125,0.00037634492,0.00028132732,0.00043449065],"category_scores_gemma":[0.0003365673,0.00032296786,0.00011284203,0.000285316,0.0002243813,0.00059919595,0.00020094575,0.00038384565,0.000009291306],"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":[0.0005099313,0.00077503786,0.95105034,0.00021725203,0.000081601254,0.000065515145,0.0064677154,0.00016876325,0.035338756,0.00092372525,0.000013521218,0.004387834],"study_design_scores_gemma":[0.020710804,0.004735087,0.5628033,0.0018236802,0.0007220516,0.00021218044,0.012167914,0.011114649,0.09751756,0.28436142,0.0004363437,0.0033949802],"about_ca_topic_score_codex":0.00008428786,"about_ca_topic_score_gemma":0.00027482212,"teacher_disagreement_score":0.388247,"about_ca_system_score_codex":0.0005986706,"about_ca_system_score_gemma":0.00006900367,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W4200057099","doi":"10.1002/pds.5403","title":"A comparison of confounder selection and adjustment methods for estimating causal effects using large healthcare databases","year":2021,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Jewish General Hospital; McMaster University; Université Laval; Université de Montréal; Programs for Assessment of Technology in Health Research Institute; McMaster University Medical Centre; Impact; McGill University; Centre Hospitalier de l’Université de Montréal; 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; Université Laval","keywords":"Confounding; Propensity score matching; Lasso (programming language); Observational study; Medicine; Statistics; Bayesian probability; Selection bias; Collinearity; Machine learning; Computer science; Econometrics; Data mining; Artificial intelligence; Mathematics","score_opus":0.34295857249468426,"score_gpt":0.6076724006262337,"score_spread":0.2647138281315495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200057099","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":[0.02223119,0.0046358807,0.9719091,0.00034625467,0.00020734894,0.00050606695,0.000052374624,0.00009287153,0.000018901575],"genre_scores_gemma":[0.18692136,0.00026905595,0.81219745,0.00042573552,0.00007301614,0.00004901636,0.000040830546,0.000015891828,0.0000076663255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970203,0.0016650622,0.00061208167,0.00033759527,0.000051018564,0.00031395478],"domain_scores_gemma":[0.9847146,0.014539966,0.00036122874,0.00012760054,0.00016339231,0.00009317564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030162195,0.00018468963,0.0007582941,0.000049940667,0.00019864278,0.0000032116927,0.000043535492,0.000082205086,0.000014321096],"category_scores_gemma":[0.004677681,0.00017223912,0.00004742636,0.00009486938,0.00009097086,0.00012837655,0.00011927731,0.00024501092,1.07570635e-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":[0.00058636075,0.0005587818,0.049085338,0.0082244715,0.00048567573,0.0000060335256,0.0021143472,0.00042811254,0.104582235,0.6702894,0.00200632,0.16163293],"study_design_scores_gemma":[0.0019849727,0.00017459909,0.0021870101,0.00046410642,0.0005071327,0.00010119838,0.0005285213,0.64627117,0.15499072,0.19085667,0.0015030436,0.0004308983],"about_ca_topic_score_codex":0.00006058427,"about_ca_topic_score_gemma":0.000044278604,"teacher_disagreement_score":0.645843,"about_ca_system_score_codex":0.00005719208,"about_ca_system_score_gemma":0.00007109951,"threshold_uncertainty_score":0.70237076},"labels":[],"label_agreement":null},{"id":"W4200191876","doi":"10.1109/embc46164.2021.9629697","title":"Machine Learning Model Validation for Early Stage Studies with Small Sample Sizes","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":39,"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 New Brunswick","funders":"","keywords":"Overfitting; Feature selection; Feature (linguistics); Cross-validation; Selection (genetic algorithm); Sample size determination; Model selection; Sample (material)","score_opus":0.22964225839714317,"score_gpt":0.4107561751219546,"score_spread":0.18111391672481145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200191876","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":[0.24235688,0.00019512813,0.7549245,0.0014452446,0.00035565707,0.00029926788,0.00018674243,0.00009367019,0.0001429613],"genre_scores_gemma":[0.6499213,0.0010720978,0.3460448,0.000108186956,0.00019928168,0.00013124911,0.00017599382,0.00004383753,0.0023032061],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986356,0.00007265009,0.00048682757,0.00033327428,0.0002102536,0.00026139437],"domain_scores_gemma":[0.9968788,0.001501888,0.00027513178,0.0002779984,0.0010254579,0.000040694616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006092218,0.00025494557,0.0004981746,0.00009262127,0.00006625771,0.000013605367,0.00040797287,0.00014977418,0.00007706663],"category_scores_gemma":[0.0034331428,0.0001811637,0.0001283408,0.0002633482,0.00024246266,0.00012996064,0.00014294828,0.00047176442,6.7070454e-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":[0.00041780638,0.00057173613,0.027128136,0.00162077,0.0033121898,0.0000075688845,0.040974032,0.27496907,0.2876745,0.35459307,0.0058634845,0.0028676833],"study_design_scores_gemma":[0.006904878,0.0015553638,0.0012160982,0.0046549058,0.00049786584,0.00004258468,0.011592712,0.51668966,0.09391065,0.34125328,0.019564139,0.002117854],"about_ca_topic_score_codex":0.00012106745,"about_ca_topic_score_gemma":0.00023773458,"teacher_disagreement_score":0.40887964,"about_ca_system_score_codex":0.00010691526,"about_ca_system_score_gemma":0.000096618765,"threshold_uncertainty_score":0.73876417},"labels":[],"label_agreement":null},{"id":"W4200348404","doi":"10.1111/rssc.12533","title":"Ranking Tailoring Variables for Constructing Individualized Treatment Rules: An Application to Schizophrenia","year":2021,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","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":"McGill University","funders":"National Institute of Environmental Health Sciences; National Institute of Mental Health; National Institutes of Health; University of Washington","keywords":"Schizophrenia (object-oriented programming); Ranking (information retrieval); Matching (statistics); Intervention (counseling); Antipsychotic; Medicine; Selection (genetic algorithm); Computer science; Psychiatry; Intensive care medicine; Machine learning","score_opus":0.05566241879820685,"score_gpt":0.35889085328848286,"score_spread":0.30322843449027603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200348404","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":[0.0040880647,0.000024800942,0.99282753,0.00017534482,0.00020744294,0.0006783144,0.0015614966,0.00007634834,0.0003606665],"genre_scores_gemma":[0.054422498,0.000019019923,0.9447857,0.00015017478,0.0002814519,0.00013189347,0.0000611038,0.00006140484,0.000086752814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99750984,0.00012995311,0.0010197992,0.00034293334,0.00054158026,0.00045588444],"domain_scores_gemma":[0.9956062,0.0024161544,0.00075451995,0.00040087602,0.0005733355,0.00024890868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071956124,0.00033511236,0.0007111471,0.000031715535,0.00047753876,0.00018790255,0.00038230713,0.00014356669,0.00008265793],"category_scores_gemma":[0.0015736276,0.00025417728,0.00018119556,0.00019319044,0.00021347949,0.00014565433,0.00015073719,0.00033770216,0.0000027704245],"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":[0.0003616634,0.00017952765,0.00004394561,0.00014403125,0.00028039695,0.0000068486065,0.0012310104,0.00037845442,0.0035019787,0.94140756,0.001781771,0.05068284],"study_design_scores_gemma":[0.0016650688,0.00042380835,0.00014944692,0.00010136649,0.00045555926,0.000046996905,0.0023807005,0.0014639905,0.010210325,0.97863555,0.0040981057,0.00036907848],"about_ca_topic_score_codex":0.000011843591,"about_ca_topic_score_gemma":0.00002626087,"teacher_disagreement_score":0.050334435,"about_ca_system_score_codex":0.00042615904,"about_ca_system_score_gemma":0.00032849386,"threshold_uncertainty_score":0.99999106},"labels":[],"label_agreement":null},{"id":"W4200496182","doi":"10.1017/s0272263121000838","title":"ARE REPLICATION STUDIES INFREQUENT BECAUSE OF NEGATIVE ATTITUDES?","year":2021,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":36,"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":"Replication (statistics); Originality; Empirical research; Psychology; Field (mathematics); Quarter (Canadian coin); Computer science; Biology; Social psychology; Mathematics; Statistics; History","score_opus":0.22446288524017477,"score_gpt":0.4964301856562038,"score_spread":0.271967300416029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200496182","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":[0.9854738,0.011983275,0.0005900154,0.00015930654,0.000120383025,0.00034636093,0.000052419866,0.00014752882,0.0011269036],"genre_scores_gemma":[0.98139715,0.0008528857,0.01668597,0.00039263917,0.00007057967,0.00017592065,0.000018221719,0.00002132199,0.00038530517],"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985727,0.00013787385,0.00052534055,0.00037496944,0.00019593559,0.00019315716],"domain_scores_gemma":[0.9973333,0.0008284457,0.000533828,0.0006674821,0.00061328494,0.000023693066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042464532,0.00018283966,0.00051602593,0.00011383045,0.00006167733,0.000008046334,0.000113378206,0.00007393207,0.00023817424],"category_scores_gemma":[0.0038516247,0.0001698503,0.000065925014,0.00033543477,0.00023395034,0.00023577274,0.00021179483,0.00015605454,0.0000049900495],"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":[0.00032176182,0.0023129536,0.029075613,0.012485166,0.0043085413,0.0021253496,0.3715785,0.00007154506,0.29382735,0.23729242,0.028674284,0.017926477],"study_design_scores_gemma":[0.00071638956,0.00012083466,0.013042547,0.0014995066,0.00008325232,0.000022388582,0.13265371,0.000006374027,0.49069184,0.36070025,0.00008490164,0.00037797767],"about_ca_topic_score_codex":0.0000070097517,"about_ca_topic_score_gemma":0.0005518625,"teacher_disagreement_score":0.2389248,"about_ca_system_score_codex":0.00027885096,"about_ca_system_score_gemma":0.000022644717,"threshold_uncertainty_score":0.69262946},"labels":[],"label_agreement":null},{"id":"W4205116055","doi":"10.1177/0272989x211072858","title":"Prioritizing Research in an Era of Personalized Medicine: The Potential Value of Unexplained Heterogeneity","year":2022,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Institute of Human Development, Child and Youth Health; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Prioritization; Value (mathematics); Key (lock); Precision medicine; Personalized medicine; MEDLINE","score_opus":0.25720169022223494,"score_gpt":0.5324951527152464,"score_spread":0.27529346249301145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205116055","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":[0.8908302,0.00024596887,0.107390545,0.00078325387,0.00012820784,0.00036367038,0.000006128494,0.00004719266,0.00020482196],"genre_scores_gemma":[0.9666851,0.000038307095,0.033012208,0.00011271073,0.00007073782,0.00005122513,0.0000024999933,0.000021943442,0.0000052313467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937968,0.0013327469,0.00086182693,0.00030319527,0.0033782823,0.00032711556],"domain_scores_gemma":[0.99385834,0.0050570583,0.00023238432,0.0005454024,0.00021414764,0.00009269436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010393911,0.00012420706,0.000437721,0.00025726168,0.00022198402,0.000008479947,0.00088117557,0.00009826352,0.0006263176],"category_scores_gemma":[0.007322989,0.00008599912,0.00007918322,0.00081480155,0.0005675345,0.0000899455,0.00072148105,0.0012011853,6.445851e-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":[0.0013869015,0.0009384,0.0028500743,0.00031803787,0.00005330555,0.0006194107,0.0072306823,0.00029353,0.046698343,0.49818987,0.0011696533,0.4402518],"study_design_scores_gemma":[0.0012477329,0.00078580156,0.0018182804,0.0013842604,0.000017826396,0.00008045655,0.0037817792,0.020257372,0.001284181,0.96883637,0.00034650866,0.00015946037],"about_ca_topic_score_codex":0.000051321338,"about_ca_topic_score_gemma":0.00004220555,"teacher_disagreement_score":0.47064647,"about_ca_system_score_codex":0.00013578098,"about_ca_system_score_gemma":0.00015713728,"threshold_uncertainty_score":0.87668306},"labels":[],"label_agreement":null},{"id":"W4205150711","doi":"10.1111/biom.13625","title":"Ultra-High Dimensional Variable Selection for Doubly Robust Causal Inference","year":2022,"lang":"en","type":"article","venue":"Biometrics","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 Toronto","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Causal inference; Covariate; Estimator; Feature selection; Propensity score matching; Computer science; Confounding; Econometrics; Outcome (game theory); Robustness (evolution); Causal model; Inference; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.16438772303541557,"score_gpt":0.38276504830221764,"score_spread":0.21837732526680206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205150711","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":[0.020734578,0.00005263868,0.9763577,0.0000893155,0.00049064244,0.00071143545,0.00023707861,0.0005885129,0.00073812215],"genre_scores_gemma":[0.4981327,0.000005212873,0.49990505,0.00012977261,0.00009766224,0.0004431507,0.00009513865,0.00004471446,0.0011466044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998305,0.000063953514,0.00035547503,0.0003586047,0.0005272406,0.0003897144],"domain_scores_gemma":[0.99753094,0.0015849047,0.00021757999,0.0002638648,0.00031337776,0.000089312685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074272725,0.00019457082,0.00026155057,0.0010400369,0.0004046092,0.00004234606,0.0002746245,0.00010056534,0.00046073162],"category_scores_gemma":[0.0022640065,0.00020074549,0.0000634025,0.004624246,0.000042888303,0.00018607646,0.00013610037,0.00027061318,0.0000067092806],"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":[0.0001374288,0.0007364746,0.0010894994,0.00015075276,0.00008100255,0.0000042529173,0.00009069569,0.005868729,0.04987502,0.8976478,0.03821912,0.0060992306],"study_design_scores_gemma":[0.0013029319,0.0016310317,0.00031745463,0.000025936513,0.00011429107,0.000058154725,0.00005332794,0.008647087,0.041784886,0.9007427,0.044430826,0.00089133554],"about_ca_topic_score_codex":0.000088019915,"about_ca_topic_score_gemma":0.000005875601,"teacher_disagreement_score":0.47739813,"about_ca_system_score_codex":0.00040632614,"about_ca_system_score_gemma":0.00016759345,"threshold_uncertainty_score":0.8186164},"labels":[],"label_agreement":null},{"id":"W4205319590","doi":"10.31219/osf.io/d4brv","title":"R package regmedint: extension of regression-based causal mediation analysis with effect measure modification by covariates","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; Rheumatology Research Foundation; Brigham and Women's Hospital","keywords":"Covariate; Mediation; Measure (data warehouse); Regression analysis; Regression; Econometrics; Extension (predicate logic); Statistics; Computer science; Mathematics; Data mining","score_opus":0.0818531986761899,"score_gpt":0.3891027195687955,"score_spread":0.3072495208926056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205319590","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":[0.05965183,0.00015967707,0.9365945,0.0002715064,0.000106618434,0.0015434321,0.00025653222,0.0007535955,0.00066229916],"genre_scores_gemma":[0.90126944,0.00005022965,0.09536597,0.000036729056,0.000032275053,0.000663848,0.0023143303,0.00008076059,0.00018639908],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959961,0.0006748585,0.0008322394,0.0008744246,0.0013464821,0.00027588158],"domain_scores_gemma":[0.9939755,0.0019794027,0.0015865675,0.0017412357,0.00060716097,0.00011014075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018629386,0.00054688496,0.0012369467,0.000619448,0.00011911821,0.000036454538,0.00047482693,0.00046692565,0.00068225653],"category_scores_gemma":[0.0019018287,0.00038433002,0.00028429457,0.00091867737,0.00012316366,0.00011296736,0.0003030174,0.0008726461,0.0000020508023],"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":[0.0071500866,0.0057513467,0.056048468,0.01464104,0.015319254,0.00016967411,0.0047585205,0.0726368,0.5872725,0.12021089,0.08031956,0.03572181],"study_design_scores_gemma":[0.0019750642,0.0016043858,0.0026379824,0.0015302114,0.007100756,0.0000042397714,0.00035163155,0.08983767,0.71554315,0.17704587,0.00012435885,0.0022446788],"about_ca_topic_score_codex":0.00019230942,"about_ca_topic_score_gemma":0.00005490538,"teacher_disagreement_score":0.84161764,"about_ca_system_score_codex":0.00036072772,"about_ca_system_score_gemma":0.00020029221,"threshold_uncertainty_score":0.9998609},"labels":[],"label_agreement":null},{"id":"W4205396314","doi":"10.1016/j.jclinepi.2022.01.008","title":"Systematic Review Reveals Lack of Causal Methodology Applied to Pooled Longitudinal Observational Infectious Disease Studies","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Canadian Institutes of Health Research","keywords":"Observational study; Causal inference; Confounding; Pooling; Inference; Infectious disease (medical specialty); Meta-analysis; Systematic review; Medicine; Longitudinal study; Disease; MEDLINE; Psychology; Computer science; Pathology; Artificial intelligence; Biology","score_opus":0.9380984862681854,"score_gpt":0.7130274982901617,"score_spread":0.22507098797802372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205396314","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":[0.000013099089,0.96448547,0.030615836,0.00079007965,0.000959323,0.0029317322,0.000060310223,0.000061318424,0.000082863124],"genre_scores_gemma":[0.0000057246843,0.9045109,0.09097643,0.003192309,0.00052856735,0.0005878696,0.000021094631,0.00008053807,0.000096540345],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9327802,0.038805615,0.02630336,0.00077705644,0.0007006602,0.00063308823],"domain_scores_gemma":[0.51459527,0.44530445,0.036736246,0.0014425694,0.0012274384,0.0006940328],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10843333,0.0008090078,0.036601633,0.0004812385,0.000088040186,0.0000049594314,0.0012726976,0.0006482128,0.00027727967],"category_scores_gemma":[0.71964306,0.0005421397,0.0037936557,0.0006995668,0.00044854527,0.00010466445,0.00070965674,0.0027803928,0.000020206358],"study_design_candidate":"systematic_review","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":[0.00009551653,0.000282777,0.00019942454,0.8567486,0.003694094,0.00008658441,0.000017410928,0.000011198451,1.2950957e-7,0.11374917,0.010856416,0.014258679],"study_design_scores_gemma":[0.00029829997,0.0010412993,0.00008114493,0.39539242,0.017924512,0.0003777945,0.000020340683,0.000001497318,8.2338445e-8,0.5345855,0.049764715,0.00051245216],"about_ca_topic_score_codex":0.0000022316858,"about_ca_topic_score_gemma":0.000002992565,"teacher_disagreement_score":0.6112097,"about_ca_system_score_codex":0.00038373956,"about_ca_system_score_gemma":0.0010572718,"threshold_uncertainty_score":0.999703},"labels":[],"label_agreement":null},{"id":"W4206590108","doi":"10.1093/biomet/asab064","title":"Multiplicative effect modelling: the general case","year":2021,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","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","funders":"","keywords":"Mathematics; Categorical variable; Covariate; Statistics; Multiplicative function; Logistic regression; Econometrics; Generalized linear model; Outcome (game theory); Additive model; Poisson regression; Odds; Regression analysis; Population; Demography; Mathematical economics","score_opus":0.24769433042141864,"score_gpt":0.45285682211812733,"score_spread":0.2051624916967087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206590108","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":[0.36222884,0.00050162483,0.634064,0.0002410258,0.00009165853,0.00041587572,0.000033002027,0.00034998887,0.0020740042],"genre_scores_gemma":[0.8091083,0.00004938484,0.18911627,0.00009397484,0.00011186869,0.000107716995,0.000007585219,0.000031427982,0.0013734365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989747,0.00014606988,0.00020731318,0.0002605962,0.00018262744,0.00022872149],"domain_scores_gemma":[0.9975514,0.0015245638,0.00009293875,0.00060689135,0.00016077312,0.000063455685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004083358,0.00015591373,0.00020913428,0.000159021,0.00012979149,0.000040079078,0.00017268871,0.00008856805,0.00006470691],"category_scores_gemma":[0.000976756,0.0001010337,0.00009780851,0.0013579284,0.0000851574,0.00007367078,0.0001243091,0.00017018733,0.00003539895],"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":[0.00013019048,0.0010294926,0.000876197,0.00043790977,0.00061938417,0.008511642,0.0030379335,0.0009094522,0.15510361,0.65082294,0.025771936,0.15274929],"study_design_scores_gemma":[0.0005053548,0.00019733621,0.000013444454,0.000037071142,0.000083514955,0.0015992259,0.00017030745,0.025369994,0.76964915,0.18742308,0.01454135,0.0004101746],"about_ca_topic_score_codex":0.000045556124,"about_ca_topic_score_gemma":0.000008375104,"teacher_disagreement_score":0.6145455,"about_ca_system_score_codex":0.000069894166,"about_ca_system_score_gemma":0.000031238014,"threshold_uncertainty_score":0.41200346},"labels":[],"label_agreement":null},{"id":"W4206712161","doi":"10.1016/j.psyneuen.2021.105514","title":"Self-selection bias in human stress research: a systematic review","year":2021,"lang":"en","type":"review","venue":"Psychoneuroendocrinology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"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 de Montréal","funders":"","keywords":"PsycINFO; Selection (genetic algorithm); Selection bias; Psychology; Publication bias; Social psychology; Attentional bias; Applied psychology; Clinical psychology; Meta-analysis; MEDLINE; Medicine; Computer science; Anxiety; Biology; Psychiatry","score_opus":0.6237328284153115,"score_gpt":0.5838207168140701,"score_spread":0.03991211160124142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206712161","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":[0.0000017140305,0.9908209,0.00015730047,0.00008329313,0.000266511,0.006271481,0.000020135158,0.000766921,0.0016117331],"genre_scores_gemma":[0.0000023832567,0.99102765,0.0030756805,0.0000968143,0.00010483199,0.004858945,0.000055912216,0.0002020969,0.0005756841],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98713404,0.0069997814,0.0026386406,0.0012997651,0.000657961,0.001269786],"domain_scores_gemma":[0.9932357,0.0032602607,0.0010972483,0.001856214,0.0004140788,0.00013647217],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010564022,0.00082424586,0.0062255566,0.0013765029,0.00015477564,0.00006179445,0.0011684204,0.0003166898,0.00014303009],"category_scores_gemma":[0.0049936064,0.0007126466,0.00061453326,0.002391784,0.0001506377,0.00012826426,0.00038995262,0.003062509,0.00013747957],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.104181e-7,0.0003403226,0.0000018757167,0.9501312,0.00013632444,0.0006452645,0.00002084345,1.4078943e-8,5.680781e-7,0.04143804,0.002866627,0.0044181207],"study_design_scores_gemma":[0.00011817682,0.00016651292,1.1850174e-7,0.74539685,0.00095039053,0.001894898,0.000018705885,7.70598e-7,0.0000065790277,0.01452482,0.23642126,0.00050089776],"about_ca_topic_score_codex":0.000014872058,"about_ca_topic_score_gemma":0.00008611974,"teacher_disagreement_score":0.23355463,"about_ca_system_score_codex":0.000516089,"about_ca_system_score_gemma":0.00023104188,"threshold_uncertainty_score":0.99953246},"labels":[],"label_agreement":null},{"id":"W4210433482","doi":"10.1016/j.ejor.2022.01.046","title":"Estimating causal effects with optimization-based methods: A review and empirical comparison","year":2022,"lang":"en","type":"review","venue":"European Journal of Operational Research","topic":"Advanced Causal Inference Techniques","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":"McGill University; HEC Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Causal inference; Inference; Computer science; Covariate; Causal model; Econometrics; Randomized experiment; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.6049499846790904,"score_gpt":0.6345053979722219,"score_spread":0.029555413293131494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210433482","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.179878e-7,0.6005214,0.39777377,0.00014544457,0.00003327463,0.00070332736,0.0000064737583,0.000022486642,0.0007935767],"genre_scores_gemma":[9.848477e-7,0.49430382,0.5053275,0.00008001678,0.00010319285,0.000043183598,0.000020514657,0.00007191756,0.000048843565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98397577,0.012430932,0.001495465,0.00035336264,0.0014111329,0.00033335137],"domain_scores_gemma":[0.9855956,0.011973426,0.00091859436,0.0003530205,0.00093163527,0.00022775227],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016309442,0.0003621499,0.0018335765,0.00051010575,0.0003922216,0.00017858582,0.0006239891,0.00005427901,0.00052121916],"category_scores_gemma":[0.01413939,0.00024490693,0.0001827305,0.00076439226,0.00021375164,0.00021318995,0.00027345467,0.0024093261,0.000006754519],"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":[0.000049136983,0.00039815225,0.0000070717338,0.07838028,0.00042846752,0.00084364583,0.00017791198,0.0055668512,0.000001172161,0.0026825778,0.018493406,0.89297134],"study_design_scores_gemma":[0.00050418486,0.00229745,0.0000012361298,0.07261631,0.0011210622,0.00102454,0.000024530938,0.009369678,0.0000040842647,0.0007103637,0.91175973,0.0005668446],"about_ca_topic_score_codex":6.715823e-7,"about_ca_topic_score_gemma":3.03257e-7,"teacher_disagreement_score":0.8932663,"about_ca_system_score_codex":0.00031308876,"about_ca_system_score_gemma":0.0014110473,"threshold_uncertainty_score":0.9998922},"labels":[],"label_agreement":null},{"id":"W4210609813","doi":"10.1002/sim.9318","title":"Preserving data privacy when using multi‐site data to estimate individualized treatment rules","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Pooling; Robustness (evolution); Data mining; Covariate; Regression; Context (archaeology); Confidentiality; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.5117738302480719,"score_gpt":0.5546970299518682,"score_spread":0.04292319970379632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210609813","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":[0.018249333,0.0001912817,0.9669385,0.0005098828,0.00018353586,0.0011078332,0.012419345,0.00021761621,0.00018270465],"genre_scores_gemma":[0.004022254,0.0000434904,0.9900901,0.00016328445,0.00008012776,0.000086198816,0.005258516,0.0000639212,0.00019214285],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973347,0.00021183505,0.00069005135,0.0007042029,0.00064403453,0.00041516722],"domain_scores_gemma":[0.9949835,0.0013752969,0.0002616292,0.0031769793,0.00006692959,0.00013565901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015452466,0.00027868745,0.0005721751,0.0002570359,0.0002000146,0.000027049618,0.0020565954,0.0000401921,0.00074019714],"category_scores_gemma":[0.006414182,0.0002459992,0.000009034956,0.00025219328,0.00010463068,0.00025320917,0.005207267,0.00030129333,0.000006290182],"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":[0.00083430856,0.0042567947,0.034812562,0.0021475167,0.0010015042,0.0032181386,0.097135544,0.0029113346,0.021259818,0.3288509,0.33390132,0.16967027],"study_design_scores_gemma":[0.0041168146,0.000856064,0.00134198,0.00067482464,0.00044820094,0.00006203958,0.001336235,0.31494668,0.00022137638,0.63328147,0.0419124,0.0008019256],"about_ca_topic_score_codex":0.0010445119,"about_ca_topic_score_gemma":0.000587451,"teacher_disagreement_score":0.31203532,"about_ca_system_score_codex":0.00038367196,"about_ca_system_score_gemma":0.00012680831,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W4210644525","doi":"10.1177/00491241211036165","title":"Moving Beyond Linear Regression: Implementing and Interpreting Quantile Regression Models With Fixed Effects","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":104,"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; Econometrics; Regression; Quantile; Linear regression; Fixed effects model; Regression analysis; Replication (statistics); Range (aeronautics); Wage; Statistics; Computer science; Mathematics; Economics; Panel data","score_opus":0.3809058897593379,"score_gpt":0.5984629512409576,"score_spread":0.21755706148161968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210644525","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":[0.44257948,0.0007950206,0.55120003,0.0005008477,0.00006233161,0.0011318657,0.000009315304,0.0004938741,0.0032272507],"genre_scores_gemma":[0.3745821,0.00004412289,0.62462187,0.000068726775,0.00005229179,0.0004340069,0.0000052893743,0.000035929777,0.00015567546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98928136,0.0077209286,0.00045810983,0.0007311508,0.0008288889,0.000979536],"domain_scores_gemma":[0.98264873,0.016221412,0.00023528162,0.0004894121,0.00023529456,0.00016988225],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014928043,0.0002802134,0.0005758141,0.00020006474,0.0015673981,0.000067668574,0.0005023113,0.00019269796,0.00022468278],"category_scores_gemma":[0.0059415344,0.00017670244,0.00008890225,0.00047411222,0.00052750256,0.0002066949,0.002793104,0.0023765753,0.000001383583],"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":[0.0008989158,0.00042153246,0.0040050256,0.0008593732,0.00014641444,0.0003021974,0.011298617,0.00008812167,0.22497724,0.44001225,0.0022310887,0.31475922],"study_design_scores_gemma":[0.00037162413,0.0012220896,0.000057930567,0.00032895122,0.000016446731,0.000029595261,0.006893532,0.012703054,0.017447684,0.96008366,0.00054190116,0.00030350257],"about_ca_topic_score_codex":0.000021524465,"about_ca_topic_score_gemma":0.0000013343637,"teacher_disagreement_score":0.52007145,"about_ca_system_score_codex":0.00021073276,"about_ca_system_score_gemma":0.000070884795,"threshold_uncertainty_score":0.99992496},"labels":[],"label_agreement":null},{"id":"W4210865241","doi":"10.1177/00491241221077238","title":"Comparing Single- and Multiple-Question Designs of Measuring Family Income in China Family Panel Studies","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Econometrics; Percentile; Economics; Contrast (vision); Quarter (Canadian coin); Demographic economics; Statistics; Mathematics; Geography; Computer science","score_opus":0.9006386086819724,"score_gpt":0.6303685016720665,"score_spread":0.27027010700990595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210865241","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":[0.9205536,0.0019802698,0.075818844,0.00010322638,0.00003650231,0.00061526155,0.0000043699074,0.00016479264,0.00072312367],"genre_scores_gemma":[0.6434115,0.00019278008,0.35617825,0.000013663696,0.000015123928,0.00015849873,0.0000011116231,0.000015285079,0.000013776609],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98836356,0.0093468465,0.0006076172,0.00046369672,0.00064235635,0.0005759034],"domain_scores_gemma":[0.98550427,0.013714969,0.00015939123,0.00030520058,0.00023583298,0.000080351376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021118358,0.00019476158,0.00076007383,0.00032128574,0.00038442106,0.000017238357,0.00038986,0.00014832028,0.000009289399],"category_scores_gemma":[0.014730973,0.0001622769,0.000069980466,0.0005489275,0.00088758604,0.00010607666,0.0013713815,0.0015892797,6.226452e-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":[0.0002946616,0.00060831156,0.067915775,0.0004537399,0.00009721679,0.000044752975,0.0079374015,0.0002661641,0.7837699,0.1047085,0.00003089711,0.033872686],"study_design_scores_gemma":[0.00037142375,0.00074472826,0.07381517,0.00012297365,0.000008917817,0.00000459496,0.010566258,0.0010600998,0.007968342,0.90511626,0.000022241251,0.00019902039],"about_ca_topic_score_codex":0.000100128585,"about_ca_topic_score_gemma":0.0000060802204,"teacher_disagreement_score":0.8004077,"about_ca_system_score_codex":0.00052331114,"about_ca_system_score_gemma":0.000044801793,"threshold_uncertainty_score":0.99356836},"labels":[],"label_agreement":null},{"id":"W4210865417","doi":"10.1038/s41366-021-00981-5","title":"Selection bias: “The unseen enemy is always the most fearsome”","year":2022,"lang":"en","type":"letter","venue":"International Journal of Obesity","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Department of Epidemiology, Biostatistics and Occupational Health, McGill University; University at Buffalo; McGill University; Department of Physiology and Biophysics, University at Buffalo; University of Minnesota","keywords":"Selection (genetic algorithm); Medicine; Psychology; Computer science; Artificial intelligence","score_opus":0.1434234288843806,"score_gpt":0.3891131524901326,"score_spread":0.24568972360575203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210865417","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":[0.010830233,0.00023502596,0.021424461,0.9600694,0.0032614109,0.00056911656,0.00022567813,0.00015949628,0.0032251815],"genre_scores_gemma":[0.03680986,0.0015150497,0.015745891,0.9133912,0.02032077,0.000099296376,0.000107862616,0.00025805543,0.01175207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965422,0.00037494983,0.0007921567,0.00020651001,0.0018345267,0.00024963205],"domain_scores_gemma":[0.9954153,0.0015227941,0.0016783655,0.00033101646,0.0010157567,0.000036789897],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012945727,0.00028970418,0.00038294206,0.0002585222,0.00025619482,0.00018005821,0.00206048,0.00026633946,0.001800895],"category_scores_gemma":[0.00084404025,0.0001766092,0.00035362676,0.0002369405,0.00012495305,0.00035179316,0.0003123096,0.0036216264,0.000020685613],"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":[0.00003031926,0.00006564094,0.0003567509,0.000015295958,0.00038522464,0.000193379,0.00032054356,0.000010897201,0.00007123545,0.0020239477,0.99567336,0.0008533972],"study_design_scores_gemma":[0.00016480815,0.00013324148,0.0002068165,0.000100278936,0.00011650299,0.0010432393,0.000071000075,0.000043953063,0.0013871714,0.1546879,0.8418542,0.000190864],"about_ca_topic_score_codex":0.000066838445,"about_ca_topic_score_gemma":0.00002041436,"teacher_disagreement_score":0.15381914,"about_ca_system_score_codex":0.0005750331,"about_ca_system_score_gemma":0.00025151446,"threshold_uncertainty_score":0.9991116},"labels":[],"label_agreement":null},{"id":"W4210899445","doi":"10.1007/s12561-022-09337-7","title":"Building an External Control Arm for Development of a New Molecular Entity: An Application in a Recurrent Glioblastoma Trial for MDNA55","year":2022,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pharma Medica Research (Canada)","funders":"","keywords":"Randomized controlled trial; Observational study; Medicine; Clinical trial; Selection bias; Protocol (science); Propensity score matching; Drug development; Biostatistics; Medical physics; Physical therapy; Surgery; Alternative medicine; Internal medicine; Drug; Epidemiology; Pathology; Psychiatry","score_opus":0.1136866173941476,"score_gpt":0.4534375624280227,"score_spread":0.3397509450338751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210899445","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":[0.28379613,0.000011717302,0.7144804,0.0000152526945,0.00009592585,0.0013973218,0.0001772253,0.000023127526,0.0000029298842],"genre_scores_gemma":[0.44415352,0.000001041519,0.55504197,0.000012953217,0.000014528117,0.00075830333,0.00000710194,0.0000071708278,0.0000034143538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99844885,0.000070072245,0.00055455347,0.00033134248,0.00034846025,0.00024671547],"domain_scores_gemma":[0.9990009,0.00037565423,0.000312529,0.00017217203,0.00007602814,0.00006269614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012805158,0.00011635263,0.00023908912,0.00023919123,0.00015720612,0.000024719206,0.00038956918,0.00003104364,0.000007883118],"category_scores_gemma":[0.00063685933,0.000110482644,0.000024057026,0.00028958297,0.00007934241,0.00013686034,0.00007996541,0.00009333965,5.727551e-8],"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":[0.0041582547,0.0009937974,0.000110577865,0.000104521016,0.000006063472,0.0000023441103,0.0026410765,0.00019156541,0.03464485,0.82176554,0.000037091464,0.13534433],"study_design_scores_gemma":[0.0059316796,0.0028974183,0.000044143653,0.000034268036,0.000009984362,0.0000010988769,0.00036309622,0.022348281,0.019981742,0.94772404,0.00048915995,0.00017505663],"about_ca_topic_score_codex":0.00003840998,"about_ca_topic_score_gemma":0.000843969,"teacher_disagreement_score":0.16035739,"about_ca_system_score_codex":0.00019011275,"about_ca_system_score_gemma":0.00032083795,"threshold_uncertainty_score":0.45053515},"labels":[],"label_agreement":null},{"id":"W4213070302","doi":"10.1186/s12874-022-01518-8","title":"Analysis approaches to address treatment nonadherence in pragmatic trials with point-treatment settings: a simulation study","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Confounding; Statistics; Instrumental variable; Confidence interval; Nonparametric statistics; Mean squared error; Medicine; Marginal structural model; Type I and type II errors; Point estimation; Selection bias; Causal inference; Econometrics; Mathematics","score_opus":0.9212178228589814,"score_gpt":0.6612591426169402,"score_spread":0.25995868024204116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213070302","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":[0.3108664,0.000069229754,0.6811788,0.0009653579,0.000030793788,0.006306695,0.000029196164,0.00015192968,0.00040158813],"genre_scores_gemma":[0.6650106,0.0000136947465,0.32525206,0.000050201237,0.00005052288,0.009188286,0.000026029225,0.00003313256,0.00037550883],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92941344,0.064639434,0.0013658736,0.0010233097,0.0026173915,0.00094052975],"domain_scores_gemma":[0.82544446,0.17260888,0.00033446582,0.0009739296,0.00017556713,0.00046271976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065930754,0.00031186323,0.0018627167,0.0014144644,0.00025468285,0.00003394751,0.0005799102,0.0001399772,0.0019315638],"category_scores_gemma":[0.11454531,0.00020780631,0.00017899489,0.0027813197,0.00020545529,0.00008293445,0.00046370865,0.00061605213,0.000011849664],"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":[0.019138591,0.045961075,0.13858664,0.00102923,0.009570846,0.0026428874,0.11412028,0.20816734,0.00071927044,0.055148564,0.00074558094,0.40416968],"study_design_scores_gemma":[0.023394933,0.099539965,0.009144852,0.0005194348,0.003750514,0.00011339055,0.15698595,0.2916821,0.0032195533,0.4066758,0.0026265548,0.0023470006],"about_ca_topic_score_codex":0.0011304315,"about_ca_topic_score_gemma":0.00868708,"teacher_disagreement_score":0.4018227,"about_ca_system_score_codex":0.001447624,"about_ca_system_score_gemma":0.0011197077,"threshold_uncertainty_score":0.9989808},"labels":[],"label_agreement":null},{"id":"W4214806201","doi":"10.1097/ede.0000000000001470","title":"Estimands and Estimation of COVID-19 Vaccine Effectiveness Under the Test-Negative Design","year":2022,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":30,"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; McGill University","funders":"","keywords":"Estimator; Inverse probability weighting; Weighting; Counterfactual thinking; Logistic regression; Causal inference; Estimation","score_opus":0.2754382722377738,"score_gpt":0.4829411994696834,"score_spread":0.2075029272319096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214806201","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":[0.0320815,0.00011725892,0.9637283,0.0031893537,0.000038507405,0.0006154603,0.000014077313,0.00013205204,0.00008346695],"genre_scores_gemma":[0.72264916,0.000020141972,0.27607623,0.000874479,0.000011511316,0.00032904703,0.0000022524462,0.000014150293,0.000023009288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99648994,0.0026125435,0.0003876006,0.00023616158,0.00007983814,0.00019388823],"domain_scores_gemma":[0.8296015,0.16953993,0.0003582413,0.00039451563,0.00004461626,0.00006118834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056454227,0.00013540035,0.00045809,0.00007174384,0.00022559178,0.0000020237937,0.0002391997,0.00006278737,0.0001139372],"category_scores_gemma":[0.11058894,0.000095679636,0.000038320883,0.0001779958,0.00017981454,0.000055612356,0.0002769257,0.0002640315,0.0000011134625],"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":[0.0004910533,0.00024784895,0.012642584,0.00043160436,0.00012744119,0.000009750682,0.0012824401,0.17841916,0.0019871127,0.7895019,0.01079224,0.0040668724],"study_design_scores_gemma":[0.00030408282,0.0005740134,0.003621533,0.000012039664,0.00003234119,0.000043581735,0.00015682985,0.02491435,0.001304764,0.9689152,0.00002939346,0.00009185971],"about_ca_topic_score_codex":0.00006738089,"about_ca_topic_score_gemma":0.000005760895,"teacher_disagreement_score":0.6905677,"about_ca_system_score_codex":0.00015364103,"about_ca_system_score_gemma":0.00008163297,"threshold_uncertainty_score":0.8969029},"labels":[],"label_agreement":null},{"id":"W4220656412","doi":"10.1007/s10654-022-00848-7","title":"The Authors Reply","year":2022,"lang":"en","type":"letter","venue":"European Journal of Epidemiology","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","funders":"","keywords":"Medicine; Epidemiology; Public health; Environmental health; Family medicine; Pathology","score_opus":0.3301344712296689,"score_gpt":0.44458047575615944,"score_spread":0.11444600452649056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220656412","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":[0.00003653821,0.0017066468,0.041229904,0.9366354,0.0022364238,0.00019143017,0.000014786842,0.000130649,0.01781825],"genre_scores_gemma":[0.00007114822,0.0013849919,0.08464765,0.8964831,0.007870809,0.000008818715,0.000017511755,0.00023255817,0.00928337],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9758732,0.019484302,0.0031745243,0.00035725159,0.00036018388,0.0007505608],"domain_scores_gemma":[0.96716046,0.026670776,0.0048469324,0.0009803091,0.00024517698,0.000096342905],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030307801,0.00035927902,0.0011414719,0.00019234345,0.00030592596,0.000018254046,0.0017980391,0.00017189815,0.00055569457],"category_scores_gemma":[0.05866989,0.00022012235,0.00052852253,0.00013200233,0.00038528803,0.000078028206,0.00041655687,0.0077297487,0.000039613624],"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":[0.000029244376,0.000007797799,0.000018439925,0.000023114306,0.00010849475,0.0021070417,0.00005517997,0.0000060113284,0.0000045383445,0.011233787,0.9827412,0.0036651571],"study_design_scores_gemma":[0.0000712723,0.00048250234,0.000013309172,0.000055063436,0.000056243996,0.00094871974,0.000020956802,0.000002946021,0.0000033258787,0.29745284,0.7007471,0.00014575168],"about_ca_topic_score_codex":0.0000019813604,"about_ca_topic_score_gemma":4.4228958e-7,"teacher_disagreement_score":0.28621903,"about_ca_system_score_codex":0.00018203924,"about_ca_system_score_gemma":0.00010186692,"threshold_uncertainty_score":0.9985022},"labels":[],"label_agreement":null},{"id":"W4220703773","doi":"10.1093/ije/dyac056","title":"The quintessence of causal DAGs for immortal time bias: time-dependent models","year":2022,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"","keywords":"Quintessence; Causal inference; Causal model; Causality (physics); Medicine; Psychology; Econometrics; Statistics; Mathematics; Physics; Cosmology","score_opus":0.2806987380650897,"score_gpt":0.4695180181210156,"score_spread":0.1888192800559259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220703773","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":[0.088063546,0.0009195136,0.8990774,0.007919301,0.0016655194,0.0005464371,0.000299787,0.000073391224,0.0014350761],"genre_scores_gemma":[0.92321897,0.00015198068,0.07404798,0.0006726705,0.00041537292,0.00008252323,0.00001987056,0.000043223557,0.0013474334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99720615,0.0005732898,0.0014085138,0.00015544191,0.0004087382,0.00024784083],"domain_scores_gemma":[0.98249185,0.014576818,0.0018638923,0.00021545094,0.00079398206,0.00005800153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0061429404,0.00013620853,0.000504096,0.00014790008,0.00010166206,0.000007752155,0.0010924471,0.000058774338,0.00027666838],"category_scores_gemma":[0.011111541,0.00009670001,0.00025258271,0.000058466274,0.0001877677,0.00018556857,0.00028432903,0.0003857418,0.000004086212],"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":[0.0012712398,0.00039874457,0.0010009937,0.000022889575,0.00095545774,0.00007217933,0.00046029573,0.025940584,0.014645641,0.89292336,0.051446784,0.01086183],"study_design_scores_gemma":[0.0003398465,0.0005265034,0.000032449076,0.000033251636,0.0000337218,0.0004948867,0.00011448359,0.029047113,0.001513869,0.9653874,0.0023757748,0.00010068812],"about_ca_topic_score_codex":0.00001824129,"about_ca_topic_score_gemma":0.0000056369013,"teacher_disagreement_score":0.83515537,"about_ca_system_score_codex":0.00020411403,"about_ca_system_score_gemma":0.00012832791,"threshold_uncertainty_score":0.9972183},"labels":[],"label_agreement":null},{"id":"W4220729324","doi":"10.1093/ectj/utac008","title":"Estimation and inference on treatment effects under treatment-based sampling designs","year":2022,"lang":"en","type":"article","venue":"Econometrics Journal","topic":"Advanced Causal Inference Techniques","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 British Columbia","funders":"Japan Society for the Promotion of Science; Social Sciences and Humanities Research Council of Canada","keywords":"Estimator; Population; Inference; Sampling (signal processing); Benchmark (surveying); Sampling design; Computer science; Sample size determination; Statistics; Econometrics; Causal inference; Statistical inference; Sample (material); Mathematics; Artificial intelligence","score_opus":0.5126904252324965,"score_gpt":0.45664355852416116,"score_spread":0.05604686670833536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220729324","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":[0.37831756,0.00017541666,0.62043136,0.00014055385,0.00012481502,0.00031740766,0.000014507691,0.00010152048,0.00037686416],"genre_scores_gemma":[0.90537363,0.00010844798,0.094165266,0.000097376425,0.000038832768,0.0001091021,0.0000072253365,0.000026012238,0.00007410416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989623,0.000118245625,0.0003072065,0.00021121389,0.00016130897,0.00023972205],"domain_scores_gemma":[0.99630606,0.0030418832,0.00029014313,0.00019653195,0.00003322339,0.0001321684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036950503,0.0002117556,0.00029336798,0.00086991116,0.0004503396,0.00011800716,0.000108145956,0.000041351886,0.00018373788],"category_scores_gemma":[0.0005367568,0.00017731109,0.00007819788,0.0004528181,0.00002854603,0.0001692468,0.00003267888,0.00020662615,0.000006646953],"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":[0.00018912011,0.0022179023,0.0069119786,0.00007944213,0.00042105702,0.000102482234,0.00090179866,0.10467209,0.00059713697,0.1264485,0.00020540704,0.7572531],"study_design_scores_gemma":[0.003498095,0.0126525285,0.0026527923,0.00007432819,0.00020515075,0.00019084841,0.0002660397,0.04647751,0.013178654,0.91903967,0.0010644835,0.0006999297],"about_ca_topic_score_codex":0.000005896853,"about_ca_topic_score_gemma":0.0000026255889,"teacher_disagreement_score":0.79259115,"about_ca_system_score_codex":0.0018958749,"about_ca_system_score_gemma":0.00012312211,"threshold_uncertainty_score":0.72305363},"labels":[],"label_agreement":null},{"id":"W4221004841","doi":"10.1002/sim.9364","title":"Assessing complier average causal effects from longitudinal trials with multiple endpoints and treatment noncompliance: An application to a study of Arthritis Health Journal","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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 British Columbia; Research Canada; Simon Fraser University","funders":"National Cancer Institute; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Econometrics; Medicine; Clinical trial; Arthritis; Internal medicine; Economics","score_opus":0.19042324253128365,"score_gpt":0.49042503604727183,"score_spread":0.3000017935159882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221004841","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":[0.4423274,0.00008701205,0.5561706,0.000059558613,0.000049569422,0.0011435171,0.00012997843,0.000022528251,0.00000984962],"genre_scores_gemma":[0.7146567,0.000048164376,0.28488842,0.00004816499,0.00006330235,0.00022636761,0.00004629995,0.00002020987,0.000002384287],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973174,0.0007850514,0.0008549802,0.00031669057,0.00050612236,0.000219811],"domain_scores_gemma":[0.9959835,0.0028297657,0.0006327836,0.0002921132,0.00009631267,0.00016554493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018025095,0.000199066,0.0010076044,0.00017305302,0.00022613308,0.00002253016,0.000120506025,0.000021629758,0.000060978207],"category_scores_gemma":[0.0008876904,0.00015462363,0.000011448372,0.0002019429,0.00008014182,0.00009580535,0.000063863685,0.00027841487,2.7915698e-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":[0.0017824507,0.006795337,0.10802416,0.00029209102,0.0004269247,0.0010502422,0.053241193,0.0012787423,0.008076456,0.013195454,0.0007855359,0.80505145],"study_design_scores_gemma":[0.041278176,0.077840045,0.33386344,0.0023504503,0.0004117771,0.00043126647,0.035399813,0.009346949,0.0020933484,0.49575916,0.00016177217,0.0010638103],"about_ca_topic_score_codex":0.0008284311,"about_ca_topic_score_gemma":0.0016308579,"teacher_disagreement_score":0.8039876,"about_ca_system_score_codex":0.00036607945,"about_ca_system_score_gemma":0.00008964897,"threshold_uncertainty_score":0.63053685},"labels":[],"label_agreement":null},{"id":"W4221019445","doi":"10.1038/s41431-022-01085-y","title":"Correction: Polygenic risk modeling for prediction of epithelial ovarian cancer risk","year":2022,"lang":"en","type":"erratum","venue":"European Journal of Human Genetics","topic":"Advanced Causal Inference Techniques","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":"McGill University; Université Laval; Royal Alexandra Hospital; Public Health Ontario; University of British Columbia; Alberta Health Services; Centre hospitalier universitaire de Québec; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Vancouver General Hospital; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Institute of General Medical Sciences; National Cancer Institute; Medical Research Council","keywords":"Ovarian cancer; Polygenic risk score; Computational biology; Biology; Bioinformatics; Medicine; Oncology; Genetics; Cancer; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.10388592556604903,"score_gpt":0.35782934395434685,"score_spread":0.2539434183882978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221019445","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":[0.015580957,0.0074870395,0.89502645,0.00004367638,0.06383951,0.0012267687,0.0055758,0.00025636927,0.010963453],"genre_scores_gemma":[0.27756393,0.108309835,0.3755829,0.00019419998,0.06896149,0.0002023672,0.0010290705,0.0034109806,0.16474521],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958313,0.00092353823,0.0018950625,0.00032650557,0.0006905298,0.00033306392],"domain_scores_gemma":[0.99373126,0.00022227634,0.004499693,0.00058104197,0.00083245843,0.00013327743],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022860751,0.00042763643,0.0008140552,0.00041522388,0.0004070462,0.00004410816,0.00077672827,0.00016087726,0.0004062156],"category_scores_gemma":[0.00076782884,0.00042120056,0.00054118375,0.00017149476,0.00009436741,0.00009496689,0.00020647036,0.0023743124,0.0000015701455],"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":[0.00024524616,0.00025561987,0.00021151906,0.00034604387,0.0008806976,0.0000425943,0.0017715576,0.018663278,0.0011297953,0.00034104774,0.96066815,0.015444476],"study_design_scores_gemma":[0.007866209,0.021038214,0.0018235819,0.00532701,0.012509427,0.00060967344,0.0020573323,0.13309334,0.0057183355,0.24573378,0.5608477,0.0033753787],"about_ca_topic_score_codex":0.000018632112,"about_ca_topic_score_gemma":0.000028721322,"teacher_disagreement_score":0.5194435,"about_ca_system_score_codex":0.00030042234,"about_ca_system_score_gemma":0.00033436087,"threshold_uncertainty_score":0.9999272},"labels":[],"label_agreement":null},{"id":"W4221060964","doi":"10.1093/ije/dyac067","title":"Time-fixed vs time-varying causal diagrams for immortal time bias","year":2022,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"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":"","keywords":"Causality (physics); Medicine; Statistics; Mathematics; Physics","score_opus":0.2364248504064162,"score_gpt":0.4574345538527232,"score_spread":0.221009703446307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221060964","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":[0.54210824,0.0009662299,0.42219704,0.022134122,0.004697252,0.0015862935,0.0007521925,0.00056709157,0.0049915253],"genre_scores_gemma":[0.5392457,0.00011444355,0.44126147,0.006820191,0.0034273504,0.00030440342,0.00039499594,0.00022472779,0.008206674],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670464,0.00074535375,0.001494439,0.00025433407,0.00040546153,0.0003957886],"domain_scores_gemma":[0.98626155,0.01118341,0.001645721,0.00021801125,0.00056611944,0.00012516788],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0050960192,0.00022491536,0.0008089695,0.00032217184,0.00012368229,0.000014287684,0.0009024967,0.00011449542,0.002568995],"category_scores_gemma":[0.014923186,0.00020140149,0.00038803768,0.000101531215,0.0001530067,0.0002385995,0.00030685536,0.00057663606,0.00006731899],"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":[0.004904264,0.0018020219,0.009631241,0.000082648396,0.0038660772,0.0009612615,0.001142526,0.012015599,0.06538305,0.22524945,0.6305568,0.044405032],"study_design_scores_gemma":[0.0016433083,0.0018412222,0.00032957972,0.00009380593,0.00013939035,0.0021533237,0.000051174684,0.032128505,0.0020315426,0.9171672,0.041926514,0.0004944692],"about_ca_topic_score_codex":0.0000096609265,"about_ca_topic_score_gemma":0.0000012919091,"teacher_disagreement_score":0.6919177,"about_ca_system_score_codex":0.0003813648,"about_ca_system_score_gemma":0.0001255025,"threshold_uncertainty_score":0.9983428},"labels":[],"label_agreement":null},{"id":"W4223522335","doi":"10.1177/13524585221085733","title":"Recommendations for the use of propensity score methods in multiple sclerosis research","year":2022,"lang":"en","type":"article","venue":"Multiple Sclerosis Journal","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia; McGill University; Jewish General Hospital","funders":"","keywords":"Propensity score matching; Covariate; Matching (statistics); Context (archaeology); Weighting; Medicine; Comparative effectiveness research; Computer science; Machine learning; Alternative medicine; Surgery; Pathology","score_opus":0.9297887613391248,"score_gpt":0.5353901558312687,"score_spread":0.3943986055078561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223522335","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":[0.38469496,0.00023845657,0.6058565,0.004532675,0.0005477122,0.0036200183,0.00031933832,0.00015534737,0.00003498382],"genre_scores_gemma":[0.4722309,0.00024488106,0.5265816,0.00009301938,0.000058579193,0.0006456513,0.00000739731,0.000048075613,0.00008988482],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995428,0.001964553,0.0009771812,0.00033303403,0.0006895285,0.0006076512],"domain_scores_gemma":[0.983339,0.014631576,0.00051897555,0.0006481892,0.00074730755,0.000114926486],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0093441075,0.00020806196,0.0004551576,0.0004590387,0.0016789573,0.00014991667,0.00078998075,0.00008361217,0.00025762556],"category_scores_gemma":[0.012367751,0.0001611058,0.00022419645,0.00094474526,0.00025690495,0.0005111431,0.0006727837,0.0015734634,0.0000014495488],"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":[0.0013620916,0.002763355,0.08742945,0.00020149205,0.00031661883,0.0000071857876,0.0071959053,0.0056481604,0.4112886,0.008583336,0.09266907,0.38253474],"study_design_scores_gemma":[0.013010485,0.002883707,0.1794686,0.0025336568,0.00031352212,0.00018818765,0.010840402,0.10328716,0.32713634,0.25039783,0.10777912,0.0021609976],"about_ca_topic_score_codex":0.00026858939,"about_ca_topic_score_gemma":0.00039846628,"teacher_disagreement_score":0.38037375,"about_ca_system_score_codex":0.0004940523,"about_ca_system_score_gemma":0.00015798202,"threshold_uncertainty_score":0.99962074},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4225262102","doi":"10.1007/s10985-022-09554-8","title":"Privacy-preserving estimation of an optimal individualized treatment rule: a case study in maximizing time to severe depression-related outcomes","year":2022,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"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 of Mental Health; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Robustness (evolution); Flexibility (engineering); Confounding; Computer science; Context (archaeology); Regression; Econometrics; Data mining; Regression analysis; Machine learning; Statistics; Mathematics","score_opus":0.11010661982874727,"score_gpt":0.4265556289728123,"score_spread":0.31644900914406504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225262102","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":[0.9867649,0.000019801237,0.010608432,0.00006872561,0.000009225036,0.0010643125,0.0011544647,0.00022004452,0.00009008079],"genre_scores_gemma":[0.7632845,0.0000011381578,0.23464897,0.000018401332,0.000004205433,0.00023250656,0.001590602,0.00003428186,0.00018537803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996747,0.0006668302,0.0009629937,0.0007330064,0.0005918823,0.00029828923],"domain_scores_gemma":[0.9958536,0.0006471839,0.00045034618,0.0028623217,0.000054831187,0.0001316853],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012363495,0.00030053494,0.000952945,0.0009937175,0.00020364269,0.000054654833,0.0012709652,0.00006605362,0.002572029],"category_scores_gemma":[0.0010492668,0.00027413352,0.0001216644,0.0020612713,0.0000217439,0.00065362063,0.0028276972,0.00020824533,0.000014464647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005942069,0.01030821,0.21393046,0.00010840841,0.010512423,0.004978479,0.037782732,0.6690176,0.00060453446,0.00008135368,0.00097277766,0.051108804],"study_design_scores_gemma":[0.0032475656,0.0009468746,0.007960473,0.00005700436,0.006408195,0.00026801554,0.010579301,0.96506673,0.00046977933,0.00398137,0.00007461963,0.00094009796],"about_ca_topic_score_codex":0.0016237705,"about_ca_topic_score_gemma":0.00021970851,"teacher_disagreement_score":0.2960491,"about_ca_system_score_codex":0.00023970955,"about_ca_system_score_gemma":0.000060636037,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W4225377897","doi":"10.1002/pds.5446","title":"Alternative analytic and matching approaches for the prevalent new‐user design: A simulation study","year":2022,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University","funders":"Janssen Pharmaceuticals; Johnson and Johnson; National Institutes of Health","keywords":"Propensity score matching; Matching (statistics); Weighting; Medicine; Statistics; Relative risk; Cohort; Efficiency; Econometrics; Mathematics; Internal medicine; Confidence interval","score_opus":0.3953143985526518,"score_gpt":0.4816124235455468,"score_spread":0.08629802499289496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225377897","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":[0.025664963,0.0006527488,0.9696631,0.0017028692,0.000082092185,0.0020649778,0.000017553237,0.000104558145,0.000047165617],"genre_scores_gemma":[0.9656791,0.00014472546,0.032842077,0.0004949677,0.00008846149,0.0004594752,0.000004601868,0.000020319794,0.00026623465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99741685,0.0015066841,0.00040194034,0.00034637612,0.00010141237,0.00022672763],"domain_scores_gemma":[0.9796233,0.019870088,0.00023919593,0.00017875912,0.000026076716,0.000062575375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054756217,0.00017608801,0.00034371827,0.00005385848,0.0005579834,0.000009344138,0.00017046502,0.000027461805,0.000051584022],"category_scores_gemma":[0.0010135418,0.00012547769,0.000048890553,0.00007986704,0.00008329655,0.00012169823,0.0002565581,0.00031867204,3.8193656e-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":[0.0020237353,0.00061650504,0.010918765,0.00017055313,0.00085585867,0.0000069761513,0.02129495,0.7625373,0.000110412664,0.14985318,0.0045741536,0.047037616],"study_design_scores_gemma":[0.0008699267,0.00015292953,0.00081831677,0.000006230303,0.00024328948,0.0000070002147,0.0016471291,0.41446716,0.00006242435,0.5805909,0.0009816225,0.0001530651],"about_ca_topic_score_codex":0.00006431351,"about_ca_topic_score_gemma":0.000009389917,"teacher_disagreement_score":0.9400142,"about_ca_system_score_codex":0.00006163284,"about_ca_system_score_gemma":0.000027816319,"threshold_uncertainty_score":0.51168317},"labels":[],"label_agreement":null},{"id":"W4226189642","doi":"10.31219/osf.io/3gf64","title":"Effect Measure Modification by Covariates in Mediation: Extending Regression-Based Causal Mediation Analysis","year":2022,"lang":"en","type":"preprint","venue":"","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":"McGill University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; Rheumatology Research Foundation; National Institutes of Health; Brigham and Women's Hospital","keywords":"Covariate; Mediation; Measure (data warehouse); Econometrics; Regression analysis; Regression; Mediator; Statistics; Index (typography); Psychology; Computer science; Mathematics; Data mining; Medicine; Political science; Internal medicine; World Wide Web","score_opus":0.09173009617309104,"score_gpt":0.42672781691702005,"score_spread":0.33499772074392903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226189642","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":[0.03163459,0.00037874433,0.9622905,0.0005893927,0.00038957188,0.0020045722,0.00021037208,0.0012497688,0.0012524459],"genre_scores_gemma":[0.9486117,0.00009366938,0.04524145,0.000059252405,0.00009169402,0.002101485,0.0035418733,0.000077887176,0.00018101894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533147,0.001169422,0.0010191295,0.0009224569,0.0011971975,0.00036032638],"domain_scores_gemma":[0.994132,0.003367916,0.0010627185,0.0011098536,0.00021964248,0.00010789783],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035577225,0.0005434655,0.0010200485,0.0011386287,0.00014589464,0.00009058758,0.0005597243,0.00057044724,0.0014522293],"category_scores_gemma":[0.0035100495,0.0004803504,0.0002846496,0.0013292033,0.00005117833,0.00018909149,0.00034560435,0.0011900802,0.0000063644598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019499533,0.0046694633,0.1962967,0.009107261,0.006864514,0.00020105125,0.0075537595,0.35669985,0.050554328,0.21857837,0.047200102,0.10032462],"study_design_scores_gemma":[0.0019683628,0.00043079272,0.004077475,0.00060230633,0.0023944788,0.0000018659576,0.000317472,0.515766,0.06834493,0.4030699,0.00031896646,0.0027074013],"about_ca_topic_score_codex":0.00020911323,"about_ca_topic_score_gemma":0.00013898493,"teacher_disagreement_score":0.9170491,"about_ca_system_score_codex":0.0011607611,"about_ca_system_score_gemma":0.0002236351,"threshold_uncertainty_score":0.9997648},"labels":[],"label_agreement":null},{"id":"W4226278827","doi":"10.1093/ije/dyac090","title":"The primary importance of the research question: implications for understanding natural versus controlled direct effects","year":2022,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"","keywords":"Natural (archaeology); Medicine; Psychology; Geography","score_opus":0.43804043204601734,"score_gpt":0.5543919310265762,"score_spread":0.11635149898055891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226278827","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":[0.11675104,0.012126411,0.62380517,0.21165799,0.01813055,0.005349717,0.00019896113,0.00015067759,0.011829483],"genre_scores_gemma":[0.98584694,0.00015254872,0.013058918,0.0003376236,0.00024798914,0.00019285813,0.000004031062,0.000013177326,0.0001458983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99673355,0.0016899519,0.0008950996,0.00012017302,0.00034169416,0.00021952044],"domain_scores_gemma":[0.9073111,0.090406135,0.0012263007,0.00023826155,0.0007875175,0.00003072581],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011116113,0.00008466272,0.00040263432,0.00011867156,0.00036891428,0.000009103361,0.00097405683,0.00004199803,0.000010143165],"category_scores_gemma":[0.05746347,0.000048200163,0.00026357773,0.00014032282,0.00030360362,0.00008275155,0.00023460032,0.00058765255,1.4088361e-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":[0.0015654946,0.000042603737,0.00335365,0.0000095564565,0.00023674626,0.0000015774034,0.000043689906,0.0000798508,0.0010288138,0.9841048,0.008666208,0.00086701126],"study_design_scores_gemma":[0.0016977508,0.0002972201,0.0028355892,0.00004079651,0.000030406694,0.00005663637,0.000114127615,0.0001377822,0.00018393253,0.99168277,0.002875756,0.000047232796],"about_ca_topic_score_codex":0.000004622865,"about_ca_topic_score_gemma":0.000021300904,"teacher_disagreement_score":0.8690959,"about_ca_system_score_codex":0.00095561764,"about_ca_system_score_gemma":0.0001910639,"threshold_uncertainty_score":0.95047593},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4226297244","doi":"10.1162/qss_c_00178","title":"Towards a moralization of bibliometrics? A response to Kyle Siler","year":2022,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Advanced Causal Inference Techniques","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":"Université du Québec à Montréal","funders":"","keywords":"Publication; Bibliometrics; Epistemology; Point (geometry); Sociology; Classics; Philosophy; History; Political science; Law; Computer science; Library science; Mathematics","score_opus":0.4986595425254802,"score_gpt":0.570894191989019,"score_spread":0.0722346494635388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226297244","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":[0.88683987,0.00041465857,0.1097823,0.00096172554,0.00020740942,0.0005468166,0.00004559421,0.00017293959,0.0010286912],"genre_scores_gemma":[0.8311115,0.00003950048,0.16844232,0.00010003086,0.000004270667,0.0001643218,3.559905e-7,0.0000105918525,0.00012712597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977988,0.00022236856,0.0003369241,0.00033484516,0.0010245577,0.00028249616],"domain_scores_gemma":[0.99708974,0.0012698313,0.00022434093,0.00029175612,0.0010622097,0.00006210471],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.003944249,0.00012928931,0.00030917613,0.0053611635,0.00049590797,0.000022268248,0.00047128054,0.000012288864,0.00005657141],"category_scores_gemma":[0.021947762,0.000113562644,0.00004392042,0.02838833,0.00061808847,0.0003923363,0.0007790055,0.00010281093,0.000006284152],"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":[0.00035913338,0.00018512661,0.0006070775,0.000058420177,0.000042694504,0.0000067635856,0.02714677,0.0002550015,0.20741585,0.75775427,0.003957395,0.0022115163],"study_design_scores_gemma":[0.00034456985,0.0040928423,0.006922289,0.000088727575,0.00003446014,0.000005938963,0.06466841,0.00054421206,0.14352544,0.7771622,0.0021221098,0.0004888195],"about_ca_topic_score_codex":0.000016460343,"about_ca_topic_score_gemma":0.0000048614984,"teacher_disagreement_score":0.063890405,"about_ca_system_score_codex":0.0002604658,"about_ca_system_score_gemma":0.0001902928,"threshold_uncertainty_score":0.99226373},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4226487945","doi":"10.1111/biom.13692","title":"Power Analysis for Cluster Randomized Trials with Continuous Coprimary Endpoints","year":2022,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; University of Ottawa","funders":"National Institute on Aging; Patient-Centered Outcomes Research Institute","keywords":"Sample size determination; Estimator; Intraclass correlation; Statistics; Cluster randomised controlled trial; Statistical power; Cluster (spacecraft); Computer science; Mathematics; Econometrics; Data mining; Randomized controlled trial; Medicine; Psychometrics","score_opus":0.18790196610096394,"score_gpt":0.42572147913694564,"score_spread":0.2378195130359817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226487945","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":[0.019901518,0.00023207275,0.9742696,0.00016974326,0.00015067866,0.002807312,0.0002975916,0.00034315966,0.0018282937],"genre_scores_gemma":[0.6042337,0.0000394153,0.39182284,0.00046334596,0.000050360355,0.0015207779,0.00012279623,0.00007239709,0.001674384],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99704874,0.000765967,0.0009069537,0.00035264535,0.000600714,0.00032496135],"domain_scores_gemma":[0.98081124,0.01752872,0.0008017423,0.0005041121,0.0002711504,0.00008306488],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008947801,0.00023035244,0.0020083697,0.0029173465,0.00017005793,0.000053479507,0.0003225098,0.00007860744,0.00072635984],"category_scores_gemma":[0.016746426,0.0001692466,0.000685419,0.0068463013,0.00010414034,0.000099680474,0.00018844452,0.00016724711,0.0000032615824],"study_design_candidate":"randomized_trial","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":[0.45187917,0.005764812,0.00463519,0.0006956744,0.04048727,0.0001570756,0.0026932685,0.00040126665,0.007060844,0.28164917,0.1724043,0.03217196],"study_design_scores_gemma":[0.41153142,0.0035941703,0.00023851682,0.00004682264,0.016981604,0.00005686699,0.0013888814,0.0030255087,0.014611384,0.4903996,0.055568773,0.0025564583],"about_ca_topic_score_codex":0.0000090942,"about_ca_topic_score_gemma":0.000002417891,"teacher_disagreement_score":0.58433217,"about_ca_system_score_codex":0.00023778886,"about_ca_system_score_gemma":0.00006533556,"threshold_uncertainty_score":0.99153596},"labels":[],"label_agreement":null},{"id":"W4226517330","doi":"10.1002/ecs2.4009","title":"Utilizing causal diagrams across quasi‐experimental approaches","year":2022,"lang":"en","type":"article","venue":"Ecosphere","topic":"Advanced Causal Inference Techniques","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":"Dalhousie University","funders":"","keywords":"Causal inference; Causal model; Computer science; Observational study; Instrumental variable; Causality (physics); Causal structure; Process (computing); Econometrics; Machine learning; Statistics; Mathematics","score_opus":0.2689129566122469,"score_gpt":0.4140008606688787,"score_spread":0.1450879040566318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226517330","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":[0.92614067,0.00068736414,0.012901366,0.00013297102,0.0003009956,0.00062170974,0.00006606687,0.0012434853,0.057905383],"genre_scores_gemma":[0.9673984,0.000004416522,0.03014991,0.000088329056,0.00007905589,0.0004573478,0.000019087569,0.000066546076,0.0017368789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984161,0.00010872091,0.00030035723,0.00036474914,0.00033404728,0.00047601826],"domain_scores_gemma":[0.9991016,0.00018897257,0.00014164047,0.00046130706,0.000019159332,0.00008733867],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037931945,0.00022566417,0.00027774464,0.000012853096,0.00047208046,0.00005115378,0.00037021315,0.00006330717,0.0031014823],"category_scores_gemma":[0.00009801944,0.00023391774,0.00010207979,0.000191187,0.00007901738,0.00019396946,0.00054758077,0.0004123961,0.0000738257],"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":[0.00014934834,0.004802428,0.0017488592,0.00018436911,0.00018526186,0.00021129788,0.01710207,0.00023132889,0.007496812,0.78917825,0.14361082,0.03509918],"study_design_scores_gemma":[0.0017705126,0.002500984,0.00046610812,0.0000730996,0.000055979122,0.00024637338,0.10254374,0.0045472328,0.16874063,0.65551406,0.061264805,0.002276467],"about_ca_topic_score_codex":0.000037168084,"about_ca_topic_score_gemma":0.00007333863,"teacher_disagreement_score":0.16124381,"about_ca_system_score_codex":0.00027779667,"about_ca_system_score_gemma":0.00003390268,"threshold_uncertainty_score":0.9978098},"labels":[],"label_agreement":null},{"id":"W4229035405","doi":"10.1111/biom.13687","title":"Coherent Modeling of Longitudinal Causal Effects on Binary Outcomes","year":2022,"lang":"en","type":"article","venue":"Biometrics","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":"University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Multiplicative function; Binary number; Variation (astronomy); Computer science; Mathematics; Econometrics","score_opus":0.2122266913199617,"score_gpt":0.4176687021793165,"score_spread":0.20544201085935482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229035405","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":[0.9043606,0.00019375401,0.0930683,0.00010430671,0.0003955234,0.0005464248,0.00006672831,0.00036865333,0.00089574023],"genre_scores_gemma":[0.97753096,0.000014793502,0.02208141,0.00006526238,0.00002475454,0.00009858258,0.000010142292,0.000034231813,0.00013984073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839777,0.00008730412,0.00035478172,0.0002482814,0.0006623257,0.00024956837],"domain_scores_gemma":[0.99806494,0.0011804717,0.00019294221,0.0004103386,0.00008861541,0.00006270534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045494933,0.00018181486,0.00036893148,0.0013935786,0.00011764952,0.000010054519,0.00029543127,0.000056292152,0.00008192689],"category_scores_gemma":[0.0010624368,0.00016465364,0.000108520915,0.0024492494,0.000028725666,0.00006278684,0.00031680267,0.00024539354,0.000006105295],"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":[0.00075668056,0.009789383,0.1422328,0.0036128676,0.0010634969,0.0007466433,0.0017169315,0.017625112,0.057456147,0.6530367,0.032812297,0.07915093],"study_design_scores_gemma":[0.00456454,0.015105711,0.014722013,0.00034317447,0.0005382439,0.000074030584,0.00085475453,0.08444582,0.101813555,0.77013713,0.004278315,0.0031227148],"about_ca_topic_score_codex":0.000019195983,"about_ca_topic_score_gemma":0.0000010597182,"teacher_disagreement_score":0.12751079,"about_ca_system_score_codex":0.00023949458,"about_ca_system_score_gemma":0.000035034234,"threshold_uncertainty_score":0.6714381},"labels":[],"label_agreement":null},{"id":"W4229367060","doi":"10.1177/26320843221085649","title":"Considerations for choosing an imputation method for addressing sparse measurement issues dictated by the study design - An illustration from per-protocol analysis in pragmatic trials","year":2022,"lang":"en","type":"article","venue":"Research Methods in Medicine & Health Sciences","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Confounding; Statistics; Computer science; Missing data; Protocol (science); Marginal structural model; Inverse probability; Econometrics; Data mining; Mathematics; Medicine; Bayesian probability; Posterior probability","score_opus":0.9263120700886384,"score_gpt":0.7689398625401077,"score_spread":0.15737220754853065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229367060","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":[0.0023774088,0.00014046453,0.8993958,0.0049264426,0.000044555407,0.09301354,0.00002708327,0.000066321496,0.000008387937],"genre_scores_gemma":[0.022012003,0.000007141829,0.8414484,0.0001631396,0.00007444896,0.13624978,0.000022757858,0.00001776928,0.000004550069],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9224863,0.07072478,0.0023473874,0.00093760405,0.0026758332,0.0008281076],"domain_scores_gemma":[0.9441259,0.05347084,0.0009012936,0.0005223752,0.00079215213,0.00018747368],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37839502,0.00020967497,0.001072829,0.0012612472,0.0021028346,0.0001845897,0.0005291219,0.000058127505,0.00011185476],"category_scores_gemma":[0.07450588,0.00014093844,0.0000618358,0.0028526592,0.00042118863,0.0005619528,0.00008279768,0.00058975845,6.22056e-8],"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":[0.0017105564,0.004618522,0.0019494168,0.0010485171,0.000473169,0.000008316283,0.27761492,0.07245298,0.10223502,0.023412688,0.0066803386,0.5077956],"study_design_scores_gemma":[0.0013727556,0.0047061075,0.00021750276,0.000141183,0.00008356995,8.590766e-7,0.06750281,0.36336163,0.0017616552,0.5606429,0.000076483135,0.00013256042],"about_ca_topic_score_codex":0.004906311,"about_ca_topic_score_gemma":0.0032043103,"teacher_disagreement_score":0.5372302,"about_ca_system_score_codex":0.00083100423,"about_ca_system_score_gemma":0.0013222733,"threshold_uncertainty_score":0.9991963},"labels":[],"label_agreement":null},{"id":"W4231108001","doi":"10.31219/osf.io/hrnwa","title":"Are Replication Studies Infrequent Because of Negative Attitudes? Insights From a Survey of Attitudes and Practices in Second Language Research","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Pennsylvania State University; University of Pennsylvania","keywords":"Replication (statistics); Originality; Empirical research; Field (mathematics); Quarter (Canadian coin); Psychology; Computer science; Social psychology; Biology; Mathematics; Statistics","score_opus":0.5843522712943052,"score_gpt":0.5849804009726127,"score_spread":0.0006281296783074986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231108001","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":[0.9933613,0.0044598985,0.00035806763,0.000062419334,0.00002979226,0.0009850228,0.00018227623,0.00006913381,0.0004921045],"genre_scores_gemma":[0.9526118,0.0015469992,0.045353156,0.00001544773,0.000017559121,0.00023085553,0.00008854429,0.0000306091,0.00010502884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996123,0.0013094047,0.0009771477,0.00083718286,0.00055222417,0.00020102711],"domain_scores_gemma":[0.9840742,0.009661303,0.0026036212,0.0015362499,0.0020727897,0.000051856772],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00238949,0.00028651653,0.0010766953,0.00036891422,0.000038436316,0.000052314732,0.00038346645,0.0003226957,0.00008524639],"category_scores_gemma":[0.034576625,0.0002491,0.000050696202,0.0003979781,0.0004251303,0.0003351205,0.0016825002,0.0009808178,7.1520503e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041727896,0.003046275,0.7874795,0.018732512,0.0029036975,0.00017721951,0.08929878,0.000034459274,0.071089506,0.024252066,0.0010761594,0.001492542],"study_design_scores_gemma":[0.00030490218,0.000100709716,0.67431074,0.0037592715,0.000045365214,0.0000012575449,0.0121844495,0.000026466121,0.15848123,0.15046184,0.0000036107026,0.00032017904],"about_ca_topic_score_codex":0.012012096,"about_ca_topic_score_gemma":0.19313549,"teacher_disagreement_score":0.18112339,"about_ca_system_score_codex":0.0002184362,"about_ca_system_score_gemma":0.00022218807,"threshold_uncertainty_score":0.9999961},"labels":[],"label_agreement":null},{"id":"W4232895294","doi":"10.1002/9780470057339.vnn143","title":"<scp>J</scp> oint <scp>M</scp> odels","year":2012,"lang":"en","type":"other","venue":"Encyclopedia of Environmetrics","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":"Simon Fraser University","funders":"","keywords":"Independence (probability theory); Conditional independence; Computer science; Joint (building); Event (particle physics); Econometrics; Process (computing); Statistical model; Artificial intelligence; Statistics; Mathematics; Engineering","score_opus":0.05943035957120976,"score_gpt":0.31891827580323073,"score_spread":0.25948791623202094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232895294","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000660892,0.007107507,0.06732644,0.000008651638,0.00076401845,0.0010792093,0.00032166127,0.0009747531,0.92175686],"genre_scores_gemma":[0.00028214537,0.023749646,0.17620568,0.00006954162,0.0011140249,0.00015005787,0.00010646901,0.0014937491,0.7968287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951141,0.00019214049,0.0012453703,0.0009179126,0.0012763896,0.0012540917],"domain_scores_gemma":[0.98944664,0.006108717,0.0018768079,0.002036267,0.00006343477,0.00046815685],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00081973645,0.0011560934,0.0016526668,0.0019270716,0.00007385297,0.00003171929,0.0012393893,0.0015849804,0.0011099427],"category_scores_gemma":[0.012852981,0.0011373557,0.00044174914,0.0013115802,0.00044503907,0.00028217022,0.0006555696,0.0012523058,0.00094627944],"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":[6.4857323e-7,0.00051228557,0.0010565514,0.00052551215,0.00015394535,0.000023340415,0.00047476366,0.0000059946556,0.00006634453,0.017386787,0.9756708,0.004123033],"study_design_scores_gemma":[0.00026679048,0.00015112548,0.00019978329,0.0002315594,0.00029232274,0.000011844307,0.00021392349,0.000007911825,0.00071359845,0.041745946,0.95593905,0.00022612479],"about_ca_topic_score_codex":0.000055843866,"about_ca_topic_score_gemma":0.000015766398,"teacher_disagreement_score":0.124928184,"about_ca_system_score_codex":0.0002763456,"about_ca_system_score_gemma":0.000103202656,"threshold_uncertainty_score":0.9998316},"labels":[],"label_agreement":null},{"id":"W4233426781","doi":"10.1002/9781118625392.wbecp401","title":"Correlational Designs","year":2015,"lang":"en","type":"other","venue":"The Encyclopedia of Clinical Psychology","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":"Toronto Metropolitan University","funders":"","keywords":"Psychology; Variety (cybernetics); Variables; Variable (mathematics); Causality (physics); Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.5570764566826809,"score_gpt":0.5965892899140837,"score_spread":0.039512833231402755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233426781","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017124987,0.00034484587,0.024647348,0.00049928937,0.00162144,0.0004635144,0.00006157775,0.0003533272,0.97199154],"genre_scores_gemma":[0.00011740286,0.0020921982,0.06180764,0.0006467039,0.0017513974,0.00005075272,0.00004201806,0.00041694773,0.93307495],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972237,0.00056545046,0.0012518051,0.00038283644,0.00032958275,0.00024662857],"domain_scores_gemma":[0.99412084,0.0033515017,0.001216935,0.0010747074,0.000124594,0.00011141791],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020253137,0.00027477782,0.00094748946,0.000110648914,0.000018223038,0.0000021652747,0.0007548067,0.00090886204,0.003702045],"category_scores_gemma":[0.0046826857,0.00018273391,0.00018791042,0.00015457887,0.0007567472,0.000024988507,0.00011431238,0.0008803381,0.00037360188],"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":[0.000042278167,0.00015975894,0.00016306891,0.00001779149,0.00006590788,0.00000372071,0.000028837489,1.7441918e-7,6.783314e-7,0.0358126,0.95809466,0.0056105275],"study_design_scores_gemma":[0.00024179829,0.00014041933,0.0000845155,0.000048422444,0.000051447605,0.000004727798,0.00000429155,0.0000017468361,5.270434e-7,0.42371696,0.5755876,0.000117580705],"about_ca_topic_score_codex":0.000009611012,"about_ca_topic_score_gemma":0.00003940701,"teacher_disagreement_score":0.38790435,"about_ca_system_score_codex":0.000011217909,"about_ca_system_score_gemma":0.00016946238,"threshold_uncertainty_score":0.9972087},"labels":[],"label_agreement":null},{"id":"W4233910395","doi":"10.1086/503412","title":"Discussion","year":2001,"lang":"en","type":"article","venue":"Infection Control and Hospital Epidemiology","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 Alberta Hospital; Canadian Institutes of Health Research; Ottawa Hospital; Canadian Institute for Health Information","funders":"","keywords":"Computer science; World Wide Web; Medicine","score_opus":0.09288309211094997,"score_gpt":0.40935153118369694,"score_spread":0.31646843907274697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233910395","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":[0.22100899,0.0002124229,0.76125985,0.012084811,0.0003941598,0.00040171755,0.0000041443404,0.0006537134,0.003980198],"genre_scores_gemma":[0.99285376,0.00043064938,0.0052804677,0.0008203085,0.0001778513,0.00007522164,0.0000024256187,0.000013664717,0.0003456589],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988929,0.000222638,0.0003495471,0.00023472376,0.000041378433,0.0002588315],"domain_scores_gemma":[0.9981155,0.0014164923,0.0001649468,0.00016282084,0.00005374665,0.00008653845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007319479,0.00013951807,0.00038894176,0.00006449433,0.00009977001,0.000006166001,0.000043626627,0.0001559662,0.0000715761],"category_scores_gemma":[0.0036922728,0.00008517168,0.00006924747,0.00007091978,0.00012607955,0.00016370727,0.000030798623,0.00018400812,0.000018903396],"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":[0.000052995045,0.00012984201,0.39064002,0.000019732572,0.00004207035,0.0000090225885,0.00007928173,0.000012399372,0.00036446156,0.49259338,0.004229717,0.11182706],"study_design_scores_gemma":[0.00045144244,0.00041786407,0.07121553,0.00001721988,0.000021012358,0.00004139072,0.000009949013,0.00069559884,0.000024278925,0.9041768,0.022767494,0.00016143777],"about_ca_topic_score_codex":0.0001067841,"about_ca_topic_score_gemma":0.00004108586,"teacher_disagreement_score":0.77184474,"about_ca_system_score_codex":0.000030095238,"about_ca_system_score_gemma":0.0000075543735,"threshold_uncertainty_score":0.4420262},"labels":[],"label_agreement":null},{"id":"W4234921364","doi":"10.1002/sim.2781","title":"The performance of different propensity score methods for estimating marginal odds ratios","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":244,"is_retracted":false,"has_abstract":true,"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","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Odds; Estimator; Matching (statistics); Medicine; Mathematics; Logistic regression","score_opus":0.16363719544178307,"score_gpt":0.47372662365848633,"score_spread":0.31008942821670327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234921364","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":[0.052861143,0.00005312101,0.9456895,0.00013756694,0.00014367163,0.00071046146,0.000021087702,0.000042779775,0.00034065865],"genre_scores_gemma":[0.14389014,0.00002468122,0.8556389,0.000017510474,0.000103859005,0.00010504983,0.000020776673,0.000018213663,0.00018084158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998661,0.00011053021,0.0006178968,0.00015586543,0.00021950259,0.00023523546],"domain_scores_gemma":[0.99544847,0.003698763,0.00031565502,0.0002784863,0.00023152708,0.00002707009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014405828,0.00015330553,0.00039560627,0.00005870846,0.00011969706,0.0000078638295,0.00018791013,0.00004498881,0.000016752208],"category_scores_gemma":[0.0033466113,0.00009087888,0.000017414486,0.00011442308,0.00033339852,0.00004524119,0.000048911057,0.00019157064,2.6925795e-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":[0.000091860435,0.00007759775,0.0044587837,0.00073018565,0.000013911304,0.0000028436052,0.00026054203,0.00006668358,0.0061830566,0.91013944,0.0030943756,0.074880704],"study_design_scores_gemma":[0.0005251256,0.0005000319,0.004005472,0.00044439881,0.000043036955,0.000004917463,0.00005520105,0.11044669,0.013352848,0.8703821,0.000110871915,0.0001293549],"about_ca_topic_score_codex":0.000030006197,"about_ca_topic_score_gemma":0.00008847591,"teacher_disagreement_score":0.11038001,"about_ca_system_score_codex":0.00007043953,"about_ca_system_score_gemma":0.000034654855,"threshold_uncertainty_score":0.4006448},"labels":[],"label_agreement":null},{"id":"W4235026130","doi":"10.31234/osf.io/ydgh9","title":"Machine Learning to Analyze Single-Case Graphs: A Replication and Extension with Nonsimulated Data","year":2020,"lang":"en","type":"preprint","venue":"","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":"Université de Montréal; Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"","keywords":"Replication (statistics); Computer science; Extension (predicate logic); Artificial intelligence; Replicate; Machine learning; False positive paradox; Dual (grammatical number); Type I and type II errors; Mathematics; Statistics; Programming language","score_opus":0.35248075217318375,"score_gpt":0.42572063644359853,"score_spread":0.07323988427041478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235026130","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":[0.15296327,0.00012909312,0.84079057,0.0013076009,0.00002493383,0.0016162763,0.00010739917,0.0021674745,0.00089340744],"genre_scores_gemma":[0.58699757,0.000048629314,0.41214076,0.00018277104,0.000017642944,0.0000326444,0.00041181842,0.00006111196,0.00010702872],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975705,0.00011559151,0.0004480925,0.0014265903,0.0002337046,0.00020553218],"domain_scores_gemma":[0.9959259,0.0003838549,0.00033967663,0.0029188455,0.00024357499,0.00018817419],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000510069,0.00036596603,0.00052479666,0.00019746555,0.00009945872,0.000098572295,0.00038014958,0.00021288768,0.000038858943],"category_scores_gemma":[0.0024085105,0.0002929323,0.000031616008,0.00033690786,0.00005549775,0.00015991124,0.0024226177,0.00080262806,0.00000553225],"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":[0.0037133452,0.0030983605,0.010917335,0.008428625,0.0031096237,0.015270549,0.01242842,0.009644834,0.22162466,0.18698107,0.01997188,0.5048113],"study_design_scores_gemma":[0.0007400862,0.0012361906,0.00018143062,0.0017185127,0.0007765469,0.001708006,0.0004708795,0.34114155,0.009981277,0.6380365,0.002052427,0.0019566165],"about_ca_topic_score_codex":0.00025350088,"about_ca_topic_score_gemma":0.00025749524,"teacher_disagreement_score":0.5028547,"about_ca_system_score_codex":0.000049733433,"about_ca_system_score_gemma":0.00004007474,"threshold_uncertainty_score":0.99995226},"labels":[],"label_agreement":null},{"id":"W4236509688","doi":"10.1002/9781118445112.stat05748","title":"Explanatory Variables","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","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":"Cancer Care Ontario","funders":"","keywords":"Explanatory model; Econometrics; Variable (mathematics); Variables; Statistics; Outcome (game theory); Mathematics; Mathematical economics","score_opus":0.14152873997644777,"score_gpt":0.4119456737486882,"score_spread":0.2704169337722404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236509688","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":[0.0000041306353,0.0005457702,0.7625706,0.00003144391,0.00039230974,0.0006770334,0.026848264,0.0020538624,0.20687659],"genre_scores_gemma":[0.00006930272,0.0025890076,0.71893036,0.00021238624,0.00046465,0.00010493096,0.004883708,0.0012443571,0.27150127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596936,0.0002491848,0.0010103491,0.0010023514,0.0008764496,0.0008923098],"domain_scores_gemma":[0.9954416,0.0011824166,0.0011523737,0.0015825278,0.00029161203,0.00034943724],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038396398,0.0010436953,0.0014113041,0.00058205577,0.00010092759,0.00007824323,0.0009398241,0.0008648785,0.008755328],"category_scores_gemma":[0.0014281567,0.00097226637,0.00008434246,0.00027724673,0.00036927732,0.00008925776,0.00027400372,0.0011305768,0.00043705993],"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":[0.000010834012,0.00016139295,0.00001015614,0.0004010846,0.00008302448,0.000037003923,0.000024044859,7.505123e-7,0.000028459772,0.389818,0.6026884,0.006736891],"study_design_scores_gemma":[0.0002706174,0.00015501455,0.0000043357945,0.0010081559,0.00012377226,0.000009011069,0.000036996465,0.00014116598,0.000031262105,0.43622395,0.5611868,0.00080889853],"about_ca_topic_score_codex":0.00023263956,"about_ca_topic_score_gemma":0.0013199802,"teacher_disagreement_score":0.06462468,"about_ca_system_score_codex":0.00020797197,"about_ca_system_score_gemma":0.00033814512,"threshold_uncertainty_score":0.99927276},"labels":[],"label_agreement":null},{"id":"W4238135399","doi":"10.1093/pch/14.8.514","title":"Research Letter","year":2009,"lang":"en","type":"article","venue":"Paediatrics & Child Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Izaak Walton Killam Health Centre","funders":"","keywords":"Computer science; Medicine","score_opus":0.17723211282039164,"score_gpt":0.47835138657275705,"score_spread":0.3011192737523654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238135399","genre_codex":"commentary","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":[0.043117993,0.009110831,0.24786496,0.44403124,0.001147596,0.0057816887,0.000087794026,0.005819252,0.24303865],"genre_scores_gemma":[0.81377083,0.0024503844,0.15410855,0.026268404,0.0027264329,0.00004898787,0.000019114626,0.00007456918,0.00053269824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738634,0.00026813935,0.00046075825,0.00034980295,0.0006805698,0.0008543817],"domain_scores_gemma":[0.99816334,0.00065316533,0.00015420909,0.0005902794,0.00018578135,0.0002531979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026718483,0.0001691638,0.00030385214,0.00036665957,0.00037837535,0.000038906328,0.00034596634,0.00012614221,0.000064007836],"category_scores_gemma":[0.0007511747,0.00015455054,0.00006946275,0.0008373984,0.000055483768,0.00014817533,0.00007274592,0.0010548948,0.00011976292],"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":[0.00001264783,0.00024741856,0.00055655156,0.00009725099,0.000004830084,0.0000115501725,0.0006399761,0.0000016491413,0.000022244838,0.53090113,0.4303215,0.037183255],"study_design_scores_gemma":[0.00022984705,0.0004411373,0.0025969937,0.000051090203,0.000004737239,0.000011119679,0.0000546184,0.000020776151,0.0002137025,0.9404309,0.05572213,0.00022294333],"about_ca_topic_score_codex":0.000028516606,"about_ca_topic_score_gemma":0.000015402642,"teacher_disagreement_score":0.7706529,"about_ca_system_score_codex":0.00028120106,"about_ca_system_score_gemma":0.00016996305,"threshold_uncertainty_score":0.6302388},"labels":[],"label_agreement":null},{"id":"W4238440528","doi":"10.1016/s0895-4356(03)00382-2","title":"Commonalities in the classical, collapsibility and counterfactual concepts of confounding","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","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":"University of Alberta","funders":"","keywords":"Counterfactual thinking; Confounding; Counterfactual conditional; Key (lock); Econometrics; Abstraction; Observational study; Computer science; Medicine; Risk analysis (engineering); Psychology; Mathematics; Epistemology; Social psychology; Computer security","score_opus":0.6440032894371513,"score_gpt":0.6306114681949174,"score_spread":0.013391821242233926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238440528","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":[0.9708239,0.00022957727,0.022498926,0.0056572575,0.00019239473,0.0001501507,0.0000060217094,0.000009819789,0.0004319893],"genre_scores_gemma":[0.9713707,0.00030225058,0.026832156,0.0013413754,0.00013319227,0.0000026249052,3.7532155e-7,0.0000064870355,0.000010824526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992004,0.0032600875,0.004167296,0.00014862523,0.00019292877,0.0002271022],"domain_scores_gemma":[0.8795268,0.11730492,0.002598664,0.00025328045,0.00022661102,0.00008973082],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029629534,0.00012680267,0.0018840897,0.000057152713,0.00003276863,0.0000055549153,0.00032766495,0.0002486162,0.000019542467],"category_scores_gemma":[0.123513445,0.00007438318,0.00021414223,0.00008268531,0.0014430747,0.00012323409,0.00006161869,0.0009424901,8.3669994e-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":[0.00032627955,0.00035612856,0.12360953,0.00008273204,0.000058277124,0.000021645801,0.0010609478,0.00004423637,0.00006641869,0.87172824,0.0012302306,0.0014153142],"study_design_scores_gemma":[0.0009607272,0.0009986286,0.036867227,0.00017202689,0.00002718473,0.000096235766,0.0010765909,0.000027879903,0.000085174644,0.958492,0.001127301,0.00006903727],"about_ca_topic_score_codex":0.000022059772,"about_ca_topic_score_gemma":0.00007559788,"teacher_disagreement_score":0.11404483,"about_ca_system_score_codex":0.000052908745,"about_ca_system_score_gemma":0.00018499672,"threshold_uncertainty_score":0.9992006},"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":"W4239929951","doi":"10.1002/0470011815.b2a09015","title":"Explanatory Variables","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","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":"Cancer Care Ontario","funders":"","keywords":"Explanatory model; Econometrics; Variable (mathematics); Variables; Statistics; Outcome (game theory); Psychology; Mathematics; Mathematical economics","score_opus":0.04665118484793098,"score_gpt":0.35852777983559364,"score_spread":0.3118765949876627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239929951","genre_codex":"other","genre_gemma":"methods","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":[0.0000015610481,0.00057432783,0.13801081,0.000014780333,0.00028770207,0.00031574583,0.0012481193,0.0005617787,0.8589852],"genre_scores_gemma":[0.000019414278,0.0034455678,0.5326541,0.00003194631,0.0003778905,0.000024439136,0.00008603378,0.00045328191,0.46290734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984838,0.00005338623,0.0005210017,0.00030554962,0.00034619984,0.00029005963],"domain_scores_gemma":[0.9979252,0.00064211997,0.0006574199,0.00061349047,0.00006951318,0.000092259266],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015313458,0.00037722386,0.0006262318,0.00028289488,0.000019936579,0.000007552766,0.00034384243,0.0004256903,0.0070566633],"category_scores_gemma":[0.0008815132,0.0003681416,0.00006345438,0.00013417799,0.00017349827,0.000036720525,0.00009078962,0.00027747382,0.0000832923],"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":[0.0000025722582,0.000058353704,0.000017415477,0.00026544876,0.00004116723,0.000013508678,0.00005468488,1.3991787e-7,0.000009372854,0.23036683,0.7599806,0.009189902],"study_design_scores_gemma":[0.00011507933,0.000050240906,0.0000065444456,0.00033805185,0.00008741761,0.0000036355898,0.000029021056,0.0000063711286,0.00014242611,0.13175422,0.8671016,0.0003654082],"about_ca_topic_score_codex":0.00005954025,"about_ca_topic_score_gemma":0.00010952704,"teacher_disagreement_score":0.39607784,"about_ca_system_score_codex":0.000052397514,"about_ca_system_score_gemma":0.00012385764,"threshold_uncertainty_score":0.99987704},"labels":[],"label_agreement":null},{"id":"W4240041394","doi":"10.31234/osf.io/kdurz","title":"Measurement Practices in Large-Scale Replications: Insights from Many Labs 2","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"McGill University","keywords":"Replication (statistics); Interpretability; Reliability (semiconductor); Construct validity; Scale (ratio); Psychology; Applied psychology; Construct (python library); Sample (material); Data science; Psychometrics; Computer science; Clinical psychology; Statistics; Artificial intelligence; Mathematics; Geography; Cartography","score_opus":0.32815826370906565,"score_gpt":0.44358004137673246,"score_spread":0.11542177766766681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240041394","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":[0.029058615,0.0018475754,0.8695836,0.008177755,0.00033437277,0.0037793417,0.00012799281,0.003213516,0.08387721],"genre_scores_gemma":[0.5044718,0.00031671225,0.49299666,0.0006162162,0.0001727399,0.0010155427,0.00008304515,0.000077601726,0.00024971578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971143,0.000192677,0.00080796785,0.00095871015,0.00067471276,0.0002516284],"domain_scores_gemma":[0.9963958,0.00035945178,0.001188496,0.0016193631,0.000330173,0.00010668596],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055140606,0.0003678057,0.0005955912,0.00013759846,0.000048978036,0.00009217174,0.0006596113,0.0004027183,0.0002474318],"category_scores_gemma":[0.0035383818,0.00033701272,0.000101852725,0.00019070924,0.00003437563,0.00023629703,0.0011118943,0.001119045,0.00010107502],"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":[0.00016126686,0.0027768584,0.0050826883,0.0018701244,0.00056165183,0.00011991138,0.011745064,0.000057360652,0.018453095,0.9186165,0.037597854,0.002957658],"study_design_scores_gemma":[0.00017550557,0.000024092662,0.0011204903,0.00050065323,0.00006328438,6.476709e-7,0.00043095308,0.0011460914,0.012333209,0.9763867,0.0074190823,0.00039929312],"about_ca_topic_score_codex":0.00038086355,"about_ca_topic_score_gemma":0.002927713,"teacher_disagreement_score":0.47541314,"about_ca_system_score_codex":0.00044168186,"about_ca_system_score_gemma":0.00022069894,"threshold_uncertainty_score":0.9999082},"labels":[],"label_agreement":null},{"id":"W4240909061","doi":"10.3410/f.733103952.793546483","title":"Faculty Opinions recommendation of Targeted maximum likelihood estimation for a binary treatment: A tutorial.","year":2018,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","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","funders":"","keywords":"Binary number; Maximum likelihood; Estimation; Computer science; Statistics; Medical physics; Mathematics; Medicine; Engineering","score_opus":0.09407374734897496,"score_gpt":0.438819592337892,"score_spread":0.344745844988917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240909061","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.77482e-7,0.00036223157,0.00327049,0.052638557,0.0011898166,0.004095283,0.9382474,0.00016712766,0.00002880848],"genre_scores_gemma":[0.0000014984305,0.00025280967,0.050048236,0.0008072575,0.0005491609,0.0016141294,0.94630045,0.000056703917,0.00036973436],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949875,0.0004309764,0.0021734901,0.00078746554,0.0011416294,0.00047894404],"domain_scores_gemma":[0.9865426,0.0005917381,0.002816746,0.0018639049,0.007918696,0.00026633628],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015293398,0.0007575703,0.0014024357,0.0004776872,0.0002852256,0.00011470916,0.0013715612,0.0010111885,0.0002921673],"category_scores_gemma":[0.018639104,0.00049375434,0.00081667874,0.0016870457,0.00037946523,0.000526705,0.0003471412,0.0005973652,0.0000214409],"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":[0.00003692845,0.0007456554,3.6294418e-7,0.00817295,0.00019478056,1.39104e-7,0.0001237736,5.0870202e-8,0.000005931774,0.0013750879,0.98515034,0.0041940203],"study_design_scores_gemma":[0.00094079383,0.0008164457,0.00002403705,0.010636946,0.00044060856,0.000016458085,0.000015917049,0.000057537913,0.00016174397,0.010928876,0.9755265,0.00043413232],"about_ca_topic_score_codex":0.00003807116,"about_ca_topic_score_gemma":0.000007853484,"teacher_disagreement_score":0.0518313,"about_ca_system_score_codex":0.00037515484,"about_ca_system_score_gemma":0.0007095784,"threshold_uncertainty_score":0.9997514},"labels":[],"label_agreement":null},{"id":"W4241024539","doi":"10.2458/azu_jmmss.v1i2.100","title":"Patterns of Enrollment in Randomized and Preference Trials of Behavioral Treatments for Insomnia","year":2011,"lang":"en","type":"article","venue":"Journal of Methods and Measurement in the Social Sciences","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":"Université de Montréal; Toronto Metropolitan University","funders":"National Institute of Nursing Research; National Institutes of Health; U.S. Department of Veterans Affairs","keywords":"Randomized controlled trial; Insomnia; Context (archaeology); Medicine; Physical therapy; Representativeness heuristic; Psychology; Clinical psychology; Psychiatry; Internal medicine; Social psychology","score_opus":0.8256298650630722,"score_gpt":0.6032540980458749,"score_spread":0.2223757670171973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241024539","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":[0.9410811,0.000499821,0.05718805,0.0000765991,0.00006192764,0.0009192812,0.000006178294,0.000002259228,0.00016479545],"genre_scores_gemma":[0.7632688,0.0003379725,0.23633765,0.000007975617,0.000012825181,0.00003099095,3.9571287e-8,0.0000021825213,0.0000015615047],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99640745,0.0019385712,0.0010553675,0.000085587424,0.0003960252,0.00011701704],"domain_scores_gemma":[0.9970797,0.001473844,0.0012209646,0.00004887737,0.00015747575,0.000019173376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0475145,0.00008793658,0.0008808828,0.00013907098,0.000048448568,0.000009995674,0.00018527791,0.00004632455,0.0000056978583],"category_scores_gemma":[0.0021399423,0.000045939316,0.00012902543,0.000095896525,0.00020507061,0.00012277464,0.000022907887,0.000078427845,3.2092093e-9],"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":[0.024848979,0.004359458,0.05220837,0.0005844538,0.000501669,0.000005256108,0.20296986,0.000002061656,0.119042814,0.12731807,0.000055504206,0.4681035],"study_design_scores_gemma":[0.0288647,0.0015332779,0.00850415,0.0004877265,0.00042581485,0.0000043390974,0.009420209,0.000011124589,0.065503076,0.88510853,0.0000115423445,0.00012549984],"about_ca_topic_score_codex":0.00013088323,"about_ca_topic_score_gemma":0.00006194211,"teacher_disagreement_score":0.75779045,"about_ca_system_score_codex":0.000035548685,"about_ca_system_score_gemma":0.0000681587,"threshold_uncertainty_score":0.98078424},"labels":[],"label_agreement":null},{"id":"W4242075296","doi":"10.1007/978-1-0716-1138-8_9","title":"Longitudinal Studies 4: Matching Strategies to Evaluate Risk","year":2021,"lang":"en","type":"book-chapter","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Calgary","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Matching (statistics); Psychological intervention; Contrast (vision); Outcome (game theory); Medicine; Econometrics; Statistics; Computer science; Mathematics; Artificial intelligence","score_opus":0.3028601004233612,"score_gpt":0.5709415834095312,"score_spread":0.26808148298616996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242075296","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":[0.00015957654,0.008148379,0.9322862,0.00008147652,0.0002736173,0.00052945124,0.000026441532,0.00019741591,0.05829741],"genre_scores_gemma":[0.00006172246,0.002215663,0.9864684,0.00014876628,0.00007200495,0.00013686896,0.000017446417,0.00012157117,0.010757585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962972,0.0012702267,0.00083146547,0.0009271374,0.00019547678,0.000478504],"domain_scores_gemma":[0.9963726,0.001858466,0.00045287423,0.00091431197,0.0003220857,0.000079704965],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003184288,0.00063789345,0.0014502136,0.00040142212,0.00006908662,0.000035697874,0.0004346189,0.0006697966,0.0001679343],"category_scores_gemma":[0.002750641,0.0005876537,0.0002435547,0.000103475926,0.00024522416,0.000058649675,0.0007022026,0.0011080498,0.000018038545],"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":[0.000015662155,0.000015176939,0.000015465297,0.0001511395,0.00030634395,0.00021482068,0.0002961152,0.000055121647,0.018952444,0.95562065,0.00004706665,0.024309978],"study_design_scores_gemma":[0.00011740034,0.00019014053,0.0000037030813,0.0004158768,0.00017734102,0.000026383743,0.00021703284,0.0000067103338,0.010397524,0.981908,0.005981855,0.00055799494],"about_ca_topic_score_codex":0.000017388811,"about_ca_topic_score_gemma":0.00012482771,"teacher_disagreement_score":0.054182142,"about_ca_system_score_codex":0.00024185763,"about_ca_system_score_gemma":0.00013672662,"threshold_uncertainty_score":0.9996575},"labels":[],"label_agreement":null},{"id":"W4242730459","doi":"10.1093/pch/16.suppl_a.9aa","title":"PDA Treatment and Mortality/Morbidity: Regression and Propensity Score Based Analyses after Adjustment for Treatment Selection Bias","year":2011,"lang":"en","type":"article","venue":"Paediatrics & Child Health","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":"Mount Sinai Hospital","funders":"","keywords":"Propensity score matching; Selection bias; Selection (genetic algorithm); Regression; Statistics; Medicine; Internal medicine; Computer science; Mathematics; Machine learning","score_opus":0.45235353733181244,"score_gpt":0.4477917747817245,"score_spread":0.004561762550087944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242730459","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":[0.9770298,0.0024807062,0.01647478,0.00032934765,0.00009929145,0.0030529338,0.000107090425,0.000294131,0.00013189955],"genre_scores_gemma":[0.9387609,0.0051747025,0.054788645,0.00030241197,0.00021374319,0.0006250431,0.000045426805,0.000045644832,0.000043491393],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983037,0.00015587815,0.00044575677,0.0005162083,0.00017711142,0.0004013062],"domain_scores_gemma":[0.99869525,0.00023609232,0.0003683651,0.00032560818,0.000112517075,0.00026217743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003868691,0.00035664163,0.0006078468,0.00019829716,0.00026517978,0.000024959774,0.000053125637,0.00012244777,0.000018038882],"category_scores_gemma":[0.00013048628,0.00024298525,0.00009798505,0.00021206893,0.00005749386,0.00013824302,0.000038804727,0.00008817039,0.000001118828],"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":[0.0007895704,0.0029541934,0.90685534,0.0013296463,0.00030055115,0.000017535596,0.003233861,0.0000055992737,0.000100303936,0.005877141,0.000848156,0.0776881],"study_design_scores_gemma":[0.005517272,0.014241805,0.87808406,0.0005256667,0.0014973496,0.000048967253,0.00020997033,0.0014167771,0.020730587,0.075131394,0.0013185304,0.0012776034],"about_ca_topic_score_codex":0.000992813,"about_ca_topic_score_gemma":0.0015730038,"teacher_disagreement_score":0.076410495,"about_ca_system_score_codex":0.00057739095,"about_ca_system_score_gemma":0.00022784177,"threshold_uncertainty_score":0.9908651},"labels":[],"label_agreement":null},{"id":"W4243433825","doi":"10.1515/iupac.79.2239","title":"Rate in Epidemiology","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","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":"University of Toronto","funders":"","keywords":"Terminology; Glossary; Chemical nomenclature; Relation (database); Meaning (existential); Computer science; Biostatistics; Management science; Epistemology; Chemistry; Medicine; Epidemiology; Linguistics; Engineering; Pathology; Philosophy; Data mining","score_opus":0.1529037961759136,"score_gpt":0.5649988680680189,"score_spread":0.4120950718921053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243433825","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004976636,0.00028939746,0.01069579,0.0007636435,0.00027541403,0.00044762678,0.9871813,0.00022992348,0.00006715061],"genre_scores_gemma":[0.0000073980545,0.0016618688,0.00461268,0.00051274407,0.00038594965,0.00007280154,0.9924016,0.000061536084,0.00028342596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965695,0.0006135531,0.0011323341,0.0006164536,0.00034938636,0.00071873056],"domain_scores_gemma":[0.9943097,0.0033997272,0.00062243105,0.0012245975,0.00030451076,0.0001389826],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037328799,0.0005317264,0.0014671725,0.0003884723,0.00003938942,0.000009948446,0.0006002572,0.0007521468,0.0019237861],"category_scores_gemma":[0.021745047,0.00039017978,0.0001495603,0.00021202894,0.00023854143,0.00011185118,0.00026774,0.0009051629,0.0000033055949],"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":[0.000061736115,0.00012510904,0.000017719982,0.00016516287,0.000028228429,0.000077729404,0.000005191071,3.3031534e-7,0.000009288655,0.0029090361,0.9946801,0.0019203604],"study_design_scores_gemma":[0.00029721038,0.00011295936,0.00001107819,0.00056616217,0.000024880801,0.000006102724,0.0000049004216,0.0000017981893,0.000029653667,0.34476578,0.65388083,0.00029864316],"about_ca_topic_score_codex":0.000077492536,"about_ca_topic_score_gemma":0.0018306753,"teacher_disagreement_score":0.34185675,"about_ca_system_score_codex":0.00074039627,"about_ca_system_score_gemma":0.00046385714,"threshold_uncertainty_score":0.999855},"labels":[],"label_agreement":null},{"id":"W4245375786","doi":"10.1002/dc.10020.abs","title":"Comment on Gopez et al.","year":2002,"lang":"en","type":"article","venue":"Diagnostic Cytopathology","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":"Mount Sinai Hospital","funders":"","keywords":"Medicine","score_opus":0.1492254624954979,"score_gpt":0.40266194453230414,"score_spread":0.25343648203680624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245375786","genre_codex":"commentary","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":[0.20237748,0.00088969036,0.20392685,0.40651605,0.0015526287,0.0030850368,0.00018061866,0.0042986297,0.177173],"genre_scores_gemma":[0.8047905,0.00073392043,0.0334416,0.16025218,0.00005155908,0.00034328745,0.000014865585,0.00006697865,0.00030509455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987026,0.00019267932,0.00028751945,0.00031526343,0.00016441924,0.0003375335],"domain_scores_gemma":[0.99337155,0.0058583287,0.00010198521,0.0005413864,0.00004883513,0.000077939745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003525028,0.00020357843,0.00030240786,0.00009274551,0.000059926457,0.000015295735,0.00022110622,0.000094538365,0.00093006983],"category_scores_gemma":[0.005850484,0.00018518892,0.00005993018,0.00010148733,0.00010904805,0.000066489694,0.000107091015,0.00031478927,0.0007189685],"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":[0.0000059179733,0.00045038364,0.0012013827,0.000012231284,0.0000065006693,0.00040777973,0.00039208774,0.0000038471385,0.0002912693,0.50989205,0.482194,0.005142536],"study_design_scores_gemma":[0.00073449913,0.001162747,0.0022004503,0.0001875224,0.000038358314,0.00023334056,0.000079945064,0.0001572433,0.0073236614,0.5493844,0.4379276,0.0005701979],"about_ca_topic_score_codex":0.000004914276,"about_ca_topic_score_gemma":0.0000071955174,"teacher_disagreement_score":0.602413,"about_ca_system_score_codex":0.000062389576,"about_ca_system_score_gemma":0.000005510465,"threshold_uncertainty_score":0.9999832},"labels":[],"label_agreement":null},{"id":"W4246230500","doi":"10.1007/978-1-59745-385-1_2","title":"Longitudinal Studies and Determination of Risk","year":2008,"lang":"en","type":"book-chapter","venue":"Methods in molecular biology","topic":"Advanced Causal Inference Techniques","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":"Memorial University of Newfoundland; St. John’s Health Sciences Centre","funders":"","keywords":"Observational study; Confounding; Casual; Selection bias; Computer science; Clinical study design; Risk analysis (engineering); Psychology; Medicine; Statistics; Clinical trial; Mathematics","score_opus":0.23388482166872585,"score_gpt":0.5290002017369217,"score_spread":0.29511538006819593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246230500","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":[0.00015137382,0.011314662,0.9770771,0.000007873443,0.000060329472,0.00023326805,0.000014300778,0.00004726257,0.011093786],"genre_scores_gemma":[0.00015065487,0.01256407,0.9859217,0.0000131617935,0.000016421267,0.000022706525,0.0000046408477,0.000038039816,0.0012686499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985589,0.00037273552,0.0004967478,0.00034971946,0.00007091396,0.00015098971],"domain_scores_gemma":[0.99731755,0.0016858552,0.00050154334,0.00033205666,0.00014047952,0.000022510065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008950259,0.00026741825,0.0007957324,0.00028413668,0.000023455988,0.0000017069407,0.00013103339,0.00045641966,0.000011571902],"category_scores_gemma":[0.0025799142,0.00024106336,0.00008452143,0.00003292921,0.00052567496,0.000022448203,0.00018952525,0.00038005452,5.9273304e-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":[0.00002213157,0.000018226921,0.0002846904,0.00031790364,0.00010858312,0.00008870139,0.00039004182,3.7271315e-7,0.011843692,0.69278646,0.000021553633,0.29411763],"study_design_scores_gemma":[0.000103445025,0.00014232498,0.000019444291,0.00016704667,0.00007065318,0.000034270153,0.00000991054,0.000009484146,0.02022655,0.9776513,0.0013621704,0.0002033854],"about_ca_topic_score_codex":0.0000038027829,"about_ca_topic_score_gemma":0.000016683098,"teacher_disagreement_score":0.29391423,"about_ca_system_score_codex":0.00005489483,"about_ca_system_score_gemma":0.000018598193,"threshold_uncertainty_score":0.9830278},"labels":[],"label_agreement":null},{"id":"W4246504292","doi":"10.1007/978-94-007-0753-5_104098","title":"Surrogate Endpoint","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Surrogate endpoint; Medicine; Internal medicine","score_opus":0.195517714390595,"score_gpt":0.38931771190457615,"score_spread":0.19379999751398114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246504292","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012202614,0.000023664647,0.17678827,0.00007327089,0.00006959334,0.00022493501,0.000012000797,0.0009931413,0.8218139],"genre_scores_gemma":[0.00038364064,0.000079887686,0.08386682,0.00019388752,0.00014006229,0.00001459312,0.000017256423,0.00012018759,0.91518366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883354,0.000010466194,0.00038298263,0.00031271102,0.00024638712,0.00021392824],"domain_scores_gemma":[0.9984714,0.0003798852,0.00024477634,0.0007153602,0.00010685426,0.00008177004],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022981172,0.00036475997,0.00050937623,0.00010275784,0.000031095984,0.000019680816,0.0002472123,0.00038201633,0.006399881],"category_scores_gemma":[0.0001259892,0.00030743185,0.00015900924,0.000008633114,0.00008501167,0.00003835942,0.0001385737,0.00039681286,0.00082653714],"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":[0.0000026734144,0.0000033729877,1.8901827e-7,0.00005335195,0.000020146543,0.000008178437,0.000010150516,4.566739e-8,0.000018165789,0.9725989,0.023076361,0.004208465],"study_design_scores_gemma":[0.00003499398,0.000033681117,1.4132203e-7,0.00008439021,0.000022804143,0.0000044053363,0.0000012352758,0.000003516325,0.00067935855,0.64186734,0.3570347,0.00023338677],"about_ca_topic_score_codex":0.0000028986153,"about_ca_topic_score_gemma":0.000028107124,"teacher_disagreement_score":0.33395836,"about_ca_system_score_codex":0.00007929976,"about_ca_system_score_gemma":0.00002795984,"threshold_uncertainty_score":0.9999514},"labels":[],"label_agreement":null},{"id":"W4249742129","doi":"10.31235/osf.io/znj38","title":"Moving Beyond Linear Regression: Implementing and Interpreting Quantile Regression Models with Fixed Effects","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"University of Alberta","funders":"","keywords":"Quantile regression; Econometrics; Quantile; Regression; Linear regression; Fixed effects model; Replication (statistics); Range (aeronautics); Regression analysis; Distribution (mathematics); Wage; Statistics; Economics; Computer science; Mathematics; Panel data; Engineering","score_opus":0.10072276198218039,"score_gpt":0.40986231130290957,"score_spread":0.3091395493207292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249742129","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":[0.10056499,0.0002991403,0.88710207,0.0003994201,0.00012937406,0.0014918272,0.000018276392,0.0017089709,0.008285923],"genre_scores_gemma":[0.46864185,0.00006403209,0.5306118,0.00013915212,0.00009461624,0.0001351772,0.000029514813,0.000108168104,0.00017568661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970029,0.00018934382,0.0007337648,0.0010314967,0.00048219418,0.0005602899],"domain_scores_gemma":[0.99679697,0.0011774554,0.00084316626,0.00080403755,0.00017971551,0.00019867969],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005250655,0.00071077794,0.0009825941,0.00015682637,0.0002218707,0.0001806351,0.00042780087,0.0004022729,0.00005619797],"category_scores_gemma":[0.0008421082,0.00048182934,0.0001181987,0.00014286173,0.00009675717,0.00033382667,0.00344233,0.0013499155,0.0000026064054],"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":[0.0016288618,0.00065075234,0.0056475154,0.04550918,0.0014611633,0.0012934731,0.025786314,0.0012096219,0.13022186,0.6255753,0.026865326,0.13415061],"study_design_scores_gemma":[0.00054520636,0.00031642927,0.000009460088,0.016664503,0.00018378076,0.000032908803,0.0008867904,0.15455045,0.09955193,0.726009,0.00012729432,0.0011222634],"about_ca_topic_score_codex":0.000045697,"about_ca_topic_score_gemma":0.00002458369,"teacher_disagreement_score":0.36807686,"about_ca_system_score_codex":0.00009430891,"about_ca_system_score_gemma":0.00009113428,"threshold_uncertainty_score":0.9997633},"labels":[],"label_agreement":null},{"id":"W4253624503","doi":"10.1002/9780470061596.risk0640","title":"Causality/Causation","year":2008,"lang":"en","type":"other","venue":"Encyclopedia of Quantitative Risk Analysis and Assessment","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":"University of Alberta","funders":"","keywords":"Causation; Causal inference; Causality (physics); Causal model; Inference; Causal structure; Epistemology; Causal reasoning; Confounding; Computer science; Psychology; Econometrics; Artificial intelligence; Mathematics; Cognition; Philosophy; Statistics","score_opus":0.09429476792521993,"score_gpt":0.4436265571106523,"score_spread":0.3493317891854324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253624503","genre_codex":"other","genre_gemma":"methods","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":[0.0015573723,0.0011663362,0.4081086,0.000031434385,0.00006291828,0.00045454822,0.00032450462,0.00023005347,0.58806425],"genre_scores_gemma":[0.005985963,0.11763891,0.7441087,0.0000140913735,0.00010601689,0.00011246226,0.00020460207,0.00032018236,0.1315091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978098,0.00034503947,0.0006565047,0.0004921501,0.00047589143,0.00022057001],"domain_scores_gemma":[0.99702555,0.0007552509,0.0015102777,0.00048461874,0.00013878456,0.000085523476],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004780642,0.0003918763,0.0012099223,0.0009226724,0.00007360721,0.000014890036,0.00015849908,0.00023031612,0.0007207791],"category_scores_gemma":[0.00033305032,0.00033432228,0.00028076224,0.0007932736,0.00022571138,0.000084472376,0.000083271865,0.000361756,0.000005277505],"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":[0.000026884163,0.00087450916,0.0974591,0.0006716961,0.013296459,0.000037714486,0.0016730289,0.000023584787,0.000073253985,0.6103028,0.25537005,0.020190937],"study_design_scores_gemma":[0.0012192029,0.00132043,0.06600747,0.00090530363,0.021368258,0.000005505737,0.0020803374,0.002026737,0.00036474777,0.37605804,0.5256213,0.00302265],"about_ca_topic_score_codex":0.0012217895,"about_ca_topic_score_gemma":0.0013697859,"teacher_disagreement_score":0.45655516,"about_ca_system_score_codex":0.00006310991,"about_ca_system_score_gemma":0.00009988594,"threshold_uncertainty_score":0.9999109},"labels":[],"label_agreement":null},{"id":"W4254941116","doi":"10.2139/ssrn.2895032","title":"Targeting Policies: Multiple Testing and Distributional Treatment Effects","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of British Columbia Hospital; University of British Columbia; Queen's University","funders":"","keywords":"Econometrics; Economics; Actuarial science","score_opus":0.09878109757502405,"score_gpt":0.38931883459932987,"score_spread":0.2905377370243058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254941116","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":[0.71116644,0.0008077115,0.28632253,0.00042669676,0.00009192604,0.00035584744,0.000010871769,0.00020054656,0.00061742886],"genre_scores_gemma":[0.9793865,0.000566126,0.019555127,0.000012141688,0.00024105051,0.0000195812,0.0000022710267,0.00002217317,0.00019500908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807066,0.000046813,0.00021953412,0.0001601397,0.00015367422,0.0013491575],"domain_scores_gemma":[0.9983952,0.0008710873,0.00033717058,0.00022103648,0.00009289592,0.000082575774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007189159,0.00017858896,0.00021313904,0.000041219762,0.000989345,0.00013841671,0.00020945189,0.000062521576,0.0000035112548],"category_scores_gemma":[0.005282153,0.00014122139,0.00005132479,0.000031705342,0.000100717334,0.00026748623,0.00007535214,0.0006466257,0.0000035902788],"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":[0.00004202629,0.00018052968,0.05767207,0.00004267216,0.00020220918,0.000020600548,0.00024267272,0.000010609592,0.014074247,0.87583214,0.0000753388,0.051604897],"study_design_scores_gemma":[0.00063193246,0.0004252457,0.002289126,0.00006623868,0.000036162703,0.00028361264,0.00018488846,0.00043658615,0.0021201815,0.99325246,0.00010318,0.00017037403],"about_ca_topic_score_codex":0.00012370414,"about_ca_topic_score_gemma":0.00012539001,"teacher_disagreement_score":0.2682201,"about_ca_system_score_codex":0.0010293992,"about_ca_system_score_gemma":0.00044402378,"threshold_uncertainty_score":0.7609342},"labels":[],"label_agreement":null},{"id":"W4255302121","doi":"10.1002/9781118445112.stat08046","title":"<scp>G</scp>‐Estimation","year":2017,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","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":"University of Waterloo; McGill University","funders":"","keywords":"Marginal structural model; Estimation; Context (archaeology); Econometrics; Computer science; Event (particle physics); Nested set model; Regression; Statistics; Confounding; Mathematics; Data mining; Economics; Geography","score_opus":0.16552744788920212,"score_gpt":0.4393178890863048,"score_spread":0.2737904411971027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255302121","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":[0.000009130928,0.00053539296,0.6930097,0.00002206421,0.00036148776,0.00085197744,0.026493795,0.0016261552,0.27709034],"genre_scores_gemma":[0.00003600871,0.0027267528,0.5705559,0.000055379613,0.00025995588,0.000087651635,0.0048659327,0.0007731072,0.42063928],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960301,0.00016002203,0.00086372613,0.0010178596,0.0009972415,0.00093107973],"domain_scores_gemma":[0.99329406,0.0015876832,0.0021129097,0.0022523103,0.0004027162,0.0003503243],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034045757,0.0010822252,0.0013488303,0.0005676738,0.00023830583,0.00020452778,0.0012951957,0.0009162937,0.00087807805],"category_scores_gemma":[0.007434683,0.0010348677,0.00010204638,0.0001768349,0.000516493,0.00016879676,0.00036387602,0.0012190902,0.00033115034],"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":[0.0000041648586,0.00022353155,0.000011677524,0.00048558784,0.00009953802,0.000072374256,0.000066885244,0.0000036269926,0.0000203915,0.1703511,0.79468364,0.033977512],"study_design_scores_gemma":[0.0003106321,0.00017753147,0.000015236917,0.0016541672,0.00016054534,0.000012568074,0.000044800294,0.00095428084,0.00004486692,0.4202275,0.5760214,0.0003764798],"about_ca_topic_score_codex":0.0002890524,"about_ca_topic_score_gemma":0.0020523928,"teacher_disagreement_score":0.24987641,"about_ca_system_score_codex":0.00024379438,"about_ca_system_score_gemma":0.0004157306,"threshold_uncertainty_score":0.9992102},"labels":[],"label_agreement":null},{"id":"W4255808401","doi":"10.1002/9781118445112.stat03727","title":"Causality/Causation","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","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":"University of Alberta","funders":"","keywords":"Causation; Causal inference; Causality (physics); Causal model; Inference; Causal structure; Epistemology; Causal reasoning; Computer science; Psychology; Artificial intelligence; Econometrics; Mathematics; Cognition; Philosophy; Statistics","score_opus":0.1732879190351021,"score_gpt":0.4376534903414204,"score_spread":0.2643655713063183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255808401","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":[0.000014487932,0.00028309377,0.83997816,0.000075238684,0.0004023033,0.00096350873,0.021336652,0.0022864102,0.13466017],"genre_scores_gemma":[0.0002774483,0.0018728878,0.69459784,0.00021294063,0.0005777836,0.0001168508,0.007842146,0.0012901938,0.29321194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956652,0.0003196955,0.0011334509,0.0010403652,0.0009857025,0.00085558114],"domain_scores_gemma":[0.9953201,0.0010089605,0.0013696885,0.0015864914,0.00039215005,0.0003225994],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004476946,0.0010314706,0.0013516188,0.0005886353,0.00010804421,0.00009346608,0.000739536,0.00086788647,0.0060358816],"category_scores_gemma":[0.0018563513,0.0009786924,0.000090746835,0.00035045983,0.00036019337,0.000102593716,0.00024089418,0.0011131043,0.00050208566],"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":[0.000014166048,0.00019664866,0.000023489094,0.0004632811,0.00008740482,0.000025645899,0.000038278868,0.000001125221,0.00005809652,0.35991895,0.6267585,0.012414397],"study_design_scores_gemma":[0.00034880787,0.00024437695,0.000024192,0.0009915002,0.00017156554,0.00000979921,0.000033710065,0.00024950522,0.00005872805,0.4980443,0.4988489,0.00097462826],"about_ca_topic_score_codex":0.0003953482,"about_ca_topic_score_gemma":0.0033276347,"teacher_disagreement_score":0.15855177,"about_ca_system_score_codex":0.00028373176,"about_ca_system_score_gemma":0.00029199707,"threshold_uncertainty_score":0.9992663},"labels":[],"label_agreement":null},{"id":"W4280489194","doi":"10.1002/jrsm.1569","title":"Causal assessment in evidence synthesis: A methodological review of reviews","year":2022,"lang":"en","type":"review","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"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":"Medical Research Council; Medical Research Council Canada; Chief Scientist Office; Wellcome Trust","keywords":"Viewpoints; Systematic review; Causal inference; Causality (physics); Transparency (behavior); Population; Computer science; MEDLINE; Data science; Management science; Medicine; Pathology; Political science; Environmental health; Engineering","score_opus":0.9459944482734105,"score_gpt":0.7674090534540664,"score_spread":0.1785853948193441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280489194","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":[4.591808e-8,0.9348742,0.055482447,0.00016228705,0.00009738453,0.0064448398,0.000050418497,0.00017169527,0.0027166794],"genre_scores_gemma":[2.927868e-8,0.51603496,0.4679727,0.000022356988,0.000050327697,0.01571788,0.0000035551598,0.00010615459,0.00009200752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.73707956,0.24934563,0.006254393,0.0022134094,0.0032483125,0.0018586784],"domain_scores_gemma":[0.32853666,0.66284597,0.0031182987,0.0045564002,0.00051843596,0.0004242282],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28095433,0.0011383046,0.012613268,0.0018337197,0.00021701696,0.00005408562,0.0035640376,0.00075710873,0.0072549134],"category_scores_gemma":[0.67089033,0.00082993886,0.0019467302,0.004452846,0.00062295556,0.0003168854,0.002372064,0.0055103037,0.000031177064],"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":[0.000006941916,0.00018379194,4.4285818e-7,0.30734745,0.00009012221,0.00004423151,0.000018169076,2.5747307e-8,0.000010384843,0.0065182573,0.001732865,0.6840473],"study_design_scores_gemma":[0.000018190633,0.00010009328,4.5468664e-7,0.37044466,0.00069663255,0.00003364447,0.000025089545,0.0000038580097,0.00013433036,0.02587573,0.6022171,0.00045024866],"about_ca_topic_score_codex":0.000061555475,"about_ca_topic_score_gemma":0.000006562062,"teacher_disagreement_score":0.6835971,"about_ca_system_score_codex":0.0023051784,"about_ca_system_score_gemma":0.0021061,"threshold_uncertainty_score":0.99941516},"labels":[],"label_agreement":null},{"id":"W4280498397","doi":"10.1080/24709360.2022.2069457","title":"Doubly weighted estimating equations and weighted multiple imputation for causal inference with an incomplete subgroup variable","year":2022,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Missing data; Statistics; Observational study; Mathematics; Estimator; Causal inference; Inference; Imputation (statistics); Subgroup analysis; Variable (mathematics); Propensity score matching; Econometrics; Medicine; Computer science; Artificial intelligence","score_opus":0.18093787325331165,"score_gpt":0.4283506853874128,"score_spread":0.24741281213410113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280498397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02317812,0.000033014876,0.97384316,0.00026226757,0.00014177371,0.0010387157,0.0010742516,0.00037532684,0.000053398537],"genre_scores_gemma":[0.32296827,0.0000041111675,0.67525494,0.0002474019,0.00005566662,0.0005734715,0.0008312848,0.000043045624,0.000021824508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970446,0.0007452972,0.0008738036,0.0005932982,0.00017234383,0.00057061895],"domain_scores_gemma":[0.9722161,0.02620832,0.000698876,0.0003978069,0.00031661443,0.00016226343],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001968676,0.00031412588,0.00066412496,0.00018571244,0.0006854188,0.000025612497,0.00023907349,0.00012628296,0.0000793927],"category_scores_gemma":[0.010906924,0.0002913339,0.000029930174,0.00030158134,0.00024276934,0.00022309994,0.0001959698,0.00035859743,0.0000016866585],"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":[0.00017887524,0.00011968438,0.004409668,0.00010084015,0.00005049161,0.0000060388998,0.000380509,0.0012009707,0.00083371036,0.9883765,0.0005506751,0.0037920605],"study_design_scores_gemma":[0.00052148633,0.0008984138,0.00038434035,0.000016874677,0.0000551443,0.000020532372,0.00008156097,0.43214044,0.00004834503,0.56528324,0.0003196055,0.00023000226],"about_ca_topic_score_codex":0.00033470266,"about_ca_topic_score_gemma":0.00019259106,"teacher_disagreement_score":0.4309395,"about_ca_system_score_codex":0.00017790924,"about_ca_system_score_gemma":0.00016681821,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W4280620201","doi":"10.1016/j.jclinepi.2022.05.006","title":"Meta-analysis of multi-jurisdictional health administrative data from distributed networks approximated individual-level multivariable regression","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Calgary; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Agricultural Research Institute of Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Random effects model; Statistics; Odds ratio; Confidence interval; Odds; Logistic regression; Medicine; Regression analysis; Computer science; Econometrics; Mathematics; Internal medicine","score_opus":0.9644975495934363,"score_gpt":0.6988432325187129,"score_spread":0.2656543170747233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280620201","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":[0.0000010496814,0.53846085,0.4468517,0.00018154478,0.00031477003,0.00047293006,0.013670335,0.00003826924,0.000008527331],"genre_scores_gemma":[0.000010759474,0.658775,0.3325102,0.00021164118,0.00023166003,0.000048548292,0.008134147,0.00004942859,0.000028623374],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.94565076,0.030883687,0.020811792,0.0011746205,0.0008066706,0.00067244656],"domain_scores_gemma":[0.73497975,0.21767265,0.044275876,0.002101679,0.00045527532,0.0005147539],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.066462286,0.00086230837,0.034130365,0.00063782296,0.0001602163,0.000014912015,0.0029639488,0.0014862097,0.0021407688],"category_scores_gemma":[0.12307938,0.0005374643,0.0073552756,0.0014131601,0.00051258784,0.0002673013,0.0014716802,0.0053227446,0.0000020517386],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036797186,0.003449343,0.0003721925,0.0023329547,0.7564438,0.00009012095,0.000072939,0.0010206659,6.278289e-8,0.008001011,0.034120616,0.19372831],"study_design_scores_gemma":[0.0008847545,0.0011765428,0.00027786952,0.001790173,0.57369053,0.00007001803,0.000064976055,0.012504519,2.1343763e-7,0.05466473,0.35415554,0.0007201008],"about_ca_topic_score_codex":0.000095770316,"about_ca_topic_score_gemma":0.000044767017,"teacher_disagreement_score":0.32003492,"about_ca_system_score_codex":0.00024277047,"about_ca_system_score_gemma":0.0020087257,"threshold_uncertainty_score":0.9998101},"labels":[],"label_agreement":null},{"id":"W4281263407","doi":"10.1109/jbhi.2022.3175862","title":"Marginal Structural Models Using Calibrated Weights With SuperLearner: Application to Type II Diabetes Cohort","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","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":"St. Michael's Hospital; North York General Hospital; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type 2 diabetes; Machine learning; Medicine; Artificial intelligence; Context (archaeology); Causal inference; Metformin; Population; Diabetes mellitus; Computer science; Statistics; Mathematics; Endocrinology","score_opus":0.10088684928470844,"score_gpt":0.38704451659541,"score_spread":0.2861576673107016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281263407","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":[0.80013746,0.00006266208,0.19813465,0.0011184969,0.00011709225,0.00033316112,0.000018536064,0.000041744275,0.000036212758],"genre_scores_gemma":[0.78264487,0.000059330807,0.21592428,0.0012015625,0.00011639961,0.000010825591,0.0000101036985,0.000017925884,0.0000147299115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979436,0.000051400944,0.0009920903,0.00007002598,0.0006463222,0.00029656355],"domain_scores_gemma":[0.99857914,0.00007183189,0.00065174646,0.0001306923,0.00018736342,0.00037921328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093278126,0.00014032917,0.00039745256,0.00023251447,0.00039027826,0.000024038947,0.00018782922,0.000054945005,0.00003874145],"category_scores_gemma":[0.000027434799,0.00009710599,0.000027755677,0.0003974325,0.000095707495,0.0003868958,0.000093816314,0.00044949638,4.1590894e-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":[0.0042060763,0.0029170585,0.05428524,0.013436021,0.0023060415,0.00017756867,0.124729656,0.04665826,0.011095838,0.29684043,0.09108163,0.3522662],"study_design_scores_gemma":[0.0019188416,0.010806121,0.0008718351,0.00057052134,0.0001490534,0.0011287994,0.0028189975,0.7506135,0.00095749483,0.21526982,0.014108639,0.00078639324],"about_ca_topic_score_codex":0.000018298731,"about_ca_topic_score_gemma":0.00000199638,"teacher_disagreement_score":0.70395523,"about_ca_system_score_codex":0.0002067645,"about_ca_system_score_gemma":0.00036485068,"threshold_uncertainty_score":0.39598674},"labels":[],"label_agreement":null},{"id":"W4281956449","doi":"10.1111/biom.13683","title":"Reader reaction to “Outcome‐adaptive lasso: Variable selection for causal inference” by Shortreed and Ertefaie (2017)","year":2022,"lang":"en","type":"letter","venue":"Biometrics","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; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Causal inference; Propensity score matching; Estimator; Statistics; Confounding; Collinearity; Lasso (programming language); Econometrics; Outcome (game theory); Computer science; Inference; Mathematics; Artificial intelligence","score_opus":0.2340422227013879,"score_gpt":0.4155220545397822,"score_spread":0.1814798318383943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281956449","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":[0.0004377463,0.00020204175,0.95864594,0.029729312,0.0012219037,0.0037741505,0.0020685154,0.0013407818,0.0025795987],"genre_scores_gemma":[0.003675528,0.00029676475,0.81851554,0.13191687,0.0031292874,0.004744676,0.0041010524,0.0007518912,0.03286843],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966851,0.00013236499,0.000759321,0.0009196414,0.00077497045,0.0007286287],"domain_scores_gemma":[0.9952251,0.00302179,0.000579402,0.000544646,0.00048630717,0.00014276562],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008516604,0.0005972543,0.0008544382,0.0026707267,0.00028504568,0.0001338602,0.00037046205,0.0011407326,0.00015057261],"category_scores_gemma":[0.0042214566,0.0006128406,0.00011468798,0.004200074,0.000067343266,0.00028855682,0.000254422,0.0015145697,0.000010977039],"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":[0.0000530338,0.000074844684,0.00018106849,0.00022351513,0.00011190482,0.000008127246,0.000055128898,7.278375e-7,0.0026060857,0.0042147874,0.9904167,0.0020540853],"study_design_scores_gemma":[0.00029619387,0.0011895008,0.000030300847,0.000048560738,0.00024725558,0.000028390023,0.00005753447,0.0001517626,0.00096881186,0.046121538,0.9500311,0.00082902604],"about_ca_topic_score_codex":0.00028237325,"about_ca_topic_score_gemma":0.0000255199,"teacher_disagreement_score":0.14013045,"about_ca_system_score_codex":0.0011294218,"about_ca_system_score_gemma":0.00014970297,"threshold_uncertainty_score":0.9996323},"labels":[],"label_agreement":null},{"id":"W4282927183","doi":"10.1177/0272989x221100717","title":"A Machine-Learning Approach for Estimating Subgroup- and Individual-Level Treatment Effects: An Illustration Using the 65 Trial","year":2022,"lang":"en","type":"article","venue":"Medical Decision Making","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":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Health Technology Assessment Programme; Medical Research Council; National Institute for Health and Care Research","keywords":"Covariate; Overfitting; Medicine; Parametric statistics; Causal inference; Subgroup analysis; Machine learning; Confidence interval; Econometrics; Statistics; Computer science; Mathematics; Internal medicine","score_opus":0.32824647215952396,"score_gpt":0.4587967880202238,"score_spread":0.13055031586069982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282927183","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":[0.15554358,0.00006693715,0.8427238,0.000030923075,0.00014555377,0.0012692031,0.000013263738,0.00015702515,0.00004971512],"genre_scores_gemma":[0.43807986,0.000002921958,0.5612696,0.000071009694,0.00014732113,0.00037006263,0.000022237573,0.000027587868,0.000009397392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739796,0.000464995,0.0004946829,0.00037794316,0.0009771659,0.00028728048],"domain_scores_gemma":[0.9944075,0.0049033347,0.00028200768,0.00026470018,0.000041836585,0.00010063767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028934279,0.00021262452,0.0003338603,0.00011054287,0.00097236066,0.00011100252,0.00029525033,0.00010708278,0.000062900224],"category_scores_gemma":[0.006136669,0.0001436153,0.000079569996,0.00020215662,0.00007998808,0.00016356332,0.00028616763,0.0004450534,1.7761768e-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":[0.0019315052,0.00041069798,0.00011362563,0.00008826212,0.000057966015,0.000022360864,0.0023819911,0.004556196,0.00021236957,0.016899472,0.00005181935,0.97327375],"study_design_scores_gemma":[0.0055840947,0.0014140109,0.000015451642,0.00010317876,0.00008886874,0.00007273138,0.00047800795,0.8749583,0.00006722887,0.116898075,0.0001404486,0.00017964753],"about_ca_topic_score_codex":0.00001530222,"about_ca_topic_score_gemma":0.000007689817,"teacher_disagreement_score":0.9730941,"about_ca_system_score_codex":0.00018770686,"about_ca_system_score_gemma":0.00007900228,"threshold_uncertainty_score":0.74787104},"labels":[],"label_agreement":null},{"id":"W4282984288","doi":"10.5539/gjhs.v14n7p32","title":"Cumulative Equivalence: Controlling for Inter-Individual Differences at Baseline Characteristic Testing of RCTs","year":2022,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Comparability; Randomization; Equivalence (formal languages); Randomized controlled trial; Medicine; Baseline (sea); Cumulative incidence; Intervention (counseling); Gold standard (test); Statistics; Mathematics; Surgery","score_opus":0.2835429106626777,"score_gpt":0.4721793295214461,"score_spread":0.18863641885876836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282984288","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":[0.7710342,0.00025174292,0.22694539,0.0004645336,0.00042896596,0.0004963764,0.00026336525,0.000038752496,0.00007668748],"genre_scores_gemma":[0.8994073,0.000013035963,0.10032039,0.00017179186,0.00005597671,0.000014471151,0.000001115165,0.000006691364,0.0000092204355],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966475,0.00017344554,0.0013250608,0.00023714786,0.0010994646,0.0005174106],"domain_scores_gemma":[0.9941068,0.0020270408,0.0026440166,0.00018624654,0.00084581383,0.00019006095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007299585,0.00016156283,0.0006264607,0.00016402244,0.0006294931,0.000033308872,0.0008886591,0.000024330622,0.000041419527],"category_scores_gemma":[0.008101042,0.00013175502,0.000094117044,0.00070720236,0.0003894026,0.000348423,0.0003930272,0.00025139668,3.544802e-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":[0.002894685,0.0026034699,0.3876863,0.003225039,0.000301237,0.0001391094,0.006656353,0.0025525724,0.051280275,0.16885406,0.004039281,0.3697676],"study_design_scores_gemma":[0.003589014,0.01656654,0.078207724,0.004342494,0.00023931872,0.0023406057,0.0047415528,0.046232224,0.0071225334,0.8348936,0.00050962035,0.0012147855],"about_ca_topic_score_codex":0.000019545925,"about_ca_topic_score_gemma":0.0000035555875,"teacher_disagreement_score":0.6660395,"about_ca_system_score_codex":0.0007697751,"about_ca_system_score_gemma":0.0009701566,"threshold_uncertainty_score":0.969829},"labels":[],"label_agreement":null},{"id":"W4283268556","doi":"10.1002/pds.5500","title":"Machine learning for improving high‐dimensional proxy confounder adjustment in healthcare database studies: An overview of the current literature","year":2022,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"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 Agency for Drugs and Technologies in Health; McGill University; McGill University Health Centre","funders":"National Institute on Aging; International Society for Pharmacoepidemiology","keywords":"Confounding; Proxy (statistics); Prioritization; Covariate; Medicine; Feature selection; Computer science; Data mining; Machine learning; Management science","score_opus":0.43556118693804624,"score_gpt":0.5536874237850973,"score_spread":0.11812623684705104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283268556","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":[0.0000066923217,0.99409103,0.00072381174,0.00047838993,0.00063768757,0.0030599406,0.0009173722,0.000080001206,0.0000050873623],"genre_scores_gemma":[0.000068801324,0.99147296,0.0054834564,0.00052371935,0.0001399297,0.001220015,0.0009959833,0.00005740976,0.00003769605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99200106,0.0049370937,0.0016557644,0.00074747106,0.00019141276,0.00046722367],"domain_scores_gemma":[0.9872992,0.0104970215,0.001468757,0.00049763126,0.00013047902,0.000106877764],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006156906,0.0005835233,0.0026496036,0.00015683111,0.00030355234,0.0000050408535,0.00040486816,0.00017136282,0.000043011165],"category_scores_gemma":[0.0037376052,0.00036986446,0.00031646874,0.0003043198,0.0001951134,0.00016927908,0.000768636,0.002381758,3.3689955e-7],"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":[0.00008605092,0.00015856422,0.0000611719,0.0798337,0.00015983681,0.000003541363,0.00029382663,0.000015743271,0.0000012619269,0.099199615,0.00046525916,0.8197214],"study_design_scores_gemma":[0.0007795955,0.00015383691,0.000011812618,0.014699815,0.00086371857,0.000039055383,0.000046820012,0.0010760642,0.0000034913455,0.08569313,0.89608073,0.0005519064],"about_ca_topic_score_codex":0.00006589926,"about_ca_topic_score_gemma":0.00003722082,"teacher_disagreement_score":0.8956155,"about_ca_system_score_codex":0.00034849838,"about_ca_system_score_gemma":0.00030378054,"threshold_uncertainty_score":0.9999198},"labels":[],"label_agreement":null},{"id":"W4283789559","doi":"10.1002/cjs.11718","title":"Causal inference: Critical developments, past and future","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Causality (physics); Statistical inference; Inference; Field (mathematics); Epistemology; Subject (documents); Causal model; Data science; Computer science; Econometrics; Mathematics; Philosophy; Statistics","score_opus":0.07887559240728977,"score_gpt":0.367192966318878,"score_spread":0.28831737391158824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283789559","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":[0.036446244,0.0011382058,0.9479787,0.004798409,0.0025533729,0.00041751208,0.0029050058,0.00007863078,0.0036839691],"genre_scores_gemma":[0.54312956,0.000056845987,0.45600107,0.0003472445,0.00029709024,0.000008193584,0.00001075986,0.000029796356,0.000119430864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988688,0.00007828015,0.00040140012,0.00009743666,0.00026228235,0.00029176933],"domain_scores_gemma":[0.99833757,0.0005593572,0.00017054104,0.00010643353,0.0003085389,0.00051753275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034773,0.00012438036,0.0002277117,0.00020956178,0.00030991342,0.000052218056,0.0001928457,0.00004472831,0.00077966304],"category_scores_gemma":[0.0010019708,0.00012530964,0.000019109433,0.00013668432,0.00015394574,0.00011432214,0.00004251976,0.00052841223,0.0000015160958],"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":[0.000009016035,0.00001768139,0.0035974707,0.000045071625,0.000028123055,0.0008449107,0.0010969029,0.0000031029172,0.000025411471,0.9337101,0.04471874,0.015903458],"study_design_scores_gemma":[0.0002530267,0.00035196147,0.0035064227,0.00003630205,0.000053385025,0.00084849173,0.0019166111,0.000033825072,0.00004943603,0.8457481,0.14692429,0.00027814746],"about_ca_topic_score_codex":0.00014443965,"about_ca_topic_score_gemma":0.0016826749,"teacher_disagreement_score":0.50668335,"about_ca_system_score_codex":0.0002756501,"about_ca_system_score_gemma":0.0012868344,"threshold_uncertainty_score":0.8536763},"labels":[],"label_agreement":null},{"id":"W4283793196","doi":"10.1136/bmjopen-2022-062572","title":"Impact of time-varying exposure on estimated effects in observational studies using routinely collected data: protocol for a cross-sectional study","year":2022,"lang":"en","type":"article","venue":"BMJ Open","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":"McMaster University; Impact","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Medicine; Observational study; Protocol (science); Cross-sectional study; Medical physics; Alternative medicine; Pathology","score_opus":0.7734215775216742,"score_gpt":0.6551119099695175,"score_spread":0.11830966755215666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283793196","genre_codex":"empirical","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5983232,8.9899424e-7,0.0015096104,0.000006725725,0.00002416142,0.39973205,0.00023173093,0.00008280332,0.00008876775],"genre_scores_gemma":[0.24069561,2.5043832e-8,0.06924124,0.000018158882,0.00002950359,0.68969804,0.00011016296,0.0000444139,0.00016284647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978942,0.0002969968,0.00075434847,0.0003938234,0.00044232057,0.00021827561],"domain_scores_gemma":[0.99674237,0.0018088593,0.000541826,0.00057353015,0.0003059737,0.000027426317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002165093,0.00019714482,0.0005269138,0.00014597077,0.0002921031,0.0000791873,0.0007210464,0.00004149105,0.00009144561],"category_scores_gemma":[0.004247017,0.00017378715,0.000054585726,0.0005576222,0.00003913407,0.00044862652,0.0014285241,0.00018267591,8.22412e-7],"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":[0.0049770195,0.0028063299,0.9602692,0.00056240294,0.00040723846,0.00002536634,0.00091574364,0.022168431,0.0045619663,0.0010813464,0.0021513517,0.000073580246],"study_design_scores_gemma":[0.010593889,0.006993009,0.8605131,0.0006565807,0.000047858204,0.0000231696,0.00019509192,0.067972705,0.0010462622,0.051397517,0.000011695544,0.0005491038],"about_ca_topic_score_codex":0.00013651482,"about_ca_topic_score_gemma":0.000031741907,"teacher_disagreement_score":0.35762763,"about_ca_system_score_codex":0.00055587274,"about_ca_system_score_gemma":0.00047569248,"threshold_uncertainty_score":0.70868343},"labels":[],"label_agreement":null},{"id":"W4285013168","doi":"10.1016/j.gloepi.2022.100080","title":"A practical guide to handling competing events in etiologic time-to-event studies","year":2022,"lang":"en","type":"article","venue":"Global Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of British Columbia","funders":"","keywords":"Event (particle physics); Data science; Computer science; Gray (unit); Psychology; Medicine","score_opus":0.35668389234934533,"score_gpt":0.5653202569144733,"score_spread":0.20863636456512796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285013168","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":[0.42745546,0.00067003065,0.5076905,0.05248408,0.0006813026,0.002909865,0.000108556545,0.0011576421,0.0068425727],"genre_scores_gemma":[0.27029586,0.00003166284,0.7173921,0.010918001,0.00010097054,0.00083358405,0.000014000045,0.000025881935,0.0003879361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99536395,0.0021527885,0.0010457044,0.00055226125,0.00017009357,0.0007151799],"domain_scores_gemma":[0.99164915,0.0074521704,0.0002936115,0.00035917136,0.00009555567,0.00015032328],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065131853,0.00023158012,0.0009336765,0.00010318782,0.00016522821,0.000002012266,0.000322341,0.00009667488,0.00023911441],"category_scores_gemma":[0.07082261,0.00021456662,0.00009097724,0.00043219182,0.000063740634,0.00005273941,0.0012414324,0.00040966287,0.00023761352],"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":[0.00057225674,0.0008114819,0.08524606,0.00013309547,0.00027659838,0.0002518072,0.0009988749,0.026251806,0.0010294075,0.63407534,0.24378501,0.0065682847],"study_design_scores_gemma":[0.00037599733,0.0009379605,0.0036392868,0.000119620694,0.00002989729,0.0001702143,0.0011203175,0.0015043719,0.000050636143,0.95895475,0.032646388,0.00045053643],"about_ca_topic_score_codex":0.000066236775,"about_ca_topic_score_gemma":0.00005231996,"teacher_disagreement_score":0.32487947,"about_ca_system_score_codex":0.0010616077,"about_ca_system_score_gemma":0.00007450495,"threshold_uncertainty_score":0.93700427},"labels":[],"label_agreement":null},{"id":"W4285490771","doi":"10.1101/2022.07.13.22277596","title":"COVID-19 pandemic surges can induce bias in trials using response adaptive randomization: A simulation study","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","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":"Hospital for Sick Children; Mount Sinai Hospital; Health Sciences Centre; University Health Network; University of Toronto; Institute for Clinical Evaluative Sciences; Sinai Health System; Sunnybrook Health Science Centre","funders":"University of Toronto","keywords":"Coronavirus disease 2019 (COVID-19); Pandemic; Randomization; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Econometrics; Clinical trial; Medicine; Virology; Mathematics; Internal medicine; Outbreak; Infectious disease (medical specialty)","score_opus":0.7326986697119655,"score_gpt":0.552732320825076,"score_spread":0.17996634888688956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285490771","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":[0.88227415,0.00008101566,0.11197794,0.00012590617,0.00026035923,0.0046647317,0.00009778607,0.00049239415,0.000025744097],"genre_scores_gemma":[0.99170417,0.000035010966,0.0069312216,0.00011158923,0.00008734788,0.00090497005,0.00003987619,0.000088635126,0.00009719243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98285794,0.013350741,0.001895069,0.0008239814,0.0007234872,0.00034876997],"domain_scores_gemma":[0.9679214,0.029114017,0.001654,0.0009310665,0.00019182226,0.00018774379],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.026477898,0.00048514592,0.0017906309,0.00085984793,0.0001742641,0.000064411615,0.00046097857,0.00035352385,0.0003736526],"category_scores_gemma":[0.11286731,0.00046812612,0.00021790962,0.0006480362,0.00007276111,0.00011627082,0.0008124638,0.0011767603,8.8193883e-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":[0.02339877,0.0011319102,0.2685063,0.0003358054,0.00036457292,0.0003188669,0.02442658,0.6782889,0.0012861853,0.0012427269,0.00006666524,0.0006327642],"study_design_scores_gemma":[0.035410922,0.0013255462,0.014442399,0.0011715385,0.0014135279,0.000040896706,0.017246552,0.11887974,0.0013150885,0.8034178,0.0013070569,0.0040289564],"about_ca_topic_score_codex":0.00048572684,"about_ca_topic_score_gemma":0.0006438742,"teacher_disagreement_score":0.80217505,"about_ca_system_score_codex":0.0020057494,"about_ca_system_score_gemma":0.0016247038,"threshold_uncertainty_score":0.999777},"labels":[],"label_agreement":null},{"id":"W4285592479","doi":"10.1002/sim.9519","title":"Bootstrap vs asymptotic variance estimation when using propensity score weighting with continuous and binary outcomes","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":43,"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; Ministerio de Sanidad, Consumo y Bienestar Social; Heart and Stroke Foundation of Canada","keywords":"Statistics; Mathematics; Propensity score matching; Estimator; Confidence interval; Weighting; Average treatment effect; Sample size determination; Delta method; Matching (statistics); Inverse probability weighting; Medicine","score_opus":0.14787825533505633,"score_gpt":0.3957896493172065,"score_spread":0.24791139398215017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285592479","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":[0.33297634,0.000050932646,0.6656471,0.00028543442,0.000078108766,0.0005626747,0.000045978853,0.00011229491,0.00024115418],"genre_scores_gemma":[0.5051744,0.000006616423,0.49450678,0.00012390128,0.000017971055,0.00003227016,0.000020393803,0.000024806515,0.00009283909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99852407,0.0001244224,0.00041325839,0.00027555088,0.00041804241,0.00024465227],"domain_scores_gemma":[0.99853635,0.0007808087,0.00028098727,0.000247961,0.00009567216,0.0000582057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000694133,0.00019157429,0.00049419265,0.00014078352,0.0001948712,0.000014046187,0.0001289051,0.00003408095,0.00011584432],"category_scores_gemma":[0.0011358759,0.0001504879,0.000007973684,0.00017562018,0.00024289348,0.00011414218,0.00013452648,0.0003871026,4.2146362e-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":[0.0004805666,0.00040156662,0.21443677,0.0012376822,0.00013624031,0.001537475,0.00844783,0.0021523386,0.0040352335,0.745907,0.0027553698,0.018471906],"study_design_scores_gemma":[0.0015743407,0.0011609311,0.02967658,0.0006655706,0.00014007391,0.00018347445,0.00070867507,0.05199682,0.00010448136,0.9133447,0.000055158045,0.0003891854],"about_ca_topic_score_codex":0.00013406375,"about_ca_topic_score_gemma":0.000047537425,"teacher_disagreement_score":0.18476018,"about_ca_system_score_codex":0.00016401625,"about_ca_system_score_gemma":0.00006731817,"threshold_uncertainty_score":0.6136719},"labels":[],"label_agreement":null},{"id":"W4285614247","doi":"10.20955/wp.2022.014","title":"The Sine Aggregatio Approach to Applied Macro","year":2022,"lang":"en","type":"report","venue":"","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":"Western University","funders":"","keywords":"Sine; Macro; Mathematics; Computer science; Geometry; Programming language","score_opus":0.2598576242959587,"score_gpt":0.4368323145212753,"score_spread":0.1769746902253166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285614247","genre_codex":"other","genre_gemma":"methods","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":[0.0000110334595,0.0001382662,0.15819326,0.00015426574,0.00022599864,0.0015193449,0.0000332469,0.0009475196,0.83877707],"genre_scores_gemma":[0.0043033035,0.0012925682,0.5388413,0.00058876426,0.00084343425,0.0065877126,0.00035227736,0.0004560507,0.44673458],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969256,0.00005137174,0.00067489425,0.0005438426,0.0013507069,0.0004535885],"domain_scores_gemma":[0.99698335,0.0007651353,0.00046315455,0.0014002057,0.00027760578,0.00011057048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014517123,0.00042536383,0.0005878513,0.00012497243,0.00035658415,0.00009654584,0.0008612681,0.00023392319,0.00063616654],"category_scores_gemma":[0.0011912417,0.00028089486,0.00014477047,0.00036670364,0.00008053034,0.000037222682,0.0007169435,0.0008381984,0.000040065952],"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":[0.000013444583,0.0001044237,0.0000022340794,0.0002028776,0.000086652646,0.0000053374056,0.00013494905,0.000014449827,0.00005223707,0.38278678,0.58948237,0.027114244],"study_design_scores_gemma":[0.000050720595,0.00003816906,0.0000028434645,0.000025741123,0.000050131934,0.00003861428,0.00020167166,0.000012531081,0.0006530283,0.25444725,0.7440941,0.00038525675],"about_ca_topic_score_codex":0.00005750847,"about_ca_topic_score_gemma":0.00004148275,"teacher_disagreement_score":0.3920425,"about_ca_system_score_codex":0.00069761515,"about_ca_system_score_gemma":0.0005122644,"threshold_uncertainty_score":0.9999643},"labels":[],"label_agreement":null},{"id":"W4288039325","doi":"10.1001/jama.2022.9262","title":"SARS-CoV-2 Omicron Variant Severity in Ontario, Canada—Reply","year":2022,"lang":"en","type":"letter","venue":"JAMA","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Virology; Pathology; Disease; Infectious disease (medical specialty)","score_opus":0.08714770748490701,"score_gpt":0.3286245882344564,"score_spread":0.24147688074954937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288039325","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":[0.036482386,0.00008660083,0.0026686995,0.9054816,0.0020401455,0.0026130727,0.0006367999,0.0010644927,0.048926223],"genre_scores_gemma":[0.0016114567,0.000009584253,0.020862715,0.9677627,0.0007041122,0.00032544392,0.00041738662,0.00017571228,0.008130883],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740106,0.0001862102,0.0006180404,0.0005991989,0.0005850488,0.0006104722],"domain_scores_gemma":[0.99806786,0.00047493193,0.0003647058,0.0009878897,0.000074741714,0.000029888384],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038432673,0.00045509363,0.00072455563,0.00016364403,0.000079072684,0.00006265433,0.0006893169,0.0005565334,0.0015566376],"category_scores_gemma":[0.0003566135,0.0004892381,0.00010408276,0.00016459943,0.000043836382,0.00015732774,0.00038312556,0.0051976005,0.000009968555],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018570008,0.00002855221,0.000060812647,0.00011166295,0.000028493376,0.0032743441,0.00021191424,4.584346e-7,0.00029192754,0.00072861795,0.99487203,0.00037263954],"study_design_scores_gemma":[0.0002472867,0.000044441702,0.00014230734,0.00009403538,0.000026971895,0.0000954898,0.000016863498,0.000007392276,0.003031969,0.07684693,0.9189272,0.00051912776],"about_ca_topic_score_codex":0.9872944,"about_ca_topic_score_gemma":0.99633104,"teacher_disagreement_score":0.07611831,"about_ca_system_score_codex":0.0057228613,"about_ca_system_score_gemma":0.0022948585,"threshold_uncertainty_score":0.9997559},"labels":[],"label_agreement":null},{"id":"W4289544708","doi":"10.1002/pst.2258","title":"Key considerations for choosing a statistical method to deal with incomplete treatment adherence in pragmatic trials","year":2022,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Inverse probability weighting; Covariate; Computer science; Weighting; Statistical inference; Inference; Key (lock); Clinical trial; Medicine; Machine learning; Econometrics; Artificial intelligence; Statistics; Mathematics; Estimator","score_opus":0.7492029465102941,"score_gpt":0.639858577016374,"score_spread":0.10934436949392001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289544708","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":[1.5025162e-7,0.100547954,0.8790714,0.000055100554,0.00006271984,0.008033418,0.011844799,0.0001953313,0.00018911004],"genre_scores_gemma":[0.0000015864046,0.27988094,0.7123267,0.00011765128,0.00007238447,0.0070005734,0.0004252872,0.00013283009,0.00004201877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99190396,0.0031728814,0.0025474066,0.0009042112,0.00059960096,0.00087191636],"domain_scores_gemma":[0.9032574,0.0949738,0.00075188343,0.0004235008,0.0001447328,0.0004486629],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034881234,0.0009011525,0.004367819,0.00036317954,0.0002661463,0.00015597865,0.00030524546,0.00019763484,0.0019272771],"category_scores_gemma":[0.010134075,0.0006864075,0.0002296556,0.0004785649,0.00013511232,0.00009048303,0.00018167823,0.0007905546,0.000023493272],"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":[0.00007351906,0.00029262673,5.029554e-7,0.0055017336,0.00022044846,0.0001049252,0.00018216102,0.0000126017585,0.0000012276598,0.34122604,0.0013210685,0.65106314],"study_design_scores_gemma":[0.000895896,0.00092299277,1.74953e-7,0.0016558367,0.0021790487,0.0000913726,0.000026423208,0.0011305016,0.000010407456,0.32104403,0.67141986,0.0006234589],"about_ca_topic_score_codex":0.00004618972,"about_ca_topic_score_gemma":0.00014250241,"teacher_disagreement_score":0.6700988,"about_ca_system_score_codex":0.0015304136,"about_ca_system_score_gemma":0.0010767253,"threshold_uncertainty_score":0.9995587},"labels":[],"label_agreement":null},{"id":"W4289835801","doi":"10.1093/aje/kwac137","title":"Causal and Associational Language in Observational Health Research: A Systematic Evaluation","year":2022,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":84,"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; McGill University; AIDS Vancouver; University of Toronto","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Medical Research Council; National Institutes of Health; Laura and John Arnold Foundation; Arnold Ventures; Stanford University; Bloomberg American Health Initiative","keywords":"Observational study; Medicine; Linguistics; Psychology; Pathology; Philosophy","score_opus":0.6763604971814872,"score_gpt":0.5975422495148568,"score_spread":0.07881824766663037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289835801","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":[0.9673522,0.0020956502,0.016397195,0.013093298,0.00012099591,0.0007593877,0.00002338821,0.000025642907,0.00013221428],"genre_scores_gemma":[0.9425914,0.000063416795,0.05592837,0.0011875663,0.000065744236,0.000115407296,0.000009874812,0.000012715951,0.00002545262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9842829,0.01321094,0.0013399167,0.00015957137,0.0006645961,0.00034209128],"domain_scores_gemma":[0.9752381,0.022369232,0.0017985203,0.00014251041,0.0003622013,0.0000894235],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057821438,0.00008596234,0.00080266315,0.00038869653,0.00012903204,0.0000041614603,0.0001836098,0.000025389254,0.00008535708],"category_scores_gemma":[0.05342214,0.00007560914,0.00005197015,0.00045762435,0.00020262586,0.000105763334,0.000100268044,0.0007034214,6.831944e-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":[0.00027336937,0.00058490597,0.16255124,0.0016890907,0.00029031988,0.0000851109,0.013075995,0.0022759512,0.0004785577,0.78591335,0.014442757,0.01833935],"study_design_scores_gemma":[0.00046746372,0.0017584321,0.033957344,0.00050001405,0.00002499988,0.00037877215,0.009504557,0.0033946086,0.0000047599383,0.94977427,0.000109482906,0.00012530932],"about_ca_topic_score_codex":0.00017492886,"about_ca_topic_score_gemma":0.0000728518,"teacher_disagreement_score":0.1638609,"about_ca_system_score_codex":0.0010479592,"about_ca_system_score_gemma":0.00047756062,"threshold_uncertainty_score":0.9701711},"labels":[],"label_agreement":null},{"id":"W4292111498","doi":"10.1002/pds.5527","title":"Meta‐analysis with sample‐standardization in multi‐site studies","year":2022,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Standardization; Estimator; Statistics; Meta-analysis; Econometrics; Population; Variance (accounting); Sample (material); Causal inference; Sample size determination; Consistency (knowledge bases); Random effects model; Mathematics; Computer science; Medicine; Artificial intelligence; Economics; Accounting","score_opus":0.6532422003705686,"score_gpt":0.5749269485207112,"score_spread":0.07831525184985733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292111498","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":[6.4183786e-7,0.8160583,0.18222106,0.00012423884,0.000046519974,0.0008233863,0.00047377637,0.00018105995,0.00007103181],"genre_scores_gemma":[0.000010626874,0.92729074,0.07106272,0.00023749191,0.000027517326,0.00088270806,0.00032146135,0.000053549433,0.00011319806],"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923896,0.004663727,0.0014849107,0.00083315064,0.00017755464,0.00045103324],"domain_scores_gemma":[0.9677392,0.030606696,0.0010344523,0.00044778734,0.00007810501,0.00009373068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007036401,0.00067950145,0.0070126634,0.000631433,0.00022425754,0.0000074002355,0.00026145484,0.00019807258,0.00055459695],"category_scores_gemma":[0.003149849,0.00045319038,0.00089523057,0.0011630035,0.0002722629,0.00015246503,0.0003323976,0.0010353612,0.0000025817055],"study_design_candidate":"meta_analysis","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":[0.00028652363,0.0004009193,0.0008040924,0.029439157,0.57056653,0.00014960808,0.002562259,0.0010170675,2.9644056e-7,0.044512484,0.0023255951,0.34793547],"study_design_scores_gemma":[0.00026143072,0.00002803587,0.0000023707714,0.00025775848,0.2654243,0.000016745753,0.00008331068,0.00012280227,7.3093656e-7,0.015678214,0.7176183,0.000505989],"about_ca_topic_score_codex":0.000082520455,"about_ca_topic_score_gemma":0.00040778331,"teacher_disagreement_score":0.7152927,"about_ca_system_score_codex":0.00025525683,"about_ca_system_score_gemma":0.00010066071,"threshold_uncertainty_score":0.999792},"labels":[],"label_agreement":null},{"id":"W4292266545","doi":"10.1007/s40264-022-01221-z","title":"Analytical Approaches to Reduce Selection Bias in As-Treated Analyses with Missing In-Hospital Drug Information","year":2022,"lang":"en","type":"article","venue":"Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; Jewish General Hospital","funders":"Korea Health Industry Development Institute; Ministry of Food and Drug Safety","keywords":"Medicine; Inverse probability weighting; Discontinuation; Hazard ratio; Selection bias; Proportional hazards model; Censoring (clinical trials); Medical prescription; Missing data; Emergency medicine; Confidence interval; Information bias; Internal medicine; Statistics; Propensity score matching; Pharmacology","score_opus":0.22544401059947272,"score_gpt":0.39293869514155394,"score_spread":0.16749468454208122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292266545","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":[0.97774553,0.000011176413,0.012571514,0.0017722537,0.000027224805,0.0007437074,0.00001265361,0.00031461735,0.006801291],"genre_scores_gemma":[0.978289,0.0000028341085,0.021236721,0.00008225232,0.000014170202,0.00012518799,0.000048186223,0.000020026748,0.00018163555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984399,0.0001839064,0.00050442,0.00023565924,0.0003541751,0.00028193445],"domain_scores_gemma":[0.9992384,0.0002510201,0.00016297074,0.000220551,0.00005295979,0.00007411812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006810212,0.00018573955,0.000294292,0.00050896365,0.00012809553,0.000042791202,0.00016368747,0.000040001712,0.00007558128],"category_scores_gemma":[0.00040521543,0.0001702483,0.000041742274,0.0016110358,0.000034898505,0.000588403,0.00011020516,0.00038756756,0.000009027637],"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":[0.0060072,0.0062157772,0.17294161,0.0008767341,0.0005422817,0.00024113026,0.15582679,0.18219358,0.0027237455,0.3194295,0.012838215,0.14016344],"study_design_scores_gemma":[0.008280738,0.0031501995,0.07836067,0.0013759673,0.0005204983,0.00026921328,0.09455717,0.28334492,0.15271899,0.35376775,0.017718382,0.0059354943],"about_ca_topic_score_codex":0.00043682195,"about_ca_topic_score_gemma":0.000258813,"teacher_disagreement_score":0.14999525,"about_ca_system_score_codex":0.00065072015,"about_ca_system_score_gemma":0.00010062077,"threshold_uncertainty_score":0.69425243},"labels":[],"label_agreement":null},{"id":"W4292760984","doi":"10.1111/insr.12518","title":"Calibration Techniques Encompassing Survey Sampling, Missing Data Analysis and Causal Inference","year":2022,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Missing data; Causal inference; Calibration; Sampling (signal processing); Empirical likelihood; Computer science; Weighting; Data mining; Statistics; Econometrics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.4095992104995709,"score_gpt":0.5409369624078981,"score_spread":0.13133775190832725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292760984","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":[0.00013125913,0.0013586673,0.9951805,0.00067603996,0.000057719895,0.00027009155,0.0017022559,0.00017345598,0.00045003786],"genre_scores_gemma":[0.15279134,0.0046128314,0.8371546,0.0010720573,0.00005984952,0.0001498808,0.0040482758,0.000034951478,0.00007621852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977323,0.00042433615,0.0006172501,0.0004628358,0.0005863547,0.00017696235],"domain_scores_gemma":[0.9958551,0.0031192007,0.0002805002,0.0005010518,0.0001528674,0.00009131204],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018133996,0.00016876002,0.00043307824,0.0001479564,0.00018421405,0.000103233484,0.00060355075,0.000030790994,0.0014679005],"category_scores_gemma":[0.00799614,0.00016203772,0.000036905403,0.00043478224,0.00009721485,0.00030663205,0.0008243246,0.00030253408,0.0000017751089],"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":[0.000032750537,0.00024003682,0.013529288,0.00068657997,0.0005220174,0.000038796985,0.000058502566,0.000009893307,0.00029365593,0.6048213,0.015102534,0.3646646],"study_design_scores_gemma":[0.00019016948,0.00016834828,0.02118757,0.0013662627,0.0011445084,0.00006480949,0.00002413085,0.045229997,0.00026960584,0.8575827,0.071838066,0.00093384867],"about_ca_topic_score_codex":0.00034474625,"about_ca_topic_score_gemma":0.00020999784,"teacher_disagreement_score":0.3637308,"about_ca_system_score_codex":0.00014570355,"about_ca_system_score_gemma":0.000080189115,"threshold_uncertainty_score":0.9994449},"labels":[],"label_agreement":null},{"id":"W4293064632","doi":"10.1002/cjs.11702","title":"Dynamic treatment regimes with interference","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Ontario Institute for Cancer Research","keywords":"Robustness (evolution); Observational study; Computer science; Ordinary least squares; Econometrics; Function (biology); Population; Data mining; Machine learning; Medicine; Mathematics; Statistics","score_opus":0.07877763027666349,"score_gpt":0.3395120526457993,"score_spread":0.2607344223691358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293064632","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":[0.041772008,0.00023082942,0.95396125,0.00043663356,0.00025121358,0.00023604785,0.0009367876,0.000034462555,0.0021407683],"genre_scores_gemma":[0.7125004,0.000020332927,0.286415,0.00005246123,0.000013350807,0.000010029182,0.0000068892177,0.000023392258,0.0009581267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992031,0.00005527912,0.00027919732,0.00008372401,0.00016042223,0.00021829008],"domain_scores_gemma":[0.99884737,0.0002291705,0.0003002925,0.00016742919,0.00017485174,0.00028089623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014066967,0.00011920763,0.00021977487,0.00019629735,0.00016186561,0.000027103659,0.00021764782,0.000017987913,0.0005142036],"category_scores_gemma":[0.00016165084,0.000096657845,0.000026718604,0.000122023266,0.00009565682,0.00007101946,0.000013344878,0.00022796323,0.0000018180327],"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":[0.00017466526,0.00017021043,0.0027200421,0.000075619624,0.00034615857,0.00844186,0.006914166,0.0006033843,0.00019092642,0.8770046,0.047286227,0.056072146],"study_design_scores_gemma":[0.0008737725,0.0064748107,0.00040404743,0.00013272301,0.000187918,0.0029199622,0.0037368175,0.0007433399,0.00039999274,0.95559317,0.028071767,0.00046168562],"about_ca_topic_score_codex":0.0006758691,"about_ca_topic_score_gemma":0.015566212,"teacher_disagreement_score":0.6707284,"about_ca_system_score_codex":0.00092917867,"about_ca_system_score_gemma":0.0012940497,"threshold_uncertainty_score":0.8686312},"labels":[],"label_agreement":null},{"id":"W4293568569","doi":"10.1257/aer.20220277","title":"Methods Matter: p-Hacking and Publication Bias in Causal Analysis in Economics: Reply","year":2022,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","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":"Wilfrid Laurier University; University of Ottawa","funders":"","keywords":"Rounding; Regression discontinuity design; Replicate; Difference in differences; Publication bias; Econometrics; Instrumental variable; Economics; Regression; Psychology; Significant difference; Statistics; Causal inference; Hacker; Computer science; Mathematics; Confidence interval; Computer security","score_opus":0.16278473372572494,"score_gpt":0.4591433702397555,"score_spread":0.29635863651403055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293568569","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":[0.8677526,0.034282856,0.035351165,0.025950441,0.00025033936,0.005357975,0.00015589646,0.00062417774,0.030274544],"genre_scores_gemma":[0.44402245,0.11902416,0.4131971,0.020423433,0.000053616124,0.0026460462,0.00012203511,0.0001406269,0.00037054747],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977123,0.00058773794,0.0009692422,0.00046754774,0.000035444227,0.00022772029],"domain_scores_gemma":[0.9979173,0.0006041892,0.0008033939,0.00061114284,0.000013886691,0.000050084425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027679305,0.00016671733,0.0009411416,0.00047688757,0.00003893102,0.000031582847,0.00024859366,0.000015042695,0.0005947066],"category_scores_gemma":[0.00031608302,0.00018755153,0.00010340312,0.00060173305,0.000093839066,0.00024631838,0.00022580412,0.0002103618,0.000016966056],"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":[0.000012568153,0.00009673049,0.1773934,0.00046961012,0.00024316758,0.0000054467296,0.00042905236,0.00030917063,0.000025156438,0.027736522,0.0040625446,0.78921664],"study_design_scores_gemma":[0.0011562855,0.0005077765,0.109731786,0.0011477127,0.0014436995,0.00016945731,0.002030566,0.0150028495,0.00029174922,0.3152805,0.55003494,0.0032027115],"about_ca_topic_score_codex":0.000910697,"about_ca_topic_score_gemma":0.00055571774,"teacher_disagreement_score":0.7860139,"about_ca_system_score_codex":0.00063779653,"about_ca_system_score_gemma":0.000057256348,"threshold_uncertainty_score":0.76481295},"labels":[],"label_agreement":null},{"id":"W4294310517","doi":"10.1515/ijb-2022-0056","title":"Causal inference for oncology: past developments and current challenges","year":2022,"lang":"en","type":"review","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Fonds de Recherche du Québec - Santé","keywords":"Causal inference; Inference; Current (fluid); Medical physics; Medicine; Econometrics; Data science; Computer science; Oncology; Mathematics; Artificial intelligence; Physics","score_opus":0.48275920743690715,"score_gpt":0.5532970978116655,"score_spread":0.07053789037475833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294310517","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":[0.0000016403741,0.93425685,0.06281343,0.0003185928,0.0014580927,0.00047155152,0.0004918167,0.000022363865,0.00016566452],"genre_scores_gemma":[0.000014154844,0.93131566,0.06807915,0.000037820955,0.00037144922,0.00007243268,0.00004035722,0.00003810036,0.000030872776],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782133,0.00017188133,0.0010656506,0.00016864175,0.0005939136,0.00017857584],"domain_scores_gemma":[0.9903691,0.0069591138,0.0019471899,0.00015959908,0.0004942515,0.000070793816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011247034,0.0002865315,0.000903183,0.00023268205,0.00009164563,0.00005445914,0.0009981262,0.00010373414,0.000048853537],"category_scores_gemma":[0.002651666,0.00018809573,0.00015383298,0.00006415095,0.00012425958,0.00008353592,0.00038272783,0.00069558836,0.0000018314092],"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":[0.00001785379,0.000072047806,6.528715e-7,0.0010795246,0.00029136418,0.000027528993,0.00022981084,1.5304565e-7,2.1767487e-7,0.094655834,0.0025565785,0.90106845],"study_design_scores_gemma":[0.0001541694,0.0001955814,0.0000013129084,0.0020796324,0.00031306685,0.00031245875,0.00008080421,0.0000042389847,0.0000016997569,0.1792551,0.81744474,0.00015718631],"about_ca_topic_score_codex":9.895064e-7,"about_ca_topic_score_gemma":0.000006645366,"teacher_disagreement_score":0.9009113,"about_ca_system_score_codex":0.00053595076,"about_ca_system_score_gemma":0.00069807726,"threshold_uncertainty_score":0.76703215},"labels":[],"label_agreement":null},{"id":"W4294833180","doi":"10.3390/e24091235","title":"Simultaneous Maximum Likelihood Estimation for Piecewise Linear Instrumental Variable Models","year":2022,"lang":"en","type":"article","venue":"Entropy","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":"University of Waterloo","funders":"","keywords":"Instrumental variable; Mathematics; Estimator; Statistics; Econometrics; Variable (mathematics); Variables; Piecewise","score_opus":0.06051922556134319,"score_gpt":0.3473483503281906,"score_spread":0.2868291247668474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294833180","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":[0.017665224,0.000027181744,0.9797138,0.00011691506,0.00016327335,0.0008547751,0.00015406817,0.0005258295,0.00077895954],"genre_scores_gemma":[0.45850304,0.0000031711122,0.54064584,0.00010023428,0.000050675157,0.0003856722,0.000066818786,0.000038877817,0.00020564826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987737,0.00004575117,0.00029882995,0.0002593027,0.0002836253,0.00033876929],"domain_scores_gemma":[0.99896675,0.00044405647,0.00014935354,0.00030563824,0.00006439437,0.00006980591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023420184,0.00016797495,0.00021273675,0.00007277781,0.00026281097,0.000024192546,0.00022418922,0.000049974715,0.0003840872],"category_scores_gemma":[0.0003382643,0.00017824021,0.00006634307,0.00014721828,0.000025962634,0.0002228855,0.00016812216,0.00020206501,0.000010720998],"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":[0.00020945643,0.0005450221,0.000014770767,0.00010585983,0.00005565076,0.0000175412,0.0006066316,0.08475522,0.008835166,0.881809,0.0035999347,0.019445734],"study_design_scores_gemma":[0.00032922628,0.00018856091,9.628447e-8,0.0000071463946,0.000019417019,0.00001038959,0.000076834964,0.41362908,0.0034891178,0.5804655,0.0016661647,0.000118463526],"about_ca_topic_score_codex":0.000012282339,"about_ca_topic_score_gemma":0.0000013335356,"teacher_disagreement_score":0.44083783,"about_ca_system_score_codex":0.0002884608,"about_ca_system_score_gemma":0.000061771694,"threshold_uncertainty_score":0.7268425},"labels":[],"label_agreement":null},{"id":"W4296527273","doi":"10.1007/s00184-022-00883-0","title":"A semiparametric multiply robust multiple imputation method for causal inference","year":2022,"lang":"en","type":"article","venue":"Metrika","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institute on Minority Health and Health Disparities; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Causal inference; Propensity score matching; Mathematics; Covariate; Observational study; Statistics; Average treatment effect; Parametric statistics; Econometrics; Semiparametric regression; Regression","score_opus":0.2165900280511105,"score_gpt":0.4543514871875161,"score_spread":0.23776145913640562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296527273","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":[0.017726697,0.00010516801,0.9794436,0.00009662742,0.00020772271,0.0013102087,0.00015135287,0.0006618801,0.00029672257],"genre_scores_gemma":[0.35654062,0.000005835547,0.6417468,0.00011406535,0.000046052017,0.0010740494,0.0000439137,0.000049217677,0.0003794246],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99772954,0.0002814224,0.00053228735,0.0004879778,0.00050248747,0.0004662554],"domain_scores_gemma":[0.9897999,0.009030602,0.00034575516,0.0004691737,0.00024870335,0.0001058315],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017183789,0.00026310203,0.00043573798,0.0008192428,0.00035803494,0.000048741174,0.0004126917,0.00009664786,0.00019156066],"category_scores_gemma":[0.014069833,0.00027157564,0.00015767357,0.002070228,0.000035955363,0.00022302123,0.00029686547,0.00041334293,0.000008246522],"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":[0.0010552038,0.00319036,0.019953702,0.0010460749,0.00062561006,0.00008173134,0.0055164737,0.08420505,0.0457361,0.31059527,0.03743588,0.49055853],"study_design_scores_gemma":[0.002958827,0.0014339762,0.00074467,0.000035383146,0.00020103478,0.000038164624,0.0011256759,0.29991245,0.04444151,0.6272716,0.020619411,0.0012173349],"about_ca_topic_score_codex":0.00010968204,"about_ca_topic_score_gemma":0.0000340752,"teacher_disagreement_score":0.4893412,"about_ca_system_score_codex":0.00040560003,"about_ca_system_score_gemma":0.00010052431,"threshold_uncertainty_score":0.99997365},"labels":[],"label_agreement":null},{"id":"W4297412566","doi":"10.1002/cjs.11728","title":"Nonparametric tests for treatment effect heterogeneity in observational studies","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Observational study; Nonparametric statistics; Propensity score matching; Econometrics; Statistics; Statistic; Parametric statistics; Confounding; Test statistic; Normality; Treatment effect; Asymptotic distribution; Mathematics; Average treatment effect; Statistical hypothesis testing; Computer science; Medicine; Estimator","score_opus":0.41402064646675224,"score_gpt":0.4684697448995436,"score_spread":0.05444909843279139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297412566","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":[0.8525025,0.0014193644,0.14160946,0.00033685617,0.0005629322,0.0009805537,0.0025009767,0.00002104425,0.00006628353],"genre_scores_gemma":[0.7357229,0.000037191363,0.26388985,0.00008789715,0.000050762115,0.00010679309,0.000018502386,0.000022274528,0.00006381585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989801,0.00010163557,0.00042799854,0.000091886766,0.0001691607,0.00022918884],"domain_scores_gemma":[0.99606675,0.003120911,0.00028864195,0.000107735104,0.0002505414,0.00016544215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005755579,0.0001253495,0.00037078184,0.00039304476,0.00014810883,0.000015282912,0.00014442945,0.000023698462,0.000035615376],"category_scores_gemma":[0.0035699045,0.00010948211,0.00005734093,0.00028147327,0.000053348776,0.000064250584,0.000013605536,0.00011625882,4.636518e-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":[0.0003658333,0.00053725386,0.2814302,0.00070349016,0.0010647948,0.0024348637,0.0042763846,0.0060319,0.0005445727,0.5200291,0.09119995,0.09138164],"study_design_scores_gemma":[0.0020701264,0.0066358647,0.0156058995,0.000092988696,0.00019380506,0.0002431429,0.00046508518,0.0007999892,0.0016111102,0.96012056,0.011755849,0.00040559197],"about_ca_topic_score_codex":0.0002684256,"about_ca_topic_score_gemma":0.016466366,"teacher_disagreement_score":0.44009143,"about_ca_system_score_codex":0.0015740887,"about_ca_system_score_gemma":0.00071892224,"threshold_uncertainty_score":0.9188618},"labels":[],"label_agreement":null},{"id":"W4297493265","doi":"10.1257/app.20200068","title":"Correction to “Temperature and Decisions: Evidence from 207,000 Court Cases” and Reply to Spamann","year":2022,"lang":"en","type":"article","venue":"American Economic Journal Applied Economics","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 Manitoba; University of Ottawa","funders":"","keywords":"Arbitration; Econometrics; Sample size determination; Sample (material); Sensitivity (control systems); Positive economics; Psychology; Economics; Statistics; Political science; Law and economics; Law; Mathematics; Engineering; Physics; Thermodynamics","score_opus":0.061078416682117054,"score_gpt":0.33712976948309,"score_spread":0.2760513528009729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297493265","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":[0.99265784,0.000100400175,0.0035932125,0.0020844724,0.00058242236,0.00047401155,0.00011215019,0.00008823405,0.0003072478],"genre_scores_gemma":[0.9377961,0.0011779253,0.05523904,0.00505781,0.00030387624,0.00016884721,0.00000562526,0.000070651105,0.00018013548],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822706,0.00005886125,0.0006868325,0.00060224993,0.00007110117,0.0003539234],"domain_scores_gemma":[0.99621433,0.0023491601,0.0005330196,0.00044139978,0.00003016814,0.0004319281],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007056153,0.00028572345,0.00059136894,0.0002456091,0.0004559028,0.00022489906,0.00032764822,0.000035682762,0.00023779074],"category_scores_gemma":[0.00047634012,0.000322888,0.00005814489,0.00010474327,0.00011436723,0.0002942928,0.0004618001,0.0006137921,0.00003810844],"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":[0.0029494015,0.00025233245,0.011940617,0.000020948484,0.0005742113,0.00012585722,0.008483511,0.034094136,0.009063853,0.021950485,0.43354487,0.4769998],"study_design_scores_gemma":[0.00291526,0.0064891493,0.026621355,0.0006443337,0.00048548076,0.010286544,0.047382828,0.0060907314,0.012223692,0.637456,0.24348192,0.0059227175],"about_ca_topic_score_codex":0.00049271074,"about_ca_topic_score_gemma":0.0002999275,"teacher_disagreement_score":0.6155055,"about_ca_system_score_codex":0.0009719134,"about_ca_system_score_gemma":0.0001258411,"threshold_uncertainty_score":0.99992234},"labels":[],"label_agreement":null},{"id":"W4300861756","doi":"10.47004/wp.cem.2022.1622","title":"IV Methods for Tobit Models","year":2022,"lang":"en","type":"report","venue":"","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":"Simon Fraser University","funders":"Economic and Social Research Council; University of Cambridge","keywords":"Tobit model; Computer science; Econometrics; Mathematics","score_opus":0.6572314321574739,"score_gpt":0.6175396490021837,"score_spread":0.039691783155290206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300861756","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":[7.8266066e-7,0.00021776825,0.63372207,0.000037592523,0.00028804192,0.0009341398,0.00006415479,0.00080420624,0.36393127],"genre_scores_gemma":[0.000013500732,0.0005183362,0.8599637,0.0000818753,0.0001642378,0.0020074644,0.00009682824,0.00015277935,0.13700129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781364,0.000117965734,0.0006749599,0.0005049741,0.0005184639,0.00036997],"domain_scores_gemma":[0.99600416,0.0020423231,0.00045731058,0.0009130258,0.00050852954,0.000074675925],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027769848,0.00037905292,0.0008652133,0.00017735753,0.00010582647,0.000028907518,0.0004644359,0.0003715092,0.0031027494],"category_scores_gemma":[0.0022373889,0.0003368202,0.00034924434,0.00013174686,0.000036122903,0.00013757384,0.00036631926,0.00055578985,0.0000029734028],"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":[0.000009303499,0.000069237954,3.2941696e-7,0.0006768012,0.000113132824,0.000004234493,0.00006930444,0.000025285519,0.0001250343,0.57471687,0.34782368,0.07636678],"study_design_scores_gemma":[0.00004216201,0.00006691531,2.6813e-8,0.000031418756,0.00007802316,0.000017878256,0.000031941978,0.0008850281,0.00096129114,0.6173163,0.38030642,0.0002626047],"about_ca_topic_score_codex":0.000063314175,"about_ca_topic_score_gemma":0.000017324819,"teacher_disagreement_score":0.22692998,"about_ca_system_score_codex":0.0006819661,"about_ca_system_score_gemma":0.0007141102,"threshold_uncertainty_score":0.9999084},"labels":[],"label_agreement":null},{"id":"W4307343125","doi":"10.1002/jrsm.1608","title":"Network meta‐interpolation: Effect modification adjustment in network meta‐analysis using subgroup analyses","year":2022,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Toronto","funders":"","keywords":"Statistics; Meta-analysis; Standard error; Mean squared error; Mathematics; Sample size determination; Subgroup analysis; Confidence interval; Data mining; Econometrics; Computer science; Medicine","score_opus":0.8152217341987545,"score_gpt":0.6479104043905357,"score_spread":0.16731132980821883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307343125","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":[0.0022674955,0.010789439,0.98414356,0.00021841004,0.00008014324,0.0014343025,0.000020503976,0.00026475175,0.00078142475],"genre_scores_gemma":[0.18639773,0.00012067775,0.8096294,0.000036738595,0.00016125233,0.0034418893,0.000010760055,0.00006967527,0.00013186126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9605968,0.034712084,0.0010539404,0.00091452134,0.0015496111,0.0011730476],"domain_scores_gemma":[0.9407361,0.057036493,0.00041936376,0.0013872118,0.00025246385,0.00016835799],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.046532635,0.00042694493,0.0024817577,0.0013100915,0.0006882597,0.00009776812,0.00083409983,0.0001436332,0.00277467],"category_scores_gemma":[0.007840147,0.00035360962,0.001431493,0.006988328,0.00016102074,0.00029301003,0.00072979886,0.0010573209,0.0000041912713],"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":[0.00051754253,0.0007172277,0.0008421571,0.00037272696,0.31714863,0.000055011446,0.00067491434,0.57704985,0.016882936,0.062399868,0.0017972004,0.021541936],"study_design_scores_gemma":[0.00013945068,0.0002467117,0.00027412825,0.00002563199,0.1883855,0.000007774099,0.00030746748,0.32875538,0.01430863,0.46652615,0.0004107156,0.00061246956],"about_ca_topic_score_codex":0.00043008025,"about_ca_topic_score_gemma":0.00009271006,"teacher_disagreement_score":0.4041263,"about_ca_system_score_codex":0.0007831217,"about_ca_system_score_gemma":0.00010712225,"threshold_uncertainty_score":0.9998916},"labels":[],"label_agreement":null},{"id":"W4308636435","doi":"10.1002/pds.5566","title":"High‐dimensional propensity scores for empirical covariate selection in secondary database studies: Planning, implementation, and reporting","year":2022,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; International Society for Pharmacoepidemiology","keywords":"Covariate; Medicine; Propensity score matching; Pharmacoepidemiology; Selection (genetic algorithm); Statistics; Econometrics; Internal medicine; Pharmacology; Computer science; Machine learning","score_opus":0.44729527161018,"score_gpt":0.5604829685782081,"score_spread":0.1131876969680281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308636435","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":[0.9665351,0.0008224193,0.028393706,0.0026536484,0.00016879341,0.0010716335,0.00017215806,0.00015556747,0.000026996973],"genre_scores_gemma":[0.92454165,0.00016347368,0.07213134,0.0023678557,0.00007806925,0.00047833248,0.00017086879,0.000020422242,0.00004798306],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971504,0.00087994675,0.0011562495,0.00043951283,0.00008833926,0.00028553474],"domain_scores_gemma":[0.99484354,0.0040519238,0.00087306363,0.000087438726,0.00008459593,0.00005942184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008450756,0.0001652278,0.000557493,0.0000992773,0.00050962606,0.0000042059714,0.000060554663,0.00003653158,0.00009667542],"category_scores_gemma":[0.0036671557,0.00014918188,0.000031150892,0.00011689973,0.00011292779,0.00018458442,0.00032388297,0.0004387573,1.996651e-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":[0.0027468966,0.0003120643,0.7490204,0.00081485417,0.00044899806,0.000109418645,0.0053173266,0.0012211115,0.008588118,0.067208186,0.14862712,0.015585548],"study_design_scores_gemma":[0.005988381,0.0005358721,0.10010632,0.00013798225,0.00028517187,0.00054440426,0.0031608723,0.007876035,0.008749208,0.86211485,0.009544991,0.0009559088],"about_ca_topic_score_codex":0.0001193063,"about_ca_topic_score_gemma":0.00009593996,"teacher_disagreement_score":0.7949067,"about_ca_system_score_codex":0.00011184677,"about_ca_system_score_gemma":0.00009718626,"threshold_uncertainty_score":0.6083461},"labels":[],"label_agreement":null},{"id":"W4308769045","doi":"10.1111/ppe.12932","title":"Multilevel modelling for measuring interaction of effects between multiple categorical variables: An illustrative application using risk factors for preeclampsia","year":2022,"lang":"en","type":"article","venue":"Paediatric and Perinatal Epidemiology","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":"McGill University","funders":"Vetenskapsrådet; European Commission","keywords":"Categorical variable; Medicine; Statistics; Multilevel model; Interaction; Receiver operating characteristic; Linear regression; Parity (physics); Regression analysis; Econometrics; Mathematics; Internal medicine","score_opus":0.332833413740033,"score_gpt":0.42794708893066297,"score_spread":0.09511367519062996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308769045","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":[0.41483086,0.00007470807,0.5840477,0.000005596035,0.000054108852,0.0007961628,0.00013848036,0.0000497407,0.0000026783484],"genre_scores_gemma":[0.7617934,0.000017260014,0.23739809,0.0000048947036,0.00012671427,0.00056515326,0.000067528264,0.000023410646,0.0000035994567],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824446,0.00043731488,0.0005533541,0.0003981638,0.00007921997,0.00028750685],"domain_scores_gemma":[0.9790139,0.020020563,0.0005956355,0.00017608306,0.00011887391,0.000074948715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015806216,0.00019215797,0.0005932871,0.00012144665,0.00030842607,0.0000040415903,0.0001350265,0.000144054,0.0000032512462],"category_scores_gemma":[0.0052931863,0.000182234,0.00010109095,0.00010406806,0.00006515922,0.00019668946,0.0000998048,0.00028039172,6.773658e-8],"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":[0.0009310363,0.00047379924,0.468571,0.0035987766,0.0004009261,0.0000012616455,0.0069774664,0.31962505,0.0032726754,0.14745086,0.00006353984,0.048633587],"study_design_scores_gemma":[0.0004137675,0.00050090556,0.0008428417,0.0000072072885,0.0001141972,0.000003865516,0.00044478627,0.74421716,0.0010391023,0.2521409,0.00009139756,0.0001838362],"about_ca_topic_score_codex":0.00043165474,"about_ca_topic_score_gemma":0.0000052379537,"teacher_disagreement_score":0.46772817,"about_ca_system_score_codex":0.00015059025,"about_ca_system_score_gemma":0.00003332868,"threshold_uncertainty_score":0.7431287},"labels":[],"label_agreement":null},{"id":"W4309631339","doi":"10.1016/j.dialog.2022.100074","title":"Relative risk reduction: Misinformative measure in clinical trials and COVID-19 vaccine efficacy","year":2022,"lang":"en","type":"article","venue":"Dialogues in Health","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"University of Waterloo","keywords":"Relative risk; Medicine; Clinical trial; Disinformation; Vaccine efficacy; Absolute risk reduction; Pandemic; Intensive care medicine; Disease; Coronavirus disease 2019 (COVID-19); Vaccination; Immunology; Internal medicine; Confidence interval; Infectious disease (medical specialty); Computer science","score_opus":0.5024346790845305,"score_gpt":0.5580280158501557,"score_spread":0.05559333676562517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309631339","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":[0.7267298,0.009666194,0.19179218,0.037399992,0.0032772871,0.021302193,0.0014314868,0.0024572667,0.0059436196],"genre_scores_gemma":[0.9697944,0.0025095684,0.025809383,0.0011406133,0.00019045194,0.00036537557,0.00008803277,0.00003654817,0.00006564808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98973113,0.006751593,0.0024515234,0.00038150666,0.00032319291,0.00036103957],"domain_scores_gemma":[0.9882396,0.009795365,0.0013064564,0.00036016147,0.00005342265,0.00024499078],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027558735,0.00019652802,0.0010727905,0.0003130314,0.0002492277,0.000014453684,0.00018147205,0.00012429843,0.00007807163],"category_scores_gemma":[0.045420017,0.00018356183,0.000093950286,0.00054348423,0.00010237747,0.0002664503,0.00018430398,0.0013187694,0.0000035467901],"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":[0.005518524,0.0032084978,0.07206237,0.0014347143,0.00027741538,0.000117287,0.17765664,0.0021985115,0.000021015541,0.4977353,0.044337608,0.19543211],"study_design_scores_gemma":[0.0049044755,0.0013228527,0.008754288,0.00015889699,0.000026669659,0.000044352844,0.004756699,0.00049301196,0.000025814346,0.9717572,0.007386868,0.00036890653],"about_ca_topic_score_codex":0.00056333985,"about_ca_topic_score_gemma":0.00031910778,"teacher_disagreement_score":0.47402188,"about_ca_system_score_codex":0.0008591286,"about_ca_system_score_gemma":0.0005675903,"threshold_uncertainty_score":0.9626208},"labels":[],"label_agreement":null},{"id":"W4309847907","doi":"10.1142/9789811270611_0028","title":"Multi-treatment Effect Estimation from Biomedical Data","year":2022,"lang":"en","type":"article","venue":"","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":"Simon Fraser University","funders":"","keywords":"Causal inference; Benchmark (surveying); Computer science; Machine learning; Inference; Task (project management); Artificial intelligence; Focus (optics); Estimation; Artificial neural network; Outcome (game theory); Data mining; Econometrics; Mathematics","score_opus":0.28531594039519925,"score_gpt":0.48049825684237407,"score_spread":0.19518231644717482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309847907","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":[0.051287852,0.00003447635,0.94602937,0.00023455382,0.000117747644,0.0005339561,0.00036302826,0.0009145875,0.00048444737],"genre_scores_gemma":[0.2690243,0.0000042811453,0.7293954,0.000052459312,0.000026251857,0.0001858591,0.00093302346,0.000018447274,0.00035998152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990858,0.00010748103,0.00017396462,0.00026735538,0.00023452319,0.00013090257],"domain_scores_gemma":[0.9983071,0.0007552632,0.00006065091,0.00081670634,0.000009243342,0.000051027262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024986413,0.000118777265,0.00017443633,0.000046872396,0.000106074265,0.000013186308,0.0003520806,0.00003029234,0.0016849483],"category_scores_gemma":[0.00035764967,0.000086163935,0.000024773795,0.000098623845,0.000033454595,0.00012515254,0.0005081662,0.00009798629,0.000040172203],"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":[0.00020068313,0.0049436186,0.0023063966,0.00011026478,0.00052116625,0.00024327564,0.0016606408,0.00018903264,0.054699235,0.04730397,0.08588564,0.8019361],"study_design_scores_gemma":[0.0027167138,0.0025403262,0.00035252832,0.00003641216,0.00023322956,0.000027568487,0.00028477242,0.58984554,0.03761966,0.3310256,0.034630697,0.00068691076],"about_ca_topic_score_codex":0.00023964411,"about_ca_topic_score_gemma":0.000025926147,"teacher_disagreement_score":0.80124915,"about_ca_system_score_codex":0.00018369564,"about_ca_system_score_gemma":0.000027150314,"threshold_uncertainty_score":0.99922764},"labels":[],"label_agreement":null},{"id":"W4310461430","doi":"10.1111/biom.13793","title":"Rejoinder to Discussions on “Instrumental Variable Estimation of the Causal Hazard Ratio”","year":2022,"lang":"en","type":"letter","venue":"Biometrics","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":"University of Toronto","funders":"","keywords":"Instrumental variable; Estimation; Econometrics; Statistics; Hazard ratio; Hazard; Psychology; Mathematics; Economics; Confidence interval; Biology","score_opus":0.12956008541337877,"score_gpt":0.3820493137410032,"score_spread":0.25248922832762444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310461430","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":[0.0033577324,0.000063198706,0.5561031,0.41188088,0.004686159,0.0060368655,0.0032703322,0.0010708462,0.013530862],"genre_scores_gemma":[0.034219522,0.000039252856,0.5993813,0.33547026,0.0017408123,0.0013175289,0.0013937814,0.00055055955,0.025886979],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973062,0.00017910886,0.00058436365,0.00040651398,0.0011754391,0.00034836],"domain_scores_gemma":[0.99734384,0.0009341166,0.0005125884,0.0010506379,0.00010164559,0.000057176283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042907213,0.00033524958,0.00044699587,0.001495658,0.00022030332,0.0000482322,0.0006996716,0.00042798877,0.0006735159],"category_scores_gemma":[0.0027035417,0.00022451772,0.00014993518,0.004741797,0.00007921906,0.00010164011,0.00052467815,0.001184539,0.000020611462],"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":[0.000009709722,0.00009630925,0.000016481952,0.00013553166,0.000037844788,0.000007938227,0.000075044896,0.00009810929,0.00044557315,0.01611597,0.9810992,0.0018622819],"study_design_scores_gemma":[0.0003827542,0.0009847946,0.00012158856,0.00044046616,0.00023917675,0.00002648297,0.000103078055,0.0006959122,0.012155097,0.16798829,0.8158862,0.00097614655],"about_ca_topic_score_codex":0.000021060865,"about_ca_topic_score_gemma":0.0000018854344,"teacher_disagreement_score":0.16521299,"about_ca_system_score_codex":0.00063228613,"about_ca_system_score_gemma":0.00015034316,"threshold_uncertainty_score":0.91555667},"labels":[],"label_agreement":null},{"id":"W4311277361","doi":"10.1002/sim.9629","title":"Consistent inverse probability of treatment weighted estimation of the average treatment effect with mismeasured time‐dependent confounders","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Observational error; Computer science; Confounding; Inverse probability; Inverse; Statistics; Function (biology); Estimation; Econometrics; Algorithm; Mathematics; Bayesian probability","score_opus":0.0685040974191771,"score_gpt":0.3618328318137441,"score_spread":0.29332873439456697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311277361","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":[0.6733039,0.00009503561,0.31396735,0.0006080114,0.0002646837,0.0077569718,0.0010376851,0.00015695355,0.0028094288],"genre_scores_gemma":[0.9041243,0.000013732936,0.09516802,0.000021328715,0.0000072109515,0.00030457808,0.00007573489,0.000020530726,0.0002645219],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806887,0.00046608955,0.0005531592,0.00021977947,0.0005304121,0.00016167015],"domain_scores_gemma":[0.9973994,0.0015010234,0.00044340256,0.000496142,0.000115967174,0.000044052387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006678597,0.00021990015,0.00060073717,0.00009149074,0.00007354111,0.0000022385384,0.00013644683,0.00003474984,0.00032965827],"category_scores_gemma":[0.0006194586,0.00012113158,0.000039544513,0.00021459095,0.00044350445,0.000024117518,0.00004533308,0.00012792437,6.6438423e-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":[0.006809243,0.009135941,0.037920237,0.004307691,0.0028445316,0.00043053745,0.04765132,0.06507106,0.033716206,0.7046112,0.004601763,0.08290026],"study_design_scores_gemma":[0.012106175,0.026093002,0.0013583573,0.00061583694,0.0009807457,0.000063331325,0.0009915568,0.048932206,0.03908321,0.86917055,0.0001512736,0.00045373803],"about_ca_topic_score_codex":0.0004118293,"about_ca_topic_score_gemma":0.00034518752,"teacher_disagreement_score":0.23082045,"about_ca_system_score_codex":0.0013665337,"about_ca_system_score_gemma":0.00023672594,"threshold_uncertainty_score":0.49396026},"labels":[],"label_agreement":null},{"id":"W4311359314","doi":"10.1016/j.jval.2022.09.143","title":"CO64 Comparison of Propensity Score Matching to Inverse Probability Weighting in Obstructive Sleep Apnea Patients With Cardiovascular Diseases","year":2022,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"","keywords":"Propensity score matching; Medicine; Confounding; Atrial fibrillation; Obstructive sleep apnea; Heart failure; Internal medicine; Cardiology; Sleep apnea; Inverse probability weighting; Matching (statistics); Intensive care medicine; Physical therapy","score_opus":0.15405656193558057,"score_gpt":0.35047196049547574,"score_spread":0.19641539855989518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311359314","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":[0.99102956,0.00007208542,0.006146708,0.000050410385,0.000049621176,0.002465997,0.000063842934,0.00009121255,0.000030538115],"genre_scores_gemma":[0.94795996,0.000001351303,0.051727973,0.00004366805,0.000008133465,0.00021770883,0.000014397112,0.000025810774,9.85392e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971545,0.0007587888,0.0007044741,0.0004117576,0.000617384,0.00035314614],"domain_scores_gemma":[0.9985986,0.0002959844,0.00033625288,0.00053837197,0.000114420516,0.00011639564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010887722,0.0001797461,0.00078636484,0.0001831364,0.00013469844,0.000007912973,0.00022088717,0.000033120723,0.000008591716],"category_scores_gemma":[0.0004956447,0.00016536473,0.00007252337,0.000604362,0.00006407772,0.00014681736,0.00030182066,0.0004194252,5.67453e-7],"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":[0.00015890153,0.0006435423,0.910453,0.00084016944,0.000027188344,0.000005130679,0.0061515365,0.07443993,0.0000070291967,0.0043246686,0.000012168862,0.0029367097],"study_design_scores_gemma":[0.0018439614,0.0015773664,0.64716303,0.001008169,0.00005336238,0.0000036230535,0.003411565,0.0074927635,0.00050845224,0.3361963,0.000066780536,0.00067462336],"about_ca_topic_score_codex":0.003873175,"about_ca_topic_score_gemma":0.0003386546,"teacher_disagreement_score":0.33187163,"about_ca_system_score_codex":0.00097655377,"about_ca_system_score_gemma":0.00017898782,"threshold_uncertainty_score":0.6743378},"labels":[],"label_agreement":null},{"id":"W4311514741","doi":"10.1111/ecin.13127","title":"Cautions when normalizing the dependent variable in a regression as a <i>z</i>‐score","year":2022,"lang":"en","type":"article","venue":"Economic Inquiry","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":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Normalization (sociology); Mathematics; Regression; Statistics; Variable (mathematics); Econometrics; Bounded function; Transformation (genetics); Linear regression; Omitted-variable bias; Regression analysis; Inference; Applied mathematics; Economics; Mathematical analysis; Computer science; Artificial intelligence","score_opus":0.1773966423125695,"score_gpt":0.3910471219627705,"score_spread":0.21365047965020104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311514741","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":[0.92046565,0.0005620768,0.02972985,0.0024756154,0.0029757097,0.0017666479,0.00007608702,0.0007691694,0.041179217],"genre_scores_gemma":[0.98134243,0.00003288079,0.014598852,0.00083389913,0.00024920044,0.00082657766,0.000017528693,0.00004926422,0.002049332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988487,0.00014722857,0.00036357835,0.0002562857,0.00010354003,0.00028069693],"domain_scores_gemma":[0.9989467,0.0003179513,0.00017842899,0.00050800806,0.000011810379,0.000037085832],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008510891,0.0001391506,0.00019515354,0.00010391773,0.00032798245,0.00003226196,0.0003924944,0.000049640836,0.0014481987],"category_scores_gemma":[0.000120169345,0.00011561622,0.000046772897,0.000077394085,0.00007235966,0.00022121957,0.0004891248,0.0004251025,0.000062295345],"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":[0.000060906346,0.00014956882,0.0016452661,0.00003436286,0.00003302919,0.00004294177,0.011901863,0.0023913453,0.0011298003,0.90862256,0.07272618,0.0012621408],"study_design_scores_gemma":[0.00030075884,0.00007258528,0.00006960514,0.00004885038,0.0000138147825,0.000094673356,0.003373549,0.0011097786,0.0015370031,0.9613692,0.03178416,0.00022599431],"about_ca_topic_score_codex":0.00055051595,"about_ca_topic_score_gemma":0.00016460131,"teacher_disagreement_score":0.06087684,"about_ca_system_score_codex":0.0006744715,"about_ca_system_score_gemma":0.0001884909,"threshold_uncertainty_score":0.99946463},"labels":[],"label_agreement":null},{"id":"W4311644650","doi":"10.22541/au.167033288.86261766/v1","title":"External Validity in Distributed Data Networks","year":2022,"lang":"en","type":"preprint","venue":"","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":true,"ca_institutions":"McGill University","funders":"","keywords":"External validity; Generalizability theory; Internal validity; Population; Observational study; Computer science; Data science; Psychology; Medicine; Statistics; Social psychology; Mathematics; Environmental health","score_opus":0.49059974418972874,"score_gpt":0.48499738617616894,"score_spread":0.005602358013559794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311644650","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":[0.005219552,0.00007712889,0.9891047,0.00012242646,0.00033546286,0.00059995876,0.000874865,0.00075793784,0.0029079763],"genre_scores_gemma":[0.48277903,0.000444179,0.5079844,0.00017609824,0.000371318,0.0004881434,0.006490038,0.00012972987,0.0011370336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776375,0.00022380514,0.0005828597,0.0007383561,0.0003446372,0.00034660194],"domain_scores_gemma":[0.9960872,0.00061060255,0.00029509354,0.0028957732,0.000043546333,0.00006776588],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011306794,0.00031049878,0.00051002705,0.00009073456,0.000047971702,0.00006228705,0.002118675,0.00027930856,0.0024183404],"category_scores_gemma":[0.0007456944,0.0003050718,0.00006616662,0.0001568577,0.000048965834,0.0001438282,0.011574107,0.0019045036,0.0000038459343],"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":[0.00018812923,0.0020973773,0.029847292,0.001285005,0.00020706847,0.00089220953,0.00034584838,0.024540877,0.00011447246,0.66807485,0.25419176,0.018215124],"study_design_scores_gemma":[0.000119702985,0.000024402307,0.0007212779,0.00015475991,0.00002900509,0.00000581939,0.000040142102,0.037392266,0.000081826394,0.95827746,0.002727684,0.00042563243],"about_ca_topic_score_codex":0.00025844257,"about_ca_topic_score_gemma":0.0002738588,"teacher_disagreement_score":0.48112026,"about_ca_system_score_codex":0.00031425728,"about_ca_system_score_gemma":0.00010055171,"threshold_uncertainty_score":0.99994016},"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":"W4313532610","doi":"10.48550/arxiv.2301.01085","title":"The Chained Difference-in-Differences","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Estimator; Inference; Identification (biology); Panel data; Term (time); Missing data; Selection (genetic algorithm); Sample (material); Binary number; Econometrics; Relevance (law); Computer science; Average treatment effect; Variation (astronomy); Statistics; Mathematics; Artificial intelligence","score_opus":0.38040915584152923,"score_gpt":0.30079861071140973,"score_spread":0.0796105451301195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313532610","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":[0.8812537,0.00006714338,0.110943615,0.00040657184,0.0007384902,0.0010791576,0.000045131746,0.001744429,0.0037217683],"genre_scores_gemma":[0.9854761,0.0010079512,0.0007476257,0.000021448526,0.000073932846,0.000014103712,0.000010261059,0.000057448047,0.012591131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977837,0.00022684911,0.0003823541,0.0008798515,0.00014221769,0.0005850354],"domain_scores_gemma":[0.99622697,0.001851009,0.0003716191,0.0013014417,0.00013377776,0.00011515939],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005066717,0.00045641453,0.00056167605,0.0002642486,0.00022772222,0.00009106037,0.0015160672,0.0004277119,0.000032835324],"category_scores_gemma":[0.0006430255,0.00037172326,0.00020535619,0.0005468855,0.00032304015,0.0000880588,0.0014735372,0.0011291328,0.00006626351],"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":[0.000057199682,0.00008946918,0.010515158,0.00014612384,0.000083861225,0.00025768834,0.00029864442,0.00076556765,0.0000417361,0.98647654,0.0005801541,0.00068783044],"study_design_scores_gemma":[0.00020064334,0.000043699667,0.0061965915,0.00027899322,0.00004736611,0.0000010893829,0.00039310777,0.014461191,0.000100653655,0.9777697,0.00007819347,0.00042881496],"about_ca_topic_score_codex":0.00021290264,"about_ca_topic_score_gemma":0.0014251225,"teacher_disagreement_score":0.11019599,"about_ca_system_score_codex":0.00030218938,"about_ca_system_score_gemma":0.00014956044,"threshold_uncertainty_score":0.99987346},"labels":[],"label_agreement":null},{"id":"W4313564705","doi":"10.2196/39876","title":"The Current Status of Secondary Use of Claims, Electronic Medical Records, and Electronic Health Records in Epidemiology in Japan: Narrative Literature Review","year":2023,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Epidemiology; Receipt; Medical record; Family medicine; MEDLINE; Population; Inclusion (mineral); World Wide Web; Psychology; Computer science; Pathology; Environmental health","score_opus":0.16428323579088036,"score_gpt":0.5074737274640504,"score_spread":0.34319049167317006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313564705","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":[0.000058276426,0.9953327,0.00035492147,0.0006081199,0.00016515984,0.0032185789,0.00010402829,0.000094660674,0.00006353431],"genre_scores_gemma":[0.0000038533476,0.9966497,0.0014156369,0.00059932517,0.000061389626,0.00084517774,0.00031583206,0.00006702293,0.000042083135],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862047,0.0023536133,0.007864798,0.00038882674,0.0011875543,0.0020005188],"domain_scores_gemma":[0.9818524,0.012866612,0.003693073,0.00085417123,0.00019818335,0.0005355449],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010800197,0.00070798636,0.0053019724,0.00054996344,0.00006764868,0.000017637265,0.0008768458,0.0010625108,0.000087466695],"category_scores_gemma":[0.021560391,0.00044891975,0.00035991208,0.0017321816,0.0006599178,0.00035418037,0.00047490385,0.0075576524,0.00000467468],"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":[0.000012106264,0.00008011225,0.000010456981,0.13080944,0.00006869602,0.0000040138984,0.0016404658,2.8338638e-8,1.6130108e-9,0.028042851,0.0102132335,0.8291186],"study_design_scores_gemma":[0.0002555824,0.0004691573,0.000004826662,0.25397602,0.0000560918,0.00006953857,0.00023092773,0.00012355822,7.657833e-8,0.056070928,0.68844515,0.0002981391],"about_ca_topic_score_codex":0.000048391325,"about_ca_topic_score_gemma":0.002490685,"teacher_disagreement_score":0.82882047,"about_ca_system_score_codex":0.0010016548,"about_ca_system_score_gemma":0.009188073,"threshold_uncertainty_score":0.9997963},"labels":[],"label_agreement":null},{"id":"W4313703179","doi":"10.1186/s12874-022-01831-2","title":"Estimation of marginal structural models under irregular visits and unmeasured confounder: calibrated inverse probability weights","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Confounding; Observational study; Marginal structural model; Estimator; Glycemic; Medicine; Statistics; Inverse probability; Longitudinal study; Monte Carlo method; Calibration; Inverse probability weighting; Randomized controlled trial; Econometrics; Computer science; Mathematics; Diabetes mellitus; Bayesian probability; Internal medicine","score_opus":0.7798766947382557,"score_gpt":0.5947207635660053,"score_spread":0.18515593117225038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313703179","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":[0.3753149,0.000037254977,0.6232016,0.00044195002,0.000049018883,0.0005284,0.0000067809956,0.00022323716,0.000196883],"genre_scores_gemma":[0.4297306,0.00006712979,0.5698603,0.000040296447,0.000037865837,0.00008142485,0.000021571512,0.000027666001,0.00013315916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877417,0.008761687,0.00063662935,0.00049859064,0.0016888002,0.0006725595],"domain_scores_gemma":[0.96807706,0.030363316,0.00014633597,0.00050878845,0.0004985335,0.00040597952],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020320874,0.00019161166,0.00063646014,0.00038242977,0.00013573172,0.000020278481,0.0003872199,0.0004698354,0.0002839224],"category_scores_gemma":[0.054469276,0.00015233355,0.00006313368,0.00082882465,0.001466495,0.0002478535,0.00040339553,0.0007541001,0.000008911481],"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":[0.00026516482,0.000040366027,0.00035300964,0.0007649652,0.000044923232,0.00002184898,0.00042446697,0.00051009696,0.002336495,0.9833229,0.0005682032,0.011347547],"study_design_scores_gemma":[0.000367619,0.00012963655,0.0011053269,0.00009193949,0.000010633757,0.000019876108,0.0001708076,0.26761204,0.0036501857,0.72673416,0.000010464099,0.000097298216],"about_ca_topic_score_codex":0.00014548127,"about_ca_topic_score_gemma":0.0003149979,"teacher_disagreement_score":0.26710194,"about_ca_system_score_codex":0.00012604364,"about_ca_system_score_gemma":0.000912244,"threshold_uncertainty_score":0.9534953},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4313892100","doi":"10.1002/cjs.11751","title":"Inducement of population sparsity","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"Orthogonalization; Context (archaeology); Parameterized complexity; Inference; Transformation (genetics); Population; Nuisance parameter; Covariance; Path (computing); Computer science; Mathematics; Applied mathematics; Calculus (dental); Mathematical optimization; Algorithm; Artificial intelligence; Statistics","score_opus":0.24927693674633059,"score_gpt":0.3945791197856565,"score_spread":0.14530218303932593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313892100","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":[0.5956208,0.00003586507,0.40190256,0.00024106647,0.0004623877,0.00020015899,0.0006163726,0.00004244932,0.0008783532],"genre_scores_gemma":[0.8730272,0.000013844248,0.12679602,0.000019432056,0.00003572248,5.4987964e-7,0.000014333865,0.000010747812,0.000082160004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923503,0.00002632461,0.00037759726,0.000044674427,0.0001624788,0.00015388987],"domain_scores_gemma":[0.99888337,0.00019718645,0.00034368408,0.000105121435,0.0002732639,0.00019740425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033059597,0.00006229389,0.00017735177,0.000269798,0.000040956238,0.00000922759,0.0001166776,0.000041478637,0.000093010276],"category_scores_gemma":[0.0010223491,0.00006142926,0.000024961702,0.00020057433,0.000042459204,0.00007147807,0.0000085928095,0.00012410928,0.000004840958],"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":[0.000011330595,0.00002399476,0.027434723,0.00016003732,0.00006722984,0.00031590252,0.0010916617,0.00016350346,0.0005995876,0.87311417,0.07851074,0.018507147],"study_design_scores_gemma":[0.00013180105,0.00014622102,0.027671086,0.00010372039,0.0000355208,0.000020172089,0.00018670844,0.00014752519,0.0009917016,0.96918947,0.0012810484,0.00009503538],"about_ca_topic_score_codex":0.0014796791,"about_ca_topic_score_gemma":0.008719704,"teacher_disagreement_score":0.2774064,"about_ca_system_score_codex":0.00013801349,"about_ca_system_score_gemma":0.00026856593,"threshold_uncertainty_score":0.48657995},"labels":[],"label_agreement":null},{"id":"W4315436872","doi":"10.1093/aje/kwad009","title":"RE: “A FRAMEWORK FOR DESCRIPTIVE EPIDEMIOLOGY”","year":2023,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Biostatistics; Epidemiology; Medicine; Public health; Clinical epidemiology; Family medicine; Library science; Gerontology; Computer science; Pathology","score_opus":0.39698030705077686,"score_gpt":0.5023215673924645,"score_spread":0.10534126034168761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315436872","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":[0.00005462113,0.00043103113,0.5743193,0.42345694,0.0010371961,0.0003553182,0.00007968351,0.00017364523,0.00009227485],"genre_scores_gemma":[0.000081935534,0.0008498092,0.592259,0.40093717,0.0052465443,0.00010599638,0.000036141464,0.00017921266,0.00030420974],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877169,0.005525892,0.004134543,0.00075400266,0.00022190208,0.0016467605],"domain_scores_gemma":[0.762064,0.22673894,0.009345371,0.0009179522,0.00071859866,0.00021513419],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.016042221,0.00077348965,0.005885142,0.0006731085,0.000117109375,0.0000065302897,0.0013584731,0.0017371237,0.000083934094],"category_scores_gemma":[0.32624537,0.00061152707,0.0012955742,0.00048582288,0.0019764707,0.0001415338,0.00018355959,0.006620066,0.000038302667],"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":[0.00010832951,0.000020766005,0.00053336605,0.00012332715,0.00046849533,0.00015258306,0.00014568667,0.000011094451,0.0000028853487,0.087018564,0.9046017,0.0068132025],"study_design_scores_gemma":[0.0001101816,0.0019027191,0.000029839257,0.0005685732,0.00021851435,0.00014106871,0.0002891321,0.000021313692,0.0000094511015,0.69093007,0.30540997,0.00036917423],"about_ca_topic_score_codex":0.00006301944,"about_ca_topic_score_gemma":0.000012724192,"teacher_disagreement_score":0.60391146,"about_ca_system_score_codex":0.00050924305,"about_ca_system_score_gemma":0.00029549975,"threshold_uncertainty_score":0.9996336},"labels":[],"label_agreement":null},{"id":"W4317779738","doi":"10.1080/10543406.2022.2162067","title":"Reweighting estimators to extend the external validity of clinical trials: methodological considerations","year":2023,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","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":"Public Health Ontario","funders":"Eli Lilly and Company","keywords":"Inference; Estimator; External validity; Clinical trial; Internal validity; Population; Randomized controlled trial; Statistical inference; Computer science; Causal inference; Econometrics; Medicine; Machine learning; Artificial intelligence; Statistics; Mathematics; Pathology","score_opus":0.9259994941309059,"score_gpt":0.7137800258193395,"score_spread":0.21221946831156635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317779738","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":[0.053170234,0.000052825246,0.94384897,0.0015132594,0.00069998845,0.0003738572,0.00017074522,0.00008031773,0.00008983378],"genre_scores_gemma":[0.2471785,0.00017143712,0.7518585,0.000336853,0.00039636326,0.0000080300415,0.0000012553993,0.000021412654,0.000027690237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990442,0.004432942,0.0037852135,0.00020857119,0.0007774711,0.00035379617],"domain_scores_gemma":[0.9043511,0.09246527,0.0017945315,0.00027440325,0.0007377507,0.00037694027],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03538271,0.0002095399,0.0013094534,0.00016518377,0.00014623579,0.000055126216,0.00035145768,0.00016614869,0.0003608619],"category_scores_gemma":[0.21783337,0.00012312295,0.00033497193,0.00039993547,0.0003798821,0.00010512041,0.00018325078,0.0009720085,0.000020667989],"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":[0.0006929791,0.00057040446,0.0027609128,0.00020653436,0.00040989646,0.0007854114,0.00048481126,0.00023274378,0.019567508,0.84710044,0.058022264,0.0691661],"study_design_scores_gemma":[0.00064897834,0.0005854497,0.0023359417,0.00014838055,0.00045781213,0.00019283271,0.00014303972,0.00532216,0.01629092,0.9721449,0.0015425013,0.00018708392],"about_ca_topic_score_codex":0.0000017628456,"about_ca_topic_score_gemma":0.0000012729512,"teacher_disagreement_score":0.19400826,"about_ca_system_score_codex":0.00004630331,"about_ca_system_score_gemma":0.00019075567,"threshold_uncertainty_score":0.9932765},"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":"W4318024824","doi":"10.1002/sim.9658","title":"Propensity score matching after multiple imputation when a confounder has missing data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"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":"Medical Research Council; Medical Research Council Canada","keywords":"Propensity score matching; Causal inference; Missing data; Imputation (statistics); Confounding; Statistics; Observational study; Average treatment effect; Matching (statistics); Estimator; Computer science; Confidence interval; Inference; Covariate; Econometrics; Mathematics; Artificial intelligence","score_opus":0.4066710686130003,"score_gpt":0.46171335322110957,"score_spread":0.05504228460810928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318024824","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":[0.03081481,0.000036582045,0.9666271,0.00090032764,0.00018831898,0.00050565973,0.00020679642,0.00036261443,0.0003577975],"genre_scores_gemma":[0.4986424,0.000025084715,0.50017637,0.00027088466,0.00011129465,0.000033723463,0.00052229007,0.000043378102,0.00017454204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983574,0.00009351783,0.00049065636,0.00035856312,0.00039615744,0.0003036839],"domain_scores_gemma":[0.997313,0.0016609111,0.00016378322,0.0006535743,0.00013361021,0.00007508329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001178013,0.00018000689,0.0003605257,0.00017856449,0.00009070049,0.000040220126,0.0002963105,0.000073516945,0.0001458393],"category_scores_gemma":[0.005262186,0.00015061391,0.000008978387,0.00024666882,0.00026349328,0.0002205848,0.00028221568,0.00031219484,0.000025650128],"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":[0.00067127903,0.00044040222,0.06816714,0.0042719417,0.00023815034,0.00408502,0.05490792,0.00018369795,0.015710454,0.346765,0.31710684,0.18745214],"study_design_scores_gemma":[0.00053006934,0.00006250145,0.012466019,0.00062072626,0.000033540473,0.0000110972605,0.000401085,0.011507642,0.000107716834,0.9736603,0.00041766115,0.00018167018],"about_ca_topic_score_codex":0.00023226977,"about_ca_topic_score_gemma":0.00048550582,"teacher_disagreement_score":0.62689525,"about_ca_system_score_codex":0.000094762465,"about_ca_system_score_gemma":0.00008239574,"threshold_uncertainty_score":0.6299708},"labels":[],"label_agreement":null},{"id":"W4318067345","doi":"10.1002/sim.9665","title":"Measuring the performance of prediction models to personalize treatment choice","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":43,"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":"Medical Research Council; Medical Research Council Canada; ZonMw; European Commission; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Covariate; Calibration; Machine learning; Baseline (sea); Outcome (game theory); Range (aeronautics); Artificial intelligence; Predictive modelling; Data mining; Statistics; Mathematics","score_opus":0.2535139144086483,"score_gpt":0.4251422307621626,"score_spread":0.17162831635351433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318067345","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":[0.48179165,0.000120728124,0.5119709,0.0009334237,0.0002778482,0.0011769306,0.00031567662,0.0003825582,0.0030303218],"genre_scores_gemma":[0.92949396,0.00049017003,0.069059014,0.000063967214,0.00011278067,0.00015792702,0.000026308695,0.000025612186,0.00057028263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895746,0.000042436437,0.0003269897,0.00014156871,0.00034760172,0.00018397407],"domain_scores_gemma":[0.99847007,0.001043003,0.00008557617,0.0002554962,0.00010228551,0.00004359917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356165,0.0001138824,0.00023397147,0.00013833752,0.000046853733,0.0000026040236,0.0001325531,0.000032632983,0.00003490682],"category_scores_gemma":[0.00078461564,0.00007208513,0.000012348723,0.0003874168,0.00009801732,0.00005173915,0.000033924392,0.00010171805,0.0000058894693],"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":[0.00021065497,0.00031192385,0.01195835,0.0011496537,0.0001745661,0.00005054548,0.05671098,0.0136581585,0.012313688,0.766417,0.043397516,0.093646936],"study_design_scores_gemma":[0.0013770588,0.0022619544,0.009245682,0.0012527964,0.00012136201,0.00000882517,0.0025477537,0.21694823,0.0064604287,0.7580605,0.0014394848,0.00027590504],"about_ca_topic_score_codex":0.00012966026,"about_ca_topic_score_gemma":0.00011366068,"teacher_disagreement_score":0.4477023,"about_ca_system_score_codex":0.00014568178,"about_ca_system_score_gemma":0.00002871421,"threshold_uncertainty_score":0.29395464},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4318450495","doi":"10.1097/ede.0000000000001596","title":"Average Causal Effect Estimation Via Instrumental Variables: the No Simultaneous Heterogeneity Assumption","year":2023,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":25,"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","funders":"Economic and Social Research Council; Medical Research Council","keywords":"Instrumental variable; Econometrics; Homogeneity (statistics); Uncorrelated; Spatial heterogeneity; Average treatment effect; Identification (biology); Statistics; Study heterogeneity; Mathematics; Propensity score matching; Economics; Biology","score_opus":0.12763056610035575,"score_gpt":0.4334693375817595,"score_spread":0.3058387714814037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318450495","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":[0.40744323,0.000016851418,0.5894247,0.00043566985,0.0004225962,0.0006563394,0.000017790659,0.00110654,0.00047623564],"genre_scores_gemma":[0.96989375,0.000039858194,0.028948916,0.00047124422,0.00016641164,0.00018210565,0.000105102255,0.000037348727,0.00015528785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99699676,0.0014019334,0.0005873286,0.00037286934,0.00013429164,0.00050683675],"domain_scores_gemma":[0.97893745,0.020127565,0.00029706233,0.0005135264,0.000052805583,0.00007161042],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036141851,0.00025303915,0.0005176044,0.00008562072,0.00020409774,0.0000105698255,0.00026550773,0.000261424,0.00011347657],"category_scores_gemma":[0.01733411,0.00017510382,0.00010710817,0.00020066721,0.00017024697,0.00013653128,0.00016217603,0.00037025797,0.00078119995],"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":[0.00086645846,0.0005447498,0.05495677,0.0013772851,0.00095394306,0.0004024483,0.0014417014,0.172989,0.07369149,0.3483699,0.053618003,0.29078826],"study_design_scores_gemma":[0.00031551032,0.000494808,0.0012566806,0.000050816372,0.00004291853,0.00008708421,0.000008565641,0.4307881,0.0071988674,0.5584814,0.0009899967,0.00028523893],"about_ca_topic_score_codex":0.00007084924,"about_ca_topic_score_gemma":0.000033498327,"teacher_disagreement_score":0.56245047,"about_ca_system_score_codex":0.00017081699,"about_ca_system_score_gemma":0.000018862213,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W4318480792","doi":"10.3390/pharmaceutics15020460","title":"Comparison of Seven Non-Linear Mixed Effect Model-Based Approaches to Test for Treatment Effect","year":2023,"lang":"en","type":"article","venue":"Pharmaceutics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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 on Aging; Uppsala Multidisciplinary Center for Advanced Computational Science; Institut de Recherches Servier; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Vetenskapsrådet; Eisai; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Merck; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Akaike information criterion; Model selection; Type I and type II errors; Mixed model; Statistics; Linear model; Selection (genetic algorithm); Econometrics; Mathematics; Computer science; Artificial intelligence","score_opus":0.5686754144864963,"score_gpt":0.5318651782905018,"score_spread":0.03681023619599444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318480792","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":[0.5159767,0.00002930795,0.4787955,0.00019939987,0.00010761088,0.003743211,0.00017257428,0.0007420378,0.00023363775],"genre_scores_gemma":[0.9022113,0.0000062062136,0.09633605,0.000034225963,0.00005536282,0.0010940147,0.000061209306,0.00007784744,0.00012375614],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850273,0.00009266379,0.00042948715,0.00031566602,0.00023723845,0.0004222263],"domain_scores_gemma":[0.9948103,0.0043787705,0.00017462274,0.00041799768,0.00006619124,0.00015215413],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068843213,0.00034698864,0.0007585013,0.00017866114,0.00007905049,0.0000127968815,0.00023989724,0.00010989669,0.00000431248],"category_scores_gemma":[0.00065206195,0.00027630333,0.0001915548,0.00038538506,0.000046040164,0.000052803985,0.00006990734,0.000108857246,0.0000278374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027669761,0.0068842336,0.031748142,0.011184273,0.0009298932,0.000023644196,0.006123342,0.42225325,0.33930686,0.005578559,0.012111985,0.16108882],"study_design_scores_gemma":[0.0008914346,0.0014503044,0.000008596859,0.000046007866,0.000157218,2.8186778e-7,0.000014780746,0.49926046,0.49549782,0.0022315101,0.00029693774,0.00014466881],"about_ca_topic_score_codex":0.0000024950402,"about_ca_topic_score_gemma":0.000004832349,"teacher_disagreement_score":0.3862346,"about_ca_system_score_codex":0.00016616567,"about_ca_system_score_gemma":0.00005646188,"threshold_uncertainty_score":0.9999689},"labels":[],"label_agreement":null},{"id":"W4318754245","doi":"10.1093/aje/kwad026","title":"Invited Commentary: Cross-Sectional Studies and Causal Inference—It’s Complicated","year":2023,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","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":"Université de Montréal; McGill University; Centre Hospitalier Universitaire Sainte-Justine","funders":"Faculty of Medicine and Health, University of Sydney; McGill University","keywords":"Causal inference; Inference; Cross-sectional study; Causality (physics); Etiology; Medicine; Psychology; Computer science; Artificial intelligence; Psychiatry; Pathology","score_opus":0.42374208400239427,"score_gpt":0.5360242416523908,"score_spread":0.11228215764999655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318754245","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":[0.0128152715,0.0004902026,0.01402536,0.9714682,0.0006363099,0.00025149004,0.000098748824,0.00019707452,0.000017344824],"genre_scores_gemma":[0.0030271588,0.0021865026,0.050207205,0.9422576,0.0020153713,0.000040367417,0.000101885445,0.000106932726,0.000056990168],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99400264,0.001968847,0.00249269,0.0004997268,0.0003077464,0.0007283714],"domain_scores_gemma":[0.9544289,0.03998971,0.0041861804,0.00045920466,0.0007821741,0.00015379001],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003830385,0.0005605258,0.0028693338,0.00058317184,0.00014801823,0.000022002998,0.00059142907,0.00043041894,0.000024339115],"category_scores_gemma":[0.019608185,0.0004425969,0.00027056725,0.00039820146,0.0031970458,0.00016178864,0.0003515314,0.0035795223,0.000007895463],"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":[0.000048905127,0.000018990499,0.0519722,0.00010729704,0.000752455,0.00023606197,0.00011108468,0.0000100871275,0.000018382458,0.00045792735,0.94559246,0.0006741423],"study_design_scores_gemma":[0.0004376632,0.0021722813,0.012568248,0.0005069263,0.00021600765,0.0011853138,0.0003124806,0.000042191055,0.000017038008,0.6862902,0.29558775,0.0006639002],"about_ca_topic_score_codex":0.00019741687,"about_ca_topic_score_gemma":0.000034603945,"teacher_disagreement_score":0.68583226,"about_ca_system_score_codex":0.00035266014,"about_ca_system_score_gemma":0.00005073228,"threshold_uncertainty_score":0.9998026},"labels":[],"label_agreement":null},{"id":"W4318755449","doi":"10.1002/sim.9675","title":"Multistate models as a framework for estimand specification in clinical trials of complex processes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"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","keywords":"Inference; Econometrics; Computer science; Estimator; Limiting; Statistics; Artificial intelligence; Mathematics","score_opus":0.7226251117965159,"score_gpt":0.6472965689702329,"score_spread":0.07532854282628298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318755449","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":[0.0036453726,0.000060097584,0.9938658,0.0004001733,0.00010118189,0.0011758633,0.00036037114,0.000105174106,0.00028595232],"genre_scores_gemma":[0.10934044,0.00090297824,0.88915855,0.000057155776,0.00010539659,0.00013219842,0.00018841011,0.00003132136,0.00008355544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968501,0.00025635725,0.0021155397,0.00026709915,0.00028456972,0.00022635718],"domain_scores_gemma":[0.96873844,0.029938841,0.0006828304,0.00028701845,0.00029615685,0.000056736724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006827249,0.00014686478,0.0009826015,0.0002672882,0.00002075436,0.0000051692705,0.0001817179,0.00012616986,0.00006023993],"category_scores_gemma":[0.129482,0.00012221532,0.000028898512,0.000571002,0.00028301682,0.00006114843,0.00003412666,0.0002325101,0.0000032301812],"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":[0.00021096724,0.00013941778,0.00032437555,0.0009582142,0.000015496127,0.000018205224,0.0013378263,0.00030285257,0.00023162551,0.9659793,0.008895449,0.021586264],"study_design_scores_gemma":[0.0010930994,0.00030817144,0.00045743908,0.0008339437,0.00002816287,9.123155e-7,0.00039930097,0.040354576,0.00024905137,0.9559451,0.0002242577,0.00010600421],"about_ca_topic_score_codex":0.000038609684,"about_ca_topic_score_gemma":0.00011005222,"teacher_disagreement_score":0.12265475,"about_ca_system_score_codex":0.00004688031,"about_ca_system_score_gemma":0.00010305611,"threshold_uncertainty_score":0.8778507},"labels":[],"label_agreement":null},{"id":"W4319058127","doi":"10.1002/sim.9663","title":"The Personalised Randomized Controlled Trial: Evaluation of a new trial design","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"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; Medical Research Council Canada; King's College London; Medical Research Council; National Institute for Health and Care Research","keywords":"Randomized controlled trial; Pooling; Randomization; Computer science; Clinical trial; Ranking (information retrieval); Outcome (game theory); Medicine; Intervention (counseling); Machine learning; Artificial intelligence; Mathematics; Surgery; Psychiatry","score_opus":0.32244574998036885,"score_gpt":0.5144343715594577,"score_spread":0.19198862157908886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319058127","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":[0.0061436775,0.0002716038,0.9702922,0.0011354896,0.00089903903,0.019563455,0.000015926124,0.00017985338,0.0014987511],"genre_scores_gemma":[0.2978032,0.0029166231,0.67405933,0.00028796727,0.002367116,0.013951214,0.00016502908,0.00021478477,0.008234729],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947929,0.0021305745,0.0013510754,0.00017849848,0.00130981,0.00023715345],"domain_scores_gemma":[0.9621731,0.03644032,0.00060905976,0.0003017912,0.00042070355,0.000055011496],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027971735,0.00016199528,0.0014204386,0.0001820295,0.000058131485,0.000008561518,0.0001966222,0.00007405569,0.00020364128],"category_scores_gemma":[0.13939115,0.00008930849,0.00008321807,0.00039153904,0.00034618593,0.00003155602,0.000024068651,0.00018420604,0.0000044660123],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.80736595,0.000030056164,1.4070159e-7,0.000013496883,0.00006963203,0.0000027161932,0.000955619,0.00002671525,0.00007341924,0.16953619,0.018458847,0.0034672176],"study_design_scores_gemma":[0.5040283,0.00037582268,4.2514534e-7,0.00006271382,0.00024746705,2.1734476e-7,0.00022114739,0.015551906,0.000038774066,0.4794095,0.000021139722,0.000042603995],"about_ca_topic_score_codex":0.000048815156,"about_ca_topic_score_gemma":0.000033079377,"teacher_disagreement_score":0.3098733,"about_ca_system_score_codex":0.000089242785,"about_ca_system_score_gemma":0.0003731539,"threshold_uncertainty_score":0.9694501},"labels":[],"label_agreement":null},{"id":"W4319457358","doi":"10.1016/b978-0-44-318780-3.00014-2","title":"Confounding in Cohort Studies - Part I","year":2023,"lang":"en","type":"book-chapter","venue":"Epidemiologic Methods","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":"University of Alberta","funders":"","keywords":"Confounding; Counterfactual thinking; Context (archaeology); Odds; Econometrics; Odds ratio; Cohort; Medicine; Statistics; Mathematics; Psychology; Logistic regression; Geography; Social psychology","score_opus":0.7893719837301452,"score_gpt":0.6362134759019756,"score_spread":0.15315850782816953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319457358","genre_codex":"other","genre_gemma":"methods","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":[0.000023643597,0.0029478853,0.2729393,0.00043808657,0.0015687348,0.001526805,0.000028595594,0.0021624898,0.7183645],"genre_scores_gemma":[0.0000055932082,0.008091702,0.62913024,0.00033327148,0.00023688367,0.00024164027,0.000019153596,0.00010493022,0.36183658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99481255,0.0015279448,0.0018657473,0.0009188196,0.0002403515,0.00063458324],"domain_scores_gemma":[0.9376454,0.060190793,0.0010188945,0.00089676795,0.000152697,0.00009545681],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025950804,0.000693002,0.0028792333,0.00035537424,0.00008351081,0.0000112373755,0.00045963144,0.0009575006,0.00038609572],"category_scores_gemma":[0.0978682,0.00054962223,0.0002991907,0.000101701575,0.0004265089,0.000079265345,0.00045580254,0.0013763275,0.00014481824],"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":[0.000006326625,0.0000061719034,0.00027521214,0.00017490216,0.0002508918,0.00006174144,0.000071140945,0.0000045924166,0.000020799862,0.96837246,0.019766353,0.010989393],"study_design_scores_gemma":[0.00006573446,0.000072234594,0.00003459101,0.00087712094,0.00011286616,0.000008368732,0.00005596271,0.00004186231,0.00008444426,0.9278906,0.070255436,0.00050076563],"about_ca_topic_score_codex":0.000010175315,"about_ca_topic_score_gemma":0.000023080309,"teacher_disagreement_score":0.35652786,"about_ca_system_score_codex":0.00040456807,"about_ca_system_score_gemma":0.000055007196,"threshold_uncertainty_score":0.99969554},"labels":[],"label_agreement":null},{"id":"W4319457428","doi":"10.1016/b978-0-44-318780-3.00019-1","title":"Case-Control Studies - Part II","year":2023,"lang":"en","type":"book-chapter","venue":"Epidemiologic Methods","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":"University of Alberta","funders":"","keywords":"Confounding; Matching (statistics); Context (archaeology); Selection bias; Control (management); Selection (genetic algorithm); Population; Information bias; Cohort; Econometrics; Statistics; Computer science; Geography; Medicine; Mathematics; Artificial intelligence; Environmental health","score_opus":0.7507360780608867,"score_gpt":0.5917191175720711,"score_spread":0.15901696048881564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319457428","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":[0.000008978956,0.005159624,0.63529795,0.00094154826,0.0015520918,0.0014893349,0.00018861755,0.0040179975,0.35134384],"genre_scores_gemma":[0.000011830164,0.0023080679,0.59051454,0.00068450574,0.00046059504,0.00022864567,0.00000954156,0.0001280115,0.40565428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99421704,0.0019809848,0.0018250498,0.001032177,0.0002304788,0.00071427703],"domain_scores_gemma":[0.92220134,0.07478209,0.0012989915,0.0012899959,0.00027482788,0.00015278638],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019829461,0.0009167234,0.0032227885,0.0002374018,0.00033250026,0.000010433547,0.00046868436,0.0012165837,0.00071440387],"category_scores_gemma":[0.10414679,0.0006750123,0.0005922451,0.00007326056,0.0004978457,0.00008348985,0.00059325877,0.0014284863,0.00016349349],"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":[0.000010762913,0.0000092202135,0.0000031324157,0.0001621763,0.0005849827,0.0011617695,0.00009635912,0.0000054823176,0.000014664848,0.8953209,0.068856396,0.033774156],"study_design_scores_gemma":[0.000118835385,0.00023589871,6.6268933e-7,0.00033145412,0.00041153491,0.0004756363,0.000047173897,0.000077058074,0.00006344796,0.89230704,0.10533085,0.0006004138],"about_ca_topic_score_codex":0.000005292779,"about_ca_topic_score_gemma":0.0000114737,"teacher_disagreement_score":0.084317334,"about_ca_system_score_codex":0.00021847704,"about_ca_system_score_gemma":0.000051314157,"threshold_uncertainty_score":0.99957013},"labels":[],"label_agreement":null},{"id":"W4319457455","doi":"10.1016/b978-0-44-318780-3.00012-9","title":"Effect Modification in Cohort Studies","year":2023,"lang":"en","type":"book-chapter","venue":"Epidemiologic Methods","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":"University of Alberta","funders":"","keywords":"Multivariate statistics; Context (archaeology); Cohort; Measure (data warehouse); Property (philosophy); Symmetry (geometry); Multivariate analysis; Mathematics; Econometrics; Psychology; Statistics; Computer science; Geography; Data mining; Geometry; Epistemology; Philosophy","score_opus":0.7122359460271557,"score_gpt":0.6399342536554881,"score_spread":0.07230169237166761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319457455","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":[0.000105968094,0.0029236167,0.62355185,0.00037941293,0.00074049016,0.0028117457,0.000022196113,0.0024623873,0.3670023],"genre_scores_gemma":[0.00004782924,0.0057957927,0.7744785,0.00015273946,0.00014698553,0.0006419242,0.000034443357,0.00011870938,0.21858308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99404097,0.0030065572,0.0014241666,0.000873696,0.0002106391,0.00044394733],"domain_scores_gemma":[0.92256147,0.07548262,0.00083810656,0.0009290054,0.00012455415,0.000064233966],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03329107,0.00061321934,0.0023781965,0.00034000174,0.0000579715,0.0000068919235,0.0004033666,0.00092876365,0.000088516535],"category_scores_gemma":[0.09956566,0.00045739347,0.00027189607,0.00010089938,0.00026701335,0.00006376248,0.0002728799,0.0010923665,0.00013060123],"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":[0.000016008176,0.0000071963173,0.00018457802,0.0003428252,0.00018384653,0.0000209261,0.00005168463,0.000015006431,0.00010260254,0.92430884,0.005481348,0.06928514],"study_design_scores_gemma":[0.000075440366,0.00021145339,0.000084334395,0.00050406094,0.00013660979,0.000004225325,0.000009317996,0.00022061044,0.0005803471,0.99336433,0.004405839,0.00040343957],"about_ca_topic_score_codex":0.000008908568,"about_ca_topic_score_gemma":0.000007909931,"teacher_disagreement_score":0.15092663,"about_ca_system_score_codex":0.00036522522,"about_ca_system_score_gemma":0.00002904617,"threshold_uncertainty_score":0.9997878},"labels":[],"label_agreement":null},{"id":"W4319790982","doi":"10.1080/03610918.2023.2170412","title":"Measurement error correction in mediation analysis under the additive hazards model","year":2023,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Advanced Causal Inference Techniques","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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Confounding; Mediation; Econometrics; Causal model; Proportional hazards model; Observational error; Set (abstract data type); Computer science; Statistics; Psychology; Mathematics; Sociology","score_opus":0.39035368825593214,"score_gpt":0.5190396433365053,"score_spread":0.12868595508057318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319790982","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":[0.012210439,0.00004571619,0.9864369,0.00039942612,0.000051709674,0.0004305202,0.000048679358,0.00016272925,0.00021387576],"genre_scores_gemma":[0.94224477,0.0001713638,0.05695936,0.000058272137,0.0000074996465,0.00013596994,0.00038149036,0.000014388439,0.000026883345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846154,0.00033602235,0.00051997555,0.00019069397,0.00034918747,0.00014256137],"domain_scores_gemma":[0.996778,0.002132099,0.00023044313,0.00044525525,0.0003860521,0.000028150167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011174446,0.00012463875,0.00019296638,0.0005867308,0.00019684852,0.000049589064,0.00018915001,0.000073638344,0.0000058944224],"category_scores_gemma":[0.00088553916,0.00011800948,0.000028295586,0.0016968121,0.000106573134,0.00018043742,0.00011207876,0.0002295631,0.0000050022845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008815721,0.00005490661,0.0007359715,0.000007236206,0.000027672218,2.3140282e-7,0.0012381145,0.92247975,0.000010569125,0.052877497,0.0002243077,0.022334933],"study_design_scores_gemma":[0.00016588609,0.000011277068,0.01926163,0.000026307502,0.000041302752,1.4609385e-7,0.00056023465,0.68114394,0.000004761036,0.2986876,0.000014652221,0.00008227287],"about_ca_topic_score_codex":0.000048663485,"about_ca_topic_score_gemma":0.0023825255,"teacher_disagreement_score":0.93003434,"about_ca_system_score_codex":0.0002981728,"about_ca_system_score_gemma":0.00006961829,"threshold_uncertainty_score":0.48122868},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4319836254","doi":"10.1080/03610926.2023.2166790","title":"Doubly weighted mean score estimating functions with a partially observed effect modifier","year":2023,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","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; London Health Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Propensity score matching; Estimator; Causal inference; Inverse probability; Observational study; Statistics; Mathematics; Confounding; Imputation (statistics); Inverse probability weighting; Missing data; Inference; Medicine; Econometrics; Computer science; Artificial intelligence; Bayesian probability; Posterior probability","score_opus":0.2590116364723314,"score_gpt":0.4956085579918074,"score_spread":0.23659692151947603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319836254","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":[0.029950697,0.00011051248,0.96809363,0.000051811392,0.00005070149,0.00049360556,0.000035693334,0.0004651208,0.00074820506],"genre_scores_gemma":[0.13426034,0.000061150764,0.8648428,0.000031820568,0.000013175503,0.00036244947,0.00007428871,0.000036754056,0.00031726036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955673,0.0033894368,0.0004175404,0.00024155997,0.00013763222,0.000246517],"domain_scores_gemma":[0.9816374,0.01706114,0.00021136912,0.0008838677,0.00013172453,0.00007446881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063644135,0.0002010799,0.00034698664,0.00015836094,0.00026922754,0.000054039192,0.0002865869,0.0000934572,0.00004236203],"category_scores_gemma":[0.003995217,0.0001655447,0.000024435449,0.00048936746,0.0002924219,0.00017399421,0.00019504194,0.0003721055,0.000007007993],"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":[0.00019764948,0.00004088674,0.00061819406,0.00015287197,0.000035464695,0.000004573524,0.0017211472,0.00014223412,0.00077011157,0.8976043,0.0001867786,0.09852581],"study_design_scores_gemma":[0.00048451484,0.00015153953,0.0010682192,0.00030019644,0.000070221424,0.0000064130422,0.00027908984,0.025525503,0.0016865847,0.97009575,0.00012472784,0.00020722109],"about_ca_topic_score_codex":0.000017423901,"about_ca_topic_score_gemma":0.00008892854,"teacher_disagreement_score":0.10430964,"about_ca_system_score_codex":0.000046907142,"about_ca_system_score_gemma":0.000041578576,"threshold_uncertainty_score":0.67507166},"labels":[],"label_agreement":null},{"id":"W4319984852","doi":"10.31234/osf.io/hmnrx","title":"A Problem in Theory and More: Measuring the Moderating Role of Culture in Many Labs 2","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"Canadian Institute for Advanced Research; University of British Columbia; York University","funders":"Canadian Institute for Advanced Research","keywords":"Replication (statistics); Sample (material); Sample size determination; Conflation; Selection (genetic algorithm); Variable (mathematics); Population; Value (mathematics); Scale (ratio); Sampling (signal processing); Research design; Psychology; Computer science; Data science; Statistics; Sociology; Geography; Epistemology; Social science; Artificial intelligence; Mathematics; Demography; Machine learning; Cartography","score_opus":0.11053391071311729,"score_gpt":0.38890621282660726,"score_spread":0.27837230211348996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319984852","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":[0.71337694,0.002078422,0.2308963,0.0012051251,0.00009274139,0.00685676,0.000053388387,0.0019643777,0.043475945],"genre_scores_gemma":[0.8396888,0.0001594947,0.1586731,0.00003637015,0.000021193255,0.0004397344,0.0000037850125,0.00005539809,0.000922155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861246,0.0001984552,0.00048626456,0.0003063498,0.00019666646,0.00019980533],"domain_scores_gemma":[0.9987907,0.0005114448,0.00020510332,0.0004096517,0.00006321478,0.000019882667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018150252,0.00021786413,0.00039215715,0.00012221243,0.000026396865,0.000033897802,0.00027382758,0.00024311706,0.000008355283],"category_scores_gemma":[0.0006123222,0.00014314617,0.00004191992,0.00013331985,0.000070901544,0.00007597785,0.0008650309,0.0008467983,7.264516e-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":[0.000028486822,0.000069923706,0.0014741399,0.0010771265,0.000030926556,0.000009581486,0.021634614,0.0020407978,0.005321779,0.96538234,0.00009400946,0.0028362856],"study_design_scores_gemma":[0.000083839455,0.000009959747,0.00023091274,0.0009972999,0.000008726579,0.0000018727727,0.0033629376,0.0054328055,0.00902906,0.9806826,0.000006103305,0.00015389091],"about_ca_topic_score_codex":0.00014363634,"about_ca_topic_score_gemma":0.0005145142,"teacher_disagreement_score":0.12631184,"about_ca_system_score_codex":0.000070037815,"about_ca_system_score_gemma":0.000041433712,"threshold_uncertainty_score":0.58373314},"labels":[],"label_agreement":null},{"id":"W4320502556","doi":"10.1287/mnsc.2023.02575","title":"Estimating Effects of Long-Term Treatments","year":2023,"lang":"en","type":"article","venue":"Management Science","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":"Quest University Canada","funders":"","keywords":"Term (time); Computer science; Scale (ratio); Identification (biology); Sequence (biology); Randomized experiment; Estimation; Data mining; Machine learning; Statistics; Mathematics; Engineering","score_opus":0.09925678041252671,"score_gpt":0.4329090803853109,"score_spread":0.33365229997278417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320502556","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":[0.72715604,0.000008292036,0.25974795,0.000038271377,0.0002121322,0.00069085415,8.9095266e-7,0.00075377384,0.011391808],"genre_scores_gemma":[0.80359083,0.000007445149,0.19500303,0.00001613666,0.000008770023,0.000069861824,9.884134e-7,0.000009951179,0.0012929941],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892807,0.000011585719,0.00017722101,0.00025197078,0.000358307,0.0002728392],"domain_scores_gemma":[0.9992962,0.00014272306,0.00011023609,0.000381617,0.000027079626,0.000042131946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004294895,0.00009527242,0.00013106353,0.00025783083,0.000104489474,0.00002551407,0.00040288814,0.000014598275,0.00001156881],"category_scores_gemma":[0.00024018758,0.0000839219,0.000027123717,0.0010724465,0.00021527744,0.00024185237,0.00032250042,0.000034484878,0.000054395638],"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":[0.000008307248,0.0003940631,0.033993527,0.0032514436,0.000098769364,0.00044118232,0.0010747164,0.00018518235,0.02671534,0.7502092,0.0011938999,0.18243437],"study_design_scores_gemma":[0.00045041626,0.00020196916,0.13130863,0.0007295636,0.00007578188,0.0000029580372,0.000060969112,0.005191355,0.12893695,0.732727,0.000009561936,0.00030487587],"about_ca_topic_score_codex":0.0000019485517,"about_ca_topic_score_gemma":4.8922385e-7,"teacher_disagreement_score":0.1821295,"about_ca_system_score_codex":0.00006283775,"about_ca_system_score_gemma":0.0000067460783,"threshold_uncertainty_score":0.34222358},"labels":[],"label_agreement":null},{"id":"W4320723608","doi":"10.1002/cjs.11763","title":"Subgroup analysis of linear models with measurement error","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Pairwise comparison; Estimator; Mathematics; Convergence (economics); Function (biology); Penalty method; Statistics; Estimation; Observational error; Linear regression; Applied mathematics; Mathematical optimization; Algorithm; Computer science","score_opus":0.28932988325194814,"score_gpt":0.3746780008865957,"score_spread":0.08534811763464756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320723608","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":[0.021423822,0.000043020078,0.977479,0.000085934254,0.000048278707,0.000093192095,0.0004761678,0.000022590182,0.0003279889],"genre_scores_gemma":[0.70209885,0.000020517016,0.29774225,0.000025402698,0.000021265736,0.0000020499263,0.000009815302,0.000022056185,0.000057826466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986015,0.00004070951,0.00052995194,0.00008795288,0.00048451993,0.00025534042],"domain_scores_gemma":[0.9975631,0.00020594205,0.00046214153,0.00020984649,0.0012091136,0.00034984984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068804435,0.00012024783,0.00044071602,0.00088836555,0.000057303507,0.000014276998,0.00020480977,0.000049225073,0.00007764654],"category_scores_gemma":[0.00061627454,0.000099733435,0.000071346956,0.0010545024,0.000106813444,0.00011115888,0.000008256658,0.00017627132,0.0000021201167],"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":[0.00009698935,0.00008831405,0.0066062063,0.00035773957,0.0044574235,0.001492779,0.00483766,0.057736266,0.0007187836,0.88183564,0.036102794,0.00566943],"study_design_scores_gemma":[0.000624533,0.0008825263,0.0041489853,0.00041124204,0.003618837,0.0000470043,0.0013929217,0.081785254,0.0015204409,0.904129,0.00093299506,0.0005062259],"about_ca_topic_score_codex":0.000983632,"about_ca_topic_score_gemma":0.04882629,"teacher_disagreement_score":0.68067497,"about_ca_system_score_codex":0.00022211981,"about_ca_system_score_gemma":0.00086874765,"threshold_uncertainty_score":0.9685302},"labels":[],"label_agreement":null},{"id":"W4320738297","doi":"10.48550/arxiv.2302.00230","title":"Revisiting the Effects of Maternal Education on Adolescents' Academic Performance: Doubly Robust Estimation in a Network-Based Observational Study","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Observational study; Estimation; Econometrics; Computer science; Statistics; Mathematics; Economics","score_opus":0.3188153627781487,"score_gpt":0.3306301684062197,"score_spread":0.011814805628071023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320738297","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":[0.94949484,0.000011033816,0.048405427,0.000054994987,0.00025345842,0.0015067145,0.0000042939746,0.0002008577,0.00006836186],"genre_scores_gemma":[0.9975457,0.000039255054,0.0019791885,0.00005927901,0.00013675436,0.000027204134,0.000033322875,0.00003837951,0.00014092661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9983855,0.00025802932,0.00043053442,0.0004884541,0.00018899608,0.00024849985],"domain_scores_gemma":[0.9977132,0.0008121269,0.00068358256,0.0005886017,0.00016036148,0.0000421086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007728999,0.00027437403,0.00034770565,0.00025342277,0.0000976456,0.000021770868,0.00060312403,0.0003158624,0.0000056352487],"category_scores_gemma":[0.00047267758,0.00025998935,0.000085339154,0.0005483709,0.0000635233,0.00017851843,0.00033374486,0.0013391234,0.000008863532],"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":[0.00010400838,0.00014934366,0.30715808,0.001350173,0.000025310246,0.000010382245,0.00010058987,0.6718378,0.000011514806,0.018177006,0.000089206595,0.0009865729],"study_design_scores_gemma":[0.0007769247,0.00017930161,0.4457518,0.011682411,0.00018042886,7.3765074e-7,0.00015980378,0.37971854,0.00044406982,0.16069527,0.0000033702843,0.00040733206],"about_ca_topic_score_codex":0.00005211334,"about_ca_topic_score_gemma":0.000012914543,"teacher_disagreement_score":0.29211926,"about_ca_system_score_codex":0.00039952673,"about_ca_system_score_gemma":0.00028135913,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W4321236346","doi":"10.1186/s12874-023-01836-5","title":"The iterative bisection procedure: a useful tool for determining parameter values in data-generating processes in Monte Carlo simulations","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Monte Carlo method; Bisection method; Statistic; Computer science; Binary data; Statistics; Covariate; Outcome (game theory); Range (aeronautics); Population; Binary number; Algorithm; Mathematics; Medicine","score_opus":0.8555054034787316,"score_gpt":0.6606382105781666,"score_spread":0.19486719290056498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321236346","genre_codex":"empirical","genre_gemma":"methods","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":[0.5783565,0.000109629786,0.4190492,0.00060926296,0.00008751546,0.0015658645,0.000027102562,0.00017656104,0.000018331673],"genre_scores_gemma":[0.4185896,0.00020842861,0.5782978,0.0000770868,0.00022067512,0.0022542467,0.000035626355,0.00004987934,0.0002666761],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908614,0.0060142796,0.0007909164,0.000623996,0.0008719446,0.0008374363],"domain_scores_gemma":[0.7321366,0.2664387,0.00014315035,0.00065070984,0.00051164086,0.00011917811],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03070352,0.00016625876,0.0004273785,0.00049659424,0.0003117763,0.000080671,0.0007357278,0.00027433806,0.000017285738],"category_scores_gemma":[0.6500702,0.0001166856,0.000035499077,0.0015643189,0.00038586243,0.00031511724,0.0005344006,0.00084933254,0.0000031509953],"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":[0.004582591,0.0016834002,0.17523198,0.015504413,0.0004466696,0.0005946833,0.08355367,0.025599549,0.025734518,0.07116593,0.022701852,0.57320076],"study_design_scores_gemma":[0.000637349,0.00027026315,0.00087369944,0.00049965776,0.000009275948,0.000012507534,0.001830683,0.621897,0.0029162902,0.37038344,0.00046393307,0.00020592149],"about_ca_topic_score_codex":0.000058892812,"about_ca_topic_score_gemma":0.013644459,"teacher_disagreement_score":0.6193667,"about_ca_system_score_codex":0.00013269972,"about_ca_system_score_gemma":0.0012410516,"threshold_uncertainty_score":0.9980947},"labels":[],"label_agreement":null},{"id":"W4321473461","doi":"10.48550/arxiv.2302.09694","title":"Disentangled Representation for Causal Mediation Analysis","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; University of South Australia","keywords":"Confounding; Mediation; Latent variable; Causal inference; Econometrics; Representation (politics); Causality (physics); Observational study; Computer science; Structural equation modeling; Outcome (game theory); Affect (linguistics); Mechanism (biology); Causal model; Artificial intelligence; Machine learning; Psychology; Statistics; Mathematics","score_opus":0.4045632747980406,"score_gpt":0.34888341111123383,"score_spread":0.055679863686806774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321473461","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":[0.15699044,0.0000052586297,0.84035194,0.000079925485,0.00024120651,0.00086285855,0.0001740418,0.0009746659,0.0003196729],"genre_scores_gemma":[0.98529017,0.00010683629,0.010568126,0.000015951375,0.00012784486,0.000026019778,0.0007084859,0.000058444544,0.003098111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982732,0.00011525773,0.00033263725,0.00087236665,0.00012024602,0.00028631082],"domain_scores_gemma":[0.99717337,0.0009925102,0.00052029034,0.00091754633,0.0002914428,0.00010482811],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032382278,0.00029008577,0.00054415,0.00063778396,0.00010777833,0.00004361986,0.00042732296,0.00034291652,0.000054837194],"category_scores_gemma":[0.00076732447,0.00034261026,0.0004605133,0.0011629774,0.000074822325,0.00020095168,0.00044775027,0.00030298525,0.000023838817],"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":[0.00025415843,0.00025993935,0.042769264,0.00054997386,0.0032942442,0.00016619377,0.0006987636,0.13733068,0.00035905014,0.80832595,0.0056166328,0.0003751686],"study_design_scores_gemma":[0.00028473462,0.00003285916,0.0013457607,0.00003272881,0.0016011804,2.5512904e-7,0.00022458716,0.116320446,0.0006027502,0.8791664,0.000034165278,0.0003540976],"about_ca_topic_score_codex":0.00010848626,"about_ca_topic_score_gemma":0.00050774217,"teacher_disagreement_score":0.8297838,"about_ca_system_score_codex":0.0003645524,"about_ca_system_score_gemma":0.000075619384,"threshold_uncertainty_score":0.9999026},"labels":[],"label_agreement":null},{"id":"W4321486913","doi":"10.1093/aje/kwad041","title":"How Choice of Effect Measure Influences Minimally Sufficient Adjustment Sets for External Validity","year":2023,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University Health Centre","funders":"Department of Epidemiology, Biostatistics and Occupational Health, McGill University; University of North Carolina at Chapel Hill; McGill University","keywords":"Measure (data warehouse); Class (philosophy); Outcome (game theory); Scale (ratio); Population; Variable (mathematics); Statistics; Mathematics; Econometrics; Conditional probability; Medicine; Computer science; Mathematical economics; Artificial intelligence; Data mining","score_opus":0.27284504910694357,"score_gpt":0.4778967647614582,"score_spread":0.20505171565451463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321486913","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":[0.8612811,0.0002689315,0.13630463,0.0014782085,0.00023592314,0.0003206873,0.000021484308,0.000063776126,0.000025247895],"genre_scores_gemma":[0.8593944,0.00016005963,0.13993081,0.00023631282,0.00018277831,0.00003945354,0.000002145122,0.000024954346,0.000029140685],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99656796,0.0013506521,0.0010956345,0.00023276663,0.0002662767,0.0004866956],"domain_scores_gemma":[0.9708338,0.025644336,0.0026269045,0.00027231534,0.0004639619,0.00015868271],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006647605,0.00023202025,0.0014086997,0.00025301764,0.000047365043,0.00000597958,0.00045485317,0.000088564906,0.00000829407],"category_scores_gemma":[0.039418392,0.00016567965,0.0003599372,0.00034129256,0.00056193175,0.00013964166,0.00007366913,0.00030688976,0.0000016701321],"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":[0.0032680258,0.0009473455,0.39070502,0.0013486162,0.0014647335,0.000119498894,0.0021126424,0.002199794,0.12859511,0.06654401,0.03750994,0.36518526],"study_design_scores_gemma":[0.0034882743,0.05721994,0.18757167,0.0019594454,0.0010310035,0.00051460596,0.0020405438,0.00195673,0.054863516,0.68185425,0.006159681,0.0013403612],"about_ca_topic_score_codex":0.00003250438,"about_ca_topic_score_gemma":0.000010885482,"teacher_disagreement_score":0.6153102,"about_ca_system_score_codex":0.000104190614,"about_ca_system_score_gemma":0.00010107615,"threshold_uncertainty_score":0.968673},"labels":[],"label_agreement":null},{"id":"W4321611071","doi":"10.1093/biostatistics/kxad002","title":"Assessing the causal effects of a stochastic intervention in time series data: are heat alerts effective in preventing deaths and hospitalizations?","year":2023,"lang":"en","type":"review","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","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":"University of British Columbia","funders":"National Institute on Minority Health and Health Disparities; National Institute of Environmental Health Sciences; Wellcome Trust; Alfred P. Sloan Foundation; National Institute on Aging; National Institutes of Health; Harvard University","keywords":"Causal inference; Estimator; Context (archaeology); Computer science; Time series; Inference; Econometrics; Series (stratigraphy); Nonparametric statistics; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.13287255036280732,"score_gpt":0.4694060812927,"score_spread":0.3365335309298927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321611071","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":[0.0003524683,0.63058954,0.3628299,0.000008610722,0.00019059738,0.0052014776,0.0006291559,0.00018655544,0.000011662206],"genre_scores_gemma":[0.002594856,0.949761,0.044545107,0.00000773422,0.00010852907,0.0012863587,0.0012089785,0.0003094996,0.00017794472],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9976269,0.0006088704,0.0008823143,0.00041107435,0.00022484001,0.0002460172],"domain_scores_gemma":[0.99252355,0.0062077334,0.0006359481,0.00052859646,0.00007268015,0.000031515712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009248536,0.0003550107,0.0012221808,0.0002878563,0.000055987664,0.000106779364,0.00035196735,0.00020083514,0.0000023339098],"category_scores_gemma":[0.007827202,0.000276519,0.00006508705,0.0005452819,0.00014562768,0.00033895767,0.0005557932,0.00034135798,0.0000028850523],"study_design_candidate":"systematic_review","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":[0.00001417557,0.000580884,0.00055732654,0.25733182,0.00041674313,0.0002909683,0.0013040184,0.000018520326,0.0000100277375,0.018384451,0.0005126168,0.72057843],"study_design_scores_gemma":[0.0013406741,0.0007983744,0.003919378,0.72595555,0.003459052,0.00014168791,0.0006999509,0.0042242752,0.00007882481,0.2550743,0.0021276786,0.002180232],"about_ca_topic_score_codex":0.000049396214,"about_ca_topic_score_gemma":0.00015809215,"teacher_disagreement_score":0.7183982,"about_ca_system_score_codex":0.00020715591,"about_ca_system_score_gemma":0.000093972,"threshold_uncertainty_score":0.9999687},"labels":[],"label_agreement":null},{"id":"W4323287872","doi":"10.2196/39455","title":"Effects of Antidepressants on COVID-19 Outcomes: Retrospective Study on Large-Scale Electronic Health Record Data","year":2023,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of General Medical Sciences","keywords":"Medicine; Propensity score matching; Logistic regression; Covariate; Psychiatry; Computer science; Internal medicine; Machine learning","score_opus":0.32409114746289336,"score_gpt":0.6173604092247256,"score_spread":0.2932692617618322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323287872","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":[0.9632231,0.00009332163,0.022426335,0.011340858,0.00042007683,0.0018090154,0.000079114456,0.0001333087,0.00047485178],"genre_scores_gemma":[0.9979517,0.00078540103,0.00044177548,0.0004540382,0.0001479449,0.00003152562,0.0000050331805,0.000046520832,0.00013606228],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894528,0.00259703,0.0010801946,0.0004874577,0.0054710894,0.00091147405],"domain_scores_gemma":[0.97472256,0.022118982,0.00079805736,0.0009136735,0.0007330103,0.0007137321],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.020360272,0.00023085371,0.0010173743,0.0010588828,0.00016120939,0.000035169036,0.0020176666,0.00015900329,0.00022964858],"category_scores_gemma":[0.123688616,0.0001629534,0.0001329542,0.0009863565,0.00020543954,0.00033455956,0.0009041011,0.0040953634,0.000042432912],"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":[0.016660461,0.046549346,0.17029078,0.0030930606,0.0047630174,0.0090115145,0.039077528,0.000016465945,0.0034964515,0.0395094,0.56762064,0.0999113],"study_design_scores_gemma":[0.016908752,0.08299023,0.18210828,0.010097195,0.00015850957,0.00018133468,0.035194773,0.0017872652,0.014540255,0.6424463,0.012573161,0.0010139688],"about_ca_topic_score_codex":0.0001446961,"about_ca_topic_score_gemma":0.00027557692,"teacher_disagreement_score":0.60293686,"about_ca_system_score_codex":0.001463442,"about_ca_system_score_gemma":0.0017132759,"threshold_uncertainty_score":0.9982022},"labels":[],"label_agreement":null},{"id":"W4323665219","doi":"10.1016/j.jclinepi.2023.03.003","title":"GRADE guidance 36: updates to GRADE's approach to addressing inconsistency","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":120,"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; Ted Rogers Centre for Heart Research; University Health Network; Impact","funders":"","keywords":"Computer science; Econometrics; Medicine; Mathematics","score_opus":0.7598412327577936,"score_gpt":0.6218911550729193,"score_spread":0.13795007768487433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323665219","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":[0.24621582,0.00031244295,0.70578927,0.03900415,0.0018926935,0.0007854442,0.000019875224,0.00057667337,0.005403621],"genre_scores_gemma":[0.28552106,0.00019083876,0.70623565,0.0067866547,0.00095251796,0.000029324905,0.0000026161144,0.000047764494,0.00023356342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98962855,0.0030716353,0.005776434,0.00047444814,0.00032582623,0.000723128],"domain_scores_gemma":[0.95318335,0.042658914,0.002474736,0.00060751,0.00038945826,0.00068604207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028033398,0.00028827135,0.0028610528,0.00035904528,0.000093121496,0.000015867108,0.0008517808,0.00043511376,0.000026132067],"category_scores_gemma":[0.24412997,0.00021718137,0.0006078691,0.0006925738,0.00023216182,0.00019632194,0.00034495338,0.0012514365,0.00011199568],"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":[0.000534807,0.0009336864,0.051003262,0.00026081427,0.00030622716,0.00015386267,0.00048997975,0.0013587098,0.00081049453,0.5060378,0.4100358,0.028074607],"study_design_scores_gemma":[0.0003960267,0.00079451356,0.032174416,0.00036618594,0.000057920948,0.00012766951,0.00016017043,0.0005387215,0.00023329355,0.95408887,0.010770226,0.00029200295],"about_ca_topic_score_codex":0.000008006424,"about_ca_topic_score_gemma":0.000006438574,"teacher_disagreement_score":0.4480511,"about_ca_system_score_codex":0.000071642244,"about_ca_system_score_gemma":0.0001585171,"threshold_uncertainty_score":0.97158724},"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":"W4327973727","doi":"10.3390/a16030166","title":"Framework for Evaluating Potential Causes of Health Risk Factors Using Average Treatment Effect and Uplift Modelling","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Advanced Causal Inference Techniques","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":"Humber Polytechnic; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Causation; Counterfactual thinking; Logistic regression; Statistics; Computer science; Econometrics; Psychology; Machine learning; Mathematics; Social psychology","score_opus":0.313532333990839,"score_gpt":0.4935268919504549,"score_spread":0.1799945579596159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327973727","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":[0.45068362,0.00007739066,0.5484359,0.0000083482455,0.000058393543,0.00052405446,0.000055145814,0.00015562821,0.0000014880338],"genre_scores_gemma":[0.49049914,0.00017984309,0.5091659,0.000003981478,0.00003963889,0.000047018475,0.000015550177,0.000037961156,0.000010988592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986392,0.00014705688,0.0004008623,0.00027409807,0.00020725344,0.00033151408],"domain_scores_gemma":[0.99733204,0.0019400176,0.00035991776,0.00023864547,0.000066140885,0.00006324011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084919936,0.00022059989,0.000506242,0.00011654147,0.00022000079,0.000021560152,0.0000712223,0.00010645251,0.000006064242],"category_scores_gemma":[0.00047866744,0.00017370496,0.00010250439,0.00017709077,0.000043859076,0.00009598125,0.00004936612,0.000119193035,7.8682757e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023188267,0.0005888726,0.007837027,0.0030091277,0.0013508943,0.000035795736,0.020594208,0.47769275,0.0068090586,0.031977326,0.00008197483,0.4497911],"study_design_scores_gemma":[0.00030127505,0.00089683424,0.000043235395,0.00017684004,0.00010816475,0.0000025603024,0.0001679184,0.6860107,0.010793476,0.3013477,0.0000039069982,0.00014738993],"about_ca_topic_score_codex":0.00040508836,"about_ca_topic_score_gemma":0.0000035677554,"teacher_disagreement_score":0.4496437,"about_ca_system_score_codex":0.000123002,"about_ca_system_score_gemma":0.000053433512,"threshold_uncertainty_score":0.7083483},"labels":[],"label_agreement":null},{"id":"W4328050658","doi":"10.1093/jrsssb/qkad008","title":"Causal inference on distribution functions","year":2023,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Advanced Causal Inference Techniques","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 Toronto","funders":"","keywords":"Causal inference; Euclidean space; Inference; Estimator; Space (punctuation); Contrast (vision); National Health and Nutrition Examination Survey; Econometrics; Computer science; Distribution (mathematics); Mathematics; Artificial intelligence; Statistics; Medicine; Pure mathematics","score_opus":0.2592960580704786,"score_gpt":0.46122099857806853,"score_spread":0.2019249405075899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328050658","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":[0.004328345,0.000011605737,0.99071735,0.0020512794,0.0008959421,0.0002348429,0.0012183527,0.0001959701,0.00034631428],"genre_scores_gemma":[0.10701735,0.00005083899,0.8905619,0.00043252532,0.00038937517,0.000034796136,0.00007278821,0.000057494224,0.0013829431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959676,0.0013215925,0.0010313176,0.0003081799,0.0007521103,0.0006191888],"domain_scores_gemma":[0.9746665,0.02370462,0.0005485118,0.00039093223,0.00041712192,0.00027234876],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028502562,0.00032862392,0.00073873845,0.000043992608,0.00042484875,0.00006312469,0.00050886656,0.00028756872,0.0005009495],"category_scores_gemma":[0.045813866,0.0002149326,0.0003008694,0.0005487316,0.0010213159,0.00014136353,0.00026047585,0.0013170431,0.00006741592],"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":[0.00023955716,0.00011734421,0.00024633924,0.00007309655,0.000137367,0.0000457373,0.00015865506,0.00026740873,0.00020125524,0.83419085,0.15795302,0.0063693477],"study_design_scores_gemma":[0.00036265532,0.0009791646,0.01045009,0.000088601584,0.0002244188,0.000053811553,0.00038711767,0.0019336814,0.0005786441,0.97707415,0.0075909067,0.00027675612],"about_ca_topic_score_codex":0.000017815322,"about_ca_topic_score_gemma":0.0000093079825,"teacher_disagreement_score":0.1503621,"about_ca_system_score_codex":0.00028514717,"about_ca_system_score_gemma":0.00017375704,"threshold_uncertainty_score":0.96222365},"labels":[],"label_agreement":null},{"id":"W4360868772","doi":"10.31235/osf.io/kwscz","title":"Causal Mediation in Panel Data – Estimation Based on Difference in Differences","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"Western University","funders":"","keywords":"Mediation; Exploit; Panel data; Mediator; Econometrics; Causal inference; Estimation; Treatment effect; Difference in differences; Computer science; Estimator; Psychology; Economics; Statistics; Mathematics; Medicine; Political science; Computer security","score_opus":0.4632158906435771,"score_gpt":0.4587096673121481,"score_spread":0.004506223331429027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360868772","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":[0.24146794,0.000015554413,0.7507162,0.0013266605,0.0005834216,0.0021785528,0.00039858135,0.0018460852,0.0014670036],"genre_scores_gemma":[0.90789634,0.00006429823,0.089966126,0.000076544384,0.000051222687,0.00040781737,0.0012437812,0.00006190875,0.00023195423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967603,0.0002483904,0.0009037058,0.0010390814,0.00065405184,0.0003944715],"domain_scores_gemma":[0.99482286,0.002692394,0.00040332496,0.001946573,0.00006588717,0.00006893489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010394938,0.00046824623,0.00070860813,0.0007604068,0.000028711293,0.00008673414,0.0012446704,0.00053933036,0.00008385496],"category_scores_gemma":[0.0041829287,0.0004141891,0.000041440057,0.00038180486,0.000072359835,0.00018895094,0.0011579359,0.0011281953,0.000035704354],"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":[0.00069147925,0.006006769,0.3520174,0.009437386,0.00017035339,0.0006237356,0.005550719,0.06344681,0.0017771091,0.37275624,0.009083779,0.17843819],"study_design_scores_gemma":[0.00018850915,0.00004107758,0.05507651,0.0007369091,0.00000912122,2.2411082e-7,0.00004256598,0.47085232,0.00019307638,0.47255304,0.000001471146,0.0003051748],"about_ca_topic_score_codex":0.0007628793,"about_ca_topic_score_gemma":0.005609671,"teacher_disagreement_score":0.6664284,"about_ca_system_score_codex":0.00033685437,"about_ca_system_score_gemma":0.00023309565,"threshold_uncertainty_score":0.999831},"labels":[],"label_agreement":null},{"id":"W4361194307","doi":"10.48550/arxiv.2303.15281","title":"Bayesian inference for optimal dynamic treatment regimes in practice","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bayesian probability; Computer science; Inference; Bayesian inference; Machine learning; Estimator; Population; Artificial intelligence; Mathematics; Statistics; Medicine","score_opus":0.26532153320503576,"score_gpt":0.35121575966666563,"score_spread":0.08589422646162986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361194307","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":[0.04522544,0.000027568838,0.9495187,0.00023033013,0.00018220507,0.0016379126,0.00010536124,0.000943085,0.0021294323],"genre_scores_gemma":[0.9058679,0.00077031367,0.086089194,0.000026488735,0.000033248885,0.000047409816,0.00006741905,0.00008684771,0.007011202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99795026,0.00014641088,0.00034623666,0.0010050829,0.00008218932,0.0004698267],"domain_scores_gemma":[0.99582106,0.002356495,0.00046382277,0.0010315715,0.00021275086,0.000114317605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034350727,0.00046647948,0.00059549976,0.00053959433,0.00008297307,0.00004958233,0.00058857136,0.00045478312,0.000018408164],"category_scores_gemma":[0.0012523301,0.00051865197,0.0002168241,0.00049869914,0.0001166645,0.00034606195,0.00055551436,0.0005011865,0.000029090816],"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":[0.00041821256,0.0006488711,0.0007756576,0.0004349505,0.0003446683,0.0008063384,0.00089974055,0.09296885,0.000052341627,0.9009951,0.000359435,0.0012958796],"study_design_scores_gemma":[0.00071426947,0.00032023212,0.000064350235,0.0003722507,0.00030747484,0.000004135851,0.0007749437,0.17099771,0.00024510548,0.8248562,0.00071977713,0.00062352774],"about_ca_topic_score_codex":0.00023503367,"about_ca_topic_score_gemma":0.00049535185,"teacher_disagreement_score":0.8634295,"about_ca_system_score_codex":0.0011789126,"about_ca_system_score_gemma":0.0003024857,"threshold_uncertainty_score":0.99972653},"labels":[],"label_agreement":null},{"id":"W4361290027","doi":"10.1002/ece3.9947","title":"Reducing bias in experimental ecology through directed acyclic graphs","year":2023,"lang":"en","type":"review","venue":"Ecology and Evolution","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Causal inference; Directed acyclic graph; Computer science; Causal model; Set (abstract data type); Inference; Observational study; Process (computing); Data science; Ecology; Causal structure; Confounding; Artificial intelligence; Econometrics; Algorithm; Mathematics; Biology","score_opus":0.2738438791699867,"score_gpt":0.4631142801097817,"score_spread":0.18927040093979497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361290027","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":[0.007404433,0.9886248,0.00015462113,0.000028304854,0.00063719344,0.0013179223,0.000013663254,0.0010371105,0.0007819457],"genre_scores_gemma":[0.003207011,0.9910246,0.004499324,0.000015652235,0.000069421214,0.00076563144,0.000060865103,0.00006464506,0.0002928179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977786,0.0004895044,0.0007090192,0.0005115739,0.00007514262,0.00043619052],"domain_scores_gemma":[0.99792504,0.0013291527,0.00039795027,0.0002787541,0.000027303255,0.000041794552],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046386453,0.00035402662,0.0013591067,0.00038306668,0.00012608568,0.000009854133,0.00016556286,0.00087588356,0.000062813226],"category_scores_gemma":[0.0008853028,0.00032869665,0.0001434081,0.000502916,0.00020194745,0.00016011634,0.00018051022,0.00058182934,0.00006756914],"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":[0.00009849949,0.0018786944,0.0030752714,0.030838098,0.0010527866,0.00046170433,0.0035438223,0.0000069330226,0.00017277715,0.79532254,0.022820024,0.14072886],"study_design_scores_gemma":[0.0004993763,0.0005109011,0.0022061148,0.006028151,0.00043310208,0.00021201803,0.0002653621,0.00004566777,0.000054432312,0.921635,0.06709448,0.0010153928],"about_ca_topic_score_codex":0.000061648876,"about_ca_topic_score_gemma":0.00052608986,"teacher_disagreement_score":0.13971347,"about_ca_system_score_codex":0.0005474492,"about_ca_system_score_gemma":0.00012361631,"threshold_uncertainty_score":0.9999165},"labels":[],"label_agreement":null},{"id":"W4362601896","doi":"10.1002/bimj.202100359","title":"Monte Carlo sensitivity analysis for unmeasured confounding in dynamic treatment regimes","year":2023,"lang":"en","type":"article","venue":"Biometrical Journal","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":"McGill University","funders":"National Institute of Mental Health","keywords":"Observational study; Monte Carlo method; Confounding; Sensitivity (control systems); Econometrics; Computer science; Sample size determination; Statistics; Probabilistic logic; Mathematics; Artificial intelligence; Engineering","score_opus":0.34084260410379097,"score_gpt":0.48306422044279523,"score_spread":0.14222161633900426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362601896","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":[0.6518376,0.00014698057,0.34649405,0.0004418931,0.0001504732,0.00043140928,0.00004686754,0.00033125022,0.000119485936],"genre_scores_gemma":[0.970368,0.00018939005,0.028887363,0.000013994306,0.000056939476,0.000030470064,0.0000047524413,0.000023342258,0.0004257414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983439,0.00016349395,0.0004662648,0.0002385265,0.00035842397,0.00042940176],"domain_scores_gemma":[0.9971422,0.0020842978,0.00023232859,0.00021769787,0.00016923701,0.00015427258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014204831,0.00018646703,0.00055816915,0.004264925,0.00012000332,0.00008281567,0.00011110515,0.0001229987,0.000010570004],"category_scores_gemma":[0.0025845778,0.00014894425,0.00033970666,0.008500045,0.00004857633,0.00013980757,0.000036023375,0.00017804724,0.0000068818936],"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":[0.0016838082,0.0044976017,0.23710638,0.00046650053,0.014322988,0.00570076,0.004969385,0.010005192,0.08084923,0.03574412,0.009333181,0.5953209],"study_design_scores_gemma":[0.008888107,0.0036174196,0.17774571,0.0004302177,0.0039616446,0.00066545984,0.002723431,0.41632402,0.015815351,0.3604623,0.006560356,0.0028060037],"about_ca_topic_score_codex":0.00004251586,"about_ca_topic_score_gemma":0.000104541024,"teacher_disagreement_score":0.5925149,"about_ca_system_score_codex":0.00096886803,"about_ca_system_score_gemma":0.000062538624,"threshold_uncertainty_score":0.607377},"labels":[],"label_agreement":null},{"id":"W4365459023","doi":"10.1002/sim.9727","title":"Causal inference with longitudinal data subject to irregular assessment times","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"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":"Causal inference; Inference; Subject (documents); Computer science; Longitudinal data; Statistics; Econometrics; Statistical inference; Artificial intelligence; Mathematics; Data mining","score_opus":0.21944373833936742,"score_gpt":0.5103172274469393,"score_spread":0.2908734891075719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365459023","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":[0.007964053,0.000017261395,0.9871262,0.0009890166,0.00013089908,0.00055342045,0.00040786868,0.00041024297,0.0024010595],"genre_scores_gemma":[0.2825489,0.00007546084,0.7156751,0.00014011524,0.0001280189,0.00008526386,0.0005586088,0.000053637537,0.00073488214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781847,0.00008671858,0.0004598812,0.00050579297,0.00069065875,0.00043849493],"domain_scores_gemma":[0.99636483,0.0020560657,0.00012611844,0.0011377676,0.00016812197,0.00014708428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012515098,0.00024757706,0.00048181694,0.0003226321,0.00006120579,0.000019159732,0.0006077879,0.0000620002,0.00034288492],"category_scores_gemma":[0.0033921173,0.0001868515,0.00000698036,0.00088257424,0.00023447293,0.00013471159,0.00038941728,0.00034686556,0.000044221953],"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":[0.000065800974,0.00010630785,0.020619689,0.00027084697,0.00006483983,0.00095486594,0.00081334414,0.00009351039,0.0006855448,0.83184767,0.13524978,0.009227788],"study_design_scores_gemma":[0.00095668295,0.0013135264,0.04186775,0.0010255427,0.00010628761,0.000026769465,0.00067718996,0.007455991,0.0002921595,0.9436412,0.002102355,0.00053454726],"about_ca_topic_score_codex":0.00015129712,"about_ca_topic_score_gemma":0.0008660852,"teacher_disagreement_score":0.27458486,"about_ca_system_score_codex":0.00012680989,"about_ca_system_score_gemma":0.0001667354,"threshold_uncertainty_score":0.7619583},"labels":[],"label_agreement":null},{"id":"W4366238420","doi":"10.1007/s12325-023-02503-3","title":"The Role of Expert Opinion in Projecting Long-Term Survival Outcomes Beyond the Horizon of a Clinical Trial","year":2023,"lang":"en","type":"article","venue":"Advances in Therapy","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":"University of Manitoba","funders":"Defense Acquisition Program Administration; AstraZeneca","keywords":"Frequentist inference; Medicine; Bayesian probability; Expert opinion; Population; Survival analysis; Placebo; Relative survival; Statistics; Bayesian inference; Internal medicine; Intensive care medicine; Mathematics","score_opus":0.26403437545403435,"score_gpt":0.5460801964420338,"score_spread":0.2820458209879994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366238420","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":[0.9914762,0.0042328243,0.00062835147,0.00021635336,0.0010853141,0.0013698587,0.000004388094,0.0001210756,0.000865668],"genre_scores_gemma":[0.96181494,0.035109263,0.0024526957,0.000019249617,0.00020481915,0.00032247047,0.0000033443673,0.000037024314,0.000036214515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976445,0.00042642225,0.0011115688,0.00022682721,0.00032239468,0.00026829],"domain_scores_gemma":[0.9926291,0.006250185,0.0005348773,0.0005036615,0.00006392602,0.000018258823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028118445,0.00016306766,0.00054162095,0.000096872005,0.00005751079,0.000011206982,0.00050771015,0.00010112342,0.000005945339],"category_scores_gemma":[0.001523773,0.00008901344,0.00013972234,0.0004904004,0.00024411661,0.0002294949,0.00009206429,0.0003054278,9.637566e-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":[0.00456308,0.00035048855,0.15939347,0.000033639564,0.00004008353,0.0000018805747,0.0021969096,0.000015744905,0.0006987372,0.04445181,0.000016480555,0.7882377],"study_design_scores_gemma":[0.013701414,0.0024230296,0.019369846,0.00025708257,0.0000044019853,0.0000012665662,0.0037152532,0.00013605425,0.014301883,0.9422119,0.003553654,0.00032419863],"about_ca_topic_score_codex":0.00003721166,"about_ca_topic_score_gemma":0.00029068036,"teacher_disagreement_score":0.8977601,"about_ca_system_score_codex":0.0000301324,"about_ca_system_score_gemma":0.00005378394,"threshold_uncertainty_score":0.36298627},"labels":[],"label_agreement":null},{"id":"W4366590256","doi":"10.1186/s12874-023-01922-8","title":"Data source profile reporting by studies that use routinely collected health data to explore the effects of drug treatment","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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; St. Joseph’s Healthcare Hamilton; Impact","funders":"West China Hospital, Sichuan University; National Key Research and Development Program of China; Sichuan University; National Natural Science Foundation of China","keywords":"Medicine; Credibility; Observational study; MEDLINE; Data source; Database; Record linkage; Family medicine; Internal medicine; Computer science; Environmental health; Population","score_opus":0.987954653323306,"score_gpt":0.7701015603537543,"score_spread":0.2178530929695517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366590256","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":[0.00003919493,0.86389923,0.12598114,0.0007651169,0.00026255436,0.0078746155,0.0007316702,0.0004309041,0.000015595024],"genre_scores_gemma":[3.2814157e-7,0.74172705,0.25153825,0.000058050442,0.0001669782,0.0020235034,0.0011958019,0.000140149,0.003149898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92147934,0.06524752,0.0050245314,0.0025217899,0.0037508141,0.001976012],"domain_scores_gemma":[0.28923878,0.6931995,0.0049479464,0.010868008,0.0007632508,0.0009825149],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.10371807,0.0006533454,0.005928603,0.00051760394,0.00038432633,0.000050832277,0.005395372,0.00052940677,0.00005174378],"category_scores_gemma":[0.8575815,0.00035803256,0.00022815866,0.0019340472,0.0010546399,0.0001674651,0.01143648,0.0019926853,0.000028299064],"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":false,"study_design_scores_codex":[0.00004032986,0.00017756794,0.000007921044,0.055917148,0.00071154936,0.000101683276,0.0014313287,4.496787e-8,0.00000386026,0.0004804738,0.33340853,0.60771954],"study_design_scores_gemma":[0.00035822706,0.00097082404,0.0000026085438,0.044293232,0.0005103992,0.000106493346,0.0028340386,0.000096293144,0.00007904817,0.0069954908,0.943315,0.0004383237],"about_ca_topic_score_codex":0.0009468112,"about_ca_topic_score_gemma":0.0020636066,"teacher_disagreement_score":0.7538634,"about_ca_system_score_codex":0.00067641714,"about_ca_system_score_gemma":0.0063806,"threshold_uncertainty_score":0.99998593},"labels":[],"label_agreement":null},{"id":"W4366992020","doi":"10.1001/jama.2023.4221","title":"Emulation of Randomized Clinical Trials With Nonrandomized Database Analyses","year":2023,"lang":"en","type":"article","venue":"JAMA","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":379,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute on Aging; National Heart, Lung, and Blood Institute; U.S. Food and Drug Administration","keywords":"Medicine; Emulation; Randomized controlled trial; Clinical trial; MEDLINE; Database; Internal medicine","score_opus":0.5650319051167182,"score_gpt":0.5950935289172615,"score_spread":0.030061623800543336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366992020","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":[0.18796499,0.000057524096,0.8069181,0.0003679145,0.00010018422,0.0022498867,0.000050716902,0.0007237386,0.0015669734],"genre_scores_gemma":[0.8491168,0.0002251393,0.1497254,0.0000609737,0.0001818837,0.00021860159,0.00010822112,0.000035525656,0.00032747097],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9941141,0.0033035353,0.0018368062,0.00023096333,0.000347329,0.00016729215],"domain_scores_gemma":[0.9553498,0.042759806,0.0010853962,0.00047425515,0.0002676274,0.000063095686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026003076,0.00015257062,0.0023804344,0.00019702385,0.000030858835,0.000023631146,0.0001499205,0.00011840148,0.00014101353],"category_scores_gemma":[0.09353598,0.000092652284,0.00042871007,0.00044202845,0.00017240552,0.00022782438,0.000060460174,0.00017324339,0.000020880345],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7526855,0.00070324494,0.000595504,0.00042869098,0.002199129,0.00006386151,0.0007847962,0.00020464018,0.026994787,0.16028799,0.017726365,0.037325505],"study_design_scores_gemma":[0.6489458,0.0001805039,0.000124522,0.00036785565,0.0011875661,0.00000295601,0.00013735068,0.014892551,0.040301904,0.29336613,0.0001918868,0.00030095663],"about_ca_topic_score_codex":0.000020950476,"about_ca_topic_score_gemma":0.00000961412,"teacher_disagreement_score":0.66115177,"about_ca_system_score_codex":0.000012872974,"about_ca_system_score_gemma":0.000053179083,"threshold_uncertainty_score":0.9140996},"labels":[],"label_agreement":null},{"id":"W4367338397","doi":"10.51387/23-nejsds29","title":"General Additive Network Effect Models","year":2023,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Advanced Causal Inference Techniques","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":"Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Inference; Specification; Outcome (game theory); Computer science; Network model; Range (aeronautics); Power (physics); Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Engineering; Machine learning; Mathematical economics","score_opus":0.17173287554959368,"score_gpt":0.4322849311017763,"score_spread":0.26055205555218264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367338397","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":[0.023337152,0.00006107896,0.97429305,0.00028908777,0.00048592492,0.00021623576,0.0005358536,0.0000567961,0.000724815],"genre_scores_gemma":[0.2876923,0.0010955319,0.70953107,0.00010448397,0.0012131982,0.000004571833,0.000047618847,0.0000293651,0.00028185133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982593,0.0001448198,0.000421083,0.000180053,0.00063227816,0.00036247342],"domain_scores_gemma":[0.99528867,0.0035172934,0.00031819468,0.00060772063,0.00015804933,0.00011006379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062042046,0.00011705273,0.00024826164,0.00015145767,0.00014223538,0.000075858006,0.0018674387,0.00002996628,0.00001972389],"category_scores_gemma":[0.0043305703,0.00007059722,0.000015333353,0.0009450638,0.0003526121,0.0008404232,0.00056059007,0.00038571542,0.0000061102437],"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":[0.00013440591,0.00003061109,0.0001899664,0.00002786069,0.00002440448,0.00025313685,0.001167795,0.011916532,0.00060052815,0.6253851,0.25301734,0.10725232],"study_design_scores_gemma":[0.0006069391,0.00015804952,0.00026867606,0.00009809628,0.000019306177,0.00007063788,0.000033627977,0.057195332,0.00033317204,0.93952006,0.0016019687,0.00009414224],"about_ca_topic_score_codex":0.000017050816,"about_ca_topic_score_gemma":0.000059369693,"teacher_disagreement_score":0.31413496,"about_ca_system_score_codex":0.00006424007,"about_ca_system_score_gemma":0.00028873378,"threshold_uncertainty_score":0.518441},"labels":[],"label_agreement":null},{"id":"W4372185084","doi":"10.1002/pds.5635","title":"A review of the use of propensity score methods with multiple treatment groups in the general internal medicine literature","year":2023,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Toronto Western Hospital; North York General Hospital; Sunnybrook Health Science Centre; NOSM University; Health Sciences Centre; University Health Network; Health Sciences North; University of Toronto","funders":"","keywords":"Propensity score matching; Medicine; Confounding; Inverse probability weighting; MEDLINE; Covariate; Pairwise comparison; Weighting; Statistics; Internal medicine; Mathematics","score_opus":0.5643266496882013,"score_gpt":0.5568337737406952,"score_spread":0.007492875947506139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372185084","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":[0.00003438757,0.99191034,0.004416042,0.0007430227,0.00009387092,0.0026038361,0.00011272712,0.00004072154,0.00004507991],"genre_scores_gemma":[0.000008767381,0.97351533,0.024978526,0.00090341107,0.00008730186,0.00029680438,0.000054062722,0.0000331781,0.00012260585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98860604,0.009027737,0.0015659527,0.0004088136,0.00013146181,0.00026002832],"domain_scores_gemma":[0.97919005,0.018555632,0.0014414869,0.00064315385,0.000121969046,0.000047711463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070537142,0.0004814804,0.0033574654,0.0001050799,0.000059825303,0.0000030735328,0.00048333884,0.0001897541,0.0000146866305],"category_scores_gemma":[0.006260585,0.00017506683,0.0003116059,0.0005461986,0.00054134,0.00008641042,0.00021721047,0.0008513647,4.2256735e-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":[0.00021223095,0.00022092847,0.0013818174,0.20290792,0.0007908706,0.000041549174,0.0014239165,0.0000036220458,0.000010082108,0.015060565,0.012912592,0.7650339],"study_design_scores_gemma":[0.0005805929,0.00019182835,0.00015593295,0.31209326,0.002129961,0.0002370084,0.000014431855,0.000071828195,0.000024767902,0.01058355,0.6736184,0.00029848196],"about_ca_topic_score_codex":0.00020573854,"about_ca_topic_score_gemma":0.000100999634,"teacher_disagreement_score":0.7647354,"about_ca_system_score_codex":0.00008205611,"about_ca_system_score_gemma":0.00009287438,"threshold_uncertainty_score":0.7494957},"labels":[],"label_agreement":null},{"id":"W4375951527","doi":"10.1093/infdis/jiad144","title":"Causal Inference and Confounding: A Primer for Interpreting and Conducting Infectious Disease Research","year":2023,"lang":"en","type":"article","venue":"The Journal of Infectious Diseases","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"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; Canadian Institutes of Health Research","keywords":"Causal inference; Confounding; Inference; Infectious disease (medical specialty); Primer (cosmetics); Medicine; Disease; Biology; Computational biology; Virology; Computer science; Internal medicine; Artificial intelligence; Pathology; Chemistry","score_opus":0.2707588557568666,"score_gpt":0.498521321367356,"score_spread":0.2277624656104894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375951527","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":[0.9870232,0.00046836914,0.011031145,0.0003023104,0.00016367446,0.000549937,0.0000142977015,0.00023292957,0.00021415633],"genre_scores_gemma":[0.9987517,0.00049230654,0.00036084047,0.00006370925,0.00018282875,0.000046261113,0.0000013745674,0.00003950995,0.000061482584],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99820167,0.0003872251,0.00049578666,0.00017049682,0.00035432895,0.00039051165],"domain_scores_gemma":[0.9889445,0.009465739,0.00041231062,0.00022667056,0.00067986094,0.00027096085],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024914318,0.0001920828,0.00033783997,0.00038953786,0.00050402456,0.00013878962,0.00017939306,0.000057819332,0.00001150485],"category_scores_gemma":[0.018059343,0.00013489553,0.00007720172,0.0004006862,0.0004678801,0.00038987966,0.00023465029,0.00045767764,0.000001997463],"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":[0.001867661,0.0007825555,0.65279967,0.0026696257,0.0009952814,0.00019358032,0.01331495,0.00026860996,0.024129374,0.26393887,0.010555502,0.028484331],"study_design_scores_gemma":[0.0010296524,0.00090398017,0.007594989,0.00074993836,0.00033577287,0.00023130453,0.0016891602,0.0007311805,0.0011670698,0.98498976,0.00027278037,0.00030439676],"about_ca_topic_score_codex":0.000027534365,"about_ca_topic_score_gemma":0.000014324643,"teacher_disagreement_score":0.7210509,"about_ca_system_score_codex":0.000100235986,"about_ca_system_score_gemma":0.00018318111,"threshold_uncertainty_score":0.99021196},"labels":[],"label_agreement":null},{"id":"W4376271032","doi":"10.1093/jrsssc/qlad034","title":"The impact of directly observed therapy on the efficacy of Tuberculosis treatment: a Bayesian multilevel approach","year":2023,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Propensity score matching; Covariate; Confounding; Multilevel model; Econometrics; Bayesian probability; Random effects model; Causal inference; Outcome (game theory); Statistics; Psychology; Mathematics; Medicine; Meta-analysis; Internal medicine","score_opus":0.12054633364644328,"score_gpt":0.3744787153095136,"score_spread":0.2539323816630703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376271032","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":[0.1436489,0.00015655886,0.8454525,0.00097017194,0.000287092,0.0025834008,0.0047182604,0.00018876849,0.001994347],"genre_scores_gemma":[0.8612799,0.00051344413,0.13759147,0.000041555646,0.0000992346,0.00007038521,0.000019000108,0.000080462036,0.00030452624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969166,0.00032998706,0.0011818593,0.00023465556,0.0008384194,0.0004984957],"domain_scores_gemma":[0.98483515,0.012832271,0.001191689,0.00066149625,0.0003434184,0.00013598887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011197755,0.0004196498,0.00082554,0.00003360425,0.0004796464,0.00006923752,0.0008092837,0.00014592917,0.0000901744],"category_scores_gemma":[0.0020318397,0.00017812726,0.00062674575,0.00039999504,0.0009465011,0.000055098728,0.0001326625,0.0005409496,0.0000029657688],"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":[0.0022628617,0.0016427671,0.00037384193,0.00018066476,0.0029412191,0.000009576572,0.006251447,0.004151278,0.0033588964,0.886428,0.048637405,0.04376202],"study_design_scores_gemma":[0.0030215206,0.0034184228,0.042895053,0.0001957737,0.00051186635,0.000015614782,0.002335023,0.032072388,0.011725878,0.902662,0.00053897896,0.0006074836],"about_ca_topic_score_codex":0.00010581248,"about_ca_topic_score_gemma":0.000009359731,"teacher_disagreement_score":0.71763104,"about_ca_system_score_codex":0.0003028813,"about_ca_system_score_gemma":0.00021267871,"threshold_uncertainty_score":0.72638184},"labels":[],"label_agreement":null},{"id":"W4376470507","doi":"10.51744/cip8","title":"Using data differently and using different data","year":2018,"lang":"en","type":"report","venue":"","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":"Impact","funders":"","keywords":"Identification (biology); Relevance (law); Computer science; Machine learning; Randomized experiment; Data mining; Data science; Risk analysis (engineering); Artificial intelligence; Mathematics; Statistics","score_opus":0.8815217562498705,"score_gpt":0.5958172277224624,"score_spread":0.28570452852740813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376470507","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":[0.033358693,0.0010251693,0.9366564,0.000034913784,0.0012501323,0.0015299007,0.0039771735,0.0012555476,0.020912083],"genre_scores_gemma":[0.023553971,0.0033879867,0.9596466,0.000069017835,0.0024748736,0.000014086286,0.005606601,0.0005251592,0.004721721],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99570376,0.00010585855,0.0009512562,0.0016021702,0.0010792464,0.0005576991],"domain_scores_gemma":[0.99013007,0.00047842745,0.00080010947,0.008040341,0.00036680207,0.00018427665],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00097008416,0.00076249166,0.00125418,0.00022173653,0.00017469004,0.00020026267,0.0025614528,0.00058372325,0.00043596243],"category_scores_gemma":[0.0020723168,0.000583243,0.00005039843,0.000119959695,0.00029348198,0.0006841792,0.010410825,0.0006212418,0.0000042605184],"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":[0.00017435841,0.002745795,0.0124598425,0.01932885,0.004769251,0.00052942213,0.0005930286,0.0000017048395,0.022380607,0.03714142,0.80851305,0.09136265],"study_design_scores_gemma":[0.0013601735,0.00042514587,0.000625146,0.011329722,0.006956412,0.0023348872,0.0004098663,0.15723568,0.005460186,0.6759896,0.12975112,0.008122036],"about_ca_topic_score_codex":0.00050491607,"about_ca_topic_score_gemma":0.00040426047,"teacher_disagreement_score":0.67876196,"about_ca_system_score_codex":0.00037847357,"about_ca_system_score_gemma":0.0005384832,"threshold_uncertainty_score":0.9996619},"labels":[],"label_agreement":null},{"id":"W4376637825","doi":"10.1515/ijb-2022-0073","title":"Bayesian inference for optimal dynamic treatment regimes in practice","year":2023,"lang":"en","type":"review","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Inference; Bayesian inference; Bayesian probability; Frequentist inference; Biostatistics; Econometrics; Estimator; Machine learning; Computer science; Artificial intelligence; Mathematics; Statistics; Medicine","score_opus":0.22417419034281136,"score_gpt":0.5431292370587046,"score_spread":0.31895504671589325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376637825","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017444507,0.41022655,0.5862666,0.0006756311,0.0008022691,0.0010078473,0.0007873179,0.00005895745,0.0001731272],"genre_scores_gemma":[0.000020334639,0.7893362,0.20991872,0.00003389114,0.0001736952,0.00006325346,0.00004406126,0.00006096463,0.00034887993],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974878,0.00018031223,0.0013939728,0.00018022532,0.00053541845,0.00022229455],"domain_scores_gemma":[0.98258305,0.0140299415,0.002298841,0.00026820294,0.0007634849,0.00005649651],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009862275,0.00034191035,0.0010396782,0.00041408846,0.000039727747,0.00010157255,0.0010345423,0.00016027532,0.000011403931],"category_scores_gemma":[0.008670338,0.00021249938,0.00030293787,0.00019165814,0.00009512311,0.00017752942,0.00011299426,0.00043622087,0.000010382513],"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":[0.000101521626,0.00022148252,5.034768e-7,0.001112301,0.0011158044,0.00038167374,0.00033929382,0.00003707124,9.670149e-7,0.13737918,0.0019989966,0.8573112],"study_design_scores_gemma":[0.00047999434,0.0006302794,4.6917654e-7,0.011685474,0.0013732146,0.0006652835,0.0002798653,0.00085759006,0.000009326241,0.2821943,0.7014732,0.00035101056],"about_ca_topic_score_codex":0.000016340453,"about_ca_topic_score_gemma":0.000045598317,"teacher_disagreement_score":0.8569602,"about_ca_system_score_codex":0.0009664516,"about_ca_system_score_gemma":0.0006871058,"threshold_uncertainty_score":0.99968004},"labels":[],"label_agreement":null},{"id":"W4376654146","doi":"10.48550/arxiv.2305.08651","title":"Methodological considerations for novel approaches to covariate-adjusted indirect treatment comparisons","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Econometrics; Robustness (evolution); Weighting; Outcome (game theory); Computer science; Extrapolation; Context (archaeology); Statistics; Mathematics; Medicine; Geography","score_opus":0.95394451213457,"score_gpt":0.4139994722693762,"score_spread":0.5399450398651937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376654146","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":[0.027393708,0.00000665598,0.966812,0.00039890446,0.00021476082,0.0025091972,0.0005059873,0.0014079467,0.0007508344],"genre_scores_gemma":[0.5556356,0.00002012003,0.44259492,0.00004767109,0.00005027923,0.000086491345,0.00008469607,0.00005288954,0.0014273818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99764806,0.00029492078,0.00040252705,0.0011218734,0.000080898804,0.0004516947],"domain_scores_gemma":[0.9921841,0.0061660707,0.00034233963,0.0009239307,0.00017185995,0.00021172519],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067267957,0.00050349813,0.0010176523,0.00036732844,0.00024298514,0.00006692928,0.00039410678,0.0005429059,0.00004919329],"category_scores_gemma":[0.002132224,0.0005025838,0.00033941382,0.0003865051,0.00013044485,0.00008660609,0.00064881175,0.00042087364,0.000037392845],"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":[0.000114427174,0.00047875216,0.0003167039,0.00012656608,0.00042845687,0.000045146644,0.00044092338,0.06436868,0.00020168528,0.93077207,0.0026269455,0.000079633195],"study_design_scores_gemma":[0.0007359972,0.0003253067,0.00032012834,0.000105328705,0.0005593886,0.000004773986,0.00040317568,0.03967979,0.002569078,0.9541942,0.00045397153,0.00064885605],"about_ca_topic_score_codex":0.00013855845,"about_ca_topic_score_gemma":0.00054594217,"teacher_disagreement_score":0.5282419,"about_ca_system_score_codex":0.00061614846,"about_ca_system_score_gemma":0.0002314017,"threshold_uncertainty_score":0.99974257},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4377093414","doi":"10.1177/17407745231174544","title":"Overview of modern approaches for identifying and evaluating heterogeneous treatment effects from clinical data","year":2023,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Computer science; Causal inference; Machine learning; Artificial intelligence; Set (abstract data type); Identification (biology); Usability; Observational study; Personalized medicine; Precision medicine; Statistical inference; Inference; Randomized experiment; Data science; Human–computer interaction; Bioinformatics; Medicine","score_opus":0.9791653892937205,"score_gpt":0.7317185737311261,"score_spread":0.2474468155625944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377093414","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":[0.84026533,0.0033869557,0.15031473,0.00013423582,0.00066382944,0.004059242,0.00064794556,0.0004943729,0.000033365235],"genre_scores_gemma":[0.6283558,0.005915212,0.36321798,0.00010402977,0.0012257888,0.0005574,0.00042135423,0.000114746195,0.000087664754],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925025,0.0028969743,0.0032432675,0.00082440174,0.00026297895,0.00026989545],"domain_scores_gemma":[0.8857547,0.11143921,0.0012350362,0.0013585521,0.00007453803,0.00013796466],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026801094,0.00023657084,0.0021194927,0.000053348835,0.00006400841,0.000040394778,0.0004297457,0.00029999344,0.000011992062],"category_scores_gemma":[0.099121146,0.00017807793,0.00045030037,0.00011543353,0.00016502444,0.00013586904,0.000505682,0.00016246758,0.000008536326],"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":[0.00030496926,0.00041918422,0.0012608977,0.00049133407,0.00061137666,0.000007088861,0.00011471585,0.000009897888,0.0005212237,0.00208563,0.0005461379,0.99362755],"study_design_scores_gemma":[0.0034492488,0.0012909105,0.0006766443,0.00048607407,0.0009293825,0.0000011899605,0.00002869578,0.044562414,0.0028108943,0.9453493,0.00018476027,0.00023049022],"about_ca_topic_score_codex":0.000008205415,"about_ca_topic_score_gemma":0.000011020905,"teacher_disagreement_score":0.99339706,"about_ca_system_score_codex":0.00002436064,"about_ca_system_score_gemma":0.00007679221,"threshold_uncertainty_score":0.9288778},"labels":[],"label_agreement":null},{"id":"W4377138740","doi":"10.1002/pds.5639","title":"Differences in target estimands between different propensity score‐based weights","year":2023,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Propensity score matching; Weighting; Statistic; Average treatment effect; Statistics; Mathematics; Matching (statistics); Observational study; Inverse probability weighting; Medicine","score_opus":0.2828403345970821,"score_gpt":0.43182025817402725,"score_spread":0.14897992357694517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377138740","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":[0.9566159,0.000108878055,0.038349938,0.002933607,0.0001404746,0.0005874093,0.00005023201,0.0007190207,0.00049450307],"genre_scores_gemma":[0.98985434,0.00030210466,0.008963675,0.0003963695,0.00011007582,0.00011030339,0.00007165218,0.000026964592,0.00016453434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996788,0.001124721,0.0007538416,0.0005628521,0.00014902964,0.00062152825],"domain_scores_gemma":[0.9912821,0.00797781,0.0002298882,0.00028284936,0.000047475536,0.00017987244],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026172178,0.0003600748,0.0010394485,0.0002538809,0.00019011709,0.0000098683995,0.0002752098,0.00017374591,0.0001037947],"category_scores_gemma":[0.0016132045,0.00026141477,0.000087325934,0.00031645803,0.00031819017,0.00015775519,0.00021480572,0.0006030415,0.000024035782],"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":[0.00013583936,0.000071727554,0.9782926,0.000121054356,0.00003382086,0.000023834438,0.00015260642,0.000008543445,0.00021425332,0.016570587,0.00213289,0.0022422632],"study_design_scores_gemma":[0.00077648216,0.000065102715,0.5491187,0.000120914345,0.000045474382,0.0000025363547,0.000015314883,0.0056026103,0.0045013623,0.4389878,0.000411293,0.0003524392],"about_ca_topic_score_codex":0.000050265557,"about_ca_topic_score_gemma":0.000054589207,"teacher_disagreement_score":0.42917392,"about_ca_system_score_codex":0.000063210464,"about_ca_system_score_gemma":0.00003895838,"threshold_uncertainty_score":0.9999838},"labels":[],"label_agreement":null},{"id":"W4378188995","doi":"10.1177/26320843231176662","title":"Implementing TMLE in the presence of a continuous outcome","year":2023,"lang":"en","type":"article","venue":"Research Methods in Medicine & Health Sciences","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Causal inference; Outcome (game theory); Inference; Machine learning; Observational study; Data mining; Artificial intelligence; Econometrics; Statistics; Mathematics","score_opus":0.8456818068301671,"score_gpt":0.7791294216930839,"score_spread":0.06655238513708328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378188995","genre_codex":"empirical","genre_gemma":"methods","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":[0.55563223,0.0031979682,0.27739498,0.12182384,0.00063151243,0.009586475,0.000015643172,0.000664302,0.03105306],"genre_scores_gemma":[0.3305875,0.00072329026,0.66771436,0.00037729004,0.00009093039,0.00031068182,0.0000011546033,0.0000152531275,0.00017952683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98814976,0.006416016,0.0013438561,0.00045738654,0.0020454305,0.0015875596],"domain_scores_gemma":[0.9712844,0.027686616,0.0002735843,0.00047546087,0.00018086513,0.00009908531],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21108794,0.00011849847,0.00056721177,0.0011664447,0.00031263294,0.000019749918,0.001293721,0.000050300492,0.000052613614],"category_scores_gemma":[0.04659854,0.00006928701,0.000029229725,0.0062737204,0.0016508577,0.0001668007,0.00038985696,0.00079455477,0.000002641904],"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":[0.000028647102,0.0001614607,0.15134208,0.0016952407,0.0000064074948,0.000057905454,0.048625167,0.000022675975,0.0052370923,0.5340094,0.010625565,0.24818835],"study_design_scores_gemma":[0.00033526475,0.0009524801,0.01194296,0.00089138106,0.0000016277302,0.0000066560683,0.05464555,0.0023516396,0.00089253916,0.9254088,0.002465398,0.00010569472],"about_ca_topic_score_codex":0.0023847239,"about_ca_topic_score_gemma":0.000819702,"teacher_disagreement_score":0.39139938,"about_ca_system_score_codex":0.00010678825,"about_ca_system_score_gemma":0.00037203424,"threshold_uncertainty_score":0.96143234},"labels":[],"label_agreement":null},{"id":"W4378549577","doi":"10.1016/j.jclinepi.2023.05.015","title":"Trials using composite outcomes neglect the presence of competing risks: a methodological survey of cardiovascular studies","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; University of Calgary; McMaster University; Impact","funders":"","keywords":"Medicine; CINAHL; Meta-analysis; Subgroup analysis; Sample size determination; Neglect; MEDLINE; Relative risk; Environmental health; Confidence interval; Statistics; Psychological intervention; Internal medicine; Psychiatry","score_opus":0.9869284378305098,"score_gpt":0.7807249804705765,"score_spread":0.20620345735993328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378549577","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005876123,0.88610166,0.1113277,0.00008975957,0.0008929943,0.0008928604,0.000061986335,0.000036714722,0.000008725299],"genre_scores_gemma":[0.000093219314,0.7989786,0.20052059,0.000042687385,0.00029479063,0.000014443243,0.000002823548,0.000047823723,0.000004963995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.71380305,0.25523207,0.02910696,0.00056711875,0.0007103996,0.0005804082],"domain_scores_gemma":[0.18383914,0.7792701,0.03418928,0.0010367634,0.0015287589,0.00013594289],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.44862053,0.0006214801,0.048079472,0.00030026858,0.000080424965,0.000006233596,0.0015380995,0.0011104636,0.00000897903],"category_scores_gemma":[0.9210906,0.00028938692,0.010166627,0.0006290395,0.0015539919,0.00007967788,0.00073781644,0.002910864,0.0000017116704],"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":[0.00059049984,0.0006349674,0.019402929,0.042093016,0.084893525,0.00014866733,0.00021563435,0.0024074574,0.0000042544702,0.010872821,0.0015595334,0.8371767],"study_design_scores_gemma":[0.0023915307,0.0035521674,0.010628914,0.11111177,0.05183417,0.0007326562,0.00038140133,0.0005636886,0.00001653795,0.7629546,0.05422373,0.0016088268],"about_ca_topic_score_codex":0.00018326445,"about_ca_topic_score_gemma":0.000014322133,"teacher_disagreement_score":0.8355679,"about_ca_system_score_codex":0.00008492104,"about_ca_system_score_gemma":0.000512671,"threshold_uncertainty_score":0.99995583},"labels":[],"label_agreement":null},{"id":"W4378803918","doi":"10.1002/pst.2317","title":"Variance estimation of the risk difference when using propensity‐score matching and weighting with time‐to‐event outcomes","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","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":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Ministry of Long-Term Care; Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences; Ministry of Health, Ontario","keywords":"Propensity score matching; Weighting; Statistics; Matching (statistics); Variance (accounting); Event (particle physics); Estimation; Mathematics; Event data; Econometrics; Inverse probability weighting; Medicine; Covariate; Economics","score_opus":0.20647756529539354,"score_gpt":0.4342598912393333,"score_spread":0.22778232594393974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378803918","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":[0.39376673,0.0000047890903,0.60544753,0.00010825791,0.000021586013,0.0003952169,0.00010509591,0.00011214373,0.00003863772],"genre_scores_gemma":[0.5689193,0.000010381729,0.4308075,0.00007427399,0.000010845843,0.000016736638,0.000003729001,0.000027476659,0.0001297804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862915,0.00013966489,0.00034965563,0.0002336919,0.00036583582,0.0002820148],"domain_scores_gemma":[0.9979639,0.0013422746,0.0002370396,0.0002430518,0.00010821153,0.00010549999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000424215,0.00018952253,0.00031415097,0.00004988058,0.00018185144,0.00003908291,0.00018520496,0.000042421485,0.000047543228],"category_scores_gemma":[0.0011886684,0.00011899287,0.000023159251,0.00023669343,0.00013965828,0.00008695851,0.00026311819,0.0002788819,0.00001472806],"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":[0.0004005523,0.00059639727,0.18265204,0.00275152,0.0005618711,0.000112611844,0.007443841,0.020821303,0.03736865,0.5265078,0.0012017895,0.21958163],"study_design_scores_gemma":[0.00031325838,0.00006799711,0.030880442,0.00035299093,0.00022240684,0.000013209314,0.000026242626,0.26984593,0.007336361,0.69062394,0.000042375465,0.00027485614],"about_ca_topic_score_codex":0.000029657334,"about_ca_topic_score_gemma":0.0000064824003,"teacher_disagreement_score":0.24902461,"about_ca_system_score_codex":0.0000597638,"about_ca_system_score_gemma":0.000038824346,"threshold_uncertainty_score":0.48523885},"labels":[],"label_agreement":null},{"id":"W4379598444","doi":"10.1093/aje/kwad133","title":"NO UNMEASURED CONFOUNDING: KNOWN UNKNOWNS OR… NOT?","year":2023,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; HEC Montréal","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Biostatistics; Confounding; Epidemiology; Medicine; Library science; Gerontology; History; Family medicine; Pathology","score_opus":0.3037576488440687,"score_gpt":0.4933054180363789,"score_spread":0.1895477691923102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379598444","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":[0.48353815,0.00027768943,0.48725674,0.010534994,0.0031096898,0.00074595615,0.000039707436,0.0015499436,0.012947116],"genre_scores_gemma":[0.7267638,0.0011151063,0.26610583,0.002416697,0.00086837116,0.000021176575,0.0000054820325,0.000095186166,0.00260838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99628836,0.0011679924,0.0014495866,0.00023822377,0.00021417973,0.00064163125],"domain_scores_gemma":[0.9804391,0.01642936,0.001960893,0.00040886088,0.0005070609,0.00025469248],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006255033,0.00024245976,0.001415351,0.0003589524,0.00007659089,0.0000073396664,0.00050505024,0.00011119039,0.00025688438],"category_scores_gemma":[0.05440521,0.00017000709,0.00023772668,0.0006874132,0.0007704994,0.00017793043,0.000097788754,0.0006070827,0.00020918722],"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":[0.0031851607,0.00033812938,0.020760782,0.0001647273,0.0010120376,0.00084105605,0.0011964809,0.00029334868,0.021537257,0.58447874,0.24877091,0.11742135],"study_design_scores_gemma":[0.0009972379,0.0062660137,0.0048024794,0.0004038287,0.00018882724,0.001218229,0.0010347107,0.00062455796,0.0019924673,0.7893661,0.19231473,0.0007907658],"about_ca_topic_score_codex":0.000036100515,"about_ca_topic_score_gemma":0.000014796372,"teacher_disagreement_score":0.24322562,"about_ca_system_score_codex":0.00015542943,"about_ca_system_score_gemma":0.00019755134,"threshold_uncertainty_score":0.95355994},"labels":[],"label_agreement":null},{"id":"W4379599462","doi":"10.1002/pds.5649","title":"Evaluating the use of methods to mitigate bias from non‐transient medications in the case‐crossover design: A systematic review","year":2023,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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","funders":"","keywords":"Crossover study; Crossover; Medicine; Clinical study design; MEDLINE; Research design; Statistics; Computer science; Clinical trial; Internal medicine; Alternative medicine; Artificial intelligence; Mathematics","score_opus":0.8142931815136372,"score_gpt":0.656054551092285,"score_spread":0.1582386304213521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379599462","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":[0.0000036233716,0.77585256,0.21492286,0.0013006597,0.00009667309,0.0075313197,0.00020100836,0.00007899523,0.000012293029],"genre_scores_gemma":[0.000003949981,0.8318329,0.16261874,0.0020869102,0.000043277472,0.0032897547,0.00003879555,0.00004904384,0.000036659516],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95818794,0.036695533,0.0037503855,0.00065619923,0.00023451968,0.00047543566],"domain_scores_gemma":[0.8058883,0.19104338,0.0017508559,0.0010746287,0.00013477154,0.0001080805],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05114196,0.0005552651,0.0042989077,0.0001580137,0.00022152864,0.00001640163,0.0007677951,0.00024629652,0.000038557617],"category_scores_gemma":[0.04864304,0.00027427715,0.00044844794,0.0008456077,0.00030104458,0.000107947766,0.00023611852,0.0010711371,0.00001867615],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028341541,0.000084968226,9.51008e-7,0.8272885,0.0010186458,0.000112745016,0.0023619416,0.00011246559,0.0000070045767,0.004904589,0.011952122,0.1521277],"study_design_scores_gemma":[0.0003839345,0.00009081934,0.0000026817274,0.85565656,0.020485202,0.0007944077,0.00025211633,0.005345401,0.00001028062,0.04923667,0.066861674,0.00088023144],"about_ca_topic_score_codex":0.00025678094,"about_ca_topic_score_gemma":0.00006289563,"teacher_disagreement_score":0.15434785,"about_ca_system_score_codex":0.00009847471,"about_ca_system_score_gemma":0.00019240403,"threshold_uncertainty_score":0.9999709},"labels":[],"label_agreement":null},{"id":"W4379768508","doi":"10.1002/jrsm.1645","title":"Methodological considerations for novel approaches to covariate‐adjusted indirect treatment comparisons","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Advanced Causal Inference Techniques","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Econometrics; Weighting; Robustness (evolution); Outcome (game theory); Computer science; Context (archaeology); Extrapolation; Statistics; Mathematics; Medicine","score_opus":0.9848045933522044,"score_gpt":0.6880955858430207,"score_spread":0.2967090075091837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379768508","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":[0.0023612294,0.000026600661,0.9877505,0.0037523136,0.00006691334,0.002740915,0.000146783,0.0010776977,0.0020770943],"genre_scores_gemma":[0.021316824,0.000031042473,0.970554,0.00003832592,0.000096842006,0.0071275895,0.0000113579135,0.00007283546,0.0007511724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9907481,0.0063374606,0.00060534396,0.0007477892,0.0005371334,0.001024175],"domain_scores_gemma":[0.76840544,0.23015517,0.00010460762,0.00075209746,0.0002917578,0.00029092073],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024735572,0.00031593148,0.0010185457,0.0008480359,0.0005912342,0.00012707456,0.0003574457,0.00027474985,0.00016900884],"category_scores_gemma":[0.17852296,0.00024666748,0.00022534796,0.0014087934,0.00023778611,0.00010977255,0.00027140972,0.00035693866,0.000057045694],"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":[0.00020991874,0.0009018177,0.00007947864,0.00020266953,0.00046534286,0.000014177688,0.0016559712,0.00026795914,0.09320831,0.7808395,0.019336488,0.10281839],"study_design_scores_gemma":[0.00024616506,0.00040093003,0.00031215817,0.00006406443,0.000077997785,0.000008986025,0.00086612074,0.007368461,0.39713648,0.58566993,0.0075434237,0.00030529004],"about_ca_topic_score_codex":0.00005087157,"about_ca_topic_score_gemma":0.000051402112,"teacher_disagreement_score":0.30392817,"about_ca_system_score_codex":0.00041202907,"about_ca_system_score_gemma":0.00024133455,"threshold_uncertainty_score":0.99999857},"labels":[],"label_agreement":null},{"id":"W4379967395","doi":"10.1002/sim.9802","title":"Causal inference for recurrent events via aggregated marginal odds ratio","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Inference; Causal inference; Odds ratio; Odds; Econometrics; Statistics; Marginal structural model; Computer science; Mathematics; Artificial intelligence; Logistic regression","score_opus":0.14131302433752374,"score_gpt":0.4749063944263714,"score_spread":0.33359337008884765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379967395","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":[0.004115914,0.00004332748,0.9931801,0.00047780498,0.0004615343,0.00080952566,0.00025347862,0.0003492686,0.00030905937],"genre_scores_gemma":[0.46855682,0.00060259807,0.5261688,0.00024930655,0.0004438182,0.0007983717,0.0011569343,0.00012454356,0.0018987806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980975,0.00008373708,0.0006372498,0.0003140651,0.00042430137,0.00044319517],"domain_scores_gemma":[0.9965462,0.0025268218,0.00022856414,0.00032951773,0.00026200715,0.00010685445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009156743,0.00023681985,0.00045047002,0.0002910976,0.000071307244,0.000007420637,0.00023453575,0.000101559286,0.00019539258],"category_scores_gemma":[0.007197313,0.00020636812,0.000022227372,0.00056884356,0.00016327987,0.000079421625,0.000074314215,0.000300922,0.000030441966],"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":[0.00018114898,0.000121778656,0.00088151434,0.0005441113,0.000039958195,0.00009974081,0.0011839331,0.000025403911,0.0019062308,0.8922354,0.051600832,0.05117993],"study_design_scores_gemma":[0.0010032294,0.0007580532,0.0013194139,0.0005510696,0.00003894943,0.0000051688053,0.00012627563,0.016424851,0.000633738,0.97790205,0.001000875,0.00023635002],"about_ca_topic_score_codex":0.000032178483,"about_ca_topic_score_gemma":0.00021317277,"teacher_disagreement_score":0.46701127,"about_ca_system_score_codex":0.00015073107,"about_ca_system_score_gemma":0.00008080515,"threshold_uncertainty_score":0.8616376},"labels":[],"label_agreement":null},{"id":"W4380051600","doi":"10.1007/s00181-023-02441-7","title":"When to use matching and weighting or regression in instrumental variable estimation? Evidence from college proximity and returns to college","year":2023,"lang":"en","type":"article","venue":"Empirical Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Institut für Arbeitsmarkt- und Berufsforschung","keywords":"Instrumental variable; Covariate; Econometrics; Propensity score matching; Weighting; Estimator; Matching (statistics); Average treatment effect; Statistics; Variance (accounting); Regression; Economics; Estimation; Variance inflation factor; Linear regression; Mathematics; Multicollinearity","score_opus":0.21134094600946787,"score_gpt":0.41446308657484643,"score_spread":0.20312214056537856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380051600","genre_codex":"empirical","genre_gemma":"methods","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":[0.9898372,0.0000060974526,0.0067514363,0.002117014,0.000055383254,0.00075080665,0.0002163603,0.0001931448,0.00007255582],"genre_scores_gemma":[0.49147955,0.00003945756,0.5075683,0.00051222177,0.00002658365,0.000088490546,0.000009202404,0.00002922099,0.00024696614],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867505,0.000065098546,0.00046145025,0.00044571748,0.00008159736,0.00027111318],"domain_scores_gemma":[0.99746543,0.0019361285,0.00011583217,0.0002628838,0.00002634606,0.00019337394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004753864,0.00018860558,0.00035931187,0.00016520552,0.000112935966,0.00009201275,0.00014484342,0.00012304899,0.000045978846],"category_scores_gemma":[0.0018041825,0.00016466092,0.000016700982,0.00027177995,0.000035034067,0.0008754426,0.0004725269,0.00019112244,0.000014706145],"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":[0.0038416432,0.0008290724,0.4908371,0.0013067545,0.00023407582,0.00041096075,0.06603041,0.0038934692,0.013439933,0.32628098,0.07066706,0.022228524],"study_design_scores_gemma":[0.00050227996,0.00021172599,0.011580606,0.0012875925,0.000017791122,0.000017357686,0.0011477654,0.03999366,0.0023658,0.94154507,0.00084784266,0.00048250108],"about_ca_topic_score_codex":0.00020327826,"about_ca_topic_score_gemma":0.000901335,"teacher_disagreement_score":0.6152641,"about_ca_system_score_codex":0.0002921111,"about_ca_system_score_gemma":0.00008268634,"threshold_uncertainty_score":0.6714677},"labels":[],"label_agreement":null},{"id":"W4380150987","doi":"10.1016/j.jval.2023.03.1581","title":"MSR45 Identifying Longitudinal Treatment Effect Trajectories Using Flexible Outcome Modeling and Clustering","year":2023,"lang":"en","type":"article","venue":"Value in Health","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":"EVERSANA (Canada)","funders":"","keywords":"Outcome (game theory); Cluster analysis; Interpretation (philosophy); Computer science; Longitudinal data; Treatment effect; Longitudinal study; Statistical power; Econometrics; Data mining; Artificial intelligence; Statistics; Medicine; Mathematics","score_opus":0.5678470637420231,"score_gpt":0.5187338618576554,"score_spread":0.04911320188436774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380150987","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":[0.8420736,0.00027743643,0.15626061,0.00007114677,0.00014870732,0.00053154357,0.0000045292827,0.00060094934,0.000031434804],"genre_scores_gemma":[0.9513351,0.00026187056,0.048185248,0.000014329913,0.000059356993,0.000053112653,0.0000030893502,0.00004543779,0.000042513293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824405,0.00017254059,0.00057517446,0.00032890635,0.00019044991,0.00048885826],"domain_scores_gemma":[0.9989124,0.00059463916,0.00013066572,0.0002452234,0.00002159171,0.00009549227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011669454,0.00022599619,0.00049775565,0.00030141714,0.00018054333,0.000050953386,0.0000834506,0.00007225632,0.0000036083436],"category_scores_gemma":[0.00025660446,0.00019759455,0.000053196218,0.000407139,0.00002905044,0.00021531225,0.000091678856,0.00016208686,0.0000038771327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018035724,0.00021130596,0.26413888,0.008840149,0.00011334482,0.00018874391,0.011879824,0.6575922,0.0033121898,0.030165546,0.000025307509,0.023352193],"study_design_scores_gemma":[0.00051921967,0.0003724899,0.00081601186,0.0008185295,0.000019100582,0.000029175515,0.00031220962,0.9184168,0.0011992137,0.07723133,0.000008058856,0.00025784565],"about_ca_topic_score_codex":0.0030018734,"about_ca_topic_score_gemma":0.0001579938,"teacher_disagreement_score":0.2633229,"about_ca_system_score_codex":0.0006440785,"about_ca_system_score_gemma":0.00006970979,"threshold_uncertainty_score":0.8057672},"labels":[],"label_agreement":null},{"id":"W4380263991","doi":"10.1002/hec.4719","title":"How does a local instrumental variable method perform across settings with instruments of differing strengths? A simulation study and an evaluation of emergency surgery","year":2023,"lang":"en","type":"article","venue":"Health Economics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Institute of Health Economics","funders":"Division of Mathematical Sciences; School for Public Health Research; Economic and Social Research Council; Medical Research Council; National Cancer Institute; National University of Singapore; British Heart Foundation; University College London; Public Health England; Department of Health and Social Care; National Institute for Health and Care Research; United Kingdom Clinical Research Collaboration; Wellcome Trust; National Institutes of Health; Cancer Research UK","keywords":"Instrumental variable; Statistics; Covariate; Sample size determination; Homogeneity (statistics); Econometrics; Sample (material); Mathematics; Mean squared error; Medicine; Chemistry","score_opus":0.1932856635232457,"score_gpt":0.4838407135181443,"score_spread":0.29055504999489856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380263991","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":[0.9859804,0.000005992062,0.012843259,0.00005050195,0.0000776795,0.0008931096,0.00005939489,0.00008097905,0.000008704712],"genre_scores_gemma":[0.97678685,0.000073627656,0.022971716,0.000009595238,0.0000197338,0.00007504561,0.000029499339,0.000028251905,0.0000056938134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847746,0.00016082176,0.00063759135,0.000274638,0.00018209917,0.00026739822],"domain_scores_gemma":[0.9984427,0.0003895119,0.0006922577,0.00026417506,0.00013062336,0.00008069444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028188336,0.00015569721,0.00047122387,0.00012575692,0.000106684536,0.000020022335,0.00007371137,0.000059971677,0.000015270742],"category_scores_gemma":[0.00022868918,0.00013228737,0.00002612707,0.0001806266,0.000038011654,0.00053258095,0.000082670565,0.00009868085,1.6890357e-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":[0.00023053057,0.0007354486,0.2629839,0.0021012696,0.00017802828,4.3426525e-7,0.014343501,0.009416878,0.00017189064,0.0026456572,0.000011432877,0.70718104],"study_design_scores_gemma":[0.0011927505,0.0009498674,0.024943475,0.00022086536,0.00006759243,0.0000021517767,0.022806209,0.9061184,0.002523665,0.040864244,0.000013865642,0.00029692857],"about_ca_topic_score_codex":0.00013327268,"about_ca_topic_score_gemma":0.00037360302,"teacher_disagreement_score":0.8967015,"about_ca_system_score_codex":0.00021967634,"about_ca_system_score_gemma":0.00016736535,"threshold_uncertainty_score":0.53945225},"labels":[],"label_agreement":null},{"id":"W4380714779","doi":"10.1136/bmj-2021-068911","title":"Use of real world data to improve drug coverage decisions in China","year":2023,"lang":"en","type":"article","venue":"BMJ","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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","funders":"","keywords":"China; Drug; Real world data; Data science; Business; Computer science; Risk analysis (engineering); Geography; Medicine; Pharmacology","score_opus":0.32239701413475724,"score_gpt":0.4823354814005586,"score_spread":0.15993846726580135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380714779","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":[0.9719794,0.000002958854,0.019717835,0.001470932,0.00013868962,0.0012765952,0.000515237,0.0005745743,0.0043238113],"genre_scores_gemma":[0.7879675,0.00010021539,0.20546769,0.000120695855,0.00007419492,0.00009816525,0.00007950279,0.000048778864,0.0060432362],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892795,0.000043815482,0.00038375994,0.00024326447,0.00020418313,0.00019701666],"domain_scores_gemma":[0.99727076,0.0012327846,0.00011970117,0.0012858082,0.000033901193,0.000057023954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063092634,0.00009854118,0.00023542652,0.00024984466,0.000018849993,0.00001779265,0.00041990404,0.000026382548,0.00002111902],"category_scores_gemma":[0.003615536,0.00008984426,0.000024004188,0.00076794374,0.000028111128,0.0002624715,0.0006852029,0.00012988594,0.000050443745],"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":[0.00014464383,0.0002777949,0.008299273,0.0000759933,0.000034130146,0.00013660677,0.0015348989,0.00018121648,0.019779285,0.13526006,0.75540054,0.07887556],"study_design_scores_gemma":[0.0004579991,0.0001377279,0.08202276,0.0006234631,0.000027883481,0.0000029840246,0.00015924308,0.0034243942,0.019884804,0.8703139,0.022355728,0.00058911147],"about_ca_topic_score_codex":0.00050569494,"about_ca_topic_score_gemma":0.0042778733,"teacher_disagreement_score":0.73505384,"about_ca_system_score_codex":0.0000423747,"about_ca_system_score_gemma":0.00004039394,"threshold_uncertainty_score":0.43283954},"labels":[],"label_agreement":null},{"id":"W4381617848","doi":"10.3390/ijerph20136194","title":"Table 2 Fallacy in Descriptive Epidemiology: Bringing Machine Learning to the Table","year":2023,"lang":"en","type":"article","venue":"International Journal of Environmental Research and Public Health","topic":"Advanced Causal Inference Techniques","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":"Ontario Tobacco Research Unit; Sunnybrook Hospital; Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"Center for Tobacco Products; National Cancer Institute; Canadian Institutes of Health Research","keywords":"Fallacy; Descriptive statistics; Contingency table; Outcome (game theory); Covariate; Table (database); Computer science; Statistics; Set (abstract data type); Psychology; Strengths and weaknesses; Data set; Machine learning; Data science; Artificial intelligence; Data mining; Mathematics; Social psychology","score_opus":0.37962706384979317,"score_gpt":0.5113429338242567,"score_spread":0.1317158699744635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381617848","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":[0.92348206,0.0010322836,0.014147324,0.059847828,0.00018666043,0.00043573356,0.00005030742,0.0000459522,0.0007718771],"genre_scores_gemma":[0.9911865,0.002930308,0.004539104,0.00046000446,0.00011902406,0.00001557869,0.000008489632,0.000015081488,0.00072589715],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761087,0.0005761444,0.0005034409,0.00014897774,0.00060876424,0.0005517829],"domain_scores_gemma":[0.99739045,0.001974762,0.00019363567,0.00009568801,0.0000766763,0.00026880056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010494502,0.00008297519,0.0002102237,0.00052501884,0.00015373685,0.00005596857,0.00041907065,0.00003682866,0.00011858127],"category_scores_gemma":[0.005833976,0.000060414164,0.000025991734,0.00033562843,0.00011485691,0.0003148876,0.00034741522,0.0008338053,0.000020184987],"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":[0.00045663436,0.0013422447,0.46946928,0.000106578314,0.00032878056,0.00039372878,0.015073199,0.0011438039,0.0047736075,0.089470185,0.03428284,0.38315913],"study_design_scores_gemma":[0.0017406986,0.0029314493,0.12641872,0.00063719077,0.000004007224,0.0004766927,0.019696845,0.009297217,0.0005203743,0.4801636,0.35768896,0.0004242313],"about_ca_topic_score_codex":0.00033520992,"about_ca_topic_score_gemma":0.00017979348,"teacher_disagreement_score":0.39069343,"about_ca_system_score_codex":0.00057175866,"about_ca_system_score_gemma":0.00016554294,"threshold_uncertainty_score":0.69842356},"labels":[],"label_agreement":null},{"id":"W4382062812","doi":"10.3390/math11132830","title":"Estimation of Mediation Effect on Zero-Inflated Microbiome Mediators","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Advanced Causal Inference Techniques","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":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mediation; Microbiome; Weighting; Causal inference; Computer science; Econometrics; Bioinformatics; Biology; Medicine; Mathematics","score_opus":0.057159393947662916,"score_gpt":0.3822569246866689,"score_spread":0.325097530739006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382062812","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":[0.9248831,0.0000058978485,0.07187137,0.000081230064,0.00015251747,0.0007366785,0.00002497099,0.0009692828,0.0012749311],"genre_scores_gemma":[0.92689705,0.000013008079,0.07259351,0.000016567237,0.000031131727,0.00009080794,0.00006973257,0.00006933214,0.00021884694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984886,0.00006564964,0.00060488144,0.0001892084,0.0003977747,0.00025388447],"domain_scores_gemma":[0.99684316,0.0021211049,0.00042191762,0.00047224702,0.00008194551,0.000059616163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000856355,0.0002268516,0.00043448748,0.00036306915,0.000050015416,0.000015886817,0.000208777,0.00016712154,0.00006450442],"category_scores_gemma":[0.002610908,0.00018996815,0.00008989634,0.00072766206,0.00007022384,0.00012382014,0.000063279476,0.00014879907,0.00034170525],"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":[0.000105471256,0.00087965373,0.0003939886,0.0059607173,0.00030974165,0.000041611547,0.010268048,0.0020871623,0.32419863,0.57110965,0.018897044,0.065748245],"study_design_scores_gemma":[0.00034408693,0.00033751054,0.000061123494,0.000300784,0.000049709444,0.0000039836364,0.000050601833,0.019005254,0.38059828,0.5989922,0.00003808372,0.00021836757],"about_ca_topic_score_codex":0.0000014702284,"about_ca_topic_score_gemma":8.9902574e-7,"teacher_disagreement_score":0.065529875,"about_ca_system_score_codex":0.00008085505,"about_ca_system_score_gemma":0.000023117005,"threshold_uncertainty_score":0.7746676},"labels":[],"label_agreement":null},{"id":"W4382318232","doi":"10.1609/aaai.v37i9.26266","title":"Disentangled Representation for Causal Mediation Analysis","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","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":"Simon Fraser University","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; University of South Australia","keywords":"Confounding; Mediation; Latent variable; Causal inference; Observational study; Econometrics; Causality (physics); Representation (politics); Computer science; Outcome (game theory); Structural equation modeling; Affect (linguistics); Mechanism (biology); Causal model; Artificial intelligence; Machine learning; Psychology; Statistics; Mathematics","score_opus":0.3166754638276828,"score_gpt":0.45770785517093737,"score_spread":0.14103239134325457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318232","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":[0.81431067,0.000007829884,0.16890001,0.0051457933,0.0005459328,0.0028437325,0.00010551625,0.0011466021,0.006993885],"genre_scores_gemma":[0.9932268,0.000030318834,0.005890503,0.000041899784,0.00008370759,0.00024447567,0.000013335962,0.000024020343,0.00044490484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813783,0.000018501487,0.00065006985,0.00040047496,0.00048485663,0.00030828704],"domain_scores_gemma":[0.99779946,0.00051498844,0.0005556757,0.00026545857,0.0008012431,0.00006314947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006515808,0.00019862145,0.00036786695,0.0003676549,0.00016240815,0.00007788249,0.000577738,0.00010494861,0.00008698989],"category_scores_gemma":[0.0033147628,0.00015403541,0.00024552984,0.002182848,0.00017796275,0.00025692076,0.00012942505,0.00015805988,0.00003143848],"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":[0.000099920675,0.00008003838,0.001344181,0.000059132046,0.000083367035,1.9884905e-7,0.0008361315,0.0000684637,0.045381352,0.9421605,0.00081287755,0.009073842],"study_design_scores_gemma":[0.00001901401,0.00007680813,0.0003147618,0.000037471225,0.00012290511,2.6226343e-7,0.0008033681,0.019690456,0.32653266,0.6522627,0.000015709404,0.00012387967],"about_ca_topic_score_codex":0.000017575861,"about_ca_topic_score_gemma":0.00003919939,"teacher_disagreement_score":0.2898978,"about_ca_system_score_codex":0.00006768423,"about_ca_system_score_gemma":0.00004097665,"threshold_uncertainty_score":0.6281382},"labels":[],"label_agreement":null},{"id":"W4382987679","doi":"10.1002/cjs.11783","title":"Rerandomization and optimal matching","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; University of Waterloo","keywords":"Covariate; Randomization; Mean squared error; Robustness (evolution); Restricted randomization; Matching (statistics); Statistics; Balance (ability); Computer science; Mathematics; Factorial experiment; Measure (data warehouse); Mathematical optimization; Randomized controlled trial; Data mining; Medicine","score_opus":0.09737256076111298,"score_gpt":0.35830805078291467,"score_spread":0.2609354900218017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382987679","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":[0.074249685,0.000043065396,0.9249246,0.0001821703,0.00012363066,0.000072834926,0.00009850884,0.000029684164,0.0002758215],"genre_scores_gemma":[0.4280896,0.00009881799,0.5714191,0.000060711096,0.0000784678,0.0000015211511,0.0000074472537,0.000024502368,0.00021978379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994025,0.000028825452,0.00026702296,0.00004915728,0.0000955328,0.00015695745],"domain_scores_gemma":[0.998956,0.00041089937,0.00016505289,0.000063351115,0.00016956372,0.00023512873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037089956,0.000065243265,0.00015780545,0.00021584578,0.00007810629,0.000040684616,0.000072067895,0.00003613338,0.00004662648],"category_scores_gemma":[0.001095384,0.00006141592,0.000014743864,0.00013042655,0.000054485616,0.000111931666,0.00000719403,0.00013537248,0.0000040878645],"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":[0.000039024955,0.0000069440807,0.0010767375,0.000120486606,0.00005688395,0.00094570126,0.0032946824,0.0006767122,0.00041324217,0.9002292,0.07198853,0.02115186],"study_design_scores_gemma":[0.00048125355,0.000076563105,0.00063103903,0.00009368636,0.00003110905,0.00014456602,0.00037178973,0.00092922855,0.0001854992,0.9954393,0.0015068251,0.00010914349],"about_ca_topic_score_codex":0.00021055894,"about_ca_topic_score_gemma":0.0017311943,"teacher_disagreement_score":0.3538399,"about_ca_system_score_codex":0.000058273556,"about_ca_system_score_gemma":0.00024992973,"threshold_uncertainty_score":0.25044686},"labels":[],"label_agreement":null},{"id":"W4383301689","doi":"10.1037/hea0001299","title":"Tutorial on causal mediation analysis with binary variables: An application to health psychology research.","year":2023,"lang":"en","type":"article","venue":"Health Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"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":"Center for Tobacco Products; Office of Behavioral and Social Sciences Research; National Institute on Drug Abuse; National Cancer Institute; National Institutes of Health; York University; New York University","keywords":"Causal inference; Mediation; Outcome (game theory); Context (archaeology); Psychology; Confounding; Causal chain; Causality (physics); Weighting; Causal model; Mediator; Social psychology; Econometrics; Medicine; Statistics; Mathematics","score_opus":0.360900368256626,"score_gpt":0.6215082897469495,"score_spread":0.26060792149032347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383301689","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":[0.07931894,0.000041831197,0.74191487,0.1661448,0.0013289703,0.004759625,0.00013894361,0.0031722607,0.003179769],"genre_scores_gemma":[0.7302757,0.0009700358,0.16423957,0.09537172,0.0025425788,0.0044016265,0.0014388455,0.0003183847,0.00044156233],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994555,0.0016324613,0.0008492714,0.0011313945,0.0006431589,0.0011887127],"domain_scores_gemma":[0.9963566,0.0007901306,0.0004145008,0.0015687743,0.00029780544,0.00057217776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005668162,0.00027099162,0.0007415213,0.0019298168,0.00038451882,0.000021277654,0.00045745797,0.00030335487,0.00008403514],"category_scores_gemma":[0.00042523048,0.00024779915,0.00005432708,0.005105768,0.0001597555,0.00013939898,0.00006715208,0.0007561248,0.00032507474],"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":[0.002637589,0.0024962253,0.003851429,0.00043322513,0.0004349106,0.00005144392,0.008182706,0.0011012653,0.0020552413,0.3171834,0.61624134,0.045331262],"study_design_scores_gemma":[0.0040533007,0.04157346,0.07678162,0.00020603984,0.00010560052,0.000060392747,0.0006848925,0.0026699395,0.000115408984,0.63229114,0.24003063,0.0014275644],"about_ca_topic_score_codex":0.00019469578,"about_ca_topic_score_gemma":0.0010366128,"teacher_disagreement_score":0.65095675,"about_ca_system_score_codex":0.00044067757,"about_ca_system_score_gemma":0.00037568726,"threshold_uncertainty_score":0.99999744},"labels":[],"label_agreement":null},{"id":"W4383682360","doi":"10.3329/jsr.v56i2.67467","title":"Properties of inverse probability of adherence weighted estimator of the per-protocol effect for sustained treatment strategies under different data-generating mechanisms and adherence patterns","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical 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":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Biogen; Michael Smith Health Research BC; Compute Canada; Western Canada Research Grid","keywords":"Estimator; Confounding; Inverse probability; Context (archaeology); Statistics; Protocol (science); Medicine; Clinical trial; Randomized controlled trial; Mathematics; Demography; Econometrics; Internal medicine; Geography","score_opus":0.44855631455749523,"score_gpt":0.5266527973104499,"score_spread":0.07809648275295467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383682360","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":[0.67509013,0.000008181925,0.30739087,0.00008043552,0.00002239288,0.017033936,0.000342374,0.000018684274,0.000013027968],"genre_scores_gemma":[0.90947986,0.000011986906,0.08740172,0.0000013097654,0.000015050652,0.0030426157,0.0000046377777,0.000018460229,0.000024338291],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997064,0.0006124313,0.00090185046,0.00022538484,0.0008778294,0.00031852716],"domain_scores_gemma":[0.9937004,0.004083886,0.00051293307,0.00048284428,0.0011176618,0.00010227894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023199655,0.00017834139,0.00061022147,0.00013060805,0.00010027013,0.00003748838,0.00048254398,0.00007938111,0.000039609993],"category_scores_gemma":[0.0050523337,0.000091690024,0.00006633709,0.00021176592,0.0005542381,0.00019338938,0.00035160937,0.0002895089,2.590718e-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":[0.0021924386,0.00095656543,0.0021904635,0.012679164,0.00028546565,0.000016391155,0.0013111992,0.00008234908,0.49302694,0.47398823,0.00028541067,0.012985384],"study_design_scores_gemma":[0.001287,0.0073708496,0.0010259021,0.001097281,0.00007095553,0.000006257864,0.002709623,0.018161448,0.30552098,0.6626318,0.0000025440222,0.00011531042],"about_ca_topic_score_codex":0.00007516634,"about_ca_topic_score_gemma":0.00009916527,"teacher_disagreement_score":0.23438977,"about_ca_system_score_codex":0.00013219209,"about_ca_system_score_gemma":0.0005168005,"threshold_uncertainty_score":0.604848},"labels":[],"label_agreement":null},{"id":"W4384155640","doi":"10.1101/2023.07.13.23292601","title":"Design differences explain variation in results between randomized trials and their non-randomized emulations","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Institutes of Health; Brigham and Women's Hospital","keywords":"Randomized controlled trial; Medicine; Confounding; Discontinuation; Randomized experiment; Research design; Sample size determination; Completely randomized design; Randomization; Observational study; Statistics; Surgery; Internal medicine","score_opus":0.4261275238457517,"score_gpt":0.44275476501233624,"score_spread":0.01662724116658454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384155640","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":[0.16575168,0.00008961305,0.82528126,0.0005931884,0.00025977512,0.0071176523,0.00013924629,0.00060077006,0.00016682193],"genre_scores_gemma":[0.8878684,0.00071802427,0.107646175,0.000013242588,0.00020664459,0.0031590494,0.00010466464,0.0000831319,0.00020069332],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9853205,0.0094472105,0.003531666,0.000894132,0.00039408234,0.0004124209],"domain_scores_gemma":[0.8794305,0.11732307,0.0021204082,0.0008330841,0.00018530767,0.00010765498],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040484212,0.00064218,0.006152247,0.0006807668,0.00010404808,0.00013942145,0.0004536188,0.0006575437,0.000019663401],"category_scores_gemma":[0.08507723,0.00043688386,0.00049299124,0.00030682728,0.00035081033,0.00015195138,0.00045958997,0.00083894463,0.000008388938],"study_design_candidate":"randomized_trial","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":[0.840043,0.0005224761,0.0021570865,0.0017368299,0.003902509,0.00004781141,0.07613531,0.0022879534,0.0038135853,0.062762104,0.00089046906,0.0057008406],"study_design_scores_gemma":[0.24157047,0.000019906374,0.0008426394,0.00063711824,0.00027741125,3.851906e-7,0.00007888028,0.0120478105,0.00085224933,0.7433229,0.0000015811555,0.00034865204],"about_ca_topic_score_codex":0.00018971831,"about_ca_topic_score_gemma":0.000051618546,"teacher_disagreement_score":0.7221167,"about_ca_system_score_codex":0.00010016203,"about_ca_system_score_gemma":0.00013316657,"threshold_uncertainty_score":0.9998083},"labels":[],"label_agreement":null},{"id":"W4384283005","doi":"10.1093/ije/dyad102","title":"Identifiability of causal effects in test-negative design studies","year":2023,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"Simons Institute for the Theory of Computing, University of California Berkeley","keywords":"Directed acyclic graph; Causal inference; Identifiability; Outcome (game theory); Causal model; Covariate; Computer science; Sampling (signal processing); Causality (physics); Econometrics; Statistics; Machine learning; Mathematics; Algorithm","score_opus":0.4196313907985724,"score_gpt":0.5530443079842668,"score_spread":0.13341291718569442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384283005","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":[0.7253907,0.00046923882,0.26816687,0.003315364,0.001804879,0.00049742154,0.000022402617,0.000109579676,0.0002235884],"genre_scores_gemma":[0.83166283,0.0003622052,0.16764298,0.00013281478,0.00011889177,0.0000176397,6.983617e-7,0.000012002741,0.000049945105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970191,0.0010045122,0.0013868673,0.00015045507,0.00023303465,0.0002060413],"domain_scores_gemma":[0.8792767,0.118364505,0.0011928404,0.00015334236,0.0009665462,0.00004608337],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007570794,0.00012608303,0.000742789,0.00044311507,0.0000141380015,0.000002693845,0.00041683612,0.00009544348,0.000019595765],"category_scores_gemma":[0.30719554,0.00009914622,0.00012485414,0.00022123475,0.0002965572,0.00018360514,0.00013317073,0.00029972938,0.000007192883],"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":[0.0011047951,0.0013112936,0.42612547,0.0006683882,0.0024750868,0.001470446,0.006172344,0.0063731396,0.039117686,0.43893564,0.048700403,0.027545301],"study_design_scores_gemma":[0.00034818167,0.00029947516,0.02089242,0.00029203008,0.000017468856,0.00004691328,0.00017429817,0.0003438637,0.010763605,0.9667296,0.000022405282,0.00006975906],"about_ca_topic_score_codex":0.00001886109,"about_ca_topic_score_gemma":0.00002010674,"teacher_disagreement_score":0.52779394,"about_ca_system_score_codex":0.00021392808,"about_ca_system_score_gemma":0.000076589815,"threshold_uncertainty_score":0.6986402},"labels":[],"label_agreement":null},{"id":"W4384626449","doi":"10.1111/1471-0528.17528","title":"We can predict, but validation and implementation remain a challenge","year":2023,"lang":"en","type":"article","venue":"BJOG An International Journal of Obstetrics & Gynaecology","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":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Psychology; Political science; Computer science","score_opus":0.12628446076782066,"score_gpt":0.43323865338135925,"score_spread":0.3069541926135386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384626449","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":[0.977138,0.00017342667,0.015664717,0.0024828038,0.003085324,0.00032382263,0.00008458392,0.00018451578,0.00086281233],"genre_scores_gemma":[0.98715514,0.0011760938,0.011211824,0.0000683827,0.00018086258,0.000019082006,0.00004330883,0.0000268166,0.00011846866],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982351,0.00014750082,0.0006967165,0.00017948714,0.000520092,0.00022110087],"domain_scores_gemma":[0.9966275,0.001698365,0.00070546794,0.00014662811,0.00070737244,0.000114674214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075936335,0.00014270112,0.0002529512,0.0009032461,0.000060525774,0.000056244397,0.00038654916,0.00012375235,0.00028039474],"category_scores_gemma":[0.0028618495,0.00013787672,0.0000629089,0.00031213375,0.000058936726,0.00048684957,0.000109756445,0.00025268857,0.0000057267134],"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":[0.00012328384,0.00071548903,0.047572073,0.00013686283,0.0007097088,0.0013534522,0.008240161,0.00016167319,0.0036812136,0.36445644,0.0062949685,0.56655467],"study_design_scores_gemma":[0.0029838474,0.0021168785,0.067905284,0.000042407955,0.00012625511,0.0003731179,0.005039468,0.0007539865,0.005803891,0.9104342,0.0039899703,0.0004307262],"about_ca_topic_score_codex":0.00000921041,"about_ca_topic_score_gemma":0.000027926659,"teacher_disagreement_score":0.56612396,"about_ca_system_score_codex":0.0004058677,"about_ca_system_score_gemma":0.00013214914,"threshold_uncertainty_score":0.56224495},"labels":[],"label_agreement":null},{"id":"W4385422417","doi":"10.1002/cjs.11788","title":"A calibration method to stabilize estimation with missing data","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Inverse probability weighting; Covariate; Weighting; Statistics; Mathematics; Property (philosophy); Calibration; Computer science; Econometrics; Applied mathematics","score_opus":0.3580087222115719,"score_gpt":0.45066885243959814,"score_spread":0.09266013022802627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385422417","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":[0.0009323248,0.000008431436,0.99740714,0.0007512546,0.000058689922,0.00013974009,0.00055221206,0.00004025719,0.0001099329],"genre_scores_gemma":[0.026862388,0.0000024226365,0.97282857,0.000106612,0.00004379901,0.0000021599515,0.000061956605,0.000027982447,0.00006409524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899757,0.00007583719,0.00036787402,0.000120113466,0.00021437534,0.00022424171],"domain_scores_gemma":[0.99801075,0.0006970654,0.00023792162,0.0003233555,0.0002889131,0.00044198774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008064492,0.00010098319,0.00019824778,0.00030535704,0.000092850336,0.0000869124,0.0002917458,0.000040552528,0.00006525162],"category_scores_gemma":[0.002700573,0.00008752428,0.000010369612,0.00040580874,0.000039212842,0.0003405517,0.000023155544,0.00015674834,0.000005835647],"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":[0.000082474784,0.000035375,0.00085442176,0.00036390556,0.00014155812,0.0015041302,0.0047867293,0.006503666,0.0022097302,0.3505666,0.31418645,0.31876498],"study_design_scores_gemma":[0.00026099585,0.0003704621,0.00039310983,0.0003389371,0.000104567385,0.0001949131,0.00051881775,0.13431047,0.0013635575,0.8565118,0.0053501776,0.00028219557],"about_ca_topic_score_codex":0.000601295,"about_ca_topic_score_gemma":0.010208132,"teacher_disagreement_score":0.5059452,"about_ca_system_score_codex":0.0001519947,"about_ca_system_score_gemma":0.0010970929,"threshold_uncertainty_score":0.5696377},"labels":[],"label_agreement":null},{"id":"W4385450150","doi":"10.1097/ede.0000000000001643","title":"Effect Measure Modification by Covariates in Mediation: Extending Regression-based Causal Mediation Analysis","year":2023,"lang":"en","type":"article","venue":"Epidemiology","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":"AstraZeneca (Canada); McGill University","funders":"U.S. National Library of Medicine; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute","keywords":"Mediation; Baseline (sea); Biomarker; Medicine; Covariate; Internal medicine; Oncology; Regression analysis; Effect modification; Regression; Psychology; Bioinformatics; Econometrics; Statistics; Biology; Confidence interval; Psychotherapist; Economics; Mathematics","score_opus":0.18077410192656415,"score_gpt":0.4787696919708121,"score_spread":0.2979955900442479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385450150","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":[0.18540934,0.00032975126,0.8071711,0.004421395,0.00028720874,0.00078178756,0.000048265487,0.0013311746,0.00021995205],"genre_scores_gemma":[0.9813534,0.00009289902,0.01695959,0.00019518936,0.000099588804,0.00042360398,0.00078774686,0.00002999003,0.000058016773],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957432,0.0022874256,0.0008351314,0.00048036643,0.00022427837,0.00042960656],"domain_scores_gemma":[0.97573936,0.023092909,0.0005322006,0.0004534219,0.000097027296,0.0000850515],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008781019,0.00023189464,0.0008164429,0.0007018159,0.0000863068,0.000007049471,0.00021081208,0.00035456222,0.00009523277],"category_scores_gemma":[0.038677465,0.00018998783,0.00013045198,0.0017727971,0.00007976767,0.00014200444,0.000039317158,0.0003101785,0.000047753834],"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":[0.00035884173,0.00028443363,0.65282387,0.00043833526,0.000669654,0.000041474937,0.0010169446,0.023536352,0.03266544,0.18186282,0.058885023,0.04741681],"study_design_scores_gemma":[0.00095772394,0.00028260285,0.050875627,0.00011657592,0.000301262,0.000001909318,0.00006193195,0.36992878,0.012552381,0.5640231,0.00030385202,0.0005942919],"about_ca_topic_score_codex":0.00006466206,"about_ca_topic_score_gemma":0.00006587303,"teacher_disagreement_score":0.79594404,"about_ca_system_score_codex":0.00022530611,"about_ca_system_score_gemma":0.00004555951,"threshold_uncertainty_score":0.96942014},"labels":[],"label_agreement":null},{"id":"W4385582407","doi":"10.1177/00222437231195577","title":"Correcting Regressor-Endogeneity Bias via Instrument-Free Joint Estimation Using Semiparametric Odds Ratio Models","year":2023,"lang":"en","type":"article","venue":"Journal of Marketing Research","topic":"Advanced Causal Inference Techniques","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":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Endogeneity; Econometrics; Instrumental variable; Conditional independence; Inference; Statistics; Parametric statistics; Conditional probability distribution; Computer science; Mathematics; Artificial intelligence","score_opus":0.7075800244134491,"score_gpt":0.5166181316429215,"score_spread":0.19096189277052766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385582407","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":[0.70907336,0.000077740675,0.28926653,0.0002278391,0.00017209328,0.00030617684,0.000003118587,0.00015048392,0.0007226696],"genre_scores_gemma":[0.86763585,0.00012826997,0.13181578,0.000009900941,0.00017606089,0.000010892307,0.0000018246659,0.00005647717,0.00016493059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931897,0.0023832556,0.0012493004,0.00028245163,0.00208453,0.0008107403],"domain_scores_gemma":[0.98530823,0.01125415,0.001042953,0.0006094032,0.0015978533,0.00018742973],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047718775,0.00021331136,0.000498877,0.001958635,0.0004358862,0.00019536201,0.0006691543,0.00017024518,0.00004895827],"category_scores_gemma":[0.10101799,0.00018975405,0.00016721366,0.0027329295,0.00013057649,0.0007970067,0.0006238022,0.001557835,0.000008516581],"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":[0.0032226176,0.0009242877,0.008747093,0.0029283334,0.0006874519,0.0009712598,0.00411684,0.12299684,0.12583502,0.014993842,0.030045964,0.68453044],"study_design_scores_gemma":[0.0005111318,0.00019222415,0.0005296924,0.0011616145,0.000030691925,0.00044684252,0.0006931218,0.638003,0.025864724,0.33233252,0.000017145245,0.00021728025],"about_ca_topic_score_codex":0.00004044168,"about_ca_topic_score_gemma":0.000007578119,"teacher_disagreement_score":0.6843132,"about_ca_system_score_codex":0.00077948614,"about_ca_system_score_gemma":0.0003298794,"threshold_uncertainty_score":0.9805739},"labels":[],"label_agreement":null},{"id":"W4385652443","doi":"10.1016/j.jclinepi.2023.08.003","title":"The implementation of target trial emulation for causal inference: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":false,"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; China Scholarship Council","keywords":"Emulation; Causal inference; Inference; Computer science; Data science; Medicine; Artificial intelligence; Psychology; Econometrics; Mathematics; Social psychology","score_opus":0.8632500706330115,"score_gpt":0.7560629111613295,"score_spread":0.107187159471682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385652443","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":[0.0000037424602,0.9054144,0.08860645,0.0004769203,0.001256615,0.00415876,0.000035688405,0.00003453366,0.000012884987],"genre_scores_gemma":[0.0000014411006,0.95131785,0.046940025,0.00015467807,0.0012003287,0.0002807745,0.0000288848,0.000050400806,0.000025607878],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9720699,0.007896891,0.018994004,0.00031166358,0.00030676043,0.00042078877],"domain_scores_gemma":[0.699774,0.2735132,0.025399301,0.00045599262,0.0007334154,0.0001240806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07035262,0.00035058265,0.010369797,0.00015233504,0.00008593108,0.000008342884,0.0006339585,0.00066247734,0.00004325255],"category_scores_gemma":[0.36353505,0.0001971663,0.0026242526,0.00026101826,0.00022644168,0.0001238526,0.00012572478,0.0011752907,0.0000046017944],"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":[0.00052075286,0.00006313225,0.000032004766,0.09828796,0.00048160314,0.0000025217978,0.0000098987575,0.0000016099488,3.27345e-8,0.04403891,0.007539059,0.8490225],"study_design_scores_gemma":[0.0031359338,0.0020721396,0.0000053467347,0.2880165,0.0016567471,0.000018383633,0.000014743455,0.000013027828,4.2072864e-7,0.5683595,0.13648434,0.00022294078],"about_ca_topic_score_codex":0.000004442397,"about_ca_topic_score_gemma":0.00002494667,"teacher_disagreement_score":0.8487996,"about_ca_system_score_codex":0.00008410305,"about_ca_system_score_gemma":0.0018061197,"threshold_uncertainty_score":0.9572676},"labels":[],"label_agreement":null},{"id":"W4385681410","doi":"10.48550/arxiv.2308.03369","title":"Variable importance for causal forests: breaking down the heterogeneity of treatment effects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","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":"Safran Electronics (Canada)","funders":"","keywords":"Consistency (knowledge bases); Confounding; Econometrics; Variable (mathematics); Random forest; Computer science; Measure (data warehouse); Regression; Causal inference; Mathematics; Statistics; Machine learning; Artificial intelligence; Data mining","score_opus":0.2595606165189933,"score_gpt":0.31303736055942316,"score_spread":0.05347674404042985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385681410","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":[0.41565713,0.000035505655,0.5811951,0.000023136157,0.00022876826,0.0018320631,0.00017756657,0.00048364318,0.00036703926],"genre_scores_gemma":[0.98394567,0.0000983169,0.014905486,0.000017328113,0.00007602232,0.000054683514,0.000044628312,0.00007221017,0.0007856559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99834806,0.000111492984,0.00034174166,0.00071683526,0.00008002635,0.00040183842],"domain_scores_gemma":[0.99600387,0.001812549,0.0006200011,0.001291182,0.00019335566,0.00007905195],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003836936,0.00041041756,0.00063013064,0.000127313,0.00014891285,0.000026137686,0.0006682787,0.00032104747,0.000011546466],"category_scores_gemma":[0.00035955405,0.00033724218,0.0003162243,0.00029438484,0.00016257442,0.00011140553,0.0005703882,0.00028279872,0.000005109824],"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":[0.00015231884,0.00022527158,0.012486949,0.0013237493,0.0006645922,0.00012523406,0.00021759639,0.022300731,0.0005805174,0.96107656,0.0006285109,0.00021797644],"study_design_scores_gemma":[0.00051672896,0.0003127242,0.0004916825,0.0003438814,0.0004613775,0.000003928768,0.000051330553,0.010762985,0.007421907,0.9790817,0.00019122983,0.00036055082],"about_ca_topic_score_codex":0.00035159124,"about_ca_topic_score_gemma":0.0011231756,"teacher_disagreement_score":0.5682885,"about_ca_system_score_codex":0.0006548205,"about_ca_system_score_gemma":0.00020183937,"threshold_uncertainty_score":0.999908},"labels":[],"label_agreement":null},{"id":"W4386304228","doi":"10.21203/rs.3.rs-3282208/v1","title":"Application of Causal Inference Methods to Pooled Longitudinal Non- Randomized Studies: A Methodological Systematic Review","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Institute of Genetics; Canadian Institutes of Health Research; European Commission","keywords":"Causal inference; Observational study; Checklist; Confounding; Systematic review; MEDLINE; Meta-analysis; Inference; Computer science; Quality (philosophy); Psychology; Data science; Medicine; Artificial intelligence; Cognitive psychology; Political science; Pathology","score_opus":0.7301174082938059,"score_gpt":0.6883117075626177,"score_spread":0.04180570073118817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386304228","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":[0.00026108563,0.013106274,0.96040785,0.0007483523,0.000110497196,0.024549266,0.000064143045,0.0005965872,0.00015592],"genre_scores_gemma":[0.020354869,0.024342047,0.91130614,0.00007564331,0.000112078385,0.043173376,0.0000577066,0.0001460506,0.0004321075],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.972785,0.019460868,0.0031419937,0.0014322345,0.0022266204,0.00095329835],"domain_scores_gemma":[0.89889467,0.091622934,0.0014087997,0.0030310517,0.004718914,0.00032361742],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07730511,0.0006745596,0.0070444224,0.0009050414,0.00015032293,0.000059969894,0.0015965691,0.0005827914,0.000038380236],"category_scores_gemma":[0.30956778,0.0004795744,0.00074723276,0.001700726,0.0007553858,0.00009309375,0.0041861916,0.00222978,0.00009952178],"study_design_candidate":"systematic_review","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":[0.0015875801,0.00015315447,0.000012547434,0.95214975,0.0010004401,0.00002287069,0.0010826113,0.00004902206,0.0006589232,0.041683294,0.0010896128,0.000510217],"study_design_scores_gemma":[0.00266492,0.00024595638,0.00001633157,0.328401,0.001025288,0.0000053677018,0.0006811876,0.0012592594,0.002200796,0.66300344,0.000007696616,0.00048877986],"about_ca_topic_score_codex":0.00015517758,"about_ca_topic_score_gemma":0.00003431807,"teacher_disagreement_score":0.6237487,"about_ca_system_score_codex":0.00062150205,"about_ca_system_score_gemma":0.00039906055,"threshold_uncertainty_score":0.9997656},"labels":[],"label_agreement":null},{"id":"W4386337675","doi":"10.21033/wp-2023-32","title":"Forecasted Treatment Effects","year":2023,"lang":"en","type":"report","venue":"","topic":"Advanced Causal Inference Techniques","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","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Environmental science; Computer science","score_opus":0.5968615873136218,"score_gpt":0.5421047526194197,"score_spread":0.05475683469420212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386337675","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059112813,0.00020305562,0.041132364,0.000072446004,0.0014708919,0.0027355044,0.000064951244,0.008912363,0.9448173],"genre_scores_gemma":[0.003467223,0.003672607,0.11296686,0.000040151266,0.0008620297,0.001960564,0.00028472368,0.00057652587,0.8761693],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982296,0.00004100916,0.00041542965,0.00039514422,0.0005704461,0.0003483358],"domain_scores_gemma":[0.99725664,0.0014108019,0.00026878744,0.000723894,0.00025413817,0.0000857619],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028615873,0.00044284828,0.00078208797,0.00019916389,0.00004085523,0.000024854293,0.00016672912,0.00044799483,0.00020229748],"category_scores_gemma":[0.0015608711,0.00031492038,0.00023240726,0.00019084374,0.00003479263,0.00004731743,0.00009475835,0.00020761049,0.00030287146],"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":[0.000012588092,0.00030002603,0.00006196975,0.002415313,0.0006726471,0.0006153839,0.00014095745,5.185655e-7,0.00021843944,0.038887292,0.75405157,0.20262328],"study_design_scores_gemma":[0.00035971974,0.0010393393,0.000038564474,0.0011416927,0.0004538616,0.000087938686,0.000029013672,0.000033676773,0.02821753,0.7592275,0.20843141,0.0009397493],"about_ca_topic_score_codex":0.00022327046,"about_ca_topic_score_gemma":0.00031798476,"teacher_disagreement_score":0.7203402,"about_ca_system_score_codex":0.0010611521,"about_ca_system_score_gemma":0.00043677728,"threshold_uncertainty_score":0.99993026},"labels":[],"label_agreement":null},{"id":"W4386368771","doi":"10.2139/ssrn.4558108","title":"Forecasted Treatment Effects","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Simon Fraser University","funders":"Economic and Social Research Council","keywords":"Environmental science","score_opus":0.12316139753934119,"score_gpt":0.4023305954514776,"score_spread":0.2791691979121364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386368771","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":[0.67137295,0.00084985537,0.31830534,0.00093199534,0.00037567515,0.0009381695,0.0000039194106,0.0022698105,0.0049522715],"genre_scores_gemma":[0.98250675,0.0036377981,0.005557579,0.00003699578,0.00026090018,0.000075620934,0.0000056102986,0.00007281198,0.007845943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973573,0.0000757723,0.00022657469,0.00015344482,0.00019828224,0.001988627],"domain_scores_gemma":[0.99916357,0.00037326792,0.0001259178,0.00020829626,0.0000539881,0.00007495727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078495627,0.00018027256,0.00022983876,0.0001711254,0.00014257077,0.000028258126,0.00017378294,0.000075525764,0.000017676266],"category_scores_gemma":[0.0002789879,0.00013710011,0.00012064151,0.00033186475,0.000027554464,0.00013903783,0.000030554147,0.00070888357,0.0001266025],"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":[0.000027470422,0.000071155446,0.00018247767,0.0000145961385,0.00015274934,0.00003347555,0.00017145093,0.000006811304,0.0014423111,0.8956774,0.0005633309,0.101656765],"study_design_scores_gemma":[0.00049200957,0.0009506574,0.00005585282,0.000030379499,0.00003884159,0.00026452192,0.00027167314,0.00011548699,0.0034844438,0.9932258,0.0009280095,0.00014232639],"about_ca_topic_score_codex":0.000009188619,"about_ca_topic_score_gemma":0.00019921735,"teacher_disagreement_score":0.31274778,"about_ca_system_score_codex":0.0014076079,"about_ca_system_score_gemma":0.0005785302,"threshold_uncertainty_score":0.55907804},"labels":[],"label_agreement":null},{"id":"W4386387103","doi":"10.1007/s10985-023-09605-8","title":"Dynamic Treatment Regimes Using Bayesian Additive Regression Trees for Censored Outcomes","year":2023,"lang":"en","type":"article","venue":"Lifetime Data Analysis","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":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Health Resources and Services Administration; National Cancer Institute; U.S. Department of Health and Human Services","keywords":"Frequentist inference; Computer science; Bayesian probability; Machine learning; Context (archaeology); Regression; Artificial intelligence; Bayesian linear regression; Bayesian inference; Censored regression model; Regression analysis; Statistics; Mathematics","score_opus":0.1547498798526498,"score_gpt":0.4599385546441727,"score_spread":0.3051886747915229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386387103","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":[0.02457498,0.00009002905,0.95440644,0.0009518476,0.000082488026,0.0012170468,0.0165458,0.0018327312,0.0002986134],"genre_scores_gemma":[0.21626331,0.00040735747,0.7459614,0.000090854686,0.00009416266,0.00028015056,0.02911628,0.00015118968,0.007635297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796814,0.00011034054,0.0004902372,0.0007251892,0.00028967962,0.00041644144],"domain_scores_gemma":[0.99610245,0.0012946771,0.00034534212,0.0020521453,0.0000961864,0.000109223016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033760385,0.00034508764,0.00085978524,0.00065728696,0.00020483484,0.000061064195,0.00060271926,0.00013104819,0.0001744729],"category_scores_gemma":[0.0009402334,0.0002530277,0.0003396757,0.0014099535,0.0000787773,0.00038067263,0.00028287215,0.000078155084,0.000027141716],"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":[0.0018679749,0.005569936,0.09192431,0.0010383043,0.11023361,0.0009319547,0.009700415,0.009482393,0.025802823,0.08716766,0.32429937,0.33198124],"study_design_scores_gemma":[0.0009582211,0.00024237142,0.003205728,0.0001674686,0.010211303,0.0000037831699,0.0012121705,0.8775152,0.0028678486,0.09745752,0.0052239303,0.0009344314],"about_ca_topic_score_codex":0.00012381023,"about_ca_topic_score_gemma":0.00041014102,"teacher_disagreement_score":0.8680328,"about_ca_system_score_codex":0.00018850343,"about_ca_system_score_gemma":0.000045236673,"threshold_uncertainty_score":0.9999922},"labels":[],"label_agreement":null},{"id":"W4386404572","doi":"10.1093/biostatistics/kxad022","title":"Variable selection in high dimensions for discrete-outcome individualized treatment rules: Reducing severity of depression symptoms","year":2023,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","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":"Université de Montréal; McGill University","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Depression (economics); Outcome (game theory); Feature selection; Selection (genetic algorithm); Variable (mathematics); Econometrics; Medicine; Statistics; Computer science; Internal medicine; Artificial intelligence; Mathematics; Mathematical economics; Economics","score_opus":0.10470571346149896,"score_gpt":0.41863948485896896,"score_spread":0.31393377139747003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386404572","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":[0.3295379,0.000016902739,0.6671747,0.00003204938,0.00012815309,0.0010488615,0.0014813003,0.00044006776,0.00014005078],"genre_scores_gemma":[0.40534538,0.000021150081,0.59410495,0.0000070123433,0.000018460492,0.00015678357,0.00016003213,0.000029669007,0.00015657986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867433,0.00007252917,0.00053276046,0.0002611017,0.00017469321,0.00028455644],"domain_scores_gemma":[0.99797374,0.0014183318,0.0002419153,0.00020994798,0.000102517995,0.000053576317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031329435,0.0001810413,0.00038749777,0.00019465697,0.000090752124,0.000014730357,0.00009402465,0.00012493841,0.000024040126],"category_scores_gemma":[0.0013738928,0.00015590171,0.00004265869,0.0004006488,0.00004726927,0.00008638029,0.000051309682,0.000084537045,0.0000041066205],"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":[0.00021331903,0.00058716687,0.04112671,0.0007132052,0.00014040878,0.000010785102,0.0015385429,0.00039751688,0.044512883,0.89795536,0.0027530396,0.010051091],"study_design_scores_gemma":[0.0013388749,0.00043915046,0.011983367,0.0003092057,0.0001351202,0.0000043459195,0.00014202681,0.0051404773,0.038294937,0.941454,0.00043237425,0.0003261547],"about_ca_topic_score_codex":0.00026677514,"about_ca_topic_score_gemma":0.0000414387,"teacher_disagreement_score":0.0758075,"about_ca_system_score_codex":0.00021102409,"about_ca_system_score_gemma":0.00006530483,"threshold_uncertainty_score":0.6357487},"labels":[],"label_agreement":null},{"id":"W4386518242","doi":"10.1353/obs.2023.a906627","title":"Using Pilot Data for Power Analysis of Observational Studies for the Estimation of Dynamic Treatment Regimes","year":2023,"lang":"en","type":"article","venue":"Observational Studies","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Observational study; Sample size determination; A priori and a posteriori; Computer science; Outcome (game theory); Sample (material); Set (abstract data type); Power analysis; Population; Range (aeronautics); Value (mathematics); Econometrics; Statistics; Data mining; Medicine; Mathematics; Machine learning; Algorithm; Engineering","score_opus":0.8646860751030502,"score_gpt":0.5938313047322161,"score_spread":0.27085477037083405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386518242","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":[0.48300526,0.0038781893,0.4998415,0.004672225,0.00030262637,0.0031251966,0.004859354,0.0002859044,0.000029766039],"genre_scores_gemma":[0.47528577,0.0010829864,0.52055883,0.00007773585,0.00004403232,0.00088521827,0.0015099719,0.000036761878,0.0005187023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985761,0.00003198152,0.00063983887,0.00027390034,0.00031512402,0.00016303218],"domain_scores_gemma":[0.98658293,0.011213753,0.0005604507,0.0005285938,0.001101909,0.000012332626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006705007,0.00018063413,0.0006413213,0.00017475252,0.00024667094,0.000008061091,0.00028061226,0.000032482443,0.0000042422153],"category_scores_gemma":[0.005709634,0.00012242106,0.00014727912,0.0008975262,0.00020129154,0.00026138758,0.0001893967,0.000028424112,2.8906837e-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":[0.00033642436,0.00054298923,0.0071498523,0.0009935317,0.030743603,5.709955e-7,0.0032845698,0.06309891,0.0029738087,0.8747246,0.012289935,0.0038611658],"study_design_scores_gemma":[0.0004995386,0.0004508621,0.03867009,0.00014328278,0.0035219064,2.6220133e-7,0.0025613445,0.44429854,0.0006966102,0.50843436,0.00051371317,0.00020952747],"about_ca_topic_score_codex":0.000012576693,"about_ca_topic_score_gemma":0.00011898376,"teacher_disagreement_score":0.38119963,"about_ca_system_score_codex":0.00018103998,"about_ca_system_score_gemma":0.00007463536,"threshold_uncertainty_score":0.6835378},"labels":[],"label_agreement":null},{"id":"W4386655763","doi":"10.48550/arxiv.2309.05639","title":"Forecasted Treatment Effects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; McMaster University","keywords":"Environmental science","score_opus":0.43589951981110575,"score_gpt":0.30973709825296974,"score_spread":0.126162421558136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386655763","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":[0.5594378,0.000031954045,0.42902377,0.00005728678,0.0006014394,0.001717819,0.00007161581,0.0037490544,0.0053092623],"genre_scores_gemma":[0.9813791,0.0002556606,0.005866208,0.000018104818,0.0000823547,0.00001421786,0.00004556626,0.00009571015,0.012243068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983583,0.00012428407,0.00021290402,0.00083267863,0.00007512084,0.00039672997],"domain_scores_gemma":[0.997542,0.0008187791,0.0002689458,0.001116347,0.00011003231,0.00014390118],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013838358,0.00045789249,0.0005653163,0.00026994676,0.00009025676,0.000031738142,0.0004932623,0.0004265149,0.000044348348],"category_scores_gemma":[0.00022878744,0.00047021837,0.00028459137,0.00034220138,0.000100346915,0.000108299086,0.00071394764,0.00040442325,0.00020846569],"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":[0.00013714156,0.0005324136,0.002078261,0.0011135223,0.00075282215,0.0026946948,0.0005264298,0.009680696,0.00029877305,0.9753929,0.0036506474,0.0031417354],"study_design_scores_gemma":[0.00045238563,0.0002316659,0.00017316642,0.00031070694,0.00027711486,0.0000027915999,0.00006039386,0.011065575,0.003157922,0.98346764,0.00031044616,0.00049017067],"about_ca_topic_score_codex":0.00013057435,"about_ca_topic_score_gemma":0.00016244448,"teacher_disagreement_score":0.42315757,"about_ca_system_score_codex":0.0007148007,"about_ca_system_score_gemma":0.00010735736,"threshold_uncertainty_score":0.99977493},"labels":[],"label_agreement":null},{"id":"W4386738802","doi":"10.1088/1742-6596/2580/1/012044","title":"Instrumental variables matter: towards causal inference using deep learning","year":2023,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","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":"University of Toronto; University of Alberta","funders":"","keywords":"Causal inference; Inference; Artificial intelligence; Computer science; Machine learning; Instrumental variable; Casual; Artificial neural network; Causal model; Field (mathematics); Outcome (game theory); Econometrics; Mathematics; Statistics","score_opus":0.1313180717800485,"score_gpt":0.38890661842647195,"score_spread":0.25758854664642344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386738802","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":[0.5671925,0.00002482214,0.42954135,0.00019430657,0.00038300976,0.00017421486,0.000013216413,0.00029190397,0.0021846783],"genre_scores_gemma":[0.9475922,0.00015645573,0.05164814,0.000035159133,0.00025310385,0.0000064594005,0.0000066280486,0.000049027625,0.00025279954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788,0.00014345892,0.0007516383,0.00021146952,0.0005616405,0.00045179308],"domain_scores_gemma":[0.99783635,0.0002888722,0.0008793084,0.00025015988,0.0006099936,0.0001352929],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051550305,0.00032007528,0.0006125776,0.00019565005,0.00020177121,0.00018350886,0.00044314086,0.00012406983,0.00026548145],"category_scores_gemma":[0.00050303136,0.00028855962,0.00014610098,0.00054731086,0.00022938292,0.0016467283,0.00025062522,0.00068655744,0.000039233397],"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":[0.00022123668,0.00027308706,0.0156019,0.0005004144,0.00038816253,0.00021645172,0.0070198844,0.0018294071,0.15419088,0.6586829,0.00065886613,0.16041681],"study_design_scores_gemma":[0.00034593864,0.0004102792,0.0010095574,0.00044946652,0.00009120443,0.00015488073,0.0027433857,0.001510802,0.17276382,0.8197261,0.00035019955,0.00044433223],"about_ca_topic_score_codex":0.000026291345,"about_ca_topic_score_gemma":0.000009819434,"teacher_disagreement_score":0.38039973,"about_ca_system_score_codex":0.00014225987,"about_ca_system_score_gemma":0.0003278748,"threshold_uncertainty_score":0.99995667},"labels":[],"label_agreement":null},{"id":"W4386790508","doi":"10.31234/osf.io/k2gzp","title":"The Causal Cookbook: Recipes for Propensity Scores, G-Computation, and Doubly Robust Standardization","year":2023,"lang":"en","type":"preprint","venue":"","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":"Université de Montréal","funders":"Institut de Valorisation des Données","keywords":"Standardization; Propensity score matching; Computation; Computer science; Econometrics; Statistics; Mathematics; Algorithm; Operating system","score_opus":0.34445286847481943,"score_gpt":0.4287171338974771,"score_spread":0.08426426542265769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386790508","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":[0.0021984826,0.00007114182,0.99171114,0.00092007197,0.00029108903,0.002833108,0.00010909286,0.0011582026,0.0007076753],"genre_scores_gemma":[0.06221073,0.0006828953,0.92461544,0.00012248298,0.00036964187,0.0014525187,0.00034409665,0.00023482315,0.009967389],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983171,0.00008341713,0.00051749544,0.0004981429,0.00030752012,0.00027632335],"domain_scores_gemma":[0.9969694,0.0013723844,0.00036697372,0.00044999178,0.0007784642,0.00006275918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011512262,0.0002955652,0.0004046133,0.0000788838,0.00038074475,0.0002904692,0.00023946489,0.00025372033,0.0000056761423],"category_scores_gemma":[0.0014632462,0.00020244921,0.0000695341,0.00009122983,0.00017309132,0.000114302726,0.0005714753,0.00034091997,0.0000032620933],"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":[0.0003926011,0.000086882384,0.0006428118,0.0017997926,0.00032469755,0.000010090782,0.00090314,0.019533973,0.00019789352,0.7632247,0.19427486,0.018608524],"study_design_scores_gemma":[0.00022963552,0.00007701224,0.00022661043,0.0002609613,0.00006387278,0.0000035281716,0.000051093633,0.008182605,0.0014697502,0.9872841,0.001845712,0.00030512427],"about_ca_topic_score_codex":0.000061459876,"about_ca_topic_score_gemma":0.0007156632,"teacher_disagreement_score":0.22405936,"about_ca_system_score_codex":0.00014621408,"about_ca_system_score_gemma":0.0001975802,"threshold_uncertainty_score":0.82556397},"labels":[],"label_agreement":null},{"id":"W4386878567","doi":"10.1002/sim.9899","title":"Addressing missing data in the estimation of time‐varying treatments in comparative effectiveness research","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"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":"Medical Research Council; Medical Research Council Canada","keywords":"Missing data; Inverse probability weighting; Imputation (statistics); Weighting; Confounding; Statistics; Inverse probability; Covariate; Econometrics; Computer science; Mathematics; Medicine; Posterior probability; Propensity score matching; Bayesian probability","score_opus":0.6914773159287642,"score_gpt":0.6378653717663129,"score_spread":0.0536119441624513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386878567","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":[0.45630333,0.0002246032,0.53523004,0.00052076904,0.00010277273,0.0027128484,0.00035322004,0.00013849084,0.0044139195],"genre_scores_gemma":[0.88146126,0.00003821154,0.118032254,0.000008792105,0.000017345903,0.000061173654,0.0003497207,0.000014669997,0.000016550224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974968,0.0010057369,0.00046761104,0.00023860346,0.00053333864,0.0002579532],"domain_scores_gemma":[0.98510766,0.014187366,0.00011828911,0.000484072,0.00008180651,0.000020809906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006176893,0.00011296058,0.0004015633,0.0005147202,0.000052267882,0.000009978951,0.0003671461,0.000050048773,0.00001840856],"category_scores_gemma":[0.007224138,0.00008088804,0.0000051109273,0.0012550624,0.00029113668,0.00013182312,0.00013398782,0.00038336514,0.0000057073757],"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":[0.0012450087,0.0025635622,0.042805873,0.007565953,0.0002049347,0.0025544444,0.18108334,0.012623332,0.05070772,0.34557292,0.019977687,0.33309522],"study_design_scores_gemma":[0.0010148403,0.00018014542,0.018870894,0.0037105363,0.000015631256,0.0000030817034,0.0016108865,0.18000013,0.0013160366,0.79318005,0.0000049599366,0.00009283982],"about_ca_topic_score_codex":0.0003154903,"about_ca_topic_score_gemma":0.00014739487,"teacher_disagreement_score":0.44760713,"about_ca_system_score_codex":0.00016934985,"about_ca_system_score_gemma":0.00006221633,"threshold_uncertainty_score":0.864849},"labels":[],"label_agreement":null},{"id":"W4386937233","doi":"10.54254/2755-2721/6/20230930","title":"Multi-treatment casual analysis using improved meta learner and uplift tree","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","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":"McMaster University","funders":"","keywords":"Causal inference; Causality (physics); Computer science; Inference; Machine learning; Artificial intelligence; Focus (optics); Casual; Tree (set theory); Causal model; Process (computing); Econometrics; Mathematics; Statistics","score_opus":0.14686260789798092,"score_gpt":0.3694765840489,"score_spread":0.22261397615091907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386937233","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":[0.28338757,0.00006109963,0.7160286,0.000013583212,0.000009216983,0.00013523173,0.000007176672,0.0003261732,0.00003135422],"genre_scores_gemma":[0.7247898,0.000011705529,0.27507415,0.000008216694,0.000014208807,0.000039090075,0.000017011289,0.00001555712,0.000030217543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999421,0.000004759532,0.00015154491,0.00019587556,0.00008466521,0.00014216328],"domain_scores_gemma":[0.99954975,0.00025935375,0.000039210707,0.00007654412,0.000022727141,0.000052400817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008367411,0.00014636354,0.00026569923,0.00018616804,0.000056932942,0.000028310678,0.000031606804,0.00004043074,0.0000051106604],"category_scores_gemma":[0.000017519034,0.00012712157,0.000054364085,0.00032851895,0.000018948525,0.000047936264,0.000044734537,0.000055564884,0.0000013000256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010406594,0.00006098881,0.00015605807,0.00007407137,0.003504178,0.0000110038945,0.0007392783,0.86529297,0.026503451,0.09394309,0.0000070520423,0.009697434],"study_design_scores_gemma":[0.00022719933,0.000017739918,0.0011099743,0.000003336154,0.0007775658,0.0000036159252,0.000060513958,0.9841405,0.0005602782,0.01292652,0.000025307036,0.00014745219],"about_ca_topic_score_codex":0.000014445505,"about_ca_topic_score_gemma":0.0000059054664,"teacher_disagreement_score":0.44140226,"about_ca_system_score_codex":0.000029744022,"about_ca_system_score_gemma":0.000009701294,"threshold_uncertainty_score":0.5183868},"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":"W4387362492","doi":"10.1080/00031305.2023.2267597","title":"Causal Quartets: Different Ways to Attain the Same Average Treatment Effect","year":2023,"lang":"en","type":"article","venue":"The American Statistician","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":"Science North","funders":"","keywords":"Variation (astronomy); Context (archaeology); Simple (philosophy); Epistemology; Mathematical economics; Mathematics; Computer science; Econometrics; Sociology; Philosophy; History; Physics","score_opus":0.10626714617887423,"score_gpt":0.4161824036868427,"score_spread":0.30991525750796844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387362492","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":[0.5336497,0.000013459196,0.45855114,0.0033942824,0.00014843333,0.0017623196,0.00043639864,0.0011492642,0.00089503784],"genre_scores_gemma":[0.9893496,0.000045396166,0.007827071,0.001204652,0.00016421107,0.00071533513,0.00003576782,0.00008523885,0.00057274365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979881,0.00037219436,0.00033088913,0.00032994733,0.00036820988,0.0006106565],"domain_scores_gemma":[0.992121,0.0065979906,0.0002261863,0.0008960207,0.000042262538,0.00011657344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044525668,0.000374517,0.0005718151,0.00010038352,0.00031631324,0.00006437115,0.000463023,0.000024869434,0.00007694253],"category_scores_gemma":[0.00081356685,0.00017772331,0.00009719453,0.0006172624,0.00037276663,0.000037385882,0.00013483877,0.00019399232,0.00038337673],"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":[0.00037123862,0.00027877442,0.0010284835,0.0000770482,0.0004306315,0.00023991051,0.01276988,0.00031118467,0.0058224658,0.4155166,0.08387211,0.4792817],"study_design_scores_gemma":[0.0009944552,0.011090647,0.02729815,0.0001810887,0.0004747386,0.00003615129,0.0041236337,0.0036241256,0.009862268,0.9261406,0.014802052,0.0013720873],"about_ca_topic_score_codex":0.0009384574,"about_ca_topic_score_gemma":0.0007961535,"teacher_disagreement_score":0.510624,"about_ca_system_score_codex":0.00029804374,"about_ca_system_score_gemma":0.000032200667,"threshold_uncertainty_score":0.72473466},"labels":[],"label_agreement":null},{"id":"W4387392109","doi":"10.1002/bimj.202300027","title":"On “Reflections on the concept of optimality of single decision point treatment regimes”","year":2023,"lang":"en","type":"article","venue":"Biometrical Journal","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":"Université Laval; McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"CONTEST; Point (geometry); Computer science; Mathematical economics; Operations research; Single point; Economics; Epistemology; Mathematics; Artificial intelligence; Philosophy; Political science; Law","score_opus":0.48936684789558677,"score_gpt":0.5017442050474353,"score_spread":0.012377357151848567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387392109","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":[0.73276633,0.00010046512,0.25457987,0.0016861319,0.0003474143,0.00055743475,0.000064973116,0.00025972674,0.009637637],"genre_scores_gemma":[0.97020173,0.000071860224,0.029454533,0.000040717638,0.000048303795,0.000007304806,0.0000013508542,0.000014542447,0.00015965206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861985,0.00012456108,0.0004756207,0.00012612362,0.00047485094,0.00017899365],"domain_scores_gemma":[0.9944501,0.004642651,0.0003466495,0.00030154412,0.0001784648,0.000080587066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005847059,0.00012087032,0.00027740072,0.00092220906,0.00010118925,0.000018183127,0.00019554675,0.00007782556,0.00012309308],"category_scores_gemma":[0.0034162318,0.000066551605,0.00017886539,0.0028374179,0.00012535695,0.00005057789,0.00004335822,0.00017443112,0.00001616739],"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":[0.0006495043,0.0048816004,0.0001457955,0.00002901239,0.00031953675,0.00006788268,0.0010582659,0.00031895944,0.0668339,0.73031396,0.03460331,0.16077828],"study_design_scores_gemma":[0.0004949218,0.0050545437,0.00044669793,0.00019765369,0.0000374041,0.00003817941,0.00024360903,0.000082253064,0.3055339,0.68664587,0.0011045426,0.0001204379],"about_ca_topic_score_codex":0.0000053449703,"about_ca_topic_score_gemma":4.7711404e-7,"teacher_disagreement_score":0.23869999,"about_ca_system_score_codex":0.00027044452,"about_ca_system_score_gemma":0.00003980611,"threshold_uncertainty_score":0.40897954},"labels":[],"label_agreement":null},{"id":"W4387493333","doi":"10.1007/s11121-023-01590-6","title":"Sample Size Requirements to Test Subgroup-Specific Treatment Effects in Cluster-Randomized Trials","year":2023,"lang":"en","type":"article","venue":"Prevention Science","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; Patient-Centered Outcomes Research Institute","keywords":"CRTS; Sample size determination; Statistics; Subgroup analysis; Randomized controlled trial; Econometrics; Restricted randomization; Treatment and control groups; Statistical power; Mathematics; Medicine; Randomization; Computer science; Confidence interval; Internal medicine","score_opus":0.36915600751963046,"score_gpt":0.5157750821082986,"score_spread":0.14661907458866813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387493333","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":[0.47408977,0.000032616328,0.5167082,0.00049864483,0.0004326917,0.0066056782,0.00001695198,0.0007891455,0.00082631456],"genre_scores_gemma":[0.8211932,0.000091616836,0.17632787,0.000052307165,0.000044108412,0.00145699,0.000003640665,0.000019977684,0.00081029267],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996886,0.00060323183,0.00090090046,0.00053133396,0.000608329,0.0004701973],"domain_scores_gemma":[0.97103757,0.027901951,0.00031020245,0.0005018621,0.000112173875,0.0001362697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0128616495,0.00019845027,0.0008152087,0.00043289518,0.00013853343,0.00010507375,0.00038520122,0.00005139615,0.000087570705],"category_scores_gemma":[0.0763602,0.00015434544,0.00017498342,0.0020068865,0.00016843212,0.00045023512,0.00017529803,0.00006946215,0.00012993673],"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":[0.010117065,0.0042950287,0.0039433246,0.00046094222,0.00011446506,0.000075073316,0.0069217323,0.00036532126,0.47202167,0.26567224,0.004730931,0.2312822],"study_design_scores_gemma":[0.021249136,0.00044991047,0.001047758,0.00027217434,0.000027304519,0.0000013948595,0.000059978447,0.00077596866,0.048194967,0.9273309,0.0003504583,0.00024004334],"about_ca_topic_score_codex":0.00003595573,"about_ca_topic_score_gemma":0.00005629285,"teacher_disagreement_score":0.66165864,"about_ca_system_score_codex":0.00043807592,"about_ca_system_score_gemma":0.000095780335,"threshold_uncertainty_score":0.93142},"labels":[],"label_agreement":null},{"id":"W4387566508","doi":"10.1017/9781316718636.014","title":"Mixing Models","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","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":"University of British Columbia","funders":"","keywords":"Mixing (physics); Computer science; Data science; Observational study; Inference; Artificial intelligence; Machine learning; Mathematics; Statistics; Physics","score_opus":0.20050221067260104,"score_gpt":0.310172993102039,"score_spread":0.10967078242943795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387566508","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012378699,0.000021709737,0.043756083,0.0000081898,0.0001322133,0.0004790147,0.00021418574,0.0018631156,0.9535131],"genre_scores_gemma":[0.00016766283,0.00011882706,0.0059708706,0.000027319844,0.000094744166,0.0000019926779,0.000030663607,0.00016309063,0.99342483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984759,0.000028239569,0.00025638007,0.0005406725,0.00034003876,0.00035877334],"domain_scores_gemma":[0.9982003,0.0003315282,0.00030076227,0.00081943104,0.00019689451,0.00015109264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014649279,0.00046006814,0.00055669306,0.00025959205,0.00015186056,0.00003302475,0.0006163966,0.0005332074,0.0000048563675],"category_scores_gemma":[0.000041805626,0.0005594351,0.00024839118,0.000010668622,0.00019844584,0.00016478068,0.000628346,0.0006710469,0.0000332789],"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":[0.000019378163,0.000004537886,4.9720914e-8,0.00012938693,0.00008741095,0.00031173928,0.000037714086,0.0000049806604,0.000038130347,0.9545687,0.04421762,0.0005803703],"study_design_scores_gemma":[0.0004631121,0.00008482131,3.3111996e-7,0.0011025147,0.00045419388,0.000024375004,0.00006420156,0.00072339684,0.0015544676,0.2294051,0.7646914,0.001432091],"about_ca_topic_score_codex":0.00003971889,"about_ca_topic_score_gemma":0.0000028735992,"teacher_disagreement_score":0.7251636,"about_ca_system_score_codex":0.00027931292,"about_ca_system_score_gemma":0.00008092212,"threshold_uncertainty_score":0.9996857},"labels":[],"label_agreement":null},{"id":"W4387664142","doi":"10.1117/12.3009382","title":"Application of propensity score and random forest in the causal inference: the causality of stroke","year":2023,"lang":"en","type":"article","venue":"","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 Alberta; University of Toronto","funders":"","keywords":"Propensity score matching; Causal inference; Causality (physics); Stroke (engine); Weighting; Matching (statistics); Heart disease; Random forest; Disease; Medicine; Statistics; Econometrics; Computer science; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.19599021130830027,"score_gpt":0.40765954338558885,"score_spread":0.21166933207728858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387664142","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":[0.9389572,0.0000096545655,0.058362503,0.0003011763,0.000008398277,0.0010773266,0.000014136762,0.00008311639,0.001186458],"genre_scores_gemma":[0.99837816,0.00003422785,0.001340772,0.00002822202,0.000009125583,0.00012855604,0.0000053644585,0.0000072809858,0.00006828045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902165,0.00013316287,0.00034912492,0.00013405304,0.00023095783,0.00013105848],"domain_scores_gemma":[0.9978538,0.0013884561,0.00018118591,0.00044860903,0.000112610614,0.000015351618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013920071,0.00009633331,0.00024674775,0.000054700322,0.00004122311,0.0000100100415,0.00023584881,0.000059097278,0.0000064529795],"category_scores_gemma":[0.0007413741,0.000047856527,0.000028811412,0.0003239451,0.0002389322,0.00008525079,0.00011692494,0.00015196862,0.0000014652296],"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":[0.00009909411,0.00011330146,0.30177465,0.00025499373,0.000020876254,0.000001729182,0.0019608028,0.000038425977,0.008412775,0.6830594,0.00040224893,0.00386171],"study_design_scores_gemma":[0.00064462813,0.00010527493,0.2637392,0.000055663564,0.000030634747,0.0000033798517,0.00087783864,0.0019445078,0.018072115,0.71435016,0.000059746042,0.000116845324],"about_ca_topic_score_codex":0.00048367569,"about_ca_topic_score_gemma":0.0018880119,"teacher_disagreement_score":0.05942094,"about_ca_system_score_codex":0.000012204963,"about_ca_system_score_gemma":0.000032629185,"threshold_uncertainty_score":0.19515325},"labels":[],"label_agreement":null},{"id":"W4387736567","doi":"10.1186/s12874-023-02062-9","title":"Longitudinal plasmode algorithms to evaluate statistical methods in realistic scenarios: an illustration applied to occupational epidemiology","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"The Quebec Population Health Research Network; Université Laval","funders":"Medical Research Council; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Medical Research Council Canada; Canadian Institutes of Health Research; Université Laval","keywords":"Covariate; Marginal structural model; Estimator; Statistics; Confidence interval; Nonparametric statistics; Coverage probability; Weighting; Computer science; Algorithm; Inverse probability; Inverse probability weighting; Mathematics; Medicine; Bayesian probability","score_opus":0.9221876644056204,"score_gpt":0.7397021868237371,"score_spread":0.18248547758188327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387736567","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":[0.016508283,0.000009371537,0.97900546,0.0021095797,0.0001803495,0.0012931477,0.000049915034,0.00034590677,0.00049797766],"genre_scores_gemma":[0.010606172,0.00002824249,0.9867672,0.0005235863,0.0002881592,0.0014455497,0.00015453559,0.000054941527,0.00013164886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9418135,0.049878333,0.0019591565,0.0016672503,0.0024270518,0.0022546747],"domain_scores_gemma":[0.75794554,0.23926508,0.00013008008,0.0007706655,0.0005414371,0.0013471707],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15162396,0.00030872968,0.0012018967,0.0013928362,0.00017864878,0.000022399157,0.0008854395,0.00065864733,0.0010757901],"category_scores_gemma":[0.5813287,0.00027285778,0.00006298727,0.00198039,0.0006962246,0.00010267201,0.0006733701,0.0015436256,0.0002728173],"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":[0.001006623,0.00017340052,0.0015426229,0.0001590946,0.000024143414,0.0001012025,0.00058121356,0.0020404845,0.0018716342,0.85029966,0.005397524,0.13680238],"study_design_scores_gemma":[0.00048121443,0.00084785774,0.022612022,0.00009542462,0.000013812563,0.000031801177,0.0003516716,0.076512784,0.00051016966,0.8977638,0.00049258815,0.00028686126],"about_ca_topic_score_codex":0.0007366828,"about_ca_topic_score_gemma":0.0043624714,"teacher_disagreement_score":0.42970473,"about_ca_system_score_codex":0.00046193597,"about_ca_system_score_gemma":0.0015744241,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W4387808596","doi":"10.3138/cpp.2022-058","title":"A Scientific Approach to Addressing Social Issues Using Administrative Data","year":2023,"lang":"fr","type":"article","venue":"Canadian Public Policy","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":true,"route_about_ca":true,"ca_institutions":"McMaster University; Carleton University; University of British Columbia","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.7379816920415992,"score_gpt":0.5430589899139062,"score_spread":0.19492270212769303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387808596","genre_codex":"commentary","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":[0.08423693,0.00397878,0.06913357,0.43079442,0.0059361784,0.007904262,0.04889373,0.00496893,0.3441532],"genre_scores_gemma":[0.73057425,0.00004928696,0.16704468,0.0035473702,0.0069398745,0.00019490093,0.0027175888,0.0004107736,0.08852125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954708,0.00026635217,0.0005471817,0.0010343143,0.0005158708,0.0021654652],"domain_scores_gemma":[0.9957426,0.00016706511,0.00020764644,0.0016248898,0.00043379996,0.0018239892],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015689767,0.00043366337,0.0005127141,0.0025326402,0.001560303,0.00207765,0.001897033,0.00039969568,0.00021564325],"category_scores_gemma":[0.0055494336,0.0005330675,0.00008403508,0.0062128413,0.0009550662,0.0016802163,0.00075493596,0.00049643376,0.00043367266],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018269326,0.000057734742,0.000029817575,0.00018521218,0.00005739028,0.000044614495,0.0038338471,0.000004522241,0.00021968115,0.6908154,0.2800099,0.024740053],"study_design_scores_gemma":[0.00019300503,0.000049542716,0.0002490211,0.00030492287,0.0000693234,0.00007142939,0.0031332239,0.013440313,0.0002812415,0.14131528,0.8399096,0.000983098],"about_ca_topic_score_codex":0.16596946,"about_ca_topic_score_gemma":0.16375865,"teacher_disagreement_score":0.64633733,"about_ca_system_score_codex":0.0023021856,"about_ca_system_score_gemma":0.018760877,"threshold_uncertainty_score":0.9997395},"labels":[],"label_agreement":null},{"id":"W4387878214","doi":"10.3233/faia230655","title":"Hydranet: A Neural Network for the Estimation of Multi-Valued Treatment Effects","year":2023,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","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":"Artificial Intelligence in Medicine (Canada)","funders":"Ministerio de Ciencia e Innovación; Generalitat de Catalunya","keywords":"Benchmarking; Estimator; Artificial neural network; Computer science; Inference; Binary number; Machine learning; Artificial intelligence; Estimation; Causal inference; Range (aeronautics); Focus (optics); Data mining; Mathematics; Econometrics; Engineering; Statistics","score_opus":0.17950489085210808,"score_gpt":0.39937386434686517,"score_spread":0.2198689734947571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387878214","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":[0.000016410571,0.0006032295,0.99499744,0.00007594063,0.00015943397,0.0032667534,0.000060252234,0.0001193094,0.0007012285],"genre_scores_gemma":[0.01675703,0.004742688,0.9360954,0.00010170308,0.0007136405,0.0111979535,0.00025581114,0.0002680107,0.02986777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885404,0.000019914914,0.0005222582,0.0002969647,0.00011003077,0.00019681496],"domain_scores_gemma":[0.99818975,0.0010511334,0.00028241242,0.00037939215,0.000061508596,0.00003578524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026111165,0.00024176705,0.00039815225,0.000109133885,0.00014031521,0.000021269463,0.00018757612,0.00018691087,0.0000042944166],"category_scores_gemma":[0.00012010353,0.00018957858,0.00010768625,0.00010214858,0.0002324736,0.000043631935,0.000035166093,0.00015097308,0.0000059421454],"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":[0.00002169429,0.000033486238,0.000002760887,0.00007842365,0.00003789022,4.0742137e-7,0.00013801447,0.0046888688,0.000009532435,0.7077208,0.00045447814,0.28681362],"study_design_scores_gemma":[0.00002793479,0.00009481427,0.0000023361924,0.00011478676,0.00011205387,5.1706525e-7,0.00006195047,0.1647562,0.0010926811,0.83221006,0.0013837684,0.00014287095],"about_ca_topic_score_codex":0.000018835946,"about_ca_topic_score_gemma":0.00010514542,"teacher_disagreement_score":0.28667074,"about_ca_system_score_codex":0.000074859934,"about_ca_system_score_gemma":0.000029064917,"threshold_uncertainty_score":0.77307904},"labels":[],"label_agreement":null},{"id":"W4388083703","doi":"10.33137/utjph.v4i1.41675","title":"Modeling Longitudinal Outcomes in a Small Matched-Pair Sample Motivated by Cardiovascular Data: A Simulation Study","year":2023,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","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":"Ted Rogers Centre for Heart Research; University Health Network; Public Health Ontario; University of Toronto","funders":"","keywords":"Generalized estimating equation; Gee; Statistics; Consistency (knowledge bases); Correlation; Sample size determination; Independence (probability theory); Mathematics; Econometrics; Estimating equations; Standard deviation; Propensity score matching; Sample (material); Maximum likelihood; Physics","score_opus":0.4156574511401765,"score_gpt":0.4214156494535488,"score_spread":0.00575819831337232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388083703","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":[0.5407084,0.0001627866,0.45833018,0.00037351827,0.000031812247,0.00026407055,0.00004443423,0.000070459995,0.000014323365],"genre_scores_gemma":[0.9716222,0.00017278189,0.028107632,0.000012134747,0.000016994263,1.7738978e-7,0.00002110887,0.000014939418,0.00003197705],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980489,0.00041569627,0.0005582234,0.00021747255,0.00043326488,0.0003264405],"domain_scores_gemma":[0.9980248,0.0004835621,0.0004241702,0.00052933156,0.00035675694,0.00018134384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004400334,0.0001396365,0.000740685,0.00018840205,0.00009254138,0.000018128052,0.00061058946,0.00006966669,0.000034879868],"category_scores_gemma":[0.0011983304,0.00014315394,0.00014095052,0.00021010658,0.00003070974,0.001076899,0.0002586431,0.00021883128,7.4748766e-7],"study_design_candidate":"simulation_or_modeling","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":[0.00031862414,0.0068300203,0.6265131,0.0010244517,0.0042185006,0.00039354953,0.056952186,0.23333555,0.000095053314,0.0031137525,0.0044574854,0.062747695],"study_design_scores_gemma":[0.011003237,0.003504525,0.11357491,0.0006828638,0.0004452559,0.000031802607,0.14325614,0.6981828,0.00001568194,0.02340642,0.00466899,0.001227383],"about_ca_topic_score_codex":0.025663197,"about_ca_topic_score_gemma":0.015629923,"teacher_disagreement_score":0.5129382,"about_ca_system_score_codex":0.00086521416,"about_ca_system_score_gemma":0.00034262336,"threshold_uncertainty_score":0.980825},"labels":[],"label_agreement":null},{"id":"W4388095903","doi":"10.1007/978-3-031-35763-3_3","title":"Optimal Transport for Counterfactual Estimation: A Method for Causal Inference","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in systems, decision and control","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"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 du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Covariate; Counterfactual thinking; Causal inference; Dimension (graph theory); Population; Econometrics; Mathematics; Average treatment effect; Quantile; Inference; Variable (mathematics); Instrumental variable; Statistics; Propensity score matching; Computer science; Psychology; Artificial intelligence; Combinatorics; Medicine; Social psychology","score_opus":0.28676399856255574,"score_gpt":0.5008328927146684,"score_spread":0.2140688941521126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388095903","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":[0.000035278124,0.002100851,0.9894921,0.000063721796,0.0007329556,0.004185536,0.0008137102,0.00028713277,0.0022886875],"genre_scores_gemma":[0.071862936,0.0031323005,0.78297836,0.00024256694,0.0007970374,0.010074051,0.00013789827,0.0005206126,0.13025427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99713403,0.000040857223,0.0013594824,0.00066363893,0.0004282491,0.00037376717],"domain_scores_gemma":[0.9838356,0.014485695,0.00053408154,0.00041203186,0.0006558688,0.00007676167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017999385,0.0005702852,0.0018353226,0.00027667152,0.00015993578,0.00004343047,0.00023924452,0.00043664855,0.0000098200735],"category_scores_gemma":[0.0023704348,0.0004757268,0.00019207169,0.000046463883,0.00017276008,0.00011645385,0.0000691653,0.00027757842,0.0000068624954],"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":[0.0010790608,0.000037047506,0.000012653149,0.0023651784,0.0007957104,0.000040805502,0.001695892,0.0008038566,0.000016837292,0.9527283,0.008269536,0.032155145],"study_design_scores_gemma":[0.0037992368,0.0007799023,0.0000052723767,0.0044087735,0.00047372183,0.00002822285,0.0011850597,0.023959223,0.000014235128,0.93456674,0.02991552,0.00086411135],"about_ca_topic_score_codex":0.000008065152,"about_ca_topic_score_gemma":0.000085793414,"teacher_disagreement_score":0.20651379,"about_ca_system_score_codex":0.00017969012,"about_ca_system_score_gemma":0.0000924194,"threshold_uncertainty_score":0.99976945},"labels":[],"label_agreement":null},{"id":"W4388124846","doi":"10.2139/ssrn.4615304","title":"A Lower Bound on the Variance of Treatment Effects Across Sites in Multi-site Randomized Controlled Trials","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Impact","funders":"","keywords":"Estimator; Statistics; Randomized controlled trial; Variance (accounting); Context (archaeology); Mathematics; Econometrics; Bayes' theorem; Upper and lower bounds; Average treatment effect; Randomized experiment; Bayesian probability; Medicine; Geography; Economics; Internal medicine","score_opus":0.1293247085524912,"score_gpt":0.4339198741289803,"score_spread":0.30459516557648914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388124846","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":[0.95188296,0.0011656914,0.042184126,0.00061770226,0.00015076056,0.003681535,0.00000985735,0.00015613135,0.00015124837],"genre_scores_gemma":[0.99249035,0.004546187,0.0008358511,0.000049760816,0.000082571256,0.0005295641,0.0000022848192,0.00003916494,0.0014242819],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943974,0.0021936896,0.001302771,0.00021652681,0.0003013918,0.001588219],"domain_scores_gemma":[0.97642124,0.022089498,0.0010149416,0.0003249934,0.000104166895,0.000045162426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024568144,0.00030508285,0.002699956,0.00017058261,0.00014600737,0.000061610466,0.00025360537,0.00011645313,0.0000225381],"category_scores_gemma":[0.017858576,0.00015097864,0.0007953158,0.00036020414,0.00013019801,0.00010775028,0.00003558737,0.00092474883,0.000023081897],"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":[0.121914506,0.00092167803,0.00017750208,0.000056598263,0.0026776828,0.000052952637,0.0028632903,0.00020890513,0.031180855,0.83553934,0.00012236221,0.0042843027],"study_design_scores_gemma":[0.18272732,0.0008814685,0.000024295408,0.0001861309,0.00019222793,0.000022381437,0.00034177012,0.0010998403,0.0040145093,0.81033796,0.00001881029,0.0001532978],"about_ca_topic_score_codex":0.000037204543,"about_ca_topic_score_gemma":0.0006817911,"teacher_disagreement_score":0.060812812,"about_ca_system_score_codex":0.001046478,"about_ca_system_score_gemma":0.0006621443,"threshold_uncertainty_score":0.99041444},"labels":[],"label_agreement":null},{"id":"W4388398918","doi":"10.1002/sim.9940","title":"Principal stratification for quantile causal effects under partial compliance","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Compute Canada","keywords":"Quantile; Econometrics; Causal inference; Copula (linguistics); Covariate; Missing data; Statistics; Bivariate analysis; Identifiability; Inference; Mathematics; Computer science; Artificial intelligence","score_opus":0.2595680897329376,"score_gpt":0.5012533153693227,"score_spread":0.24168522563638511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388398918","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":[0.009180914,0.00001834423,0.9884038,0.0004037848,0.00031051232,0.0008679812,0.00010928885,0.00031732125,0.0003880369],"genre_scores_gemma":[0.6266121,0.000045942925,0.37169972,0.00013059759,0.00022961022,0.0004488296,0.00028617322,0.000047783953,0.0004992254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986592,0.000060397153,0.000432178,0.00025711875,0.00027390925,0.00031721796],"domain_scores_gemma":[0.99626917,0.00310113,0.00014576563,0.00029484805,0.00012396071,0.00006510942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006582256,0.00015335553,0.0003199563,0.00012106771,0.0000630478,0.000008988714,0.00014766211,0.00007472691,0.000044209897],"category_scores_gemma":[0.0030914245,0.00013585255,0.000014944139,0.0002958722,0.00018205699,0.00005370392,0.000030130332,0.00017128956,0.000022760756],"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":[0.000027168753,0.00003896149,0.00016109516,0.0004155856,0.000010063764,0.000016529097,0.00033597418,0.000044916884,0.0051723025,0.97692174,0.014000094,0.0028555933],"study_design_scores_gemma":[0.0006749341,0.00031781325,0.0027385443,0.00030084973,0.000027260288,0.00000193818,0.00019455138,0.016204257,0.0033470893,0.9755824,0.0004570502,0.00015331178],"about_ca_topic_score_codex":0.000021177104,"about_ca_topic_score_gemma":0.00012733942,"teacher_disagreement_score":0.6174312,"about_ca_system_score_codex":0.00007832233,"about_ca_system_score_gemma":0.000045303805,"threshold_uncertainty_score":0.5539906},"labels":[],"label_agreement":null},{"id":"W4388430092","doi":"10.1515/jci-2022-0032","title":"Identification of in-sample positivity violations using regression trees: The PoRT algorithm","year":2023,"lang":"en","type":"article","venue":"Journal of Causal Inference","topic":"Advanced Causal Inference Techniques","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":"Université de Montréal","funders":"Agence Nationale de la Recherche; Rhode Island State Council on the Arts","keywords":"Covariate; Regression; Sample (material); Identification (biology); Observational study; Algorithm; Statistics; Tree (set theory); Regression analysis; Decision tree; Computer science; Mathematics; Econometrics; Psychology; Artificial intelligence; Biology","score_opus":0.19089771261834143,"score_gpt":0.4657380321503103,"score_spread":0.27484031953196886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388430092","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":[0.4644059,0.000029933568,0.53505075,0.00014206524,0.00011786426,0.00014280796,0.00002056406,0.00004010151,0.00005003461],"genre_scores_gemma":[0.97148615,0.000116543415,0.028269105,0.000012751982,0.00006471591,0.000005142678,0.0000033021597,0.000015093964,0.000027167203],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998068,0.00016365912,0.0010189504,0.00011607255,0.00044616227,0.00018720728],"domain_scores_gemma":[0.9959878,0.0019139834,0.0012342423,0.0003025419,0.00051148486,0.000049969072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001642657,0.0001328162,0.00033089053,0.00033963285,0.000083853745,0.000031094325,0.00028707556,0.00009164933,0.000019081659],"category_scores_gemma":[0.0027205455,0.00008985605,0.00009494118,0.0007714921,0.00010898905,0.0005153227,0.00008249128,0.00035455008,0.000002213306],"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":[0.00013902834,0.00081081863,0.058895946,0.00021397279,0.0001744148,0.00018953363,0.004491966,0.0035372707,0.74955744,0.10430772,0.0012112431,0.07647068],"study_design_scores_gemma":[0.00034402005,0.00020065227,0.06173891,0.0008508728,0.00008222844,0.0000835812,0.0006625966,0.03422857,0.06779629,0.83371294,0.00006965588,0.00022966659],"about_ca_topic_score_codex":0.00005288962,"about_ca_topic_score_gemma":0.00004320637,"teacher_disagreement_score":0.7294052,"about_ca_system_score_codex":0.00010671794,"about_ca_system_score_gemma":0.00017046723,"threshold_uncertainty_score":0.36642233},"labels":[],"label_agreement":null},{"id":"W4388454889","doi":"10.1093/jrsssc/qlad096","title":"Variable selection for individualised treatment rules with discrete outcomes","year":2023,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Observational study; Feature selection; Variable (mathematics); Selection (genetic algorithm); Computer science; Machine learning; Data mining; Mathematics; Statistics","score_opus":0.05987198688175837,"score_gpt":0.3608529226673868,"score_spread":0.3009809357856284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388454889","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":[0.0018764598,0.000005119763,0.9936821,0.0003701731,0.00013903413,0.0006681451,0.0027225271,0.00014827294,0.00038818613],"genre_scores_gemma":[0.018282233,0.000016577966,0.9797005,0.00010526701,0.00012010125,0.00013363478,0.00006756681,0.00007005871,0.0015040268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997923,0.00007444577,0.00070133276,0.00022756998,0.0005923912,0.00048125247],"domain_scores_gemma":[0.99574846,0.00293163,0.00064281304,0.00022750016,0.00030045825,0.00014913316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005470249,0.0003325961,0.0006563365,0.00003880525,0.00042697217,0.00011119258,0.00030403776,0.00012498607,0.00011178781],"category_scores_gemma":[0.0007525412,0.00018868274,0.00016713869,0.0002624653,0.00029031665,0.00011162403,0.00008060877,0.00029808932,0.0000057330294],"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":[0.0003226347,0.000121912635,0.00058388966,0.00013520487,0.0005192711,0.000003906858,0.0005521396,0.00056389,0.00012398961,0.945846,0.04977853,0.0014486153],"study_design_scores_gemma":[0.0012614373,0.0010455172,0.0022483896,0.00004974154,0.00047712427,0.000012031949,0.0005668501,0.0025673206,0.0006834629,0.9857811,0.0050157667,0.00029125827],"about_ca_topic_score_codex":0.00002176683,"about_ca_topic_score_gemma":0.000029396499,"teacher_disagreement_score":0.044762764,"about_ca_system_score_codex":0.00033042656,"about_ca_system_score_gemma":0.00020943535,"threshold_uncertainty_score":0.76942587},"labels":[],"label_agreement":null},{"id":"W4388717130","doi":"10.3899/jrheum.2023-0499","title":"Statistical and Scientific Considerations Concerning the Interpretation, Replicability, and Transportability of Research Findings","year":2023,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observational study; Interpretation (philosophy); Psychology; Intervention (counseling); Population; Affect (linguistics); Statistical analysis; Management science; Cognitive psychology; Computer science; Statistics; Medicine; Mathematics; Environmental health; Engineering; Psychiatry","score_opus":0.24853913203660724,"score_gpt":0.4777099926540065,"score_spread":0.22917086061739925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388717130","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":[0.97326326,0.000099276236,0.024131136,0.0022239215,0.000046538364,0.00017293452,0.000009868176,0.000021928568,0.00003112562],"genre_scores_gemma":[0.9957371,0.00011613767,0.0041120397,0.0000078443345,0.0000015848326,0.0000044660333,6.6040985e-7,0.000005934336,0.00001426137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983416,0.0005874724,0.0005852201,0.00010590372,0.00022983996,0.00014994296],"domain_scores_gemma":[0.98345345,0.015546724,0.00021360134,0.00025437557,0.0004926821,0.00003918596],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008015076,0.000060393562,0.00025376191,0.00011494882,0.0002899031,0.00002884398,0.00014292226,0.000045533983,0.000043308086],"category_scores_gemma":[0.009366604,0.000033778422,0.00002087928,0.00022612333,0.0027254052,0.00009625446,0.00007201729,0.0003798781,8.5742437e-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":[0.00012791189,0.000042111013,0.1438513,0.00024882462,0.000055124,0.0000046465907,0.021955678,0.000017325065,0.0023743755,0.8272283,0.0032715886,0.00082283025],"study_design_scores_gemma":[0.00013248815,0.00011991179,0.009864697,0.00009811337,0.00002500726,0.00060257985,0.0024313768,0.00057796354,0.00072354253,0.9853556,0.00003298381,0.000035696077],"about_ca_topic_score_codex":0.000034790773,"about_ca_topic_score_gemma":0.0001153155,"teacher_disagreement_score":0.15812734,"about_ca_system_score_codex":0.000017577122,"about_ca_system_score_gemma":0.00010431567,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W4388795592","doi":"10.1007/s10742-023-00317-y","title":"Propensity score weighting with survey weighted data when outcomes are binary: a simulation study","year":2023,"lang":"en","type":"article","venue":"Health Services and Outcomes Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"London Health Sciences Centre","funders":"National Cancer Institute; National Institute on Aging; National Cancer Center","keywords":"Propensity score matching; Weighting; Statistics; Observational study; Average treatment effect; Population; Mathematics; Econometrics; Medicine","score_opus":0.8783707654311809,"score_gpt":0.649225151849151,"score_spread":0.2291456135820299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388795592","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":[0.9862556,0.00013318617,0.0071196537,0.0026821431,0.0000860136,0.0029370813,0.0001178536,0.00063237274,0.000036112157],"genre_scores_gemma":[0.85325414,0.0002573722,0.14470707,0.00076466665,0.000056096127,0.000170523,0.0002788073,0.00010407215,0.0004072775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9853398,0.010710771,0.0007966238,0.0010596225,0.0009453862,0.0011477927],"domain_scores_gemma":[0.9716147,0.02513446,0.00048083818,0.0017102612,0.000752198,0.00030753537],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030755555,0.0003532182,0.0013756987,0.00063055963,0.0007362805,0.00011329791,0.00095811475,0.00017454181,0.000036573583],"category_scores_gemma":[0.00311548,0.00023121583,0.000034170684,0.001171438,0.00020265733,0.00054486515,0.0020058432,0.00082943315,0.000018835028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023109376,0.00019363537,0.9899134,0.00097654364,0.00010721055,0.0000536236,0.0036954079,0.000019489104,0.000008467272,0.00074624293,0.00016044872,0.0038944415],"study_design_scores_gemma":[0.00080469,0.0008476855,0.94719416,0.00018341171,0.00001601328,0.000004570345,0.0047885748,0.0077562067,0.000008860022,0.037911486,0.00023542804,0.00024892882],"about_ca_topic_score_codex":0.008103124,"about_ca_topic_score_gemma":0.03883896,"teacher_disagreement_score":0.13758741,"about_ca_system_score_codex":0.00011043427,"about_ca_system_score_gemma":0.00021487074,"threshold_uncertainty_score":0.998502},"labels":[],"label_agreement":null},{"id":"W4388851130","doi":"10.1002/sim.9963","title":"Two‐stage targeted maximum likelihood estimation for mixed aggregate and individual participant data analysis with an application to multidrug resistant tuberculosis","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University Health Centre; Université de Montréal; McGill University; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Aggregate data; Weighting; Computer science; Missing data; Estimation; Tuberculosis; Aggregate (composite); Inverse probability weighting; Meta-analysis; Statistics; Population; Contrast (vision); Medicine; Econometrics; Machine learning; Artificial intelligence; Mathematics; Internal medicine; Estimator; Pathology","score_opus":0.1470997536980372,"score_gpt":0.4430485501490196,"score_spread":0.2959487964509824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388851130","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":[0.06072353,0.000032429387,0.93449014,0.0004479822,0.00002508559,0.0011841087,0.0028402992,0.0002443912,0.000012013902],"genre_scores_gemma":[0.28766167,0.00003345851,0.7074398,0.00006718573,0.000030238483,0.00039052792,0.0043236315,0.00003633802,0.000017180588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782634,0.00010637808,0.0006141932,0.000600627,0.00045180524,0.00040063373],"domain_scores_gemma":[0.9971807,0.001247904,0.0002526418,0.00094680756,0.00017714576,0.00019479531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018513019,0.00023102763,0.00054517563,0.0005368121,0.000099923906,0.000029918136,0.0003294079,0.00006220178,0.000014843436],"category_scores_gemma":[0.002879417,0.00018695912,0.00001269166,0.0013556273,0.00014193432,0.00018629388,0.00015808307,0.00015104536,0.000002790417],"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":[0.002922502,0.0011828198,0.009199622,0.0029819221,0.0041491375,0.00026549332,0.030728083,0.01113864,0.029559512,0.4493851,0.01709635,0.4413908],"study_design_scores_gemma":[0.0013003798,0.0007121553,0.006305296,0.0001768251,0.0018581729,0.000001266343,0.0017268525,0.57314855,0.000982188,0.41336074,0.00010311045,0.00032447703],"about_ca_topic_score_codex":0.000357855,"about_ca_topic_score_gemma":0.0053523337,"teacher_disagreement_score":0.5620099,"about_ca_system_score_codex":0.000049107326,"about_ca_system_score_gemma":0.00004310614,"threshold_uncertainty_score":0.76239717},"labels":[],"label_agreement":null},{"id":"W4388865742","doi":"10.1007/s40471-023-00339-7","title":"Emulating a Target Trial in Perinatal Pharmacoepidemiology: Challenges and Methodological Approaches","year":2023,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Jewish General Hospital; McGill University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Pharmacoepidemiology; Randomized controlled trial; Emulation; Medicine; Observational study; Clinical trial; Context (archaeology); Translational research; Clinical study design; Translational science; Causal inference; Data science; Intensive care medicine; Computer science; Psychology; Pharmacology; Internal medicine; Pathology","score_opus":0.8642482365844785,"score_gpt":0.5896862401110604,"score_spread":0.27456199647341806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388865742","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":[0.93844634,0.017665472,0.03419978,0.003296156,0.0016074014,0.0019780123,0.000007671581,0.0017495841,0.0010495525],"genre_scores_gemma":[0.80946034,0.0068334513,0.18185952,0.00011579749,0.00049497886,0.0010757253,0.000053695792,0.000060689432,0.00004582317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918616,0.004173445,0.0019003947,0.0010780949,0.000121888195,0.00086461444],"domain_scores_gemma":[0.9758293,0.022601498,0.0008836852,0.0004829176,0.000040650426,0.00016195163],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.023864478,0.00037568787,0.0016531373,0.00028766604,0.0000878677,0.0000041518415,0.00016394719,0.00039960942,0.00003091518],"category_scores_gemma":[0.08409939,0.0003045111,0.0001606265,0.0002367721,0.0003966822,0.00015388272,0.00039790352,0.0008991525,0.000005769742],"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":[0.0036938884,0.00066267647,0.13931763,0.00144911,0.00020406596,0.0015313841,0.0026849045,0.0006048231,0.00037486773,0.5004015,0.0060623316,0.34301284],"study_design_scores_gemma":[0.00192539,0.00021821665,0.0074405978,0.00009906046,0.000023732244,0.00031712858,0.00015017201,0.004363696,0.000066937806,0.9824882,0.0025673974,0.0003394486],"about_ca_topic_score_codex":0.000006165557,"about_ca_topic_score_gemma":0.0000037599034,"teacher_disagreement_score":0.48208672,"about_ca_system_score_codex":0.00006701163,"about_ca_system_score_gemma":0.000040706127,"threshold_uncertainty_score":0.9999407},"labels":[],"label_agreement":null},{"id":"W4389036121","doi":"10.23889/ijpds.v8i1.2176","title":"Generating synthetic data from administrative health records for drug safety and effectiveness studies","year":2023,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Advanced Causal Inference Techniques","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":"Université de Montréal; Manitoba Health; McGill University; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Real world data; Population; Medical prescription; Computer science; Medicine; Data science; Pharmacology; Environmental health","score_opus":0.5555152502297888,"score_gpt":0.5974494260819023,"score_spread":0.041934175852113564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389036121","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":[0.15980192,0.00023234302,0.82378197,0.0031264692,0.002617036,0.001150037,0.009062573,0.00020857251,0.000019085159],"genre_scores_gemma":[0.6228616,0.0006085171,0.37295163,0.00014164204,0.0005569172,0.000052809977,0.0027212673,0.000027720671,0.00007788577],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980444,0.00010036679,0.0005399996,0.00055676984,0.00052597985,0.00023249057],"domain_scores_gemma":[0.99503297,0.003146146,0.00050091057,0.0005968378,0.000630289,0.00009284207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005590062,0.00013005844,0.00024181826,0.0001984724,0.0006558919,0.00026719325,0.0016296565,0.000024170507,0.0000062607633],"category_scores_gemma":[0.012366887,0.00011155628,0.000023572758,0.00022123793,0.00016735893,0.002600687,0.0008747869,0.00011847503,0.0000013648024],"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":[0.0021022111,0.0004566848,0.022514367,0.00077881536,0.0012589147,0.000040202554,0.005841257,0.0020476647,0.011794378,0.3871595,0.07305709,0.49294892],"study_design_scores_gemma":[0.0008291127,0.00018619382,0.00859043,0.0008108617,0.00004217279,0.000053201027,0.0012845317,0.33309636,0.00088974583,0.65009564,0.0037783606,0.0003433649],"about_ca_topic_score_codex":0.00007823215,"about_ca_topic_score_gemma":0.00030117348,"teacher_disagreement_score":0.49260557,"about_ca_system_score_codex":0.0002328311,"about_ca_system_score_gemma":0.00022074298,"threshold_uncertainty_score":0.99595237},"labels":[],"label_agreement":null},{"id":"W4389238863","doi":"10.1007/s12561-023-09403-8","title":"Use of Generalized Propensity Scores for Assessing Effects of Multiple Exposures","year":2023,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Waterloo","funders":"National Institute on Alcohol Abuse and Alcoholism","keywords":"Confounding; Statistics; Conditional independence; Propensity score matching; Econometrics; Causal inference; Bivariate analysis; Joint probability distribution; Estimator; Inverse probability weighting; Causal model; Regression analysis; Marginal structural model; Weighting; Biostatistics; Conditional probability distribution; Mathematics; Medicine; Epidemiology","score_opus":0.32523508943013857,"score_gpt":0.4596776250189145,"score_spread":0.13444253558877595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389238863","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":[0.71102214,0.000011151875,0.28812987,0.00000936243,0.00011998795,0.00049651216,0.00013210668,0.00006700016,0.000011898925],"genre_scores_gemma":[0.55129766,0.000023651652,0.44860357,0.000005055305,0.0000052259675,0.000030193223,0.000005044211,0.000006258756,0.000023377164],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988723,0.0000751402,0.00038392394,0.00019574208,0.00026143965,0.00021150283],"domain_scores_gemma":[0.99460644,0.0047275065,0.0002754152,0.00018560656,0.0001774061,0.000027650844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005358119,0.00010213376,0.00030436183,0.00019554276,0.00005604538,0.00003135736,0.00019425424,0.000045926263,0.0000021326712],"category_scores_gemma":[0.010845004,0.00008157804,0.000027467593,0.0004757378,0.00041026602,0.00022264749,0.00008181602,0.000052023563,3.189408e-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":[0.00004637286,0.00020446336,0.11773747,0.001900183,0.000015242574,0.000014065033,0.0010818309,0.00011548386,0.4529205,0.41593772,0.00208439,0.007942295],"study_design_scores_gemma":[0.00023842482,0.0001781279,0.031693958,0.00026463345,0.000012138314,4.4384237e-7,0.0000938823,0.0064952383,0.45015848,0.51071316,0.000020332283,0.00013118664],"about_ca_topic_score_codex":0.000115474664,"about_ca_topic_score_gemma":0.00024087956,"teacher_disagreement_score":0.16047369,"about_ca_system_score_codex":0.000018671706,"about_ca_system_score_gemma":0.000069059264,"threshold_uncertainty_score":0.99748707},"labels":[],"label_agreement":null},{"id":"W4389372502","doi":"10.1136/archdischild-2023-326340","title":"Building a better model: abandon kitchen sink regression","year":2023,"lang":"en","type":"review","venue":"Archives of Disease in Childhood Fetal & Neonatal","topic":"Advanced Causal Inference Techniques","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":"University of New Brunswick; Dalhousie University","funders":"","keywords":"Overfitting; Directed acyclic graph; Regression; Regression analysis; Computer science; Outcome (game theory); Feature selection; Model selection; Econometrics; Logistic regression; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.10328008754121099,"score_gpt":0.4137124541359426,"score_spread":0.3104323665947316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389372502","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":[0.0010946632,0.976015,0.018369228,0.000054545246,0.000097855904,0.0023031614,0.00095509033,0.0007606999,0.00034978008],"genre_scores_gemma":[0.0019020619,0.93184644,0.06489443,0.000026362713,0.00017452052,0.00039202315,0.00033934455,0.00032483504,0.00009995816],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962171,0.00022662952,0.0014008025,0.000918436,0.0005772271,0.00065985776],"domain_scores_gemma":[0.9959082,0.001859204,0.00081538915,0.0010637675,0.000026104262,0.0003273582],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022011859,0.0008937466,0.0022345213,0.00080298877,0.00008048599,0.000035825513,0.0010249336,0.00025513323,0.000012669777],"category_scores_gemma":[0.0007630139,0.0007247213,0.001108656,0.00043585393,0.00027456298,0.00036579528,0.00092579314,0.0010495003,0.000016715612],"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":[0.000066884495,0.00030016628,0.000012880972,0.016910022,0.00018330663,0.00015871532,0.0004315131,0.00003412068,0.000004259471,0.014570383,0.000057950758,0.9672698],"study_design_scores_gemma":[0.0005925265,0.000077020515,0.000040975297,0.08524091,0.0007243576,0.000014856581,0.000015894851,0.00095721585,0.000028619139,0.90461725,0.0066843033,0.001006063],"about_ca_topic_score_codex":0.000013321109,"about_ca_topic_score_gemma":0.000007268592,"teacher_disagreement_score":0.9662637,"about_ca_system_score_codex":0.000073905234,"about_ca_system_score_gemma":0.0003857169,"threshold_uncertainty_score":0.99952036},"labels":[],"label_agreement":null},{"id":"W4389487798","doi":"10.1093/aje/kwad241","title":"The application of target trials with longitudinal targeted maximum likelihood estimation to assess the effect of alcohol consumption in adolescence on depressive symptoms in adulthood","year":2023,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"Cancer Research Society","keywords":"Alcohol consumption; Estimation; Longitudinal study; Maximum likelihood; Medicine; Alcohol; Depressive symptoms; Consumption (sociology); Longitudinal data; Psychiatry; Clinical psychology; Environmental health; Demography; Psychology; Statistics; Cognition; Biology; Mathematics","score_opus":0.12295481846560558,"score_gpt":0.45446400099653117,"score_spread":0.3315091825309256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389487798","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":[0.6562904,0.000067208945,0.34237298,0.0005454391,0.000031974396,0.00066263566,0.0000065528466,0.000016891025,0.0000059183412],"genre_scores_gemma":[0.9721029,0.00012672768,0.027519617,0.000063308435,0.000025673506,0.00014091244,0.0000041955354,0.00001621024,4.507434e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99358845,0.003962081,0.0017013632,0.00020668273,0.00022325084,0.00031816683],"domain_scores_gemma":[0.9650433,0.031064166,0.00328936,0.00035171476,0.00018939731,0.00006202726],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012887263,0.00018213862,0.0012928474,0.000309418,0.000040296225,0.0000039662687,0.00038273903,0.000071699236,0.0000024939702],"category_scores_gemma":[0.028190885,0.000093305964,0.00010764473,0.00071303063,0.0004053934,0.00009222751,0.0000470863,0.00041664793,0.0000023495097],"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":[0.0027915814,0.0001005665,0.8714081,0.00010809848,0.0001242935,0.000009988395,0.00035013512,0.017786918,0.005388547,0.0058692945,0.00014042066,0.095922075],"study_design_scores_gemma":[0.0023509688,0.010271099,0.70040935,0.0018202697,0.00017053448,0.00007736878,0.0004324339,0.012485704,0.037146863,0.2345145,0.000015657877,0.0003052504],"about_ca_topic_score_codex":0.00005928323,"about_ca_topic_score_gemma":0.00004443521,"teacher_disagreement_score":0.3158125,"about_ca_system_score_codex":0.000104315885,"about_ca_system_score_gemma":0.000058395828,"threshold_uncertainty_score":0.9799951},"labels":[],"label_agreement":null},{"id":"W4389676925","doi":"10.1002/sim.9973","title":"Accommodating misclassification effects on optimizing dynamic treatment regimes with Q‐learning","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Actua; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Computer science; Econometrics; Estimation; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.09089600466695962,"score_gpt":0.43294174638760535,"score_spread":0.3420457417206457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389676925","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":[0.063864864,0.000042467476,0.9270312,0.0010247581,0.00012691432,0.00092179806,0.0000183668,0.0010474293,0.0059222076],"genre_scores_gemma":[0.46504235,0.00024156128,0.5329236,0.000052880718,0.000065647946,0.00019622598,0.00016605448,0.00006613113,0.0012455542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877924,0.000118704644,0.00029240505,0.00026374048,0.00027785503,0.00026808283],"domain_scores_gemma":[0.9957135,0.0037043171,0.00018785146,0.00028399003,0.00005752752,0.00005282081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040306506,0.00019720722,0.0003354667,0.000253593,0.00009170705,0.000010886666,0.00010510617,0.000055734534,0.000019689707],"category_scores_gemma":[0.0020972625,0.00014027354,0.0000108871955,0.0003996035,0.00009190542,0.000048580496,0.000023243845,0.00026312855,0.000016690678],"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":[0.0002337197,0.00023191859,0.0025926367,0.0009258032,0.00013302854,0.0006958063,0.008734629,0.0031777627,0.012942693,0.55182606,0.0046719247,0.413834],"study_design_scores_gemma":[0.004389892,0.007356266,0.0056818156,0.005782649,0.00020800435,0.000025820664,0.005298896,0.1396579,0.010012213,0.819703,0.0010032771,0.0008802519],"about_ca_topic_score_codex":0.000023913044,"about_ca_topic_score_gemma":0.00004032514,"teacher_disagreement_score":0.41295373,"about_ca_system_score_codex":0.00028029052,"about_ca_system_score_gemma":0.000028207698,"threshold_uncertainty_score":0.57201886},"labels":[],"label_agreement":null},{"id":"W4389899943","doi":"10.1111/jebm.12577","title":"Reporting, handling, and interpretation of time‐varying drug treatments in observational studies using routinely collected healthcare data","year":2023,"lang":"en","type":"article","venue":"Journal of Evidence-Based Medicine","topic":"Advanced Causal Inference Techniques","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":"McMaster University; Impact","funders":"National Natural Science Foundation of China","keywords":"Observational study; Discontinuation; Medicine; Logistic regression; Protocol (science); Pharmacoepidemiology; Meta-analysis; Internal medicine; Alternative medicine; Pharmacology; Pathology; Medical prescription","score_opus":0.8265753926692315,"score_gpt":0.5867571796628459,"score_spread":0.23981821300638562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389899943","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":[0.9845934,0.0030345093,0.007225073,0.0046365308,0.0001223043,0.00032186988,0.000008493677,0.000048509723,0.000009329142],"genre_scores_gemma":[0.9517133,0.0013013463,0.04658158,0.00015537547,0.00011707258,0.000003964426,0.000020136453,0.000019770541,0.00008745844],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647254,0.00019610881,0.0024171637,0.00019177228,0.00055501336,0.00016741607],"domain_scores_gemma":[0.9908666,0.003566196,0.004308049,0.00028330545,0.00090464985,0.00007117],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004663147,0.00015176751,0.00081067503,0.0004986415,0.00006006685,0.000007993114,0.00019649402,0.000049396207,0.000011133138],"category_scores_gemma":[0.04846497,0.00010176848,0.000038935465,0.00076092145,0.00013459552,0.0005696526,0.00009086275,0.00021596039,2.3722356e-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":[0.0041998234,0.00077012484,0.73316103,0.009010569,0.001600936,0.0018119342,0.035136454,0.008638682,0.14444155,0.0011363965,0.02684068,0.033251822],"study_design_scores_gemma":[0.008592253,0.004225258,0.060237315,0.20474118,0.0015552604,0.00040617428,0.0070794076,0.52590567,0.026016502,0.16033934,0.00006128583,0.00084037706],"about_ca_topic_score_codex":0.00010933447,"about_ca_topic_score_gemma":0.000039883715,"teacher_disagreement_score":0.67292374,"about_ca_system_score_codex":0.00024232508,"about_ca_system_score_gemma":0.0004187647,"threshold_uncertainty_score":0.9595502},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4389989768","doi":"10.1016/j.jval.2023.11.011","title":"Unanchored Population-Adjusted Indirect Comparison Methods for Time-to-Event Outcomes Using Inverse Odds Weighting, Regression Adjustment, and Doubly Robust Methods With Either Individual Patient or Aggregate Data","year":2023,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MD Precision (Canada); Precision Nanosystems (Canada); University of British Columbia","funders":"Medical Research Council; Bristol-Myers Squibb","keywords":"Inverse probability weighting; Statistics; Propensity score matching; Weighting; Confidence interval; Regression; Population; Hazard ratio; Proportional hazards model; Standard error; Medicine; Econometrics; Mathematics","score_opus":0.5243210205611497,"score_gpt":0.5456246118675028,"score_spread":0.021303591306353065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389989768","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":[0.37067893,0.000451718,0.62135154,0.0006230507,0.00031687264,0.0053868573,0.00027923787,0.00087714323,0.00003462819],"genre_scores_gemma":[0.0060279504,0.000048902624,0.99291754,0.00023419646,0.00004299376,0.00019164369,0.00027204579,0.00010919182,0.00015554641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995415,0.001584957,0.0011629007,0.0007829939,0.0003860508,0.000668144],"domain_scores_gemma":[0.99524015,0.0024673443,0.001016898,0.0009234487,0.00009895619,0.0002531957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00457551,0.00041272034,0.0010608245,0.000608028,0.00023004705,0.000050333154,0.0004048183,0.00018103335,0.00003153757],"category_scores_gemma":[0.0018252168,0.00028803386,0.000047554004,0.0011032406,0.000058825644,0.00031753615,0.00051956106,0.00032666334,0.0000037395803],"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":[0.0013516172,0.000834629,0.040525716,0.0026563278,0.00046078075,0.000028296648,0.013993484,0.046521634,0.0006322464,0.002831681,0.0093615325,0.88080204],"study_design_scores_gemma":[0.003221322,0.0020499525,0.017395223,0.004865019,0.0002735489,0.000030319066,0.0012371725,0.93611705,0.0030999049,0.027622273,0.0028569705,0.0012312669],"about_ca_topic_score_codex":0.0010704673,"about_ca_topic_score_gemma":0.00022520642,"teacher_disagreement_score":0.8895954,"about_ca_system_score_codex":0.0003876157,"about_ca_system_score_gemma":0.00022809776,"threshold_uncertainty_score":0.9999572},"labels":[],"label_agreement":null},{"id":"W4390127909","doi":"10.1016/j.jval.2023.09.2170","title":"MSR111 Causal Inference and Statistical Considerations for Indirectly Comparing Time-to-Event Endpoints for Treatments with Different Starting Points for Outcome Assessment in Resectable NSCLC","year":2023,"lang":"en","type":"article","venue":"Value in Health","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":"Roche (Canada)","funders":"","keywords":"Outcome (game theory); Causal inference; Inference; Event (particle physics); Statistical inference; Medicine; Internal medicine; Computer science; Statistics; Artificial intelligence; Mathematics; Pathology","score_opus":0.31694711317792057,"score_gpt":0.49713635470914014,"score_spread":0.18018924153121957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390127909","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":[0.6057858,0.00000989019,0.38609773,0.0011832545,0.00004656269,0.006187222,0.0004459026,0.00020208528,0.000041575604],"genre_scores_gemma":[0.69083256,0.0000062953027,0.3062473,0.00011368765,0.000016723341,0.002582547,0.00007162769,0.00004475812,0.00008453056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99742514,0.00017848895,0.00095517805,0.00047893813,0.00022896097,0.0007332787],"domain_scores_gemma":[0.9908798,0.008332556,0.00025494813,0.00023779052,0.0001041401,0.00019080995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014935823,0.0002630056,0.00072488724,0.00034400178,0.00020306928,0.000059241316,0.000085660766,0.000071807895,0.000014130031],"category_scores_gemma":[0.0026349216,0.0002301465,0.00003450648,0.0002190111,0.00004124893,0.0001242138,0.000078837176,0.00019080877,0.0000023664081],"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":[0.0018148398,0.0024722498,0.33339205,0.0072280397,0.00028715478,0.000045486933,0.010656842,0.012294509,0.0017050861,0.6168423,0.0034880624,0.009773364],"study_design_scores_gemma":[0.0045644892,0.0027840084,0.030732669,0.0012505812,0.000039543364,0.000004040906,0.0005206371,0.19054219,0.0011568905,0.76787716,0.000049034155,0.00047877044],"about_ca_topic_score_codex":0.00044628966,"about_ca_topic_score_gemma":0.0012503532,"teacher_disagreement_score":0.3026594,"about_ca_system_score_codex":0.00070372806,"about_ca_system_score_gemma":0.00032089886,"threshold_uncertainty_score":0.9385102},"labels":[],"label_agreement":null},{"id":"W4390166159","doi":"10.1101/2023.12.21.23300389","title":"Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Healthcare","year":2023,"lang":"en","type":"review","venue":"medRxiv","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":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science; Statistical inference; Pooling; Health care; Data mining; Workflow; Inference; USable; Statistical model; Management science; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.5197468601909546,"score_gpt":0.5752067852484413,"score_spread":0.05545992505748665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390166159","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":[0.0000014184881,0.7776885,0.21888337,0.00013611154,0.000022900105,0.0020261693,0.00105049,0.00018304863,0.000007985811],"genre_scores_gemma":[0.0000049686664,0.91106147,0.08757991,0.00014763256,0.000034784774,0.00056865305,0.00052122504,0.00006910477,0.000012227857],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9970432,0.00039483944,0.00141157,0.0004973096,0.00035552762,0.00029756365],"domain_scores_gemma":[0.99539804,0.0030854282,0.00048073634,0.0005628984,0.00027128524,0.00020161731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074464706,0.0004042332,0.002916742,0.00018586892,0.000063944484,0.00003271213,0.0002955144,0.0003965595,0.00011768445],"category_scores_gemma":[0.0072660125,0.00031978573,0.00014894824,0.00082412764,0.000088786874,0.00006079841,0.00022905186,0.0006861734,0.000015832027],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029909181,0.000049681526,0.000013840941,0.7568573,0.0002480851,0.000027633965,0.0000473547,7.289929e-7,0.0000011270516,0.1087997,0.0017297295,0.13222186],"study_design_scores_gemma":[0.00005112609,0.00012467285,0.000008905103,0.93824565,0.0014376639,0.000019703342,0.000015505248,0.000011418709,0.000003525172,0.027714942,0.031837326,0.0005295885],"about_ca_topic_score_codex":0.000026674828,"about_ca_topic_score_gemma":0.000058981055,"teacher_disagreement_score":0.18138836,"about_ca_system_score_codex":0.00008681259,"about_ca_system_score_gemma":0.00035843087,"threshold_uncertainty_score":0.99992543},"labels":[],"label_agreement":null},{"id":"W4390743877","doi":"10.57264/cer-2023-0147","title":"Quantitative bias analysis for external control arms using real-world data in clinical trials: a primer for clinical researchers","year":2024,"lang":"en","type":"review","venue":"Journal of Comparative Effectiveness 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":"Public Health Ontario; University of Toronto; McMaster University; Impact","funders":"","keywords":"Robustness (evolution); Missing data; External validity; Medicine; Confounding; Sample size determination; Population; Clinical trial; Data collection; Computer science; Statistics; Machine learning","score_opus":0.9834323930954177,"score_gpt":0.8240222415215248,"score_spread":0.15941015157389293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390743877","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":[0.0008893286,0.5295447,0.45985883,0.000031165233,0.00035519924,0.008582532,0.00067911396,0.000029043544,0.000030088835],"genre_scores_gemma":[0.0019415319,0.88001734,0.11549736,0.0000043694267,0.0011703563,0.0010524122,0.00007208915,0.00016833216,0.00007618614],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9050604,0.080735974,0.009428098,0.0015136952,0.0020953047,0.0011665077],"domain_scores_gemma":[0.59380805,0.3951927,0.0050100097,0.0014303263,0.00411909,0.00043977902],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33425945,0.0008316274,0.016129646,0.0056879367,0.00018756163,0.00037240362,0.0027693245,0.0006265301,0.000016289465],"category_scores_gemma":[0.12180561,0.0005502163,0.0047719446,0.005079334,0.0014451537,0.00065140665,0.0007213948,0.006224374,0.000008687379],"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":[0.04622059,0.0063511305,0.0064348853,0.07784056,0.08507364,0.0005796313,0.0008958925,0.00024999375,0.0000436797,0.07763619,0.0063892147,0.6922846],"study_design_scores_gemma":[0.015715634,0.0225216,0.0018879095,0.17294413,0.060109936,0.000080349986,0.0015218693,0.067155525,0.000081045604,0.44818282,0.20681317,0.002986006],"about_ca_topic_score_codex":0.00010301141,"about_ca_topic_score_gemma":0.00043772394,"teacher_disagreement_score":0.68929857,"about_ca_system_score_codex":0.0014905385,"about_ca_system_score_gemma":0.0044742306,"threshold_uncertainty_score":0.99969494},"labels":[],"label_agreement":null},{"id":"W4390811869","doi":"10.1101/2024.01.11.575211","title":"Through the lens of causal inference: Decisions and pitfalls of covariate selection","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","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":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Covariate; Causal inference; Inference; Selection (genetic algorithm); Through-the-lens metering; Lens (geology); Econometrics; Computer science; Psychology; Economics; Artificial intelligence; Engineering","score_opus":0.10514839863080201,"score_gpt":0.35556451503322134,"score_spread":0.25041611640241934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390811869","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":[0.8629249,0.0014229043,0.13101685,0.00050226547,0.00077512924,0.0017664318,0.00054966105,0.00093828456,0.00010361222],"genre_scores_gemma":[0.93289095,0.00085653365,0.06585659,0.00005197302,0.00010329443,0.0001354839,1.3889482e-7,0.00009970995,0.0000053476065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974471,0.0001699535,0.0009107565,0.00063583744,0.00046004297,0.00037634833],"domain_scores_gemma":[0.99617034,0.0011408553,0.00074925844,0.0010210893,0.0008345725,0.00008390294],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008959409,0.0004739845,0.0007820495,0.0002121528,0.000098544006,0.00008038076,0.00048571124,0.00054066046,0.000029280478],"category_scores_gemma":[0.003196291,0.00037593473,0.00013945934,0.0006208387,0.000346978,0.00015801088,0.0010404674,0.001096641,0.0000069846037],"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":[0.000029462448,0.00014973205,0.00056102424,0.0010607947,0.00030511618,0.000007229104,0.00013284838,0.000044448887,0.48582155,0.51118565,0.0006968334,0.000005286327],"study_design_scores_gemma":[0.00040569072,0.00028541585,0.006103317,0.0040915934,0.00083648204,1.0003824e-7,0.000020921074,0.00076848717,0.8724712,0.11240468,0.0014941293,0.0011179496],"about_ca_topic_score_codex":0.00012880107,"about_ca_topic_score_gemma":0.000014743457,"teacher_disagreement_score":0.398781,"about_ca_system_score_codex":0.00014554894,"about_ca_system_score_gemma":0.0007741439,"threshold_uncertainty_score":0.9998693},"labels":[],"label_agreement":null},{"id":"W4390892810","doi":"10.1111/bcp.15998","title":"Observational studies to emulate randomized trials: Some real‐world barriers","year":2024,"lang":"en","type":"article","venue":"British Journal of Clinical Pharmacology","topic":"Advanced Causal Inference Techniques","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":"McGill University; Jewish General Hospital","funders":"McGill University","keywords":"Observational study; Randomized controlled trial; Medicine; Randomization; Emulation; Medical physics; Psychology; Surgery; Internal medicine","score_opus":0.6694319031572994,"score_gpt":0.6509946010066823,"score_spread":0.01843730215061712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390892810","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":[0.838346,0.030974075,0.04832375,0.036489807,0.038213253,0.0042977193,0.00018234269,0.0010766571,0.0020963764],"genre_scores_gemma":[0.68616074,0.07749293,0.1907279,0.019944042,0.019846903,0.00033264002,0.000008979153,0.000222509,0.005263374],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99041706,0.0035667506,0.0049529653,0.0002994613,0.00043238647,0.00033135558],"domain_scores_gemma":[0.95075756,0.046758346,0.0011951637,0.00011089636,0.0007524959,0.00042554442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028941333,0.00021314502,0.0033334813,0.00027570763,0.00008973998,0.00008167785,0.00038631083,0.00016265511,0.0008471129],"category_scores_gemma":[0.080507286,0.00018799557,0.00110514,0.00032250048,0.0004162418,0.00048976246,0.00013753519,0.001150566,0.000022907947],"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":[0.014634116,0.00020287122,0.00006408092,0.00020750414,0.0035881046,0.0024283645,0.00021606564,0.00013346082,0.00089210155,0.063546255,0.8749357,0.039151408],"study_design_scores_gemma":[0.035671256,0.0003575707,0.00013210271,0.0009325371,0.0013293173,0.000341078,0.00006759117,0.000404827,0.00079026155,0.9262648,0.033411857,0.0002967531],"about_ca_topic_score_codex":0.000008054684,"about_ca_topic_score_gemma":0.000019385285,"teacher_disagreement_score":0.8627186,"about_ca_system_score_codex":0.000118511285,"about_ca_system_score_gemma":0.000441919,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W4390961241","doi":"10.48550/arxiv.2401.06909","title":"Sensitivity Analysis for Matched Observational Studies with Continuous Exposures and Binary Outcomes","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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 Institutes of Health; York University","keywords":"Sensitivity (control systems); Binary number; Observational study; Matching (statistics); Population; Binary data; Statistics; Mathematics; Causal inference; Computer science; Algorithm; Medicine","score_opus":0.40646540614942905,"score_gpt":0.3405128909393795,"score_spread":0.06595251521004958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390961241","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":[0.82998157,0.00012588386,0.16834468,0.00018662101,0.00006328476,0.00058149773,0.00016508273,0.00044169143,0.00010968218],"genre_scores_gemma":[0.973986,0.0001283182,0.024057955,0.000050619252,0.000027880767,0.000012975863,0.000045052766,0.000037375903,0.0016537938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985267,0.00010064714,0.00024361219,0.00079768506,0.00009383807,0.00023755431],"domain_scores_gemma":[0.9969899,0.0017263858,0.00027629538,0.0005284049,0.0004093233,0.000069704176],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041521128,0.0003884525,0.0009860047,0.00034993948,0.00010614309,0.000049365688,0.00015774013,0.00021401909,0.0000067558162],"category_scores_gemma":[0.00032823006,0.00033874298,0.0002599266,0.00044353734,0.00024225711,0.00012039174,0.0008184578,0.0003654464,0.0000019767197],"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":[0.00026462492,0.00019316362,0.2781646,0.001844884,0.012000227,0.00071013696,0.001084351,0.020294936,0.00020757529,0.6843042,0.0008085856,0.00012274443],"study_design_scores_gemma":[0.00032204355,0.00013376068,0.018895734,0.00023336564,0.0041464544,0.0000037744558,0.0011454272,0.013467661,0.00026924023,0.9608022,0.000026177246,0.0005541694],"about_ca_topic_score_codex":0.000049015525,"about_ca_topic_score_gemma":0.00040808014,"teacher_disagreement_score":0.27649802,"about_ca_system_score_codex":0.0001609292,"about_ca_system_score_gemma":0.00008111615,"threshold_uncertainty_score":0.9999065},"labels":[],"label_agreement":null},{"id":"W4391368285","doi":"10.1097/ede.0000000000001694","title":"Visualizing External Validity: Graphical Displays to Inform the Extension of Treatment Effects from Trials to Clinical Practice","year":2023,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute of Environmental Health Sciences; UCB US; Patient-Centered Outcomes Research Institute; Novo Nordisk; Sanofi; GlaxoSmithKline; Pharmaceutical Research and Manufacturers of America Foundation","keywords":"Clinical trial; Clinical Practice; Medical physics; Covariate; Population; Visualization; Computer science; Randomized controlled trial; Measure (data warehouse); Medicine; Data science; Data mining; Family medicine; Machine learning; Surgery; Pathology","score_opus":0.6902984386938299,"score_gpt":0.635397533206193,"score_spread":0.05490090548763693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391368285","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":[0.6868515,0.000077525045,0.29985684,0.010417108,0.0007144855,0.0015366501,0.000031389423,0.00035767944,0.00015683394],"genre_scores_gemma":[0.5965688,0.0006723271,0.3916896,0.009052287,0.0010877723,0.0006805723,0.000031940715,0.00007070727,0.00014600181],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9914196,0.005215941,0.0021754706,0.0004958311,0.00020218219,0.0004909362],"domain_scores_gemma":[0.80174446,0.1964928,0.00071458763,0.0007146795,0.00013183463,0.0002016337],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01976749,0.00025463902,0.0016773068,0.00015437524,0.00010670434,0.000007929852,0.00031735355,0.00028220162,0.000027188295],"category_scores_gemma":[0.31869838,0.00014842214,0.00035177503,0.00045620292,0.00012592795,0.00011323686,0.00029485684,0.00030127846,0.00013831169],"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":[0.0023939412,0.0008054998,0.027998758,0.0001275846,0.00067647395,0.00015755458,0.0035931773,0.00017705589,0.018537622,0.7302442,0.058099017,0.15718912],"study_design_scores_gemma":[0.000715067,0.0038950827,0.03440897,0.00028183308,0.00030781908,0.000017946377,0.00025005912,0.0005149452,0.0053708805,0.9300057,0.02393873,0.00029291885],"about_ca_topic_score_codex":0.00044523098,"about_ca_topic_score_gemma":0.0000698076,"teacher_disagreement_score":0.29893088,"about_ca_system_score_codex":0.000101768695,"about_ca_system_score_gemma":0.000059938797,"threshold_uncertainty_score":0.6870405},"labels":[],"label_agreement":null},{"id":"W4391368298","doi":"10.1097/ede.0000000000001711","title":"Differential Participation, a Potential Cause of Spurious Associations in Observational Cohorts in Environmental Epidemiology","year":2023,"lang":"en","type":"article","venue":"Epidemiology","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":true,"ca_institutions":"McGill University; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto; Health Canada","funders":"National Institute on Aging; Health Canada; Government of Canada","keywords":"Spurious relationship; Observational study; Differential (mechanical device); Selection bias; Differential effects; Econometrics; Cohort study; Population; Information bias; Cohort; Medicine; Environmental health; Statistics; Mathematics; Physics","score_opus":0.40291812067690513,"score_gpt":0.4843232539837756,"score_spread":0.08140513330687049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391368298","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":[0.9805078,0.00003997071,0.016766222,0.0018357628,0.00016333284,0.00039119352,0.00009078388,0.00014429714,0.000060628216],"genre_scores_gemma":[0.99073935,0.00012728613,0.008084071,0.00029982554,0.000068553454,0.0001949555,0.0003793009,0.000024328292,0.00008235018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99548745,0.0016624706,0.0017242526,0.0003919843,0.00011633348,0.00061750424],"domain_scores_gemma":[0.98783255,0.0111242775,0.000636483,0.000309677,0.000026265932,0.000070738686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028679594,0.0001929341,0.001032924,0.00033336948,0.00004527593,0.0000013248405,0.00018956476,0.00033555113,0.00025249852],"category_scores_gemma":[0.02125835,0.00019527249,0.00010866553,0.00033356197,0.00022015531,0.00011398048,0.00014228623,0.00034200464,0.000031126026],"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":[0.000021585749,0.0001855688,0.8932941,0.000015372038,0.000030140933,0.000016607837,0.00020848175,0.0012884759,0.0010148524,0.102297254,0.001264284,0.0003632761],"study_design_scores_gemma":[0.000220271,0.000041239433,0.5611413,0.000014152385,0.000011909188,0.0000026138023,0.000020347545,0.0030169182,0.00011022664,0.43530878,0.000021707094,0.00009047967],"about_ca_topic_score_codex":0.00017967133,"about_ca_topic_score_gemma":0.00043218583,"teacher_disagreement_score":0.33301154,"about_ca_system_score_codex":0.00024299194,"about_ca_system_score_gemma":0.000042027263,"threshold_uncertainty_score":0.986986},"labels":[],"label_agreement":null},{"id":"W4391368301","doi":"10.1097/ede.0000000000001700","title":"It Is Time to Think About Time: The Impact of Secular Trends on Bias Parameter Values from Validation Studies","year":2023,"lang":"en","type":"article","venue":"Epidemiology","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":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Selection bias; Statistics; Observational error; Categorical variable; Information bias; Econometrics; Non-response bias; Confounding; Errors-in-variables models; Computer science; Mathematics","score_opus":0.4446297754692033,"score_gpt":0.5345987961979093,"score_spread":0.089969020728706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391368301","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":[0.96221393,0.00037373888,0.0063571013,0.025402635,0.0001386734,0.0006748377,0.00028416567,0.00097456144,0.003580331],"genre_scores_gemma":[0.75086415,0.0014534483,0.1783198,0.032212652,0.0012071296,0.00081913034,0.0007508643,0.0004162559,0.03395658],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99734086,0.001088046,0.0006942223,0.00036254566,0.00014338255,0.00037094866],"domain_scores_gemma":[0.9764949,0.0222099,0.00037530193,0.00074189255,0.00011798247,0.00006004493],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002813014,0.00025232733,0.00087724713,0.0001969032,0.000076747354,0.000005936245,0.0003156161,0.00018266431,0.0011765143],"category_scores_gemma":[0.021925906,0.00014785882,0.0002663555,0.0004017763,0.00017103982,0.00007363789,0.00016646905,0.00022128744,0.0014255662],"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":[0.000049062393,0.000044521606,0.0007415871,0.00001273118,0.000468257,0.0000035696098,0.004001887,0.0007219727,0.0021695385,0.0020864427,0.9855919,0.0041085244],"study_design_scores_gemma":[0.00012807778,0.000629286,0.0043153157,0.00011670454,0.0000756307,0.0000021269177,0.000114693416,0.003320817,0.007987849,0.9818537,0.0012417543,0.00021399824],"about_ca_topic_score_codex":0.00007400193,"about_ca_topic_score_gemma":0.0000020211648,"teacher_disagreement_score":0.98435014,"about_ca_system_score_codex":0.00010081551,"about_ca_system_score_gemma":0.000020218631,"threshold_uncertainty_score":0.99973655},"labels":[],"label_agreement":null},{"id":"W4391716914","doi":"10.1186/s12874-024-02147-z","title":"Comparison of statistical methods used to meta-analyse results from interrupted time series studies: an empirical study","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Monash University; Medical Research Council; Australian Government","keywords":"Interrupted time series; Interrupted Time Series Analysis; Series (stratigraphy); Meta-analysis; Time series; Computer science; Psychological intervention; Research design; Statistical analysis; Econometrics; Statistics; Data mining; Medicine; Machine learning; Mathematics","score_opus":0.9784031228965239,"score_gpt":0.81904854844297,"score_spread":0.15935457445355383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391716914","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":[0.00002780316,0.4921082,0.5040647,0.00018703964,0.00019971763,0.00245861,0.00059652724,0.00028912877,0.00006829985],"genre_scores_gemma":[0.0000059744784,0.26852596,0.72919494,0.000032448334,0.00023193056,0.0012831762,0.00017170867,0.00016008671,0.00039376906],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78412867,0.19989277,0.006857774,0.0028644367,0.0047093714,0.0015469897],"domain_scores_gemma":[0.6232934,0.37112746,0.00077610795,0.0024382344,0.0011829934,0.0011817871],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13498779,0.001169153,0.01756354,0.0018579965,0.00014565473,0.00008082485,0.002896521,0.001545893,0.0021931147],"category_scores_gemma":[0.6552001,0.00071874016,0.0012327669,0.0026155475,0.0020635019,0.00015139038,0.003602706,0.00538307,0.00024589812],"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":[0.0014238638,0.002606505,0.000009655024,0.016538016,0.029601617,0.0005402082,0.014854008,0.000001001151,0.000022116348,0.0055968245,0.043996725,0.88480943],"study_design_scores_gemma":[0.001191757,0.012907038,0.00000493029,0.011783907,0.07060119,0.00006957822,0.01873358,0.0006462292,0.00023981022,0.47522372,0.40667707,0.0019212017],"about_ca_topic_score_codex":0.0002931237,"about_ca_topic_score_gemma":0.0016900896,"teacher_disagreement_score":0.88288826,"about_ca_system_score_codex":0.00057323935,"about_ca_system_score_gemma":0.00299694,"threshold_uncertainty_score":0.9997503},"labels":[],"label_agreement":null},{"id":"W4391780126","doi":"10.1093/jrsssc/qlae008","title":"Revisiting the effects of maternal education on adolescents’ academic performance: Doubly robust estimation in a network-based observational study","year":2024,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; National Institute on Aging; University of North Carolina at Chapel Hill","keywords":"Observational study; Estimation; Psychology; Statistics; Mathematics; Economics","score_opus":0.06762390301399934,"score_gpt":0.3678736315680582,"score_spread":0.30024972855405885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391780126","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":[0.15521535,0.00010228528,0.8421018,0.00050672685,0.0006065954,0.0011910235,0.00010603549,0.000057505,0.00011266036],"genre_scores_gemma":[0.8298049,0.000021215381,0.16954923,0.00017635494,0.00028399448,0.00005585184,0.000010559868,0.000035360634,0.00006252851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730104,0.00021060195,0.0011195102,0.00020473913,0.0008592055,0.00030492304],"domain_scores_gemma":[0.99582726,0.0029800157,0.0006831089,0.00023403805,0.00020479891,0.000070754024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013163709,0.00025700958,0.00042632298,0.00004443331,0.00019780292,0.00008691843,0.00043121548,0.000119439996,0.000032595748],"category_scores_gemma":[0.0010573455,0.00015970274,0.0001070834,0.00032887553,0.0002173156,0.0001423135,0.0000912055,0.0011790948,0.0000024404508],"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":[0.00096968794,0.00070466875,0.022923173,0.006377529,0.0002980577,0.000023634302,0.0021138096,0.14098151,0.00025656354,0.7160368,0.027669549,0.081645034],"study_design_scores_gemma":[0.0014440613,0.0011554679,0.27798918,0.007976336,0.0005929292,0.000021250677,0.0008302961,0.21428536,0.00089890335,0.49398953,0.00027724908,0.000539429],"about_ca_topic_score_codex":0.0000096251015,"about_ca_topic_score_gemma":0.0000032296311,"teacher_disagreement_score":0.6745896,"about_ca_system_score_codex":0.00035579535,"about_ca_system_score_gemma":0.00040269582,"threshold_uncertainty_score":0.6512489},"labels":[],"label_agreement":null},{"id":"W4391813293","doi":"10.1007/s10260-024-00744-2","title":"Determining sample sizes for combined incident and prevalent cohort studies with and without follow-up","year":2024,"lang":"en","type":"article","venue":"Statistical Methods & Applications","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":"University of Regina","funders":"","keywords":"Cohort; Sample size determination; Statistics; Event (particle physics); Sample (material); Sampling (signal processing); Cohort study; Econometrics; Computer science; Mathematics; Medicine","score_opus":0.2077124691976119,"score_gpt":0.5430278245062908,"score_spread":0.33531535530867895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391813293","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":[0.0034239567,0.0005498481,0.99326384,0.00015341233,0.000028733528,0.0019007919,0.00024814182,0.0003353324,0.00009596303],"genre_scores_gemma":[0.052826256,0.00021723681,0.94178176,0.00003731199,0.000028206845,0.0049566412,0.000016601207,0.000040083385,0.000095931726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877363,0.00011673774,0.00032619608,0.00043557558,0.00013532271,0.00021252465],"domain_scores_gemma":[0.9866996,0.012717513,0.00007416482,0.00025716698,0.00014562409,0.00010595633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080970925,0.00019324904,0.00039045818,0.00005947969,0.0001680806,0.00007437721,0.00007904667,0.00005179994,0.000012474473],"category_scores_gemma":[0.002605841,0.00014847596,0.000021971591,0.0001222546,0.0003363964,0.00008644042,0.00009903782,0.00013088739,8.1182446e-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":[0.00003234526,0.000027743645,0.0015876065,0.0006914211,0.00019113524,7.8772445e-7,0.00043460165,2.3663762e-7,0.00059645483,0.8347432,0.00020816537,0.16148633],"study_design_scores_gemma":[0.00026909975,0.00028327043,0.0012065617,0.00014714716,0.00048877764,0.000012958366,0.00028270137,0.002066014,0.0011715144,0.9919766,0.0018872389,0.0002081187],"about_ca_topic_score_codex":0.000006237171,"about_ca_topic_score_gemma":0.000023395292,"teacher_disagreement_score":0.1612782,"about_ca_system_score_codex":0.000052867796,"about_ca_system_score_gemma":0.000039735467,"threshold_uncertainty_score":0.6054674},"labels":[],"label_agreement":null},{"id":"W4391847795","doi":"10.1016/j.cjca.2024.02.005","title":"Causal Inference Challenges in the Relationship Between Social Determinants and Cardiovascular Outcomes","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Medicine; Causal inference; Inference; Artificial intelligence; Pathology","score_opus":0.36950571825910056,"score_gpt":0.4292176100910344,"score_spread":0.05971189183193382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391847795","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":[0.96024203,0.013874955,0.017425753,0.0037894764,0.00046749334,0.0003134525,0.000038925242,0.000045342666,0.0038025426],"genre_scores_gemma":[0.998896,0.00017648505,0.00046718869,0.000022365422,0.00040715517,0.000007823091,5.7234234e-7,0.000014201315,0.000008233477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987177,0.00039426313,0.00035521094,0.00013262886,0.00014333788,0.00025684046],"domain_scores_gemma":[0.9970153,0.0025587338,0.000067348694,0.00018097239,0.00006699007,0.00011065931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016631274,0.0001264645,0.00054823153,0.0003063982,0.00008693009,0.00003960439,0.00023111567,0.00017231636,0.0000020291657],"category_scores_gemma":[0.0019867748,0.000088461085,0.00019201446,0.00012379873,0.00018512788,0.00014953168,0.000015792612,0.0005305731,0.00000188377],"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":[0.0000022018091,7.726392e-7,0.8417975,0.00008822697,0.00023286515,0.0006672312,0.0028172662,0.000012582621,0.0000015125474,0.11816559,0.00071373495,0.03550057],"study_design_scores_gemma":[0.00009348431,0.000057714195,0.65954065,0.000073220544,0.0001143744,0.0002963695,0.0005350592,0.0000018129613,0.000003834025,0.33187357,0.0073080454,0.00010189236],"about_ca_topic_score_codex":0.0001385745,"about_ca_topic_score_gemma":0.0021268385,"teacher_disagreement_score":0.21370797,"about_ca_system_score_codex":0.0000870648,"about_ca_system_score_gemma":0.00036237112,"threshold_uncertainty_score":0.36073384},"labels":[],"label_agreement":null},{"id":"W4391953805","doi":"10.21203/rs.3.rs-3824985/v1","title":"Accounting for center-level effects in multicenter randomized controlled trials","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Randomized controlled trial; Protocol (science); Random effects model; Fixed effects model; Medicine; Econometrics; Psychology; Statistics; Meta-analysis; Economics; Panel data; Mathematics; Alternative medicine; Surgery; Internal medicine","score_opus":0.37805691469864283,"score_gpt":0.5681275528826683,"score_spread":0.19007063818402542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391953805","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":[0.12239519,0.0125921555,0.5175716,0.00448652,0.0048954803,0.31872204,0.0025412114,0.0036926328,0.013103177],"genre_scores_gemma":[0.8384459,0.0006483213,0.098752126,0.00005264514,0.00091731135,0.058780257,0.00017278358,0.00030659573,0.0019240564],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9864148,0.0070985127,0.0028278378,0.0010441233,0.0014061346,0.0012086069],"domain_scores_gemma":[0.8856718,0.11143023,0.00073295366,0.0009221757,0.0011024141,0.00014046232],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06316197,0.0006212138,0.0072077056,0.0014887212,0.00010796444,0.00048712798,0.000738194,0.000739009,0.00008070898],"category_scores_gemma":[0.22183245,0.000423598,0.0020932828,0.0003168493,0.00022560757,0.000105511586,0.002046073,0.002967955,0.00004267847],"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":[0.4585922,0.002167542,0.0002723151,0.10088269,0.004221624,0.00032580772,0.004207077,0.000079156496,0.0036515896,0.38913727,0.017866326,0.018596428],"study_design_scores_gemma":[0.20602106,0.0000732861,0.000005934623,0.01169951,0.00020333595,9.2977e-7,0.00013660232,0.0078850845,0.0019935411,0.7715007,0.00014804122,0.00033199048],"about_ca_topic_score_codex":0.000088867535,"about_ca_topic_score_gemma":0.00009900972,"teacher_disagreement_score":0.7160507,"about_ca_system_score_codex":0.0006614747,"about_ca_system_score_gemma":0.0004203589,"threshold_uncertainty_score":0.9998216},"labels":[],"label_agreement":null},{"id":"W4392231166","doi":"10.1101/2024.02.26.24303405","title":"Statistical pitfalls of multiple exposures in causal observational studies and tools to address them","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","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":"Western University","funders":"","keywords":"Observational study; Computer science; Statistical analysis; Data science; Econometrics; Risk analysis (engineering); Management science; Statistics; Medicine; Mathematics; Engineering","score_opus":0.48566379628747175,"score_gpt":0.47650119864697077,"score_spread":0.00916259764050098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392231166","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":[0.9857992,0.0006512548,0.011459035,0.00022207026,0.00019996476,0.0008128011,0.00041444274,0.0001824985,0.00025871926],"genre_scores_gemma":[0.8457201,0.00012907045,0.1535133,0.000048821865,0.00005863393,0.00035213353,0.000026593212,0.000041381005,0.00010993535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808687,0.00011579838,0.00071135367,0.00048040945,0.00036712553,0.00023842604],"domain_scores_gemma":[0.9955834,0.0035609792,0.00016207113,0.00040690703,0.00021261671,0.00007398746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063945993,0.00030377952,0.000725854,0.00014772957,0.000020512243,0.000049969265,0.0002558829,0.00018972151,0.000031009386],"category_scores_gemma":[0.0054429187,0.00025891053,0.000048237704,0.00013024914,0.00016131911,0.00007143907,0.0013995384,0.0005627863,0.000008298709],"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":[0.00014715454,0.00029002328,0.23846057,0.0097011775,0.0004505192,0.00019777994,0.0087027745,0.00016942233,0.009264145,0.7238484,0.004336669,0.0044313413],"study_design_scores_gemma":[0.0001308199,0.000070696675,0.07246881,0.001744808,0.000048679718,0.0000032433063,0.00034084468,0.000111097026,0.0067933486,0.9178993,0.00009303623,0.0002953314],"about_ca_topic_score_codex":0.000033607783,"about_ca_topic_score_gemma":0.0002754941,"teacher_disagreement_score":0.19405086,"about_ca_system_score_codex":0.00009064532,"about_ca_system_score_gemma":0.00009314327,"threshold_uncertainty_score":0.9999863},"labels":[],"label_agreement":null},{"id":"W4392284023","doi":"10.7189/jogh.14.04046","title":"Reporting of equity in observational epidemiology: A methodological review","year":2024,"lang":"en","type":"review","venue":"Journal of Global Health","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":"Queen's University; SickKids Foundation; Hospital for Sick Children; Women's College Hospital; Impact; Ottawa Hospital; Public Health Ontario; University of British Columbia; McMaster University; Ottawa Public Health; Western University; University of Toronto; Royal College of Physicians and Surgeons of Canada; Bruyère; University of Ottawa","funders":"","keywords":"Observational study; Epidemiology; Equity (law); MEDLINE; Medicine; Data science; Computer science; Political science; Internal medicine","score_opus":0.9527690064534525,"score_gpt":0.7736420090006217,"score_spread":0.17912699745283078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392284023","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":[0.00000237278,0.98219174,0.015322247,0.0011661398,0.00025687309,0.00065058505,0.000050806604,0.00003604873,0.00032319783],"genre_scores_gemma":[0.000001321018,0.7109851,0.28835565,0.00049359305,0.00011789268,0.00001913731,0.0000050955973,0.000014275707,0.000007888823],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9799879,0.003286444,0.015495251,0.0003061304,0.00047160388,0.0004526805],"domain_scores_gemma":[0.96198857,0.005422962,0.031657096,0.00036586067,0.00037345607,0.00019205036],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05773063,0.00036033124,0.008588943,0.00012531628,0.000022307988,0.0000049388127,0.0004957273,0.0003678841,0.00003139013],"category_scores_gemma":[0.10715706,0.00022355413,0.001123109,0.0008239797,0.000089372035,0.00010345304,0.00029163118,0.0014414733,0.0000030010824],"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":[0.000004525338,0.000059162423,0.000056717192,0.17538376,0.000064284264,0.00007558841,0.000004176581,2.0082841e-7,1.5841447e-8,0.15114816,0.013969488,0.6592339],"study_design_scores_gemma":[0.000030859486,0.00022595991,0.00004025899,0.25587508,0.0003232815,0.0011600415,0.000002936388,0.000001407184,3.196342e-8,0.5461709,0.1960609,0.0001083286],"about_ca_topic_score_codex":0.000026705633,"about_ca_topic_score_gemma":0.000021397389,"teacher_disagreement_score":0.65912557,"about_ca_system_score_codex":0.00273358,"about_ca_system_score_gemma":0.0044083274,"threshold_uncertainty_score":0.9702646},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4392289616","doi":"10.1111/ppe.13066","title":"Multiple mediators, causal assumptions and potential caveats","year":2024,"lang":"en","type":"editorial","venue":"Paediatric and Perinatal Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"University of British Columbia; National Institute of Environmental Health Sciences; National Heart and Lung Institute","keywords":"Medicine","score_opus":0.06783392576210283,"score_gpt":0.3945308558003913,"score_spread":0.3266969300382885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392289616","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":[0.0054742815,0.032551218,0.02064745,0.0009324225,0.934376,0.00094941433,0.0033962522,0.0012661058,0.00040687126],"genre_scores_gemma":[0.018850653,0.02994099,0.037285123,0.00011054974,0.9107937,0.00036765973,0.0008272906,0.00022602938,0.0015980039],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99653256,0.0004991842,0.0009356074,0.0010274778,0.00029098743,0.00071418344],"domain_scores_gemma":[0.9764019,0.02234677,0.00037802113,0.00041079585,0.00014497641,0.00031751994],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017550514,0.0006452505,0.0014165788,0.000340348,0.00018334443,0.0000379042,0.0002600908,0.0020199786,0.00008238025],"category_scores_gemma":[0.029474068,0.0005607917,0.00017581055,0.00017514227,0.00047598992,0.00014649256,0.0006381512,0.0019665444,0.00004306694],"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":[0.000032648815,0.000020669995,0.0007898787,0.0009920774,0.000095419346,0.00010258329,0.00009512676,0.0000012098085,0.000007846519,0.012564361,0.9827305,0.002567695],"study_design_scores_gemma":[0.00039306853,0.00026104855,0.00023256803,0.00008467296,0.00037490317,0.0000898878,0.00003349719,0.000442733,0.0000044968933,0.31712657,0.6802439,0.0007126537],"about_ca_topic_score_codex":0.00019872957,"about_ca_topic_score_gemma":0.000069909824,"teacher_disagreement_score":0.3045622,"about_ca_system_score_codex":0.000117982956,"about_ca_system_score_gemma":0.0001808889,"threshold_uncertainty_score":0.99968433},"labels":[],"label_agreement":null},{"id":"W4392302028","doi":"10.23736/s1973-9087.24.08435-1","title":"Introduction to target trial emulation in rehabilitation: a systematic approach to emulate a randomized controlled trial using observational data","year":2024,"lang":"en","type":"article","venue":"European Journal of Physical and Rehabilitation Medicine","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":"Canadian Memorial Chiropractic College; University of Alberta; Ontario Tech University","funders":"Canada Research Chairs","keywords":"Randomized controlled trial; Observational study; Causal inference; Rehabilitation; Emulation; Medicine; Context (archaeology); Counterfactual thinking; Population; Psychological intervention; Physical medicine and rehabilitation; Physical therapy; Psychology; Nursing; Social psychology; Surgery","score_opus":0.13415060138641638,"score_gpt":0.4083997131747009,"score_spread":0.27424911178828454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392302028","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":[0.63299453,0.0001780344,0.34461504,0.011272174,0.00085057336,0.009816763,0.000005308917,0.00008053748,0.00018706212],"genre_scores_gemma":[0.7169124,0.000003202166,0.27853566,0.00007248546,0.0042304825,0.00012980182,0.000016210706,0.000037492588,0.000062284176],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9933361,0.003247608,0.0021928947,0.00039160793,0.0006771636,0.00015464393],"domain_scores_gemma":[0.98827654,0.010235205,0.0005502291,0.00035987401,0.00043175588,0.00014640126],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014083195,0.00022238705,0.0017399959,0.000582737,0.00005369232,0.000052669802,0.00021765321,0.000032053664,0.000012334072],"category_scores_gemma":[0.04419989,0.00013553209,0.00019722503,0.00062193954,0.00017128118,0.00054363615,0.000072810195,0.00028232412,0.0000036551412],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9001608,0.0007453665,0.0000023214836,0.0038437191,0.0001827396,0.000011365469,0.016940163,0.004490949,0.0021982964,0.068972915,0.0021736524,0.00027774158],"study_design_scores_gemma":[0.8106087,0.005286942,0.000046792862,0.005009865,0.00040227114,0.000022376196,0.0011585928,0.088808216,0.000005045979,0.08834752,0.00010272245,0.000200973],"about_ca_topic_score_codex":0.0000027055762,"about_ca_topic_score_gemma":4.4023724e-7,"teacher_disagreement_score":0.089552075,"about_ca_system_score_codex":0.00012315794,"about_ca_system_score_gemma":0.00007711276,"threshold_uncertainty_score":0.9638512},"labels":[],"label_agreement":null},{"id":"W4392505897","doi":"10.2196/47744","title":"Real-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Relevance (law); Terminology; Discontinuation; Quality (philosophy); Descriptive statistics; Data quality; Real world data; Medical physics; Computer science; Internal medicine; Statistics; Data science; Operations management; Mathematics","score_opus":0.43328506035763853,"score_gpt":0.6275695511884054,"score_spread":0.19428449083076688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392505897","genre_codex":"empirical","genre_gemma":"methods","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":[0.76480204,0.000009300191,0.22651842,0.0010624181,0.000117113326,0.00645227,0.0003156578,0.0004187935,0.00030399184],"genre_scores_gemma":[0.48956022,0.00004587846,0.5048692,0.0003297673,0.00027720968,0.0033727176,0.0011417365,0.00005305595,0.0003501781],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99763227,0.00020719234,0.001023135,0.0002266953,0.0006732589,0.00023742382],"domain_scores_gemma":[0.99542636,0.0033673858,0.00024320673,0.00061699474,0.00015706156,0.00018897944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032344193,0.00019126406,0.0003634939,0.00017798117,0.00009619612,0.00016593776,0.00018226307,0.0001141076,0.00030223516],"category_scores_gemma":[0.0016147288,0.00014867226,0.000032214404,0.00028753426,0.00006277128,0.0009317819,0.00020703133,0.000173216,0.0000298891],"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":[0.000049066806,0.00041291196,0.00025154406,0.00013892993,0.00012308349,0.000025638807,0.018898278,0.0000014026747,0.0000084748235,0.04333029,0.005631905,0.9311285],"study_design_scores_gemma":[0.0061946516,0.014245243,0.0045645214,0.0013706755,0.0020149483,0.000309006,0.09255243,0.36000434,0.0006342296,0.43691635,0.079180956,0.0020126558],"about_ca_topic_score_codex":0.00018192973,"about_ca_topic_score_gemma":0.0029027094,"teacher_disagreement_score":0.92911583,"about_ca_system_score_codex":0.000521013,"about_ca_system_score_gemma":0.00027722458,"threshold_uncertainty_score":0.60626787},"labels":[],"label_agreement":null},{"id":"W4392822382","doi":"10.48550/arxiv.2403.08130","title":"Imputation of Counterfactual Outcomes when the Errors are Predictable","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Counterfactual thinking; Imputation (statistics); Econometrics; Statistics; Computer science; Missing data; Psychology; Economics; Mathematics; Social psychology","score_opus":0.22674297205928162,"score_gpt":0.29453571847325416,"score_spread":0.06779274641397254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392822382","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":[0.79709,0.00007992149,0.196849,0.00021974315,0.0004025006,0.00078312785,0.0002334614,0.00071391853,0.003628314],"genre_scores_gemma":[0.9947452,0.00005491101,0.0021152257,0.000035908746,0.00003194123,0.000003585112,0.000014965498,0.00004424565,0.0029540306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987038,0.000092886505,0.0003170782,0.000513011,0.00013674068,0.00023649784],"domain_scores_gemma":[0.99789315,0.0005143263,0.0005020031,0.0008203092,0.00021433663,0.000055851422],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003041365,0.0003149163,0.00046872714,0.00017520241,0.00006772921,0.00003669604,0.00068740867,0.00029234035,0.00010610989],"category_scores_gemma":[0.0002509518,0.00025067033,0.00021786641,0.00019032884,0.00020705118,0.00013100702,0.0011984465,0.000755696,0.000030027099],"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":[0.00011811985,0.0002803276,0.014253599,0.0022563557,0.0010066457,0.00020039931,0.0046532163,0.044063915,0.00017257086,0.9204846,0.01214785,0.00036237188],"study_design_scores_gemma":[0.00012745189,0.00004182469,0.00038625507,0.00035273493,0.0003080978,0.0000018273677,0.0009724332,0.015444353,0.0007543171,0.9812366,0.00013061942,0.00024348339],"about_ca_topic_score_codex":0.00012097671,"about_ca_topic_score_gemma":0.000100718906,"teacher_disagreement_score":0.19765517,"about_ca_system_score_codex":0.00023131291,"about_ca_system_score_gemma":0.00013065539,"threshold_uncertainty_score":0.9999946},"labels":[],"label_agreement":null},{"id":"W4392846070","doi":"10.1086/730455","title":"Do Preregistration and Preanalysis Plans Reduce <i>p</i>-Hacking and Publication Bias? Evidence from 15,992 Test Statistics and Suggestions for Improvement","year":2024,"lang":"en","type":"article","venue":"Journal of Political Economy Microeconomics","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":"Wilfrid Laurier University; University of Ottawa","funders":"Leibniz-Gemeinschaft","keywords":"Statistics; Test (biology); Hacker; Publication bias; Psychology; Computer science; Data science; Computer security; Mathematics; Biology","score_opus":0.12121629860942378,"score_gpt":0.3940866936875985,"score_spread":0.27287039507817473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392846070","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":[0.495824,0.0010716105,0.4941866,0.006673084,0.00010043484,0.00057016686,0.0012036873,0.00005878857,0.00031160645],"genre_scores_gemma":[0.84552,0.00042462084,0.15349689,0.00022512174,0.00021026078,0.00002884903,0.000023274375,0.000025493564,0.000045461595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856466,0.000026981397,0.0008487074,0.00028462466,0.00004348041,0.00023155834],"domain_scores_gemma":[0.9948771,0.004086647,0.0003861826,0.00017817797,0.0002658759,0.00020601488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064367143,0.00016733067,0.00034320855,0.00016375161,0.00007261874,0.00056424824,0.000102638376,0.00009505099,0.000019880034],"category_scores_gemma":[0.0021192306,0.00016231838,0.000052161104,0.00003621793,0.00015796024,0.00083298393,0.00005636935,0.00020293318,9.0518654e-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":[0.000027034275,0.000051141167,0.0023631288,0.0003501847,0.0001802206,0.0000031551679,0.00034109154,0.000003674104,0.004994413,0.97766495,0.0020393915,0.011981591],"study_design_scores_gemma":[0.00027904395,0.00032963548,0.00071473856,0.00038178355,0.00039419346,0.00010356991,0.00038563606,0.007116362,0.010033001,0.9783291,0.0016955768,0.00023734079],"about_ca_topic_score_codex":0.000033177937,"about_ca_topic_score_gemma":0.00005479665,"teacher_disagreement_score":0.349696,"about_ca_system_score_codex":0.00022797915,"about_ca_system_score_gemma":0.00016649204,"threshold_uncertainty_score":0.6619151},"labels":[],"label_agreement":null},{"id":"W4392938758","doi":"10.1111/jebm.12600","title":"Handling time‐varying treatments in observational studies: A scoping review and recommendations","year":2024,"lang":"en","type":"review","venue":"Journal of Evidence-Based Medicine","topic":"Advanced Causal Inference Techniques","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":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"National Natural Science Foundation of China","keywords":"Observational study; Protocol (science); Workflow; Observational methods in psychology; Computer science; Set (abstract data type); Process (computing); Medical physics; Management science; Selection (genetic algorithm); Medicine; Alternative medicine; Machine learning; Engineering","score_opus":0.833002005037274,"score_gpt":0.6314645032262648,"score_spread":0.20153750181100916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392938758","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":[0.0000011530515,0.9912341,0.0011485246,0.005989903,0.00020208232,0.0013498343,0.00000756657,0.000040603754,0.00002622278],"genre_scores_gemma":[5.276739e-7,0.9681724,0.030632144,0.00053262536,0.0003106679,0.00013449503,0.0000151311915,0.000048858994,0.00015316495],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99582946,0.00041098087,0.0027154656,0.00030272902,0.0005074122,0.00023396892],"domain_scores_gemma":[0.9873541,0.00973238,0.0020441106,0.00027366905,0.00047059535,0.0001251366],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040293713,0.00046551984,0.0036990563,0.00073972205,0.00006453998,0.000022503344,0.00025672055,0.00014566565,0.00012918748],"category_scores_gemma":[0.017628001,0.00025716273,0.00026772136,0.00080474035,0.00013237819,0.00048470555,0.00007844762,0.00080942974,0.0000073163555],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012553236,0.00008026924,0.0000059395916,0.5247491,0.0006466462,0.00020852653,0.0001921479,0.0000013013026,0.0000039709453,0.00038582415,0.01209285,0.46162087],"study_design_scores_gemma":[0.00025888399,0.0003458553,1.9003845e-7,0.9668669,0.0066588726,0.00015291736,0.00002379945,0.000010822493,0.0000019485892,0.008415849,0.017065698,0.00019825892],"about_ca_topic_score_codex":0.0000024310846,"about_ca_topic_score_gemma":0.0000033845622,"teacher_disagreement_score":0.46142262,"about_ca_system_score_codex":0.0007047621,"about_ca_system_score_gemma":0.001044717,"threshold_uncertainty_score":0.9999881},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4393008884","doi":"10.1186/s12874-024-02156-y","title":"An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"McGill University; McGill University Health Centre; Université de Montréal; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Outcome (game theory); Estimator; Context (archaeology); Mediation; Logistic regression; Causal inference; Statistics; Binary number; Regression analysis; Parametric statistics; Regression; Computer science; Econometrics; Mathematics","score_opus":0.8753729356200297,"score_gpt":0.6686037868933843,"score_spread":0.20676914872664542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393008884","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":[0.38238388,0.00040026344,0.61186725,0.00038457641,0.000072568444,0.0046891663,0.00007731073,0.00012164977,0.000003341555],"genre_scores_gemma":[0.5899888,0.000017719887,0.40540534,0.000027702556,0.0001384321,0.0043398403,0.0000227106,0.000048948656,0.000010477089],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97958297,0.016219204,0.0009958225,0.0008522554,0.0017041528,0.00064562215],"domain_scores_gemma":[0.84567976,0.15268336,0.00017645684,0.00040238243,0.0006438909,0.00041413525],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0906725,0.0002863589,0.0010418494,0.0006614878,0.00018614152,0.00004810103,0.00027051865,0.0005131958,0.000121583296],"category_scores_gemma":[0.21931003,0.00018605673,0.00009321883,0.0003984308,0.0007234795,0.00018788243,0.0001233611,0.0005852776,3.712569e-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":[0.028044162,0.0068088863,0.061602447,0.021651007,0.0011091353,0.0017398184,0.017264966,0.00011474491,0.017395206,0.03139863,0.0037224276,0.80914855],"study_design_scores_gemma":[0.0047132056,0.008311931,0.0009586082,0.00025291782,0.0004051929,0.00017802321,0.0050798533,0.8613454,0.0007751282,0.11770263,0.000019133633,0.0002579667],"about_ca_topic_score_codex":0.000022759046,"about_ca_topic_score_gemma":0.00026472917,"teacher_disagreement_score":0.8612307,"about_ca_system_score_codex":0.00014865721,"about_ca_system_score_gemma":0.0018514836,"threshold_uncertainty_score":0.936344},"labels":[],"label_agreement":null},{"id":"W4393132304","doi":"10.1016/j.envint.2024.108602","title":"A tool to assess risk of bias in non-randomized follow-up studies of exposure effects (ROBINS-E)","year":2024,"lang":"en","type":"article","venue":"Environment International","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":806,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; McMaster University; Ottawa Hospital; Impact","funders":"Medical Research Council; National Institute of Environmental Health Sciences; National Institute for Health and Care Research; National Institutes of Health; Cancer Research UK; CHDI Foundation; National Council for Air and Stream Improvement; NIHR Bristol Biomedical Research Centre; United Soybean Board","keywords":"Randomized controlled trial; Environmental health; Environmental science; Medicine; Internal medicine","score_opus":0.12522902878883774,"score_gpt":0.40282318924047794,"score_spread":0.2775941604516402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393132304","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":[0.94094336,0.0002154607,0.057091676,0.000087042696,0.00034312974,0.0007042056,0.000045545792,0.000047362268,0.00052220735],"genre_scores_gemma":[0.9564459,0.00036625817,0.04219811,0.000019799867,0.000033222408,0.00027538478,0.0000066485477,0.00001998069,0.00063469284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986017,0.00013466037,0.0005435788,0.00021153053,0.00039602612,0.00011254267],"domain_scores_gemma":[0.99685454,0.00272239,0.00017442649,0.00019791888,0.000028477389,0.00002222618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009781662,0.00015137083,0.00048606496,0.0002050435,0.000010514449,0.000008858913,0.00019413138,0.000054438693,0.00012428025],"category_scores_gemma":[0.001942199,0.00012276976,0.0001466754,0.00008213105,0.00011202237,0.000089270674,0.00015909954,0.00013828943,0.000019279418],"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":[0.014335889,0.0026668278,0.031742647,0.003935367,0.007156226,0.00017951692,0.03528987,0.007473036,0.22994861,0.6161821,0.008145136,0.04294479],"study_design_scores_gemma":[0.03230687,0.0006607444,0.005584974,0.0032527056,0.00035836318,0.000005187832,0.00082005066,0.0027833432,0.3658728,0.5863158,0.0013684058,0.00067073],"about_ca_topic_score_codex":0.000012222779,"about_ca_topic_score_gemma":0.0000069165026,"teacher_disagreement_score":0.13592419,"about_ca_system_score_codex":0.0001687247,"about_ca_system_score_gemma":0.0000130007575,"threshold_uncertainty_score":0.5006406},"labels":[],"label_agreement":null},{"id":"W4393140763","doi":"10.1109/incc58754.2023.00013","title":"Short-term and Long-term Causal Effect Estimation with Double-head Transformer","year":2023,"lang":"en","type":"article","venue":"","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":"Western University","funders":"","keywords":"Term (time); Computer science; Transformer; Estimation; Artificial intelligence; Risk analysis (engineering); Machine learning; Reliability engineering; Econometrics; Engineering; Mathematics; Systems engineering","score_opus":0.11039837924466502,"score_gpt":0.41948003132210654,"score_spread":0.30908165207744154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393140763","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":[0.7494796,0.000008112521,0.24619734,0.00007367803,0.000023403802,0.0006521557,0.0000031753598,0.0011800405,0.0023824961],"genre_scores_gemma":[0.981126,0.000026308539,0.017892784,0.000016938933,0.000022975244,0.00016209845,0.000031503085,0.000045678968,0.00067572953],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989681,0.000025153347,0.00022070234,0.00026245636,0.00022655996,0.00029697688],"domain_scores_gemma":[0.9992752,0.000303696,0.000037206926,0.00025477677,0.0000418407,0.000087287575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025495986,0.00022477075,0.00027320252,0.00012296821,0.000078272555,0.000051582687,0.0000924781,0.000102920516,0.000068536516],"category_scores_gemma":[0.00002487405,0.00015629253,0.000033341927,0.00023473143,0.000090870766,0.00035028404,0.00002184904,0.00015311434,0.000033998447],"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":[0.001625563,0.0003587357,0.30146375,0.003961974,0.00034318274,0.0005169644,0.0028905112,0.00008144753,0.06194751,0.17505555,0.0019638033,0.449791],"study_design_scores_gemma":[0.0065215346,0.004590885,0.26159117,0.0016814142,0.00064189226,0.000504474,0.0001235816,0.0051494525,0.59402955,0.122527875,0.00006311853,0.002575037],"about_ca_topic_score_codex":0.000007929199,"about_ca_topic_score_gemma":0.00017458502,"teacher_disagreement_score":0.532082,"about_ca_system_score_codex":0.000038538812,"about_ca_system_score_gemma":0.000015840898,"threshold_uncertainty_score":0.63734245},"labels":[],"label_agreement":null},{"id":"W4393325638","doi":"10.1177/25152459241236149","title":"The Causal Cookbook: Recipes for Propensity Scores, G-Computation, and Doubly Robust Standardization","year":2024,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","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":"Université de Montréal","funders":"Institut de Valorisation des Données","keywords":"Causal inference; Observational study; Identification (biology); Computer science; Consistency (knowledge bases); Causal model; Inference; Variable (mathematics); Estimator; Instrumental variable; Econometrics; Data science; Toolbox; Machine learning; Artificial intelligence; Mathematics; Statistics","score_opus":0.2889949678395071,"score_gpt":0.6290214928348979,"score_spread":0.3400265249953908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393325638","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":[0.016573256,0.0058718855,0.973198,0.0010322203,0.00032229652,0.00068875676,0.000003363334,0.00009093989,0.0022192944],"genre_scores_gemma":[0.12945013,0.006308665,0.86397696,0.000082596445,0.000034081837,0.00010720439,6.1049593e-7,0.0000074288505,0.000032337946],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981211,0.00039939306,0.00035960574,0.00060331787,0.0002287429,0.00028787428],"domain_scores_gemma":[0.9910381,0.008372883,0.00024017428,0.00017355758,0.00012028524,0.000054992386],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010598188,0.00013346593,0.00019846085,0.00010354345,0.00030507738,0.0003376156,0.00024157258,0.000072058196,0.000003572419],"category_scores_gemma":[0.011424905,0.000079115875,0.000015242282,0.00071037235,0.0010396912,0.0017942325,0.00010610081,0.0003027247,2.3951006e-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":[0.00015581728,0.000043396798,0.0012763656,0.00007696341,0.0000024850076,0.000007969004,0.0002929807,0.00030029338,0.00097617286,0.292982,0.00006367321,0.70382184],"study_design_scores_gemma":[0.00016856453,0.00024913443,0.0019163225,0.000119678974,0.000007565532,0.000029387158,0.00011957343,0.0072812317,0.0004966794,0.9709937,0.018473271,0.00014490545],"about_ca_topic_score_codex":0.0000070637584,"about_ca_topic_score_gemma":0.00009482528,"teacher_disagreement_score":0.70367694,"about_ca_system_score_codex":0.000059721573,"about_ca_system_score_gemma":0.00003958544,"threshold_uncertainty_score":0.9969023},"labels":[],"label_agreement":null},{"id":"W4393900325","doi":"10.3389/fepid.2024.1326306","title":"Making predictions under interventions: a case study from the PREDICT-CVD cohort in New Zealand primary care","year":2024,"lang":"en","type":"article","venue":"Frontiers in Epidemiology","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":"Artificial Intelligence in Medicine (Canada)","funders":"NIHR Cambridge Biomedical Research Centre; Economic and Social Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Medical Research Council; National Heart Foundation of New Zealand; Public Health Agency; Department of Health and Social Care; UK Research and Innovation; Engineering and Physical Sciences Research Council; Health and Social Care Research and Development Division; National Institute for Health and Care Research; Scottish Government; British Heart Foundation; Wellcome Trust","keywords":"Causal inference; Psychological intervention; Medicine; Absolute risk reduction; Estimation; Observational study; Blood pressure; Cohort; Marginal structural model; Cohort study; Risk assessment; Econometrics; Statistics; Confidence interval; Internal medicine; Computer science; Mathematics","score_opus":0.258877684922014,"score_gpt":0.47204901177817493,"score_spread":0.21317132685616091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393900325","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":[0.21671472,0.010614115,0.7666312,0.0010503886,0.001662022,0.0020298061,0.00010769622,0.0005623116,0.0006277427],"genre_scores_gemma":[0.87606007,0.00030284314,0.1217768,0.00041399678,0.00027140655,0.0005399095,0.00007621123,0.00005788803,0.0005009051],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99674636,0.0011409377,0.0010366476,0.00055277214,0.00010913057,0.00041416968],"domain_scores_gemma":[0.9955493,0.0036274367,0.00015421388,0.000573278,0.000032937023,0.000062823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018175759,0.00023846983,0.00068761106,0.0002779627,0.00007555917,0.000021048883,0.0003079067,0.00023420624,0.000035407218],"category_scores_gemma":[0.0019154822,0.00018175978,0.00015591599,0.0003820669,0.00015828734,0.00018218499,0.00019487133,0.00084717554,0.0000041431026],"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":[0.000024796085,0.00012640857,0.90602815,0.000094543066,0.00016646847,0.0006594948,0.0046749683,0.0003086766,0.0000012361699,0.0039679315,0.078276075,0.005671259],"study_design_scores_gemma":[0.0005798396,0.00027789504,0.12332955,0.0016699983,0.00024628988,0.00027541353,0.02186995,0.003353345,0.0000017720816,0.8466444,0.0014673127,0.000284231],"about_ca_topic_score_codex":0.0026075807,"about_ca_topic_score_gemma":0.007511946,"teacher_disagreement_score":0.84267646,"about_ca_system_score_codex":0.00066458614,"about_ca_system_score_gemma":0.00016991877,"threshold_uncertainty_score":0.74119484},"labels":[],"label_agreement":null},{"id":"W4393985972","doi":"10.1002/pds.5790","title":"Clarifying the causal contrast: An empirical example applying the prevalent new user study design","year":2024,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"University of North Carolina at Chapel Hill; Cecil G. Sheps Center for Health Services Research, University of North Carolina, Chapel Hill; Agency for Healthcare Research and Quality","keywords":"Medicine; Propensity score matching; Hazard ratio; Confounding; Pharmacoepidemiology; Internal medicine; Population; Weighting; Oncology; Pharmacology; Environmental health; Confidence interval; Medical prescription","score_opus":0.3642857016108703,"score_gpt":0.503481748549599,"score_spread":0.13919604693872872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393985972","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":[0.025110498,0.0032646295,0.9590839,0.0075037596,0.00040254547,0.003561708,0.000011598847,0.00078749296,0.00027386475],"genre_scores_gemma":[0.97232217,0.00070434436,0.021595247,0.003339617,0.00059138425,0.00086678594,0.000006519296,0.000062326326,0.00051158195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937094,0.004306021,0.0006997531,0.00058789284,0.00017960164,0.00051736867],"domain_scores_gemma":[0.97717863,0.021990852,0.00013525566,0.0004833976,0.00004372227,0.00016814617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010666795,0.0003291054,0.0004973648,0.000053595846,0.0005458002,0.000057514313,0.0004318704,0.00013561187,0.00015991459],"category_scores_gemma":[0.0013809078,0.00017252706,0.000088116576,0.00018498072,0.00027604317,0.0002877307,0.00021954755,0.0011881599,0.000015767118],"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":[0.0014483327,0.0011880622,0.05724077,0.0005166175,0.0017888898,0.00022516031,0.047504064,0.0017474191,0.0036481633,0.3672974,0.29463017,0.22276494],"study_design_scores_gemma":[0.001473673,0.00046385737,0.0067916857,0.00016203539,0.0011254882,0.00020331351,0.0038286785,0.03786434,0.0014113912,0.8124683,0.13331956,0.00088770327],"about_ca_topic_score_codex":0.00023122587,"about_ca_topic_score_gemma":0.000078524856,"teacher_disagreement_score":0.9472117,"about_ca_system_score_codex":0.00006612575,"about_ca_system_score_gemma":0.000110257344,"threshold_uncertainty_score":0.7035449},"labels":[],"label_agreement":null},{"id":"W4394780946","doi":"10.48550/arxiv.2404.07411","title":"Joint mixed-effects models for causal inference in clustered network-based observational studies","year":2024,"lang":"en","type":"preprint","venue":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Alliance de recherche numérique du Canada","keywords":"Causal inference; Inference; Observational study; Context (archaeology); Confounding; Econometrics; Computer science; Outcome (game theory); Generalized linear mixed model; Mixed model; Random effects model; Bayesian inference; Multilevel model; Bayesian probability; Machine learning; Statistics; Artificial intelligence; Mathematics; Meta-analysis; Medicine; Geography","score_opus":0.36679597903241584,"score_gpt":0.4424464871940364,"score_spread":0.07565050816162056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394780946","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":[0.3269774,0.0046352227,0.6547315,0.0021821517,0.003912676,0.004913782,0.00028105936,0.0020472764,0.00031894055],"genre_scores_gemma":[0.7029932,0.0003570282,0.29311556,0.00040946685,0.0008839647,0.0015763968,0.00020010905,0.0002639301,0.00020034157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99354345,0.00053438544,0.0022319758,0.0015793066,0.0008223305,0.0012885516],"domain_scores_gemma":[0.9881147,0.008540488,0.0010770368,0.0011715527,0.00088993093,0.00020628257],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0029639977,0.0012917351,0.0020814703,0.00079515495,0.0003176358,0.00034101564,0.00095375144,0.00090629427,0.0000053200843],"category_scores_gemma":[0.005410077,0.0012116606,0.0006593321,0.0005957358,0.00024244023,0.0002626283,0.0016022879,0.0030176186,0.000010685692],"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":[0.00038802132,0.0006740541,0.0006294215,0.013805265,0.0015205657,0.00046320792,0.0073338132,0.36620617,0.003711335,0.5857612,0.015392911,0.004114032],"study_design_scores_gemma":[0.0006680324,0.00023377512,0.000057394835,0.009942064,0.00030964505,0.000009538836,0.00016262449,0.15088056,0.0059198216,0.8306446,0.00009812836,0.0010738327],"about_ca_topic_score_codex":0.000031713796,"about_ca_topic_score_gemma":0.00026505225,"teacher_disagreement_score":0.3760158,"about_ca_system_score_codex":0.0009823594,"about_ca_system_score_gemma":0.00097058347,"threshold_uncertainty_score":0.99998343},"labels":[],"label_agreement":null},{"id":"W4394782483","doi":"10.1093/biomet/asae021","title":"Sensitivity analysis for matched observational studies with continuous exposures and binary outcomes","year":2024,"lang":"en","type":"article","venue":"Biometrika","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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 Institutes of Health; York University","keywords":"Sensitivity (control systems); Mathematics; Binary number; Observational study; Matching (statistics); Statistics; Binary data; Population; Econometrics; Medicine","score_opus":0.34501543094769704,"score_gpt":0.4661735827427737,"score_spread":0.12115815179507666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394782483","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":[0.81577826,0.0015324048,0.18075103,0.00074090896,0.00006140827,0.00042239676,0.00012799072,0.0005428195,0.00004278205],"genre_scores_gemma":[0.8525074,0.000068626825,0.1466942,0.000061767314,0.000029400837,0.00009232028,0.000020764355,0.000020863927,0.00050463335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990579,0.000039580314,0.00023436027,0.00029184343,0.00020269184,0.00017360572],"domain_scores_gemma":[0.99588567,0.0035981447,0.000074911004,0.00019303377,0.00020775956,0.00004050427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005899311,0.00017309719,0.00051183806,0.0008515581,0.00006762673,0.00006353741,0.000049155704,0.00006209459,0.000007598658],"category_scores_gemma":[0.0010988489,0.00011833163,0.00010328307,0.0019135787,0.00012341392,0.00017410757,0.00005760834,0.000062618994,0.0000014184459],"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":[0.00021764557,0.0003771269,0.67966115,0.0019899267,0.015337222,0.00022531662,0.0022860463,0.000025562314,0.02455562,0.24924366,0.008470243,0.017610488],"study_design_scores_gemma":[0.0012409835,0.0016308733,0.51209056,0.00045178845,0.0047097807,0.000047230795,0.0030364497,0.0028430286,0.030528793,0.43677795,0.005122071,0.0015205045],"about_ca_topic_score_codex":0.00001143581,"about_ca_topic_score_gemma":0.00004471,"teacher_disagreement_score":0.1875343,"about_ca_system_score_codex":0.000054830944,"about_ca_system_score_gemma":0.000025611407,"threshold_uncertainty_score":0.4825424},"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":"W4394872301","doi":"10.1093/aje/kwae048","title":"Variable selection when estimating effects in external target populations","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Covariate; Statistics; Outcome (game theory); Selection (genetic algorithm); Inverse probability weighting; Weighting; Selection bias; Econometrics; Medicine; Mathematics; Computer science; Machine learning; Propensity score matching","score_opus":0.12775130415988278,"score_gpt":0.45730091661832684,"score_spread":0.32954961245844405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394872301","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":[0.0075673624,0.00043036856,0.9906745,0.00052372104,0.0003896335,0.00009453024,0.0000012778164,0.00008841311,0.0002301997],"genre_scores_gemma":[0.078983516,0.000002456698,0.92047274,0.00023619381,0.00023800241,0.000010830809,8.9220913e-7,0.000021573827,0.000033769385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977466,0.0007448553,0.0009595405,0.0001662185,0.00008065188,0.0003021718],"domain_scores_gemma":[0.9926896,0.006406263,0.0006281461,0.00011327867,0.00008122208,0.00008149517],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032279168,0.0001331268,0.00066832075,0.00031402527,0.000034251094,0.000010145644,0.00014916145,0.00006176811,0.00007243069],"category_scores_gemma":[0.012741099,0.0001113754,0.000089618305,0.0003435942,0.0001272067,0.00025079137,0.000029363495,0.0005615901,0.0000049770574],"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":[0.000013764202,0.000026955724,0.013648705,0.000048227834,0.000024077046,0.000028234876,0.00016711859,0.0021438582,0.00066863815,0.9718115,0.0011569503,0.010262004],"study_design_scores_gemma":[0.00006953412,0.00045659428,0.0008985162,0.0004667085,0.0000224051,0.00035653252,0.00002605045,0.03406953,0.000089662906,0.96315026,0.00030012446,0.00009406709],"about_ca_topic_score_codex":0.00015689943,"about_ca_topic_score_gemma":0.000010754736,"teacher_disagreement_score":0.07141615,"about_ca_system_score_codex":0.00019516778,"about_ca_system_score_gemma":0.00007961748,"threshold_uncertainty_score":0.995575},"labels":[],"label_agreement":null},{"id":"W4394958256","doi":"10.1186/s12874-024-02210-9","title":"Application of causal inference methods in individual-participant data meta-analyses in medicine: addressing data handling and reporting gaps with new proposed reporting guidelines","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","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":"University of British Columbia","funders":"Institute of Genetics; National Institute on Alcohol Abuse and Alcoholism; Universitätsklinikum Heidelberg; Canadian Institutes of Health Research; European Commission","keywords":"Causal inference; Inference; MEDLINE; Meta-analysis; Data science; Computer science; Medicine; Psychology; Data mining; Artificial intelligence","score_opus":0.9950486106954662,"score_gpt":0.8322164748674158,"score_spread":0.16283213582805045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394958256","genre_codex":"review","genre_gemma":"methods","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":[0.0000078617195,0.51387644,0.48457366,0.00019607638,0.0000373722,0.0011789558,0.000027515716,0.000072054754,0.000030039904],"genre_scores_gemma":[0.00001574113,0.4071996,0.5919271,0.000014663951,0.00017660267,0.0002376635,0.00032355465,0.00007550068,0.000029560375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9055645,0.04879054,0.031557504,0.0055107926,0.0061618746,0.002414777],"domain_scores_gemma":[0.39232743,0.5349138,0.04785432,0.01951433,0.0032423832,0.002147754],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33174077,0.0007644609,0.009966109,0.0020330527,0.0000967391,0.00008062248,0.0033581357,0.0010299422,0.0001023519],"category_scores_gemma":[0.89496875,0.0004392756,0.0001955549,0.0030624892,0.0014829874,0.0003970282,0.0068161907,0.0040823002,0.0000013989803],"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":[0.00003788037,0.00007412397,0.0001170925,0.038651254,0.0019913423,0.00042985004,0.00050435524,0.000004901753,0.0001837941,0.0027477778,0.0006714506,0.95458615],"study_design_scores_gemma":[0.0017069118,0.0010718121,0.0000705219,0.2623882,0.10037695,0.0026136488,0.004059404,0.040384274,0.0008069925,0.4948292,0.088761695,0.0029303757],"about_ca_topic_score_codex":0.004615001,"about_ca_topic_score_gemma":0.008151507,"teacher_disagreement_score":0.9516558,"about_ca_system_score_codex":0.00011248483,"about_ca_system_score_gemma":0.008537846,"threshold_uncertainty_score":0.9998059},"labels":[],"label_agreement":null},{"id":"W4395078282","doi":"10.1080/00949655.2024.2344126","title":"A threshold mixed-effects Tobit model for treatment-sensitive subgroup identification based on longitudinal measures with floor and ceiling effects and a continuous covariate","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Covariate; Tobit model; Statistics; Econometrics; Ceiling effect; Ceiling (cloud); Medicine","score_opus":0.09827815014044103,"score_gpt":0.39856960133919783,"score_spread":0.3002914511987568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395078282","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":[0.24616109,0.00007340126,0.7532055,0.000041422347,0.000034030625,0.00042567818,0.00001812664,0.0000360851,0.0000046993205],"genre_scores_gemma":[0.8666883,0.000011009523,0.13320012,0.000022514125,0.000030077425,0.000013049292,0.000011962718,0.000016903525,0.0000060377347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990926,0.00007324993,0.00032545233,0.00019371438,0.00020742853,0.00010756687],"domain_scores_gemma":[0.99568594,0.0037471475,0.00017547715,0.0000448775,0.0002673757,0.000079164354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035049522,0.00015323295,0.00029674193,0.0001560153,0.000093005256,0.00015557997,0.000016512766,0.00005720589,4.3020964e-7],"category_scores_gemma":[0.00044761304,0.0001134199,0.000026711137,0.00007026392,0.0000640545,0.0002082718,0.000005957732,0.00008519551,1.688477e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002011627,0.0002218749,0.0007744024,0.0014980868,0.00020523679,0.000118355405,0.001286734,0.72438216,0.0022402066,0.1296368,0.000030556366,0.13759398],"study_design_scores_gemma":[0.0011465529,0.0011891901,0.004322703,0.00034484107,0.00019201117,0.00001976147,0.000023221703,0.85284024,0.00048770246,0.13933133,0.0000011155956,0.00010135411],"about_ca_topic_score_codex":0.0000025208617,"about_ca_topic_score_gemma":0.000005234218,"teacher_disagreement_score":0.6205272,"about_ca_system_score_codex":0.00006987114,"about_ca_system_score_gemma":0.00003606253,"threshold_uncertainty_score":0.4625129},"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":"W4396228487","doi":"10.1002/pds.5796","title":"Use of quantitative bias analysis to evaluate single‐arm trials with real‐world data external controls","year":2024,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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 of Toronto","funders":"International Society for Pharmacoepidemiology","keywords":"Publication bias; Confounding; Information bias; Meta-analysis; Econometrics; Statistics; Computer science; Selection bias; Medicine; Data mining; Internal medicine; Mathematics","score_opus":0.6914768235977365,"score_gpt":0.5761454646243113,"score_spread":0.11533135897342528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396228487","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":[0.12609611,0.0013226514,0.86534894,0.0035796033,0.0001706257,0.001199547,0.0011622813,0.00042945385,0.00069079996],"genre_scores_gemma":[0.6809683,0.0014992064,0.31597334,0.0007961399,0.000102897306,0.000072921095,0.000102368824,0.000040691502,0.00044411418],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99311733,0.004082486,0.0014806585,0.00072901446,0.00021670962,0.00037378195],"domain_scores_gemma":[0.94100416,0.057314932,0.0006260198,0.00069226057,0.00018757887,0.00017503394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018164566,0.00031642077,0.0019388193,0.00051752635,0.00007709328,0.000030638043,0.0003545488,0.000062846535,0.00016386971],"category_scores_gemma":[0.015285611,0.00021436837,0.00016827205,0.00093208445,0.00034103447,0.00047483805,0.00026726112,0.00034497093,0.000008129334],"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":[0.011889109,0.00088710507,0.03359597,0.00060805585,0.0149885,0.0001574143,0.0024313298,0.003357417,0.037300095,0.789237,0.0242928,0.08125517],"study_design_scores_gemma":[0.0040638,0.0025186406,0.012060632,0.0017900087,0.03198584,0.000052891013,0.0005433731,0.21512295,0.038613115,0.6525283,0.038348723,0.0023717443],"about_ca_topic_score_codex":0.0005372919,"about_ca_topic_score_gemma":0.0010130644,"teacher_disagreement_score":0.55487216,"about_ca_system_score_codex":0.00006179478,"about_ca_system_score_gemma":0.00007066565,"threshold_uncertainty_score":0.99300903},"labels":[],"label_agreement":null},{"id":"W4396640278","doi":"10.52058/2786-6025-2024-4(32)-1192-1205","title":"МЕТОД ІНТЕРПОЛЯЦІЇ ДЛЯ ПРОГНОЗУВАННЯ МЕТРИК ВИКОРИСТАННЯ ХМАРНИХ ОБЧИСЛЕНЬ В СТАТИСТИЧНОМУ НАВЧАННІ","year":2024,"lang":"uk","type":"article","venue":"Наука і техніка сьогодні","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":"Tellabs (Canada)","funders":"","keywords":"Political science","score_opus":0.21565560629080563,"score_gpt":0.47545511865320317,"score_spread":0.2597995123623975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396640278","genre_codex":"other","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":[0.024350397,0.060119487,0.25827855,0.012400879,0.016386796,0.010238099,0.0028076104,0.025480753,0.58993745],"genre_scores_gemma":[0.8334154,0.006496428,0.05719243,0.0022092287,0.0044600614,0.0010785555,0.00044381397,0.0018780725,0.09282602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98599494,0.00074859406,0.0035133727,0.0033889448,0.002494349,0.0038598224],"domain_scores_gemma":[0.98952436,0.0032053115,0.00092889165,0.004374926,0.0006652664,0.0013012211],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0026639353,0.0028808906,0.0028684677,0.0014807059,0.0008130617,0.0018183063,0.0029468557,0.0021268723,0.013177419],"category_scores_gemma":[0.0017452645,0.002864601,0.0015373867,0.0026072757,0.0012381864,0.0024809418,0.0017443692,0.003995774,0.017808558],"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":[0.00024337802,0.0011250381,0.00019569002,0.0049420944,0.001354834,0.0018556509,0.0048697204,0.00009956274,0.010273717,0.7171117,0.18892422,0.06900438],"study_design_scores_gemma":[0.0012639378,0.0011393293,0.00015101283,0.0041781915,0.0012762552,0.00047131153,0.0012908241,0.0066543976,0.022428235,0.51677024,0.4403754,0.0040008826],"about_ca_topic_score_codex":0.00036254738,"about_ca_topic_score_gemma":0.00025909333,"teacher_disagreement_score":0.809065,"about_ca_system_score_codex":0.0016389515,"about_ca_system_score_gemma":0.0016967417,"threshold_uncertainty_score":0.9992179},"labels":[],"label_agreement":null},{"id":"W4396646664","doi":"10.31234/osf.io/z4yqe","title":"Clarifying the reliability paradox: poor test-retest reliability attenuates group differences","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Causal Inference Techniques","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":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Reliability (semiconductor); Reliability engineering; Test (biology); Group (periodic table); Psychology; Computer science; Engineering; Chemistry; Physics; Biology","score_opus":0.1347329622286347,"score_gpt":0.39283176116411844,"score_spread":0.2580987989354837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396646664","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":[0.82144123,0.0016059917,0.080443345,0.029076895,0.0033445852,0.010530301,0.00079996564,0.01562145,0.03713621],"genre_scores_gemma":[0.8987977,0.00023143843,0.09754896,0.00033276217,0.00032305924,0.0011202669,0.000040634743,0.00014357976,0.001461626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99424934,0.0004686703,0.0015891902,0.0019284568,0.00091218855,0.0008521793],"domain_scores_gemma":[0.98401344,0.011257475,0.00059993303,0.0035078407,0.00042672822,0.00019456397],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031031587,0.0011007306,0.00131394,0.00014611988,0.00031169652,0.0004861247,0.0019129007,0.0011906956,0.00038575003],"category_scores_gemma":[0.011867978,0.00065318606,0.0005928279,0.0003959814,0.0008977885,0.00017762154,0.0046169953,0.0050507854,0.00016822612],"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":[0.00014982744,0.0026971183,0.0775327,0.016789643,0.0005749807,0.00011003274,0.0034717317,0.00014635969,0.0032806622,0.81404877,0.06297641,0.018221779],"study_design_scores_gemma":[0.00008532859,0.0001469842,0.0020730323,0.0008315378,0.00025344273,0.000009626604,0.0002491926,0.003015345,0.001977863,0.9898162,0.0007151188,0.00082634634],"about_ca_topic_score_codex":0.0005102223,"about_ca_topic_score_gemma":0.00016419806,"teacher_disagreement_score":0.17576742,"about_ca_system_score_codex":0.00047298626,"about_ca_system_score_gemma":0.00023339276,"threshold_uncertainty_score":0.99959195},"labels":[],"label_agreement":null},{"id":"W4396659425","doi":"10.1038/s41598-024-60348-4","title":"Causal impact evaluation of occupational safety policies on firms’ default using machine learning uplift modelling","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Gradient boosting; Computer science; Causality (physics); Context (archaeology); Machine learning; Boosting (machine learning); Artificial intelligence; Psychological intervention; Work (physics); Business; Operations research; Medicine; Engineering; Nursing","score_opus":0.30628914770360177,"score_gpt":0.49325954893740775,"score_spread":0.18697040123380598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396659425","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":[0.78306264,0.00018513775,0.21455897,0.000013563301,0.0009192946,0.00036196908,0.00001541609,0.00027096912,0.00061206735],"genre_scores_gemma":[0.9825636,0.0000036278282,0.016926173,0.00000334811,0.000056143454,0.000012835625,0.0000880652,0.00003193146,0.000314267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704677,0.000121029385,0.0007226702,0.00050832646,0.0013355005,0.00026569533],"domain_scores_gemma":[0.9982198,0.00029338166,0.00037244763,0.00049644953,0.0005503528,0.00006755507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048763487,0.0001890223,0.00024387099,0.0003944738,0.0002542901,0.00016937176,0.00009123394,0.0000859082,0.00021532072],"category_scores_gemma":[0.0010982819,0.00015554916,0.00013919747,0.0005819921,0.00014290909,0.0003284274,0.000061550774,0.0002484284,0.0000057363704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049439597,0.00009310332,0.0024884692,0.00014050253,0.000069665315,0.000051989522,0.0013122403,0.9469856,0.03536089,0.010752501,0.00056926615,0.002126347],"study_design_scores_gemma":[0.00004487706,0.000041367923,0.00012546692,0.00028386046,0.00007351051,0.00009182129,0.000041347554,0.75277144,0.018619893,0.22748375,0.00027425092,0.00014839777],"about_ca_topic_score_codex":0.00021310592,"about_ca_topic_score_gemma":0.000028185128,"teacher_disagreement_score":0.21673125,"about_ca_system_score_codex":0.0003933103,"about_ca_system_score_gemma":0.0005032225,"threshold_uncertainty_score":0.6343111},"labels":[],"label_agreement":null},{"id":"W4396722098","doi":"10.1093/aje/kwae058","title":"Data-driven simulations to assess the impact of study imperfections in time-to-event analyses","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"Medical Research Council; Canadian Institutes of Health Research; Université de Bourgogne; Institut National de la Santé et de la Recherche Médicale; Deutsche Forschungsgemeinschaft; McGill University","keywords":"Computer science; Covariate; Event (particle physics); Confounding; Econometrics; Statistics; Flexibility (engineering); R package; Data mining; Mathematics; Machine learning","score_opus":0.46027936864257873,"score_gpt":0.6080347499274775,"score_spread":0.1477553812848988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396722098","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":[0.74594456,0.00004428117,0.25269598,0.0008413491,0.00003930942,0.00029553668,0.000069524525,0.000027903838,0.00004152725],"genre_scores_gemma":[0.9611975,0.000014569629,0.038552016,0.000110270084,0.000073891846,0.000009940337,0.000003603535,0.000018061379,0.000020159981],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9967742,0.001482399,0.0011447439,0.00021253516,0.00013647847,0.0002496605],"domain_scores_gemma":[0.98387843,0.014668167,0.0005358408,0.00062343193,0.000168593,0.0001255265],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036593077,0.00014756207,0.0008745784,0.0005205571,0.000036648904,0.0000105756735,0.0006815517,0.000030641582,0.00015670632],"category_scores_gemma":[0.012917097,0.00008545282,0.00016665235,0.0010808214,0.00014679861,0.00015336151,0.00021868752,0.0003848822,0.000015021624],"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":[0.000251977,0.0015853652,0.31281275,0.000029723158,0.0022665614,0.00009068069,0.0030127396,0.601954,0.016385503,0.0030992664,0.024121575,0.034389902],"study_design_scores_gemma":[0.00089201727,0.03471902,0.5025829,0.0011717437,0.0015595515,0.0006206621,0.005666454,0.14377928,0.00077260035,0.30443197,0.0025906893,0.0012130624],"about_ca_topic_score_codex":0.00049329066,"about_ca_topic_score_gemma":0.00016368313,"teacher_disagreement_score":0.45817468,"about_ca_system_score_codex":0.00018913881,"about_ca_system_score_gemma":0.00016204486,"threshold_uncertainty_score":0.9953975},"labels":[],"label_agreement":null},{"id":"W4396811591","doi":"10.1002/pds.5787","title":"Describing diversity of real world data sources in pharmacoepidemiologic studies: The <scp>DIVERSE</scp> scoping review","year":2024,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"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":"International Society for Pharmacoepidemiology","keywords":"Diversity (politics); Standardization; Data science; Information retrieval; Set (abstract data type); Computer science; Medicine; Political science","score_opus":0.568981206596947,"score_gpt":0.5322999137570632,"score_spread":0.03668129283988375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396811591","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":[0.20733413,0.7437041,0.021833407,0.014601372,0.0014254542,0.0050344234,0.00043779815,0.001616599,0.004012717],"genre_scores_gemma":[0.30612287,0.6790545,0.009808933,0.0044961083,0.00020200062,0.00007283011,0.000043001248,0.00003416299,0.00016557054],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939667,0.0031737909,0.001326074,0.0007908784,0.00016998516,0.0005725751],"domain_scores_gemma":[0.9414155,0.0570954,0.0005672201,0.0006926982,0.00009455649,0.00013466147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020340012,0.00036092533,0.0013868979,0.00018934882,0.00034743713,0.0000082169645,0.0009387525,0.00007640824,0.00004185345],"category_scores_gemma":[0.0192642,0.00024143718,0.00012641637,0.00061804533,0.0009392947,0.0004772655,0.0028531924,0.0008680719,0.000007605782],"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":[0.00018314154,0.00033710734,0.31587955,0.049095366,0.0020189546,0.00030565035,0.01141574,0.00034067233,0.0008496459,0.15033302,0.38196942,0.08727175],"study_design_scores_gemma":[0.0036284898,0.00033449175,0.006543532,0.2887062,0.0056170933,0.00018543946,0.016495934,0.023616686,0.004510977,0.6236274,0.024942365,0.0017913603],"about_ca_topic_score_codex":0.0003087371,"about_ca_topic_score_gemma":0.00055428525,"teacher_disagreement_score":0.4732944,"about_ca_system_score_codex":0.00010712523,"about_ca_system_score_gemma":0.00008538486,"threshold_uncertainty_score":0.988997},"labels":[],"label_agreement":null},{"id":"W4396860094","doi":"10.1007/978-3-031-49783-4_9","title":"Individual Fairness","year":2024,"lang":"ca","type":"book-chapter","venue":"Springer Actuarial","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Business","score_opus":0.12824130651895554,"score_gpt":0.3662141904112268,"score_spread":0.23797288389227128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396860094","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067445566,0.000975507,0.026308123,0.00046615954,0.010551042,0.0023197606,0.0008150609,0.0031381082,0.9547518],"genre_scores_gemma":[0.29289484,0.0013012679,0.061823066,0.00048614782,0.022149386,0.0003759719,0.000457519,0.0023626056,0.6181492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946756,0.000041280993,0.0014285548,0.0014792163,0.0013678716,0.0010075253],"domain_scores_gemma":[0.9963742,0.00074538,0.0006475262,0.0016400845,0.0002546278,0.0003381908],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.00078198715,0.0015355509,0.0015630655,0.00062166917,0.00021365534,0.00058309664,0.0012839969,0.0019759014,0.008307967],"category_scores_gemma":[0.00041871282,0.0015215926,0.00076838175,0.000120889315,0.0005081232,0.00038777725,0.0015367551,0.0029427365,0.0071425135],"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":[0.000095618365,0.00006514065,0.0000023942532,0.0006883376,0.0007445681,0.00028816704,0.0008762566,0.0000017632881,0.00034072986,0.98431355,0.0033094788,0.009274026],"study_design_scores_gemma":[0.0003827993,0.00023487263,0.000005884863,0.001428393,0.0011049373,0.000041032803,0.000047972473,0.000024368115,0.0023338697,0.75532913,0.23775014,0.001316579],"about_ca_topic_score_codex":0.000039800856,"about_ca_topic_score_gemma":0.00004147294,"teacher_disagreement_score":0.3366026,"about_ca_system_score_codex":0.00046329937,"about_ca_system_score_gemma":0.00033065095,"threshold_uncertainty_score":0.9997393},"labels":[],"label_agreement":null},{"id":"W4396860482","doi":"10.1007/978-3-031-49783-4_12","title":"Post-Processing","year":2024,"lang":"en","type":"book-chapter","venue":"Springer Actuarial","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science","score_opus":0.10493613826065408,"score_gpt":0.36937943561441,"score_spread":0.26444329735375594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396860482","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034533357,0.0003654883,0.008063418,0.00023513124,0.001283992,0.0004160946,0.000062314175,0.0018851705,0.98765385],"genre_scores_gemma":[0.006812802,0.00007499222,0.039473467,0.00021547347,0.0035611189,0.000036195917,0.00003577961,0.00047535196,0.94931483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981176,0.000005945054,0.0004921608,0.00057320873,0.0004219283,0.00038911114],"domain_scores_gemma":[0.9986978,0.00018629784,0.00023820582,0.0005898234,0.00017652326,0.000111310466],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022452224,0.0005436865,0.00057452515,0.00024026052,0.00007709817,0.00015854562,0.0003717354,0.0006526347,0.0015771007],"category_scores_gemma":[0.00021522125,0.0005019082,0.00025761852,0.000028252014,0.00012123225,0.00016886776,0.00032021845,0.0010518032,0.001026955],"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":[0.000027798988,0.000009488231,9.6670774e-8,0.000300543,0.00006887189,0.00007787917,0.00017460606,1.520374e-7,0.0005912081,0.9823871,0.0033607997,0.013001446],"study_design_scores_gemma":[0.00008231309,0.000058241963,2.6503383e-7,0.00061910547,0.00016000985,0.0000145180165,0.000006077598,0.000011397921,0.00088301173,0.79026866,0.20744844,0.00044794002],"about_ca_topic_score_codex":0.00000771164,"about_ca_topic_score_gemma":0.000019097559,"teacher_disagreement_score":0.20408764,"about_ca_system_score_codex":0.00023497456,"about_ca_system_score_gemma":0.0001831053,"threshold_uncertainty_score":0.99975085},"labels":[],"label_agreement":null},{"id":"W4397022047","doi":"10.1093/aje/kwae071","title":"Validation of algorithms in studies based on routinely collected health data: general principles","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":39,"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; SickKids Foundation; University of Toronto","funders":"Galderma; National Institutes of Health; Aarhus Universitet; Region Midtjylland; Sanofi","keywords":"Computer science; Operationalization; External validity; Data mining; Terminology; Algorithm; Context (archaeology); Covariate; Data science; Management science; Machine learning; Statistics; Mathematics","score_opus":0.48073120424196,"score_gpt":0.5450480657461021,"score_spread":0.06431686150414212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397022047","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":[0.33402708,0.002499331,0.65185606,0.010394825,0.00043935684,0.00039228416,0.00008640785,0.00012237678,0.00018229903],"genre_scores_gemma":[0.4195755,0.00092771574,0.57849604,0.00077370415,0.00014400113,0.000008147227,0.000017709292,0.000024387613,0.000032762935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611133,0.001509839,0.001709831,0.00023997472,0.00014795741,0.00028107504],"domain_scores_gemma":[0.9879976,0.009818053,0.0015375771,0.00037924506,0.00019421644,0.000073314724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067303735,0.0001549016,0.0012656546,0.00041218236,0.000025240914,0.000003749471,0.00032405823,0.00004427025,0.0000107786045],"category_scores_gemma":[0.016649043,0.00011432304,0.00008140888,0.0005504315,0.00033767932,0.0001309915,0.00007907944,0.00037783326,8.6334757e-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":[0.0015737754,0.001674736,0.07952616,0.0018360247,0.001904058,0.00042097847,0.0055839783,0.052765805,0.0038013537,0.454784,0.068052396,0.32807675],"study_design_scores_gemma":[0.0017325806,0.01772599,0.014923411,0.0050515053,0.00023212643,0.00040442552,0.002672311,0.23566702,0.0047916123,0.7082838,0.007587171,0.0009280771],"about_ca_topic_score_codex":0.00010648432,"about_ca_topic_score_gemma":0.000030149782,"teacher_disagreement_score":0.32714865,"about_ca_system_score_codex":0.00026211317,"about_ca_system_score_gemma":0.00036859675,"threshold_uncertainty_score":0.99163413},"labels":[],"label_agreement":null},{"id":"W4398400885","doi":"10.7910/dvn/hgihgc/xwzkab","title":"confirmatory study survey [coding details].pdf","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","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":"University of Toronto","funders":"","keywords":"Socioeconomic status; Entitlement (fair division); Replication (statistics); Privilege (computing); Psychology; Survey data collection; Coding (social sciences); Social psychology; Sociology; Social science; Political science; Demography; Statistics; Economics; Law; Mathematics; Mathematical economics","score_opus":0.18521111859153333,"score_gpt":0.38815769152307145,"score_spread":0.20294657293153812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398400885","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005709607,5.0115904e-7,0.0019037095,0.0000018395103,0.0003836783,0.0013402583,0.9955733,0.0004999205,0.00023971738],"genre_scores_gemma":[0.00014475585,0.00014983548,0.003024178,0.00028846806,0.00017954569,0.0001364276,0.9957949,0.000084200445,0.00019769775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99617845,0.0006947915,0.00090971007,0.0009179486,0.00074678677,0.0005522976],"domain_scores_gemma":[0.995146,0.0011936199,0.000667088,0.0024932341,0.00020040934,0.00029967545],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013032914,0.0007344473,0.0011261216,0.00023045854,0.00016786024,0.00017032007,0.0015593757,0.00040702667,0.025047274],"category_scores_gemma":[0.004147457,0.0007470656,0.00014385005,0.0003115353,0.0001476092,0.00047390157,0.001228543,0.0012114019,0.19723183],"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":[0.000057325615,0.00032475847,0.00009476598,0.00027393157,0.0001766073,0.00038206956,0.00006545912,2.0065144e-7,0.000016316373,0.0002150641,0.99833274,0.00006078554],"study_design_scores_gemma":[0.00047737543,0.00021223584,0.00010044833,0.00012949113,0.0002853599,0.000014063859,0.0003026478,0.0000070467863,0.00008194396,0.0012916928,0.9963527,0.00074502476],"about_ca_topic_score_codex":0.00049646007,"about_ca_topic_score_gemma":0.0014170997,"teacher_disagreement_score":0.17218456,"about_ca_system_score_codex":0.00019885917,"about_ca_system_score_gemma":0.00022623732,"threshold_uncertainty_score":0.999498},"labels":[],"label_agreement":null},{"id":"W4399693737","doi":"10.1097/ede.0000000000001768","title":"Natural effects with a recanting witness: non-identifiability or meaningless estimand?","year":2024,"lang":"en","type":"letter","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","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":true,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Witness; Epidemiology; Judaism; University hospital; Clinical epidemiology; Library science; History; Medicine; Family medicine; Political science; Law; Pathology; Archaeology","score_opus":0.177492612641698,"score_gpt":0.44420275572671886,"score_spread":0.26671014308502083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399693737","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007879165,0.0021827505,0.4211724,0.54627717,0.0074052257,0.005000554,0.00008899881,0.005529913,0.004463828],"genre_scores_gemma":[0.014912158,0.00009229641,0.51185995,0.44618875,0.008859255,0.0015915232,0.00038837342,0.0006882766,0.01541938],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99436307,0.0013759854,0.0012614076,0.0015062743,0.00028833348,0.0012049295],"domain_scores_gemma":[0.96366954,0.033799443,0.0008891356,0.0013344962,0.0002172939,0.00009011925],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0031930367,0.0009160668,0.002549585,0.00027955262,0.000128082,0.00003731545,0.0007472604,0.0015983664,0.00008220413],"category_scores_gemma":[0.026138645,0.00058161846,0.00026425213,0.00037267528,0.00072681153,0.0001868919,0.00039046048,0.005506593,0.00009488445],"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":[0.00007791928,0.000026392785,0.0002804067,0.0053474316,0.00026110647,0.0012779796,0.00016256906,0.0000050069148,0.0000832366,0.0065361275,0.98400146,0.0019403498],"study_design_scores_gemma":[0.0003265834,0.00048300112,0.00011658488,0.0044893213,0.00052130903,0.0005636711,0.000017643213,0.0010236915,0.00053834385,0.9189359,0.07178476,0.001199193],"about_ca_topic_score_codex":0.00010071235,"about_ca_topic_score_gemma":0.00013499078,"teacher_disagreement_score":0.91239977,"about_ca_system_score_codex":0.00032326882,"about_ca_system_score_gemma":0.00021923959,"threshold_uncertainty_score":0.99969774},"labels":[],"label_agreement":null},{"id":"W4399726225","doi":"10.1080/00031305.2024.2368794","title":"High-Dimensional Propensity Score and Its Machine Learning Extensions in Residual Confounding Control","year":2024,"lang":"en","type":"article","venue":"The American Statistician","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Confounding; Residual; Computer science; Proxy (statistics); Exploit; Causal inference; Parametric statistics; Machine learning; Econometrics; Artificial intelligence; Data mining; Statistics; Algorithm; Mathematics","score_opus":0.12057004770728635,"score_gpt":0.39189234053654654,"score_spread":0.2713222928292602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399726225","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":[0.9411444,0.00036521643,0.056046367,0.0010746703,0.00008331317,0.00055218156,0.00013211326,0.00040313054,0.00019862926],"genre_scores_gemma":[0.98444796,0.000041807813,0.014851331,0.000332033,0.000054449192,0.00003162512,0.0000107952565,0.000037534493,0.00019249188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863946,0.00026899046,0.0002865076,0.0002808539,0.0002296313,0.00029455323],"domain_scores_gemma":[0.99730337,0.002248378,0.0001386288,0.0001700152,0.000071757524,0.00006787832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005871254,0.00018145287,0.0003951644,0.000117279444,0.000171867,0.00006204726,0.0001149357,0.000023645605,0.000049028666],"category_scores_gemma":[0.001282953,0.00012568593,0.0000201018,0.00027522,0.00033561318,0.000099630604,0.00009714024,0.00050504145,0.000017660097],"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":[0.00019901413,0.00005673265,0.0020354947,0.00011443428,0.000084032035,0.0005437787,0.0009814316,0.00021900966,0.0128379725,0.9527827,0.001108532,0.029036885],"study_design_scores_gemma":[0.0010463246,0.0011764589,0.05082829,0.0012876204,0.00030596257,0.00029374118,0.000760612,0.08463199,0.0022276326,0.85568464,0.00069734437,0.0010593934],"about_ca_topic_score_codex":0.0006763979,"about_ca_topic_score_gemma":0.00039692133,"teacher_disagreement_score":0.097098045,"about_ca_system_score_codex":0.0000704745,"about_ca_system_score_gemma":0.00006422827,"threshold_uncertainty_score":0.51253235},"labels":[],"label_agreement":null},{"id":"W4399754935","doi":"10.1080/26941899.2024.2360892","title":"Model Selection for Exposure-Mediator Interaction","year":2024,"lang":"en","type":"article","venue":"Data Science in Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; Eisai Incorporated; Canadian Institutes of Health Research; University of Southern California; AbbVie Canada; National Institutes of Health; Genentech; Takeda Pharmaceutical Company; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Pfizer; Biogen; BioClinica; Roche; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Meso Scale Diagnostics; Novartis Pharmaceuticals Corporation; Merck; Alzheimer's Association","keywords":"Mediator; Selection (genetic algorithm); Psychology; Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.405217553711427,"score_gpt":0.5323269213190341,"score_spread":0.12710936760760716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399754935","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":[0.20091788,0.000024055515,0.7958739,0.0002724762,0.0010236092,0.00048719498,0.0000974351,0.00045937218,0.0008440641],"genre_scores_gemma":[0.7679349,0.000014147967,0.23185049,0.00003144938,0.00004914366,0.00006242681,0.0000075208513,0.000008355047,0.000041529696],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975528,0.000014324511,0.00032341602,0.00091873854,0.000715897,0.00047479064],"domain_scores_gemma":[0.9981956,0.00067919586,0.0000719161,0.0007510712,0.00020062918,0.000101584104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006322799,0.000116229974,0.00013323278,0.0007023422,0.00026697275,0.00047773658,0.0020638085,0.000036958405,0.000011866293],"category_scores_gemma":[0.0078085545,0.00010018411,0.000018200106,0.0032284171,0.0011329523,0.009439817,0.00050668477,0.00019345556,0.00001225813],"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":[0.0000182372,0.000116283125,0.0008165714,0.00013647687,0.0000017145434,0.000003054325,0.0014430052,0.0008882766,0.52305263,0.42653552,0.004635344,0.042352866],"study_design_scores_gemma":[0.000035083634,0.00004689615,0.000041116273,0.000081869366,0.0000031724157,0.000009603698,0.00015544723,0.79430294,0.030552123,0.17395751,0.00069017016,0.00012404987],"about_ca_topic_score_codex":0.00001570248,"about_ca_topic_score_gemma":0.000086070875,"teacher_disagreement_score":0.79341465,"about_ca_system_score_codex":0.00040870934,"about_ca_system_score_gemma":0.0010211818,"threshold_uncertainty_score":0.9348133},"labels":[],"label_agreement":null},{"id":"W4399790739","doi":"10.1186/s13063-024-08202-w","title":"Accounting for center-level effects in multicenter randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Trials","topic":"Advanced Causal Inference Techniques","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":"Population Health Research Institute; McMaster University; Impact","funders":"McMaster University; Population Health Research Institute","keywords":"Randomized controlled trial; Medicine; Logistic regression; Random effects model; Protocol (science); Outcome (game theory); Fixed effects model; Test (biology); Econometrics; Statistics; Meta-analysis; Alternative medicine; Panel data; Internal medicine; Mathematics","score_opus":0.37717584300951007,"score_gpt":0.5227859937060347,"score_spread":0.14561015069652467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399790739","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":[0.018419031,0.0019638285,0.9265198,0.0006492258,0.0025819805,0.047008324,0.00016452846,0.0012269422,0.0014663239],"genre_scores_gemma":[0.7644337,0.00024504313,0.21428426,0.00029469834,0.0013471189,0.017782414,0.000035634792,0.0001649697,0.0014121906],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9903387,0.0044806907,0.0040403926,0.00041079905,0.0002900485,0.0004393957],"domain_scores_gemma":[0.79065,0.2078551,0.0010151081,0.00030143728,0.00012257311,0.000055779157],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07014435,0.00034659312,0.008021555,0.00037158237,0.00004120575,0.00020672065,0.00020408655,0.00019629215,0.00012310185],"category_scores_gemma":[0.29951933,0.00020988783,0.0017048963,0.00015927004,0.000055156666,0.00025697917,0.00005288392,0.00020337355,0.000024034129],"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":[0.45845792,0.0005750597,0.00003516673,0.0031390723,0.0026809862,0.000052436655,0.00141157,0.000009225721,0.039068338,0.45283005,0.01018687,0.031553313],"study_design_scores_gemma":[0.48090437,0.000050086248,0.0000015764996,0.0013777605,0.0007396139,0.0000014676363,0.000029616811,0.0027073014,0.016816195,0.4964883,0.00064557453,0.00023814653],"about_ca_topic_score_codex":0.000011970919,"about_ca_topic_score_gemma":0.0000128114925,"teacher_disagreement_score":0.74601465,"about_ca_system_score_codex":0.00010961839,"about_ca_system_score_gemma":0.00007010489,"threshold_uncertainty_score":0.9574821},"labels":[],"label_agreement":null},{"id":"W4399815117","doi":"10.1145/3673761","title":"Learning Individual Treatment Effects under Heterogeneous Interference in Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Causal Inference Techniques","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 Waterloo","funders":"National Natural Science Foundation of China","keywords":"Weighting; Benchmark (surveying); Interference (communication); Computer science; Generalization; Regression; Spillover effect; Observational study; Range (aeronautics); Confounding; Sample (material); Process (computing); Machine learning; Artificial intelligence; Mathematics; Statistics; Medicine","score_opus":0.16936547919897604,"score_gpt":0.4090027000751428,"score_spread":0.23963722087616673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399815117","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":[0.06544109,0.0013175621,0.9307624,0.000080874794,0.0005373316,0.00042651495,0.00063453306,0.00058054907,0.00021915582],"genre_scores_gemma":[0.99103624,0.00055406225,0.006857961,0.00003149366,0.00009440262,0.00016134398,0.0006290935,0.000071109855,0.0005643214],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981499,0.00019800321,0.00036454253,0.00078798766,0.00014209226,0.00035752656],"domain_scores_gemma":[0.9952724,0.002961618,0.00004923349,0.0016225765,0.00001990836,0.000074242125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018764404,0.00036068115,0.00036565,0.0002312582,0.00010258633,0.00026487454,0.0009986944,0.00017267457,0.000114273724],"category_scores_gemma":[0.00012948146,0.00031188942,0.00009673797,0.00036047806,0.00008045635,0.0009977834,0.00011116696,0.0006170847,0.00008598671],"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":[0.00028281345,0.0031897947,0.0003974202,0.00038379623,0.0014776937,0.00037108737,0.0047205454,0.0153815495,0.0013056712,0.006385251,0.0012355152,0.96486884],"study_design_scores_gemma":[0.003558624,0.005103437,0.0009495682,0.007596092,0.002090263,0.00010604079,0.001710208,0.14749944,0.067888804,0.75274134,0.0070654084,0.0036907825],"about_ca_topic_score_codex":0.00012531327,"about_ca_topic_score_gemma":0.0016319739,"teacher_disagreement_score":0.96117806,"about_ca_system_score_codex":0.0003590089,"about_ca_system_score_gemma":0.000114815775,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4400059274","doi":"10.1093/aje/kwae151","title":"Triple challenges—small sample size in both exposure and control groups to scan rare maternal outcomes in a signal identification approach: a simulation study","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Hamilton Health Sciences Foundation","keywords":"Sample size determination; Statistics; Incidence (geometry); Type I and type II errors; Poisson regression; Poisson distribution; Statistical power; Medicine; Statistic; Econometrics; Mathematics; Population","score_opus":0.17154134662257073,"score_gpt":0.4271610364481177,"score_spread":0.25561968982554695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400059274","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":[0.6924611,0.00036041893,0.30578983,0.0007817162,0.00005798219,0.00048939354,0.00001057552,0.000036344445,0.000012653504],"genre_scores_gemma":[0.9450748,0.00009053901,0.054472107,0.00019286606,0.000066485925,0.00006655876,9.36755e-7,0.00002657261,0.000009156931],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961524,0.0015225486,0.0015098884,0.0003393808,0.00014321461,0.0003325463],"domain_scores_gemma":[0.9836601,0.015253073,0.000667837,0.00021296223,0.00008324495,0.00012281012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051756096,0.00021382996,0.0011666003,0.00046340964,0.000024390032,0.000020650086,0.00021855792,0.000074913856,0.00001526984],"category_scores_gemma":[0.010023837,0.00017033063,0.00009036035,0.0002911757,0.00011944081,0.00019168985,0.00004678884,0.0004273741,0.0000010272877],"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":[0.0007741632,0.00088230486,0.8762452,0.00015531134,0.00023843956,0.00012605378,0.008465513,0.007410192,0.00082295225,0.011971704,0.000033298576,0.09287488],"study_design_scores_gemma":[0.0015322921,0.0036110075,0.71470815,0.0002309562,0.00008104342,0.00009714748,0.005905209,0.011783974,0.000023832845,0.2616645,0.00004322241,0.00031867967],"about_ca_topic_score_codex":0.00026585461,"about_ca_topic_score_gemma":0.00035347184,"teacher_disagreement_score":0.2526137,"about_ca_system_score_codex":0.00018319149,"about_ca_system_score_gemma":0.000048871305,"threshold_uncertainty_score":0.99831516},"labels":[],"label_agreement":null},{"id":"W4400245371","doi":"10.6339/24-jds1143","title":"Physician Effects in Critical Care: A Causal Inference Approach Through Propensity Weighting with Parametric and Super Learning Methods","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","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":"Western University","funders":"","keywords":"Propensity score matching; Weighting; Causal inference; Covariate; Confounding; Inverse probability weighting; Estimator; Parametric statistics; Intensive care unit; Computer science; Medicine; Statistics; Intensive care medicine; Machine learning; Mathematics","score_opus":0.32995507111031813,"score_gpt":0.5379351258148638,"score_spread":0.20798005470454567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400245371","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":[0.15925053,0.0007925133,0.83889264,0.00008422919,0.000070450515,0.00018899488,0.000003262585,0.00005709082,0.0006603087],"genre_scores_gemma":[0.5136003,0.00002849429,0.4863088,0.000019037065,0.0000304724,0.0000023710845,6.4271643e-7,0.0000081023145,0.0000018055879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801666,0.0002532307,0.00036325643,0.00043797534,0.0005882335,0.00034062582],"domain_scores_gemma":[0.99633944,0.002762388,0.00013369524,0.00039032323,0.00027428207,0.000099843746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003244107,0.00016247186,0.00037976578,0.0003242841,0.00014720831,0.00032647024,0.0007325846,0.000049449944,0.0000014323614],"category_scores_gemma":[0.008248367,0.000106223946,0.000020015863,0.0017824899,0.000857624,0.0048086317,0.00052699103,0.00090377417,6.741744e-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":[0.00013012715,0.0005623878,0.016588723,0.0047129137,0.000076463446,0.0010467462,0.015693106,0.00020910623,0.06137669,0.62869716,0.00013563862,0.27077094],"study_design_scores_gemma":[0.0017958652,0.005685781,0.011450324,0.010785124,0.0007080071,0.003157263,0.011229194,0.15454242,0.10064759,0.6957391,0.0017775972,0.0024817302],"about_ca_topic_score_codex":0.000018011688,"about_ca_topic_score_gemma":0.0000046897553,"teacher_disagreement_score":0.35434973,"about_ca_system_score_codex":0.00012156891,"about_ca_system_score_gemma":0.0003896698,"threshold_uncertainty_score":0.9874662},"labels":[],"label_agreement":null},{"id":"W4400421737","doi":"10.1093/aje/kwae188","title":"A simple Cox approach to estimating risk ratios without sharing individual-level data in multisite studies","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":"Western University","funders":"CVS Health; Kaiser Permanente Washington Health Research Institute; Kaiser Permanente","keywords":"Computer science; Poisson regression; Confidence interval; Regression analysis; Data set; Meta-analysis; Statistics; Poisson distribution; Data mining; Software; Medicine; Mathematics; Population; Machine learning; Environmental health; Artificial intelligence","score_opus":0.5139494630489853,"score_gpt":0.535567055144398,"score_spread":0.021617592095412697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400421737","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":[0.1769406,0.00087877037,0.8212562,0.00032512637,0.00011470071,0.00023388812,0.000071841816,0.00008825246,0.00009057793],"genre_scores_gemma":[0.40489897,0.0001088014,0.594501,0.00030355642,0.00012866031,0.000016378628,0.000008835529,0.000025783991,0.000007991696],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964238,0.0008730725,0.0015744058,0.00048354015,0.00018278677,0.00046238676],"domain_scores_gemma":[0.98681235,0.01110448,0.001117954,0.00067151734,0.00014749299,0.00014621411],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010316494,0.00024702726,0.0013684785,0.00041104504,0.000064359556,0.00002365204,0.0008731988,0.00006292261,0.000006533667],"category_scores_gemma":[0.05266946,0.0001901553,0.000080956765,0.00050708133,0.0003103306,0.0004010941,0.00066504604,0.0008352672,0.0000053164636],"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":[0.00022067441,0.0003671019,0.5866297,0.0005767291,0.0019097441,0.00021097412,0.017093755,0.014627566,0.0005561935,0.06741739,0.01660723,0.29378295],"study_design_scores_gemma":[0.0004101946,0.0010137847,0.010932,0.0011193939,0.0002956404,0.00051242055,0.0050826157,0.13417727,0.000091126414,0.8451344,0.0006681336,0.000563036],"about_ca_topic_score_codex":0.00021428693,"about_ca_topic_score_gemma":0.00009800876,"teacher_disagreement_score":0.777717,"about_ca_system_score_codex":0.00015113449,"about_ca_system_score_gemma":0.00007295267,"threshold_uncertainty_score":0.9553103},"labels":[],"label_agreement":null},{"id":"W4400479474","doi":"10.1016/j.jclinepi.2024.111458","title":"Statistical analysis of self-reported health conditions in cohort studies: handling of missing onset age","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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 Alberta","funders":"National Cancer Institute; National Institutes of Health; American Lebanese Syrian Associated Charities","keywords":"Epidemiology; Outcome (game theory); Medicine; Missing data; Cohort study; Cohort; Demography; Pediatrics; Internal medicine; Statistics","score_opus":0.6556764497310326,"score_gpt":0.676722069545854,"score_spread":0.021045619814821448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400479474","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":[0.50810784,0.0015726656,0.48743942,0.002148623,0.00032427773,0.00019370476,0.00008138937,0.00005238163,0.000079688965],"genre_scores_gemma":[0.7260754,0.002086041,0.27143535,0.0003063494,0.00006199182,0.0000035482365,0.00001205664,0.000012276193,0.0000069960597],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98631567,0.0034198677,0.009488338,0.00025557782,0.00023096422,0.0002896033],"domain_scores_gemma":[0.86532545,0.12946887,0.004354473,0.0002800569,0.00039136567,0.00017979967],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03526728,0.0001534075,0.0048260675,0.0006175554,0.000026628933,0.0000035274957,0.00016992478,0.0002245999,0.000060564358],"category_scores_gemma":[0.16321298,0.00011529057,0.00060640596,0.0006648255,0.00047910394,0.0000887349,0.000054809465,0.0009275633,6.3932083e-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":[0.00020947258,0.0011663198,0.7590199,0.0013450925,0.023266163,0.0010206333,0.0010487537,0.0008657587,0.00008309101,0.19579649,0.009234435,0.0069439067],"study_design_scores_gemma":[0.00032616322,0.0008626813,0.16113536,0.0011283889,0.002742414,0.00009221985,0.00021562012,0.005913989,0.00003153738,0.82726943,0.000164171,0.000118035015],"about_ca_topic_score_codex":0.00004417578,"about_ca_topic_score_gemma":0.00008931567,"teacher_disagreement_score":0.63147295,"about_ca_system_score_codex":0.00012385691,"about_ca_system_score_gemma":0.00051859533,"threshold_uncertainty_score":0.9933953},"labels":[],"label_agreement":null},{"id":"W4400520097","doi":"10.1101/2024.07.11.24310262","title":"Instrumental variable analysis: choice of control variables is critical and can lead to biased results","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute for Health and Care Research","keywords":"Lead (geology); Instrumental variable; Variable (mathematics); Econometrics; Control (management); Control variable; Economics; Statistics; Mathematics; Geology; Management","score_opus":0.11356824131295581,"score_gpt":0.4128930792674072,"score_spread":0.2993248379544514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400520097","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":[0.7848063,0.0005284634,0.18770815,0.0051763705,0.00050554855,0.0021488352,0.0074758427,0.0011485541,0.0105019165],"genre_scores_gemma":[0.9104184,0.000022271079,0.088625036,0.00031474684,0.0000884426,0.00015429246,0.000037122645,0.000051792664,0.00028787507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997268,0.00015081104,0.0009327996,0.0008349185,0.00042588194,0.00038757702],"domain_scores_gemma":[0.9965205,0.0018669877,0.00022492075,0.0009646615,0.0002250114,0.00019792712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091132236,0.00041501364,0.0011132294,0.0005266385,0.00004967328,0.0000970954,0.00040489962,0.0003810363,0.000094231065],"category_scores_gemma":[0.0045536547,0.0003841405,0.000175595,0.00067669293,0.00017402547,0.000052399446,0.00082530227,0.00073960854,0.0000068746976],"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":[0.0009525915,0.0014726146,0.022642992,0.013253587,0.012026788,0.00020322886,0.006011738,0.0018454532,0.044094633,0.876689,0.016687019,0.004120345],"study_design_scores_gemma":[0.0008278298,0.00027375107,0.0008767581,0.0018645892,0.0048162993,0.00000676033,0.00021836143,0.009046105,0.028565189,0.9517485,0.0008455089,0.0009103323],"about_ca_topic_score_codex":0.0007569175,"about_ca_topic_score_gemma":0.00019380999,"teacher_disagreement_score":0.1256121,"about_ca_system_score_codex":0.00012343095,"about_ca_system_score_gemma":0.0001716017,"threshold_uncertainty_score":0.99986106},"labels":[],"label_agreement":null},{"id":"W4400599257","doi":"10.1186/s12874-024-02273-8","title":"SurvdigitizeR: an algorithm for automated survival curve digitization","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","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":"McMaster University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; York University; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Digitization; Algorithm; Computer science; Censoring (clinical trials); Mean squared error; Artificial intelligence; Statistics; Mathematics; Pattern recognition (psychology); Computer vision","score_opus":0.8083186803653117,"score_gpt":0.6766793295584699,"score_spread":0.13163935080684186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400599257","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":[0.0017886498,0.00020746284,0.99128157,0.00040922186,0.00054657256,0.0008651672,0.00008050799,0.003373927,0.0014469215],"genre_scores_gemma":[0.0043328907,0.00020131591,0.9929213,0.00006572774,0.0006270848,0.0005948836,0.0001728805,0.00010407567,0.0009798422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856981,0.010178166,0.0006779403,0.0007490044,0.0016734408,0.0010233416],"domain_scores_gemma":[0.8689452,0.12919284,0.000058481066,0.0005194496,0.00073212414,0.0005519119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043371756,0.00022924933,0.0006207895,0.00048782738,0.000162032,0.00014634038,0.0006642517,0.0005715738,0.0005433795],"category_scores_gemma":[0.16955072,0.000189426,0.00013066421,0.000797667,0.000713791,0.0003632659,0.00026247627,0.0008846831,0.000048791586],"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":[0.000055320554,0.00013036496,0.000046903217,0.00050392386,0.00004759922,0.00007276624,0.00022598039,0.0000019227853,0.0005456158,0.49552447,0.008954152,0.493891],"study_design_scores_gemma":[0.0002886463,0.00049971935,0.000040889998,0.00019923935,0.000013448807,0.0000407652,0.00020839543,0.22746615,0.0026539704,0.7586538,0.009729596,0.00020536479],"about_ca_topic_score_codex":0.00008487943,"about_ca_topic_score_gemma":0.000352981,"teacher_disagreement_score":0.49368563,"about_ca_system_score_codex":0.00018265758,"about_ca_system_score_gemma":0.0015125653,"threshold_uncertainty_score":0.9850501},"labels":[],"label_agreement":null},{"id":"W4400692562","doi":"10.1093/biomtc/ujae065","title":"Multiply robust estimation of marginal structural models in observational studies subject to covariate-driven observations","year":2024,"lang":"en","type":"article","venue":"Biometrics","topic":"Advanced Causal Inference Techniques","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":"Université de Montréal","funders":"National Institute of Child Health and Human Development; National Institute of Environmental Health Sciences; National Institute on Aging; Eunice Kennedy Shriver National Institute of Child Health and Human Development; North Carolina State University; Fonds de Recherche du Québec - Santé; University of North Carolina; National Institutes of Health; National Science Foundation","keywords":"Covariate; Causal inference; Estimator; Observational study; Confounding; Econometrics; Marginal structural model; Inference; Computer science; Estimation; Specification; Statistics; Data mining; Mathematics; Artificial intelligence; Engineering","score_opus":0.649482041297089,"score_gpt":0.4852762919118487,"score_spread":0.1642057493852403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400692562","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":[0.42350447,0.0003332431,0.5747349,0.00033948536,0.00019638502,0.0004617987,0.00012118345,0.00025044905,0.000058063448],"genre_scores_gemma":[0.5404299,0.000030873074,0.45934173,0.000024237952,0.000020305482,0.000048370795,0.00003173297,0.000016743294,0.000056115372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848574,0.000045695007,0.0005638037,0.00027069487,0.00041249482,0.0002215787],"domain_scores_gemma":[0.99765176,0.0015763483,0.00011635817,0.00022985971,0.00037637987,0.000049327773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045677,0.0001757572,0.0003171738,0.0018013858,0.000046447458,0.00004233348,0.00020241023,0.000096501746,0.0000119553],"category_scores_gemma":[0.0031429154,0.00016203195,0.00005861576,0.006037173,0.000056386278,0.00054817885,0.000113786096,0.00014267817,0.0000047934445],"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":[0.000032898828,0.000090974754,0.004636462,0.0007036398,0.00011077592,0.000014168193,0.0016849769,0.18949905,0.0043794946,0.79015124,0.0014992343,0.0071971044],"study_design_scores_gemma":[0.00016184342,0.00010134696,0.015918754,0.0002573206,0.000031860203,0.000003173782,0.00014569778,0.5744086,0.0013778213,0.40731037,0.00006327838,0.00021991586],"about_ca_topic_score_codex":0.000045121033,"about_ca_topic_score_gemma":0.00004442687,"teacher_disagreement_score":0.38490957,"about_ca_system_score_codex":0.00033607686,"about_ca_system_score_gemma":0.0001032284,"threshold_uncertainty_score":0.6607471},"labels":[],"label_agreement":null},{"id":"W4400812228","doi":"10.2196/53622","title":"Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics","year":2024,"lang":"en","type":"review","venue":"JMIR Medical Informatics","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":true,"route_about_ca":false,"ca_institutions":"British Columbia Academic Health Science Network; British Columbia Environmental and Occupational Health Research Network; Université de Sherbrooke","funders":"","keywords":"Preprint; Analytics; Computer science; Data science; World Wide Web","score_opus":0.3043032434029367,"score_gpt":0.5666461887389151,"score_spread":0.26234294533597846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400812228","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":[2.0017907e-7,0.62258095,0.3739217,0.00019861264,0.000034531764,0.0022365937,0.00081709836,0.00014985347,0.000060466016],"genre_scores_gemma":[0.0000012927964,0.8334726,0.16385596,0.0012262629,0.000054712757,0.0004153877,0.000912779,0.000049749542,0.000011261167],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99372154,0.00022635375,0.004002507,0.0002937113,0.0012727077,0.00048319032],"domain_scores_gemma":[0.9950468,0.0022491906,0.0010382017,0.0006449808,0.00026736618,0.0007534667],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014770906,0.0006239336,0.0042106993,0.0003626033,0.00007442108,0.00010056788,0.0005285437,0.0008420552,0.0003676759],"category_scores_gemma":[0.0053511625,0.00043977718,0.00025869076,0.0011289814,0.00025745397,0.00018072102,0.0005204627,0.0019068038,0.000031968528],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017920044,0.00007493106,1.7369891e-7,0.6436849,0.0002929314,0.00001053275,0.00033187415,6.613487e-7,8.553578e-9,0.058259755,0.029343972,0.26799846],"study_design_scores_gemma":[0.000092585484,0.00023045912,1.7304143e-7,0.8425457,0.0019547069,0.00008853486,0.00013922837,0.00091211806,2.4828043e-7,0.009006681,0.14447458,0.00055502594],"about_ca_topic_score_codex":0.000007930138,"about_ca_topic_score_gemma":0.000015193098,"teacher_disagreement_score":0.26744342,"about_ca_system_score_codex":0.0002375337,"about_ca_system_score_gemma":0.0020851512,"threshold_uncertainty_score":0.9998054},"labels":[],"label_agreement":null},{"id":"W4400899848","doi":"10.24072/pcjournal.564","title":"hdmax2, an R package to perform high dimension mediation analysis","year":2025,"lang":"en","type":"article","venue":"Peer Community Journal","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":"Centre Hospitalier Universitaire Sainte-Justine; Université du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Dimension (graph theory); Mediation; R package; Computer science; Mathematics; Sociology; Programming language; Combinatorics; Social science","score_opus":0.1767762054822567,"score_gpt":0.4470982631207183,"score_spread":0.2703220576384616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400899848","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":[0.7649952,0.000012048066,0.2314249,0.0014824278,0.000103616476,0.000120808894,0.000008087222,0.00016618393,0.0016866813],"genre_scores_gemma":[0.9198646,0.000019199799,0.07904686,0.00040359236,0.000056447607,0.000009566484,0.00003569926,0.000014516982,0.0005495232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99814665,0.00061532663,0.0004257328,0.000100604375,0.00046486664,0.00024679847],"domain_scores_gemma":[0.9974843,0.00062615867,0.00018501804,0.00085081515,0.0006791651,0.00017449829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025459658,0.00016575227,0.00034635063,0.0006424214,0.00075411104,0.00012621674,0.0005666452,0.00010381357,0.00023719274],"category_scores_gemma":[0.0017087436,0.00014546451,0.00012057802,0.0009028061,0.000039651837,0.00043452802,0.0002458481,0.0012885567,0.000010723226],"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":[0.00069855887,0.006108406,0.14556433,0.00040280618,0.005048537,0.00010880336,0.064149074,0.0019086816,0.06366134,0.38755223,0.09375781,0.23103942],"study_design_scores_gemma":[0.00048517578,0.0004190913,0.037470676,0.00010313886,0.0006592762,0.000026372865,0.0033345874,0.0016068405,0.014386677,0.9396806,0.0014238242,0.000403776],"about_ca_topic_score_codex":0.00021570154,"about_ca_topic_score_gemma":0.0008687716,"teacher_disagreement_score":0.5521283,"about_ca_system_score_codex":0.00025260745,"about_ca_system_score_gemma":0.000060523354,"threshold_uncertainty_score":0.5931871},"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":"W4401037694","doi":"10.1002/sim.10167","title":"Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data","year":2024,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Observational study; Computer science; Identification (biology); Rule of thumb; Clinical trial; Medical physics; Machine learning; Artificial intelligence; Medicine; Statistics; Mathematics; Algorithm","score_opus":0.9530672804330427,"score_gpt":0.7219823764569416,"score_spread":0.23108490397610104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401037694","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":[0.000008143533,0.6042439,0.3843291,0.000024875431,0.00023124451,0.0025732594,0.008512603,0.000062056075,0.000014803703],"genre_scores_gemma":[0.0000024559743,0.60254395,0.3892054,0.00001128513,0.00048107762,0.0006537865,0.0070103,0.000060795875,0.000030971572],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934943,0.0020441473,0.0028026218,0.0009983415,0.0004102376,0.00025039172],"domain_scores_gemma":[0.93012404,0.067819685,0.00090336276,0.0009915729,0.0000636356,0.00009768207],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.016098939,0.00057782716,0.004963802,0.00013543015,0.000044534998,0.00003006069,0.00040696873,0.0003587962,0.000020555934],"category_scores_gemma":[0.059856884,0.00033496064,0.00015185765,0.00012071101,0.00022331018,0.00005787926,0.00026943244,0.0004755424,0.0000026370928],"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":[0.000024496912,0.000052736727,0.000013261723,0.01041631,0.00046211088,0.000011039758,0.00006042682,3.315997e-7,2.5722986e-7,0.015395315,0.0024162703,0.9711474],"study_design_scores_gemma":[0.0011970942,0.0013836294,0.000004125835,0.018884683,0.010457662,0.00000657527,0.000013139609,0.031988952,8.738142e-7,0.88360935,0.052074082,0.00037984992],"about_ca_topic_score_codex":0.000031048756,"about_ca_topic_score_gemma":0.00009487042,"teacher_disagreement_score":0.9707676,"about_ca_system_score_codex":0.00021829363,"about_ca_system_score_gemma":0.00028074282,"threshold_uncertainty_score":0.99991024},"labels":[],"label_agreement":null},{"id":"W4401195388","doi":"10.1002/sim.10188","title":"Evaluation and comparison of covariate balance metrics in studies with time‐dependent confounding","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Université Laval; Centre hospitalier de l'Université Laval","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Confounding; Statistics; Inverse probability weighting; Censoring (clinical trials); Marginal structural model; Weighting; Inverse probability; Mahalanobis distance; Econometrics; Causal inference; Proportional hazards model; Residual; Propensity score matching; Computer science; Mathematics; Medicine; Bayesian probability; Posterior probability","score_opus":0.26558728525217706,"score_gpt":0.5410066149450267,"score_spread":0.2754193296928496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401195388","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":[0.047685508,0.007321811,0.94199646,0.00021351341,0.00021319329,0.0008590785,0.000057609774,0.000094934316,0.0015578724],"genre_scores_gemma":[0.82056904,0.00046968274,0.17880449,0.000012556301,0.000021891594,0.000033310112,0.000011575355,0.0000148008385,0.00006268614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846584,0.00012623782,0.0004898176,0.00018420898,0.0006015773,0.00013232845],"domain_scores_gemma":[0.9963036,0.0031413,0.00013132536,0.00012884493,0.00027092893,0.000023963596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029832784,0.00011829697,0.000476226,0.00034518496,0.0000148035815,0.000007449915,0.00006182045,0.000039155973,0.00004070479],"category_scores_gemma":[0.0060332324,0.00008720042,0.0000041300177,0.0004659748,0.0002063339,0.00006099018,0.00003353257,0.00021049548,0.0000012234035],"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":[0.00008628958,0.00013935425,0.012930131,0.0021975883,0.00020785822,0.00012411732,0.015470206,0.00031111314,0.0030674436,0.91623694,0.0027248147,0.046504173],"study_design_scores_gemma":[0.0008484476,0.0004929464,0.0008729477,0.0023467985,0.00018612637,0.0000066277335,0.002100605,0.12594736,0.0007143642,0.8663069,0.00003951932,0.00013732677],"about_ca_topic_score_codex":0.0000371916,"about_ca_topic_score_gemma":0.00017308803,"teacher_disagreement_score":0.77288353,"about_ca_system_score_codex":0.00020869443,"about_ca_system_score_gemma":0.0000614177,"threshold_uncertainty_score":0.7222778},"labels":[],"label_agreement":null},{"id":"W4401219712","doi":"10.1002/cjs.11825","title":"Bayesian jackknife empirical likelihood‐based inference for missing data and causal inference","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Minority Health and Health Disparities; National Institute of General Medical Sciences; National Security Agency; Simons Foundation; National Science Foundation","keywords":"Jackknife resampling; Missing data; Inference; Causal inference; Estimator; Empirical likelihood; Econometrics; Imputation (statistics); Computer science; Bayesian inference; Statistics; Bayesian probability; Mathematics; Artificial intelligence","score_opus":0.23073993883908367,"score_gpt":0.4527775907923348,"score_spread":0.22203765195325115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401219712","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":[0.0012704466,0.0005014991,0.9942055,0.0010249923,0.0002646823,0.00019293177,0.0023544326,0.00004521708,0.00014029944],"genre_scores_gemma":[0.46094447,0.000034023895,0.5385393,0.00021559221,0.00014233557,0.000003894568,0.000050362287,0.00003890342,0.000031106665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833065,0.0000616962,0.0006554851,0.00027011556,0.00022857642,0.0004534982],"domain_scores_gemma":[0.99476475,0.0033746948,0.00022201678,0.00040204378,0.0004167474,0.0008197613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007039428,0.00022670935,0.00037611753,0.00033398997,0.00014605443,0.00033363784,0.00048301672,0.00013027583,0.00010204685],"category_scores_gemma":[0.0066671125,0.00020777638,0.00003675562,0.00019604217,0.00023248233,0.00038161202,0.00004641908,0.00045504703,0.0000026209011],"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":[0.00008395053,0.00009584455,0.0102685075,0.0027132789,0.00031289188,0.0028002467,0.0025783442,0.000065004235,0.0005945551,0.3763121,0.25747278,0.34670246],"study_design_scores_gemma":[0.00030166854,0.0004081435,0.00034321478,0.0010188486,0.00019336032,0.00014219523,0.000133111,0.074802175,0.0002573561,0.8946588,0.027344605,0.00039649097],"about_ca_topic_score_codex":0.0002949839,"about_ca_topic_score_gemma":0.008645678,"teacher_disagreement_score":0.5183467,"about_ca_system_score_codex":0.00018900109,"about_ca_system_score_gemma":0.0041233064,"threshold_uncertainty_score":0.8472875},"labels":[],"label_agreement":null},{"id":"W4401273264","doi":"10.1186/s12874-024-02284-5","title":"Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Propensity score matching; Artificial intelligence; Computer science; Machine learning; Deep learning; Supervised learning; Matching (statistics); Unsupervised learning; Observational study; Variance (accounting); Statistics; Artificial neural network; Mathematics","score_opus":0.7400976786095773,"score_gpt":0.5810570523530081,"score_spread":0.15904062625656923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401273264","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":[0.12551333,0.0003384064,0.8703568,0.0015580694,0.00013667243,0.0011815708,0.0000046146233,0.00047217504,0.00043834004],"genre_scores_gemma":[0.21901543,0.00013593417,0.7796817,0.0001024626,0.00017432657,0.00053625857,0.000009674103,0.000080471924,0.0002637372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897632,0.0059753386,0.0006849127,0.0008344821,0.0013984818,0.0013435608],"domain_scores_gemma":[0.93853605,0.060290914,0.000057843274,0.00042522902,0.00026396985,0.00042597673],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036705654,0.0002852754,0.000807647,0.0007947055,0.00022905214,0.00007876803,0.00079070736,0.00056519447,0.00020066327],"category_scores_gemma":[0.09709975,0.00022257063,0.00015989845,0.0007049383,0.0005977142,0.00017507178,0.0005622273,0.0035368386,0.000005454438],"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":[0.000516354,0.00012963648,0.00079969113,0.004294736,0.000073920986,0.00029129972,0.009550062,0.0062731113,0.005440981,0.739445,0.00030242628,0.23288283],"study_design_scores_gemma":[0.00028732728,0.00025061317,0.000034491353,0.0006747518,0.000009880229,0.00004994519,0.00056415354,0.2363728,0.001360049,0.7599655,0.00024846816,0.0001820368],"about_ca_topic_score_codex":0.0005268015,"about_ca_topic_score_gemma":0.004681815,"teacher_disagreement_score":0.2327008,"about_ca_system_score_codex":0.0003835712,"about_ca_system_score_gemma":0.0013110093,"threshold_uncertainty_score":0.9987621},"labels":[],"label_agreement":null},{"id":"W4401328848","doi":"10.1080/03155986.2024.2383095","title":"PresAIse, a prescriptive AI solution for enterprise","year":2024,"lang":"en","type":"article","venue":"INFOR Information Systems and Operational Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Knowledge management","score_opus":0.23603342410095832,"score_gpt":0.4916251351898137,"score_spread":0.25559171108885537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401328848","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":[0.0030580473,0.00049422274,0.9749091,0.0009785581,0.00036419806,0.0032773926,0.0003150156,0.00037346725,0.016229954],"genre_scores_gemma":[0.9793781,0.00009524806,0.013423306,0.00019022406,0.00028275326,0.0029110378,0.00021106958,0.000022419308,0.0034858598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998316,0.00006350767,0.000545292,0.0001366008,0.0006573045,0.00028133375],"domain_scores_gemma":[0.99768096,0.00082369737,0.000049703638,0.000159269,0.0011980088,0.00008838877],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019387144,0.000120811455,0.00014820763,0.000404688,0.00030695455,0.0010671932,0.00012783184,0.00011733518,0.0000272825],"category_scores_gemma":[0.0011501804,0.000098231125,0.000043927168,0.00022781381,0.000094494804,0.0039602304,0.00008845041,0.0002630503,0.00006130464],"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":[0.00006561756,0.00001144459,0.000017573804,0.00067238475,0.000026687652,4.999008e-7,0.0018861364,0.00006010008,0.00020977236,0.9311912,0.06001754,0.005841041],"study_design_scores_gemma":[0.00035530794,0.00035732452,0.000058403304,0.0005364523,0.000009553316,0.00002993017,0.00086142734,0.29849005,0.0007362213,0.06939284,0.6289524,0.00022011402],"about_ca_topic_score_codex":0.00007474146,"about_ca_topic_score_gemma":0.0000064425303,"teacher_disagreement_score":0.97632,"about_ca_system_score_codex":0.00016850543,"about_ca_system_score_gemma":0.0002571251,"threshold_uncertainty_score":0.9999698},"labels":[],"label_agreement":null},{"id":"W4401386448","doi":"10.1080/07350015.2024.2388643","title":"Difference-in-Differences Estimator of Quantile Treatment Effect on the Treated","year":2024,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Advanced Causal Inference Techniques","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":"Toronto Metropolitan University","funders":"Alliance de recherche numérique du Canada","keywords":"Estimator; Quantile; Covariate; Econometrics; Consistency (knowledge bases); Mathematics; Statistics; Confidence interval; Outcome (game theory)","score_opus":0.09785292078610203,"score_gpt":0.3699782721082899,"score_spread":0.27212535132218785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401386448","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":[0.97557646,0.0002148661,0.023455989,0.00013631217,0.00017777114,0.00014551438,0.000101166355,0.000016041005,0.00017586596],"genre_scores_gemma":[0.9930558,0.0005478116,0.0062587634,0.000005569248,0.000045661836,0.000008516366,0.0000014660085,0.000014844612,0.000061533625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991576,0.0000488897,0.000497701,0.000104730825,0.00007309764,0.000117982214],"domain_scores_gemma":[0.99671894,0.00281074,0.0002650552,0.00011743004,0.00005285492,0.000034947592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023900883,0.00016242395,0.0004871146,0.0001425928,0.000029733623,0.000052022864,0.00009746323,0.00004572558,0.00007249619],"category_scores_gemma":[0.00024426103,0.00008390711,0.000042977095,0.00007358958,0.000090043635,0.00006898764,0.000015302952,0.00010550282,0.0000029337075],"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":[0.0004096284,0.0003373834,0.042377688,0.00087583007,0.00037417363,0.00023839244,0.00083785586,0.00016757355,0.0013078006,0.8341212,0.0017995114,0.11715292],"study_design_scores_gemma":[0.0014795259,0.00467152,0.15913163,0.0028648349,0.00043736715,0.00021197078,0.0002905757,0.030789232,0.009286384,0.790015,0.00030296284,0.00051900704],"about_ca_topic_score_codex":0.000079091704,"about_ca_topic_score_gemma":0.000050999555,"teacher_disagreement_score":0.11675394,"about_ca_system_score_codex":0.00011544899,"about_ca_system_score_gemma":0.00007905219,"threshold_uncertainty_score":0.34216326},"labels":[],"label_agreement":null},{"id":"W4401391220","doi":"10.1007/s40273-024-01401-y","title":"Improving Transparency of Decision Models Through the Application of Decision Analytic Models with Omitted Objects Displayed (DAMWOOD)","year":2024,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; Institute of Health Economics; University of Alberta","funders":"Medical Research Council","keywords":"Transparency (behavior); Computer science; Decision model; Decision analysis; Management science; Scrutiny; Data science; Economics; Machine learning; Computer security; Mathematical economics; Political science","score_opus":0.09701390709738864,"score_gpt":0.40910001256669143,"score_spread":0.3120861054693028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401391220","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":[0.19221865,0.00034851828,0.805654,0.00004090627,0.000060867933,0.00065609656,0.0000600533,0.00014893526,0.0008119913],"genre_scores_gemma":[0.87469476,0.00038537045,0.12467389,0.0000377439,0.000032516396,0.000094324954,0.000010234048,0.000057810474,0.000013372751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982152,0.000036519352,0.00086681003,0.00042553782,0.00021388516,0.00024202785],"domain_scores_gemma":[0.9974892,0.001353076,0.00037266006,0.00059755467,0.00013226544,0.00005522763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004272108,0.00026595203,0.00046766002,0.00012977829,0.0000627225,0.000036941317,0.0004653271,0.00009477947,0.000018875488],"category_scores_gemma":[0.000041396263,0.00018607407,0.00014088931,0.0003012112,0.0001162986,0.00093971967,0.00007544979,0.00025305225,0.000003778157],"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":[0.0008873481,0.0003961102,0.000035845736,0.0009909313,0.00038535486,0.0000097852,0.0049504465,0.27291575,0.045543715,0.53199106,0.00040553187,0.14148813],"study_design_scores_gemma":[0.00028213076,0.000047677157,0.0000012894603,0.00011874767,0.00012941669,0.000005609581,0.000077826684,0.49999815,0.03621787,0.46298322,0.000020662503,0.00011739103],"about_ca_topic_score_codex":0.00010404159,"about_ca_topic_score_gemma":0.00006920535,"teacher_disagreement_score":0.6824761,"about_ca_system_score_codex":0.00013225924,"about_ca_system_score_gemma":0.000121507306,"threshold_uncertainty_score":0.75878805},"labels":[],"label_agreement":null},{"id":"W4401484096","doi":"10.1515/jci-2022-0079","title":"Estimation of network treatment effects with non-ignorable missing confounders","year":2024,"lang":"en","type":"article","venue":"Journal of Causal Inference","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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Estimation; Missing data; Statistics; Econometrics; Computer science; Mathematics; Economics","score_opus":0.08442930811171528,"score_gpt":0.4148608621997699,"score_spread":0.33043155408805464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401484096","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":[0.09165462,0.00044895735,0.9053304,0.00013798251,0.00022222068,0.000253694,0.0000021353019,0.000088815534,0.0018611281],"genre_scores_gemma":[0.8614064,0.00009838217,0.13822994,0.000021159869,0.00010529676,0.000007866711,0.0000011540517,0.00002629744,0.00010350647],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858284,0.00006768322,0.00060421805,0.00013933679,0.00035800666,0.00024793603],"domain_scores_gemma":[0.9971557,0.0017906524,0.00049097644,0.00020396065,0.00025086038,0.00010780682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004317829,0.00022309726,0.0005169161,0.0001559784,0.00005288749,0.00009393966,0.00014765513,0.00009312481,0.00003105596],"category_scores_gemma":[0.00035522573,0.00015016033,0.00009732911,0.00030518137,0.000118723874,0.0005375316,0.000021990712,0.0002561446,0.0000038344597],"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":[0.00088076567,0.0009444774,0.0022199429,0.00457818,0.001922519,0.001562465,0.005092411,0.06952415,0.03135297,0.42814204,0.0072324653,0.44654763],"study_design_scores_gemma":[0.0009369086,0.005301544,0.00031052233,0.007768349,0.00054272916,0.00035746495,0.00012124685,0.032076232,0.09867836,0.8529378,0.0005322058,0.00043659008],"about_ca_topic_score_codex":0.000016392545,"about_ca_topic_score_gemma":0.000012553475,"teacher_disagreement_score":0.7697518,"about_ca_system_score_codex":0.00022636395,"about_ca_system_score_gemma":0.00041008808,"threshold_uncertainty_score":0.61233604},"labels":[],"label_agreement":null},{"id":"W4401499316","doi":"10.1177/00236772231217777","title":"Causal mediation analysis: How to avoid fooling yourself that <i>X</i> causes <i>Y</i>","year":2024,"lang":"en","type":"article","venue":"Laboratory Animals","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":"Prioris.ai (Canada)","funders":"","keywords":"Mediation; Causal inference; Outcome (game theory); Mechanism (biology); Causal analysis; Causal model; Psychology; Intervention (counseling); Statistical analysis; Computer science; Cognitive psychology; Medicine; Econometrics; Risk analysis (engineering); Statistics; Epistemology; Mathematics; Psychiatry; Pathology","score_opus":0.10422228867727054,"score_gpt":0.3861531258761427,"score_spread":0.28193083719887213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401499316","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":[0.64781046,0.0038405235,0.332886,0.0037844933,0.0008763565,0.0013583843,0.00088256766,0.006457609,0.0021035734],"genre_scores_gemma":[0.9727822,0.00008473054,0.025684418,0.0006084559,0.00034403885,0.00015378441,0.000019671903,0.00007915577,0.00024355692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979875,0.00016330428,0.00033999438,0.000568458,0.0004914648,0.00044924952],"domain_scores_gemma":[0.9981866,0.0006626202,0.0001318007,0.00052969164,0.0002764362,0.00021285913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083404273,0.00032982533,0.00050493446,0.0004661649,0.00012224859,0.00031718303,0.00027903504,0.00018390201,0.00012050207],"category_scores_gemma":[0.00074628455,0.0003074899,0.00014182704,0.0023119892,0.000053453736,0.0006069244,0.00009530884,0.000319875,0.00009045281],"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":[0.00011433743,0.00024180234,0.010352784,0.0011691886,0.0026693204,0.00058000133,0.0069441423,0.00029015006,0.4343777,0.4544424,0.08746005,0.001358121],"study_design_scores_gemma":[0.0003290656,0.0005512643,0.0015000488,0.00059662905,0.0023775906,0.000015895625,0.002430313,0.0010084338,0.7442959,0.15350866,0.0913198,0.0020663952],"about_ca_topic_score_codex":0.0000063227853,"about_ca_topic_score_gemma":0.00014436875,"teacher_disagreement_score":0.3249717,"about_ca_system_score_codex":0.00014487638,"about_ca_system_score_gemma":0.00014530576,"threshold_uncertainty_score":0.9999377},"labels":[],"label_agreement":null},{"id":"W4401517718","doi":"10.1515/ijb-2023-0116","title":"History-restricted marginal structural model and latent class growth analysis of treatment trajectories for a time-dependent outcome","year":2024,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Advanced Causal Inference Techniques","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":"McGill University Health Centre; Université de Montréal; McGill University; Institut National de Santé Publique du Québec; Université Laval","funders":"Canadian Institutes of Health Research; Université Laval","keywords":"Econometrics; Marginal structural model; Outcome (game theory); Class (philosophy); Latent class model; Structural equation modeling; Statistics; Marginal model; Mathematics; Computer science; Causal inference; Mathematical economics; Regression analysis; Artificial intelligence","score_opus":0.10769438102764733,"score_gpt":0.39364910278080345,"score_spread":0.2859547217531561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401517718","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":[0.33597946,0.00057241344,0.6600345,0.0009066689,0.00056755036,0.000293284,0.001509899,0.000057164572,0.00007907886],"genre_scores_gemma":[0.9318358,0.00014605261,0.0674944,0.000031558266,0.00007327502,0.000006291657,0.000019728444,0.000017406104,0.0003755408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987711,0.000030475423,0.0006114189,0.00010506512,0.00037749493,0.000104458966],"domain_scores_gemma":[0.9978052,0.0010517333,0.00039758332,0.000097352044,0.0006036549,0.00004448863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021421214,0.00014206165,0.0003507646,0.00034891116,0.000023947869,0.00003983835,0.0002562714,0.000043103617,0.000037267117],"category_scores_gemma":[0.0003876831,0.0000877755,0.00016109661,0.00010733394,0.00010109524,0.00010832697,0.00003610197,0.00011399332,3.9072933e-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":[0.0009270431,0.00016667685,0.0029754806,0.00016717073,0.01074213,0.00012700389,0.0030189867,0.0047080307,0.016148042,0.95123464,0.004325324,0.0054594814],"study_design_scores_gemma":[0.00070480007,0.00075875747,0.0013437972,0.00009471222,0.003682103,0.00011531715,0.00010156778,0.48307687,0.0024136782,0.5071725,0.00032096007,0.00021489162],"about_ca_topic_score_codex":0.00002695437,"about_ca_topic_score_gemma":0.000024030822,"teacher_disagreement_score":0.5958563,"about_ca_system_score_codex":0.0007628059,"about_ca_system_score_gemma":0.00015541996,"threshold_uncertainty_score":0.3579381},"labels":[],"label_agreement":null},{"id":"W4401613484","doi":"10.1097/ccm.0000000000006371","title":"Toward Precision in Critical Care Research: Methods for Observational and Interventional Studies","year":2024,"lang":"en","type":"review","venue":"Critical Care Medicine","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":"Toronto General Hospital; University of Toronto; University Health Network","funders":"U.S. National Library of Medicine; Canadian Institutes of Health Research; National Institutes of Health; National Center for Advancing Translational Sciences; National Sanitarium Association; National Heart, Lung, and Blood Institute; National Security Agency; U.S. Department of Defense","keywords":"Medicine; Observational study; Psychological intervention; Intensive care medicine; Randomized controlled trial; Clinical trial; Intervention (counseling); Acute respiratory distress; External validity; Population; Research design; Treatment effect; Nursing; Surgery; Internal medicine","score_opus":0.9246768419156625,"score_gpt":0.7668087164089641,"score_spread":0.15786812550669838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401613484","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":[0.000001087688,0.9384985,0.05716944,0.001808444,0.0006070837,0.0013301141,0.00016107429,0.00013918606,0.0002850539],"genre_scores_gemma":[0.00010323592,0.7183548,0.2789167,0.000048131427,0.00060823304,0.0016305759,0.00017004614,0.000086170374,0.00008206495],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99557954,0.0010487827,0.0012928913,0.00083742524,0.0007037485,0.00053758535],"domain_scores_gemma":[0.95445603,0.0425907,0.00005694412,0.00038099376,0.002323741,0.00019160108],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034050208,0.00047567522,0.002189107,0.0006195824,0.00011611038,0.00004660763,0.00034035405,0.0004574594,0.00007803146],"category_scores_gemma":[0.13153617,0.00032661593,0.00030807502,0.00051664264,0.0016163118,0.00013582541,0.00056340045,0.0013964998,0.000005657883],"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":[0.0000074763498,0.000023859391,6.070952e-7,0.16620117,0.000029044275,0.000030735406,0.0011782736,3.453354e-9,6.266649e-7,0.41374344,0.002099935,0.41668484],"study_design_scores_gemma":[0.0001285465,0.0006488519,5.534284e-7,0.0798243,0.0007770591,0.000033329507,0.007777037,0.0000072189378,0.0000039837864,0.6494051,0.26116443,0.00022958459],"about_ca_topic_score_codex":0.0000040820714,"about_ca_topic_score_gemma":0.000011822635,"teacher_disagreement_score":0.41645527,"about_ca_system_score_codex":0.0006634083,"about_ca_system_score_gemma":0.00026236047,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W4401642076","doi":"10.1097/mcc.0000000000001186","title":"Subgroup analyses and heterogeneity of treatment effects in randomized trials: a primer for the clinician","year":2024,"lang":"en","type":"review","venue":"Current Opinion in Critical Care","topic":"Advanced Causal Inference Techniques","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 Alberta","funders":"","keywords":"Medicine; Randomized controlled trial; Subgroup analysis; MEDLINE; Intensive care medicine; Internal medicine; Meta-analysis","score_opus":0.8215538829094038,"score_gpt":0.6981431834382862,"score_spread":0.1234106994711176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401642076","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":[0.0000065792537,0.98171,0.010248517,0.000026367215,0.0015242802,0.0061801835,0.0002425799,0.000052637082,0.000008821645],"genre_scores_gemma":[0.00047927516,0.9912135,0.0029356815,0.0000025516972,0.00024345881,0.004989937,0.00008541461,0.00004897434,0.0000012293464],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99487954,0.0020486233,0.0021015245,0.0005082751,0.00017953181,0.0002825001],"domain_scores_gemma":[0.9393063,0.059786387,0.00031333434,0.0004137398,0.00011674426,0.000063493746],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026041034,0.0004915554,0.005611957,0.00031019893,0.000030131305,0.000040401443,0.00020297963,0.0002915526,0.0000043206373],"category_scores_gemma":[0.022879155,0.00025682824,0.001461116,0.00027985868,0.000306,0.000049053746,0.0001121567,0.00040382735,0.0000012099678],"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":[0.00058516103,0.0001682872,0.0000046818964,0.18361779,0.00019778131,0.000001121506,0.00026349167,1.7121748e-7,2.2899529e-7,0.05416885,0.000090642796,0.7609018],"study_design_scores_gemma":[0.04465525,0.0014642334,0.000002689592,0.27824777,0.01956266,0.000013167281,0.000492773,0.0003431634,0.000096115335,0.36270785,0.2909462,0.0014681515],"about_ca_topic_score_codex":0.000016289225,"about_ca_topic_score_gemma":0.000020060163,"teacher_disagreement_score":0.7594336,"about_ca_system_score_codex":0.00031257898,"about_ca_system_score_gemma":0.00019353519,"threshold_uncertainty_score":0.9999884},"labels":[],"label_agreement":null},{"id":"W4401798123","doi":"10.1038/s41562-024-01939-z","title":"Causal inference on human behaviour","year":2024,"lang":"en","type":"review","venue":"Nature Human Behaviour","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Causal inference; Inference; Causal model; Key (lock); Data science; Observational study; Causal structure; Statistical inference; Computer science; Randomized experiment; Causal reasoning; Psychology; Cognitive psychology; Management science; Epistemology; Artificial intelligence; Econometrics; Cognition; Mathematics","score_opus":0.32275330399114127,"score_gpt":0.5595938479781803,"score_spread":0.23684054398703908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401798123","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":[0.00039426,0.98706895,0.00008972447,0.000021284131,0.0009767961,0.0025905543,0.0005878719,0.0031142493,0.0051562977],"genre_scores_gemma":[0.0070883897,0.96893376,0.0031176815,0.00012866309,0.0013338414,0.0014114981,0.0012969536,0.001036401,0.015652789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99392956,0.00032420296,0.001745366,0.0017529294,0.0012003649,0.0010475498],"domain_scores_gemma":[0.9956446,0.00048354667,0.00097228517,0.0022817925,0.00028298324,0.00033478637],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.00069273345,0.001951842,0.0033981688,0.0011107934,0.00044152915,0.00035310912,0.001784119,0.0042227753,0.0006639733],"category_scores_gemma":[0.0003896874,0.0015655343,0.0012756072,0.00070908765,0.00024738983,0.00023622037,0.00064614497,0.010825679,0.0005330976],"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":[0.0000046912705,0.00090385077,0.00010750268,0.016464554,0.00027533324,0.0012964023,0.00021959143,5.5259328e-8,0.00001925284,0.82266825,0.065869845,0.09217069],"study_design_scores_gemma":[0.00035405674,0.0009991959,0.00008980995,0.065046266,0.010270911,0.00022974603,0.000035135177,2.806976e-7,0.00009740267,0.23268145,0.68617606,0.0040196925],"about_ca_topic_score_codex":0.000037744765,"about_ca_topic_score_gemma":0.00016036128,"teacher_disagreement_score":0.6203062,"about_ca_system_score_codex":0.00095820246,"about_ca_system_score_gemma":0.00030253627,"threshold_uncertainty_score":0.9993225},"labels":[],"label_agreement":null},{"id":"W4401807474","doi":"10.1007/s40471-024-00353-3","title":"The Target Cohort Approach: An Extension of the Target Trial Framework to Nested Case-Control Studies with Incidence Density Sampling","year":2024,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; Public Health Ontario; University of Toronto","funders":"","keywords":"Nested case-control study; Statistics; Extension (predicate logic); Incidence (geometry); Sampling (signal processing); Econometrics; Cohort; Mathematics; Computer science; Medicine","score_opus":0.34456670489819724,"score_gpt":0.5020242451527828,"score_spread":0.15745754025458553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401807474","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":[0.41966596,0.0042463844,0.57152563,0.00045402945,0.0015850783,0.0021821477,0.000008050801,0.0003174081,0.000015294754],"genre_scores_gemma":[0.79569083,0.00013285391,0.2032307,0.00015202121,0.0002941615,0.00043874353,0.0000059847353,0.000039380666,0.00001534293],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99529564,0.0013912625,0.0015878287,0.0008813641,0.0002988466,0.0005450627],"domain_scores_gemma":[0.9825669,0.014204437,0.00097553706,0.0016214562,0.00048729137,0.0001444092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010051613,0.00038727594,0.001214592,0.000080544014,0.00042131948,0.00002222429,0.0002966822,0.00023762982,0.0000048674715],"category_scores_gemma":[0.05470561,0.0001864772,0.0001985944,0.00040885215,0.0006026262,0.0001706928,0.00026817486,0.0009375304,0.0000012529636],"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":[0.0069557917,0.0011713074,0.6515354,0.0017456566,0.0025143595,0.0038778416,0.0063651637,0.011610685,0.00091816625,0.28197187,0.014809209,0.016524553],"study_design_scores_gemma":[0.00045939744,0.00041054236,0.004833915,0.000930685,0.00038781966,0.00436862,0.00038748365,0.0031388141,0.00034848604,0.9835612,0.00079199165,0.000381037],"about_ca_topic_score_codex":0.000028910632,"about_ca_topic_score_gemma":0.000020093741,"teacher_disagreement_score":0.70158935,"about_ca_system_score_codex":0.00013162784,"about_ca_system_score_gemma":0.0001746114,"threshold_uncertainty_score":0.953257},"labels":[],"label_agreement":null},{"id":"W4401832609","doi":"10.1016/j.jpain.2024.104558","title":"Response Letter to Pamela E Macintyre’s Letter to the Editor","year":2024,"lang":"en","type":"letter","venue":"Journal of Pain","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Seqirus; Prince of Wales Hospital Foundation; Avant Foundation; Alberta Innovates","keywords":"Psychology; Letter to the editor; Psychoanalysis; Philosophy; Political science; Law","score_opus":0.07034623115932609,"score_gpt":0.3776135619668007,"score_spread":0.3072673308074746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401832609","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":[0.00016033424,0.00007378572,0.10590488,0.88709307,0.005941069,0.0005082177,0.000044371172,0.00012036488,0.00015393276],"genre_scores_gemma":[0.00009068035,0.0000056236527,0.036800645,0.8176153,0.13590823,0.000059326303,0.0000025420134,0.0001585694,0.009359105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947937,0.0018709645,0.0011687124,0.00036135325,0.0011973149,0.00060792203],"domain_scores_gemma":[0.99278367,0.0052024983,0.0005984245,0.000892997,0.00035311823,0.0001693169],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008945861,0.0005269678,0.0007929688,0.00064258924,0.00007655979,0.00023387102,0.0011885888,0.00077628123,0.00030246508],"category_scores_gemma":[0.005896589,0.00032495265,0.00047289403,0.00035033948,0.000062700856,0.00014733819,0.0002705383,0.005407507,0.0005755202],"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":[0.00016690411,0.000016560474,0.0000011859739,0.00012458969,0.00010682634,0.0018011491,0.0006560217,0.0000046703135,0.0013282602,0.00006752533,0.99475867,0.00096766185],"study_design_scores_gemma":[0.00008254374,0.00049567485,0.0000018245747,0.0010777874,0.00011140105,0.00011607921,0.000030100598,0.000005254132,0.0008532823,0.025168894,0.9716695,0.0003876427],"about_ca_topic_score_codex":0.0000034572392,"about_ca_topic_score_gemma":0.0000069811686,"teacher_disagreement_score":0.12996717,"about_ca_system_score_codex":0.00046409408,"about_ca_system_score_gemma":0.00015180335,"threshold_uncertainty_score":0.99992025},"labels":[],"label_agreement":null},{"id":"W4401850710","doi":"10.1177/17407745241268054","title":"Estimands in clinical trials of complex disease processes","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Context (archaeology); Causal inference; Meaning (existential); Disease; Clinical trial; Intensive care medicine; Medicine; Computer science; Psychology; Psychotherapist","score_opus":0.9162224055802772,"score_gpt":0.7317444564015385,"score_spread":0.18447794917873872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401850710","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":[0.507594,0.011983707,0.4223586,0.014371627,0.009147037,0.017397365,0.0021636323,0.0057362583,0.009247818],"genre_scores_gemma":[0.91839033,0.0019833513,0.076838985,0.00030906367,0.0017081664,0.00024301597,0.000044078715,0.00008454572,0.00039845667],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97699773,0.00903863,0.012468267,0.00073359004,0.00042033644,0.00034143787],"domain_scores_gemma":[0.583972,0.4098773,0.003154277,0.0018680221,0.00046267637,0.00066571054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12182597,0.00028807262,0.004052255,0.00019207996,0.000022265567,0.000069848815,0.00059715234,0.00037864316,0.00058056484],"category_scores_gemma":[0.7444162,0.00020426935,0.0011642372,0.0005493043,0.00047696513,0.00020338451,0.00023458441,0.0006815643,0.000051973744],"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":[0.007006563,0.0062076673,0.028018463,0.008213409,0.0010172795,0.00047715488,0.0003176896,0.000020133679,0.0006137007,0.36681217,0.1550071,0.42628866],"study_design_scores_gemma":[0.0017442995,0.0005164701,0.0019650455,0.0014662229,0.00039906666,0.0000013643036,0.00002353051,0.0007960636,0.00039717238,0.9812299,0.011178255,0.0002825789],"about_ca_topic_score_codex":0.000004015678,"about_ca_topic_score_gemma":0.000009849058,"teacher_disagreement_score":0.6225902,"about_ca_system_score_codex":0.000033106273,"about_ca_system_score_gemma":0.00071605685,"threshold_uncertainty_score":0.904265},"labels":[],"label_agreement":null},{"id":"W4402042387","doi":"10.1073/pnas.2402736121","title":"On the role of parameterization in models with a misspecified nuisance component","year":2024,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","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":"University of Toronto","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; UK Research and Innovation","keywords":"Orthogonality; Nuisance parameter; Consistency (knowledge bases); Estimator; Unification; Mathematics; Component (thermodynamics); Inference; Applied mathematics; Interpretation (philosophy); Econometrics; Computer science; Statistics; Discrete mathematics; Artificial intelligence; Physics","score_opus":0.17862417495625385,"score_gpt":0.3845647740426162,"score_spread":0.20594059908636234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402042387","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":[0.9861966,0.00010518169,0.0002541229,0.0016627017,0.000005597309,0.00033660966,0.000009122414,0.00003180842,0.011398276],"genre_scores_gemma":[0.9886863,0.000018136336,0.0111874845,0.00005027294,0.000009063983,0.00002247045,4.3863274e-8,0.000004357498,0.000021855043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873126,0.0000070196393,0.0002650344,0.00014975766,0.0007624594,0.000084483865],"domain_scores_gemma":[0.9990612,0.0005488873,0.00023764503,0.000010659776,0.00013164151,0.00000992408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085215166,0.00007187405,0.00012418785,0.00012524077,0.000042214804,0.000015141519,0.00046464513,0.00004011691,0.0000071479367],"category_scores_gemma":[0.00036436704,0.000036048456,0.000030017647,0.00067727664,0.0004967481,0.00030335016,0.00005214074,0.00014133655,2.2701441e-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":[0.0000122135,0.000028261882,0.00007893443,0.000053626594,0.000004138434,2.5099793e-9,0.00028998672,0.00042613404,0.17369834,0.825225,0.000047027814,0.00013631028],"study_design_scores_gemma":[0.000022368087,0.000033700086,0.00027097866,0.0003550411,0.0000026934872,9.3673333e-7,0.00012078073,0.018227967,0.3409688,0.63995844,0.000009966112,0.000028309732],"about_ca_topic_score_codex":0.0000027462768,"about_ca_topic_score_gemma":7.4374945e-8,"teacher_disagreement_score":0.18526655,"about_ca_system_score_codex":0.000032182532,"about_ca_system_score_gemma":0.00002057325,"threshold_uncertainty_score":0.1830289},"labels":[],"label_agreement":null},{"id":"W4402194648","doi":"10.1111/1475-6773.14376","title":"Addressing immortal time bias in precision medicine: Practical guidance and methods development","year":2024,"lang":"en","type":"article","venue":"Health Services 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 British Columbia; Simon Fraser University","funders":"Terry Fox Research Institute; Genome British Columbia; Genome Canada","keywords":"Precision medicine; Pooling; Imputation (statistics); Missing data; Computer science; Data mining; Matching (statistics); Statistics; Sample size determination; Population; Personalized medicine; Selection bias; Econometrics; Machine learning; Medicine; Artificial intelligence; Mathematics; Bioinformatics","score_opus":0.6727635142755471,"score_gpt":0.6964341676211453,"score_spread":0.023670653345598147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402194648","genre_codex":"empirical","genre_gemma":"methods","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":[0.48052645,0.0908068,0.3266072,0.04874162,0.00095283403,0.011180326,0.000030989057,0.0038481667,0.037305627],"genre_scores_gemma":[0.073892966,0.0007327411,0.9241136,0.00031653387,0.00013442441,0.00020611809,0.000010840071,0.00006202401,0.0005307829],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958004,0.0013916488,0.0007255766,0.00051339046,0.0008870899,0.000681948],"domain_scores_gemma":[0.99261177,0.006489182,0.00011697923,0.00033496937,0.000206341,0.00024077464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015065288,0.00016996756,0.00038367393,0.00052686164,0.00019385543,0.00010641154,0.00021877974,0.00013401372,0.00018876445],"category_scores_gemma":[0.0011741553,0.00013099221,0.000015845968,0.0008997202,0.00014655052,0.00038134746,0.00035868,0.0009183553,0.000045682395],"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":[0.00017532508,0.0002307552,0.0008800868,0.016568754,0.00004280137,0.00027493443,0.03625248,0.0000022637735,0.0050410293,0.04393914,0.0048860223,0.8917064],"study_design_scores_gemma":[0.00088378275,0.0011455799,0.0094438,0.038209822,0.000015266258,0.00024934692,0.006187302,0.09459383,0.0140673,0.7691149,0.06523123,0.0008578465],"about_ca_topic_score_codex":0.00034067174,"about_ca_topic_score_gemma":0.0003278283,"teacher_disagreement_score":0.8908486,"about_ca_system_score_codex":0.00035576613,"about_ca_system_score_gemma":0.0005922209,"threshold_uncertainty_score":0.53417075},"labels":[],"label_agreement":null},{"id":"W4402323319","doi":"10.1002/pst.2436","title":"Propensity Score Analysis With Baseline and Follow‐Up Measurements of the Outcome Variable","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","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":"Propensity score matching; Baseline (sea); Statistics; Weighting; Estimator; Observational study; Variable (mathematics); Matching (statistics); Regression analysis; Mathematics; Medicine","score_opus":0.4838276404501285,"score_gpt":0.4782297378790365,"score_spread":0.005597902571091995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402323319","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":[0.018065337,0.0001271427,0.98023665,0.00012899836,0.00009485927,0.00043073963,0.0002990825,0.00013841865,0.0004787592],"genre_scores_gemma":[0.7782694,0.000018282484,0.22116576,0.00012649152,0.000019322228,0.00002012221,0.000009976268,0.000025050163,0.00034555295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985611,0.00012812363,0.00037379822,0.00024893216,0.00046635093,0.0002216885],"domain_scores_gemma":[0.998556,0.0007638929,0.00008327199,0.00027395945,0.00022020777,0.000102678685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078695844,0.00017031313,0.00035796402,0.00006721527,0.00006970308,0.00004445928,0.00015765509,0.000045436333,0.0001834842],"category_scores_gemma":[0.00096325955,0.000099059565,0.000047747093,0.0006556474,0.00019660637,0.00008251629,0.00012538963,0.00027450948,0.0000025599602],"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":[0.00029682365,0.0003582284,0.4034584,0.0024671997,0.0028239603,0.000054256423,0.00032340837,0.0001283463,0.0060947216,0.5673823,0.0037648866,0.012847508],"study_design_scores_gemma":[0.002461731,0.00043036707,0.016132742,0.00081636914,0.020016551,0.000052360032,0.000047634894,0.12914056,0.08975075,0.733953,0.005820202,0.0013777073],"about_ca_topic_score_codex":0.000024428466,"about_ca_topic_score_gemma":0.000040479605,"teacher_disagreement_score":0.7602041,"about_ca_system_score_codex":0.000057354177,"about_ca_system_score_gemma":0.00006110372,"threshold_uncertainty_score":0.4039532},"labels":[],"label_agreement":null},{"id":"W4402329644","doi":"10.1016/j.neuchi.2024.101589","title":"Understanding why restrictive trial eligibility criteria are inappropriate","year":2024,"lang":"en","type":"review","venue":"Neurochirurgie","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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 Alberta Hospital; Health Sciences Centre; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; MEDLINE; Intensive care medicine; Political science","score_opus":0.6175615042305665,"score_gpt":0.5330371539830381,"score_spread":0.08452435024752847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402329644","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":[0.000006605446,0.96219224,0.02241344,0.00007576004,0.0021253633,0.0042784736,0.00022621454,0.0022752178,0.006406708],"genre_scores_gemma":[0.000029616158,0.99517035,0.0028787146,0.00007342374,0.00068925164,0.00057284284,0.000035661764,0.00028699526,0.00026312508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953871,0.0006403082,0.0014312419,0.0013328901,0.00056903425,0.0006394409],"domain_scores_gemma":[0.9956265,0.0016678695,0.0010099378,0.0014196659,0.000096919226,0.000179069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072238705,0.0010310482,0.0029074373,0.00050050154,0.00015403118,0.00027266293,0.00075179536,0.00071158964,0.000079893114],"category_scores_gemma":[0.0027848566,0.00080872874,0.00092598464,0.0009414164,0.00016178394,0.00024374173,0.0005479794,0.0018982548,0.00012193953],"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":[0.0025382515,0.00087158516,3.9055118e-7,0.14204451,0.0009272201,0.0015426489,0.00036155636,3.6561102e-7,0.0000075065213,0.46157864,0.23152044,0.1586069],"study_design_scores_gemma":[0.0009128327,0.00021105492,3.7137443e-8,0.010015319,0.0011666502,0.00002908775,0.000028475246,0.0000047611757,0.0000030827607,0.5406941,0.4463978,0.00053677446],"about_ca_topic_score_codex":0.0000068178065,"about_ca_topic_score_gemma":0.000009165259,"teacher_disagreement_score":0.21487737,"about_ca_system_score_codex":0.0010644444,"about_ca_system_score_gemma":0.00040238633,"threshold_uncertainty_score":0.9994364},"labels":[],"label_agreement":null},{"id":"W4402576198","doi":"10.1371/journal.pmed.1004455","title":"Behavioral risk factors and socioeconomic inequalities in ischemic heart disease mortality in the United States: A causal mediation analysis using record linkage data","year":2024,"lang":"en","type":"article","venue":"PLoS Medicine","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":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"National Institute on Alcohol Abuse and Alcoholism; Centers for Disease Control and Prevention; National Institutes of Health","keywords":"Socioeconomic status; Medicine; Demography; Marital status; National Death Index; Cohort study; Mediation; Proportional hazards model; Gerontology; Cohort; Hazard ratio; Population; Environmental health; Confidence interval; Internal medicine","score_opus":0.3274916916027929,"score_gpt":0.4624875178117706,"score_spread":0.1349958262089777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402576198","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":[0.9957142,0.0002387415,0.002770735,0.00042413906,0.00003909249,0.00032636538,0.0003558664,0.00012310765,0.00000776306],"genre_scores_gemma":[0.9968445,0.0003565247,0.0013168642,0.000112453126,0.000072755,0.000028986959,0.0012420693,0.000021332946,0.0000045610846],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983559,0.00028805708,0.0005651077,0.0003490037,0.0002372805,0.00020464153],"domain_scores_gemma":[0.99780345,0.0013707932,0.00013455798,0.00058650406,0.000028575521,0.000076133896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012116411,0.00019107916,0.0004319232,0.00053850363,0.000039450122,0.00003281174,0.00022147378,0.00007294874,0.000073656],"category_scores_gemma":[0.0006882367,0.00012837382,0.000029767702,0.0006206862,0.00017083286,0.00033416145,0.000105998006,0.0004181962,0.0000010276482],"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":[0.000017023898,0.00013476795,0.9833197,0.0002758619,0.00015719519,0.000038307768,0.01472165,0.000054427066,0.0004160261,0.00037257833,0.00036098072,0.00013145964],"study_design_scores_gemma":[0.0012105062,0.0003308194,0.19815384,0.001409076,0.006365044,0.000004009802,0.040281568,0.5629628,0.00042955298,0.18743317,0.00038289197,0.0010367183],"about_ca_topic_score_codex":0.005722364,"about_ca_topic_score_gemma":0.0021554092,"teacher_disagreement_score":0.7851659,"about_ca_system_score_codex":0.00015446194,"about_ca_system_score_gemma":0.000057882105,"threshold_uncertainty_score":0.8650541},"labels":[],"label_agreement":null},{"id":"W4402581782","doi":"10.1038/s41592-024-02405-4","title":"Propensity score matching","year":2024,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Propensity score matching; Matching (statistics); Computational biology; Computer science; Biology; Medicine; Internal medicine; Mathematics; Statistics","score_opus":0.2954066621601936,"score_gpt":0.548128130712416,"score_spread":0.25272146855222233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402581782","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":[0.016481528,0.0015112981,0.966413,0.00033025292,0.0005655805,0.00028050464,0.000003856696,0.0017112689,0.012702701],"genre_scores_gemma":[0.08435088,0.000018382254,0.9141338,0.00021484411,0.00016059245,0.000022512542,0.0000020279501,0.00004205725,0.001054921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887604,0.00025663647,0.00018496737,0.00029405867,0.00018188258,0.00020640405],"domain_scores_gemma":[0.99798954,0.001484931,0.00003900073,0.00036518238,0.000070143964,0.00005122748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016803705,0.00016133665,0.00024070895,0.00009816678,0.00005689664,0.0000783904,0.00020166821,0.00034349892,0.00010136439],"category_scores_gemma":[0.001735277,0.00011904262,0.00008284872,0.0002955267,0.000040415813,0.0002045946,0.00011734912,0.0013888772,0.000016859094],"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":[0.0000067163587,0.000018768345,0.00004036483,0.00029604335,0.000029839519,0.00005751203,0.0003311953,5.605e-7,0.033417266,0.78017527,0.004924588,0.18070187],"study_design_scores_gemma":[0.000022781132,0.000019067184,0.00010521086,0.00019779328,0.000023730674,0.00003446138,0.000013244944,0.00009863821,0.084967464,0.8977368,0.016636593,0.0001442454],"about_ca_topic_score_codex":0.000003652233,"about_ca_topic_score_gemma":0.0000034679224,"teacher_disagreement_score":0.18055761,"about_ca_system_score_codex":0.00007218286,"about_ca_system_score_gemma":0.000042957803,"threshold_uncertainty_score":0.6034057},"labels":[],"label_agreement":null},{"id":"W4402615312","doi":"10.1016/j.jclinepi.2024.111532","title":"Using causal diagrams within the Grading of Recommendations, Assessment, Development and Evaluation framework to evaluate confounding adjustment in observational studies","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","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":"Western University","funders":"","keywords":"Confounding; Observational study; Causal inference; Causal model; Medicine; Marginal structural model; Internal medicine; Pathology","score_opus":0.8879150233324599,"score_gpt":0.7146830698223894,"score_spread":0.17323195351007048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402615312","genre_codex":"empirical","genre_gemma":"methods","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":[0.71339166,0.0013929284,0.27578792,0.0076359874,0.0013351846,0.0004082925,0.0000018555501,0.000015809988,0.00003035264],"genre_scores_gemma":[0.43662238,0.00044513462,0.5621017,0.00059119007,0.00019780679,0.000025342988,0.0000016364597,0.0000100891375,0.0000047012804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9896871,0.0047120443,0.004753698,0.00023876775,0.0003965695,0.00021181624],"domain_scores_gemma":[0.8994379,0.09761547,0.0021446664,0.00017090177,0.00053621765,0.00009486236],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080264546,0.0001503594,0.0012218242,0.00018492575,0.00006927487,0.000012718089,0.00016125542,0.00015799275,0.00001856404],"category_scores_gemma":[0.12158931,0.000095282805,0.000116913405,0.00022357418,0.00015947796,0.00019562703,0.00011114238,0.0008369274,5.988746e-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":[0.000076130076,0.00013835367,0.07944689,0.00019515936,0.00056214066,0.000007104437,0.0019643928,0.0028784694,0.00013502252,0.8398923,0.0012090266,0.073494956],"study_design_scores_gemma":[0.00023703107,0.00024680243,0.03662434,0.0018210595,0.00015240454,0.000019046338,0.0007717522,0.020551883,0.00009160235,0.9391187,0.00026510353,0.00010030123],"about_ca_topic_score_codex":0.000005214639,"about_ca_topic_score_gemma":0.000033256325,"teacher_disagreement_score":0.2863138,"about_ca_system_score_codex":0.0003634867,"about_ca_system_score_gemma":0.0005782182,"threshold_uncertainty_score":0.9470612},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4402652454","doi":"10.1002/cjs.11832","title":"Robust causal inference for point exposures with missing confounders","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health","keywords":"Missing data; Causal inference; Estimator; Confounding; Robustness (evolution); Computer science; Inference; Econometrics; Observational study; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.18440192511003298,"score_gpt":0.373473420600046,"score_spread":0.18907149549001304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402652454","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":[0.0011600696,0.00025085217,0.9968941,0.00042915507,0.00024654582,0.00017008491,0.00030120695,0.000037749473,0.00051020965],"genre_scores_gemma":[0.38173828,0.000013087959,0.6178276,0.000097345306,0.00010891822,0.000005204515,0.0000070546103,0.0000414639,0.0001610164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989183,0.00002731213,0.0004299578,0.00012257337,0.00017656415,0.00032529316],"domain_scores_gemma":[0.99742156,0.0013225423,0.00018757,0.00013442461,0.00050066534,0.00043321808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034615825,0.00016339515,0.0002662291,0.00025111248,0.00011066303,0.00022484927,0.00016929019,0.00006831406,0.00011322505],"category_scores_gemma":[0.0013769874,0.00013319385,0.000041307063,0.00012402334,0.00019210874,0.00023202314,0.000005834104,0.00028709022,0.0000020126527],"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":[0.000027418078,0.0000099970475,0.00024742298,0.000378227,0.0001269607,0.0009086026,0.0012591671,0.00019518855,0.0001587749,0.93869686,0.045185536,0.012805861],"study_design_scores_gemma":[0.00027200062,0.0007188933,0.00008320021,0.00094163057,0.00014875941,0.00042277316,0.0006841125,0.001886971,0.0006485649,0.98615986,0.007741722,0.00029151374],"about_ca_topic_score_codex":0.00045985045,"about_ca_topic_score_gemma":0.015896387,"teacher_disagreement_score":0.38057822,"about_ca_system_score_codex":0.00028796395,"about_ca_system_score_gemma":0.002454798,"threshold_uncertainty_score":0.88705575},"labels":[],"label_agreement":null},{"id":"W4402979128","doi":"10.1371/journal.pone.0296951","title":"AteMeVs: An R package for the estimation of the average treatment effect with measurement error and variable selection for confounders","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science and Technology Council","keywords":"Spurious relationship; Computer science; Inference; R package; Weighting; Confounding; Data mining; Estimation; Statistics; Standard error; Causal inference; Software; Variable (mathematics); Machine learning; Mathematics; Artificial intelligence; Medicine; Engineering","score_opus":0.23819350771080977,"score_gpt":0.37140491475370685,"score_spread":0.13321140704289708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402979128","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":[0.072682306,0.00007577171,0.92312324,0.00017885352,0.000021220552,0.0036106429,0.00002602771,0.00016475774,0.00011720611],"genre_scores_gemma":[0.89009917,0.000008925038,0.108530335,0.000013412409,0.000022025884,0.0011752994,0.0000060582142,0.000024682366,0.000120088815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936026,0.000041146814,0.00014728853,0.00013923673,0.00020142925,0.000110615714],"domain_scores_gemma":[0.9988955,0.00070663984,0.0000760111,0.00018547801,0.0001186138,0.000017734335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049165485,0.00011558495,0.00016755315,0.000023918914,0.00011463244,0.00003965903,0.00005808377,0.0000374018,0.0000061691103],"category_scores_gemma":[0.00024800625,0.000055101704,0.000030258227,0.00008413084,0.000042296335,0.00012401374,0.000008858993,0.000046052246,2.7129795e-7],"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":[0.0016334765,0.0031256012,0.0010263912,0.011594686,0.005122318,8.757936e-7,0.006795028,0.0018446594,0.4093265,0.5322702,0.0005572909,0.026702989],"study_design_scores_gemma":[0.0007778528,0.0040407153,0.000036043188,0.0008488054,0.0012085569,0.000002482241,0.00009463054,0.1830421,0.60692805,0.20280886,0.00006407321,0.00014782387],"about_ca_topic_score_codex":0.000027528902,"about_ca_topic_score_gemma":0.00007279246,"teacher_disagreement_score":0.81741685,"about_ca_system_score_codex":0.00017302978,"about_ca_system_score_gemma":0.000051611747,"threshold_uncertainty_score":0.22469822},"labels":[],"label_agreement":null},{"id":"W4403017633","doi":"10.2196/58085","title":"Addressing Information Biases Within Electronic Health Record Data to Improve the Examination of Epidemiologic Associations With Diabetes Prevalence Among Young Adults: Cross-Sectional Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Behavioral Risk Factor Surveillance System; Medicine; Environmental health; Public health; National Health and Nutrition Examination Survey; Odds ratio; Population; Missing data; Public health surveillance; Causal inference; Information bias; Health equity; Odds; Ethnic group; Gerontology; Demography; Logistic regression; Statistics; Selection bias","score_opus":0.17580675024240525,"score_gpt":0.45769225470288116,"score_spread":0.2818855044604759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403017633","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":[0.94647,0.000056167082,0.049889706,0.00020434064,0.00016920088,0.0023585653,0.0002618497,0.00044931413,0.00014083598],"genre_scores_gemma":[0.9870674,0.00004406088,0.011625978,0.00036686924,0.00007596292,0.00050387153,0.00027234366,0.00001793655,0.000025594361],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958611,0.00030496297,0.00194603,0.00020368319,0.0012234938,0.00046069818],"domain_scores_gemma":[0.9945565,0.0031289868,0.0010753355,0.0007257428,0.00033153433,0.00018190892],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073519694,0.00023583326,0.00039581602,0.00022131354,0.00024689577,0.00020597993,0.0008104953,0.00017933965,0.000042131975],"category_scores_gemma":[0.0125196455,0.00014725041,0.000045124456,0.00067239825,0.00023640698,0.0028076537,0.00034623966,0.0007904204,0.000009896299],"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":[0.00013140608,0.000947181,0.7569284,0.008693838,0.00057677494,0.0000037714137,0.09359954,0.0004239676,0.000022156344,0.03192013,0.005291296,0.10146153],"study_design_scores_gemma":[0.0010155737,0.003755387,0.70024693,0.0045213336,0.00011954282,0.000016792377,0.015290202,0.259277,0.00016884097,0.014570042,0.00028303955,0.00073530746],"about_ca_topic_score_codex":0.00009176364,"about_ca_topic_score_gemma":0.00036478302,"teacher_disagreement_score":0.25885302,"about_ca_system_score_codex":0.00053875794,"about_ca_system_score_gemma":0.00061828597,"threshold_uncertainty_score":0.99579835},"labels":[],"label_agreement":null},{"id":"W4403177596","doi":"10.7326/m23-2907","title":"School Mask Mandates and COVID-19: The Challenge of Using Difference-in-Differences Analysis of Observational Data to Estimate the Effectiveness of a Public Health Intervention","year":2024,"lang":"en","type":"article","venue":"Annals of Internal Medicine","topic":"Advanced Causal Inference Techniques","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 Toronto","funders":"Klinisk Institut, Syddansk Universitet; Rotman School of Management, University of Toronto; Sloan School of Management, Massachusetts Institute of Technology; University of Toronto Scarborough; Syddansk Universitet; St. George's, University of London; University of California, San Francisco; University of Toronto; Massachusetts Institute of Technology","keywords":"Medicine; Observational study; Coronavirus disease 2019 (COVID-19); Public health; 2019-20 coronavirus outbreak; Intervention (counseling); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Family medicine; Nursing; Virology; Internal medicine; Disease","score_opus":0.5969371067729305,"score_gpt":0.578315589099546,"score_spread":0.018621517673384602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403177596","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":[0.7984356,0.0022811894,0.19149584,0.0071868943,0.000044415297,0.00037103015,0.00012606365,0.000017715922,0.00004121524],"genre_scores_gemma":[0.9975084,0.00043498815,0.0018394778,0.00014275935,0.00001770331,0.000017429587,0.00002274432,0.000008395249,0.00000806735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978001,0.00052063016,0.0009000263,0.00023835151,0.00038981126,0.0001510861],"domain_scores_gemma":[0.994808,0.0038469997,0.0005109121,0.00049053796,0.0002466122,0.00009694487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055023315,0.00013904707,0.00071427913,0.00047086805,0.000024193025,0.000010606221,0.00059629657,0.000038642964,0.000070199945],"category_scores_gemma":[0.0065205023,0.00007274626,0.00008012961,0.00071075174,0.00035897948,0.00015361317,0.0003005195,0.00016167309,8.5522124e-8],"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":[0.001044821,0.0009954885,0.39451444,0.020767786,0.005730746,0.000018863027,0.0112087885,0.00036165994,0.017829062,0.50913227,0.0005557633,0.037840314],"study_design_scores_gemma":[0.00067365676,0.0020477546,0.4211612,0.018781625,0.00065209536,0.00001085311,0.0025147747,0.06777883,0.006192265,0.47990426,0.00005528861,0.00022739722],"about_ca_topic_score_codex":0.0014958158,"about_ca_topic_score_gemma":0.00047188232,"teacher_disagreement_score":0.1990728,"about_ca_system_score_codex":0.000034942826,"about_ca_system_score_gemma":0.000118971875,"threshold_uncertainty_score":0.7806122},"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":"W4403274525","doi":"10.1093/infdis/jiae493","title":"SMART Designs: Bridging the Gap Between Clinical Trials and Practice in Infectious Diseases","year":2024,"lang":"en","type":"article","venue":"The Journal of Infectious Diseases","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Bridging (networking); Psychological intervention; Randomized controlled trial; Flexibility (engineering); Clinical trial; Personalized medicine; Medicine; Clinical Practice; Computer science; Intensive care medicine; Bioinformatics; Family medicine; Nursing; Biology","score_opus":0.31563343946283245,"score_gpt":0.5225529930281148,"score_spread":0.2069195535652823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403274525","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":[0.8299152,0.030401826,0.1286933,0.0048076576,0.0013256362,0.001987026,0.00012324117,0.00089256844,0.0018535263],"genre_scores_gemma":[0.99323624,0.0049028397,0.000297092,0.0003514702,0.0011142654,0.000025756834,0.0000014742957,0.00004888636,0.000021980575],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922399,0.005158513,0.0016661981,0.00019790269,0.00043647664,0.00030101466],"domain_scores_gemma":[0.9228534,0.07528921,0.0010199348,0.00037245307,0.00025785863,0.00020710536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0120640965,0.00027531845,0.0008727894,0.00025835275,0.00021309972,0.00026041077,0.0003051156,0.000104358594,0.00003445995],"category_scores_gemma":[0.06852488,0.00014608723,0.00034989713,0.00044820656,0.00035743948,0.00080839795,0.00013624036,0.00087133254,0.000008151643],"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":[0.002116162,0.0031343387,0.4747588,0.0013745574,0.004773196,0.0011401894,0.0053725014,0.0004515228,0.0009869382,0.05389016,0.056318633,0.395683],"study_design_scores_gemma":[0.0016052873,0.0013094341,0.032430675,0.0014965187,0.0050049582,0.0015663747,0.00090439914,0.00024079354,0.0001886714,0.9515188,0.0032349962,0.0004990978],"about_ca_topic_score_codex":0.000042350086,"about_ca_topic_score_gemma":0.00002300678,"teacher_disagreement_score":0.8976286,"about_ca_system_score_codex":0.00014168091,"about_ca_system_score_gemma":0.00030254532,"threshold_uncertainty_score":0.93932134},"labels":[],"label_agreement":null},{"id":"W4403324648","doi":"10.2139/ssrn.4984628","title":"Are Causal Effect Estimations Enough for Optimal Recommendations Under Multitreatment Scenarios?","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"Western University","funders":"","keywords":"Econometrics; Economics; Computer science","score_opus":0.13319135079358244,"score_gpt":0.44017721545306965,"score_spread":0.3069858646594872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403324648","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":[0.015865838,0.0022834367,0.97031355,0.0066556884,0.0009690649,0.0024760058,0.0002652501,0.00082237046,0.00034880592],"genre_scores_gemma":[0.5975421,0.0031573463,0.38986957,0.00015033955,0.0012143103,0.0022989742,0.00036886078,0.00044020265,0.0049582957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957431,0.00020222567,0.000810936,0.0006272296,0.00035137485,0.0022651423],"domain_scores_gemma":[0.9968728,0.0011360499,0.00092798116,0.00060059596,0.00031448333,0.00014813563],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001945165,0.00067464035,0.0007754497,0.0003642929,0.00044249467,0.0002811019,0.00050987554,0.0004796072,0.00006327983],"category_scores_gemma":[0.00086988567,0.0005807629,0.00053875154,0.00016862982,0.00007767462,0.00016146983,0.00048936956,0.005773859,0.00004570755],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103684906,0.0004452483,0.000037115,0.0005703825,0.0021691693,0.000019620242,0.00038198166,0.006162618,0.00014260976,0.9640355,0.005438201,0.020493874],"study_design_scores_gemma":[0.00058117585,0.00058324204,0.0000063400203,0.0008435864,0.00083706714,0.00029200298,0.0005044743,0.005009431,0.0006048464,0.9895196,0.0006896849,0.0005285418],"about_ca_topic_score_codex":0.00004614535,"about_ca_topic_score_gemma":0.00097634614,"teacher_disagreement_score":0.58167624,"about_ca_system_score_codex":0.0055287094,"about_ca_system_score_gemma":0.0026842565,"threshold_uncertainty_score":0.99966437},"labels":[],"label_agreement":null},{"id":"W4403423632","doi":"10.1007/978-3-031-67604-8_5","title":"The Application of Randomized and Quasi-Experimental Designs in Federal Government Program Evaluation","year":2024,"lang":"en","type":"book-chapter","venue":"Contributions to economics","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":"Employment and Social Development Canada","funders":"","keywords":"Government (linguistics); Computer science; Political science","score_opus":0.0852557673877345,"score_gpt":0.4114723712296289,"score_spread":0.3262166038418944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403423632","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":[0.012011989,0.014562069,0.5529897,0.0042678607,0.0008750069,0.097366534,0.0030903956,0.0010878281,0.3137486],"genre_scores_gemma":[0.88273257,0.0028628085,0.04240428,0.00013005834,0.00034104747,0.03255046,0.00036974146,0.00025978492,0.038349234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985919,0.000050128554,0.0007659481,0.00028720897,0.00014303192,0.0001618028],"domain_scores_gemma":[0.9982228,0.0008973897,0.0003580473,0.00032584777,0.00014390652,0.000051983705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017067356,0.0002200287,0.00062630797,0.00006166506,0.00008845075,0.00007674358,0.0001329313,0.00018420149,0.000014983928],"category_scores_gemma":[0.00045591086,0.00018524319,0.00013155522,0.000018668474,0.00017114118,0.000064037646,0.000109131004,0.00019224604,0.000012119951],"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":[0.00057107076,0.00006883438,0.0000011850051,0.00001697145,0.00007451167,2.1742818e-7,0.00006987417,0.000016181599,0.000053333686,0.9837554,0.00009685512,0.015275556],"study_design_scores_gemma":[0.0053291214,0.00016695425,9.2288724e-7,0.00010487687,0.00011609166,0.0000030308338,0.000045544155,0.009368498,0.0015991839,0.9691241,0.013938086,0.00020359269],"about_ca_topic_score_codex":0.000009361931,"about_ca_topic_score_gemma":0.00014686577,"teacher_disagreement_score":0.8707206,"about_ca_system_score_codex":0.0013641653,"about_ca_system_score_gemma":0.00010098059,"threshold_uncertainty_score":0.75539976},"labels":[],"label_agreement":null},{"id":"W4403431962","doi":"10.1093/ije/dyae137","title":"Staggered interventions with no control groups","year":2024,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Canada Research Chairs; University of Toronto","funders":"Banting Research Foundation","keywords":"Psychological intervention; Medicine; Control (management); Psychology; Environmental health; Family medicine; Computer science; Nursing; Artificial intelligence","score_opus":0.24966978745009702,"score_gpt":0.5112616415463053,"score_spread":0.2615918540962082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403431962","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":[0.011904302,0.00090977066,0.9787156,0.0047686514,0.0014175634,0.00010826958,0.000033713903,0.00011264004,0.0020294779],"genre_scores_gemma":[0.8675343,0.00019248803,0.13031676,0.0006942974,0.0007400295,0.000013533546,0.000005943785,0.000026435013,0.00047624938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981615,0.00030239485,0.0010065256,0.00014471098,0.00020027855,0.0001845799],"domain_scores_gemma":[0.9932615,0.005249398,0.0005241297,0.00012955023,0.0007574879,0.00007793771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022187703,0.00013005358,0.00043175413,0.00028265608,0.000018190858,0.000022742453,0.00041495747,0.000084721454,0.0004988139],"category_scores_gemma":[0.0070215366,0.00008745921,0.00028710143,0.00007024652,0.00013425677,0.0003014105,0.000040921972,0.00041826608,0.00004134674],"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":[0.00029718457,0.00012710752,0.0022792625,0.000076538585,0.0009843402,0.00040895853,0.000089558154,0.000073788375,0.0006947927,0.9594789,0.026092,0.009397549],"study_design_scores_gemma":[0.0005554322,0.00068169215,0.0005064454,0.0011779665,0.000091411064,0.0011248761,0.000037492555,0.0007240159,0.00015680442,0.9719375,0.02287432,0.00013206732],"about_ca_topic_score_codex":0.0000065149825,"about_ca_topic_score_gemma":0.000010396918,"teacher_disagreement_score":0.85563,"about_ca_system_score_codex":0.0001536242,"about_ca_system_score_gemma":0.00007699414,"threshold_uncertainty_score":0.84059423},"labels":[],"label_agreement":null},{"id":"W4403567836","doi":"10.1007/s12561-024-09461-6","title":"Benefits of Repeated Matched-Cohort and Nested Case–Control Analyses with Time-dependent Exposure in Observational Studies","year":2024,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"BC Centre for Disease Control; St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Observational study; Biostatistics; Cohort study; Econometrics; Medicine; Statistics; Epidemiology; Internal medicine; Mathematics","score_opus":0.24423021167723682,"score_gpt":0.45873918055149415,"score_spread":0.21450896887425733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403567836","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":[0.9725698,0.0014065572,0.024798598,0.00011980423,0.000054851982,0.0004063577,0.00044721682,0.00010154525,0.00009527263],"genre_scores_gemma":[0.8856024,0.00020037127,0.11404717,0.000015870113,0.000008278239,0.00003844966,0.0000054576853,0.000009792225,0.00007216392],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985832,0.00007988686,0.00047399814,0.00032856056,0.00034884815,0.00018548027],"domain_scores_gemma":[0.99771637,0.0017947151,0.00012909567,0.00015112844,0.00017705209,0.000031630396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008222665,0.00015191404,0.00036144556,0.00027024004,0.0000439122,0.00004363909,0.00011296719,0.00005080055,0.000016407585],"category_scores_gemma":[0.0010695928,0.00010920611,0.000011897992,0.0006871636,0.00037431705,0.00021481531,0.00004580085,0.00012393681,7.739129e-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":[0.00010923398,0.00030738176,0.5056711,0.0012119192,0.00031885545,0.002243339,0.0063174493,0.0027538158,0.009129347,0.460805,0.00035135695,0.010781194],"study_design_scores_gemma":[0.0007983644,0.0009932114,0.21893974,0.0017890712,0.00027338037,0.00051678374,0.005142753,0.02117609,0.00921748,0.7404048,0.000008275336,0.0007400637],"about_ca_topic_score_codex":0.00010692405,"about_ca_topic_score_gemma":0.0015228419,"teacher_disagreement_score":0.28673136,"about_ca_system_score_codex":0.000060781116,"about_ca_system_score_gemma":0.000083741885,"threshold_uncertainty_score":0.44532958},"labels":[],"label_agreement":null},{"id":"W4403707130","doi":"10.48550/arxiv.2409.11269","title":"Testing for racial bias using inconsistent perceptions of race","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Canadian Institute for Advanced Research; Colorado State University; National Science Foundation","keywords":"Race (biology); Racial bias; Perception; Psychology; Social psychology; Sociology; Gender studies","score_opus":0.5281622615802808,"score_gpt":0.34887634735150397,"score_spread":0.17928591422877682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403707130","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":[0.6576836,0.000025926262,0.33973053,0.000015295765,0.0001759481,0.0006185821,0.00011127778,0.00036862816,0.0012701947],"genre_scores_gemma":[0.8803261,0.000010872836,0.11893217,0.000009519062,0.00008734284,0.0000038017386,0.000010768028,0.000049942348,0.0005694685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986525,0.00007476949,0.00035484432,0.0005907147,0.0000727177,0.00025442694],"domain_scores_gemma":[0.9975729,0.00093929016,0.000415164,0.0005879187,0.0004079816,0.00007673461],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033787984,0.00029215138,0.0004955495,0.00030874857,0.000111387155,0.000030305106,0.00036667363,0.0003170035,0.000033218625],"category_scores_gemma":[0.0010223577,0.00033538858,0.0003020124,0.00037928435,0.00017928152,0.000090338675,0.0011204403,0.0005311876,0.00000786288],"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":[0.00013343414,0.00035799554,0.0041746227,0.0044265413,0.0004411752,0.0001413826,0.0016310238,0.05115248,0.016120024,0.91921365,0.00057677133,0.0016309142],"study_design_scores_gemma":[0.00016117288,0.00007118573,0.00008287756,0.0008479179,0.00050876796,0.0000053281497,0.00046562732,0.08767574,0.0011029828,0.9086911,0.000037036352,0.0003502432],"about_ca_topic_score_codex":0.00007702707,"about_ca_topic_score_gemma":0.000048670747,"teacher_disagreement_score":0.22264248,"about_ca_system_score_codex":0.00036018682,"about_ca_system_score_gemma":0.00027577856,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W4404021068","doi":"10.1097/ede.0000000000001808","title":"A Structural Description of Biases That Generate Immortal Time","year":2024,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":75,"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; Jewish General Hospital","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Medical Research Council; National Institute for Health and Care Research","keywords":"Selection (genetic algorithm); Computer science; Emulation; Selection bias; Term (time); Observational study; Statistics; Artificial intelligence; Psychology; Mathematics; Social psychology","score_opus":0.5136780440079687,"score_gpt":0.47685382740507143,"score_spread":0.03682421660289725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404021068","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":[0.94118965,0.0013837353,0.055032674,0.0004130242,0.0003059657,0.00018400387,0.00003275332,0.0005506527,0.00090754865],"genre_scores_gemma":[0.9264474,0.00005069304,0.07251082,0.00014281367,0.00012840227,0.000023117414,0.000025775445,0.000023015406,0.0006479583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987405,0.0002945926,0.0004240525,0.00023699917,0.000058602807,0.00024527273],"domain_scores_gemma":[0.9963788,0.0031709464,0.00013411429,0.00023615838,0.000037853166,0.000042120977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082042936,0.00014124002,0.00044140793,0.00010195372,0.000025673799,0.0000056820695,0.000119739634,0.0001348193,0.00041885657],"category_scores_gemma":[0.0034097293,0.00010770386,0.000101659,0.00010318097,0.00014925427,0.00015648025,0.0000552693,0.00016808345,0.000041147665],"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":[0.000049282888,0.000032906868,0.008411828,0.0003296949,0.00019766092,0.00006147545,0.00047983084,0.00028471363,0.10569282,0.81889075,0.048709467,0.016859565],"study_design_scores_gemma":[0.00004875512,0.00011152622,0.0012565588,0.000108271444,0.00003365823,0.00006222118,0.00001707071,0.029577108,0.012191935,0.956092,0.00035804926,0.00014286622],"about_ca_topic_score_codex":0.00003866108,"about_ca_topic_score_gemma":0.000011062911,"teacher_disagreement_score":0.13720122,"about_ca_system_score_codex":0.00004666184,"about_ca_system_score_gemma":0.000024265746,"threshold_uncertainty_score":0.45861855},"labels":[],"label_agreement":null},{"id":"W4404420616","doi":"10.1016/j.neuchi.2024.101610","title":"Lies, damned lies, and statistical populations","year":2024,"lang":"en","type":"editorial","venue":"Neurochirurgie","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":"University of Alberta Hospital; Health Sciences Centre; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine","score_opus":0.13536886320562494,"score_gpt":0.43699602258912074,"score_spread":0.3016271593834958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404420616","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":[0.00009461568,0.0009138159,0.037006814,0.00023490418,0.94768065,0.0008328456,0.0026635327,0.0026311534,0.007941677],"genre_scores_gemma":[0.00066856516,0.001276733,0.1440314,0.000121228884,0.8427699,0.00028942377,0.0016819998,0.00055985025,0.008600864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736536,0.00010084909,0.00060640695,0.0007548107,0.0007363414,0.00043625728],"domain_scores_gemma":[0.99534726,0.0034549509,0.00019557247,0.00066903565,0.00015550038,0.00017769882],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021369284,0.0005350963,0.00067681755,0.00021272956,0.0001314603,0.00022025821,0.0003205453,0.0007469289,0.00013043302],"category_scores_gemma":[0.0060018064,0.00050604925,0.000084372616,0.0001946916,0.00018384472,0.00014578328,0.00038014541,0.0017430907,0.000084556756],"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":[0.000017119957,0.000032519525,0.0000013895133,0.00037147116,0.000020448819,0.00009355425,0.000042256044,2.6002468e-7,0.000025454861,0.17965572,0.81871766,0.0010221299],"study_design_scores_gemma":[0.00008299572,0.00009058895,0.000006475604,0.00016780685,0.00012247797,0.0000053887375,0.0000062782183,0.000036790752,0.000017040678,0.4445937,0.55459046,0.0002799823],"about_ca_topic_score_codex":0.00004645357,"about_ca_topic_score_gemma":0.00010048471,"teacher_disagreement_score":0.26493797,"about_ca_system_score_codex":0.00010855519,"about_ca_system_score_gemma":0.0002671908,"threshold_uncertainty_score":0.9997391},"labels":[],"label_agreement":null},{"id":"W4404546549","doi":"10.30683/1929-2279.2024.13.08","title":"Scientific Tasks in Biomedical and Oncological Research: Describing, Predicting, and Explaining","year":2024,"lang":"en","type":"article","venue":"Journal of cancer research updates","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Scientific evidence; Computer science; Sociology of scientific knowledge; Scientific literature; Data science; Descriptive statistics; Management science; Artificial intelligence; Epistemology; Mathematics","score_opus":0.6179883343554925,"score_gpt":0.596347538729944,"score_spread":0.021640795625548548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404546549","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":[0.9860716,0.009823701,0.0006642968,0.0025456178,0.00018385409,0.00026429057,0.0000112536545,0.00005658312,0.0003788289],"genre_scores_gemma":[0.9873309,0.0027712018,0.009386717,0.000013098616,0.00026492195,0.00004391941,0.000001106654,0.000023662713,0.00016444494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963094,0.000604898,0.0005631102,0.0003297731,0.0015481745,0.0006446433],"domain_scores_gemma":[0.99525577,0.0035201965,0.000088477515,0.0001653666,0.00067118846,0.0002989747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01685551,0.000119502176,0.00030776786,0.0014870818,0.00026496235,0.0006042606,0.00032752904,0.00014547039,0.00013792381],"category_scores_gemma":[0.0065083043,0.00008493155,0.000035219302,0.0011323664,0.0016986593,0.00061501266,0.00042063653,0.0022229096,0.000002455462],"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":[0.0009254191,0.00086114806,0.05518807,0.0021155032,0.00031520688,0.005197347,0.020471927,0.000008937589,0.17379674,0.19255002,0.18400188,0.36456782],"study_design_scores_gemma":[0.0008868105,0.0022410008,0.0016147004,0.007196934,0.000026709853,0.0004139471,0.005317439,0.0021285228,0.017964073,0.89720404,0.06470889,0.00029694306],"about_ca_topic_score_codex":0.000079545134,"about_ca_topic_score_gemma":0.00017556819,"teacher_disagreement_score":0.70465404,"about_ca_system_score_codex":0.00038475657,"about_ca_system_score_gemma":0.00061024894,"threshold_uncertainty_score":0.96575594},"labels":[],"label_agreement":null},{"id":"W4404567028","doi":"10.1002/sim.10223","title":"Q‐Learning in Dynamic Treatment Regimes With Misclassified Binary Outcome","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Outcome (game theory); Artificial intelligence; Machine learning; Population; Binary classification; Statistics; Data mining; Medicine; Mathematics; Support vector machine","score_opus":0.10451381065403711,"score_gpt":0.4508819754438676,"score_spread":0.34636816478983046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404567028","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":[0.11825331,0.0014246675,0.8587128,0.0028713902,0.00044118412,0.0014050502,0.00012771608,0.0013574554,0.015406415],"genre_scores_gemma":[0.6555179,0.00041914047,0.3365663,0.00005416134,0.000046715453,0.000118594784,0.00007732459,0.000069613714,0.0071302718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868125,0.00007958304,0.00044843473,0.00028759762,0.00023879902,0.00026432425],"domain_scores_gemma":[0.99832994,0.001287333,0.00007161556,0.00022522912,0.000032790555,0.000053101146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036730047,0.00021390333,0.00042519285,0.00033795286,0.000024847659,0.000012142552,0.00009676059,0.00006867601,0.0001240324],"category_scores_gemma":[0.0007293827,0.0001420209,0.000013301396,0.0003597539,0.00017962998,0.000057675723,0.000024225248,0.00039618174,0.00000971309],"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":[0.00016605582,0.0002747477,0.017039536,0.0011116602,0.00009213573,0.005905994,0.007789266,0.00022428333,0.0015299309,0.90280765,0.0032782506,0.059780482],"study_design_scores_gemma":[0.0019892964,0.004057587,0.0057800747,0.0034452642,0.00012770353,0.000068142384,0.0030902636,0.046401065,0.00020262582,0.9309851,0.0033121957,0.00054067734],"about_ca_topic_score_codex":0.000082803876,"about_ca_topic_score_gemma":0.0004603318,"teacher_disagreement_score":0.5372646,"about_ca_system_score_codex":0.0004537818,"about_ca_system_score_gemma":0.00007116841,"threshold_uncertainty_score":0.5791444},"labels":[],"label_agreement":null},{"id":"W4404583154","doi":"10.3138/jmvfh-2024-0016","title":"Comments on Gray and Bourke ‘Remediation of intrusive symptoms of PTSD in fewer than five sessions: A 30-person pre-pilot study of the RTM Protocol’","year":2024,"lang":"en","type":"article","venue":"Journal of Military Veteran and Family Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Gray (unit); Protocol (science); Psychology; Clinical psychology; Psychiatry; Medicine; Alternative medicine; Nuclear medicine; Pathology","score_opus":0.11721478040038104,"score_gpt":0.4286900091009749,"score_spread":0.31147522870059385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404583154","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":[0.98923665,0.0007075113,0.00016162642,0.00020820215,0.000078777906,0.009541259,0.00002826611,0.000009050378,0.00002865347],"genre_scores_gemma":[0.9978241,0.00026618026,0.0012923614,0.00015178327,0.00002678902,0.00041781404,6.487863e-7,0.000013837059,0.0000064928586],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99807084,0.0003952897,0.0008870473,0.00013886999,0.00036499812,0.00014297846],"domain_scores_gemma":[0.99858004,0.00051242125,0.00050628756,0.00019251418,0.00013312206,0.00007563902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010244086,0.0001454936,0.00050304417,0.0002260926,0.000044029115,0.000003823658,0.00013779372,0.000044145243,0.0000036996564],"category_scores_gemma":[0.0001946439,0.00009018846,0.000048945727,0.00017320532,0.00009180308,0.00015688542,0.00004794523,0.00036536483,6.62923e-8],"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":[0.013351682,0.022567518,0.23518084,0.024892857,0.0012368776,0.000110637564,0.5305717,0.00019507324,0.03264308,0.0052370015,0.007935259,0.12607749],"study_design_scores_gemma":[0.008513534,0.098751396,0.7682575,0.020844478,0.00013556927,0.000056922407,0.05255359,0.0013498535,0.0016605208,0.047331564,0.00012517809,0.00041991365],"about_ca_topic_score_codex":0.0004831835,"about_ca_topic_score_gemma":0.00015380925,"teacher_disagreement_score":0.53307664,"about_ca_system_score_codex":0.00010154962,"about_ca_system_score_gemma":0.00014258658,"threshold_uncertainty_score":0.36777788},"labels":[],"label_agreement":null},{"id":"W4404589755","doi":"10.52294/001c.124817","title":"Through the lens of causal inference: Decisions and pitfalls of covariate selection","year":2024,"lang":"en","type":"article","venue":"Aperture Neuro","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":"McGill University","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Causal inference; Covariate; Selection (genetic algorithm); Inference; Lens (geology); Computer science; Econometrics; Psychology; Artificial intelligence; Machine learning; Mathematics; Optics; Physics","score_opus":0.16093200396003512,"score_gpt":0.4150338968016802,"score_spread":0.2541018928416451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404589755","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":[0.0996208,0.0013863202,0.8691354,0.017255312,0.00060626696,0.0013175788,0.00012049398,0.0010052319,0.009552646],"genre_scores_gemma":[0.98130095,0.0005258973,0.0165339,0.0014276836,0.0000390049,0.000017739787,0.0000022200916,0.00002711559,0.00012546066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991182,0.000067855704,0.00028747867,0.00018992288,0.00019402463,0.00014251238],"domain_scores_gemma":[0.98175806,0.017799955,0.00008712606,0.00022729991,0.000104991144,0.000022540878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00016047602,0.00013075484,0.00021201473,0.000049539667,0.000048280424,0.000021338392,0.00013640866,0.00009515848,0.000038953873],"category_scores_gemma":[0.012175684,0.00008104718,0.000050290386,0.00029342336,0.00012944825,0.00019609794,0.000079969,0.00027610591,0.0000026976093],"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":[0.000018233095,0.000050485578,0.00007688139,0.00010855606,0.00004264695,0.0000053248064,0.0011956947,0.000009679026,0.07145906,0.9096624,0.014884789,0.0024861952],"study_design_scores_gemma":[0.00011719786,0.00030003113,0.00029940507,0.00027553938,0.00009052809,0.000042751642,0.00006458995,0.0012828811,0.02379967,0.9203694,0.053201918,0.00015611347],"about_ca_topic_score_codex":0.000034132834,"about_ca_topic_score_gemma":0.00003063662,"teacher_disagreement_score":0.8816802,"about_ca_system_score_codex":0.000012766201,"about_ca_system_score_gemma":0.00007025188,"threshold_uncertainty_score":0.9961452},"labels":[],"label_agreement":null},{"id":"W4404681647","doi":"10.1093/aje/kwae437","title":"Modern sources of controls in case-control studies","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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":"McGill University; McGill University Health Centre; Public Health Ontario; University of Toronto","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institute on Aging","keywords":"Medicine; Control (management); Computer science; Artificial intelligence","score_opus":0.1981083945195597,"score_gpt":0.48364762285779234,"score_spread":0.28553922833823264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404681647","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":[0.66350186,0.015246684,0.31874153,0.0020429008,0.00014100202,0.0001492159,0.000011876246,0.000051408108,0.000113542264],"genre_scores_gemma":[0.9386282,0.0007071578,0.060162604,0.00035734964,0.00009900779,0.000009673411,1.020317e-7,0.00001909372,0.00001682419],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968903,0.0010780088,0.0014790945,0.00016014476,0.00009053161,0.00030192218],"domain_scores_gemma":[0.97175515,0.026760904,0.0010391737,0.00018250734,0.00019323452,0.00006903464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004670148,0.00016209326,0.0016523382,0.0003194636,0.000016646489,0.0000030232266,0.00017939972,0.000058841706,0.000015156379],"category_scores_gemma":[0.015952744,0.00011283568,0.0001993755,0.0002168715,0.0007139679,0.00012895839,0.00003298222,0.00043677332,0.0000012712775],"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":[0.000930156,0.00033578326,0.082008466,0.00060561416,0.003632176,0.011143139,0.009649518,0.0039335974,0.005726332,0.39839306,0.004325324,0.47931683],"study_design_scores_gemma":[0.00037617152,0.0014197981,0.00029813554,0.00039696306,0.00015123769,0.004507015,0.0019155155,0.0026327006,0.00021876417,0.9876833,0.0002658139,0.0001345657],"about_ca_topic_score_codex":0.00005739421,"about_ca_topic_score_gemma":0.000041617208,"teacher_disagreement_score":0.58929026,"about_ca_system_score_codex":0.000093662115,"about_ca_system_score_gemma":0.00006813208,"threshold_uncertainty_score":0.99233633},"labels":[],"label_agreement":null},{"id":"W4404709178","doi":"10.1056/evide2400384","title":"Truncated, Not Forgotten — Handling Left Truncation in Time-to-Event Studies","year":2024,"lang":"en","type":"letter","venue":"NEJM Evidence","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":"Health Sciences North","funders":"","keywords":"Truncation (statistics); Event (particle physics); Computer science; Mathematics; Statistics; Physics","score_opus":0.3079535159591048,"score_gpt":0.4714579623514579,"score_spread":0.16350444639235312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404709178","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":[0.0054652514,0.0048933425,0.012721341,0.9693579,0.00095755217,0.0035056907,0.00006267721,0.00221729,0.00081894296],"genre_scores_gemma":[0.015609784,0.00256085,0.08258437,0.80148315,0.004806827,0.0021354628,0.0001506164,0.00082205,0.089846894],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996315,0.00018020895,0.0009838296,0.00095830497,0.0009193164,0.00064333377],"domain_scores_gemma":[0.9954882,0.002856978,0.00033194397,0.00093265413,0.00030387955,0.000086337364],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011645939,0.0006196146,0.00097548915,0.0005742398,0.00007662851,0.00015085268,0.0007230474,0.0006720886,0.00021469282],"category_scores_gemma":[0.006082332,0.00055585813,0.00018400219,0.00046224266,0.00010444344,0.00045602655,0.00047735093,0.0020006173,0.001638992],"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":[0.000019337738,0.00002036861,0.000035159323,0.0016207466,0.00008148254,0.00030796847,0.0012248093,0.000018220173,0.0011104485,0.00029044843,0.993195,0.002075999],"study_design_scores_gemma":[0.00028309535,0.0004717606,0.00007997548,0.03897324,0.00050124514,0.00009279505,0.00015630916,0.00063026504,0.013234261,0.43533447,0.5081119,0.0021306993],"about_ca_topic_score_codex":0.000026935635,"about_ca_topic_score_gemma":0.000043672342,"teacher_disagreement_score":0.4850831,"about_ca_system_score_codex":0.0009119599,"about_ca_system_score_gemma":0.0002043069,"threshold_uncertainty_score":0.9996893},"labels":[],"label_agreement":null},{"id":"W4404725899","doi":"10.1186/s12874-024-02402-3","title":"Non-collapsibility and built-in selection bias of period-specific and conventional hazard ratio in randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Queen's University; McGill University; McGill University Health Centre","funders":"","keywords":"Hazard ratio; Marginal structural model; Statistics; Weighting; Proportional hazards model; Inverse probability weighting; Hazard; Covariate; Econometrics; Confounding; Mathematics; Confidence interval; Medicine; Chemistry; Propensity score matching","score_opus":0.7400147912349078,"score_gpt":0.6258450755790635,"score_spread":0.11416971565584422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404725899","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":[0.38905182,0.002948902,0.603291,0.00096594065,0.00014298299,0.0032577566,0.0000049141067,0.00005574668,0.00028098744],"genre_scores_gemma":[0.69581205,0.0029710033,0.29939938,0.00001772974,0.00012801403,0.0013610113,0.000004860211,0.000023593848,0.0002823956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9382921,0.056660175,0.0026691474,0.00064024696,0.0012358791,0.0005024934],"domain_scores_gemma":[0.6409687,0.35809532,0.0002255114,0.00021755823,0.00030746462,0.00018549299],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27228534,0.00016657806,0.003640863,0.0008719248,0.000042273397,0.00004165006,0.00015711613,0.00038937406,0.00078077684],"category_scores_gemma":[0.5429326,0.000111480804,0.00023126895,0.0005753588,0.0013677052,0.00009526097,0.00015537096,0.00088409486,0.0000020523162],"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":[0.13681266,0.00032171188,0.0032834725,0.0019777897,0.00023965834,0.00008799338,0.0015282487,0.0000039610895,0.022393985,0.8142864,0.00095777685,0.01810634],"study_design_scores_gemma":[0.090781696,0.0002509209,0.00087927637,0.00062469096,0.00003664382,0.000038805196,0.00036190718,0.020112813,0.0040358156,0.88264525,0.00010783803,0.0001243339],"about_ca_topic_score_codex":0.00011532081,"about_ca_topic_score_gemma":0.0013606062,"teacher_disagreement_score":0.3067602,"about_ca_system_score_codex":0.00011825537,"about_ca_system_score_gemma":0.0010484717,"threshold_uncertainty_score":0.8548959},"labels":[],"label_agreement":null},{"id":"W4404837160","doi":"10.1002/sim.10278","title":"Dynamic Treatment Regimes on Dyadic Networks","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"University of Waterloo","funders":"","keywords":"Dyad; Computer science; Context (archaeology); Outcome (game theory); Population; Path (computing); Mathematical optimization; Econometrics; Machine learning; Mathematics; Medicine; Psychology","score_opus":0.07713181625879532,"score_gpt":0.45058179005342597,"score_spread":0.37344997379463063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404837160","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":[0.0012373207,0.001198644,0.9860435,0.00079553045,0.0004970385,0.00037596718,0.00005812386,0.00045613266,0.009337742],"genre_scores_gemma":[0.5945712,0.0033460527,0.39290053,0.0003584393,0.00030729867,0.00018167312,0.00015023729,0.00011905526,0.00806555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988629,0.000052051564,0.00034139096,0.00026944166,0.00021908488,0.00025509336],"domain_scores_gemma":[0.997594,0.0019422699,0.00005054583,0.00031736062,0.00003103291,0.00006480814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028707916,0.00020205531,0.00032753826,0.00019752639,0.000028699618,0.000012493921,0.00010678699,0.00007798416,0.00024772336],"category_scores_gemma":[0.00061285705,0.00014247009,0.00001939527,0.00023823121,0.00016552559,0.00003502419,0.00001843615,0.00026417707,0.00002505573],"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":[0.000016999327,0.00005419229,0.000025506799,0.000088695044,0.000027895943,0.00043240312,0.00047854724,0.00007670243,0.000034555105,0.91909045,0.021040235,0.058633838],"study_design_scores_gemma":[0.00029501578,0.00095637684,0.00008102798,0.00095949986,0.000050937273,0.000014219496,0.000117345146,0.05002395,0.00005700452,0.94336635,0.003927683,0.00015059108],"about_ca_topic_score_codex":0.000033553533,"about_ca_topic_score_gemma":0.000072897834,"teacher_disagreement_score":0.59333384,"about_ca_system_score_codex":0.00039846404,"about_ca_system_score_gemma":0.000038745464,"threshold_uncertainty_score":0.5809762},"labels":[],"label_agreement":null},{"id":"W4404838868","doi":"10.1002/9781118445112.stat08040.pub2","title":"Dynamic Treatment Regimes (Updated)","year":2024,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","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":"","keywords":"Computer science","score_opus":0.12673538890750674,"score_gpt":0.4386927029725705,"score_spread":0.3119573140650638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404838868","genre_codex":"methods","genre_gemma":"other","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":[0.000017693525,0.0065582343,0.43581063,0.00027747336,0.0011025905,0.0023730807,0.13983452,0.007137476,0.4068883],"genre_scores_gemma":[0.000046421355,0.00756662,0.45019895,0.00004852564,0.00012758492,0.00011924117,0.0072331163,0.0013026219,0.5333569],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960251,0.00013879489,0.00096507696,0.0012835697,0.0007006355,0.000886817],"domain_scores_gemma":[0.9967895,0.00036570826,0.0007281818,0.0016082926,0.00020054777,0.00030773215],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.00015254048,0.0012918361,0.0014262234,0.0007259778,0.000066621746,0.00013428717,0.00064546574,0.0007564211,0.005623603],"category_scores_gemma":[0.00028568166,0.0010687385,0.00013919362,0.00041082033,0.00036026284,0.000084796826,0.00023758608,0.00089792156,0.0014627784],"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":[0.000020004909,0.00036869274,0.0000017505197,0.0004776073,0.0003222977,0.0002761146,0.00008711656,6.1263125e-7,0.00003104223,0.22944838,0.7485814,0.020384988],"study_design_scores_gemma":[0.00025575218,0.00042200962,0.0000010494824,0.0012407205,0.00035325112,0.000019820223,0.00007449521,0.00031776913,0.000027789383,0.44061634,0.5558914,0.00077959173],"about_ca_topic_score_codex":0.00037323468,"about_ca_topic_score_gemma":0.0033012659,"teacher_disagreement_score":0.21116795,"about_ca_system_score_codex":0.0007130996,"about_ca_system_score_gemma":0.00040388486,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W4405184953","doi":"10.1016/j.jclinepi.2024.111638","title":"Empirical estimation of disutilities and decision thresholds for composite endpoints","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University; Hamilton Health Sciences","funders":"","keywords":"Estimation; Composite number; Statistics; Econometrics; Mathematics; Computer science; Medicine; Economics; Algorithm","score_opus":0.6337335036538869,"score_gpt":0.6538808126028767,"score_spread":0.02014730894898975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405184953","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":[0.39654726,0.0005312996,0.60136855,0.0010767851,0.00028700888,0.000096686315,0.000008118799,0.000023477902,0.000060793333],"genre_scores_gemma":[0.53130454,0.0003443142,0.46799406,0.000187526,0.00014258228,0.0000031709253,0.0000010543483,0.000009819614,0.000012902323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954446,0.00058425614,0.003499807,0.00017331033,0.00012820655,0.00016984195],"domain_scores_gemma":[0.8740805,0.12448618,0.0010071134,0.00014733867,0.00017171456,0.0001071776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013972993,0.00011970623,0.0015410051,0.00011589817,0.000024263327,0.000007308649,0.00014825801,0.000272095,0.000020036707],"category_scores_gemma":[0.08090079,0.00007956557,0.000381912,0.000063991894,0.000330866,0.00017399494,0.000064005246,0.00046006445,0.0000011476446],"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":[0.0013790678,0.0003169936,0.05822246,0.00084206153,0.00026408312,0.000026122567,0.00027607544,0.00029239303,0.0002038214,0.4863577,0.020621916,0.43119732],"study_design_scores_gemma":[0.00029603293,0.0009225624,0.0087724775,0.0004835235,0.000072558796,0.00009564122,0.000021370071,0.019193767,0.00017388063,0.96909297,0.00081052835,0.0000646801],"about_ca_topic_score_codex":9.906237e-7,"about_ca_topic_score_gemma":0.0000017241334,"teacher_disagreement_score":0.48273528,"about_ca_system_score_codex":0.00002194784,"about_ca_system_score_gemma":0.00007629038,"threshold_uncertainty_score":0.9268412},"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":"W4405393380","doi":"10.1093/aje/kwae447","title":"Towards robust causal inference in epidemiologic research: employing double cross-fit TMLE in right heart catheterization data","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; British Columbia Centre for Disease Control; Michael Smith Health Research BC","keywords":"Observational study; Causal inference; Computer science; Inference; Epidemiology; Relevance (law); Data science; Machine learning; Data mining; Econometrics; Artificial intelligence; Medicine; Statistics; Mathematics; Pathology","score_opus":0.7041649067897078,"score_gpt":0.6040121800564162,"score_spread":0.10015272673329156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405393380","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":[0.6884654,0.0012867814,0.30306515,0.005625339,0.000416815,0.00043524476,0.000036752717,0.00015986936,0.0005086285],"genre_scores_gemma":[0.85213906,0.00078436,0.14636202,0.00039110234,0.00019808803,0.000028041986,0.000019274747,0.00004249638,0.00003557413],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99120843,0.0042716484,0.00250296,0.0006961042,0.00030041655,0.0010204137],"domain_scores_gemma":[0.9688177,0.028899021,0.0007984196,0.00095988,0.0003179799,0.00020700492],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03329469,0.00029892032,0.0016020826,0.0010474793,0.000077746794,0.00004352497,0.0011993648,0.00021986003,0.00012033619],"category_scores_gemma":[0.057315562,0.00023056442,0.00012445393,0.0014047871,0.0012140052,0.00085899147,0.0005498483,0.0020288634,0.000019161678],"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":[0.0007712043,0.000549853,0.62340003,0.00034662767,0.00016396288,0.0009738677,0.0019563697,0.015419869,0.0025277666,0.3143356,0.0074634445,0.03209139],"study_design_scores_gemma":[0.00053607847,0.0015758305,0.027648523,0.0011386799,0.00002527189,0.0003163925,0.00037122102,0.012491848,0.00032516525,0.9510942,0.0040167645,0.0004599951],"about_ca_topic_score_codex":0.0015661424,"about_ca_topic_score_gemma":0.00042788926,"teacher_disagreement_score":0.6367586,"about_ca_system_score_codex":0.0004993947,"about_ca_system_score_gemma":0.0004816474,"threshold_uncertainty_score":0.99542654},"labels":[],"label_agreement":null},{"id":"W4405627559","doi":"10.48550/arxiv.2412.14447","title":"Good Controls Gone Bad: Difference-in-Differences with Covariates","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"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":"Covariate; Econometrics; Statistics; Economics; Psychology; Mathematics","score_opus":0.16029442886371298,"score_gpt":0.27127922135343546,"score_spread":0.11098479248972248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405627559","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":[0.8709255,0.00017715467,0.11479753,0.00013455022,0.00026263326,0.0011730111,0.0001256802,0.0012141643,0.011189819],"genre_scores_gemma":[0.9900813,0.00025115904,0.0056267604,0.000038836293,0.00007382333,0.000019358264,0.000022616494,0.000083240135,0.0038029128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972087,0.00019180025,0.0004447369,0.0013533822,0.00017804264,0.0006233025],"domain_scores_gemma":[0.9972855,0.0008651041,0.00038130043,0.0011052324,0.0001830229,0.00017984663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030717443,0.0007373461,0.0011093166,0.00048457598,0.00008257381,0.00013698738,0.0009893692,0.00058520795,0.00016244661],"category_scores_gemma":[0.00016299459,0.0006468913,0.00020284171,0.00060621055,0.00030870063,0.00013640149,0.0012652021,0.0016929437,0.00006974851],"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":[0.00017551018,0.00024603828,0.012764745,0.00049078785,0.00026860746,0.0007963583,0.00031369817,0.0009298114,0.0001811732,0.9834966,0.00009628789,0.00024037709],"study_design_scores_gemma":[0.0006782283,0.000215292,0.0029386976,0.0013161377,0.0003281848,0.000008799033,0.00024058328,0.009918441,0.0004060394,0.98309,0.000041766056,0.00081786077],"about_ca_topic_score_codex":0.00029894803,"about_ca_topic_score_gemma":0.0007682796,"teacher_disagreement_score":0.11915584,"about_ca_system_score_codex":0.00039890912,"about_ca_system_score_gemma":0.0002932421,"threshold_uncertainty_score":0.99959826},"labels":[],"label_agreement":null},{"id":"W4405744723","doi":"10.1007/978-3-031-65937-9_12","title":"Regression-Based Estimation of Optimal Adaptive Treatment Strategies: Key Methods","year":2024,"lang":"en","type":"book-chapter","venue":"","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 Health Centre; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"","keywords":"Key (lock); Regression; Estimation; Computer science; Regression analysis; Statistics; Mathematics; Machine learning; Engineering","score_opus":0.23294005803725717,"score_gpt":0.48569731981574543,"score_spread":0.25275726177848823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405744723","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":[0.0000033434671,0.0001761484,0.568986,0.000026313357,0.000049361,0.00042942923,0.000048212005,0.00043521423,0.429846],"genre_scores_gemma":[0.00074934715,0.000054870667,0.7594186,0.00000890441,0.00003199822,0.000074688316,0.000040725496,0.000096952725,0.23952392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838215,0.00003955396,0.0006511321,0.000442035,0.00029659332,0.00018851744],"domain_scores_gemma":[0.9970745,0.001592416,0.00045966188,0.0006200399,0.00018128981,0.000072096365],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002576128,0.00056554005,0.0008159807,0.00026719802,0.000033348802,0.000036112073,0.00017808517,0.00047169696,0.0011599405],"category_scores_gemma":[0.000116451985,0.00039020064,0.00027683045,0.000042716307,0.00015853198,0.00013556909,0.000061389,0.00029382177,0.000039137387],"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":[0.00003799468,0.000039220504,1.9668622e-8,0.00020978118,0.00013769501,0.000017145523,0.00016787856,0.0006850725,0.00014152574,0.9694774,0.00038782356,0.028698446],"study_design_scores_gemma":[0.00013046694,0.0007677781,4.333873e-8,0.0014667411,0.00029709344,0.0000034918564,0.00013074184,0.02957179,0.021154273,0.94327384,0.0028571358,0.00034661268],"about_ca_topic_score_codex":0.000020928157,"about_ca_topic_score_gemma":0.000010858044,"teacher_disagreement_score":0.1904326,"about_ca_system_score_codex":0.00038023794,"about_ca_system_score_gemma":0.00034597976,"threshold_uncertainty_score":0.999855},"labels":[],"label_agreement":null},{"id":"W4405813361","doi":"10.1101/2024.12.20.24319429","title":"Causation and prevention in epidemiology: assumptions, derivations, and measures old and new","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","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":"Montreal Police Service","funders":"","keywords":"Causation; Epidemiology; Epistemology; Psychology; Medicine; Philosophy","score_opus":0.3567433570850655,"score_gpt":0.463564339118824,"score_spread":0.1068209820337585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405813361","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":[0.92210025,0.0061072065,0.06823225,0.0022238847,0.00011605958,0.0007548005,0.000012260143,0.00029546223,0.00015781955],"genre_scores_gemma":[0.8225118,0.006773664,0.16924152,0.00011396285,0.000120917066,0.00024098264,0.000037841568,0.00005251513,0.00090683217],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984309,0.0002640846,0.00052936893,0.0004922636,0.000106732965,0.00017665874],"domain_scores_gemma":[0.9986209,0.0007547902,0.00021036675,0.00028569397,0.00004334862,0.00008487636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015699707,0.00023319935,0.0004321437,0.00026183834,0.000043720363,0.000044173514,0.0000727841,0.00035039752,0.000010879315],"category_scores_gemma":[0.0029214364,0.00022226186,0.000030386871,0.000090451475,0.00009877247,0.000097306984,0.00043450334,0.0006097595,0.00000209764],"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":[0.000023830373,0.00006933474,0.36461747,0.002572581,0.00013727482,0.0000137547395,0.0017607685,0.000026803533,0.002268396,0.53835726,0.002975827,0.08717668],"study_design_scores_gemma":[0.000101195765,0.00002626164,0.067972384,0.0007298165,0.000064830194,0.000011599674,0.00003417263,0.00036041456,0.00027159037,0.9299764,0.0002701458,0.00018117891],"about_ca_topic_score_codex":0.0001287331,"about_ca_topic_score_gemma":0.00047374854,"teacher_disagreement_score":0.39161912,"about_ca_system_score_codex":0.00007029976,"about_ca_system_score_gemma":0.00006587672,"threshold_uncertainty_score":0.9063576},"labels":[],"label_agreement":null},{"id":"W4406096298","doi":"10.1080/10618600.2024.2449074","title":"Simultaneous Estimation of Multiple Treatment Effects from Observational Studies","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","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 Toronto","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Instrumental variable; Observational study; Inference; Confounding; Proxy (statistics); Robustness (evolution); Marginal structural model; Computer science; Econometrics; Exploit; Machine learning; Statistics; Mathematics; Data mining; Artificial intelligence","score_opus":0.11160337066313168,"score_gpt":0.42757067412792427,"score_spread":0.31596730346479257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406096298","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":[0.23735106,0.00034379962,0.76181674,0.00019040219,0.000069182955,0.00009701055,0.00011212901,0.000011419545,0.000008261665],"genre_scores_gemma":[0.55730724,0.000090362606,0.4425165,0.000040477284,0.00001559867,0.0000024362005,0.0000153687,0.0000031545387,0.000008847522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895346,0.00006375452,0.00056678744,0.0000841298,0.00025903695,0.00007284408],"domain_scores_gemma":[0.98112154,0.017784659,0.00038375464,0.000048749473,0.0006201781,0.00004112323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012596838,0.000113062546,0.00036628547,0.00012053874,0.000056549045,0.000011717526,0.000058287813,0.00004756541,0.0000036509782],"category_scores_gemma":[0.0033391572,0.000084798994,0.000052009884,0.00014319866,0.00014106566,0.000073457995,0.00002168201,0.00009512793,1.796695e-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":[0.00020452806,0.00043650848,0.004345863,0.0002662754,0.0006291645,0.00004535819,0.00035385822,0.05402788,0.0002168744,0.8669458,0.0008585992,0.0716693],"study_design_scores_gemma":[0.00059270294,0.0003445016,0.01080498,0.00017525547,0.00011342991,0.000005462792,0.000028803614,0.08641617,0.00041038118,0.90100336,0.0000441927,0.000060760904],"about_ca_topic_score_codex":0.0000065388617,"about_ca_topic_score_gemma":0.0000073567435,"teacher_disagreement_score":0.3199562,"about_ca_system_score_codex":0.000051536423,"about_ca_system_score_gemma":0.00006988665,"threshold_uncertainty_score":0.39975244},"labels":[],"label_agreement":null},{"id":"W4406234762","doi":"10.1002/alz.092745","title":"What happens next? Repeated administration of a social and structural determinants of health questionnaire in an Alzheimer’s Disease Research Center","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Center (category theory); Disease; Administration (probate law); Psychology; Gerontology; Medicine; Clinical psychology; Political science; Pathology","score_opus":0.28456953624418424,"score_gpt":0.5049184064742167,"score_spread":0.22034887023003247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406234762","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":[0.95489407,0.04341026,0.00023462556,0.00044421366,0.00014898827,0.00071085343,0.000028821405,0.00011243294,0.000015765057],"genre_scores_gemma":[0.9973077,0.0002605604,0.002272942,0.000020452611,0.000031401356,0.00004241119,0.000033121272,0.000030064428,0.0000013305711],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978665,0.00038103768,0.00072127825,0.0003532301,0.0003599195,0.0003180438],"domain_scores_gemma":[0.99917006,0.00007990836,0.0001960786,0.00027454857,0.00017374402,0.000105671745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009078328,0.0001659037,0.00031449395,0.00022599593,0.00010050427,0.00012078408,0.0001551423,0.000080898375,0.000032502354],"category_scores_gemma":[0.00007243718,0.00015888928,0.000048926562,0.00026576346,0.00023998812,0.0012583052,0.00010330624,0.00020887879,0.000001367708],"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":[0.0009789394,0.0010765503,0.14203586,0.0013276407,0.0036822658,0.00025499062,0.023565415,0.0000030437093,0.0052578785,0.12738271,0.0009167607,0.6935179],"study_design_scores_gemma":[0.0015862025,0.0027048162,0.40393043,0.0062169046,0.0054914905,0.00006025041,0.0042318692,0.0091329925,0.06310816,0.501835,0.0004117754,0.001290122],"about_ca_topic_score_codex":0.0001469665,"about_ca_topic_score_gemma":0.00094633497,"teacher_disagreement_score":0.69222784,"about_ca_system_score_codex":0.000016462473,"about_ca_system_score_gemma":0.00022273212,"threshold_uncertainty_score":0.64793164},"labels":[],"label_agreement":null},{"id":"W4406234893","doi":"10.1002/alz.085900","title":"Estimating Potential Eligibility for Disease Modifying Therapies for Alzheimer’s Disease Using Population‐Based Data in Alberta, Canada","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","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":true,"ca_institutions":"University of Toronto; McGill University; Hotchkiss Brain Institute; University of Alberta; University of Calgary","funders":"","keywords":"Disease; Medicine; Alzheimer's disease; Population; Gerontology; Environmental health; Internal medicine","score_opus":0.20633603041511392,"score_gpt":0.435868251140564,"score_spread":0.22953222072545007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406234893","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":[0.043221936,0.02977039,0.9201521,0.0010312335,0.0007629485,0.00333275,0.0013617986,0.00035751602,0.00000931358],"genre_scores_gemma":[0.7099031,0.0000028662616,0.28869402,0.0001267409,0.00012154903,0.00029760395,0.00077955524,0.000072869094,0.0000016886777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975258,0.000075646436,0.0006950982,0.00081775733,0.00035180844,0.0005338658],"domain_scores_gemma":[0.99745226,0.00096710405,0.00017700114,0.0010768534,0.00010762935,0.00021915788],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005436972,0.00035365662,0.00034275735,0.00013189694,0.00024176853,0.00016037092,0.0005164342,0.000063219326,0.000041866704],"category_scores_gemma":[0.0005373533,0.00035441015,0.00012400853,0.00019024531,0.00004555039,0.0006775409,0.00019303475,0.00013595656,8.396045e-7],"study_design_candidate":"simulation_or_modeling","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":[0.004504805,0.0033788355,0.12139474,0.007622565,0.060696494,0.0004796506,0.0020006292,0.16922818,0.0032335846,0.19369896,0.036235563,0.397526],"study_design_scores_gemma":[0.00033278283,0.000015846326,0.001081618,0.00021224328,0.009050224,5.670344e-7,0.000019260093,0.8422125,0.00033327658,0.14591736,0.00040741512,0.00041691388],"about_ca_topic_score_codex":0.121831015,"about_ca_topic_score_gemma":0.12385678,"teacher_disagreement_score":0.6729843,"about_ca_system_score_codex":0.00006923314,"about_ca_system_score_gemma":0.0008544074,"threshold_uncertainty_score":0.9998908},"labels":[],"label_agreement":null},{"id":"W4406245583","doi":"10.1214/24-ejs2338","title":"Pseudo-empirical likelihood methods for causal inference","year":2025,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Empirical likelihood; Causal inference; Inference; Econometrics; Statistics; Artificial intelligence; Estimator; Computer science","score_opus":0.09943190733000731,"score_gpt":0.522855835819901,"score_spread":0.42342392848989374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406245583","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":[0.00096489675,0.0004663686,0.99711543,0.0004262576,0.000196682,0.0002616643,0.00003404227,0.000059083843,0.00047559585],"genre_scores_gemma":[0.05162137,0.0004032804,0.9472239,0.00022413176,0.00009383239,0.000021063408,0.0000039486913,0.00002894311,0.00037951872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978678,0.00018612265,0.000868781,0.00016975276,0.00021579645,0.00069171365],"domain_scores_gemma":[0.9930517,0.0052529797,0.000552812,0.00024352253,0.00080243737,0.00009656418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001819125,0.00021677799,0.0005416577,0.00022579174,0.000089877074,0.000038788505,0.00038522054,0.00013174319,0.00003812358],"category_scores_gemma":[0.006802519,0.00018786354,0.00011214526,0.00027511374,0.0000922848,0.00014615778,0.00006110346,0.00076026446,0.0000016239729],"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":[0.000084339765,0.00011632688,0.00013841744,0.00008889562,0.00014079196,0.00000523917,0.00010978266,0.0000047469007,0.0017571757,0.9174541,0.013040038,0.06706013],"study_design_scores_gemma":[0.00053260016,0.00084971666,0.000050734052,0.000097867574,0.00018201595,0.00003980833,0.00007065861,0.0009380457,0.007874612,0.9782891,0.010907213,0.0001675776],"about_ca_topic_score_codex":0.0000024388767,"about_ca_topic_score_gemma":0.00001945476,"teacher_disagreement_score":0.06689255,"about_ca_system_score_codex":0.0004468294,"about_ca_system_score_gemma":0.0014499502,"threshold_uncertainty_score":0.81437415},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4406856354","doi":"10.2196/58981","title":"Methods to Adjust for Confounding in Test-Negative Design COVID-19 Effectiveness Studies: Simulation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Confounding; Multivariable calculus; Propensity score matching; Logistic regression; Multinomial logistic regression; Statistics; Medicine; Demography; Mathematics; Engineering","score_opus":0.6385098421897869,"score_gpt":0.7123872341679632,"score_spread":0.07387739197817633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406856354","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":[0.033985663,0.000033405075,0.95191216,0.00017359406,0.000072256385,0.013084679,0.000017905631,0.00020450016,0.0005158059],"genre_scores_gemma":[0.7828908,0.0000062141,0.20697297,0.000074870346,0.000017142462,0.009881723,0.0000012599395,0.000025954698,0.00012904551],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99358505,0.0040899664,0.000651813,0.0004700026,0.00053282233,0.0006703662],"domain_scores_gemma":[0.8085045,0.18949534,0.00013398877,0.00041350085,0.0013028112,0.00014983396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018707594,0.0002687613,0.00067487895,0.0013045487,0.0004991614,0.000078531644,0.0004140707,0.000120950994,0.000012397941],"category_scores_gemma":[0.12385384,0.00023296777,0.000066221924,0.0022579853,0.00022517164,0.0005192041,0.00041203876,0.00056193763,0.000009750723],"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":[0.00712825,0.008531063,0.007388368,0.013243057,0.001365508,0.000055077904,0.5413561,0.04218038,0.011604184,0.26835722,0.008345043,0.09044577],"study_design_scores_gemma":[0.0020192356,0.0026658524,0.0016628623,0.00058705185,0.000019610292,4.953663e-7,0.05211848,0.013850106,0.018884605,0.9076806,0.00022865953,0.00028249883],"about_ca_topic_score_codex":0.000039126287,"about_ca_topic_score_gemma":0.00006313224,"teacher_disagreement_score":0.7489052,"about_ca_system_score_codex":0.0026215566,"about_ca_system_score_gemma":0.0004262607,"threshold_uncertainty_score":0.950015},"labels":[],"label_agreement":null},{"id":"W4406936496","doi":"10.1007/s10654-024-01191-9","title":"Risks and rates, and the mathematical link between them","year":2025,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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","funders":"","keywords":"Medicine; Public health; Epidemiology; Link (geometry); Intensive care medicine; Environmental health; Internal medicine; Pathology","score_opus":0.39737497137081135,"score_gpt":0.4767041794445317,"score_spread":0.07932920807372035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406936496","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":[0.08069819,0.0023867383,0.85829407,0.026011862,0.00011159558,0.00028299127,0.000003837729,0.000073459436,0.03213725],"genre_scores_gemma":[0.7980962,0.0012819942,0.19868843,0.0012218207,0.00037437325,0.0000022415945,5.3780485e-7,0.000026954269,0.0003074789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99520034,0.003280653,0.0011091969,0.00013696298,0.00006050549,0.00021235367],"domain_scores_gemma":[0.98000306,0.018958563,0.0006269885,0.00023447991,0.000097478034,0.00007943329],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013621492,0.00014330185,0.00073437905,0.0000686085,0.00008277883,0.000012838534,0.0002622887,0.00005216185,0.000029431149],"category_scores_gemma":[0.023168275,0.00007673009,0.00008184717,0.00007356516,0.0006709468,0.00006726624,0.00018726196,0.00057508674,0.0000075269513],"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":[0.00007284077,0.000009756203,0.0065347455,0.00005518219,0.00011551076,0.0000312527,0.000211415,0.0000011688637,0.000025890997,0.9412327,0.0037834856,0.047926087],"study_design_scores_gemma":[0.0006798361,0.00009670616,0.0053064846,0.00017396832,0.000103197206,0.00019401727,0.000059387105,0.00006992104,0.00006752899,0.98728067,0.0058987997,0.00006946559],"about_ca_topic_score_codex":0.0000011573065,"about_ca_topic_score_gemma":2.4240265e-7,"teacher_disagreement_score":0.717398,"about_ca_system_score_codex":0.000014164906,"about_ca_system_score_gemma":0.000019452658,"threshold_uncertainty_score":0.98506},"labels":[],"label_agreement":null},{"id":"W4407149091","doi":"10.1002/pds.70112","title":"Evaluating the Role of High‐Dimensional Proxy Data in Confounding Adjustment in Multiple Sclerosis Research: A Case Study","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Canadian Institutes of Health Research; Multiple Sclerosis Society of Canada","keywords":"Medicine; Propensity score matching; Confounding; Proportional hazards model; Hazard ratio; Proxy (statistics); Cohort study; Retrospective cohort study; Glatiramer acetate; Pharmacoepidemiology; Demography; Covariate; Cohort; Medical prescription; Population; Internal medicine; Disease; Confidence interval; Environmental health; Statistics; Pharmacology","score_opus":0.6246042941558562,"score_gpt":0.5871360786941076,"score_spread":0.03746821546174861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407149091","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":[0.9949161,0.0011467692,0.0009898219,0.00093903625,0.00007858177,0.0017213841,0.000034037403,0.000040514504,0.00013376698],"genre_scores_gemma":[0.98600036,0.00017433794,0.013316435,0.00019869616,0.000023686956,0.00024150658,0.000011316857,0.0000097006005,0.00002397418],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926828,0.005264442,0.0009421622,0.00050862395,0.00020347697,0.00039847384],"domain_scores_gemma":[0.97154224,0.027511116,0.00019205447,0.0005963708,0.000115769755,0.000042468033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028607145,0.00015889305,0.00050878525,0.00024594445,0.0002017518,0.0000047523167,0.00037567,0.00007332083,0.000024320878],"category_scores_gemma":[0.012934039,0.00011520159,0.000022426635,0.0004168925,0.00030914033,0.00015771936,0.0009868715,0.0007371862,9.561334e-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":[0.001962394,0.0026044976,0.7116992,0.00036045295,0.00027984043,0.00022408384,0.009392508,0.0015435211,0.016863327,0.1408303,0.0013746243,0.11286526],"study_design_scores_gemma":[0.004703138,0.00029281946,0.025128815,0.00067381124,0.00012855775,0.000059193153,0.015283781,0.2720985,0.0030852084,0.67808974,0.00014441066,0.0003120027],"about_ca_topic_score_codex":0.0042153355,"about_ca_topic_score_gemma":0.001462071,"teacher_disagreement_score":0.6865704,"about_ca_system_score_codex":0.00011955097,"about_ca_system_score_gemma":0.000117795214,"threshold_uncertainty_score":0.99538046},"labels":[],"label_agreement":null},{"id":"W4407173849","doi":"10.1002/sim.70000","title":"Regression—A Means, Not an End","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Computer science; Statistics; Regression; Regression analysis; Mathematics","score_opus":0.1246073718061269,"score_gpt":0.4895811887662412,"score_spread":0.3649738169601143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407173849","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":[0.0020770915,0.000099793455,0.9754211,0.00097283523,0.00028391555,0.00027524173,0.00007027439,0.00021686869,0.02058289],"genre_scores_gemma":[0.13311806,0.00019967247,0.8626459,0.0010093462,0.000107768086,0.000047203856,0.00005776503,0.00002738357,0.002786858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987096,0.00009410232,0.00044155697,0.00023828304,0.00029125166,0.00022519933],"domain_scores_gemma":[0.9979784,0.0012781593,0.000103392165,0.00045701268,0.00011621099,0.00006683153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064504263,0.00016036225,0.00035657946,0.00021758185,0.00004756601,0.0000064954293,0.0002307947,0.00008494752,0.00042246154],"category_scores_gemma":[0.00421939,0.00012067408,0.000010063089,0.0002661295,0.0002444689,0.00006796983,0.000057226105,0.00031028752,0.0000048806455],"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":[0.000022643726,0.0000518944,0.00027576598,0.00010151345,0.000007100013,0.000049213602,0.000419056,0.0000011459398,0.0014232474,0.93932855,0.03123243,0.027087443],"study_design_scores_gemma":[0.00044080988,0.00014388032,0.0005855665,0.0006008532,0.000025239768,0.0000024217807,0.0003378608,0.00065115554,0.002592831,0.9903932,0.004109778,0.00011640514],"about_ca_topic_score_codex":0.000058689853,"about_ca_topic_score_gemma":0.00023340572,"teacher_disagreement_score":0.13104098,"about_ca_system_score_codex":0.00009257036,"about_ca_system_score_gemma":0.000061324274,"threshold_uncertainty_score":0.5051309},"labels":[],"label_agreement":null},{"id":"W4407241761","doi":"10.1016/j.jclinepi.2025.111716","title":"Using methods to extend inferences to specific target populations to improve the precision of subgroup analyses","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","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":"McGill University","funders":"National Institute on Aging; Vetenskapsrådet; Forté Foundation","keywords":"Statistics; Econometrics; Medicine; Mathematics; Computer science","score_opus":0.8483721148779694,"score_gpt":0.7299655129983066,"score_spread":0.11840660187966279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407241761","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":[0.09658557,0.00017420058,0.89648604,0.0052171266,0.00085485424,0.0003764696,0.000007416316,0.000019296622,0.00027901927],"genre_scores_gemma":[0.12102768,0.000057212146,0.8767586,0.0018189406,0.00025685728,0.000008987185,4.703908e-7,0.000011514886,0.000059764458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883945,0.0050685513,0.005641534,0.00033144106,0.0002195677,0.00034438996],"domain_scores_gemma":[0.92651623,0.06945417,0.002334479,0.00064140075,0.0007641785,0.00028950916],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029553805,0.00020181453,0.0023355323,0.00042993488,0.00008149108,0.0000124265935,0.00071224384,0.00025877004,0.00007513286],"category_scores_gemma":[0.24172567,0.000119877885,0.00052605965,0.000739614,0.00014716465,0.00012594726,0.00031955118,0.00068876275,0.0000042969477],"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":[0.0010637149,0.0005477944,0.05779065,0.0000778461,0.00039065597,0.000008384147,0.0004310655,0.012660219,0.034941398,0.58971244,0.019814117,0.28256172],"study_design_scores_gemma":[0.00015139907,0.00085517555,0.031681813,0.0002489214,0.000098991724,0.0000065483973,0.0001249579,0.00069829094,0.003922603,0.9564074,0.005683899,0.00011998029],"about_ca_topic_score_codex":0.00003967525,"about_ca_topic_score_gemma":0.000030464835,"teacher_disagreement_score":0.366695,"about_ca_system_score_codex":0.00007045327,"about_ca_system_score_gemma":0.00016635006,"threshold_uncertainty_score":0.9992786},"labels":[],"label_agreement":null},{"id":"W4407262364","doi":"10.1002/sim.70009","title":"Inverse Probability of Treatment Weighting Using the Propensity Score With Competing Risks in Survival Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Inverse probability weighting; Inverse probability; Statistics; Weighting; Survival analysis; Econometrics; Inverse; Average treatment effect; Computer science; Posterior probability; Mathematics; Medicine; Bayesian probability","score_opus":0.3133595065600282,"score_gpt":0.4585707417670098,"score_spread":0.1452112352069816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407262364","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":[0.6643048,0.000013931926,0.3344631,0.00006554718,0.000021703174,0.00049493875,0.000018677727,0.00002181144,0.0005954722],"genre_scores_gemma":[0.7294624,0.00001476682,0.27045226,0.000014881113,0.000009460397,0.00001677241,0.0000090107405,0.0000066870775,0.00001376728],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99852633,0.00027108582,0.00057097455,0.00022587275,0.00021715554,0.00018858185],"domain_scores_gemma":[0.9973945,0.0017453108,0.00027221153,0.00038373529,0.00018037923,0.000023869421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014179181,0.0001559918,0.0006450625,0.00024936796,0.00005409339,0.000004829229,0.00013478998,0.00004274516,0.000021446978],"category_scores_gemma":[0.001999321,0.00008804639,0.0000213916,0.0011748369,0.00042137832,0.000033858156,0.000061595434,0.00021566948,8.202676e-8],"study_design_candidate":"observational","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":[0.00008348625,0.00014886481,0.873932,0.000266947,0.00017167766,0.000027166861,0.0022396527,0.001678843,0.00047804535,0.119276084,0.000010390197,0.001686824],"study_design_scores_gemma":[0.0019836833,0.0006257776,0.12150501,0.0019132113,0.0013413832,0.0000026687683,0.003819599,0.072122715,0.00234997,0.79403275,0.000011707816,0.0002915006],"about_ca_topic_score_codex":0.003825331,"about_ca_topic_score_gemma":0.018533858,"teacher_disagreement_score":0.75242704,"about_ca_system_score_codex":0.0004096045,"about_ca_system_score_gemma":0.00013787254,"threshold_uncertainty_score":0.99937534},"labels":[],"label_agreement":null},{"id":"W4407289331","doi":"10.1016/j.cjca.2025.02.012","title":"On the Consistency Assumption for Causal Inference in Cardiovascular Epidemiology: Reply","year":2025,"lang":"en","type":"letter","venue":"Canadian Journal of Cardiology","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":true,"route_about_ca":false,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"","keywords":"Medicine; Causal inference; Consistency (knowledge bases); Epidemiology; Inference; Internal medicine; Artificial intelligence; Pathology","score_opus":0.20135572875256627,"score_gpt":0.39214995943747505,"score_spread":0.19079423068490878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407289331","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":[0.0004242503,0.0030758474,0.31970477,0.66256315,0.0028451288,0.0018623966,0.00036151058,0.000055317636,0.009107644],"genre_scores_gemma":[0.10276505,0.0008735283,0.018719489,0.86334586,0.011818356,0.00068029325,0.00016726316,0.00021905063,0.0014110805],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954077,0.0018693074,0.001333989,0.00040897992,0.00018596157,0.0007940433],"domain_scores_gemma":[0.97592646,0.021492975,0.000791559,0.0010057152,0.00062381674,0.0001594928],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005124272,0.0004147807,0.0023555334,0.00084389606,0.0001329732,0.000019844414,0.00078676,0.0012597704,0.000018989784],"category_scores_gemma":[0.047857825,0.0003065852,0.0011286716,0.00020081762,0.000473465,0.00007216522,0.000031753327,0.0033263953,0.0000042005477],"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":[0.000015794645,9.1309295e-7,0.0005355804,0.000115330186,0.0006414703,0.00042183895,0.000029896579,0.0005216768,0.0000013542566,0.05628212,0.94024795,0.0011860469],"study_design_scores_gemma":[0.0001718004,0.00016874142,0.00013216631,0.0003490829,0.00022198359,0.00011743856,0.000016805894,0.000007086027,0.0000072374733,0.4477221,0.550903,0.0001825376],"about_ca_topic_score_codex":0.0006932435,"about_ca_topic_score_gemma":0.0011987773,"teacher_disagreement_score":0.39144,"about_ca_system_score_codex":0.0008058306,"about_ca_system_score_gemma":0.0027179853,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W4407318751","doi":"10.1016/j.cmpb.2025.108658","title":"Methods in dynamic treatment regimens using observational healthcare data: A systematic review","year":2025,"lang":"en","type":"review","venue":"Computer Methods and Programs in Biomedicine","topic":"Advanced Causal Inference Techniques","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 Alberta","funders":"Alberta Innovates; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Observational study; Computer science; Health care; Intensive care medicine; Medicine; Data science; Internal medicine","score_opus":0.7636693510484898,"score_gpt":0.6750781406282522,"score_spread":0.08859121042023754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407318751","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":[6.370405e-8,0.5553434,0.4398836,0.00013118068,0.00015441597,0.0043750484,0.00002396223,0.0000837717,0.000004556638],"genre_scores_gemma":[6.5325825e-9,0.4996022,0.4992925,0.00010496453,0.00003866492,0.000575334,0.0003318289,0.000028153243,0.000026364114],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9903039,0.0052818903,0.002637836,0.0010548927,0.00024866872,0.00047283806],"domain_scores_gemma":[0.9915771,0.005389023,0.0010480366,0.0017491685,0.00011222315,0.00012448945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008947699,0.00076247816,0.006363666,0.0007213278,0.000053031676,0.000042101485,0.00073159713,0.00039329106,0.0000032556202],"category_scores_gemma":[0.001041268,0.0005106045,0.00019871183,0.0019191382,0.00015968681,0.00013120464,0.00063315773,0.0005260883,3.288725e-7],"study_design_candidate":"systematic_review","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":[8.3883356e-7,0.00006663,0.0000011157492,0.46968043,0.0000669472,0.000016485228,0.000036985548,1.7460653e-8,1.3194354e-7,0.0008485299,0.000012697341,0.5292692],"study_design_scores_gemma":[0.00024359183,0.00027527078,4.6292698e-7,0.9151826,0.0016478277,0.00012278775,0.00001580996,0.0026901078,1.5182468e-7,0.02144311,0.057973906,0.0004043542],"about_ca_topic_score_codex":0.00007950062,"about_ca_topic_score_gemma":0.00003374203,"teacher_disagreement_score":0.52886486,"about_ca_system_score_codex":0.0007319169,"about_ca_system_score_gemma":0.000415377,"threshold_uncertainty_score":0.9997346},"labels":[],"label_agreement":null},{"id":"W4407402000","doi":"10.1101/2025.02.09.25321976","title":"Data-Driven Insights on Opioid Use and Health Behavior Trends Following Decriminalization: Zero-Shot Sentiment and Behavior Analysis","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","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":"Schwartz/Reisman Emergency Medicine Institute; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Decriminalization; Zero (linguistics); Shot (pellet); Psychology; Criminology; Chemistry","score_opus":0.3404336173703156,"score_gpt":0.4710067046048623,"score_spread":0.13057308723454675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407402000","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":[0.93959385,0.0004769288,0.05742913,0.00016083803,0.00026349985,0.0010274105,0.0004728977,0.00043495014,0.00014052044],"genre_scores_gemma":[0.9035419,0.00084408687,0.09188288,0.00023364731,0.000052057287,0.00061103475,0.0018601227,0.00006690173,0.0009073553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968839,0.00021065907,0.0008307617,0.0012292652,0.0004961681,0.00034920065],"domain_scores_gemma":[0.9969016,0.00027028142,0.0005010563,0.0019939144,0.00010672195,0.00022643484],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047591317,0.00055192347,0.001113675,0.0009673096,0.00020923304,0.00023272324,0.00054648204,0.0003052442,0.000037820802],"category_scores_gemma":[0.00015132048,0.0005233687,0.00018988992,0.0005477192,0.00008831871,0.00027888562,0.0016937284,0.00054567424,0.000001013721],"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":[0.00009681789,0.004420992,0.882246,0.0033082902,0.004891708,0.00082352903,0.011984218,0.0003325425,0.00092400354,0.03313959,0.0055517335,0.052280527],"study_design_scores_gemma":[0.0031799958,0.0014217845,0.80982864,0.0065674647,0.07536637,0.00005256775,0.0009094101,0.015521321,0.008163281,0.06580319,0.00673298,0.006452994],"about_ca_topic_score_codex":0.00019600635,"about_ca_topic_score_gemma":0.00036847944,"teacher_disagreement_score":0.07241741,"about_ca_system_score_codex":0.00020573044,"about_ca_system_score_gemma":0.00013384364,"threshold_uncertainty_score":0.99972177},"labels":[],"label_agreement":null},{"id":"W4407815305","doi":"10.1093/wber/lhaf004","title":"Does It Matter Who You Ask For Time Use Data?","year":2025,"lang":"en","type":"article","venue":"The World Bank Economic Review","topic":"Advanced Causal Inference Techniques","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":"Impact","funders":"","keywords":"Ask price; Economics; Economy","score_opus":0.1377301586154332,"score_gpt":0.41703798619254956,"score_spread":0.27930782757711636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407815305","genre_codex":"commentary","genre_gemma":"other","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":[0.0027704833,0.076512486,0.09045179,0.49790525,0.0031992127,0.0352694,0.003475572,0.0029601692,0.28745565],"genre_scores_gemma":[0.0006877256,0.05929626,0.10665163,0.06494198,0.00053083414,0.0017333205,0.00030335927,0.00020913327,0.76564574],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985833,0.00009114163,0.000646559,0.00038062586,0.0000434231,0.00025492432],"domain_scores_gemma":[0.99618405,0.0013571114,0.00026726027,0.0021302493,0.000030777097,0.00003054979],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011238174,0.00022262192,0.0006385187,0.0000636485,0.00009010022,0.00007951804,0.0010651675,0.000036203746,0.0026966566],"category_scores_gemma":[0.00028645742,0.00011914367,0.00012639003,0.0000938271,0.000081076185,0.00041297346,0.0003951627,0.00014561864,0.001102719],"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":[0.000005865725,0.000012937005,0.00005078625,0.0013084492,0.000059050617,2.6240164e-7,0.000010939339,8.089816e-7,0.000010436192,0.06695506,0.9238158,0.007769637],"study_design_scores_gemma":[0.00007724161,0.000005593772,0.000016620523,0.002918771,0.0001673207,0.0000011768554,0.000002363386,0.00019547911,0.00015155037,0.18479306,0.8115136,0.00015725059],"about_ca_topic_score_codex":0.0000119366805,"about_ca_topic_score_gemma":0.00019549667,"teacher_disagreement_score":0.47819012,"about_ca_system_score_codex":0.00011715081,"about_ca_system_score_gemma":0.000052233903,"threshold_uncertainty_score":0.99967504},"labels":[],"label_agreement":null},{"id":"W4408028303","doi":"10.2139/ssrn.5146292","title":"Improving Targeting Policies Using Transfer Learning","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Transfer of learning; Policy learning; Computer science; Artificial intelligence; Machine learning","score_opus":0.08629939527334263,"score_gpt":0.3893813575189802,"score_spread":0.30308196224563755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408028303","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":[0.1321918,0.0024777378,0.86309725,0.00013417412,0.00027955268,0.000340928,0.0000064556834,0.00048597707,0.0009860975],"genre_scores_gemma":[0.92418325,0.0048039206,0.066717155,0.000076803946,0.000986442,0.00003356955,0.000013359243,0.00015860771,0.0030269192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948105,0.0002900194,0.0008659707,0.00045733957,0.00041766567,0.0031584646],"domain_scores_gemma":[0.99852425,0.0003137174,0.0004478453,0.00033825636,0.00028559275,0.000090357746],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031791157,0.0005362323,0.00070507725,0.00042684836,0.00048405092,0.00018695065,0.0006892281,0.00049200025,0.000026017919],"category_scores_gemma":[0.001088209,0.00052315986,0.00037604748,0.00020878101,0.000075360185,0.00022440827,0.00045994794,0.013321973,0.0000019633949],"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":[0.000057241305,0.000102124046,0.00046881888,0.00067921897,0.0006337356,0.000013925714,0.0015772405,0.006602135,0.016733272,0.94225645,0.000060519225,0.030815309],"study_design_scores_gemma":[0.0002007178,0.000104862534,0.0000017726549,0.0005709312,0.00020969851,0.00013492584,0.0019722346,0.0036870502,0.0036501177,0.9887376,0.00020788622,0.0005221958],"about_ca_topic_score_codex":0.00031892437,"about_ca_topic_score_gemma":0.00021138442,"teacher_disagreement_score":0.7963801,"about_ca_system_score_codex":0.0030595069,"about_ca_system_score_gemma":0.004999898,"threshold_uncertainty_score":0.999722},"labels":[],"label_agreement":null},{"id":"W4408119906","doi":"10.1161/circoutcomes.124.011188","title":"Association Between Use of WATCHMAN Device and 1-Year Mortality Using High-Dimensional Propensity Scores to Reduce Confounding","year":2025,"lang":"en","type":"article","venue":"Circulation Cardiovascular Quality and Outcomes","topic":"Advanced Causal Inference Techniques","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":"McGill University; Université de Montréal; McGill University Health Centre","funders":"","keywords":"Medicine; Atrial fibrillation; Propensity score matching; Hazard ratio; Cohort; Confounding; Internal medicine; Left atrial appendage occlusion; Stroke (engine); Cohort study; Observational study; Proportional hazards model; Warfarin; Percutaneous coronary intervention; Cardiology; Confidence interval; Myocardial infarction","score_opus":0.3540911417097541,"score_gpt":0.45313742823230146,"score_spread":0.09904628652254738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408119906","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":[0.93164104,0.00007342512,0.06738974,0.0001586155,0.0000644817,0.0005384085,0.000025687985,0.000083880026,0.000024734656],"genre_scores_gemma":[0.982993,0.000010076427,0.016796356,0.00010580269,0.00002816496,0.000008947543,0.000016004054,0.000011819997,0.000029799645],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979484,0.00045468847,0.0005786508,0.00034505533,0.0004947888,0.00017843036],"domain_scores_gemma":[0.99778056,0.001113817,0.00024368141,0.0004302342,0.00036133413,0.00007036418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025032158,0.00017334158,0.0008093803,0.00012503106,0.00016326053,0.00006550268,0.00006475049,0.00015127072,0.0000033483211],"category_scores_gemma":[0.002821967,0.00016681325,0.00020891808,0.00023089237,0.000067132176,0.00035002702,0.00013379566,0.0001325187,5.333496e-7],"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":[0.000008137171,0.000015363816,0.9680673,0.00025953804,0.0011897603,7.050313e-7,0.00012672889,0.00030304535,0.0013394711,0.027593728,0.00001293183,0.0010832731],"study_design_scores_gemma":[0.0003171108,0.0000071815316,0.9546616,0.00012886019,0.0006006392,7.78681e-7,0.000038053626,0.00009417868,0.0036228544,0.04030116,0.000047264035,0.00018031875],"about_ca_topic_score_codex":0.000897863,"about_ca_topic_score_gemma":0.000033973276,"teacher_disagreement_score":0.051352005,"about_ca_system_score_codex":0.00019798765,"about_ca_system_score_gemma":0.000050354494,"threshold_uncertainty_score":0.6802447},"labels":[],"label_agreement":null},{"id":"W4408251803","doi":"10.1016/j.annepidem.2025.03.001","title":"Systematic review of applied transportability and generalizability analyses: A landscape analysis","year":2025,"lang":"en","type":"review","venue":"Annals of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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; St. Paul's Hospital; Willow Biosciences (Canada)","funders":"","keywords":"Generalizability theory; Medicine; Statistics","score_opus":0.5609992239350639,"score_gpt":0.5951165765724884,"score_spread":0.03411735263742455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408251803","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":[0.0000043523655,0.9822721,0.014079026,0.00005896035,0.000014638841,0.0024988633,0.00029512987,0.00006870261,0.00070822675],"genre_scores_gemma":[0.000021940916,0.98595333,0.0127617195,0.00039686513,0.000010368023,0.0005752877,0.0002379613,0.000021432059,0.00002107041],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9891356,0.0032098799,0.006243312,0.0008122582,0.00017676892,0.00042218153],"domain_scores_gemma":[0.9694765,0.023312502,0.0045756665,0.0020725166,0.0004415998,0.00012118354],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.014659395,0.00060527783,0.0193616,0.00060831296,0.000026480677,0.0000018011986,0.00056376,0.0005848654,0.000119282864],"category_scores_gemma":[0.032994863,0.00041382958,0.0024023668,0.0016604379,0.00037904104,0.00004299427,0.00011486046,0.00034987746,7.3201835e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049295477,0.00007472953,0.00004343178,0.965404,0.0032967664,6.3137855e-7,0.000013961813,0.0000011208532,1.4527313e-7,0.02593689,0.00038886556,0.0048345514],"study_design_scores_gemma":[0.00005426335,0.00008262894,0.000011163651,0.7458136,0.052386135,0.000002968865,0.000011706772,0.000019259964,0.000008479698,0.19781466,0.0033305618,0.00046457295],"about_ca_topic_score_codex":0.000042015432,"about_ca_topic_score_gemma":0.000025890386,"teacher_disagreement_score":0.21959038,"about_ca_system_score_codex":0.00002208146,"about_ca_system_score_gemma":0.00018483777,"threshold_uncertainty_score":0.9998314},"labels":[],"label_agreement":null},{"id":"W4408297730","doi":"10.1017/rsm.2025.2","title":"Effect modification and non-collapsibility together may lead to conflicting treatment decisions: A review of marginal and conditional estimands and recommendations for decision-making","year":2025,"lang":"en","type":"review","venue":"Research Synthesis Methods","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Medical Research Council","keywords":"Lead (geology); Marginal structural model; Computer science; Risk analysis (engineering); Actuarial science; Econometrics; Economics; Business; Causal inference","score_opus":0.536206654897272,"score_gpt":0.6934173618985573,"score_spread":0.15721070700128525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408297730","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":[0.000010821497,0.5622438,0.43270034,0.0001874383,0.000017616427,0.0044267005,0.00023898749,0.00003002588,0.00014424106],"genre_scores_gemma":[0.0000106302205,0.5163332,0.48014757,0.000010727064,0.000014299383,0.0033950468,0.000014071777,0.000024608644,0.00004978765],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9932663,0.0040050778,0.0011013161,0.00083914073,0.00040367918,0.00038450558],"domain_scores_gemma":[0.70565,0.29273152,0.0003599257,0.00063742575,0.00048608493,0.00013504756],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.021902742,0.00042361874,0.0023251215,0.0007189739,0.00032464607,0.000076983844,0.000246472,0.0002685082,0.00004668765],"category_scores_gemma":[0.17748784,0.00031448712,0.0002233739,0.0006087561,0.00023755117,0.00011700229,0.00030192902,0.00031581247,8.859418e-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":[0.000051824645,0.00005708857,0.0000027719884,0.05562502,0.00010965258,7.5645704e-7,0.00003927765,6.169403e-8,0.00001153737,0.0028130403,0.00039169687,0.9408973],"study_design_scores_gemma":[0.00025377108,0.0010250211,0.000009483471,0.6058107,0.0014705474,0.00003757233,0.000062836356,0.0004089213,0.00061221,0.14391653,0.24585417,0.0005382342],"about_ca_topic_score_codex":0.000009124606,"about_ca_topic_score_gemma":0.0000040123005,"teacher_disagreement_score":0.94035906,"about_ca_system_score_codex":0.00036112778,"about_ca_system_score_gemma":0.0003335322,"threshold_uncertainty_score":0.99993074},"labels":[],"label_agreement":null},{"id":"W4408320751","doi":"10.1002/cjs.70000","title":"Sample empirical likelihood methods for causal inference","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Inference; Empirical likelihood; Sample (material); Econometrics; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.209577783021491,"score_gpt":0.5161440346327254,"score_spread":0.3065662516112344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408320751","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":[0.00036352823,0.00013577718,0.99730897,0.0005076776,0.00037197754,0.00019721941,0.0005701896,0.000021337528,0.0005232962],"genre_scores_gemma":[0.020617196,0.00002131159,0.97861904,0.0004753923,0.000073233634,0.000011831028,0.00000940542,0.000021598307,0.00015096812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986272,0.00010815851,0.0006337767,0.0001253815,0.00010511864,0.0004003791],"domain_scores_gemma":[0.9921032,0.0060931537,0.00029805928,0.00021278801,0.0008537813,0.00043901405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00083107274,0.00015989224,0.00039617694,0.0003459558,0.000130967,0.00006256523,0.00031704266,0.00011673578,0.00010868332],"category_scores_gemma":[0.018628689,0.00015055375,0.00007173976,0.00023247876,0.00013144869,0.00010858303,0.000018847442,0.00032088786,0.000001316223],"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":[0.000016653155,0.000022420672,0.0021492438,0.00011403722,0.00007535928,0.000030370642,0.00035151996,0.0000062561976,0.00011753015,0.8293431,0.080063015,0.08771049],"study_design_scores_gemma":[0.0002382397,0.00019625873,0.0003305964,0.00011304835,0.00009086552,0.000015703388,0.00011596508,0.00049563294,0.0009584902,0.94844,0.04886519,0.0001399908],"about_ca_topic_score_codex":0.00060944137,"about_ca_topic_score_gemma":0.0077248565,"teacher_disagreement_score":0.11909691,"about_ca_system_score_codex":0.0002993827,"about_ca_system_score_gemma":0.0028960337,"threshold_uncertainty_score":0.9896378},"labels":[],"label_agreement":null},{"id":"W4408340192","doi":"10.1002/cjs.70001","title":"Doubly robust criterion for causal inference","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causal inference; Inference; Computer science; Mathematics; Artificial intelligence; Econometrics","score_opus":0.16039079229112435,"score_gpt":0.40598532928507336,"score_spread":0.245594536993949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408340192","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":[0.0018548669,0.000090783076,0.9956217,0.00035320024,0.00042067672,0.00018442847,0.00042132696,0.00001804943,0.0010349854],"genre_scores_gemma":[0.24765976,0.000021227364,0.75111276,0.0002822998,0.000092205686,0.000010160163,0.000010406677,0.00002174002,0.0007894332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989592,0.000029000092,0.0005092618,0.000097682096,0.000111851834,0.00029299318],"domain_scores_gemma":[0.9975351,0.000903526,0.00026397148,0.00016721658,0.00084632466,0.00028383717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003257719,0.00013299781,0.0002810372,0.0003210476,0.00011890734,0.0000752264,0.00025193943,0.000087458415,0.0000872932],"category_scores_gemma":[0.0034518647,0.00012896025,0.000047678124,0.00015527819,0.00011310607,0.00014863355,0.000011842465,0.00022861673,0.0000016841749],"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":[0.000020958898,0.0000139291,0.0007153779,0.00015213678,0.000040726005,0.00007894167,0.00021699113,0.00007100565,0.00016100168,0.87068385,0.118494965,0.009350114],"study_design_scores_gemma":[0.00036615328,0.00021402168,0.00043003223,0.00029551066,0.000079868994,0.00002881635,0.000107154374,0.00039503077,0.000781395,0.973938,0.023201454,0.00016254792],"about_ca_topic_score_codex":0.00043289436,"about_ca_topic_score_gemma":0.012878018,"teacher_disagreement_score":0.24580489,"about_ca_system_score_codex":0.0002627936,"about_ca_system_score_gemma":0.001714087,"threshold_uncertainty_score":0.7186237},"labels":[],"label_agreement":null},{"id":"W4408408683","doi":"10.1002/sim.70034","title":"Guidelines and Best Practices for the Use of Targeted Maximum Likelihood and Machine Learning When Estimating Causal Effects of Exposures on Time‐To‐Event Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","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":true,"ca_institutions":"Université de Montréal; Institut National de Santé Publique du Québec; Université Laval","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Fonds de Recherche du Québec - Santé; International Society for Pharmacoepidemiology","keywords":"Computer science; Outcome (game theory); Machine learning; Counterfactual thinking; Event (particle physics); Causal inference; Covariate; A priori and a posteriori; Artificial intelligence; Data mining; Statistics","score_opus":0.16736663226226037,"score_gpt":0.4647206712009353,"score_spread":0.29735403893867496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408408683","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":[0.010962751,0.00053936534,0.9856863,0.0015773686,0.00009589971,0.0009849517,0.00007941516,0.000035617624,0.000038338458],"genre_scores_gemma":[0.017925797,0.00011878603,0.98119193,0.00021728492,0.00002757661,0.00007369191,0.000015515592,0.000021326987,0.00040809324],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868476,0.000103594655,0.00064663164,0.0001849064,0.00022149234,0.00015860765],"domain_scores_gemma":[0.980132,0.018807372,0.0005572874,0.00019702617,0.0002679997,0.00003834638],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000845587,0.00017023161,0.0005000303,0.00016198715,0.000060344133,0.000010348825,0.00010016709,0.00005238818,0.000013439996],"category_scores_gemma":[0.07612917,0.000108848704,0.000013753748,0.000108488304,0.00015845383,0.000059063586,0.000091949514,0.00019156132,2.5820535e-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":[0.0008847423,0.0008352403,0.03733682,0.012267311,0.0008366526,0.000055966048,0.009006996,0.0020059694,0.029642314,0.19952033,0.04297217,0.6646355],"study_design_scores_gemma":[0.0024714908,0.003902004,0.0025415588,0.005305071,0.00063582946,0.0000051428206,0.0005269161,0.11835946,0.008145823,0.8555183,0.0022700094,0.00031839762],"about_ca_topic_score_codex":0.00037707374,"about_ca_topic_score_gemma":0.00014214596,"teacher_disagreement_score":0.6643171,"about_ca_system_score_codex":0.000020688243,"about_ca_system_score_gemma":0.000029860608,"threshold_uncertainty_score":0.93165296},"labels":[],"label_agreement":null},{"id":"W4408502051","doi":"10.1038/s41592-025-02629-y","title":"Propensity score weighting","year":2025,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Propensity score matching; Weighting; Computational biology; Computer science; Biology; Internal medicine; Medicine","score_opus":0.2518400596419759,"score_gpt":0.5445541503713819,"score_spread":0.29271409072940596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408502051","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":[0.011167891,0.0004466292,0.9231678,0.00041271336,0.0003367337,0.00034623392,0.000001475791,0.00067135174,0.06344915],"genre_scores_gemma":[0.03680013,0.0000099086,0.95974964,0.00059349305,0.000058724363,0.000026578004,0.0000013579048,0.00001664644,0.002743543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988528,0.00031875554,0.0002216265,0.0002624961,0.00013127748,0.00021307172],"domain_scores_gemma":[0.9976949,0.0015384585,0.00009460935,0.00046753,0.00016966119,0.000034860423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529965,0.00015246976,0.00029442017,0.00011441061,0.00009728993,0.000025604002,0.000257496,0.00039120342,0.000046215853],"category_scores_gemma":[0.0071951896,0.0001189141,0.000068186535,0.00041260896,0.000053041127,0.000105687366,0.00016847493,0.0010538967,0.000002943427],"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":[0.000012578785,0.00003379729,0.0008785852,0.00011259475,0.00002448872,0.0000061589667,0.00005681324,1.8764945e-7,0.018820234,0.83066475,0.0053910427,0.14399877],"study_design_scores_gemma":[0.00006540293,0.000012143133,0.0004576514,0.00010972648,0.000021639356,0.0000029886326,0.00000948148,0.000052127267,0.24562922,0.7393268,0.01420983,0.000103000115],"about_ca_topic_score_codex":0.0000027734777,"about_ca_topic_score_gemma":0.000005170469,"teacher_disagreement_score":0.226809,"about_ca_system_score_codex":0.00007265184,"about_ca_system_score_gemma":0.000054295015,"threshold_uncertainty_score":0.8613834},"labels":[],"label_agreement":null},{"id":"W4408540877","doi":"10.1093/ofid/ofaf173","title":"Quantifying Potential Immortal Time Bias in Observational Studies in Acute Severe Infection","year":2025,"lang":"en","type":"article","venue":"Open Forum Infectious Diseases","topic":"Advanced Causal Inference Techniques","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":"Institute of Infection and Immunity","funders":"Medical Research Council; National Institute for Health and Care Research; Wellcome Trust","keywords":"Medicine; Observational study; Intensive care medicine; Internal medicine","score_opus":0.2998184884738356,"score_gpt":0.4849450123111662,"score_spread":0.18512652383733064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408540877","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":[0.98971653,0.00022728233,0.0019343394,0.0003062282,0.00032599628,0.0013123171,0.000059618982,0.0003838122,0.00573386],"genre_scores_gemma":[0.99720085,0.0001511313,0.0011242343,0.00029864765,0.00002132062,0.00044510877,0.00006201997,0.000028807988,0.0006678571],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826694,0.00015897038,0.00058080326,0.0004047214,0.00020567523,0.00038289934],"domain_scores_gemma":[0.9987846,0.00049880287,0.0001981319,0.00030780328,0.0001589841,0.00005169993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033724777,0.00027474138,0.0005231365,0.0004326247,0.00018107025,0.00014306394,0.0002632037,0.00011523479,0.00011706015],"category_scores_gemma":[0.0012272514,0.00027137346,0.00011089428,0.00083062815,0.00010618842,0.0010906005,0.0005508021,0.00024031193,0.000026049396],"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":[0.00010709284,0.0006365444,0.89823055,0.00015084355,0.00022129276,0.00007160725,0.00011078864,0.0006726456,0.00023928337,0.09242275,0.0048852195,0.0022514018],"study_design_scores_gemma":[0.0015439403,0.00015658826,0.22051695,0.00076101377,0.00015856726,0.00002917197,0.00023264438,0.0017700533,0.00045582117,0.77364737,0.00020990877,0.00051794836],"about_ca_topic_score_codex":0.00044361432,"about_ca_topic_score_gemma":0.0028492552,"teacher_disagreement_score":0.68122464,"about_ca_system_score_codex":0.00043231956,"about_ca_system_score_gemma":0.00016769774,"threshold_uncertainty_score":0.99997383},"labels":[],"label_agreement":null},{"id":"W4408615022","doi":"10.1287/msom.2023.0548","title":"Policy Optimization for Personalized Interventions in Behavioral Health","year":2025,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","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 Ottawa","funders":"","keywords":"Psychological intervention; Personalized medicine; Business; Computer science; Operations management; Economics; Medicine; Nursing","score_opus":0.13566382763771526,"score_gpt":0.4651434924299436,"score_spread":0.32947966479222834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408615022","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":[0.010364482,0.000032563876,0.9762342,0.00882238,0.00008525944,0.0022721207,0.000023670626,0.00030361422,0.0018617326],"genre_scores_gemma":[0.20861982,0.00011125384,0.7769955,0.0027148144,0.00004274875,0.0024083504,0.0002240614,0.000046364472,0.008837084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987206,0.00006220636,0.0005138294,0.00030042796,0.00011798333,0.00028499623],"domain_scores_gemma":[0.9993881,0.000052880776,0.00007852021,0.00036296734,0.00007683597,0.000040719086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033264857,0.00017675693,0.00023500646,0.000585749,0.00024842718,0.000112086695,0.00024458926,0.0000485145,0.00008603464],"category_scores_gemma":[0.00002337045,0.00018879739,0.00009529221,0.00037494703,0.000018508923,0.00025238973,0.00016315284,0.00010611774,0.000004095444],"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":[0.000027786587,0.0006949778,0.000027291666,0.002069477,0.00006771796,0.0000021286462,0.0012361426,0.13220888,0.000017016142,0.84727275,0.00092808885,0.01544774],"study_design_scores_gemma":[0.011035555,0.00084041676,0.0035821951,0.008367236,0.0006436183,0.0000076042697,0.01656334,0.2195453,0.011857497,0.70226246,0.022747258,0.0025474883],"about_ca_topic_score_codex":0.0005916066,"about_ca_topic_score_gemma":0.0032588898,"teacher_disagreement_score":0.19923867,"about_ca_system_score_codex":0.0004891912,"about_ca_system_score_gemma":0.000060880528,"threshold_uncertainty_score":0.7698934},"labels":[],"label_agreement":null},{"id":"W4408884128","doi":"10.1001/jamanetworkopen.2025.2152","title":"Quantitative Bias Analysis for Single-Arm Trials With External Control Arms","year":2025,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"Advanced Causal Inference Techniques","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":"Public Health Ontario; University of Toronto","funders":"","keywords":"Confounding; Hazard ratio; Observational study; Randomized controlled trial; Medicine; Hazard; Statistics; Confidence interval; Internal medicine; Mathematics","score_opus":0.4142205521263314,"score_gpt":0.49229273442198207,"score_spread":0.07807218229565066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408884128","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":[0.010282161,0.00019800298,0.9780713,0.000991581,0.00008322202,0.0027872806,0.0000516883,0.00016357588,0.0073712054],"genre_scores_gemma":[0.5102845,0.000018113275,0.48693338,0.00065521145,0.00013727907,0.00073616696,0.000016406866,0.000028582645,0.0011904071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976579,0.0005328146,0.000807544,0.00040279204,0.00020061267,0.00039831258],"domain_scores_gemma":[0.9888935,0.00948482,0.0007085754,0.0005137412,0.00032927011,0.00007006961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044638403,0.00025875497,0.001362302,0.00016874004,0.00014350167,0.00041256062,0.00068864226,0.0001347595,0.000119915996],"category_scores_gemma":[0.0034572221,0.00018497824,0.00026225176,0.0010017441,0.00008381488,0.00038210393,0.00015404608,0.00018961234,0.0000041974295],"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":[0.007127256,0.00063898705,0.013206822,0.00009892145,0.0055171615,0.000019362007,0.00045839182,0.007084744,0.0006858923,0.9364011,0.012737226,0.016024081],"study_design_scores_gemma":[0.0038293542,0.0013638261,0.0010275826,0.00071180286,0.0026808179,0.0000021309388,0.00031487207,0.008816068,0.0024752095,0.97569937,0.002668385,0.0004105574],"about_ca_topic_score_codex":0.000053722226,"about_ca_topic_score_gemma":0.00023645465,"teacher_disagreement_score":0.5000023,"about_ca_system_score_codex":0.00010116202,"about_ca_system_score_gemma":0.00009213647,"threshold_uncertainty_score":0.75431937},"labels":[],"label_agreement":null},{"id":"W4409055681","doi":"10.1016/j.apmr.2025.01.056","title":"Identifying What Matters to Adults with Mobility Limitations Regarding Their Experiences with Medications: A Concept Mapping Study 1131","year":2025,"lang":"en","type":"article","venue":"Archives of Physical Medicine and Rehabilitation","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":"University of Toronto","funders":"","keywords":"Psychology; Rehabilitation; Medicine; Physical therapy","score_opus":0.06485814509009839,"score_gpt":0.3825831507416942,"score_spread":0.3177250056515958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409055681","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":[0.8691487,0.00008536455,0.123633526,0.0055422415,0.000023439437,0.0012720091,0.0000013512308,0.00007852963,0.00021485618],"genre_scores_gemma":[0.94760436,0.000013532869,0.051558644,0.00014826322,0.00002579888,0.00062164105,0.0000035764526,0.000009176789,0.000015032493],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9988009,0.00014594106,0.00033575727,0.0003405079,0.00023755907,0.00013935569],"domain_scores_gemma":[0.989791,0.009565991,0.00014854257,0.00030528675,0.000120969074,0.00006822087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021355826,0.00015496914,0.00035664922,0.00025773168,0.00012413936,0.00001989344,0.00013190099,0.00001714398,0.0000022160878],"category_scores_gemma":[0.0013590303,0.00009281825,0.000035121626,0.00042284784,0.0008909624,0.0004072108,0.000054607204,0.000116445706,1.6961121e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017602561,0.00049574795,0.00089915923,0.00043919584,0.000089884685,6.6678865e-7,0.9249115,0.000017942277,0.0020743043,0.019208021,0.00006984118,0.05161773],"study_design_scores_gemma":[0.00072418916,0.0029615136,0.0064090188,0.005431801,0.000059003214,6.97512e-7,0.85590947,0.00031469663,0.0007680169,0.12729059,0.000016714152,0.00011426584],"about_ca_topic_score_codex":0.000035830206,"about_ca_topic_score_gemma":0.00004573655,"teacher_disagreement_score":0.10808256,"about_ca_system_score_codex":0.000018064447,"about_ca_system_score_gemma":0.00003264553,"threshold_uncertainty_score":0.37850183},"labels":[],"label_agreement":null},{"id":"W4409423144","doi":"10.1177/25152459251326571","title":"Navigating Unmeasured Confounding in Nonexperimental Psychological Research: A Practical Guide to Computing and Interpreting E-Value","year":2025,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Confounding; Value (mathematics); Psychology; Psychological research; Econometrics; Computer science; Statistics; Social psychology; Mathematics","score_opus":0.40287867640893543,"score_gpt":0.758232983432707,"score_spread":0.3553543070237715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409423144","genre_codex":"empirical","genre_gemma":"methods","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":[0.69888145,0.0012363847,0.2724907,0.0022031104,0.00030270673,0.0008309748,6.4579757e-7,0.00008838138,0.023965657],"genre_scores_gemma":[0.47452918,0.00035123577,0.5246568,0.00039257712,0.0000133453,0.000047727724,1.1345068e-7,0.000005174077,0.000003903942],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99351513,0.002794798,0.00094714056,0.0013566006,0.00053157494,0.000854761],"domain_scores_gemma":[0.9802346,0.018712314,0.000392605,0.00038363095,0.00011550345,0.00016134119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036158703,0.00024519706,0.00049391395,0.00036425146,0.00028639036,0.0002409647,0.0005903377,0.00019009726,0.000013100609],"category_scores_gemma":[0.087959975,0.00020105559,0.00002408502,0.002848813,0.0015664164,0.0015272981,0.000815634,0.0021172427,0.0000010554938],"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":[0.00040203196,0.0006307377,0.031633582,0.00007518083,0.000003682466,0.00012855804,0.003070631,0.000052620948,0.05706253,0.32146016,0.000021278125,0.585459],"study_design_scores_gemma":[0.0010979194,0.0010057029,0.014285923,0.0024934427,0.000007149726,0.00018534184,0.01143455,0.007829018,0.0054885717,0.95271367,0.0028435288,0.0006152001],"about_ca_topic_score_codex":0.00006715169,"about_ca_topic_score_gemma":0.00006007431,"teacher_disagreement_score":0.6312535,"about_ca_system_score_codex":0.00027810317,"about_ca_system_score_gemma":0.000038625138,"threshold_uncertainty_score":0.9924774},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4409592567","doi":"10.1177/23969873251332118","title":"Conducting descriptive epidemiology and causal inference studies using observational data: A 10-point primer for stroke researchers","year":2025,"lang":"en","type":"review","venue":"European Stroke Journal","topic":"Advanced Causal Inference Techniques","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Observational study; Causal inference; Interpretability; Observational methods in psychology; Inference; Data science; Psychological intervention; Computer science; Medicine; Machine learning; Artificial intelligence; Psychiatry; Pathology","score_opus":0.9514757015146624,"score_gpt":0.6367079876816275,"score_spread":0.3147677138330349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409592567","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":[0.00004252408,0.87931144,0.117519945,0.00007812134,0.00034220517,0.0010919953,0.0008052543,0.00010927788,0.00069925765],"genre_scores_gemma":[0.000004950048,0.70294607,0.29386717,0.00004502545,0.0005624939,0.000028777124,0.00007349776,0.0000881629,0.002383854],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922213,0.0035883866,0.002140527,0.0008482604,0.00036824902,0.00083325146],"domain_scores_gemma":[0.97773486,0.017894449,0.002181191,0.0008611393,0.0010773126,0.0002510478],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011844277,0.0006841579,0.0027164079,0.00048083122,0.00055908604,0.00013852624,0.001086015,0.00021058439,0.000039865343],"category_scores_gemma":[0.07681012,0.00054024544,0.0003234439,0.00022838761,0.0005135633,0.0007659626,0.0017008318,0.0019433623,0.000005287453],"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":[0.00011704901,0.00016464585,0.00013567158,0.027775908,0.0046251058,0.00021901885,0.0010131069,0.000012944078,0.000113338465,0.030161584,0.03788632,0.8977753],"study_design_scores_gemma":[0.00089910626,0.0006133904,0.0000101879805,0.050322853,0.003254931,0.0008483598,0.0022999186,0.0002372839,0.0000197004,0.045254182,0.89484227,0.0013978088],"about_ca_topic_score_codex":0.000005141516,"about_ca_topic_score_gemma":0.0000058471464,"teacher_disagreement_score":0.8963775,"about_ca_system_score_codex":0.0005931613,"about_ca_system_score_gemma":0.0011246146,"threshold_uncertainty_score":0.9997049},"labels":[],"label_agreement":null},{"id":"W4409802238","doi":"10.1093/biomtc/ujaf041","title":"Optimal dynamic treatment regime estimation in the presence of nonadherence","year":2025,"lang":"en","type":"article","venue":"Biometrics","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; University of Waterloo; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Estimator; Robustness (evolution); Estimation; Reliability (semiconductor); Computer science; Population; Outcome (game theory); Econometrics; Process (computing); Precision medicine; Medicine; Mathematics; Statistics; Economics","score_opus":0.11847246443711536,"score_gpt":0.4363638841518298,"score_spread":0.31789141971471446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409802238","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":[0.26302177,0.00037913152,0.72982675,0.00033848576,0.00008093154,0.00087614165,0.00001968197,0.00012282093,0.005334311],"genre_scores_gemma":[0.81581897,0.00009908765,0.18352176,0.000015333346,0.0000023120501,0.000070463364,0.0000041512085,0.000005059787,0.00046287788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991724,0.000058545924,0.00027772266,0.00015008415,0.00020043863,0.00014081511],"domain_scores_gemma":[0.9979867,0.0014036243,0.00013071833,0.00039069392,0.00007447333,0.000013792674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034696242,0.000105468054,0.00017186356,0.00080666295,0.000026845957,0.00001623203,0.00029930726,0.0000698147,0.0000099556455],"category_scores_gemma":[0.001412052,0.000072352115,0.000037210073,0.0037438795,0.00007805011,0.00009391188,0.000044749107,0.0000700399,0.0000046807804],"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":[0.000112074755,0.002520196,0.0047143223,0.00065493205,0.000107934466,0.000040393767,0.0025005764,0.0011471984,0.013101238,0.6308491,0.0037037258,0.34054828],"study_design_scores_gemma":[0.0015221849,0.0016187044,0.01534501,0.0006760112,0.00015275089,0.000015693882,0.0011448992,0.1235145,0.06081808,0.791655,0.0028933492,0.0006437891],"about_ca_topic_score_codex":0.000054907174,"about_ca_topic_score_gemma":0.000014194006,"teacher_disagreement_score":0.5527972,"about_ca_system_score_codex":0.00016796544,"about_ca_system_score_gemma":0.00006397083,"threshold_uncertainty_score":0.29504335},"labels":[],"label_agreement":null},{"id":"W4409890912","doi":"10.1111/jre.13405","title":"Risk of Bias Evaluation of Cross‐Sectional Studies: Adaptation of the Newcastle‐Ottawa Scale","year":2025,"lang":"en","type":"article","venue":"Journal of Periodontal Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":120,"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":"Cross-sectional study; Confounding; Context (archaeology); Scale (ratio); Cohort; Rating scale; Contrast (vision); Medicine; Psychology; Computer science; Geography; Statistics; Mathematics; Pathology; Artificial intelligence; Cartography","score_opus":0.6463724630743077,"score_gpt":0.607364568122784,"score_spread":0.03900789495152368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409890912","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":[0.99395186,0.0006039816,0.0036576937,0.00008109846,0.00014511262,0.00034981343,0.000018291072,0.000004934671,0.0011871896],"genre_scores_gemma":[0.99157774,0.00018373018,0.007884284,0.000002612969,0.00004525011,0.000010992708,4.1141314e-7,0.000009057422,0.00028593105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99545777,0.0009667232,0.0010599714,0.000108621454,0.0022458774,0.00016105737],"domain_scores_gemma":[0.98869336,0.0019806297,0.001059308,0.00027785567,0.007954806,0.000034040848],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012305294,0.000091437134,0.00036394008,0.0003850292,0.00012864338,0.000017269927,0.00036295992,0.00008966917,0.00007075324],"category_scores_gemma":[0.019379232,0.000060940158,0.00021629389,0.0006341349,0.0006037401,0.00024018943,0.00015606788,0.0005308507,5.8893596e-7],"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":[0.0012166861,0.0012792441,0.7864124,0.0013581564,0.0010525313,0.0000037189302,0.012639029,0.0048204926,0.12434879,0.030059772,0.0026201925,0.03418897],"study_design_scores_gemma":[0.0016451692,0.0011619056,0.4462434,0.0012655912,0.0002040485,0.00002541405,0.012509595,0.0050470284,0.1820739,0.34952077,0.00018296727,0.00012020707],"about_ca_topic_score_codex":0.00017660827,"about_ca_topic_score_gemma":0.0005661681,"teacher_disagreement_score":0.340169,"about_ca_system_score_codex":0.00037892244,"about_ca_system_score_gemma":0.00081969163,"threshold_uncertainty_score":0.98888093},"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":"W4409918350","doi":"10.1080/13576275.2025.2497605","title":"Letter","year":2025,"lang":"en","type":"letter","venue":"Mortality","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Philosophy","score_opus":0.23741347383835726,"score_gpt":0.44715184643090433,"score_spread":0.20973837259254707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409918350","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":[0.00019897395,0.000030654646,0.039853096,0.86616516,0.0006367059,0.0006432394,0.00017093282,0.0015111292,0.09079009],"genre_scores_gemma":[0.00014457176,0.000007463397,0.012642438,0.9599098,0.0023798656,0.00013748831,0.000158373,0.00005014894,0.02456985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824905,0.00011395648,0.00042321306,0.00045275493,0.00038203647,0.00037900667],"domain_scores_gemma":[0.9980377,0.00038781954,0.00020576325,0.0012525904,0.00009096519,0.00002517366],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025463366,0.0003550965,0.0005347896,0.00010129824,0.000050659914,0.00003992503,0.0004519329,0.00086956884,0.0004479146],"category_scores_gemma":[0.0003593971,0.00032620385,0.00019236554,0.00012658496,0.000101247315,0.00008096808,0.00016990333,0.0019144987,0.000053873206],"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":[5.8996227e-7,0.000012394693,0.00008925292,0.0003615498,0.00006000149,0.00019402514,0.000010846365,2.631e-8,0.000008310814,0.0055927355,0.9934539,0.00021634443],"study_design_scores_gemma":[0.000026726211,0.0000061059695,0.000038409966,0.00008326417,0.00006282776,0.0000014468137,4.5862666e-7,0.0000011624492,0.00044100446,0.37757295,0.62156284,0.00020279204],"about_ca_topic_score_codex":0.000053535263,"about_ca_topic_score_gemma":0.000018644512,"teacher_disagreement_score":0.37198022,"about_ca_system_score_codex":0.00012653515,"about_ca_system_score_gemma":0.000068583155,"threshold_uncertainty_score":0.999919},"labels":[],"label_agreement":null},{"id":"W4410288395","doi":"10.2196/71873","title":"Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Advanced Causal Inference Techniques","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","funders":"U.S. Food and Drug Administration; National Institute of Neurological Disorders and Stroke; U.S. Department of Health and Human Services","keywords":"Pipeline (software); Computer science; Scalability; Data science; Disease; Missing data; Health records; Sampling bias; Medicine; Clinical trial; MEDLINE; Machine learning; Data mining; Artificial intelligence; Sample size determination; Health care; Database","score_opus":0.35156122820201635,"score_gpt":0.5739641170098899,"score_spread":0.22240288880787357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410288395","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":[0.5893547,0.0048657246,0.35239935,0.04906618,0.0016011472,0.00249531,0.000012729951,0.000106294945,0.00009858495],"genre_scores_gemma":[0.987302,0.0051893564,0.0057656323,0.00016463014,0.00048179118,0.00007283699,7.564417e-7,0.000032545235,0.0009904684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949954,0.0006638991,0.0013236292,0.00022301843,0.0020412689,0.00075278943],"domain_scores_gemma":[0.98377466,0.014403367,0.0004893984,0.00038829132,0.0006710022,0.00027326308],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014277369,0.00015069093,0.0006202441,0.0006686999,0.00005975375,0.000068253,0.0010850158,0.00009227846,0.00007532288],"category_scores_gemma":[0.043909106,0.00009628944,0.00019146575,0.0006985422,0.00026124532,0.00044363987,0.00037979707,0.0018323249,7.664192e-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":[0.0069636554,0.0012906978,0.15909685,0.0061282204,0.00075236714,0.0003490827,0.0013704096,0.00070079666,0.00066092354,0.5132329,0.18605123,0.123402864],"study_design_scores_gemma":[0.0037354978,0.0051966584,0.023499917,0.044626553,0.00011938876,0.000036391975,0.00041452385,0.016600586,0.0041023837,0.84261245,0.058561902,0.000493754],"about_ca_topic_score_codex":0.0013247405,"about_ca_topic_score_gemma":0.011057777,"teacher_disagreement_score":0.3979473,"about_ca_system_score_codex":0.0031552722,"about_ca_system_score_gemma":0.005389728,"threshold_uncertainty_score":0.96414447},"labels":[],"label_agreement":null},{"id":"W4410292011","doi":"10.1016/j.jclinepi.2025.111828","title":"There is no upper limit on the maximum effect that can be detected in randomized trials","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"McGill University; McGill University Health Centre","funders":"National Institute of Neurological Disorders and Stroke; National Cancer Institute; National Institutes of Health","keywords":"Randomized controlled trial; Limit (mathematics); Medicine; Internal medicine; Mathematics; Mathematical analysis","score_opus":0.5842019234852277,"score_gpt":0.5934001139642046,"score_spread":0.009198190478976853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410292011","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":[0.736185,0.0010767019,0.057713073,0.18901707,0.0034424444,0.0035050884,0.000024463237,0.00016387693,0.008872295],"genre_scores_gemma":[0.93608785,0.0029178886,0.02728892,0.032217328,0.00061526184,0.00012632208,0.0000013632072,0.00004502916,0.00070005294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9404096,0.050709717,0.007851587,0.00031787387,0.0002539398,0.00045729833],"domain_scores_gemma":[0.3455019,0.64850223,0.005014794,0.0005800107,0.00027589028,0.00012516096],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17121689,0.0003082057,0.008322367,0.00022698122,0.00005409825,0.000011725654,0.0006374566,0.0006765975,0.00037013763],"category_scores_gemma":[0.7845791,0.0001430565,0.0019129373,0.00021355717,0.00047397526,0.00006281222,0.000106924614,0.0022038317,0.000012805372],"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":[0.24670155,0.0010103578,0.069462225,0.00030184348,0.0029875233,0.00014643153,0.000296307,0.000041235144,0.00034036522,0.44289893,0.16072834,0.07508491],"study_design_scores_gemma":[0.034715187,0.001012587,0.0024563796,0.00066108775,0.0002768253,0.000012165805,0.000030159503,0.0002574054,0.0012012587,0.95582736,0.0034068965,0.00014270254],"about_ca_topic_score_codex":0.00002907353,"about_ca_topic_score_gemma":0.000033794586,"teacher_disagreement_score":0.61336225,"about_ca_system_score_codex":0.00008162762,"about_ca_system_score_gemma":0.00021537638,"threshold_uncertainty_score":0.95746744},"labels":[],"label_agreement":null},{"id":"W4410337793","doi":"10.1016/j.arth.2025.04.032","title":"Total Hip Arthroplasty versus Education and Exercise: A Secondary Analysis of Propensity Matched Data Comparing Outcomes Across Hip Osteoarthritis Symptom Severity","year":2025,"lang":"en","type":"article","venue":"The Journal of Arthroplasty","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Department of Medicine, University of Toronto; European Research Council; Canadian Institutes of Health Research; University Health Network Foundation; Horizon 2020 Framework Programme; Ontario Trillium Foundation; Region Sjælland; Arthritis Society","keywords":"Propensity score matching; Osteoarthritis; Medicine; Physical therapy; Arthroplasty; Total hip arthroplasty; Hip arthroplasty; Hip surgery; Physical medicine and rehabilitation; Internal medicine; Surgery; Alternative medicine","score_opus":0.09348904435676114,"score_gpt":0.39046450475438904,"score_spread":0.2969754603976279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410337793","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":[0.9917191,0.000680068,0.006058688,0.00025537258,0.00050806557,0.00037317566,0.000109303495,0.00005263119,0.00024355533],"genre_scores_gemma":[0.99155056,0.00039790798,0.0077881585,0.000037849342,0.000036461264,0.0000057425227,0.000019606081,0.000018371436,0.00014532666],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99775875,0.00023804841,0.0010109546,0.00026290002,0.00042035992,0.00030900273],"domain_scores_gemma":[0.9963617,0.0010595906,0.0010101149,0.000994008,0.00046944243,0.00010515717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014991027,0.00028514263,0.0011961127,0.0002482223,0.00025396098,0.00007297173,0.0004563142,0.00011735156,0.0000692212],"category_scores_gemma":[0.00070018217,0.00020569781,0.00016153605,0.0006572825,0.00043354236,0.00074763905,0.0007392591,0.0005622525,0.0000021264361],"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":[0.006998252,0.003020563,0.4161883,0.0014139367,0.009889447,0.000051592324,0.015709301,0.0005426001,0.0047042747,0.0059278966,0.0085369935,0.5270168],"study_design_scores_gemma":[0.008990242,0.0013363654,0.91319066,0.002365883,0.009638859,0.0003981463,0.017798632,0.0024133222,0.011531142,0.029826779,0.0012346756,0.0012752949],"about_ca_topic_score_codex":0.000066253066,"about_ca_topic_score_gemma":0.0006771861,"teacher_disagreement_score":0.5257416,"about_ca_system_score_codex":0.00009334997,"about_ca_system_score_gemma":0.00037422436,"threshold_uncertainty_score":0.83881134},"labels":[],"label_agreement":null},{"id":"W4410376957","doi":"10.1002/pds.70155","title":"How Effective Are Machine Learning and Doubly Robust Estimators in Incorporating High‐Dimensional Proxies to Reduce Residual Confounding?","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Estimator; Propensity score matching; Logistic regression; Proxy (statistics); Lasso (programming language); Statistics; Observational study; Residual; Econometrics; Regression; Medicine; Computer science; Machine learning; Mathematics; Algorithm","score_opus":0.06151136878612086,"score_gpt":0.41288480805064215,"score_spread":0.3513734392645213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410376957","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":[0.9284301,0.0011335574,0.051835787,0.015865676,0.0002567163,0.001518794,0.000029880526,0.00042868571,0.00050081883],"genre_scores_gemma":[0.9192065,0.0000634651,0.07937979,0.0006795617,0.000054214364,0.00016256748,0.000015327345,0.000019862693,0.00041871812],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973402,0.0011916489,0.00049105356,0.0005291446,0.000091001166,0.00035697914],"domain_scores_gemma":[0.99177337,0.0075898087,0.00030644922,0.00012423904,0.000091282716,0.00011482448],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003367821,0.00029637985,0.0007119817,0.0002535013,0.00028342634,0.00002392835,0.00010611591,0.0001446448,0.000008276692],"category_scores_gemma":[0.008356232,0.00026018175,0.0000299847,0.00025843558,0.00027120498,0.00022133737,0.00030056678,0.000782537,0.0000010669858],"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":[0.002186703,0.00018361537,0.58501834,0.0009395504,0.00023721393,0.00009076165,0.001204622,0.0053544184,0.012460721,0.36446795,0.0057071624,0.022148956],"study_design_scores_gemma":[0.0049784705,0.00033959374,0.07662873,0.0020315072,0.00024699525,0.0000835236,0.00085525063,0.031987283,0.03326475,0.8460042,0.0021898157,0.0013898689],"about_ca_topic_score_codex":0.00012113241,"about_ca_topic_score_gemma":0.00010494421,"teacher_disagreement_score":0.5083896,"about_ca_system_score_codex":0.00010518787,"about_ca_system_score_gemma":0.000045358305,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W4410480739","doi":"10.1002/sim.70102","title":"Continuous‐Time Causal Inference With Marked Point Process Weights: An Example on Sodium‐Glucose Co‐Transporters 2 Inhibitor Medications and Urinary Tract Infection","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"University of Manitoba; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal structural model; Covariate; Confounding; Medicine; Causal inference; Time point; Clinical endpoint; Internal medicine; Statistics; Clinical trial; Mathematics","score_opus":0.043079783093944224,"score_gpt":0.39116520241493435,"score_spread":0.34808541932099013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410480739","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":[0.46371552,0.000050957922,0.53077507,0.0005281613,0.00010857253,0.0010932895,0.00013379597,0.00034759264,0.003247074],"genre_scores_gemma":[0.9472442,0.00022711791,0.05145119,0.00028080275,0.0000776067,0.00020135046,0.0002716443,0.00003911747,0.00020696943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998094,0.00013109866,0.00061487063,0.0004522763,0.00040568426,0.00030204296],"domain_scores_gemma":[0.9973951,0.0015868297,0.00023886582,0.00040554357,0.00022628164,0.00014736297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070480956,0.00030230475,0.0005305656,0.0003923493,0.00011653245,0.000018939527,0.00014638028,0.00013385374,0.00015510869],"category_scores_gemma":[0.00078338804,0.00023505538,0.000012146415,0.0003506653,0.0005757267,0.00022923794,0.000017957429,0.0004943787,0.0000028713905],"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":[0.0018261168,0.005672331,0.1033865,0.0030494719,0.0003202387,0.00089394615,0.017528718,0.000025933017,0.005347625,0.82173955,0.007953575,0.032255974],"study_design_scores_gemma":[0.003978851,0.006124005,0.06637472,0.0036657068,0.00034408964,0.00008257687,0.0013806657,0.0019881038,0.004238292,0.9103819,0.0007033087,0.0007377752],"about_ca_topic_score_codex":0.0003345123,"about_ca_topic_score_gemma":0.0002680777,"teacher_disagreement_score":0.48352867,"about_ca_system_score_codex":0.00012766082,"about_ca_system_score_gemma":0.00017316705,"threshold_uncertainty_score":0.95852804},"labels":[],"label_agreement":null},{"id":"W4410496288","doi":"10.1080/2330443x.2025.2505485","title":"Designing Randomized Experiments to Predict Unit-Specific Treatment Effects","year":2025,"lang":"en","type":"article","venue":"Statistics and Public Policy","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":"Kellogg's (Canada); Science North","funders":"Institute of Education Sciences","keywords":"Randomized controlled trial; Randomized experiment; Unit (ring theory); Statistics; Environmental science; Econometrics; Mathematics; Medicine; Internal medicine; Mathematics education","score_opus":0.10377384455206441,"score_gpt":0.43091742576745856,"score_spread":0.32714358121539416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410496288","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":[0.004270703,0.00022121811,0.9844805,0.00043842717,0.0000865065,0.0011574496,0.00011745134,0.00021903837,0.00900868],"genre_scores_gemma":[0.37912637,0.00055849476,0.61627746,0.0005260271,0.00011718179,0.00080636056,0.00003779846,0.000039030947,0.002511266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874526,0.00019324431,0.00031708012,0.0002441366,0.0001383943,0.00036185526],"domain_scores_gemma":[0.9970994,0.0022449489,0.00008307575,0.00028516498,0.00009903899,0.00018837153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029307464,0.00022279655,0.00049894943,0.00036820574,0.00013591327,0.00012401963,0.00012212596,0.00006538209,0.00002623956],"category_scores_gemma":[0.002039694,0.00017956791,0.0000393846,0.00032201875,0.00011925333,0.000079035235,0.00008722576,0.00007552339,0.0000060234042],"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":[0.00039423467,0.000082343046,0.000055598543,0.000047745154,0.000078072815,0.0000055328273,0.00043158114,4.7419402e-7,0.00068588567,0.9556571,0.005221601,0.037339803],"study_design_scores_gemma":[0.017530441,0.00023123313,0.000071469,0.00010133136,0.000046167886,0.0000022947427,0.00008317687,0.00018421678,0.008543748,0.9605782,0.01240998,0.00021774975],"about_ca_topic_score_codex":0.00018425689,"about_ca_topic_score_gemma":0.000012858026,"teacher_disagreement_score":0.37485567,"about_ca_system_score_codex":0.00016113196,"about_ca_system_score_gemma":0.00018740512,"threshold_uncertainty_score":0.7322567},"labels":[],"label_agreement":null},{"id":"W4410799412","doi":"10.1002/ejhf.3707","title":"Global Heart Failure Epidemiology Versus Enrolment in Pivotal Trials: A Formidable Mismatch","year":2025,"lang":"en","type":"article","venue":"European Journal of Heart Failure","topic":"Advanced Causal Inference Techniques","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":"Population Health Research Institute; McMaster University; Hamilton Health Sciences","funders":"","keywords":"Representativeness heuristic; Medicine; Epidemiology; Clinical trial; Population; Demography; Environmental health; Internal medicine; Statistics","score_opus":0.18523273088193667,"score_gpt":0.44819951082789244,"score_spread":0.26296677994595574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410799412","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":[0.5244577,0.0043965913,0.20043066,0.24461669,0.0042151865,0.0037319236,0.00011861381,0.00090481585,0.017127847],"genre_scores_gemma":[0.5230238,0.000038488004,0.47520867,0.0010293386,0.00036241696,0.000012490049,0.0000034331595,0.000049716476,0.00027168143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929773,0.0034108374,0.0023387922,0.00032672405,0.00031268282,0.000633618],"domain_scores_gemma":[0.9955735,0.0027256643,0.0007924281,0.00045835294,0.00025392065,0.0001961146],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0110028535,0.00035066291,0.001519626,0.00029736653,0.000098915945,0.000041792453,0.00048012086,0.00013183425,0.00015094192],"category_scores_gemma":[0.009357312,0.0002845997,0.00045451833,0.00043730557,0.00011762741,0.00034902952,0.00018922848,0.000782355,0.00004466551],"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":[0.0013931787,0.00041591492,0.010400856,0.0001764281,0.00025333645,0.00026186704,0.00026409456,0.00020713417,0.002480814,0.049400102,0.93251854,0.002227738],"study_design_scores_gemma":[0.006861375,0.001886466,0.0029856612,0.0012794764,0.00016292685,0.0004952666,0.00096122496,0.000059410122,0.001998051,0.15304062,0.82973355,0.0005359376],"about_ca_topic_score_codex":0.000015317219,"about_ca_topic_score_gemma":0.00013290327,"teacher_disagreement_score":0.274778,"about_ca_system_score_codex":0.00037373704,"about_ca_system_score_gemma":0.00023867119,"threshold_uncertainty_score":0.9999606},"labels":[],"label_agreement":null},{"id":"W4410810617","doi":"10.1371/journal.pone.0324639","title":"Is there a competitive advantage to using multivariate statistical or machine learning methods over the Bross formula in the hdPS framework for bias and variance estimation?","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","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":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Lasso (programming language); Computer science; Context (archaeology); Mean squared error; Random forest; Feature selection; Selection bias; Proxy (statistics); Machine learning; Mathematics; Biology","score_opus":0.29627820605033617,"score_gpt":0.5109115217999374,"score_spread":0.2146333157496012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410810617","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":[0.024329461,0.00006656097,0.9730501,0.00079081516,0.000012818207,0.0013732805,0.00010516546,0.00008400911,0.000187761],"genre_scores_gemma":[0.15107757,0.000017732971,0.84785265,0.0006874017,0.000016279437,0.00021235298,0.0000048334814,0.000023061222,0.00010811577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985839,0.00041159597,0.00031465007,0.0002510861,0.00018892765,0.0002498084],"domain_scores_gemma":[0.98524237,0.014213235,0.00012994997,0.00029409144,0.00008889486,0.00003148458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012100331,0.00017853975,0.00033268638,0.00006614904,0.00021997125,0.000089244,0.0002003306,0.000098925564,0.00005767051],"category_scores_gemma":[0.009573549,0.00010419736,0.000027932412,0.00030351855,0.00008133768,0.00012778428,0.00013275977,0.00048575248,0.0000012272766],"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":[0.00018356387,0.00033181824,0.0011618509,0.000320699,0.000107438624,0.000004234294,0.0040526,0.000073218194,0.0016848542,0.9881864,0.0000146813245,0.0038786037],"study_design_scores_gemma":[0.00033884373,0.00012665807,0.0013728868,0.0010470337,0.00012409486,0.0000017715295,0.00080191845,0.18180814,0.0034985323,0.8106278,0.00010290363,0.00014940066],"about_ca_topic_score_codex":0.000050474307,"about_ca_topic_score_gemma":0.00005186972,"teacher_disagreement_score":0.18173493,"about_ca_system_score_codex":0.00006804608,"about_ca_system_score_gemma":0.00003937456,"threshold_uncertainty_score":0.9987692},"labels":[],"label_agreement":null},{"id":"W4410846226","doi":"10.1101/2025.05.29.25328403","title":"Glucose-lowering effects of physical activity in type 1 diabetes: A causal modelling and matched-pair analysis approach","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","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":"York University; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Type 2 diabetes; Physical activity; Internal medicine; Diabetes mellitus; Endocrinology; Psychology; Medicine; Chemistry; Econometrics; Mathematics; Physical medicine and rehabilitation","score_opus":0.07677183290813011,"score_gpt":0.36105178172942126,"score_spread":0.28427994882129115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410846226","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":[0.7234247,0.00015266743,0.27552378,0.000007692905,0.00004212611,0.00045637268,0.000010795363,0.00016938799,0.00021249877],"genre_scores_gemma":[0.9565996,0.00009038617,0.043041654,0.000004723308,0.000031363423,0.00015528944,0.000009161393,0.000031632022,0.00003621468],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982381,0.00016089165,0.00034724438,0.0006471594,0.0002760919,0.00033052606],"domain_scores_gemma":[0.99759966,0.0011603904,0.00030350138,0.00076939387,0.00009972641,0.00006733521],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046845753,0.000404633,0.001390453,0.00052261486,0.000026997683,0.000025062966,0.00031384046,0.00032009554,0.0000018279001],"category_scores_gemma":[0.00036898837,0.00039041918,0.00021719419,0.0007927323,0.00010033932,0.00009245165,0.0007553545,0.0008522541,4.178453e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045957937,0.008291609,0.26605892,0.09609528,0.009851423,0.000120809476,0.019115258,0.40756777,0.14033256,0.031102793,0.00004755272,0.020956432],"study_design_scores_gemma":[0.00022142075,0.00008071403,0.0026469103,0.0011071608,0.0011285107,2.3971322e-7,0.00003539307,0.6032556,0.27932855,0.11164964,0.000002834731,0.00054297934],"about_ca_topic_score_codex":0.00007108175,"about_ca_topic_score_gemma":0.000016852975,"teacher_disagreement_score":0.263412,"about_ca_system_score_codex":0.00011383685,"about_ca_system_score_gemma":0.00007134083,"threshold_uncertainty_score":0.99985474},"labels":[],"label_agreement":null},{"id":"W4410953661","doi":"10.1016/j.fertnstert.2025.05.168","title":"Recommendation to improve the rigor and impact of nonrandomized studies of interventions in fertility treatment research","year":2025,"lang":"en","type":"article","venue":"Fertility and Sterility","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"Merck KGaA; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Merck Healthcare KGaA","keywords":"Fertility; Psychological intervention; Randomized controlled trial; Rigour; Medicine; Psychology; Gynecology; Environmental health; Internal medicine; Mathematics; Psychiatry; Population","score_opus":0.4673525755076959,"score_gpt":0.588457109762856,"score_spread":0.12110453425516016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410953661","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":[0.9944636,0.00018545864,0.0032772992,0.0004007849,0.0000268507,0.0013227833,0.00008335435,0.000019083554,0.00022078265],"genre_scores_gemma":[0.9982772,0.000062058825,0.001400592,0.0000057077477,0.0000018243531,0.00018906475,0.000003080203,0.0000031361649,0.00005734886],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99798286,0.00080415374,0.0006707113,0.00027453076,0.00010051026,0.00016721341],"domain_scores_gemma":[0.996997,0.0021426966,0.000104958766,0.00042992356,0.0002889117,0.000036533507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037437296,0.00012477476,0.0005492502,0.00012230873,0.00008504064,0.00001274377,0.00009433981,0.000058339225,0.000030657146],"category_scores_gemma":[0.0032804005,0.00007588095,0.00012604325,0.0002629247,0.00036665256,0.00010209647,0.00022202401,0.00013189847,1.4943704e-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":[0.2545799,0.007951981,0.15898186,0.0084789945,0.0016063588,0.0000019368695,0.03016843,0.0000051338507,0.044006687,0.0027715482,0.0002060088,0.49124116],"study_design_scores_gemma":[0.0014515404,0.00072803337,0.78709346,0.00019679088,0.000033054246,1.0128636e-7,0.00092223444,0.00012354675,0.011271424,0.198117,0.000009554845,0.000053251635],"about_ca_topic_score_codex":0.0008640333,"about_ca_topic_score_gemma":0.002187718,"teacher_disagreement_score":0.6281116,"about_ca_system_score_codex":0.00022189961,"about_ca_system_score_gemma":0.000052275383,"threshold_uncertainty_score":0.3927183},"labels":[],"label_agreement":null},{"id":"W4410967593","doi":"10.29220/csam.2025.32.3.259","title":"A comparison of propensity score-based causal estimators for analyzing partially missing confounder","year":2025,"lang":"en","type":"article","venue":"Communications for Statistical Applications and Methods","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":"University of Calgary; McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Propensity score matching; Missing data; Estimator; Statistics; Confounding; Econometrics; Mathematics; Causal inference","score_opus":0.4389368396050024,"score_gpt":0.6008971631796389,"score_spread":0.16196032357463652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410967593","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":[0.00016235637,0.00021554573,0.99620336,0.0005848514,0.00001264085,0.002155647,0.00017991393,0.00010782886,0.0003778427],"genre_scores_gemma":[0.12070262,0.00001405819,0.8765277,0.000051390754,0.0000052387722,0.0025436378,0.00011084726,0.000015490254,0.000028974977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987114,0.00018153207,0.00062946166,0.0002356397,0.000063244705,0.00017870066],"domain_scores_gemma":[0.98500735,0.013182645,0.00024888894,0.0010277639,0.00046206504,0.000071293296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010160119,0.00014157282,0.00046290265,0.00011215487,0.0004483221,0.00004188114,0.00037717057,0.000085465865,0.000004567849],"category_scores_gemma":[0.00261848,0.00013604523,0.000058861027,0.00026417908,0.00045886537,0.00005244527,0.00013877205,0.00013447474,1.6733759e-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":[0.000024154546,0.00020836519,0.0011652132,0.0002876035,0.00003362123,9.415957e-9,0.00003821887,0.0000057635993,0.0021318963,0.88698703,0.0002010017,0.10891715],"study_design_scores_gemma":[0.00033009954,0.00007390363,0.0007359015,0.000093998795,0.00025529414,3.7678217e-7,0.000050037183,0.069681495,0.011561188,0.9065776,0.010494112,0.00014600609],"about_ca_topic_score_codex":0.0000109776365,"about_ca_topic_score_gemma":0.000029820596,"teacher_disagreement_score":0.12054026,"about_ca_system_score_codex":0.000049609833,"about_ca_system_score_gemma":0.00017954427,"threshold_uncertainty_score":0.5547763},"labels":[],"label_agreement":null},{"id":"W4411394384","doi":"10.1007/s12561-025-09495-4","title":"Causal Inference on Missing Exposure via Robust Estimation","year":2025,"lang":"en","type":"article","venue":"Statistics in Biosciences","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":"University of Waterloo","funders":"","keywords":"Causal inference; Inference; Biostatistics; Estimation; Missing data; Econometrics; Computer science; Statistics; Data mining; Artificial intelligence; Machine learning; Mathematics; Public health; Economics; Medicine","score_opus":0.12353098767810926,"score_gpt":0.44517602030833536,"score_spread":0.3216450326302261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411394384","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":[0.009065073,0.000020298701,0.98527664,0.0002416872,0.00026111686,0.00021472452,0.00004209003,0.00015452274,0.004723838],"genre_scores_gemma":[0.52633625,0.000012141732,0.47336772,0.000101151956,0.000008177901,0.000016550372,0.0000047348894,0.0000051765396,0.00014808781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985863,0.00007441611,0.00039148086,0.00033268196,0.0003244872,0.00029064328],"domain_scores_gemma":[0.997872,0.0015683766,0.0001414169,0.00027245417,0.00009916766,0.00004657794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005121277,0.00016961063,0.00020998345,0.00029567714,0.00015760362,0.00009195153,0.00031695058,0.00008686268,0.000041265474],"category_scores_gemma":[0.0036018107,0.0001494926,0.000016001548,0.00065766694,0.00033335027,0.00019469652,0.0000700777,0.00021709816,0.000007843479],"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":[0.000009132985,0.00009545925,0.0019800398,0.00007116728,0.0000030252008,0.000011001465,0.0002463344,0.00061831035,0.0012388858,0.9434539,0.00084930554,0.05142341],"study_design_scores_gemma":[0.00010748349,0.00013566583,0.00255707,0.00025792734,0.00000703585,0.0000011095822,0.0001068896,0.0350729,0.005147425,0.9563825,0.000055789442,0.00016817133],"about_ca_topic_score_codex":0.000044550492,"about_ca_topic_score_gemma":0.00020383917,"teacher_disagreement_score":0.51727116,"about_ca_system_score_codex":0.00012575118,"about_ca_system_score_gemma":0.00014757129,"threshold_uncertainty_score":0.6096131},"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":"W4411607629","doi":"10.1002/pds.70174","title":"Simultaneously Dealing With Immortal Time Bias and Residual Confounding: A Case Study of a High‐Dimensional Propensity Score Approach With a Nested Case–Control Framework in Multiple Sclerosis Research","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Confounding; Medicine; Observational study; Hazard ratio; Confidence interval; Residual; Matching (statistics); Meta-analysis; Statistics; Internal medicine; Computer science; Mathematics; Algorithm","score_opus":0.35328064349770466,"score_gpt":0.44569927190225594,"score_spread":0.09241862840455128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411607629","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":[0.98380435,0.00019846765,0.013249189,0.00023214558,0.000015368509,0.0023198721,0.000036482936,0.00010247165,0.000041635336],"genre_scores_gemma":[0.9664023,0.000023757155,0.03320605,0.0001364018,0.00002193646,0.0001509939,0.000007015695,0.000027055015,0.000024516974],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995028,0.0027482505,0.0007882508,0.0007064208,0.0002228155,0.0005062502],"domain_scores_gemma":[0.9743059,0.024592316,0.00028999732,0.00033040406,0.0003454433,0.00013588322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069445814,0.0003297569,0.0010754394,0.00032280767,0.00043327655,0.000015809745,0.0001227644,0.00018685144,0.000009769739],"category_scores_gemma":[0.0044499543,0.00023391945,0.000026028632,0.0004796358,0.0007417893,0.00014247061,0.00020204831,0.001129728,4.3121872e-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":[0.021203082,0.0029894377,0.87946516,0.0009664367,0.0013289435,0.032105878,0.009840633,0.014262808,0.0015411099,0.03151465,0.00016943157,0.0046124314],"study_design_scores_gemma":[0.06807016,0.00884145,0.065960616,0.006792687,0.0034599127,0.09013338,0.037065353,0.59366715,0.003291601,0.11864402,0.00003121918,0.004042471],"about_ca_topic_score_codex":0.0037462248,"about_ca_topic_score_gemma":0.0021848127,"teacher_disagreement_score":0.8135046,"about_ca_system_score_codex":0.00006923802,"about_ca_system_score_gemma":0.00011471679,"threshold_uncertainty_score":0.9538958},"labels":[],"label_agreement":null},{"id":"W4411623088","doi":"10.1093/fampra/cmaf043","title":"Causal mediation analysis: what is it and how can it be used to inform practice and policy?","year":2025,"lang":"en","type":"article","venue":"Family Practice","topic":"Advanced Causal Inference Techniques","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":"Université de Sherbrooke; Jewish General Hospital; Université du Québec en Abitibi-Témiscamingue; McGill University Health Centre; Université de Montréal; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Mediation; Psychological intervention; Outcome (game theory); Medicine; Intervention (counseling); Toolbox; Causal model; Mechanism (biology); Causal analysis; Nursing; Risk analysis (engineering); Computer science; Epistemology","score_opus":0.1383430506533034,"score_gpt":0.45613738218223726,"score_spread":0.3177943315289339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411623088","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03153867,0.00067497237,0.079537265,0.85925686,0.00021418932,0.0014790723,0.00007207656,0.00044808342,0.026778838],"genre_scores_gemma":[0.57821745,0.0062173633,0.22555201,0.18245566,0.00022591745,0.0003294945,0.00005682719,0.00007817525,0.0068671107],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981845,0.00020510505,0.0003564706,0.00041609033,0.0005052844,0.0003325441],"domain_scores_gemma":[0.99224436,0.0059785205,0.00045707542,0.00055338925,0.00058681937,0.00017984542],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001285854,0.00026874113,0.00041539897,0.00061188254,0.00019114392,0.0006334196,0.00017632384,0.00019349734,0.000013517046],"category_scores_gemma":[0.021680865,0.00026616035,0.00004781179,0.0017061777,0.00007327179,0.0049855476,0.0002373544,0.00037288692,0.0000066406255],"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":[0.0010399956,0.0008052139,0.0017596788,0.0007921718,0.00600171,0.00014819103,0.092302516,0.000048969374,0.008706646,0.509326,0.31231344,0.06675549],"study_design_scores_gemma":[0.000855201,0.00036240698,0.001354064,0.00019317781,0.003218116,0.0000413416,0.09213647,0.00067366014,0.002895839,0.025523238,0.8719913,0.00075523555],"about_ca_topic_score_codex":0.00053197873,"about_ca_topic_score_gemma":0.0007291085,"teacher_disagreement_score":0.6768012,"about_ca_system_score_codex":0.0002125176,"about_ca_system_score_gemma":0.00025405828,"threshold_uncertainty_score":0.9999791},"labels":[],"label_agreement":null},{"id":"W4411699008","doi":"10.1353/obs.2025.a963647","title":"A new four-arm within-study comparison: Design, implementation, and data","year":2025,"lang":"en","type":"article","venue":"Observational Studies","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":"Education and Early Childhood Development","funders":"University of Virginia","keywords":"Computer science","score_opus":0.8056678441780485,"score_gpt":0.5920920188067013,"score_spread":0.21357582537134723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411699008","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":[0.06729232,0.0018384603,0.92069,0.0065565924,0.00027070253,0.0020302893,0.00005211498,0.0004973579,0.00077217846],"genre_scores_gemma":[0.2858196,0.000097760065,0.71205515,0.0006927358,0.000076173324,0.00015224003,0.00004800568,0.000016699798,0.0010416398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877745,0.000071637056,0.00045484272,0.00032264885,0.00023713187,0.00013629768],"domain_scores_gemma":[0.99757147,0.0015833968,0.00016800218,0.00039861456,0.00024799656,0.000030536823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006103451,0.00015702164,0.00030796573,0.0000562072,0.00023257888,0.000040989617,0.000279146,0.000026545757,0.000035877772],"category_scores_gemma":[0.0009503031,0.00013668957,0.000013256973,0.00025090546,0.00005452496,0.00030854327,0.00056380517,0.000093115515,0.0000024032524],"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":[0.00004360716,0.0002126781,0.14928043,0.00007473416,0.0005853141,0.000003476784,0.002698604,0.000020274047,0.00006099994,0.5260883,0.31536007,0.005571491],"study_design_scores_gemma":[0.00066057936,0.00017817135,0.045432758,0.00006520603,0.00015335612,0.0000012871831,0.012195277,0.00028946443,0.0005438249,0.9357738,0.004499969,0.00020634092],"about_ca_topic_score_codex":0.00005028731,"about_ca_topic_score_gemma":0.0005529972,"teacher_disagreement_score":0.40968546,"about_ca_system_score_codex":0.000061139326,"about_ca_system_score_gemma":0.00010871986,"threshold_uncertainty_score":0.5574039},"labels":[],"label_agreement":null},{"id":"W4411734481","doi":"10.1007/978-3-031-87083-5_9","title":"Surrogate Endpoints","year":2025,"lang":"en","type":"book-chapter","venue":"","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":"McMaster University","funders":"","keywords":"Surrogate endpoint; Medicine; Internal medicine","score_opus":0.17652251141792635,"score_gpt":0.40848504335957947,"score_spread":0.23196253194165312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411734481","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.0085986e-7,0.00005559269,0.035631914,0.000090536676,0.0001065353,0.0003063651,0.000030355046,0.0010760827,0.9627019],"genre_scores_gemma":[0.000054719967,0.00014735553,0.07922611,0.0001924117,0.000052689385,0.000015531701,0.000016477785,0.00005508069,0.9202396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989113,0.000007943043,0.00036274426,0.00031569574,0.00020880369,0.00019347195],"domain_scores_gemma":[0.9985703,0.00043798942,0.00016878742,0.0006480304,0.00012101832,0.000053824806],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014275433,0.00034060783,0.00046545637,0.0001565441,0.00003336562,0.000018643019,0.00026602185,0.00039040289,0.004932699],"category_scores_gemma":[0.00018916465,0.00030335572,0.00014899237,0.000017323957,0.000068023175,0.000060576705,0.00019049797,0.00040676075,0.00030830974],"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":[0.0000027206997,0.000005699449,2.6878752e-7,0.00008156194,0.00003286108,0.000015147219,0.000007848784,1.4045141e-8,0.000015582793,0.9271184,0.06674611,0.0059737787],"study_design_scores_gemma":[0.00004332865,0.000018336426,9.717903e-8,0.0002824886,0.000035619552,0.000002777218,0.000001824757,0.000002336955,0.0014214369,0.75863355,0.23934111,0.00021710171],"about_ca_topic_score_codex":0.0000031503066,"about_ca_topic_score_gemma":0.00003029295,"teacher_disagreement_score":0.172595,"about_ca_system_score_codex":0.00010031897,"about_ca_system_score_gemma":0.000072811,"threshold_uncertainty_score":0.9999418},"labels":[],"label_agreement":null},{"id":"W4411777752","doi":"10.1093/cid/ciaf317","title":"Does Piperacillin-Tazobactam Increase Mortality Risk Compared With Cefepime? Collider Bias and the Importance of Assumptions in Instrumental Variable Analyses","year":2025,"lang":"en","type":"article","venue":"Clinical Infectious Diseases","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":"Jewish General Hospital; McGill University","funders":"National Institute for Health and Care Research","keywords":"Cefepime; Piperacillin/tazobactam; Medicine; Instrumental variable; Collider; Piperacillin; Variable (mathematics); Statistics; Intensive care medicine; Econometrics; Microbiology; Antibiotics; Particle physics; Mathematics; Bacteria; Physics","score_opus":0.17018066114500954,"score_gpt":0.4804230636962383,"score_spread":0.3102424025512287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411777752","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":[0.99273837,0.00016653359,0.0044969777,0.00008050225,0.00008280521,0.00080611464,0.00031565395,0.00018890484,0.0011241575],"genre_scores_gemma":[0.9974657,0.0005051089,0.0014849395,0.0002282496,0.000031529362,0.0001799964,0.000026849115,0.000016733751,0.00006087843],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99718535,0.0007645177,0.0011717761,0.00042153156,0.0002162706,0.00024055768],"domain_scores_gemma":[0.99172014,0.0066766916,0.00063322525,0.00064711075,0.0001903368,0.00013250967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010745482,0.00025695915,0.000887589,0.00012718927,0.0001688416,0.000054593995,0.00018903449,0.000120242395,0.000095511394],"category_scores_gemma":[0.00637285,0.0001343847,0.00016717658,0.00060315785,0.0011937541,0.00022612435,0.00015722946,0.00038224465,0.0000012331788],"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":[0.00020449284,0.00096290803,0.9739566,0.000099018784,0.0003023935,0.000005289564,0.000029072553,0.00008543069,0.000013035817,0.023981007,0.0001613961,0.00019939843],"study_design_scores_gemma":[0.0026121135,0.000108324915,0.6374826,0.00021731122,0.00075347896,0.00000121889,0.00018160017,0.00083685416,0.00013975486,0.35742235,0.00005051348,0.0001938975],"about_ca_topic_score_codex":0.0010457626,"about_ca_topic_score_gemma":0.004280078,"teacher_disagreement_score":0.33647397,"about_ca_system_score_codex":0.00008132447,"about_ca_system_score_gemma":0.00020964422,"threshold_uncertainty_score":0.7629357},"labels":[],"label_agreement":null},{"id":"W4412011438","doi":"10.1007/s10654-025-01245-6","title":"Revisiting the hazards of hazard ratios through simulations and case studies","year":2025,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","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":"McGill University; McGill University Health Centre","funders":"National Cancer Institute; Canadian Institutes of Health Research; National Institutes of Health; McGill University","keywords":"Hazard ratio; Proportional hazards model; Medicine; Hazard; Event (particle physics); Econometrics; Statistics; Internal medicine; Confidence interval; Mathematics","score_opus":0.3282653714412905,"score_gpt":0.5058808842061283,"score_spread":0.17761551276483784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412011438","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":[0.30491608,0.00785669,0.6726846,0.009272741,0.00021863227,0.00023518594,0.000008713806,0.000046641246,0.004760697],"genre_scores_gemma":[0.86036485,0.0006599383,0.13811953,0.000613016,0.000154554,7.34571e-7,2.7594527e-7,0.000011314112,0.00007577258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99576676,0.002604415,0.0013163857,0.00010841599,0.000055522854,0.00014847553],"domain_scores_gemma":[0.9845619,0.01370385,0.0010842473,0.00023638955,0.00038801722,0.000025575688],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006408723,0.00011330148,0.0005810758,0.00007230464,0.00012828484,0.0000047155813,0.00015725661,0.000025349931,0.000010413207],"category_scores_gemma":[0.04505282,0.00006853397,0.00008862918,0.00012190382,0.00033149778,0.000121341705,0.0001311588,0.00030443489,6.491179e-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":[0.000078488294,0.000042207812,0.008696378,0.00038387877,0.0007310037,0.001183751,0.0035253204,0.0017363509,0.0014567602,0.92289263,0.013736721,0.045536496],"study_design_scores_gemma":[0.00041991644,0.00025443267,0.0008952139,0.0007437265,0.00024248203,0.0023402697,0.0017159024,0.0006951824,0.00064915227,0.9853642,0.0065469644,0.00013258011],"about_ca_topic_score_codex":0.0000013363485,"about_ca_topic_score_gemma":0.000002612609,"teacher_disagreement_score":0.5554488,"about_ca_system_score_codex":0.00002508188,"about_ca_system_score_gemma":0.000033247303,"threshold_uncertainty_score":0.9629911},"labels":[],"label_agreement":null},{"id":"W4412016582","doi":"10.1007/s10985-025-09663-0","title":"Multi-source analyses of average treatment effects with failure time outcomes","year":2025,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Patient-Centered Outcomes Research Institute","keywords":"Econometrics; Statistics; Computer science; Mathematics","score_opus":0.11227128017266187,"score_gpt":0.4428673142433821,"score_spread":0.33059603407072025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412016582","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":[0.02892142,0.0001184668,0.9687566,0.00022457354,0.00000925339,0.00048600638,0.000700843,0.00036411965,0.00041872213],"genre_scores_gemma":[0.443559,0.00003919291,0.54419607,0.00012029002,0.00001633678,0.00006616609,0.0018343921,0.00004247983,0.010126069],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820185,0.00016288715,0.00049413653,0.0005893112,0.00029130676,0.00026051464],"domain_scores_gemma":[0.99557835,0.0012636532,0.0003145537,0.0026577038,0.00010997117,0.00007576027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023856368,0.00034642153,0.0012038797,0.0006537236,0.000074326155,0.00003945349,0.0007578991,0.00010602191,0.0002653785],"category_scores_gemma":[0.0005678703,0.00023195615,0.00025633673,0.0017594787,0.0001077032,0.00025015333,0.00031741557,0.00010811382,0.000030407806],"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":[0.0007238632,0.011457029,0.52410316,0.0024207635,0.24310781,0.00037396746,0.0022938247,0.018186474,0.12504333,0.008301055,0.030318664,0.03367005],"study_design_scores_gemma":[0.009845711,0.0020878152,0.04870474,0.0012974878,0.16784498,0.0000124121025,0.000699073,0.3800798,0.35321346,0.01603705,0.016018393,0.004159058],"about_ca_topic_score_codex":0.0004147352,"about_ca_topic_score_gemma":0.0004094827,"teacher_disagreement_score":0.47539842,"about_ca_system_score_codex":0.000082161714,"about_ca_system_score_gemma":0.00005402726,"threshold_uncertainty_score":0.9458897},"labels":[],"label_agreement":null},{"id":"W4412063123","doi":"10.1002/pds.70172","title":"High‐Dimensional Disease Risk Score for Dealing With Residual Confounding Bias in Estimating Treatment Effects With a Survival Outcome","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":"BC Centre for Disease Control; Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Confounding; Propensity score matching; Medicine; Hazard ratio; Proportional hazards model; Information bias; Statistics; Residual; Demography; Internal medicine; Selection bias; Confidence interval; Mathematics","score_opus":0.1726632869011169,"score_gpt":0.46878429929867044,"score_spread":0.2961210123975535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412063123","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":[0.71589947,0.0004274956,0.28071946,0.0011300374,0.0001653727,0.0012982099,0.00006816959,0.00021907968,0.00007270462],"genre_scores_gemma":[0.71795815,0.00009469102,0.28120744,0.0002999051,0.000055299344,0.00027011023,0.000030118259,0.00002322652,0.00006105382],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768215,0.00072621874,0.0005975408,0.00048278645,0.00009419473,0.00041712186],"domain_scores_gemma":[0.9772665,0.02201359,0.00031766528,0.00020452122,0.000067438756,0.00013032257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026011425,0.00033185788,0.0007916719,0.000121828845,0.00027745691,0.000009671586,0.00009027377,0.00007325051,0.00000799803],"category_scores_gemma":[0.0037930936,0.00022126937,0.000049609236,0.00010422108,0.00019736595,0.000117836105,0.00006060485,0.0002829047,6.2667203e-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":[0.0046266266,0.00016884641,0.66823304,0.0006229299,0.00027757537,0.00007341725,0.00020926399,0.00944616,0.00011150607,0.30917192,0.00011719588,0.006941527],"study_design_scores_gemma":[0.016656302,0.000905076,0.088434055,0.0025381702,0.0017190013,0.000027014801,0.00013981061,0.1098852,0.003212351,0.77498674,0.00024140421,0.0012548612],"about_ca_topic_score_codex":0.00033961236,"about_ca_topic_score_gemma":0.00027564037,"teacher_disagreement_score":0.579799,"about_ca_system_score_codex":0.00014813372,"about_ca_system_score_gemma":0.00009990111,"threshold_uncertainty_score":0.9023103},"labels":[],"label_agreement":null},{"id":"W4412082903","doi":"10.1093/ije/dyaf114","title":"Balancing scores and causal diagrams","year":2025,"lang":"en","type":"article","venue":"International Journal of Epidemiology","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":"University of British Columbia","funders":"","keywords":"Confounding; Propensity score matching; Medicine; Outcome (game theory); Statistics; Internal medicine; Mathematics","score_opus":0.15563451929346245,"score_gpt":0.49166695294933793,"score_spread":0.3360324336558755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412082903","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":[0.2931044,0.0012161519,0.692425,0.008856602,0.0014931414,0.00009402176,0.0000061930573,0.000056563593,0.0027478966],"genre_scores_gemma":[0.8844368,0.0005037314,0.11293636,0.0016752847,0.0002509579,0.0000037602567,0.000001590936,0.000007582657,0.00018397054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872863,0.00020786376,0.0007074083,0.00010579244,0.000105001534,0.00014527248],"domain_scores_gemma":[0.99342495,0.005606144,0.00047067797,0.00009371001,0.00035548263,0.000049021728],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017917121,0.00009227822,0.00035696992,0.00021291168,0.000021755075,0.000009013345,0.00028201664,0.00008498422,0.00003548843],"category_scores_gemma":[0.017603913,0.00007178164,0.00007072843,0.0000513358,0.00013174073,0.00013469177,0.00010134145,0.00025546746,0.0000013276529],"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":[0.000060614315,0.000037240396,0.09666541,0.000013655742,0.00017208546,0.00004660972,0.000057869234,0.000014470391,0.00097528915,0.86610895,0.010641901,0.025205908],"study_design_scores_gemma":[0.00023090279,0.0000712323,0.011859788,0.00018168268,0.000019356361,0.00017986556,0.00002633766,0.00013314559,0.000827911,0.98196524,0.004446125,0.000058410267],"about_ca_topic_score_codex":0.000015488684,"about_ca_topic_score_gemma":0.000018559098,"teacher_disagreement_score":0.5913324,"about_ca_system_score_codex":0.00008353103,"about_ca_system_score_gemma":0.000053978874,"threshold_uncertainty_score":0.9906712},"labels":[],"label_agreement":null},{"id":"W4412173418","doi":"10.1017/rsm.2025.10021","title":"Regression augmented weighting adjustment for indirect comparisons in health decision modelling","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Computer science; Regression analysis; Econometrics; Statistics; Regression; Machine learning; Mathematics; Medicine","score_opus":0.6488356191652721,"score_gpt":0.6639908171596867,"score_spread":0.01515519799441456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412173418","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":[0.0030607465,0.0011936296,0.9917498,0.0007803959,0.00008686779,0.0016183542,0.000008743772,0.00021390969,0.0012875528],"genre_scores_gemma":[0.01869961,0.0006443611,0.9791272,0.0000341971,0.000033048917,0.0010748217,0.0000028608956,0.000039925893,0.00034396886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99296534,0.0039780857,0.000940424,0.00059054204,0.00061601325,0.0009096197],"domain_scores_gemma":[0.93301773,0.06566726,0.00021752152,0.0006647255,0.00029050972,0.00014226834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02569179,0.00023019801,0.00078989926,0.001185554,0.0003763894,0.00004917974,0.00046741674,0.00017912353,0.000034158766],"category_scores_gemma":[0.025278693,0.00018798995,0.00011976324,0.0011242209,0.00009704023,0.0001416294,0.00029956998,0.00064542115,0.0000022411348],"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":[0.0002827421,0.000394168,0.00014525527,0.0008237957,0.000049296123,0.00000232522,0.00032854968,0.00068316015,0.004548033,0.08255699,0.006626704,0.90355897],"study_design_scores_gemma":[0.0002747535,0.000095785224,0.00005933554,0.0046778857,0.000010952646,6.9934754e-7,0.00049506524,0.20328973,0.15822382,0.62682295,0.0058766264,0.00017239373],"about_ca_topic_score_codex":0.00010353154,"about_ca_topic_score_gemma":0.00004372301,"teacher_disagreement_score":0.9033866,"about_ca_system_score_codex":0.000982528,"about_ca_system_score_gemma":0.00032284865,"threshold_uncertainty_score":0.9829318},"labels":[],"label_agreement":null},{"id":"W4412388536","doi":"10.1002/cjs.70016","title":"A class of directed acyclic graphs with mixed data types in mediation analysis","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institutes of Health","keywords":"Directed acyclic graph; Class (philosophy); Mixed graph; Mediation; Computer science; Mathematics; Combinatorics; Sociology; Artificial intelligence; Graph; Line graph","score_opus":0.07980555718791991,"score_gpt":0.360890885522459,"score_spread":0.2810853283345391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412388536","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":[0.12884234,0.00027877366,0.8677082,0.0003032874,0.00013795924,0.00020978649,0.0015784081,0.000025713898,0.000915557],"genre_scores_gemma":[0.77223986,0.0000453223,0.22757252,0.00002647451,0.000007507053,0.0000013751514,0.00005951461,0.000008518229,0.000038921098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900806,0.000069751404,0.000508044,0.000100496225,0.00015624285,0.0001574141],"domain_scores_gemma":[0.99813294,0.00059920846,0.00041540395,0.0003296713,0.00038903163,0.0001337361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035835392,0.00009292446,0.00037402392,0.0010693546,0.000025571575,0.000016944236,0.00033851905,0.000056004807,0.000037804217],"category_scores_gemma":[0.0019527746,0.000079991885,0.000024942521,0.0012646087,0.00010187209,0.00012991857,0.000016752503,0.0001868999,2.6571382e-7],"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":[0.00013306117,0.00014248567,0.30030984,0.00037483496,0.0024348514,0.0005039215,0.0013152873,0.00060780725,0.00039507405,0.6381445,0.03535887,0.020279508],"study_design_scores_gemma":[0.00089867215,0.00025172892,0.10820939,0.00044138014,0.0016400808,0.000015840056,0.0005446773,0.0074226577,0.00085453154,0.8779808,0.0014149499,0.00032524826],"about_ca_topic_score_codex":0.0016599781,"about_ca_topic_score_gemma":0.28707433,"teacher_disagreement_score":0.6433975,"about_ca_system_score_codex":0.0001245046,"about_ca_system_score_gemma":0.00091168174,"threshold_uncertainty_score":0.7259347},"labels":[],"label_agreement":null},{"id":"W4412424131","doi":"10.1002/sim.70038","title":"Natural Effects in the Presence of an Intermediate Confounder: Evaluation of Pragmatic Estimation Strategies With an Emphasis on the Relationship Between Natural and Interventional Effects","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","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; McGill University Health Centre; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Estimator; Confounding; Outcome (game theory); Natural (archaeology); Econometrics; Statistics; Mediation; Computer science; Mathematics; Biology","score_opus":0.09314129423726326,"score_gpt":0.47612402867371983,"score_spread":0.3829827344364566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412424131","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":[0.8344435,0.00010003324,0.16390696,0.00017100146,0.00006652447,0.0011485132,0.000013240179,0.000016068301,0.00013414313],"genre_scores_gemma":[0.96660066,0.000002849853,0.03315113,0.000029199551,0.000013275293,0.00011329869,0.00007780324,0.000006958016,0.0000048177117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976603,0.0010496343,0.00046031305,0.00015141406,0.0005713951,0.00010696311],"domain_scores_gemma":[0.9793888,0.019834824,0.00028987686,0.00026268704,0.00020827004,0.00001555528],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029233678,0.0001320999,0.00027899144,0.00020708088,0.000042067004,0.000016440112,0.00019742157,0.000047487592,0.0000040875916],"category_scores_gemma":[0.014405873,0.000072399875,0.000010428044,0.00029830594,0.00045120798,0.00022060992,0.000023820234,0.00034984486,9.399036e-8],"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":[0.00008609254,0.00010663759,0.01086097,0.0012113071,0.0000270536,0.0000033322847,0.0035702486,0.00011214907,0.00011243291,0.97214234,0.00004024093,0.011727196],"study_design_scores_gemma":[0.00068583037,0.00070414745,0.31246504,0.0021482217,0.00009136491,0.000001313285,0.001154188,0.02917117,0.00019778479,0.6533351,8.880677e-8,0.000045766486],"about_ca_topic_score_codex":0.000042190713,"about_ca_topic_score_gemma":0.00036278894,"teacher_disagreement_score":0.31880724,"about_ca_system_score_codex":0.00006873897,"about_ca_system_score_gemma":0.00008622258,"threshold_uncertainty_score":0.9938962},"labels":[],"label_agreement":null},{"id":"W4412435511","doi":"10.1016/s2352-4642(25)00131-2","title":"Target trial emulation in paediatric research: how can causal effects be estimated from observational data?","year":2025,"lang":"en","type":"review","venue":"The Lancet Child & Adolescent Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","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":"Women's College Hospital; Hospital for Sick Children; Toronto Rehabilitation Institute; SickKids Foundation; University of Toronto; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Observational study; Emulation; Randomized controlled trial; Causal inference; Observational methods in psychology; Medicine; Clinical trial; Medical physics; Computer science; Data science; Psychology; Surgery; Pathology","score_opus":0.6773655559287957,"score_gpt":0.55709968852989,"score_spread":0.12026586739890566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412435511","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":[0.00004697893,0.96939945,0.0033336156,0.012105335,0.00085464824,0.010247638,0.003338818,0.00056857616,0.00010496466],"genre_scores_gemma":[0.00020063411,0.9678534,0.0178054,0.001007717,0.0040190597,0.0003968814,0.008561203,0.00010723717,0.000048413407],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913146,0.004028792,0.0013017756,0.0010544534,0.0011433525,0.001157025],"domain_scores_gemma":[0.98975,0.006220026,0.0010484174,0.0026158185,0.0001728827,0.00019284457],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0057781064,0.0006804881,0.003203861,0.00053271523,0.00038942514,0.0001380348,0.0020397452,0.0004500677,0.00001681381],"category_scores_gemma":[0.0061185244,0.0004961081,0.00018661487,0.0016643194,0.00014029544,0.00022280421,0.0009392795,0.004321531,0.000008569573],"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":[0.0020313754,0.0016149277,0.00069903117,0.12799291,0.00033175916,0.00004705851,0.0007193144,0.00005667223,3.0985137e-7,0.051449865,0.33254302,0.48251376],"study_design_scores_gemma":[0.01375377,0.00047897678,0.0016959348,0.14168546,0.0005504084,0.000011243956,0.00004611879,0.0012301122,0.0000029226094,0.135639,0.70337665,0.001529436],"about_ca_topic_score_codex":0.00050207536,"about_ca_topic_score_gemma":0.00097183284,"teacher_disagreement_score":0.4809843,"about_ca_system_score_codex":0.0012194164,"about_ca_system_score_gemma":0.0024975827,"threshold_uncertainty_score":0.99974906},"labels":[],"label_agreement":null},{"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":"W4412493510","doi":"10.1038/s41746-025-01821-w","title":"Negative control-calibrated difference-in-difference analyses: addressing unmeasured confounding in RWD with application to racial/ethnic differences","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Advanced Causal Inference Techniques","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":"University of Toronto","funders":"National Center for Advancing Translational Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Eye Institute; National Institute of Mental Health; U.S. National Library of Medicine; Patient-Centered Outcomes Research Institute; National Institute on Aging; National Institutes of Health","keywords":"Confounding; Ethnic group; Causal inference; Health records; Health equity; Control (management); Health care; Medicine; Psychology; Computer science; Statistics; Mathematics; Public health; Artificial intelligence; Nursing; Internal medicine","score_opus":0.19159917289522901,"score_gpt":0.4660973734039519,"score_spread":0.27449820050872287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412493510","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":[0.5851677,0.00014789762,0.40581015,0.000751872,0.0000646813,0.0013772418,0.00001798151,0.0003094015,0.006353071],"genre_scores_gemma":[0.9964132,0.000019487685,0.0023734826,0.00036986303,0.000051311737,0.0004064519,0.000020462465,0.000032178345,0.00031361447],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99714446,0.00015136234,0.0009116132,0.00067495677,0.0005649578,0.0005526217],"domain_scores_gemma":[0.9966749,0.0020683974,0.00032505838,0.0005109258,0.00024636014,0.00017436793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003668761,0.00046826896,0.0011362974,0.0007723429,0.00007772416,0.00010500502,0.00046748464,0.00018279617,0.00002501368],"category_scores_gemma":[0.003077459,0.00033532697,0.0000461766,0.002174338,0.00040067284,0.00039492248,0.00008882007,0.00049264304,0.0000049185664],"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":[0.0035130477,0.0016964298,0.25209665,0.001202514,0.0005488937,0.00019561735,0.015587582,0.0003609693,0.23930357,0.20402034,0.00026410978,0.28121027],"study_design_scores_gemma":[0.006953993,0.0012472301,0.3124357,0.011345692,0.00020335455,0.000009511136,0.0040230122,0.007431225,0.012154855,0.6429501,0.000039344304,0.0012059393],"about_ca_topic_score_codex":0.00018700378,"about_ca_topic_score_gemma":0.0010583458,"teacher_disagreement_score":0.4389298,"about_ca_system_score_codex":0.0003272925,"about_ca_system_score_gemma":0.00016739343,"threshold_uncertainty_score":0.9999099},"labels":[],"label_agreement":null},{"id":"W4412527389","doi":"10.1002/sim.70194","title":"A Simple Diagnostic for the Positivity Assumption for Continuous Exposures","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"HEC Montréal; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Simple (philosophy); Statistics; Computer science; Econometrics; Mathematics","score_opus":0.0848985461080552,"score_gpt":0.46413627148375325,"score_spread":0.37923772537569805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412527389","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":[0.0015947967,0.00023346311,0.99454427,0.00097453455,0.00020670003,0.0017498469,0.00033852493,0.000083581144,0.00027431094],"genre_scores_gemma":[0.58294725,0.00017541408,0.41353422,0.00062837714,0.00019266742,0.0018044023,0.0001267089,0.000031690543,0.0005592707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990491,0.00005098333,0.0003661781,0.00017520139,0.0001345917,0.0002239363],"domain_scores_gemma":[0.9635839,0.03583392,0.00011576529,0.00024693515,0.00019571585,0.000023792209],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009440454,0.00012992369,0.0003162543,0.00008418414,0.00010092508,0.000010803787,0.00015407884,0.00006222076,0.000020808904],"category_scores_gemma":[0.031756174,0.00008882949,0.000024833716,0.00011824378,0.00017095104,0.000033364966,0.000031066586,0.00013001873,5.103427e-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":[0.00005875695,0.00005214388,0.001265501,0.00025435627,0.000027608965,0.0000033583115,0.00020586571,0.0000070509122,0.00053438253,0.9027185,0.07061793,0.024254547],"study_design_scores_gemma":[0.0008782601,0.00031682666,0.0032160762,0.000230802,0.00011463896,9.4324554e-7,0.00024389933,0.0020697417,0.0009659994,0.987769,0.004104732,0.0000890877],"about_ca_topic_score_codex":0.00005346413,"about_ca_topic_score_gemma":0.00039772002,"teacher_disagreement_score":0.5813525,"about_ca_system_score_codex":0.0000761106,"about_ca_system_score_gemma":0.000037751102,"threshold_uncertainty_score":0.9763998},"labels":[],"label_agreement":null},{"id":"W4412611378","doi":"10.1080/03610918.2025.2534890","title":"Estimating average treatment effect using multiple imputation for handling confounder missingness","year":2025,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","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":"University of Calgary; McGill University","funders":"","keywords":"Missing data; Imputation (statistics); Confounding; Statistics; Econometrics; Computer science; Mathematics","score_opus":0.350366369946548,"score_gpt":0.5625194638831538,"score_spread":0.21215309393660575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412611378","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":[0.039532248,0.000113369264,0.95890135,0.000042476735,0.00008565494,0.0010506898,0.00005628329,0.0001255294,0.00009242843],"genre_scores_gemma":[0.52492934,0.000008434996,0.4747521,0.000017650638,0.000007501114,0.00006766828,0.00019561866,0.000011163009,0.00001054144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880207,0.00020370408,0.0005325886,0.00021744118,0.00009263013,0.00015156886],"domain_scores_gemma":[0.9900196,0.009103076,0.0002454935,0.00033555485,0.0002658569,0.000030400455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039923567,0.0001817502,0.00027400794,0.00024575792,0.00041945948,0.00011425276,0.00012332908,0.00008443739,0.0000021280941],"category_scores_gemma":[0.0013911751,0.00018684962,0.00003042579,0.00025032918,0.00009490868,0.000178757,0.000068699286,0.00009910498,3.993066e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044779572,0.000106517364,0.0022242842,0.00016957932,0.000027110438,3.876059e-7,0.00074311724,0.74513954,0.00017778511,0.06259113,0.00001014508,0.18876562],"study_design_scores_gemma":[0.0009191238,0.000056327244,0.0003874678,0.0001946152,0.00004405592,6.956586e-7,0.000048651713,0.7133978,0.0000987133,0.28470218,0.00003937948,0.00011098995],"about_ca_topic_score_codex":0.000056143403,"about_ca_topic_score_gemma":0.000063780346,"teacher_disagreement_score":0.48539707,"about_ca_system_score_codex":0.00031275986,"about_ca_system_score_gemma":0.00007581108,"threshold_uncertainty_score":0.7619506},"labels":[],"label_agreement":null},{"id":"W4412862751","doi":"10.1007/s43441-025-00849-0","title":"Real-World Data and Causal Machine Learning to Enhance Drug Development","year":2025,"lang":"en","type":"review","venue":"Therapeutic Innovation & Regulatory Science","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":"University of British Columbia","funders":"Sanofi","keywords":"Pharmacy; Drug development; Computer science; Drug; Data science; Machine learning; Artificial intelligence; Pharmacology; Medicine; Family medicine","score_opus":0.21358238904276414,"score_gpt":0.4842258044071093,"score_spread":0.2706434153643451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412862751","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":[0.0012428378,0.9151228,0.07184164,0.0002858518,0.0006476175,0.004417533,0.00007832828,0.001717297,0.0046461136],"genre_scores_gemma":[0.0012854447,0.8360283,0.14854002,0.00041321246,0.00011267938,0.00027615894,0.00019674483,0.00011236696,0.013035101],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996093,0.00017824977,0.0012101699,0.0011918315,0.0007997315,0.0005270487],"domain_scores_gemma":[0.996296,0.0006305325,0.0008605366,0.0016392942,0.00048312542,0.00009049338],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0047152364,0.0005293018,0.0011337927,0.0017331819,0.0005228164,0.00015914967,0.0017477163,0.00009990492,0.00002644647],"category_scores_gemma":[0.00070924463,0.00045815206,0.00003258946,0.0073741265,0.00062518974,0.00054894335,0.0012454963,0.00062428863,0.00001841138],"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":[0.0000029676366,0.000019086387,0.00001001477,0.0019826267,0.000024854477,0.0000011381001,0.00023026628,4.6525346e-7,0.000088774716,0.08643987,0.00012627731,0.9110737],"study_design_scores_gemma":[0.000045831857,0.000031938827,0.000050470768,0.0074076233,0.000108603395,0.000007088799,0.0000341087,0.000086778804,0.0008521,0.01597959,0.9746942,0.0007016476],"about_ca_topic_score_codex":0.000017330227,"about_ca_topic_score_gemma":0.000090378184,"teacher_disagreement_score":0.97456795,"about_ca_system_score_codex":0.0005363467,"about_ca_system_score_gemma":0.0019880992,"threshold_uncertainty_score":0.99978703},"labels":[],"label_agreement":null},{"id":"W4413024598","doi":"10.1002/pst.70029","title":"Target Aggregate Data Adjustment Method for Transportability Analysis Utilizing Summary‐Level Data From the Target Population","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","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":"McMaster University; University of British Columbia; York University; Centre for Advancing Health Outcomes; Impact; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Censoring (clinical trials); Interpretability; Computer science; Weighting; Causal inference; Population; Statistics; Aggregate data; Statistical inference; Inference; Inverse probability weighting; Econometrics; Data mining; Estimator; Artificial intelligence; Mathematics; Medicine","score_opus":0.513051299481403,"score_gpt":0.5578152948638562,"score_spread":0.044763995382453126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413024598","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":[0.00016097771,0.00051147415,0.90627193,0.0006918149,0.00018910013,0.001079428,0.09076774,0.00020721914,0.00012032456],"genre_scores_gemma":[0.02206435,0.0002126538,0.94603753,0.0006672596,0.000099124154,0.000088252265,0.03071651,0.00003446834,0.000079852194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967419,0.00039375178,0.00093774544,0.0009909213,0.0004408203,0.00049486774],"domain_scores_gemma":[0.98808014,0.008619275,0.00026657083,0.0026903932,0.00019748896,0.00014614615],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022952245,0.00034186267,0.00066929555,0.00008520847,0.00024533583,0.00007005839,0.0018508882,0.00012644735,0.00041915776],"category_scores_gemma":[0.0039249784,0.00026660706,0.00009512868,0.00061916607,0.00013480717,0.00035343075,0.000675447,0.00041790944,0.0000032228704],"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":[0.00073832145,0.0011866787,0.045884773,0.00088728283,0.0052211727,0.000018491413,0.00031136983,0.00046950436,0.00052265363,0.69278115,0.11516026,0.13681832],"study_design_scores_gemma":[0.00035051725,0.000012489073,0.0043354505,0.000032606917,0.0028015333,2.0501734e-7,0.000043459528,0.43915883,0.0007807065,0.53401065,0.018262453,0.00021109016],"about_ca_topic_score_codex":0.00050677615,"about_ca_topic_score_gemma":0.0005856783,"teacher_disagreement_score":0.43868932,"about_ca_system_score_codex":0.00014237904,"about_ca_system_score_gemma":0.000100721394,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W4413113797","doi":"10.1007/s40264-025-01597-8","title":"The Extent and Magnitude of Bias in Case-Crossover Studies of Real-World Non-transient Medications Patterns: A Simulation Study with Real-World Examples","year":2025,"lang":"en","type":"article","venue":"Drug Safety","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":"University of Toronto","funders":"","keywords":"Medicine; Crossover study; Statistics; Logistic regression; Magnitude (astronomy); Crossover; Cohort; Cohort study; Econometrics; Internal medicine; Mathematics; Computer science; Artificial intelligence; Pathology","score_opus":0.13412218584066074,"score_gpt":0.4441656779692209,"score_spread":0.3100434921285602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413113797","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":[0.98733187,0.00012161927,0.009197869,0.00031726758,0.00003294952,0.0015279229,0.000046739846,0.00006578114,0.0013579663],"genre_scores_gemma":[0.99534774,0.000776708,0.003286143,0.000017517617,0.00000830762,0.00014009404,0.000004573573,0.000015818363,0.00040310292],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99831885,0.00018261702,0.0007769427,0.00025359006,0.00028661088,0.00018137955],"domain_scores_gemma":[0.99470574,0.0041177506,0.00033880826,0.0005186023,0.0002891082,0.000030018431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011429883,0.00018073099,0.0004377965,0.00022779452,0.00014993582,0.000012619339,0.00014389865,0.000026458878,0.000006169232],"category_scores_gemma":[0.00027081856,0.00011833091,0.000035808505,0.000547995,0.00026638794,0.00010461275,0.00011386094,0.00015400178,1.7406602e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001279927,0.0030576754,0.7632357,0.0021246837,0.0012621033,0.00017612707,0.0743034,0.005187073,0.00037798,0.1314342,0.00043455817,0.0171266],"study_design_scores_gemma":[0.002655518,0.0003581842,0.90302336,0.0020766202,0.00047160644,0.0000064777423,0.04187288,0.0019921258,0.0022858393,0.04457565,0.00027012645,0.00041160893],"about_ca_topic_score_codex":0.0029256165,"about_ca_topic_score_gemma":0.12548447,"teacher_disagreement_score":0.13978769,"about_ca_system_score_codex":0.0001175017,"about_ca_system_score_gemma":0.00006232694,"threshold_uncertainty_score":0.8904731},"labels":[],"label_agreement":null},{"id":"W4413214703","doi":"10.15695/jstem/v8i1.05","title":"Testing the Efficacy of Educational Interventions on Matched Student Samples: A Primer for Propensity Score Matching in R","year":2025,"lang":"en","type":"article","venue":"The Journal of STEM Outreach","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 Manitoba","funders":"National Institutes of Health","keywords":"Propensity score matching; Matching (statistics); Psychological intervention; Primer (cosmetics); Psychology; Internal medicine; Statistics; Computer science; Medicine; Mathematics; Chemistry","score_opus":0.3755214620628621,"score_gpt":0.4685429570865438,"score_spread":0.09302149502368173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413214703","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":[0.9728361,0.00011423081,0.024341796,0.0014369813,0.00007593011,0.0008079775,0.0000066324837,0.000012400668,0.00036794727],"genre_scores_gemma":[0.98479575,0.0000052006867,0.014907901,0.000046680143,0.00003977361,0.00002209786,8.720151e-7,0.0000115426365,0.0001702072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99869,0.00017527542,0.0007247252,0.00007494413,0.00021055176,0.00012451963],"domain_scores_gemma":[0.99281096,0.0059091314,0.0006877845,0.0002559271,0.0003176365,0.000018581932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019414296,0.00010936674,0.00030522543,0.00012495073,0.00009438924,0.000022173974,0.00044355332,0.00003233878,0.000006677266],"category_scores_gemma":[0.0009127718,0.00005733811,0.00013698416,0.00020497703,0.00006271999,0.00008645399,0.00009132201,0.0002861847,6.181739e-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":[0.0021014756,0.009938288,0.22696806,0.0031699666,0.0014724629,0.000006495036,0.04189168,0.0020699552,0.043662034,0.61185974,0.0049916245,0.05186822],"study_design_scores_gemma":[0.0015237444,0.0005899815,0.34845224,0.009614717,0.00040736445,0.00004673931,0.005110171,0.000037435384,0.010370194,0.6236252,0.000037573016,0.00018463458],"about_ca_topic_score_codex":0.00003266652,"about_ca_topic_score_gemma":0.000028216411,"teacher_disagreement_score":0.12148417,"about_ca_system_score_codex":0.00013343003,"about_ca_system_score_gemma":0.00012988047,"threshold_uncertainty_score":0.23381802},"labels":[],"label_agreement":null},{"id":"W4413251260","doi":"10.3389/jpps.2025.14587","title":"A review to determine regulatorily and reimbursement successes of studies conducted using data from Canadian patient support programs based on the real-world evidence guidelines published by Canadian drug agency and health Canada","year":2025,"lang":"en","type":"review","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reimbursement; Checklist; Guideline; Medicine; Transparency (behavior); Agency (philosophy); Health care; Family medicine; Computer science; Psychology; Political science","score_opus":0.7435917888039851,"score_gpt":0.6146929825048406,"score_spread":0.12889880629914452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413251260","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":[0.00031674572,0.97379404,0.000019773806,0.02270097,0.00039677354,0.0021850355,0.0005273321,0.000014453104,0.000044880308],"genre_scores_gemma":[0.0014281634,0.98544943,0.0057408884,0.0071713976,0.000093113114,0.000045489604,0.00002758591,0.000023406994,0.000020543977],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941158,0.0007364695,0.00258618,0.0006995524,0.0011208446,0.00074113184],"domain_scores_gemma":[0.9926973,0.002407815,0.00181109,0.000633762,0.0010431602,0.0014068506],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005810688,0.0005540502,0.002088366,0.00053256145,0.00040644043,0.00017282464,0.0017437644,0.000045883517,0.00013408702],"category_scores_gemma":[0.005017646,0.0003356549,0.00011360961,0.0016531841,0.00045873242,0.0006139722,0.00036282532,0.0006143594,1.7645688e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114934755,0.000051968596,0.00025307506,0.020790286,0.00020462743,0.000062985266,0.00007665196,0.000001746806,0.000007915669,0.00014112875,0.26212022,0.7162779],"study_design_scores_gemma":[0.00013606533,0.00013652227,0.0000026460089,0.10664285,0.00097506586,0.000019483328,0.00007321393,0.0003074237,0.00007779542,0.00032422936,0.8909652,0.00033949572],"about_ca_topic_score_codex":0.94161844,"about_ca_topic_score_gemma":0.9789426,"teacher_disagreement_score":0.7159384,"about_ca_system_score_codex":0.001493668,"about_ca_system_score_gemma":0.02577609,"threshold_uncertainty_score":0.9999095},"labels":[],"label_agreement":null},{"id":"W4413374629","doi":"10.1093/aje/kwaf182","title":"Use of causal inference methods in case–control studies: a methodology review","year":2025,"lang":"en","type":"review","venue":"American Journal of Epidemiology","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":"AstraZeneca (Canada); Université de Montréal; Statistics Canada; Institut National de la Recherche Scientifique","funders":"","keywords":"Causal inference; Covariate; Inverse probability weighting; Inference; Propensity score matching; Statistics; Weighting; Confounding; Estimator; Econometrics; Computer science; Medicine; Artificial intelligence; Mathematics","score_opus":0.7751389073668156,"score_gpt":0.6853217108520706,"score_spread":0.08981719651474496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413374629","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":[8.912955e-7,0.61261666,0.38638008,0.00019469902,0.00016949646,0.0005699167,0.000031766165,0.000019178107,0.00001731077],"genre_scores_gemma":[6.983356e-7,0.52100384,0.47819057,0.0006429529,0.000043081305,0.00007214927,0.0000013599353,0.000027232847,0.000018140054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9378151,0.0528172,0.007928539,0.0005645384,0.00015575744,0.00071884866],"domain_scores_gemma":[0.63584864,0.35040906,0.011944834,0.0008680818,0.00077951053,0.0001498695],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03739278,0.0007777655,0.020773206,0.0011955454,0.000031142874,0.0000030646713,0.00080458686,0.00042767898,0.000044112294],"category_scores_gemma":[0.46723104,0.0005370921,0.0013756204,0.0014073388,0.001400406,0.0001746698,0.0002821157,0.002134607,0.000001253091],"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":[0.000023214026,0.000056026187,0.000038566348,0.03532591,0.0012735659,0.00060369726,0.00005875658,0.0000045832953,7.0810574e-7,0.014491049,0.0013215519,0.9468024],"study_design_scores_gemma":[0.00031243722,0.0023921744,0.0000031093653,0.27166256,0.009621788,0.013037836,0.00021617561,0.0000098264,0.0000025234667,0.25846684,0.44344187,0.0008328604],"about_ca_topic_score_codex":0.00015386751,"about_ca_topic_score_gemma":0.000057545585,"teacher_disagreement_score":0.9459695,"about_ca_system_score_codex":0.00042560088,"about_ca_system_score_gemma":0.0010423952,"threshold_uncertainty_score":0.99970806},"labels":[],"label_agreement":null},{"id":"W4413452402","doi":"10.31234/osf.io/rqexa_v1","title":"Think outside the box: Making up causal hypotheses from unreliable evidence","year":2025,"lang":"en","type":"article","venue":"","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":"Dalhousie University","funders":"Dalhousie University","keywords":"Psychology; Econometrics; Data science; Epistemology; Computer science; Economics; Philosophy","score_opus":0.26856933784134346,"score_gpt":0.4539863764565206,"score_spread":0.18541703861517717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413452402","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":[0.016219772,0.0009215986,0.8778642,0.0036873315,0.00063621916,0.0008089853,0.000013389594,0.0019374299,0.09791111],"genre_scores_gemma":[0.7874225,0.00013531926,0.19015878,0.0024177816,0.00008756727,0.000067033325,0.0000012418712,0.000035029647,0.019674744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985677,0.00010542442,0.00038225783,0.00033369634,0.0002772106,0.0003336864],"domain_scores_gemma":[0.992804,0.006003413,0.00013006052,0.00090896455,0.000120656645,0.00003293991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048904796,0.0002271627,0.00028572138,0.00007085138,0.0001975223,0.00012497064,0.00063504546,0.00011957504,0.0005910054],"category_scores_gemma":[0.004006795,0.00014351428,0.00008036843,0.00026894768,0.0001301955,0.0003678543,0.0003128705,0.00032764045,0.000081666636],"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":[0.0000329689,0.000043830387,0.00083962677,0.000057995883,0.00007650686,0.000010397462,0.0010308967,0.000015508276,0.0059165633,0.9184613,0.06878585,0.004728502],"study_design_scores_gemma":[0.000073715615,0.00002409413,0.0002908426,0.0007626737,0.000056096007,0.0000017122418,0.0008885719,0.00031964594,0.03970184,0.9543895,0.0033099935,0.00018128243],"about_ca_topic_score_codex":0.000410805,"about_ca_topic_score_gemma":0.00028631478,"teacher_disagreement_score":0.77120274,"about_ca_system_score_codex":0.00011089898,"about_ca_system_score_gemma":0.00010450971,"threshold_uncertainty_score":0.64710945},"labels":[],"label_agreement":null},{"id":"W4413696582","doi":"10.1097/ede.0000000000001902","title":"Is Checking for Sequential Positivity Violations Getting You Down? Try sPoRT!","year":2025,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; McGill University Health Centre; Université de Montréal","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada; National Institute of Child Health and Human Development; Institut de Valorisation des Données; National Institute on Drug Abuse; National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism; National Institute of Allergy and Infectious Diseases; National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; Fogarty International Center; National Heart, Lung, and Blood Institute","keywords":"Computer science","score_opus":0.27364992656943876,"score_gpt":0.5105732487689053,"score_spread":0.23692332219946655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413696582","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":[0.07222003,0.00011280065,0.9166973,0.0047773635,0.0002446624,0.0005544109,0.000035906058,0.00044188977,0.004915612],"genre_scores_gemma":[0.66825175,0.000016640293,0.32770833,0.0027672693,0.00018553316,0.00019064013,0.000034458495,0.000022226039,0.0008231602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998286,0.00016656914,0.0006773294,0.00038245364,0.000047944584,0.00043971598],"domain_scores_gemma":[0.99483395,0.004296928,0.00031930543,0.000388592,0.0001126407,0.000048583974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021467204,0.00018295577,0.0005921904,0.00012269751,0.00019273895,0.0000075454545,0.00018242894,0.00026580013,0.00006343904],"category_scores_gemma":[0.0068995757,0.00017619476,0.00017710983,0.00014752476,0.00010687992,0.00013427544,0.00010734185,0.0003130644,0.000006243495],"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":[0.000028612729,0.000054894157,0.03514116,0.000107921776,0.00007086237,0.0000022928652,0.00015242516,0.000018732715,0.0031233018,0.9469409,0.00927184,0.005087084],"study_design_scores_gemma":[0.00018534176,0.000048880935,0.003279639,0.00009646353,0.000060650145,0.000005884088,0.000038254104,0.0020381766,0.007619971,0.9821357,0.0043193977,0.00017161628],"about_ca_topic_score_codex":0.0000540819,"about_ca_topic_score_gemma":0.000024519955,"teacher_disagreement_score":0.5960317,"about_ca_system_score_codex":0.00012015453,"about_ca_system_score_gemma":0.00007347228,"threshold_uncertainty_score":0.8259935},"labels":[],"label_agreement":null},{"id":"W4413981169","doi":"10.1136/heartjnl-2025-326218","title":"Benefit–risk of colchicine and spironolactone in acute myocardial infarction: a prespecified generalised pairwise comparisons analysis of the CLEAR trial","year":2025,"lang":"en","type":"article","venue":"Heart","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":"London Health Sciences Centre; Southlake Regional Health Center; Genome Prairie; Health Sciences Centre; Centre Hospitalier Universitaire de Sherbrooke; Sunnybrook Health Science Centre; University of Ottawa; Hamilton Health Sciences; Population Health Research Institute","funders":"Institute of Circulatory and Respiratory Health; Canadian Institutes of Health Research; Boston Scientific Corporation; Population Health Research Institute","keywords":"Medicine; Spironolactone; Myocardial infarction; Internal medicine; Placebo; Stroke (engine); Relative risk; Cardiology; Heart failure; Confidence interval","score_opus":0.08060094350871745,"score_gpt":0.3891539290421738,"score_spread":0.30855298553345634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413981169","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":[0.99534976,0.00006178057,0.002942202,0.00040027525,0.00006994013,0.00067080976,0.000041967232,0.000040168212,0.00042311772],"genre_scores_gemma":[0.991567,0.0001068473,0.008057506,0.000072878756,0.000023269567,0.000039325536,0.0000038925878,0.000008873214,0.0001203782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988139,0.00016441198,0.00052991346,0.0001829924,0.00017478615,0.00013394398],"domain_scores_gemma":[0.99880946,0.0003916044,0.00021207135,0.00047832308,0.00008018716,0.000028363856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039438432,0.00011995553,0.00064731593,0.00028763263,0.000044259767,0.000008412081,0.000116218456,0.00009876413,0.00003414415],"category_scores_gemma":[0.00022108654,0.00009157494,0.00018135073,0.0008223757,0.00013283316,0.00005611864,0.00010006343,0.00020256048,2.3969727e-7],"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":[0.042011127,0.00190319,0.7285405,0.00032185134,0.008642667,0.0000038314165,0.0032384656,0.0036647846,0.05876874,0.13103276,0.019685963,0.0021861568],"study_design_scores_gemma":[0.026411327,0.0010261469,0.82901776,0.00028149382,0.0064198957,0.0000020320253,0.00043523923,0.009413913,0.044428617,0.0771035,0.005004787,0.0004552802],"about_ca_topic_score_codex":0.000267047,"about_ca_topic_score_gemma":0.00054993114,"teacher_disagreement_score":0.100477315,"about_ca_system_score_codex":0.000039258124,"about_ca_system_score_gemma":0.00004069369,"threshold_uncertainty_score":0.37343177},"labels":[],"label_agreement":null},{"id":"W4413983884","doi":"10.1001/jamanetworkopen.2025.30277","title":"Design, Conduct, and Analysis of Externally Controlled Trials","year":2025,"lang":"en","type":"article","venue":"JAMA Network Open","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":"McMaster University; Impact","funders":"National Science Fund for Distinguished Young Scholars; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"External validity; Randomized controlled trial; Medicine; Research design; Selection bias; Clinical trial; Clinical study design; Covariate; Transparency (behavior); Protocol (science); Publication bias; Data collection; Meta-analysis; Medical physics; Statistics; Psychology; Alternative medicine; Computer science; Surgery; Internal medicine; Social psychology","score_opus":0.34572509597844836,"score_gpt":0.4984841668945698,"score_spread":0.15275907091612145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413983884","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":[0.02550502,0.0009957344,0.95553,0.0006245702,0.00008212163,0.0029413274,0.000013210678,0.000102298436,0.014205756],"genre_scores_gemma":[0.54459506,0.00039858886,0.4501965,0.0006403854,0.00008327943,0.00039716702,0.000010505795,0.00002232978,0.0036561626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99725175,0.0010901523,0.0010716585,0.00024257947,0.0001437206,0.00020011833],"domain_scores_gemma":[0.98941404,0.009212168,0.00072250934,0.0004264135,0.00018003609,0.000044807643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008502855,0.00016934308,0.002445756,0.00019313426,0.00005938082,0.0001563717,0.0004956059,0.000121178804,0.00022379754],"category_scores_gemma":[0.0044671213,0.000121531724,0.00020844988,0.0007819668,0.00006859981,0.00022498785,0.00033374567,0.00013339738,9.302956e-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":[0.0069649946,0.00027006125,0.008623268,0.00013015418,0.01857236,0.000021134836,0.0004625842,0.0028112154,0.0054694875,0.8642164,0.053686097,0.038772233],"study_design_scores_gemma":[0.004476837,0.0001538593,0.0020317324,0.00038353002,0.0049097342,8.9183555e-7,0.000056980254,0.008712378,0.0033801638,0.97493774,0.0007366946,0.00021946205],"about_ca_topic_score_codex":0.000032117357,"about_ca_topic_score_gemma":0.00003472142,"teacher_disagreement_score":0.51909006,"about_ca_system_score_codex":0.000027525663,"about_ca_system_score_gemma":0.00007219884,"threshold_uncertainty_score":0.5347884},"labels":[],"label_agreement":null},{"id":"W4414120871","doi":"10.1007/s40487-025-00366-y","title":"A Practical Approach to Understanding Real-World Study Methodology in Cancer Research: A Vodcast","year":2025,"lang":"en","type":"article","venue":"Oncology and Therapy","topic":"Advanced Causal Inference Techniques","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":"University of Calgary","funders":"Pfizer","keywords":"Sample size determination; Research design; MEDLINE; Clinical Practice; Evidence-based medicine; Statistical analysis; Clinical trial; Statistical model","score_opus":0.8987679318139231,"score_gpt":0.6867908155549045,"score_spread":0.2119771162590186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414120871","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":[0.31065696,0.0002418073,0.49876392,0.016441766,0.0002445328,0.004206189,0.0000043957,0.0003035849,0.16913687],"genre_scores_gemma":[0.7867468,0.00090437423,0.20952336,0.00059351977,0.00004300161,0.0009976458,6.4131984e-7,0.000019458683,0.0011712167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971093,0.0018149422,0.00025944333,0.00035183664,0.00012067044,0.00034383536],"domain_scores_gemma":[0.9945526,0.005044349,0.000053640873,0.00023515952,0.000055081746,0.000059153557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040805903,0.00012251636,0.00040525384,0.00053844444,0.00012654415,0.000016492539,0.000129546,0.00015219656,0.00003329938],"category_scores_gemma":[0.00065432914,0.00010255766,0.000019427309,0.00078769226,0.00019063342,0.000073898074,0.000117756805,0.00061559974,0.0000013152289],"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":[0.0005872799,0.0011434254,0.004225088,0.000016203598,0.00006440797,0.00002805162,0.003967774,0.0000014516602,0.0005723051,0.9781987,0.0016481661,0.0095471265],"study_design_scores_gemma":[0.001038405,0.001048697,0.0014756995,0.000035570898,0.000012002179,0.00000581972,0.0070958463,0.000041820113,0.0004803241,0.9834377,0.0052102082,0.00011788235],"about_ca_topic_score_codex":0.00058382197,"about_ca_topic_score_gemma":0.0053422833,"teacher_disagreement_score":0.47608984,"about_ca_system_score_codex":0.0005592914,"about_ca_system_score_gemma":0.00025404448,"threshold_uncertainty_score":0.41821796},"labels":[],"label_agreement":null},{"id":"W4414268632","doi":"10.32388/219by1","title":"Review of: \"Misestimation of Expected Genetic Differences: A Statistical Note on Some Recent Papers\"","year":2025,"lang":"en","type":"peer-review","venue":"","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":"Université Laval","funders":"","keywords":"Statistical analysis; Genetic data; Statistical model; Statistical hypothesis testing","score_opus":0.17544894329272584,"score_gpt":0.4634740095513075,"score_spread":0.2880250662585817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414268632","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":[0.000009177498,0.5089986,0.3697886,0.017962635,0.0011878669,0.009926404,0.0034303246,0.0010441805,0.08765223],"genre_scores_gemma":[0.000013916334,0.72084403,0.26245525,0.0031567216,0.000039670253,0.00037406266,0.00054989604,0.000046557194,0.012519875],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99624574,0.0002925124,0.0018335456,0.0005337254,0.0008037135,0.0002907851],"domain_scores_gemma":[0.99446374,0.002264427,0.0012075139,0.0011118453,0.00085874816,0.000093708564],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039611454,0.0005473028,0.0022400436,0.000182817,0.000027188113,0.000008206342,0.0005122123,0.00031080487,0.0040864795],"category_scores_gemma":[0.009711521,0.00041794247,0.00021598974,0.00038919025,0.00014985964,0.0000496516,0.00015179811,0.00048487296,0.000014220252],"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":[0.000010793574,0.0002095521,7.11901e-7,0.23778847,0.000067521796,0.000003623241,0.000013498846,1.8267001e-7,0.000050849172,0.08024904,0.6097457,0.07186005],"study_design_scores_gemma":[0.00021138327,0.00048829016,0.000026462905,0.5472534,0.0011226684,0.0000043144405,0.0000057591114,0.000039869403,0.00067912356,0.23509555,0.21441074,0.000662455],"about_ca_topic_score_codex":0.000033068995,"about_ca_topic_score_gemma":0.000016002457,"teacher_disagreement_score":0.395335,"about_ca_system_score_codex":0.00019323012,"about_ca_system_score_gemma":0.00049159187,"threshold_uncertainty_score":0.99982727},"labels":[],"label_agreement":null},{"id":"W4414404097","doi":"10.1002/pds.70223","title":"Demystifying Clone‐Censor‐Weighting to Study Treatment Initiation Windows: An Example Using Publicly Available Synthetic Medicare Claims Data","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","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":"Jewish General Hospital; McGill University","funders":"","keywords":"Pharmacoepidemiology; MEDLINE; Data collection; Research design","score_opus":0.4703262874495665,"score_gpt":0.5073642905431359,"score_spread":0.037038003093569416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414404097","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":[0.7782876,0.00075835525,0.21358304,0.0023499776,0.00036736336,0.0022641085,0.0001258462,0.0007702392,0.001493461],"genre_scores_gemma":[0.9225659,0.00032554145,0.07529902,0.0012698238,0.0001393292,0.00013740265,0.00012773146,0.000037653706,0.00009759963],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949338,0.0021765754,0.001020558,0.001109657,0.00016117837,0.00059823826],"domain_scores_gemma":[0.99179316,0.006396598,0.0003273074,0.0011000817,0.0001364017,0.00024648372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006109729,0.0003845564,0.00082334393,0.0002491344,0.00060459547,0.00003453945,0.00053706253,0.00015592788,0.0002398918],"category_scores_gemma":[0.0031122512,0.00033020234,0.000047137968,0.00036186364,0.0001231544,0.00066433573,0.00057575473,0.000367376,0.000013498599],"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":[0.002208493,0.006232152,0.49763682,0.0010544978,0.0027711308,0.00023009206,0.026005354,0.0012253406,0.02268752,0.114869125,0.01973123,0.30534825],"study_design_scores_gemma":[0.015673181,0.0021510585,0.013390024,0.0019130902,0.0058564185,0.00027574727,0.028606117,0.24261528,0.036897253,0.59625846,0.051402315,0.0049610306],"about_ca_topic_score_codex":0.001253964,"about_ca_topic_score_gemma":0.00032225737,"teacher_disagreement_score":0.4842468,"about_ca_system_score_codex":0.00025129635,"about_ca_system_score_gemma":0.00013580539,"threshold_uncertainty_score":0.999915},"labels":[],"label_agreement":null},{"id":"W4414425742","doi":"10.1056/evidstat2500246","title":"How Propensity Scores Work","year":2025,"lang":"en","type":"review","venue":"NEJM Evidence","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":"Sinai Health System; University of Toronto","funders":"","keywords":"","score_opus":0.5882542406166034,"score_gpt":0.5149152834846253,"score_spread":0.07333895713197802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414425742","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":[5.764559e-7,0.98208034,0.0139839165,0.00014667821,0.00020269357,0.0019270083,0.000008954928,0.00072106486,0.00092878845],"genre_scores_gemma":[0.0000052576356,0.9551722,0.034085765,0.000050355964,0.00014771803,0.0004894153,0.000005625955,0.000058294907,0.0099853715],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753886,0.000313295,0.00057740917,0.0007139554,0.00042721772,0.00042927844],"domain_scores_gemma":[0.9937306,0.003915385,0.00060308044,0.0014350535,0.00021780533,0.00009806842],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000585459,0.00061940757,0.002220934,0.00020826502,0.000106096675,0.00022880697,0.0011099103,0.0004551055,0.00003978039],"category_scores_gemma":[0.010237362,0.00046191752,0.00043294142,0.00090565404,0.00015502208,0.0005052715,0.00058103737,0.00086586113,0.00007058921],"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":[0.0000032434918,0.00002032076,0.0000072124576,0.045856003,0.000035448782,0.00003028051,0.000014797594,1.6063678e-8,3.2681467e-7,0.014565569,0.0136018675,0.92586493],"study_design_scores_gemma":[0.00001731218,0.000034227258,0.0000011034177,0.26892743,0.00046179513,0.000013348915,0.00000250735,1.4251657e-7,0.000018820678,0.04714351,0.68293566,0.0004441717],"about_ca_topic_score_codex":0.0000053137524,"about_ca_topic_score_gemma":0.000009881841,"teacher_disagreement_score":0.92542076,"about_ca_system_score_codex":0.0002561226,"about_ca_system_score_gemma":0.0005530981,"threshold_uncertainty_score":0.9997833},"labels":[],"label_agreement":null},{"id":"W4414476142","doi":"10.1002/cjs.70014","title":"Rank‐based estimation of propensity score weights via subclassification","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Weighting; Estimator; Robustness (evolution); Consistency (knowledge bases); Propensity score matching; Estimation; A-weighting","score_opus":0.14609836062377696,"score_gpt":0.3524692437893049,"score_spread":0.20637088316552793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414476142","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":[0.02681079,0.000039670864,0.97203964,0.00020994675,0.00013127702,0.00018401924,0.00009324788,0.00001214831,0.00047927254],"genre_scores_gemma":[0.6628061,0.0000039869374,0.33705327,0.000042016152,0.000011887511,0.000001930539,0.000009692118,0.0000082501365,0.0000628502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989823,0.00005803424,0.00056499545,0.00007975224,0.00016350612,0.00015141361],"domain_scores_gemma":[0.99796236,0.00034144914,0.0005360431,0.00019588144,0.0007985799,0.00016568827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003376579,0.00010332405,0.00027555774,0.00035015703,0.000075160926,0.000022067521,0.0001786554,0.00007181646,0.00005240654],"category_scores_gemma":[0.0013235444,0.00009454732,0.00003809283,0.00022457182,0.00014234954,0.00012451145,0.0000054166308,0.00018523037,0.0000016710816],"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":[0.000056540488,0.00006591174,0.0058528776,0.00049776246,0.0000660558,0.00008384457,0.00026134425,0.00042509747,0.0014891808,0.9352184,0.013271168,0.042711794],"study_design_scores_gemma":[0.00036016968,0.00013410424,0.0076846112,0.0004659245,0.00011007042,0.000015475738,0.000023617662,0.010231842,0.017560078,0.96287835,0.00040694207,0.000128791],"about_ca_topic_score_codex":0.00040843253,"about_ca_topic_score_gemma":0.0038067207,"teacher_disagreement_score":0.6359953,"about_ca_system_score_codex":0.00023531639,"about_ca_system_score_gemma":0.0015102236,"threshold_uncertainty_score":0.3855528},"labels":[],"label_agreement":null},{"id":"W4414484180","doi":"10.1002/sim.70273","title":"Designing Stepped Wedge Cluster Randomized Trials With a Baseline Measurement of the Outcome","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","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":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; Patient-Centered Outcomes Research Institute","keywords":"Baseline (sea); Sample size determination; Outcome (game theory); Estimator; Randomized controlled trial; Context (archaeology); Cluster randomised controlled trial; Cluster (spacecraft)","score_opus":0.2478030119876625,"score_gpt":0.4705801716423711,"score_spread":0.2227771596547086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414484180","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":[0.00040924802,0.0001429188,0.9943993,0.0010288812,0.00017701808,0.0022967265,0.000027810705,0.000047623747,0.0014704821],"genre_scores_gemma":[0.23756245,0.0000450738,0.7610509,0.0005020732,0.00004733951,0.00024472605,0.00000551759,0.000024274595,0.00051764474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99553645,0.0017488946,0.001655259,0.00018963868,0.0006698234,0.0001999434],"domain_scores_gemma":[0.9827043,0.015743086,0.00063437055,0.00043641505,0.00044874154,0.000033123346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01994594,0.00019663354,0.0016601417,0.00017752827,0.0000403523,0.0000051503475,0.00023865025,0.000062597566,0.000085007036],"category_scores_gemma":[0.09347335,0.00009699322,0.000058388287,0.00035131545,0.0004240273,0.000027955442,0.000065060376,0.00027417482,5.86241e-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":[0.03885047,0.00031501072,0.002746641,0.0017807636,0.00055640674,0.000027772028,0.0018621372,0.000105412386,0.008747317,0.904017,0.03315932,0.00783176],"study_design_scores_gemma":[0.119813174,0.00015313494,0.00013580237,0.003015135,0.00075768214,0.0000021452192,0.00043569726,0.0015923745,0.009087265,0.8646889,0.00013708758,0.00018165051],"about_ca_topic_score_codex":0.000050850238,"about_ca_topic_score_gemma":0.00018325339,"teacher_disagreement_score":0.2371532,"about_ca_system_score_codex":0.00013421984,"about_ca_system_score_gemma":0.00013230121,"threshold_uncertainty_score":0.9141627},"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":"W4414966744","doi":"10.1093/biomtc/ujaf128","title":"Inverse-intensity weighted generalized estimating equations for longitudinal data subject to irregular observation: which variables should be included in the visit rate model?","year":2025,"lang":"en","type":"article","venue":"Biometrics","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":"Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Outcome (game theory); Conditional independence; Regression analysis; Inverse probability weighting; Generalized estimating equation; Regression; Linear regression; Weighting","score_opus":0.5402143993276196,"score_gpt":0.47497695751935703,"score_spread":0.06523744180826258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414966744","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":[0.03236782,0.00003769993,0.9616798,0.003838146,0.00015621366,0.0013028913,0.00024561872,0.00023325939,0.00013851134],"genre_scores_gemma":[0.13838623,0.000011665112,0.8593042,0.0013230403,0.000058918282,0.00021633855,0.00052639464,0.000026443986,0.00014677848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785686,0.00014800348,0.00066357636,0.0005554381,0.0003997283,0.0003764246],"domain_scores_gemma":[0.99403274,0.0033424376,0.00023319665,0.001433822,0.0008948657,0.000062964995],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003430187,0.00025810002,0.00044464477,0.0014059361,0.0002906458,0.00015713989,0.0011317458,0.00018639154,0.000008264589],"category_scores_gemma":[0.019679254,0.00021119614,0.000053398195,0.010370125,0.000044533583,0.00044640293,0.0006257869,0.00022116509,0.0000019068452],"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":[0.00025863553,0.00069222593,0.0035976227,0.0006315801,0.00022698726,0.000011076182,0.0012788658,0.009938299,0.013579228,0.90457624,0.06134997,0.0038592587],"study_design_scores_gemma":[0.0003812117,0.000043053602,0.00033856483,0.00007018479,0.00008739023,9.463327e-7,0.000073076386,0.729502,0.002090242,0.26660138,0.00061181455,0.00020012146],"about_ca_topic_score_codex":0.00014920425,"about_ca_topic_score_gemma":0.0003409476,"teacher_disagreement_score":0.7195637,"about_ca_system_score_codex":0.0002504855,"about_ca_system_score_gemma":0.00022384885,"threshold_uncertainty_score":0.9885784},"labels":[],"label_agreement":null},{"id":"W4415036455","doi":"10.48550/arxiv.2505.20893","title":"A longitudinal Bayesian framework for estimating causal dose-response relationships","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","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":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research","keywords":"Bayesian probability; Outcome (game theory); Propensity score matching; Causal model; Marginal model; Confounding; Nonparametric statistics; Dirichlet process; Generalized estimating equation","score_opus":0.32400446500037133,"score_gpt":0.4596934005287543,"score_spread":0.13568893552838296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415036455","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":[0.15353757,0.00007549884,0.8416454,0.0008523962,0.0006404843,0.0015299511,0.00014179059,0.0011609584,0.00041590945],"genre_scores_gemma":[0.3870677,0.0000060221305,0.6109322,0.000069085814,0.0002644318,0.0008319303,0.000042188567,0.000067004956,0.0007194603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99674726,0.0004138318,0.0009801375,0.0009343271,0.00032097645,0.00060345104],"domain_scores_gemma":[0.98691094,0.010381207,0.0007052467,0.0014968752,0.0003512867,0.0001544273],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018742349,0.00062825857,0.0008251941,0.00031713495,0.0004221071,0.00009799363,0.00070002774,0.0010992486,0.00008141235],"category_scores_gemma":[0.026346967,0.00065910805,0.00032137046,0.00030242302,0.00014880445,0.00017554266,0.0008492405,0.0025268449,0.000028674347],"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":[0.0015419319,0.0005714782,0.24987943,0.0040810094,0.0006795347,0.000097391734,0.003302831,0.002132178,0.00050964445,0.7274051,0.0062891804,0.0035103185],"study_design_scores_gemma":[0.00023180137,0.00010137163,0.013355593,0.0024831886,0.00023597275,0.000007830472,0.00010508171,0.0068008946,0.001063391,0.9747403,0.00021637045,0.00065818947],"about_ca_topic_score_codex":0.00002517813,"about_ca_topic_score_gemma":0.000035842135,"teacher_disagreement_score":0.24733526,"about_ca_system_score_codex":0.00039339316,"about_ca_system_score_gemma":0.00047202263,"threshold_uncertainty_score":0.99977434},"labels":[],"label_agreement":null},{"id":"W4415059812","doi":"10.1080/10705511.2025.2559270","title":"Controlling for Large Sets of Measured Confounders in Mediation Analysis: Comparison of Bayesian Model Averaging, the LASSO, and Path Analysis","year":2025,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","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":"Université Laval; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Bayesian probability; Path analysis (statistics); Path (computing); Bayesian inference; Confounding; Mediation","score_opus":0.16874481179621337,"score_gpt":0.44927888921299813,"score_spread":0.28053407741678477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415059812","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":[0.35995954,0.00016224923,0.63936466,0.00014535716,0.000030440176,0.00027508807,0.000038959362,0.000016450078,0.0000072311504],"genre_scores_gemma":[0.8785906,0.000025113364,0.12127896,0.000006104412,0.000012359125,0.000014336072,0.000059633414,0.000009589133,0.0000033338818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760306,0.0001973634,0.0012844693,0.00026725946,0.00041379518,0.00023407482],"domain_scores_gemma":[0.9972796,0.0007658426,0.0009555523,0.0003511934,0.0006014758,0.000046365425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020274126,0.00018862395,0.000782878,0.00080466,0.00026848493,0.000043291046,0.0002980683,0.00011301849,0.0000032913601],"category_scores_gemma":[0.0008246185,0.00013995879,0.00022412407,0.0008930763,0.000054466145,0.00033239787,0.000102478385,0.00030714748,1.4685532e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001439021,0.000031416956,0.027843785,0.00005905214,0.0010092,2.1077457e-7,0.0035001072,0.95166624,0.0005805421,0.014617372,0.0000017915889,0.0005463648],"study_design_scores_gemma":[0.0007366019,0.000024739711,0.0007753912,0.000048412625,0.001210511,4.796339e-7,0.0018185454,0.6663176,0.000097413285,0.32888713,2.7026005e-8,0.00008319405],"about_ca_topic_score_codex":0.00003150098,"about_ca_topic_score_gemma":0.0005531718,"teacher_disagreement_score":0.51863104,"about_ca_system_score_codex":0.00011894538,"about_ca_system_score_gemma":0.00013791508,"threshold_uncertainty_score":0.5707354},"labels":[],"label_agreement":null},{"id":"W4415096581","doi":"10.1002/pds.70235","title":"Comparing <scp>IPCW</scp> Models to Adjust for Informative Censoring During <scp>COVID</scp> ‐19 Using Data From the Clinical Practice Research Datalink","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Weighting; Pharmacoepidemiology; MEDLINE; Inverse probability weighting","score_opus":0.7158032594089283,"score_gpt":0.6151038036979035,"score_spread":0.10069945571102479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415096581","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":[0.17745432,0.0015702955,0.8089133,0.0020999466,0.00070453493,0.0025886288,0.0010142886,0.00047069637,0.005183998],"genre_scores_gemma":[0.45156142,0.0045090076,0.5311607,0.0097785415,0.0011631767,0.000371526,0.0006726681,0.000110636916,0.00067229464],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99155456,0.0038338804,0.0019904561,0.0011233526,0.00033925349,0.001158516],"domain_scores_gemma":[0.7741999,0.22232112,0.00074376044,0.0017651193,0.00053639355,0.00043370127],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.027478151,0.00043427275,0.0011209622,0.00021748297,0.0013007835,0.000077506294,0.0017323517,0.0003065061,0.0000055567402],"category_scores_gemma":[0.13342245,0.00035163484,0.00011979937,0.0005073238,0.0005508818,0.0019201129,0.0037020433,0.002052567,0.000014687469],"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":[0.0012238614,0.0007801274,0.05103163,0.0018081737,0.0024730293,0.00005846219,0.024272067,0.021560589,0.0024882164,0.38433337,0.501467,0.008503473],"study_design_scores_gemma":[0.0029160792,0.00007820841,0.0027177276,0.00070025073,0.0006972558,0.00003795445,0.013857934,0.37976345,0.0018806787,0.38362733,0.21346566,0.0002574613],"about_ca_topic_score_codex":0.00050738215,"about_ca_topic_score_gemma":0.00011071591,"teacher_disagreement_score":0.35820287,"about_ca_system_score_codex":0.00023556677,"about_ca_system_score_gemma":0.0003125864,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W4415221337","doi":"10.1002/cjs.70021","title":"Kernel estimation of average treatment effects in models with unmeasured confounders","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Estimator; Kernel density estimation; Kernel (algebra); Parametric statistics; Estimation; Inverse probability; Estimation theory; Kernel regression; Kernel method","score_opus":0.07484188317513137,"score_gpt":0.3414153379963154,"score_spread":0.26657345482118405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415221337","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":[0.014954091,0.00006888667,0.9836431,0.0000506196,0.00005250446,0.00020820691,0.000068851055,0.0000063015113,0.00094742683],"genre_scores_gemma":[0.726168,0.000011637191,0.27370846,0.000023382558,0.0000039592032,0.0000037277769,0.0000030703393,0.000009146167,0.000068633664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920034,0.000048549453,0.00038508323,0.00006932828,0.00013133939,0.00016534117],"domain_scores_gemma":[0.9987276,0.00050001295,0.0002678598,0.00012683777,0.00023662871,0.00014106961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001687783,0.00011647254,0.00031296787,0.0003257302,0.000029073517,0.000017207662,0.00009647882,0.000052612468,0.000011244412],"category_scores_gemma":[0.00042835245,0.00009794432,0.000023625373,0.00016422343,0.00009662686,0.000116097275,0.0000030221022,0.000120644916,3.1662825e-7],"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":[0.000055733395,0.000054368757,0.0007941174,0.00025416867,0.000109857574,0.00032499825,0.0011713116,0.031804018,0.000073082425,0.9513549,0.0006739163,0.013329496],"study_design_scores_gemma":[0.000878596,0.00043687274,0.0005936095,0.0006352131,0.00007671517,0.00002092214,0.00012395113,0.02088589,0.0011660841,0.9750504,0.000030229936,0.000101554986],"about_ca_topic_score_codex":0.0019895288,"about_ca_topic_score_gemma":0.029532386,"teacher_disagreement_score":0.7112139,"about_ca_system_score_codex":0.0006395466,"about_ca_system_score_gemma":0.0014246362,"threshold_uncertainty_score":0.9881761},"labels":[],"label_agreement":null},{"id":"W4415322104","doi":"10.1007/s40471-025-00374-6","title":"Transporting: What Is It and How Do You Do It?","year":2025,"lang":"en","type":"article","venue":"Current Epidemiology Reports","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":"McGill University","funders":"National Institute on Drug Abuse; Wake Forest University","keywords":"Generalizability theory; External validity; Estimator; Population; Internal validity; Field (mathematics)","score_opus":0.2733632021131419,"score_gpt":0.4917979683271415,"score_spread":0.2184347662139996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415322104","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":[0.38066664,0.08993831,0.37563157,0.13403,0.0065756147,0.0030097154,0.000023066712,0.0017995982,0.008325481],"genre_scores_gemma":[0.9324396,0.02295309,0.03710377,0.0035775243,0.0002500925,0.000393331,0.00003906853,0.00007533851,0.00316817],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99702954,0.00026505347,0.0011593105,0.0008549725,0.00012834228,0.00056280306],"domain_scores_gemma":[0.99574894,0.0019836812,0.0010469188,0.0009134175,0.00016106988,0.00014596124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033819852,0.00035755459,0.001062487,0.00016984608,0.00012522464,0.000046836907,0.00016786423,0.0003196751,0.00010551173],"category_scores_gemma":[0.007110735,0.00030742504,0.00018377758,0.00020403141,0.00033267747,0.00043549735,0.00011584962,0.00054864807,0.000003111501],"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":[0.000026924572,0.00021659848,0.369502,0.0009162365,0.00016329314,0.00024835157,0.0013041906,0.0000044291255,0.00027271057,0.135489,0.32880983,0.16304643],"study_design_scores_gemma":[0.000120780365,0.00004595238,0.0015103819,0.0010630774,0.00011525232,0.00018022514,0.00044401825,0.000031612853,0.0008116781,0.8041368,0.19122049,0.00031971183],"about_ca_topic_score_codex":0.0000035137205,"about_ca_topic_score_gemma":0.0000043765112,"teacher_disagreement_score":0.6686478,"about_ca_system_score_codex":0.00006726331,"about_ca_system_score_gemma":0.00008334935,"threshold_uncertainty_score":0.9999378},"labels":[],"label_agreement":null},{"id":"W4415385981","doi":"10.1111/jep.70298","title":"Understanding and Managing Confounders, Mediators and Colliders in Research","year":2025,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","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":"University of Calgary; Memorial University of Newfoundland","funders":"","keywords":"Causal inference; Element (criminal law); Causality (physics); Causal structure; Causal model; Data collection; Causal reasoning","score_opus":0.8119926734466607,"score_gpt":0.6927171313995422,"score_spread":0.11927554204711854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415385981","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":[0.6415762,0.0025109595,0.23284899,0.06570262,0.001202686,0.0022142683,0.000001263338,0.000049428654,0.05389361],"genre_scores_gemma":[0.96468735,0.0018868725,0.033011276,0.00033649956,0.000040461317,0.0000068559402,1.5609211e-7,0.000007209898,0.00002331573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955645,0.0021035508,0.001280182,0.00015947978,0.000733274,0.0001589869],"domain_scores_gemma":[0.9496164,0.048959736,0.00060116814,0.00012428468,0.00063444994,0.00006396749],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053303264,0.0000731309,0.00029105705,0.00058936805,0.000060584283,0.00006945684,0.00008430228,0.00013067713,0.000017619812],"category_scores_gemma":[0.14157692,0.00006787287,0.000025972302,0.00050180004,0.00021839434,0.0007854156,0.00007561368,0.0011392342,4.624567e-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":[0.0010371368,0.0005126938,0.05375081,0.00024071083,0.00014310285,0.00013938098,0.002031986,0.00016686613,0.00007790252,0.91511816,0.006576171,0.020205082],"study_design_scores_gemma":[0.0014072206,0.00015883755,0.0042947987,0.00043993143,0.00006150036,0.000019393972,0.011856418,0.0033162977,0.000013148793,0.9779425,0.00042963965,0.00006027886],"about_ca_topic_score_codex":0.000015785086,"about_ca_topic_score_gemma":0.0001197762,"teacher_disagreement_score":0.32311118,"about_ca_system_score_codex":0.00051207875,"about_ca_system_score_gemma":0.00034199475,"threshold_uncertainty_score":0.97482353},"labels":[],"label_agreement":null},{"id":"W4415495055","doi":"10.1093/aje/kwaf239","title":"Evaluating treatment benefit predictors using observational data: contending with identification and confounding bias","year":2025,"lang":"en","type":"article","venue":"American Journal of Epidemiology","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Observational study; Confounding; Causal inference; Identification (biology); Intuition; Calibration; Measure (data warehouse); Instrumental variable","score_opus":0.7092128010368095,"score_gpt":0.577015850385838,"score_spread":0.13219695065097148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415495055","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":[0.64967644,0.00016531027,0.3494636,0.00044435047,0.00007704587,0.00011425727,0.000007800824,0.000020596823,0.000030594303],"genre_scores_gemma":[0.6642627,0.0001260727,0.3353135,0.00017152655,0.00006446572,0.000005285559,0.000010029111,0.000010729342,0.000035683093],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978801,0.00047730017,0.0010524917,0.0002444199,0.00012425141,0.00022144323],"domain_scores_gemma":[0.9880589,0.009236321,0.0019872785,0.00033507365,0.00031324636,0.000069163936],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004250293,0.00015456341,0.00071830064,0.00020886434,0.00011459728,0.000015734147,0.00022183752,0.00004232669,0.0000064966966],"category_scores_gemma":[0.011346377,0.00011092787,0.0000407853,0.00022951196,0.00039533715,0.00035071516,0.00007208064,0.00016046732,1.5137955e-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":[0.0002552671,0.000087764645,0.68304044,0.00004486809,0.00064857455,0.000010800569,0.00040820282,0.0013455831,0.007089234,0.23877554,0.000121374585,0.068172365],"study_design_scores_gemma":[0.0020958884,0.004983736,0.123366624,0.0016915606,0.0014057374,0.0007613025,0.0033490884,0.06420525,0.0017796785,0.7946466,0.0011135781,0.00060091633],"about_ca_topic_score_codex":0.00011537328,"about_ca_topic_score_gemma":0.000020978765,"teacher_disagreement_score":0.5596738,"about_ca_system_score_codex":0.00027840852,"about_ca_system_score_gemma":0.00016738009,"threshold_uncertainty_score":0.9969815},"labels":[],"label_agreement":null},{"id":"W4415614733","doi":"10.1093/biomtc/ujaf143","title":"Adaptive stratified sampling design in two-phase studies for average causal effect estimation","year":2025,"lang":"en","type":"article","venue":"Biometrics","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":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Confounding; Estimator; Sampling design; Sampling (signal processing); Stratified sampling; Sample size determination; Causal inference; Observational study; Stratification (seeds)","score_opus":0.39395430355975664,"score_gpt":0.544197749972689,"score_spread":0.15024344641293236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415614733","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":[0.022412501,0.0003697107,0.9751312,0.000028954497,0.00014736895,0.0015167827,0.000024340283,0.00023583435,0.00013331142],"genre_scores_gemma":[0.5152464,0.000026200309,0.48434034,0.000019401657,0.00001572628,0.00026961422,0.000008426944,0.000014141992,0.000059736143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872184,0.00012279119,0.0004273464,0.00028152013,0.00017720327,0.00026932592],"domain_scores_gemma":[0.990438,0.008932608,0.00015878127,0.00023656136,0.00020033587,0.000033744316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011835864,0.00020786539,0.00041442615,0.0017196662,0.00008817026,0.000039780287,0.00014795183,0.000088046225,0.0000027908202],"category_scores_gemma":[0.010308376,0.00018839713,0.000057119854,0.003126745,0.000057800284,0.00017451298,0.00005933993,0.00013415125,0.000002193842],"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":[0.0011895854,0.0011378783,0.00030843014,0.0018092806,0.0004727642,0.000034996727,0.0013372102,0.0055784895,0.037824288,0.48859885,0.00307628,0.45863193],"study_design_scores_gemma":[0.0030906878,0.0012482156,0.000071825176,0.00036189027,0.00010177957,0.0000014715955,0.00019919896,0.06450508,0.11005022,0.8199382,0.00006975491,0.0003616944],"about_ca_topic_score_codex":0.000009337251,"about_ca_topic_score_gemma":0.0000121262765,"teacher_disagreement_score":0.4928339,"about_ca_system_score_codex":0.00034727537,"about_ca_system_score_gemma":0.00006989942,"threshold_uncertainty_score":0.9980282},"labels":[],"label_agreement":null},{"id":"W4415827025","doi":"10.2196/84173","title":"Authors’ Response to Peer Reviews of “Assessing the Limitations of Large Language Models in Clinical Practice Guideline–Concordant Treatment Decision-Making on Real-World Data: Retrospective Study”","year":2025,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Clinical Practice; Peer review; MEDLINE; Language model; Peer group","score_opus":0.426025978404257,"score_gpt":0.6231956014630726,"score_spread":0.19716962305881564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415827025","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":[0.5467781,0.00026187042,0.4112343,0.017053723,0.00037957454,0.008933841,0.00022471699,0.00024961075,0.014884313],"genre_scores_gemma":[0.66821545,0.00019385607,0.32966623,0.00035454618,0.000032051463,0.00021957334,0.000008450414,0.000023024584,0.0012868366],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949935,0.001771537,0.0020081792,0.00048005715,0.00052127236,0.00022544626],"domain_scores_gemma":[0.9757853,0.02075382,0.000934245,0.0018332411,0.0006466432,0.00004671811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013953034,0.00020698262,0.00083370757,0.0003333222,0.00007399604,0.000029861072,0.00052056235,0.00006404571,0.0000074447294],"category_scores_gemma":[0.11063974,0.00013606375,0.00010281194,0.0010156566,0.00006260074,0.00035352586,0.0003186728,0.00032506167,0.0000027299131],"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":[0.009944779,0.018755972,0.009070643,0.00015993994,0.00076704996,0.00030709524,0.059500936,0.0006437396,0.0027473497,0.32935527,0.14539425,0.423353],"study_design_scores_gemma":[0.0072181164,0.007638263,0.07153243,0.00999743,0.0018733502,0.000009516654,0.109972216,0.01602135,0.002627759,0.52490884,0.2466462,0.0015545347],"about_ca_topic_score_codex":0.00014430346,"about_ca_topic_score_gemma":0.0032085925,"teacher_disagreement_score":0.42179844,"about_ca_system_score_codex":0.00037366137,"about_ca_system_score_gemma":0.00023425875,"threshold_uncertainty_score":0.8968517},"labels":[],"label_agreement":null},{"id":"W4415882029","doi":"10.1101/2025.11.02.25339322","title":"Target trial emulation of physical activity and cardiovascular disease risk: What is impact of the exposure assessment method?","year":2025,"lang":"","type":"preprint","venue":"medRxiv","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":"McMaster University","funders":"","keywords":"Causal inference; Confounding; Observational study; Randomized controlled trial; Pedometer; Risk assessment; Cohort; Physical activity; Poisson regression","score_opus":0.08296499534171012,"score_gpt":0.4432584972852671,"score_spread":0.360293501943557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415882029","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":[0.6724685,0.0007520341,0.32286412,0.000044489534,0.0002823186,0.0029026493,0.00057227205,0.000047260095,0.00006635281],"genre_scores_gemma":[0.95849115,0.0018874428,0.039089218,0.0000044497374,0.00016635293,0.0002558856,0.000011991088,0.00004710792,0.00004642559],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930083,0.0032196983,0.0009791028,0.001076753,0.0013298581,0.0003862446],"domain_scores_gemma":[0.99173564,0.002195865,0.001838727,0.0034730295,0.0005550452,0.00020172376],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032679318,0.00079375185,0.0024895968,0.00018664228,0.00015560017,0.00009647032,0.000713441,0.0004466377,0.00006861139],"category_scores_gemma":[0.0017136313,0.0005619069,0.0033887548,0.00041904664,0.0003700394,0.000543575,0.0014855968,0.0013911101,4.6925953e-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":[0.03276364,0.014220651,0.21278986,0.020310245,0.044381794,0.000026914115,0.017916266,0.16096215,0.028661897,0.012181101,0.00013736496,0.45564812],"study_design_scores_gemma":[0.015188731,0.00169104,0.26122254,0.0052121626,0.0130517855,0.0000021121593,0.00040111106,0.17466334,0.13140297,0.39544052,0.00007991047,0.0016437741],"about_ca_topic_score_codex":0.00024829144,"about_ca_topic_score_gemma":0.000002168347,"teacher_disagreement_score":0.45400435,"about_ca_system_score_codex":0.00029164104,"about_ca_system_score_gemma":0.0009846662,"threshold_uncertainty_score":0.99968326},"labels":[],"label_agreement":null},{"id":"W4415907925","doi":"10.5539/gjhs.v17n6p98","title":"Quantitative Modeling of the Critical Impact of Socioeconomic Status on Body Mass Index Using Double Machine Learning","year":2025,"lang":"","type":"article","venue":"Global Journal of Health Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Socioeconomic status; Causal inference; Body mass index; National Health and Nutrition Examination Survey; Covariate; Causal model; Index (typography); Inference; Descriptive statistics","score_opus":0.15242326378727833,"score_gpt":0.5238442982923169,"score_spread":0.3714210345050386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415907925","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":[0.6996052,0.0011565101,0.29770443,0.0004055697,0.00040223228,0.00030409437,0.00004277502,0.000010383004,0.00036876532],"genre_scores_gemma":[0.9586111,0.00036595698,0.040909495,0.000079550955,0.000018319783,7.85039e-7,1.674594e-7,0.000011009285,0.000003658955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949387,0.00032005383,0.0024715452,0.00033215614,0.0009791343,0.000958447],"domain_scores_gemma":[0.99441546,0.00056816946,0.0028482713,0.0004010008,0.0014780074,0.0002890936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005013268,0.00031270413,0.0011011239,0.0003799074,0.0006199323,0.000082642575,0.0010579517,0.00012640121,0.00002993898],"category_scores_gemma":[0.001910525,0.00022636248,0.0003891949,0.0011194762,0.0016531766,0.0008013703,0.0002977355,0.001107254,9.692377e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012079618,0.00048902846,0.103323266,0.00088659197,0.00013554403,0.0000052945743,0.00074886496,0.64039546,0.007462806,0.24346715,0.000023626795,0.0018544139],"study_design_scores_gemma":[0.00080508715,0.0020998113,0.0038699212,0.0028431737,0.00006465338,0.00004858347,0.0013938728,0.79295623,0.0017791201,0.19395883,0.0000016379944,0.00017904215],"about_ca_topic_score_codex":0.0008962832,"about_ca_topic_score_gemma":0.000013575981,"teacher_disagreement_score":0.2590058,"about_ca_system_score_codex":0.0036646088,"about_ca_system_score_gemma":0.010186827,"threshold_uncertainty_score":0.9954245},"labels":[],"label_agreement":null},{"id":"W4415945807","doi":"10.21203/rs.3.rs-7565524/v1","title":"The Impact of Dependency and Serial Correlation in Matched ITSA: Methodological Considerations","year":2025,"lang":"","type":"preprint","venue":"Research Square","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":"University of Toronto","funders":"","keywords":"Correlation; Dependency (UML); Robustness (evolution); Autocorrelation; Type I and type II errors; Monte Carlo method; Series (stratigraphy); Regression analysis; Joint (building)","score_opus":0.5293367373186046,"score_gpt":0.6071778789169079,"score_spread":0.07784114159830324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415945807","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":[0.6216399,0.0040967115,0.3380769,0.002384364,0.00061708374,0.017494304,0.0010165467,0.00036826415,0.014305902],"genre_scores_gemma":[0.94164324,0.00471182,0.052405436,0.0000037191205,0.000081530765,0.00062936614,0.00003447275,0.000029741565,0.00046070636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98786557,0.0076041995,0.0016380079,0.0008457789,0.0011228969,0.00092354434],"domain_scores_gemma":[0.950079,0.046088986,0.0005220556,0.0012325009,0.0018984122,0.00017900468],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014537655,0.0004833032,0.0011799873,0.0006675533,0.00059733907,0.00028067292,0.0005298768,0.0011386196,0.00048488882],"category_scores_gemma":[0.053947456,0.0003391282,0.00030557808,0.0007942763,0.001071695,0.00023425053,0.002060716,0.0039187656,0.000008281969],"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":[0.0015708085,0.0012213985,0.025081001,0.004409717,0.0005952985,0.00009741127,0.0103812115,0.010967531,0.0068374253,0.92171663,0.0015338612,0.015587679],"study_design_scores_gemma":[0.0005277867,0.0006139178,0.017330308,0.0018151464,0.000033606128,0.000015488118,0.0018829523,0.0099265035,0.0023622746,0.9652076,0.000009871542,0.00027457564],"about_ca_topic_score_codex":0.0013265453,"about_ca_topic_score_gemma":0.0009755493,"teacher_disagreement_score":0.32000327,"about_ca_system_score_codex":0.000825768,"about_ca_system_score_gemma":0.0021758587,"threshold_uncertainty_score":0.99990606},"labels":[],"label_agreement":null},{"id":"W4416148163","doi":"10.1093/ijpp/riaf111","title":"Realist evaluations: relevance to pharmacy practice and education","year":2025,"lang":"en","type":"article","venue":"International Journal of Pharmacy Practice","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":"University of Toronto","funders":"Monash University","keywords":"Relevance (law); Psychological intervention; Pharmacy; Pharmacy practice; Population","score_opus":0.1676751014141028,"score_gpt":0.5932963085363024,"score_spread":0.42562120712219964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416148163","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":[0.01963583,0.0044394433,0.5398807,0.3139897,0.0065405974,0.0014741626,0.000041424275,0.0002477253,0.11375042],"genre_scores_gemma":[0.31720915,0.005239028,0.64818096,0.02583385,0.0010327285,0.000084841784,0.000007636424,0.000043715303,0.0023680914],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975954,0.00038597413,0.00082926196,0.00021315964,0.0008203979,0.00015579945],"domain_scores_gemma":[0.987868,0.0057425876,0.0011752612,0.00019234284,0.004888178,0.00013361426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023636885,0.00017176097,0.00021241394,0.00044341333,0.0000861419,0.00018111648,0.0005346759,0.000028909608,0.00010122792],"category_scores_gemma":[0.050592847,0.00016947403,0.00006383612,0.0003148835,0.000050395684,0.0034654161,0.00014850163,0.00051026593,0.000017309023],"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":[0.0040574893,0.0018561049,0.00035377516,0.00009288372,0.00085594057,0.00013304246,0.0014164181,0.00010146899,0.025254756,0.32803673,0.17182323,0.46601817],"study_design_scores_gemma":[0.0016756307,0.000060136055,0.000039202907,0.0002909746,0.00037485763,0.00086030853,0.0007111333,0.00025811436,0.016623456,0.14620094,0.83274496,0.00016028929],"about_ca_topic_score_codex":0.00009590187,"about_ca_topic_score_gemma":0.0000053651543,"teacher_disagreement_score":0.66092175,"about_ca_system_score_codex":0.00039892877,"about_ca_system_score_gemma":0.000855131,"threshold_uncertainty_score":0.95740443},"labels":[],"label_agreement":null},{"id":"W4416185308","doi":"10.1136/bmjph-2025-002918","title":"Associations between social determinants of health and COVID-19 outcomes by variants of concern: a Bayesian spatiotemporal analysis","year":2025,"lang":"en","type":"article","venue":"BMJ Public Health","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":true,"ca_institutions":"St. Paul's Hospital; Institute for Clinical Evaluative Sciences; BC Centre for Disease Control; Public Health Ontario; University of British Columbia; Simon Fraser University; Toronto General Hospital; University Health Network; University of Toronto","funders":"Institute of Infection and Immunity; British Columbia Centre for Disease Control; Provincial Health Services Authority; Canada Research Chairs","keywords":"Socioeconomic status; Social determinants of health; Pandemic; Health equity; Disadvantaged; Preparedness; Bayesian probability; Disease","score_opus":0.3449884958753923,"score_gpt":0.5513007527290257,"score_spread":0.20631225685363336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416185308","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":[0.099168114,0.00016090495,0.8371119,0.059058595,0.0000461768,0.00158762,0.0022099102,0.00023317285,0.00042363483],"genre_scores_gemma":[0.9807988,0.000036096513,0.016596317,0.0021822043,0.000014739469,0.00003998609,0.00016290817,0.000015449552,0.00015352794],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99652326,0.0007120613,0.0016598356,0.00029422442,0.00037493327,0.00043570637],"domain_scores_gemma":[0.9960271,0.0011338254,0.001989325,0.00033390798,0.00019091448,0.0003249191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003721179,0.0001812915,0.0015159523,0.00047180481,0.00025760345,0.000025960857,0.0002233724,0.00015601306,0.00002542299],"category_scores_gemma":[0.0040388587,0.00017710941,0.00013502124,0.001134782,0.00015513077,0.00017994292,0.000103880906,0.00016182502,2.4849498e-7],"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":[0.000003876104,0.00014607309,0.93484825,0.00047235237,0.00035525952,3.7682346e-7,0.0022678343,2.4022833e-7,0.0000017328624,0.03269465,0.011077066,0.018132292],"study_design_scores_gemma":[0.001512086,0.00040699838,0.8262713,0.00011767879,0.00022699888,8.498968e-7,0.001449123,0.00060561456,0.00006771657,0.166625,0.0022859918,0.00043064426],"about_ca_topic_score_codex":0.0043552425,"about_ca_topic_score_gemma":0.0012505163,"teacher_disagreement_score":0.88163066,"about_ca_system_score_codex":0.0005540953,"about_ca_system_score_gemma":0.0040637716,"threshold_uncertainty_score":0.7222312},"labels":[],"label_agreement":null},{"id":"W4416208598","doi":"10.1002/pds.70255","title":"<scp>The Reporting</scp> and Methodological Recommendations for Observational Studies Estimating the Effects of Deprescribing Medications (REMROSE‐D) ISPE‐Endorsed Guidance","year":2025,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","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":"Université Laval","funders":"National Institute on Aging; International Society for Pharmacoepidemiology","keywords":"Observational study; Deprescribing; Confounding; Pharmacoepidemiology; MEDLINE","score_opus":0.49440347288314307,"score_gpt":0.5652237796287686,"score_spread":0.0708203067456255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416208598","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":[0.016231585,0.005825529,0.94534194,0.03058595,0.00039659376,0.0011312951,0.000019829678,0.00014468822,0.00032257498],"genre_scores_gemma":[0.10627923,0.002414619,0.8862535,0.0037687991,0.00010864286,0.00081775576,0.000022475982,0.000013456182,0.0003215343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99613005,0.0017346974,0.0014835771,0.00032314766,0.000079549936,0.00024896016],"domain_scores_gemma":[0.7954356,0.20225818,0.0016726633,0.00030758107,0.0002800676,0.00004591294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013899936,0.00017511248,0.0005806945,0.000049363505,0.00070967566,0.0000063462994,0.000210702,0.00008367521,0.0000027024773],"category_scores_gemma":[0.26607653,0.00010369861,0.00008299441,0.00018105935,0.0006398014,0.00010380695,0.0002252999,0.0003295837,1.528474e-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":[0.00003725491,0.00007673427,0.016216163,0.0009946759,0.0006414954,0.0000014442971,0.002573154,0.00011626374,0.0043081357,0.8239068,0.12983206,0.021295827],"study_design_scores_gemma":[0.00042273809,0.000031247393,0.0049535655,0.00028583064,0.0003388613,0.000011549487,0.0004963408,0.009123258,0.005257241,0.97247094,0.006543674,0.000064762455],"about_ca_topic_score_codex":0.000011627429,"about_ca_topic_score_gemma":0.000008780922,"teacher_disagreement_score":0.25217658,"about_ca_system_score_codex":0.0000304182,"about_ca_system_score_gemma":0.000049125905,"threshold_uncertainty_score":0.7401056},"labels":[],"label_agreement":null},{"id":"W4416377097","doi":"10.1017/9781108641784.015","title":"The Future of Chilling Effects and How to Stop It","year":2025,"lang":"","type":"book-chapter","venue":"Cambridge University Press eBooks","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":"York University","funders":"","keywords":"Dystopia; Enforcement; Automation; Law enforcement; Public policy","score_opus":0.03421890552399471,"score_gpt":0.26841114290517043,"score_spread":0.23419223738117573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416377097","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007418197,0.0014291002,0.059575934,0.0006517042,0.0005790466,0.0032299499,0.00034594946,0.0002535108,0.93319297],"genre_scores_gemma":[0.0073700882,0.0032778052,0.0069645243,0.00014336797,0.00021439718,0.0000056716426,0.000009042327,0.000077494165,0.9819376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778354,0.00014716583,0.00035256683,0.0007676727,0.00043156795,0.000517456],"domain_scores_gemma":[0.9954977,0.0017735038,0.0006365606,0.0012844142,0.0005325545,0.00027527334],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035201418,0.000767961,0.0010227227,0.00029700302,0.00066444074,0.000109203254,0.0010213333,0.00069523725,0.000001374615],"category_scores_gemma":[0.00019874892,0.00072361715,0.00029269914,0.00003355369,0.00066339446,0.00014057281,0.0014783819,0.0010124169,0.0000013405012],"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":[0.00017197707,0.000013134267,0.0000016153643,0.0013847665,0.00029474453,0.000075836,0.0002584365,0.0000012965917,0.0004242232,0.9669424,0.011378112,0.01905344],"study_design_scores_gemma":[0.0006042414,0.0003395125,0.000009730391,0.003163305,0.0008179598,0.000012675076,0.000672801,0.000089055444,0.012584002,0.00113848,0.97974396,0.00082427886],"about_ca_topic_score_codex":0.000022277032,"about_ca_topic_score_gemma":0.000007481209,"teacher_disagreement_score":0.96836585,"about_ca_system_score_codex":0.00022500163,"about_ca_system_score_gemma":0.0001469597,"threshold_uncertainty_score":0.9995215},"labels":[],"label_agreement":null},{"id":"W4416404588","doi":"10.1007/s44199-025-00132-z","title":"The Modified Instrumental Variable (MIV) for Endogenous Instrumental Variables","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Applications","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Instrumental variable; Estimator; Lottery; Earnings; Variable (mathematics); Variables; Quarter (Canadian coin)","score_opus":0.0689276498258833,"score_gpt":0.38176654182534,"score_spread":0.3128388919994567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416404588","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":[0.0017941728,0.000103876686,0.9910169,0.00011335703,0.000048686576,0.00049695774,0.00015777566,0.00002552004,0.0062427022],"genre_scores_gemma":[0.71834356,0.00017693982,0.280558,0.00014849435,0.000092390175,0.00030187142,0.0000086490345,0.00001471766,0.0003553756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990702,0.00008972688,0.0004558189,0.00010704599,0.00010784346,0.00016935043],"domain_scores_gemma":[0.99394125,0.0055067656,0.00020972425,0.00015453318,0.00012198147,0.00006576468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00106765,0.00010557046,0.00020057247,0.000046997997,0.00042444048,0.00006178741,0.00020208434,0.000054001484,0.000021361371],"category_scores_gemma":[0.00067743455,0.00007158743,0.000039181425,0.00012676834,0.0002498635,0.00009936219,0.000055661792,0.00017703277,6.1086337e-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":[0.00014216405,0.000098668475,0.000010593819,0.000037935526,0.00006532571,5.841611e-7,0.000025116778,0.0000032201513,0.0019117598,0.9648111,0.00036577668,0.032527793],"study_design_scores_gemma":[0.0003727729,0.00010324784,0.000019929457,0.000035940237,0.000093744544,0.000042143725,0.0003278071,0.00010838223,0.0027681931,0.9873199,0.008739405,0.00006855576],"about_ca_topic_score_codex":0.0000012305486,"about_ca_topic_score_gemma":6.2344697e-7,"teacher_disagreement_score":0.7165494,"about_ca_system_score_codex":0.000057496865,"about_ca_system_score_gemma":0.0000891525,"threshold_uncertainty_score":0.3264496},"labels":[],"label_agreement":null},{"id":"W4416423288","doi":"10.1097/hjh.0000000000004188","title":"Target trial emulation in hypertension research: a scoping review of current applications and methodological practices","year":2025,"lang":"en","type":"article","venue":"Journal of Hypertension","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":"University of Alberta","funders":"","keywords":"Causal inference; Confounding; Observational study; Emulation; Marginal structural model; Weighting; Systematic review; MEDLINE","score_opus":0.8325902265006923,"score_gpt":0.6368799860046752,"score_spread":0.19571024049601704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416423288","genre_codex":"empirical","genre_gemma":"methods","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":[0.36508906,0.2522121,0.36399025,0.0092951385,0.00063877954,0.00801829,0.0000042464862,0.00010246251,0.00064965105],"genre_scores_gemma":[0.33632737,0.15195617,0.5108353,0.0004914262,0.00022267582,0.00011990291,0.0000039120487,0.0000256398,0.000017569326],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972259,0.0009981234,0.0010407175,0.00016663082,0.0004217723,0.00014689304],"domain_scores_gemma":[0.99242234,0.0050082644,0.0012094133,0.00022225128,0.0010900543,0.00004770123],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006907909,0.00010215559,0.00068166637,0.00041001715,0.000063128195,0.000012543355,0.00013744993,0.00009185167,0.000010150157],"category_scores_gemma":[0.023824802,0.00007162933,0.00007752468,0.0005063565,0.000084594525,0.00026847376,0.00010893808,0.00054462504,4.499976e-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":[0.026311103,0.007946331,0.002820034,0.1168706,0.0002761616,0.00029525656,0.00059535145,0.00007084473,0.30348194,0.14160194,0.02555751,0.37417293],"study_design_scores_gemma":[0.010390075,0.001356625,0.00074391335,0.27915254,0.00026747762,0.00030093855,0.0002587468,0.0008211783,0.011539581,0.69210225,0.0027735715,0.00029310575],"about_ca_topic_score_codex":0.0000040858868,"about_ca_topic_score_gemma":0.0000027156216,"teacher_disagreement_score":0.55050033,"about_ca_system_score_codex":0.000056433604,"about_ca_system_score_gemma":0.00019013291,"threshold_uncertainty_score":0.98439795},"labels":[],"label_agreement":null},{"id":"W4416524804","doi":"10.1016/b978-0-323-90509-1.00016-3","title":"Categorical variable analyses: Chi-square, Fisher's exact, and Mantel–Haenszel","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","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":"University of Calgary","funders":"","keywords":"Categorical variable; Nonparametric statistics; Statistical hypothesis testing; Confounding; Null hypothesis; Sample size determination; Robustness (evolution); Demographics","score_opus":0.11124870922501105,"score_gpt":0.3827075715131068,"score_spread":0.27145886228809574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416524804","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008959267,0.0007999892,0.008987785,0.0000399314,0.00017392074,0.0008972734,0.00007094637,0.00058138696,0.9884398],"genre_scores_gemma":[0.00026071724,0.0003448461,0.04603319,0.00035151263,0.00020686576,0.00011568374,0.000041927877,0.00015186176,0.95249337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99719745,0.000059744678,0.0008909748,0.0008811016,0.00045311524,0.0005176315],"domain_scores_gemma":[0.9974282,0.00048461498,0.0004544263,0.0012008456,0.00022684128,0.00020511536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036907397,0.00084617984,0.0013615097,0.00036997994,0.00016388435,0.000111015645,0.0004810017,0.0007930483,0.0005421135],"category_scores_gemma":[0.00026054986,0.00077049335,0.00025560835,0.00004967317,0.00024577655,0.00011177053,0.00046361733,0.0011065323,0.00003927821],"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":[0.000018358236,0.00002368409,0.0000037464888,0.0005658823,0.00028613338,0.00008583244,0.000092183465,2.2270562e-7,0.000050698138,0.5560371,0.0031317014,0.4397044],"study_design_scores_gemma":[0.0001422867,0.000078422316,0.0000021785913,0.0005840734,0.00035883777,0.000032560947,0.000008996125,0.000023321778,0.00012804686,0.6072864,0.39084345,0.00051143405],"about_ca_topic_score_codex":0.000006246292,"about_ca_topic_score_gemma":0.0000266994,"teacher_disagreement_score":0.43919298,"about_ca_system_score_codex":0.0002222342,"about_ca_system_score_gemma":0.00020882336,"threshold_uncertainty_score":0.9994746},"labels":[],"label_agreement":null},{"id":"W4416583604","doi":"10.2139/ssrn.5795725","title":"Forecasting Social Science: Evidence from 100 Projects","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"University of Toronto","funders":"","keywords":"Download; Set (abstract data type); Consensus forecast; Field (mathematics); Affect (linguistics); Data set","score_opus":0.27771820100406813,"score_gpt":0.4491877264042935,"score_spread":0.17146952540022536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416583604","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":[0.22948837,0.00562363,0.7432257,0.001086911,0.0016691315,0.0019996127,0.00006897012,0.0011307279,0.015706966],"genre_scores_gemma":[0.95240545,0.003065639,0.040551662,0.00008687638,0.0015920632,0.000117502575,0.000008175303,0.000072843126,0.0020997697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937263,0.00018657083,0.0008052493,0.00078343076,0.0010607615,0.0034376932],"domain_scores_gemma":[0.9968819,0.00075198675,0.0010124223,0.0005559234,0.0006914266,0.000106345986],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0056596645,0.0005067542,0.00068731804,0.0005365519,0.0008135485,0.0003470277,0.0019281515,0.00043771145,0.000036028043],"category_scores_gemma":[0.0043254253,0.00046948929,0.00028519708,0.0006037751,0.0003787615,0.0005790271,0.0014460959,0.009231807,0.000005281623],"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":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00011646163,0.00015854211,0.00058445596,0.00029666504,0.0003880086,0.00002596106,0.0034356646,0.000027348855,0.0019917802,0.8900069,0.0008335673,0.10213463],"study_design_scores_gemma":[0.00015123957,0.00012210467,0.000021050773,0.0015649946,0.00014060676,0.0000723531,0.0010205405,0.00066082244,0.0025006805,0.9932492,0.0000626307,0.0004338279],"about_ca_topic_score_codex":0.0001702593,"about_ca_topic_score_gemma":0.00031101695,"teacher_disagreement_score":0.7229171,"about_ca_system_score_codex":0.0058530234,"about_ca_system_score_gemma":0.023689276,"threshold_uncertainty_score":0.9997757},"labels":[],"label_agreement":null},{"id":"W4416667820","doi":"10.1007/s40572-025-00513-7","title":"Pitfalls of Using Negative Control Outcomes in Environmental Epidemiology","year":2025,"lang":"en","type":"article","venue":"Current Environmental Health Reports","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"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; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Epidemiology; Environmental epidemiology; MEDLINE; Incidence (geometry); Environmental pollution; Public health","score_opus":0.17524805033359694,"score_gpt":0.4832174802762613,"score_spread":0.3079694299426644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416667820","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":[0.96398,0.0021165994,0.03152548,0.00023175108,0.00042794124,0.0014399731,0.00007838775,0.00007355324,0.00012627865],"genre_scores_gemma":[0.9895939,0.00045028428,0.0095270425,0.00026051453,0.0000136671515,0.00006136033,0.000022944918,0.000024050403,0.00004623545],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966535,0.00037664472,0.0017658072,0.00048983196,0.00020967556,0.0005045265],"domain_scores_gemma":[0.99723876,0.0009982905,0.001121604,0.0005185547,0.000002688086,0.00012010069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011270333,0.00029136153,0.0010195218,0.00019430232,0.000079249476,0.0000026110472,0.00012843401,0.000117961696,0.00009377519],"category_scores_gemma":[0.00036997965,0.000276417,0.00013927554,0.0000732867,0.00033102548,0.00013516906,0.00014704073,0.00035598947,0.0000028531508],"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":[0.000037294863,0.0012007618,0.966837,0.0002637091,0.000045486362,0.00002991334,0.00025898352,0.00008710122,0.0013890382,0.0038391962,0.00013836495,0.025873153],"study_design_scores_gemma":[0.0016643959,0.00029826665,0.45803323,0.0007970018,0.000069407666,0.00009058113,0.0005134827,0.00077457423,0.006515069,0.52902824,0.00157566,0.000640077],"about_ca_topic_score_codex":0.00006507934,"about_ca_topic_score_gemma":0.000011548889,"teacher_disagreement_score":0.52518904,"about_ca_system_score_codex":0.0010664794,"about_ca_system_score_gemma":0.000073976604,"threshold_uncertainty_score":0.9999688},"labels":[],"label_agreement":null},{"id":"W4416705645","doi":"10.1177/01410768251380376","title":"Long overdue recognition of Klim McPherson’s 1974 article on sequential analysis of trial data JLL Bulletin: commentaries on the history of treatment evaluation","year":2025,"lang":"en","type":"article","venue":"Journal of the Royal Society of Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"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; Impact","funders":"","keywords":"Alternative medicine; MEDLINE; Clinical trial","score_opus":0.2798806997035428,"score_gpt":0.42528571711147817,"score_spread":0.14540501740793538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416705645","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":[0.96834266,0.0005739272,0.008289095,0.020041807,0.0006942718,0.0009803234,0.000090342015,0.000011976613,0.00097558735],"genre_scores_gemma":[0.9956893,0.0001581879,0.0031026776,0.0004997403,0.0001411148,0.000007298143,0.000019390065,0.000009261959,0.00037305587],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977523,0.0003572736,0.00093318615,0.00010781542,0.0007583159,0.000091080976],"domain_scores_gemma":[0.99550724,0.0016690675,0.0018581674,0.0005338975,0.00040725805,0.00002436868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029631148,0.00012328732,0.00064687163,0.00007898729,0.00003965457,0.0000019578326,0.00036933614,0.00007318415,0.00052041234],"category_scores_gemma":[0.0014769281,0.000065753346,0.0003808948,0.00021334029,0.00040573988,0.00003997956,0.00007411151,0.00019496908,1.8877384e-7],"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":[0.024343321,0.005396632,0.001973035,0.0008463178,0.020061402,0.0000024733101,0.022195917,0.005150887,0.030664273,0.0043093143,0.8445146,0.040541798],"study_design_scores_gemma":[0.14315686,0.040899295,0.012121381,0.016041879,0.09911389,0.0000094160705,0.02952041,0.12611604,0.35867423,0.16194381,0.011422497,0.000980319],"about_ca_topic_score_codex":0.0003095072,"about_ca_topic_score_gemma":0.000039800518,"teacher_disagreement_score":0.83309215,"about_ca_system_score_codex":0.0008471156,"about_ca_system_score_gemma":0.00021889119,"threshold_uncertainty_score":0.56981504},"labels":[],"label_agreement":null},{"id":"W4416757099","doi":"10.1080/26941899.2025.2583507","title":"Are Neural Representation Learning Methods a Viable Alternative to TMLE for Causal Estimation?","year":2025,"lang":"en","type":"article","venue":"Data Science in Science","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Feature learning; Representation (politics); Estimator; Variance (accounting); Causal inference; Artificial neural network; Deep learning","score_opus":0.42050086401940895,"score_gpt":0.6220922742342814,"score_spread":0.20159141021487242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416757099","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":[0.074868344,0.0000049975165,0.92246217,0.0005955965,0.00028996452,0.0007598858,0.00003240293,0.00013420246,0.0008524371],"genre_scores_gemma":[0.33553067,0.000001536914,0.6640273,0.0001729671,0.000011596383,0.00011046999,0.0000065824656,0.0000050231756,0.00013388318],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727076,0.00010723813,0.0004085855,0.001036332,0.00064106873,0.0005360382],"domain_scores_gemma":[0.9963258,0.0016890456,0.00028488933,0.0011341813,0.0004524352,0.000113649636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0093640555,0.00013347334,0.00023475909,0.0008263484,0.000584018,0.00036721496,0.00290131,0.000028973785,0.000008664995],"category_scores_gemma":[0.0601025,0.00012429904,0.000016979699,0.0054012774,0.0011169455,0.004476441,0.0014397937,0.0001901666,0.0000041720295],"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":[0.00008386008,0.0002969643,0.027083075,0.00016910414,0.000007767514,0.000015480644,0.004532276,0.057443496,0.28335547,0.42150068,0.0036234453,0.20188838],"study_design_scores_gemma":[0.000115668045,0.000049279257,0.0026743058,0.00011483431,0.0000055598994,0.0000026571674,0.0008990202,0.6812903,0.06545769,0.2488286,0.0003971246,0.00016494692],"about_ca_topic_score_codex":0.0001153088,"about_ca_topic_score_gemma":0.00006869477,"teacher_disagreement_score":0.6238468,"about_ca_system_score_codex":0.00029985516,"about_ca_system_score_gemma":0.00041761398,"threshold_uncertainty_score":0.94781464},"labels":[],"label_agreement":null},{"id":"W4416776461","doi":"10.52937/hira.25.5.2.e4","title":"Predictive Analytics on Drug Shortages and Future Challenges: A Review","year":2025,"lang":"en","type":"review","venue":"Health Insurance Review & Assessment Service Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Economic shortage; Predictive analytics; Analytics; Drug; Data analysis","score_opus":0.47794546858610765,"score_gpt":0.6274221429656508,"score_spread":0.14947667437954315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416776461","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":[5.48382e-8,0.9510514,0.00010581146,0.02676382,0.00017706607,0.015559699,0.00041951897,0.0003782768,0.0055443468],"genre_scores_gemma":[1.673385e-7,0.98094213,0.0055523044,0.0058762105,0.00044991839,0.0064917305,0.00022278521,0.0001833616,0.00028136346],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.983191,0.006952187,0.0033541478,0.0020424072,0.0026768134,0.0017834437],"domain_scores_gemma":[0.98643404,0.0062972107,0.0017717385,0.0031116526,0.0016952604,0.0006901193],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.016557096,0.0014309594,0.00840097,0.00079858076,0.0005589653,0.00008787473,0.0016677942,0.0005266626,0.00011535496],"category_scores_gemma":[0.0012589237,0.0010917376,0.0006274193,0.0038391135,0.00017370807,0.0003255478,0.0007931814,0.0051951217,0.000052588854],"study_design_candidate":"systematic_review","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":[0.0000022224458,0.00013267116,0.0000011929407,0.49675852,0.00010214828,0.000011313407,0.000022551427,1.5518614e-8,2.3621678e-9,0.01111073,0.012487058,0.47937158],"study_design_scores_gemma":[0.00006796769,0.00018820967,0.000008632995,0.4795633,0.00024514034,0.000016726553,0.000044253375,0.0000025196282,2.5510156e-8,0.0030657772,0.5164304,0.00036706266],"about_ca_topic_score_codex":0.000039050876,"about_ca_topic_score_gemma":0.00012127606,"teacher_disagreement_score":0.5039433,"about_ca_system_score_codex":0.0018492966,"about_ca_system_score_gemma":0.004981656,"threshold_uncertainty_score":0.999844},"labels":[],"label_agreement":null},{"id":"W4416781974","doi":"10.48550/arxiv.2511.20985","title":"Two-stage Estimation for Causal Inference Involving a Semi-continuous Exposure","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","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":"Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers; National Institute on Alcohol Abuse and Alcoholism; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Causal inference; Causal model; Inference; Estimation; Propensity score matching; Consistency (knowledge bases); Estimator; Marginal structural model","score_opus":0.1793615873005519,"score_gpt":0.3095050894872094,"score_spread":0.1301435021866575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416781974","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":[0.107257456,0.00014471372,0.881538,0.00004569107,0.000606874,0.0033709733,0.0005283039,0.0010530311,0.005455001],"genre_scores_gemma":[0.9080405,0.0006274911,0.07158853,0.00010224971,0.00013341245,0.000058106387,0.00019774865,0.00010299351,0.019148927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944516,0.00039697668,0.0012595053,0.002421115,0.00024710168,0.0012237238],"domain_scores_gemma":[0.99082893,0.003248398,0.0017241132,0.0024657913,0.0013601969,0.00037254207],"candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0010647989,0.0013795821,0.0017111601,0.0008420992,0.0006088978,0.00026969696,0.0018659204,0.0012768611,0.00026059485],"category_scores_gemma":[0.0029142194,0.0017783678,0.0006839825,0.0010926083,0.00045700296,0.0010863749,0.0022088033,0.0017790018,0.00005078933],"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":[0.00029249387,0.00038256543,0.0030621698,0.0027437208,0.00036698885,0.00014718478,0.0010426868,0.19651707,0.00054190046,0.7929255,0.00022622662,0.0017515033],"study_design_scores_gemma":[0.0015853553,0.0003368046,0.00006827855,0.0023202517,0.0007725188,0.000003774775,0.00095368794,0.46614274,0.003097484,0.5229271,0.000387152,0.0014048178],"about_ca_topic_score_codex":0.00036099562,"about_ca_topic_score_gemma":0.00047634987,"teacher_disagreement_score":0.8099494,"about_ca_system_score_codex":0.0013711732,"about_ca_system_score_gemma":0.0011433861,"threshold_uncertainty_score":0.99989545},"labels":[],"label_agreement":null},{"id":"W4416833813","doi":"10.2196/80911","title":"Establish a PrEP (Pre-Exposure Prophylaxis) Epidemiology, Modeling, and Surveillance (PREMISE) System to Analyze Trends in PrEP Uptake and the Impact of PrEP Programs and Policies: Protocol for a Natural Experiment and Modeling Study in the United States","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","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":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Protocol (science); Data collection; Matching (statistics); Pre-exposure prophylaxis; Program evaluation","score_opus":0.3626300923104187,"score_gpt":0.6189278606352093,"score_spread":0.2562977683247906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416833813","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42577833,0.000018414952,0.0011392095,0.00008653266,7.392898e-7,0.57288224,0.000010691818,0.000055947366,0.000027884864],"genre_scores_gemma":[0.45497304,0.0000013519522,0.0016626797,0.000006085301,0.0000074320988,0.54330957,0.0000034883158,0.000017275523,0.000019055908],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943439,0.0025274737,0.001178375,0.00076504884,0.00042685636,0.0007583714],"domain_scores_gemma":[0.99612373,0.0021671094,0.00024493653,0.00079803227,0.0005466082,0.00011959237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011142277,0.00037257888,0.0008885439,0.00078596524,0.0002054578,0.00023469487,0.0004887842,0.00017017762,0.0000010819147],"category_scores_gemma":[0.0024221782,0.0002043695,0.0000673412,0.0014076834,0.00041288938,0.00023505103,0.0005930924,0.00069599727,2.3028198e-8],"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":[0.04947034,0.008310818,0.6471666,0.023557404,0.00070120336,0.000026037942,0.16454348,0.02945846,0.001382813,0.026459588,0.0007792074,0.048144042],"study_design_scores_gemma":[0.009278306,0.008199476,0.008551076,0.0047325003,0.000007033868,0.000012076465,0.012868543,0.9275777,0.0000862926,0.028233636,0.0000695936,0.000383818],"about_ca_topic_score_codex":0.0027558259,"about_ca_topic_score_gemma":0.0008996106,"teacher_disagreement_score":0.8981192,"about_ca_system_score_codex":0.00021159353,"about_ca_system_score_gemma":0.0001378107,"threshold_uncertainty_score":0.83339465},"labels":[],"label_agreement":null},{"id":"W4417026703","doi":"10.48550/arxiv.2512.03254","title":"Assumption-Lean Differential Variance Inference for Heterogeneous Treatment Effect Detection","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","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":"Natural Sciences and Engineering Research Council of Canada; Svenska Sällskapet för Medicinsk Forskning","keywords":"Causal inference; Estimator; Average treatment effect; Inference; Observational study; Homogeneous; Treatment effect; Randomized experiment; Covariate","score_opus":0.122897541158739,"score_gpt":0.40795764254051187,"score_spread":0.28506010138177285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417026703","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":[0.4738573,0.00016164199,0.518239,0.00004589374,0.0017036871,0.004694223,0.00030210085,0.0007779493,0.00021815296],"genre_scores_gemma":[0.9758621,0.0011837032,0.011905658,0.00006528414,0.0007742356,0.006853397,0.0002481679,0.0001837375,0.002923742],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931429,0.00054352684,0.0019474805,0.0024334234,0.0005599581,0.0013727248],"domain_scores_gemma":[0.99066466,0.004153479,0.0015263559,0.0026948762,0.00062033045,0.00034032433],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00062126544,0.0021246641,0.0024897503,0.0004873292,0.0007150557,0.00023435954,0.0010988847,0.0016890484,0.00037696338],"category_scores_gemma":[0.0018851305,0.0019699684,0.0013154448,0.00036701624,0.0002933862,0.0003133431,0.00095271086,0.0012612868,0.00017869417],"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":[0.005732624,0.007526534,0.07913261,0.020639123,0.00933783,0.00017032892,0.0033584756,0.0059705777,0.14536157,0.01757228,0.00019369875,0.70500433],"study_design_scores_gemma":[0.0035717585,0.006034882,0.0044456674,0.003136497,0.0030809147,0.000033423345,0.00003354293,0.014696124,0.8653842,0.09510471,0.0017030087,0.0027752463],"about_ca_topic_score_codex":0.00018902033,"about_ca_topic_score_gemma":0.00036619158,"teacher_disagreement_score":0.7200227,"about_ca_system_score_codex":0.002184958,"about_ca_system_score_gemma":0.00040766175,"threshold_uncertainty_score":0.99960697},"labels":[],"label_agreement":null},{"id":"W4417029871","doi":"10.1215/00703370-12344620","title":"A Commentary on “Gender Bias in Parental Attitude: An Experimental Approach” by Begum, Grossman, and Islam (2018)","year":2025,"lang":"en","type":"article","venue":"Demography","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 Ottawa","funders":"","keywords":"Islam; Transparency (behavior); Randomization; Population; Random assignment; Research design","score_opus":0.1410463498715367,"score_gpt":0.40107064766773953,"score_spread":0.26002429779620284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417029871","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":[0.98528945,0.00065409526,0.0064327875,0.00033614165,0.000100766345,0.00078627194,0.00006911788,0.00039116773,0.0059402045],"genre_scores_gemma":[0.9784613,0.000048658218,0.019201856,0.0019267474,0.00002302548,0.00019171278,0.00008992788,0.000028011991,0.00002872781],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986183,0.00011537374,0.0003191601,0.0004371932,0.00019801492,0.00031195712],"domain_scores_gemma":[0.9992879,0.00014506707,0.000077818324,0.00039272007,0.000015510597,0.00008097286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023022012,0.00027280045,0.0002980454,0.0003545573,0.00010251529,0.000050019942,0.00021686684,0.00012490219,0.000021921753],"category_scores_gemma":[0.00001982916,0.00026094666,0.00007796435,0.00038840843,0.00019872822,0.00023481208,0.00012528544,0.00026200054,0.0000013730671],"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":[0.00030683022,0.008517356,0.35028145,0.0003673828,0.00031847457,0.000035354384,0.005419015,0.0000043437412,0.017681478,0.24118319,0.3701644,0.005720747],"study_design_scores_gemma":[0.00793803,0.002784285,0.046825007,0.00070400705,0.00022649224,0.000041403237,0.019675147,0.0012939153,0.16821669,0.7285696,0.02038837,0.0033370473],"about_ca_topic_score_codex":0.000041945128,"about_ca_topic_score_gemma":0.00003623216,"teacher_disagreement_score":0.4873864,"about_ca_system_score_codex":0.000064668144,"about_ca_system_score_gemma":0.0000084765115,"threshold_uncertainty_score":0.99998426},"labels":[],"label_agreement":null},{"id":"W4417317269","doi":"10.57264/cer-2025-0196","title":"R WE ready for reimbursement? A round-up of developments in real-world evidence relating to health technology assessment: part 23","year":2025,"lang":"en","type":"article","venue":"Journal of Comparative Effectiveness 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":"Kingston Health Sciences Centre; Public Health Ontario; University of Toronto","funders":"","keywords":"Transformative learning; Health technology; MEDLINE; Health information technology; Clinical trial; Evidence-based medicine; Real world evidence","score_opus":0.6211705210896415,"score_gpt":0.6597066368166193,"score_spread":0.03853611572697779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417317269","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":[0.6083534,0.0010423193,0.37552878,0.0030450213,0.0003961417,0.0062063057,0.000015230612,0.00008716319,0.0053256294],"genre_scores_gemma":[0.92515284,0.00030389446,0.073386885,0.000014930979,0.000027834009,0.00049794454,0.0000015970924,0.000019261102,0.0005948446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947508,0.0020589856,0.0014162472,0.00034019788,0.00083842635,0.0005953293],"domain_scores_gemma":[0.9842002,0.012314993,0.0007916934,0.0003570694,0.0022243322,0.0001117382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012851226,0.00022107291,0.0011965161,0.0026489673,0.00019538426,0.000039767157,0.0006027595,0.000110928835,0.0000063957714],"category_scores_gemma":[0.0033299942,0.00019485758,0.000086463864,0.002967677,0.00019911272,0.00042281215,0.0002762152,0.0010825358,0.0000020440748],"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":[0.0026845115,0.0009473848,0.062707596,0.0028523318,0.00041481742,0.000024822371,0.0032929927,0.00042381402,0.02720253,0.8764282,0.004693152,0.018327883],"study_design_scores_gemma":[0.0026804516,0.0048424113,0.04353916,0.03715877,0.000035280424,0.000010887425,0.004945456,0.00035731294,0.1273435,0.7751019,0.0035936295,0.0003912329],"about_ca_topic_score_codex":0.00007511421,"about_ca_topic_score_gemma":0.00044127394,"teacher_disagreement_score":0.3167994,"about_ca_system_score_codex":0.002204538,"about_ca_system_score_gemma":0.0018089096,"threshold_uncertainty_score":0.79460615},"labels":[],"label_agreement":null},{"id":"W4417410525","doi":"10.1016/j.cmpb.2025.109187","title":"Random forests for individual treatment effect estimation with the R package ITERF","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","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":"HEC Montréal","funders":"","keywords":"Random forest; Estimation; R package; Treatment effect; Random effects model; Average treatment effect","score_opus":0.13721998632751883,"score_gpt":0.48554932193520345,"score_spread":0.34832933560768464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417410525","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":[0.02767084,0.00031983462,0.9688238,0.0007995641,0.000084248575,0.0021477793,0.0000028386169,0.00011898874,0.000032137297],"genre_scores_gemma":[0.058640007,0.000019505005,0.94028693,0.00010821588,0.00006116656,0.0008055229,0.000030203759,0.000012128603,0.000036303645],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899346,0.0002705925,0.00022842774,0.000223653,0.000090712565,0.000193152],"domain_scores_gemma":[0.9965376,0.0030633851,0.00008781034,0.00023964165,0.00003752201,0.000034030996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017166616,0.00019124844,0.00039139777,0.00013638526,0.00007241013,0.00004701016,0.00012294775,0.00006843805,0.0000010634917],"category_scores_gemma":[0.000106393505,0.00008780185,0.00003838883,0.00030949453,0.00018603732,0.000050781455,0.00005413475,0.00008582963,9.033718e-8],"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":[0.00017029067,0.00006976822,0.0018687801,0.00017013209,0.000065888365,0.0000026049602,0.0005621091,0.0000019864171,0.000054920263,0.0033698543,0.00017839596,0.9934853],"study_design_scores_gemma":[0.024480497,0.020869274,0.010225838,0.0026550174,0.00088931207,0.000056332312,0.00016668411,0.08071882,0.013486797,0.8263447,0.019418117,0.00068857626],"about_ca_topic_score_codex":0.000010959443,"about_ca_topic_score_gemma":0.000028051229,"teacher_disagreement_score":0.9927967,"about_ca_system_score_codex":0.000037021255,"about_ca_system_score_gemma":0.000016722375,"threshold_uncertainty_score":0.35804555},"labels":[],"label_agreement":null},{"id":"W4417426866","doi":"10.48550/arxiv.2507.14391","title":"Policy relevance of causal quantities in networks","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Banff International Research Station for Mathematical Innovation and Discovery","keywords":"Relevance (law); Outcome (game theory); Representation (politics); Interpretation (philosophy); Contrast (vision); Causal inference","score_opus":0.20032257674614407,"score_gpt":0.30952604999941846,"score_spread":0.1092034732532744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417426866","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":[0.19470552,0.00014343228,0.7839351,0.000072112605,0.0002639798,0.0006856403,0.00008876048,0.00048491263,0.019620502],"genre_scores_gemma":[0.9882229,0.0012476654,0.0062664496,0.000034956105,0.00005555472,0.0000027000083,0.000011404375,0.000023056087,0.004135291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984979,0.00013521363,0.00039022355,0.0005671996,0.00006727747,0.00034218642],"domain_scores_gemma":[0.9977276,0.00071796187,0.00040395118,0.0009211673,0.00017094918,0.000058401674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025318272,0.00031761322,0.0006337862,0.000585916,0.000036301037,0.000012593011,0.0006937026,0.00045984585,0.000022720378],"category_scores_gemma":[0.00059418747,0.00038662713,0.0001563101,0.00073363126,0.00022681608,0.00014397143,0.0009953362,0.00082454557,0.0000025872232],"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":[0.00004773077,0.000079748876,0.0019579518,0.00038415604,0.00004037438,0.00006339724,0.00011743502,0.06456858,0.000013928891,0.9323253,0.00023357461,0.0001678469],"study_design_scores_gemma":[0.00022678138,0.000039163093,0.00022966904,0.0009170872,0.000052245567,8.6215067e-7,0.00013543913,0.03383112,0.00046477417,0.96370155,0.00007149864,0.00032979046],"about_ca_topic_score_codex":0.0007831564,"about_ca_topic_score_gemma":0.00069730444,"teacher_disagreement_score":0.7935174,"about_ca_system_score_codex":0.00035386873,"about_ca_system_score_gemma":0.00034499884,"threshold_uncertainty_score":0.99985856},"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},{"id":"W4417479607","doi":"10.1016/j.jval.2025.09.1447","title":"HPR37 Bridging the Gap: How Early Access Shapes Pricing and Reimbursed Populations in France","year":2025,"lang":"en","type":"article","venue":"Value in Health","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":"Network for Business Sustainability","funders":"","keywords":"Bridging (networking); Mode (computer interface)","score_opus":0.31934627059427295,"score_gpt":0.47770535900780214,"score_spread":0.1583590884135292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417479607","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":[0.9136276,0.00076169457,0.07209385,0.0117962025,0.000086659,0.00092158164,0.000003706424,0.00018195286,0.0005266993],"genre_scores_gemma":[0.9832215,0.00014313297,0.015880784,0.00050471484,0.000026117877,0.00006390754,8.459829e-7,0.000014100187,0.00014493517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99879646,0.00019387947,0.00036190922,0.00022614657,0.00013067522,0.00029093216],"domain_scores_gemma":[0.9989176,0.0006252339,0.00015400325,0.00023759826,0.00003144039,0.000034160115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007989224,0.00011642639,0.00024457357,0.00021987177,0.00012681556,0.000077742225,0.00022015443,0.00005810673,0.0000028731033],"category_scores_gemma":[0.00072849885,0.0000963414,0.000018818633,0.00060806464,0.00004903915,0.00026821473,0.0000991751,0.0003394629,4.1307317e-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":[0.000012156787,0.00009765671,0.33488882,0.0009311315,0.000008950223,0.000008788811,0.0037132679,0.0028494732,0.00023856855,0.63142866,0.0005242891,0.025298264],"study_design_scores_gemma":[0.00026652988,0.00003660029,0.2560689,0.0015015405,0.0000042065276,0.0000022122347,0.00018837738,0.0244679,0.0002264655,0.71691716,0.00017846093,0.000141665],"about_ca_topic_score_codex":0.0032833891,"about_ca_topic_score_gemma":0.0004175484,"teacher_disagreement_score":0.085488506,"about_ca_system_score_codex":0.00014764532,"about_ca_system_score_gemma":0.00008816953,"threshold_uncertainty_score":0.49635243},"labels":[],"label_agreement":null},{"id":"W4417479756","doi":"10.1016/j.jval.2025.09.2151","title":"HTA368 When Less Is More? Learnings From a Recent NICE Submission Utilizing a Novel Predictive Individual-Level Surrogacy Approach to Predict Overall Survival (OS) in the Absence of Trial-Level Evidence","year":2025,"lang":"en","type":"article","venue":"Value in Health","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":"MD Precision (Canada)","funders":"","keywords":"Nice; Overall survival; Survival analysis; Baseline (sea); MEDLINE","score_opus":0.5191381405924437,"score_gpt":0.45008090499140646,"score_spread":0.06905723560103721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417479756","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":[0.69272435,0.0009110413,0.2924463,0.0049309796,0.0003521545,0.006506106,0.000571553,0.00026100007,0.0012965555],"genre_scores_gemma":[0.86369264,0.0010545327,0.13316938,0.0012617547,0.00007834718,0.00052394025,0.00003120075,0.0000559595,0.00013225722],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99432,0.0012146039,0.0016358014,0.000898023,0.001207957,0.00072364236],"domain_scores_gemma":[0.9922172,0.005642985,0.0007531846,0.00097498426,0.00024951826,0.00016214485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0069967965,0.00040808928,0.00095305836,0.00047117518,0.00013254181,0.00006222711,0.001180807,0.0002630813,0.000017957904],"category_scores_gemma":[0.008260297,0.0003389634,0.000104743245,0.0011656145,0.00013672546,0.00044367244,0.00045130108,0.0010567518,0.0000015481182],"study_design_candidate":"theoretical_or_conceptual","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":[0.032793816,0.013015374,0.11484,0.009790625,0.00054323545,0.000033995842,0.48858875,0.0134856785,0.0053893435,0.23378798,0.017774418,0.06995679],"study_design_scores_gemma":[0.034715146,0.0032162564,0.23415522,0.04186789,0.00018833371,0.000015873919,0.046962366,0.059791643,0.005868131,0.56905615,0.001976561,0.0021864225],"about_ca_topic_score_codex":0.015238278,"about_ca_topic_score_gemma":0.0002947017,"teacher_disagreement_score":0.44162637,"about_ca_system_score_codex":0.0006671291,"about_ca_system_score_gemma":0.0011192574,"threshold_uncertainty_score":0.99990624},"labels":[],"label_agreement":null},{"id":"W4417480375","doi":"10.1016/j.jval.2025.09.2882","title":"RWD132 Out of Sight, Out of Mind? A Simulation Study Assessing the Use of Quantitative Bias Analysis for Outcome Misclassification in Single-Arm Trials With External Control Comparisons","year":2025,"lang":"en","type":"article","venue":"Value in Health","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":"Public Health Ontario","funders":"","keywords":"Outcome (game theory); Control (management); External validity; Clinical trial; Range (aeronautics)","score_opus":0.8275028844107982,"score_gpt":0.5910186809017658,"score_spread":0.23648420350903243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417480375","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":[0.4428477,0.000034442146,0.5551343,0.00014282166,0.000026291827,0.0017620547,0.000034404242,0.00001051779,0.0000074576296],"genre_scores_gemma":[0.87667495,0.0000031495413,0.12317827,0.000018113495,0.000005625975,0.00009048429,0.000004910613,0.000011302199,0.000013192426],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950082,0.0017797708,0.0024665506,0.00024456775,0.0003134652,0.00018748836],"domain_scores_gemma":[0.9758632,0.020791983,0.0025414005,0.00040644777,0.0003705945,0.000026373966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004983213,0.00016164192,0.0014712146,0.00066536805,0.00004263335,0.000022703289,0.00016393527,0.00006915144,0.000002543589],"category_scores_gemma":[0.006905961,0.00011158053,0.00014252581,0.0007314112,0.00010224808,0.00017639034,0.000020224848,0.00015725664,7.6297155e-8],"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":[0.0007940276,0.0038236466,0.5597974,0.0006923853,0.00047366403,6.0360463e-7,0.010775908,0.40525144,0.0028460366,0.014009046,0.0000068663057,0.0015289518],"study_design_scores_gemma":[0.0043322076,0.002295236,0.12495268,0.0015198695,0.00092229893,8.769291e-8,0.0071740146,0.8324628,0.004270299,0.021827273,0.00002151654,0.00022173804],"about_ca_topic_score_codex":0.0009105237,"about_ca_topic_score_gemma":0.0017886739,"teacher_disagreement_score":0.43484473,"about_ca_system_score_codex":0.00021444271,"about_ca_system_score_gemma":0.00022511512,"threshold_uncertainty_score":0.8267579},"labels":[],"label_agreement":null},{"id":"W4417481050","doi":"10.1016/j.jval.2025.09.3352","title":"MSR66 Dealing With Missing Data in Health Economic Studies of Small to Moderate Size: How to Minimize Bias","year":2025,"lang":"en","type":"article","venue":"Value in Health","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":"Centre hospitalier universitaire de Québec; Université Laval","funders":"","keywords":"Missing data; Imputation (statistics); Sample size determination; Matching (statistics); Sample (material); Propensity score matching","score_opus":0.538504278450313,"score_gpt":0.49361757745006957,"score_spread":0.044886701000243445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417481050","genre_codex":"empirical","genre_gemma":"methods","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":[0.6153342,0.0024687895,0.30848202,0.06911458,0.00022365847,0.0036199302,0.0001567031,0.0003137826,0.00028630652],"genre_scores_gemma":[0.30609107,0.0005036948,0.6915506,0.0016451511,0.00002212356,0.00005555881,0.000004731225,0.000035010475,0.00009202996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974214,0.0003315868,0.0010237214,0.00055606244,0.00013505026,0.00053221977],"domain_scores_gemma":[0.9962448,0.0021939941,0.0003966976,0.0009336582,0.00006747062,0.00016341406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029087104,0.00023322043,0.00093072676,0.00038845907,0.00008109345,0.000030385589,0.00043583903,0.000059350758,0.0000026988216],"category_scores_gemma":[0.0023208626,0.00021814671,0.00002143916,0.0003971944,0.000045415454,0.00014014526,0.00033675713,0.00023809298,0.0000015380848],"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":[0.0021848148,0.0011060617,0.023861166,0.03161312,0.00038520593,0.00007130557,0.0459206,0.35809433,0.00077286107,0.41620064,0.008139092,0.111650795],"study_design_scores_gemma":[0.004187784,0.0025155284,0.0029691074,0.044704903,0.000044252458,0.000018258628,0.012894304,0.14279383,0.0077869263,0.77756613,0.0027657636,0.001753184],"about_ca_topic_score_codex":0.004478184,"about_ca_topic_score_gemma":0.0040615094,"teacher_disagreement_score":0.38306862,"about_ca_system_score_codex":0.0009159761,"about_ca_system_score_gemma":0.0010268028,"threshold_uncertainty_score":0.8895765},"labels":[],"label_agreement":null},{"id":"W4417481417","doi":"10.1016/j.jval.2025.09.3482","title":"MSR206 Transporting Treatment Effects for Survival Outcomes Under Informative Censoring: A Simulation Study Using Summary-Level Data in the Target Population","year":2025,"lang":"en","type":"article","venue":"Value in Health","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":"York University; Simon Fraser University","funders":"","keywords":"Censoring (clinical trials); Weighting; Population; Inverse probability weighting; Aggregate data; Data source","score_opus":0.5533582391859345,"score_gpt":0.5444820383462802,"score_spread":0.008876200839654347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417481417","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":[0.6938322,0.000033955315,0.30165023,0.00023848594,0.000105373896,0.003965913,0.00005813801,0.00008245426,0.000033229026],"genre_scores_gemma":[0.94274175,0.00000739232,0.05687261,0.00009843277,0.000016342503,0.00012744688,0.00010567302,0.000016321057,0.000014040145],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978336,0.0004516976,0.0009027787,0.00026186075,0.00022929788,0.00032075885],"domain_scores_gemma":[0.99531347,0.0037510607,0.00033265437,0.0005356399,0.00004086597,0.000026332891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022564156,0.00019749795,0.00047129698,0.00023736706,0.00013652751,0.000026190399,0.00023782178,0.000064707805,7.245128e-7],"category_scores_gemma":[0.0007966927,0.00014537231,0.000039768332,0.00038263976,0.000013790863,0.000389251,0.000041331212,0.0001514914,1.7214616e-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":[0.00011038888,0.0010849228,0.61639935,0.0010620048,0.000059187245,0.0000035111186,0.015175395,0.32190272,0.000008048455,0.039636303,0.0000070475144,0.0045511085],"study_design_scores_gemma":[0.0023292834,0.00043655396,0.38526657,0.00061404466,0.000045504206,3.423785e-7,0.005257261,0.42634442,0.00004684268,0.17939216,0.00003141825,0.00023560143],"about_ca_topic_score_codex":0.0053917044,"about_ca_topic_score_gemma":0.0015447141,"teacher_disagreement_score":0.24890952,"about_ca_system_score_codex":0.00072677294,"about_ca_system_score_gemma":0.00014180191,"threshold_uncertainty_score":0.815068},"labels":[],"label_agreement":null},{"id":"W6889009026","doi":"10.25384/sage.21150918","title":"sj-docx-5-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.22514693702797306,"score_gpt":0.44020639408531165,"score_spread":0.2150594570573386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889009026","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":[0.22302979,0.00007803673,0.7000128,0.000055624507,0.00042201835,0.0038809874,0.07226219,0.00018842408,0.00007013807],"genre_scores_gemma":[0.9480983,0.00013987339,0.034726296,0.00013985854,0.00052073965,0.0014634581,0.014617232,0.00017846566,0.00011580625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606895,0.0008089491,0.0009063005,0.0007342108,0.00089677784,0.0005847932],"domain_scores_gemma":[0.9975344,0.00066055864,0.00047251044,0.0010926174,0.00011739683,0.00012251493],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004624949,0.0003512057,0.00080948556,0.000617503,0.0003619905,0.00019285288,0.000815929,0.00008751249,0.011185649],"category_scores_gemma":[0.00013859646,0.00036699753,0.00016939938,0.00063816784,0.000036213238,0.0010650842,0.00062823953,0.00043094505,0.0000048040283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01956208,0.00983323,0.0019317662,0.00085437554,0.00909926,0.0012130114,0.0049648057,0.46738014,0.43125352,0.0022530633,0.022480218,0.029174536],"study_design_scores_gemma":[0.01148728,0.0021253387,0.0004452809,0.00091583485,0.004197104,0.00019020493,0.0015346351,0.47182655,0.07240957,0.42900407,0.0032970493,0.0025670892],"about_ca_topic_score_codex":0.0007380892,"about_ca_topic_score_gemma":0.00019664991,"teacher_disagreement_score":0.72506845,"about_ca_system_score_codex":0.0010511407,"about_ca_system_score_gemma":0.00015079646,"threshold_uncertainty_score":0.9998782},"labels":[],"label_agreement":null},{"id":"W6889071373","doi":"10.25384/sage.19561100","title":"sj-docx-1-msj-10.1177_13524585221085733 – Supplemental material for Recommendations for the use of propensity score methods in multiple sclerosis research","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"University of British Columbia; Providence Health Care","funders":"","keywords":"Propensity score matching; Multiple sclerosis; MEDLINE; Fingolimod; Mallinckrodt","score_opus":0.8819585361904688,"score_gpt":0.5843098793734013,"score_spread":0.29764865681706754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889071373","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":[0.025136586,0.0005080088,0.8013221,0.00835844,0.0006001331,0.009428906,0.15449318,0.00013021637,0.00002243624],"genre_scores_gemma":[0.022939153,0.0006747664,0.9714938,0.00011947334,0.00014466194,0.0015416845,0.0027101978,0.00007353149,0.0003027594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966509,0.0010872306,0.0008853957,0.0004006624,0.0004742604,0.0005015893],"domain_scores_gemma":[0.99024045,0.0075174565,0.00044978186,0.0013885106,0.00033623655,0.00006756144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0110655185,0.00017305517,0.00040679448,0.0002585436,0.0008339546,0.00016389076,0.0014845557,0.00005833754,0.011591122],"category_scores_gemma":[0.005682514,0.00013613899,0.00009114631,0.00043680813,0.0001387454,0.00081997464,0.0023182505,0.00052879896,0.0000010698242],"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":[0.001081905,0.00095383415,0.0013396221,0.00022134726,0.0002019992,0.000005189498,0.0010010896,0.000052245276,0.13379714,0.0012911641,0.67209744,0.18795699],"study_design_scores_gemma":[0.0045149312,0.0013386179,0.0012555845,0.0011817378,0.00025077743,0.00005809174,0.0042440444,0.010909934,0.21763793,0.19025345,0.5675701,0.0007848083],"about_ca_topic_score_codex":0.00026707165,"about_ca_topic_score_gemma":0.00048670833,"teacher_disagreement_score":0.18896228,"about_ca_system_score_codex":0.00022075356,"about_ca_system_score_gemma":0.0001428709,"threshold_uncertainty_score":0.9893124},"labels":[],"label_agreement":null},{"id":"W6889103111","doi":"10.25384/sage.20210629","title":"sj-pdf-3-mdm-10.1177_0272989X221103163 – Supplemental material for An Introductory Tutorial on Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis","score_opus":0.2633656101172559,"score_gpt":0.4509371966833401,"score_spread":0.1875715865660842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889103111","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":[0.5039814,0.00006273865,0.45711064,0.00004545047,0.00062125304,0.0027935435,0.035214156,0.00014249654,0.000028313618],"genre_scores_gemma":[0.9521593,0.00009621453,0.032175377,0.000077663986,0.00084274134,0.0007448131,0.013758976,0.000111882444,0.000033059197],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99610215,0.0010038763,0.00084561243,0.0007898124,0.00071531185,0.000543228],"domain_scores_gemma":[0.9975692,0.00045405756,0.00042610144,0.001289572,0.00012997369,0.00013109154],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004866784,0.0003306653,0.0007444291,0.0006364191,0.00037569617,0.00017712175,0.0008239651,0.00008277072,0.0094562145],"category_scores_gemma":[0.00018473662,0.0003516629,0.0001275591,0.00066662306,0.000047860478,0.0016218079,0.00045653398,0.00044703853,0.0000022891322],"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":[0.01864531,0.011038762,0.00423526,0.0009176977,0.0066583753,0.00048467214,0.008163002,0.34595338,0.53776085,0.0040705567,0.023609178,0.038462948],"study_design_scores_gemma":[0.011079428,0.0038430993,0.0017870079,0.000728696,0.004146326,0.00016760961,0.0038595342,0.31355223,0.06290881,0.5878931,0.00696128,0.0030728278],"about_ca_topic_score_codex":0.0008269646,"about_ca_topic_score_gemma":0.00044323588,"teacher_disagreement_score":0.5838226,"about_ca_system_score_codex":0.0009329984,"about_ca_system_score_gemma":0.00015612198,"threshold_uncertainty_score":0.99989355},"labels":[],"label_agreement":null},{"id":"W6889141474","doi":"10.25384/sage.21150909","title":"sj-docx-2-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.2244178642766549,"score_gpt":0.4398329656675916,"score_spread":0.21541510139093673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889141474","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":[0.22570391,0.000078001525,0.697366,0.00005561108,0.00042186838,0.0038767096,0.072240345,0.00018823678,0.00006933368],"genre_scores_gemma":[0.9483417,0.00013916938,0.034462698,0.00013930924,0.00051824236,0.0014551759,0.014652284,0.0001775607,0.000113845635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606824,0.00080933375,0.0009064346,0.0007342911,0.0008968092,0.0005848707],"domain_scores_gemma":[0.9975342,0.0006606191,0.00047252697,0.0010927236,0.000117409036,0.00012252622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004628289,0.00035121836,0.00080954056,0.0006176022,0.00036199702,0.0001927933,0.00081600895,0.00008752654,0.011112795],"category_scores_gemma":[0.00013867115,0.00036701016,0.00016940426,0.00063832686,0.000036215424,0.0010647483,0.0006284419,0.00043109144,0.0000048291163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019570114,0.009674614,0.0019194501,0.00084911607,0.009042662,0.0012067492,0.0049366015,0.4654988,0.43375093,0.00222739,0.0222292,0.029094376],"study_design_scores_gemma":[0.011503282,0.0021355553,0.00044539018,0.00091758027,0.0042045717,0.00019055078,0.0015383697,0.472894,0.07301157,0.42728788,0.0032995213,0.0025717102],"about_ca_topic_score_codex":0.0007326639,"about_ca_topic_score_gemma":0.00019498444,"teacher_disagreement_score":0.72263783,"about_ca_system_score_codex":0.0010510723,"about_ca_system_score_gemma":0.00015008404,"threshold_uncertainty_score":0.99987817},"labels":[],"label_agreement":null},{"id":"W6889165924","doi":"10.25384/sage.21150915","title":"sj-docx-4-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.22514693702797306,"score_gpt":0.44020639408531165,"score_spread":0.2150594570573386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889165924","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":[0.22343016,0.00007786733,0.6997756,0.00005550159,0.00042118342,0.0038677373,0.07211453,0.00018801003,0.000069416514],"genre_scores_gemma":[0.9483797,0.00013868217,0.03448278,0.00013887437,0.0005166339,0.0014495827,0.0146031985,0.00017701359,0.00011353545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606836,0.00080925034,0.00090643263,0.0007342784,0.0008967964,0.00058486365],"domain_scores_gemma":[0.9975343,0.00066055846,0.00047252432,0.0010927188,0.00011739472,0.00012252646],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004627836,0.0003512194,0.0008095397,0.000617704,0.00036197377,0.00019276983,0.0008163645,0.00008752378,0.011112365],"category_scores_gemma":[0.00013864378,0.0003670112,0.00016940308,0.00063839357,0.000036209363,0.0010646547,0.00062842545,0.00043107953,0.0000048290963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01950223,0.009655668,0.001936494,0.00084744405,0.009024883,0.0012043528,0.004917778,0.4692738,0.43021318,0.002228956,0.022170585,0.029024618],"study_design_scores_gemma":[0.011508075,0.0021298125,0.00044764206,0.00091783615,0.004205712,0.00019061156,0.0015360572,0.473425,0.07258966,0.42716986,0.0033073537,0.0025723844],"about_ca_topic_score_codex":0.00073354173,"about_ca_topic_score_gemma":0.00019522868,"teacher_disagreement_score":0.72494954,"about_ca_system_score_codex":0.0010510061,"about_ca_system_score_gemma":0.00015007111,"threshold_uncertainty_score":0.99987817},"labels":[],"label_agreement":null},{"id":"W6901953627","doi":"10.6084/m9.figshare.16823703.v1","title":"Additional file 1 of Statistical reanalysis of vascular event outcomes in primary and secondary vascular prevention trials","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"Western University","funders":"","keywords":"Vascular access; Event (particle physics); Clinical trial; Vascular disease; MEDLINE","score_opus":0.1257677356698285,"score_gpt":0.3932770141944738,"score_spread":0.26750927852464534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901953627","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011652952,0.00010264144,0.0009025144,0.0000057517127,0.0000030499716,0.00020699408,0.99792504,0.000024784318,0.000712716],"genre_scores_gemma":[0.0009492703,0.000010660234,0.08887705,0.00001591243,0.000012588276,0.0005707718,0.9093301,0.0000160948,0.00021753694],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984527,0.00027093032,0.00067104015,0.00019413739,0.0003045927,0.000106582054],"domain_scores_gemma":[0.9929791,0.0061633205,0.0003500064,0.00027437744,0.0001964516,0.000036707628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024087886,0.00011310737,0.0006980566,0.000093855895,0.000014138938,0.0000069829803,0.00007500817,0.000088332934,0.97386354],"category_scores_gemma":[0.028721849,0.00010503348,0.00022001137,0.00015798555,0.000014672997,0.00010648626,0.000106721105,0.00012028573,0.000018710747],"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":[0.0000052052205,0.00018881024,0.000008887193,0.0007443723,0.00020299858,0.000012714307,0.000030061177,0.0000027784802,0.00007971175,0.0005467683,0.9924187,0.0057589645],"study_design_scores_gemma":[0.0031647498,0.0005245706,0.09040602,0.026868103,0.00087487727,0.000026243664,0.00047592973,0.0006500321,0.015091087,0.5828249,0.27771458,0.0013789068],"about_ca_topic_score_codex":0.0000016924056,"about_ca_topic_score_gemma":0.000013935088,"teacher_disagreement_score":0.9738448,"about_ca_system_score_codex":0.000044057066,"about_ca_system_score_gemma":0.0001890812,"threshold_uncertainty_score":0.97945964},"labels":[],"label_agreement":null},{"id":"W6901985572","doi":"10.6084/m9.figshare.20006741.v1","title":"Examining the correlation between treatment effects in clinical trials and economic modeling","year":2022,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Correlation; Clinical trial; Covariance; Depression (economics); Identification (biology); Analysis of covariance; Treatment effect; Statistical model","score_opus":0.6675690856680238,"score_gpt":0.5169106529655247,"score_spread":0.150658432702499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901985572","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":[0.93295145,0.00070737634,0.0062599117,0.00021558015,0.00022713405,0.005014664,0.05210361,0.0006388227,0.0018814275],"genre_scores_gemma":[0.99444103,0.000005411131,0.0013492355,0.00002631811,0.000098992474,0.0008603519,0.0031710744,0.000017680788,0.00002989623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851555,0.0006390369,0.0004944319,0.00017494986,0.00006526286,0.00011076884],"domain_scores_gemma":[0.9909054,0.008671902,0.00020550922,0.00018179143,0.000008010256,0.000027402413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011557067,0.000094556664,0.00033576012,0.000042364496,0.000096440934,0.000019845704,0.000078561985,0.00005018448,0.003750377],"category_scores_gemma":[0.0042811544,0.00006994273,0.00004820064,0.000039329636,0.000004032268,0.00007355082,0.00013088624,0.00019983204,0.00002524774],"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":[0.00025440063,0.00048910367,0.045308538,0.0006402726,0.00046972017,0.00011841674,0.0071601802,0.06563502,0.00006458879,0.012491292,0.06191258,0.80545586],"study_design_scores_gemma":[0.0033208914,0.0018076415,0.010459895,0.0013921869,0.00017817674,0.000018474648,0.0008155808,0.70426756,0.00034487582,0.27113712,0.0055183303,0.0007392534],"about_ca_topic_score_codex":0.000009665632,"about_ca_topic_score_gemma":0.00001201023,"teacher_disagreement_score":0.80471665,"about_ca_system_score_codex":0.00018296788,"about_ca_system_score_gemma":0.000038325623,"threshold_uncertainty_score":0.9971603},"labels":[],"label_agreement":null},{"id":"W6902071779","doi":"10.6084/m9.figshare.20006741","title":"Examining the correlation between treatment effects in clinical trials and economic modeling","year":2022,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Correlation; Clinical trial; Covariance; Depression (economics); Identification (biology); Analysis of covariance; Treatment effect; Statistical model","score_opus":0.6675690856680238,"score_gpt":0.5169106529655247,"score_spread":0.150658432702499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902071779","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":[0.93295145,0.00070737634,0.0062599117,0.00021558015,0.00022713405,0.005014664,0.05210361,0.0006388227,0.0018814275],"genre_scores_gemma":[0.99444103,0.000005411131,0.0013492355,0.00002631811,0.000098992474,0.0008603519,0.0031710744,0.000017680788,0.00002989623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851555,0.0006390369,0.0004944319,0.00017494986,0.00006526286,0.00011076884],"domain_scores_gemma":[0.9909054,0.008671902,0.00020550922,0.00018179143,0.000008010256,0.000027402413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011557067,0.000094556664,0.00033576012,0.000042364496,0.000096440934,0.000019845704,0.000078561985,0.00005018448,0.003750377],"category_scores_gemma":[0.0042811544,0.00006994273,0.00004820064,0.000039329636,0.000004032268,0.00007355082,0.00013088624,0.00019983204,0.00002524774],"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":[0.00025440063,0.00048910367,0.045308538,0.0006402726,0.00046972017,0.00011841674,0.0071601802,0.06563502,0.00006458879,0.012491292,0.06191258,0.80545586],"study_design_scores_gemma":[0.0033208914,0.0018076415,0.010459895,0.0013921869,0.00017817674,0.000018474648,0.0008155808,0.70426756,0.00034487582,0.27113712,0.0055183303,0.0007392534],"about_ca_topic_score_codex":0.000009665632,"about_ca_topic_score_gemma":0.00001201023,"teacher_disagreement_score":0.80471665,"about_ca_system_score_codex":0.00018296788,"about_ca_system_score_gemma":0.000038325623,"threshold_uncertainty_score":0.9971603},"labels":[],"label_agreement":null},{"id":"W6902148588","doi":"10.6084/m9.figshare.26650401","title":"Additional file 1 of A blueprint for a multi-disease, multi-domain Bayesian adaptive platform trial incorporating adult and paediatric subgroups: the Staphylococcus aureus Network Adaptive Platform trial","year":2024,"lang":"en","type":"article","venue":"Open MIND","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":"","keywords":"Blueprint; Bayesian network; Bayesian probability; Adaptive design; Staphylococcus aureus; Clinical trial","score_opus":0.17231381836221704,"score_gpt":0.3783417479961035,"score_spread":0.20602792963388644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902148588","genre_codex":"dataset","genre_gemma":"methods","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":[0.013719371,0.00025518858,0.4615161,0.00010383365,0.00054614973,0.025861854,0.49596062,0.00013959261,0.0018972759],"genre_scores_gemma":[0.03007464,0.000009047391,0.95502555,0.000033432207,0.0010710943,0.008269365,0.0049087396,0.000092714676,0.00051542313],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732065,0.00010756819,0.0009840657,0.0006888553,0.00040407068,0.00049478794],"domain_scores_gemma":[0.989615,0.008811206,0.00066625664,0.00041466425,0.00028559574,0.00020723902],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009217089,0.0004409501,0.00064169045,0.00014607715,0.0003102415,0.00023417744,0.00056265667,0.00022379025,0.023458669],"category_scores_gemma":[0.0028210918,0.00033069364,0.0002600134,0.00045002493,0.0002792191,0.0006614682,0.00051242544,0.00047337037,0.000023593979],"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":[0.24067119,0.0018392311,0.000008982341,0.0002971835,0.001038267,0.00013096162,0.0043647247,0.00017378863,0.00006224924,0.06593234,0.5570946,0.12838648],"study_design_scores_gemma":[0.14473891,0.007064844,0.00006213866,0.0030647689,0.0006687366,0.000013251674,0.009255206,0.23485382,0.0003567841,0.55492413,0.042958714,0.0020387175],"about_ca_topic_score_codex":0.000030710875,"about_ca_topic_score_gemma":0.0005288442,"teacher_disagreement_score":0.5141359,"about_ca_system_score_codex":0.00018302958,"about_ca_system_score_gemma":0.000662612,"threshold_uncertainty_score":0.9999145},"labels":[],"label_agreement":null},{"id":"W6902166563","doi":"10.6084/m9.figshare.26695770","title":"Additional file 2 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Relation (database); Mediation; Binary data; Sensitivity (control systems); Component (thermodynamics)","score_opus":0.42631790204951725,"score_gpt":0.46249822641172494,"score_spread":0.036180324362207694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902166563","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012223887,0.000076585886,0.0014842299,0.000024485726,0.000012408956,0.003983871,0.9820519,0.00013594591,0.000006655933],"genre_scores_gemma":[0.43748724,3.4408322e-7,0.07311745,0.00002239661,0.00011292127,0.030967481,0.45819035,0.00007569012,0.0000261125],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984545,0.00019812047,0.00047719062,0.00034859244,0.00035472555,0.00016688136],"domain_scores_gemma":[0.98566854,0.013379933,0.00030204406,0.0001954294,0.00037390244,0.000080131365],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000535275,0.00020407702,0.0004247366,0.0001807855,0.000069527276,0.000028806797,0.00007927375,0.00014375694,0.18224183],"category_scores_gemma":[0.016519815,0.0001499564,0.0000659157,0.00013945729,0.000029963334,0.00024368164,0.000035360863,0.00009722483,0.0000012300255],"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":[0.0006969166,0.0008504602,0.00008156349,0.0038824044,0.0001520258,0.000086967615,0.0010064205,0.000032249096,0.00014184904,0.000052851476,0.9759767,0.017039588],"study_design_scores_gemma":[0.0028586937,0.004279112,0.00095825584,0.003020346,0.00043183635,0.00009709853,0.0015656376,0.9756482,0.0004221073,0.00942568,0.0008788251,0.00041417906],"about_ca_topic_score_codex":7.5849607e-7,"about_ca_topic_score_gemma":0.000015098742,"teacher_disagreement_score":0.975616,"about_ca_system_score_codex":0.00005785784,"about_ca_system_score_gemma":0.00029403027,"threshold_uncertainty_score":0.9917645},"labels":[],"label_agreement":null},{"id":"W6907708011","doi":"10.25384/sage.21150921","title":"sj-pdf-7-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.2213778857077405,"score_gpt":0.4381728732261409,"score_spread":0.2167949875184004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907708011","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":[0.20471601,0.000068228655,0.7356573,0.000055580353,0.00042748588,0.0039731823,0.054828875,0.00017418632,0.00009914683],"genre_scores_gemma":[0.9401343,0.00015771909,0.041210145,0.00016705293,0.0006123644,0.0017369647,0.015569519,0.00019812697,0.00021381122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961177,0.0008136761,0.00089570804,0.00071987486,0.0008791991,0.0005738568],"domain_scores_gemma":[0.9975785,0.0006572393,0.0004669527,0.0010602365,0.00011570324,0.000121366975],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046139355,0.00034520504,0.0007978367,0.0006106693,0.00035861836,0.00018907603,0.0007966876,0.00008973785,0.015190251],"category_scores_gemma":[0.00014742588,0.00036186035,0.0001674957,0.0006224095,0.000035649915,0.0010418879,0.00060741504,0.00042576884,0.000009115142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018735496,0.009559291,0.0018934907,0.0008799209,0.009033526,0.0011058054,0.004546243,0.45946917,0.44405565,0.0017581721,0.022072542,0.0268907],"study_design_scores_gemma":[0.011881609,0.0021469686,0.00043585018,0.000979061,0.004197533,0.00017671898,0.001557434,0.48461583,0.070881754,0.41734806,0.003232498,0.0025466771],"about_ca_topic_score_codex":0.000679951,"about_ca_topic_score_gemma":0.00019516263,"teacher_disagreement_score":0.73541826,"about_ca_system_score_codex":0.0010458567,"about_ca_system_score_gemma":0.00014881558,"threshold_uncertainty_score":0.99988335},"labels":[],"label_agreement":null},{"id":"W6907773071","doi":"10.25384/sage.21150906","title":"sj-docx-1-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.2244314052399313,"score_gpt":0.43983683059009443,"score_spread":0.21540542535016313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907773071","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":[0.2286133,0.00007785778,0.6919825,0.000055362485,0.00042104258,0.003863886,0.074729554,0.00018830232,0.00006815619],"genre_scores_gemma":[0.9472586,0.00014308946,0.03506044,0.00014073502,0.0005221413,0.0014385863,0.01514532,0.00017896973,0.00011210553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607307,0.00080852624,0.0009054542,0.00073346705,0.00089536235,0.0005841467],"domain_scores_gemma":[0.99753875,0.0006589223,0.00047205994,0.0010910085,0.00011688767,0.00012239016],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004581912,0.00035096126,0.00080859713,0.00061667745,0.00036079893,0.00019214007,0.00081570796,0.000087457694,0.011067622],"category_scores_gemma":[0.00013683295,0.00036677977,0.00016930918,0.0006376662,0.00003617183,0.0010633668,0.00062867743,0.00043156018,0.000004738642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01947698,0.009796247,0.0019409582,0.0008511191,0.009032637,0.001219354,0.004937407,0.46316773,0.43575612,0.00212639,0.022411866,0.02928319],"study_design_scores_gemma":[0.011631701,0.0021370545,0.00045411728,0.00092698395,0.004231049,0.00019689184,0.0015720644,0.4743892,0.0709561,0.42754123,0.003375462,0.002588159],"about_ca_topic_score_codex":0.0007116835,"about_ca_topic_score_gemma":0.00019570513,"teacher_disagreement_score":0.71864533,"about_ca_system_score_codex":0.0010499863,"about_ca_system_score_gemma":0.00014931637,"threshold_uncertainty_score":0.9998784},"labels":[],"label_agreement":null},{"id":"W6907780344","doi":"10.25384/sage.20210623","title":"sj-pdf-1-mdm-10.1177_0272989X221103163 – Supplemental material for An Introductory Tutorial on Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis","score_opus":0.26336814566487415,"score_gpt":0.4509560228082778,"score_spread":0.18758787714340364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907780344","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":[0.50817895,0.00006256048,0.45241812,0.000044576613,0.00062178465,0.002787445,0.03571587,0.00014233895,0.000028326009],"genre_scores_gemma":[0.95147115,0.00010133284,0.032460682,0.00007934644,0.0008674555,0.0007535372,0.014118476,0.000113959264,0.000034063574],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99609816,0.0010053277,0.0008463814,0.00079052994,0.00071578036,0.00054384145],"domain_scores_gemma":[0.99756026,0.00046160014,0.00042638005,0.0012913311,0.0001292873,0.00013116655],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00487354,0.00033085988,0.0007448364,0.0006366723,0.00037559564,0.00017517072,0.0008236956,0.00008329463,0.009304122],"category_scores_gemma":[0.00018380405,0.00035186333,0.00012896144,0.0006640553,0.00004890535,0.0016172848,0.0004558782,0.00044992226,0.000002212443],"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":[0.018509239,0.010754145,0.0042521674,0.0009116042,0.006599062,0.00048205635,0.007981954,0.3460677,0.5406625,0.0038850938,0.022662835,0.037231646],"study_design_scores_gemma":[0.011175879,0.0038570554,0.0017597715,0.0007382863,0.0042001423,0.00017068912,0.003801366,0.31857032,0.063141644,0.58244616,0.007047639,0.0030910622],"about_ca_topic_score_codex":0.00080639054,"about_ca_topic_score_gemma":0.000445187,"teacher_disagreement_score":0.57856107,"about_ca_system_score_codex":0.0009231915,"about_ca_system_score_gemma":0.0001548196,"threshold_uncertainty_score":0.9998933},"labels":[],"label_agreement":null},{"id":"W6911956846","doi":"10.5281/zenodo.15318811","title":"La révolution causale à l'ère de l'IA : Vers une approche hybride entre théorie scientifique et découverte automatisée","year":2025,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear 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":"University of Ottawa","funders":"","keywords":"Context (archaeology); Perspective (graphical); Identity (music); Identification (biology)","score_opus":0.04567019172075941,"score_gpt":0.32683687552926055,"score_spread":0.2811666838085011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911956846","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":[0.007293384,0.00050706737,0.5857328,0.0060463334,0.00041775152,0.0012828197,0.00045138862,0.0033018715,0.3949666],"genre_scores_gemma":[0.7218479,0.0021970577,0.06843569,0.0011469176,0.0003501083,0.0000023073364,0.002935521,0.0051376927,0.19794683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99606407,0.0013874675,0.0005390829,0.00070508115,0.0005155345,0.0007887545],"domain_scores_gemma":[0.99745613,0.000270893,0.00026097373,0.00084090536,0.00091654033,0.0002545771],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023570578,0.0003521138,0.00034276518,0.00043581912,0.0016798504,0.0009993187,0.0011895712,0.00028216062,0.0050137904],"category_scores_gemma":[0.0035299414,0.0004145397,0.00011503099,0.0016032229,0.00071572664,0.00067337544,0.0014727227,0.00088735885,0.0021271468],"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":[0.000044150675,0.00032339877,0.000006005498,0.00084694906,0.000099454686,0.00004274128,0.0031777802,0.00012186552,0.0069642034,0.39940205,0.5145206,0.0744508],"study_design_scores_gemma":[0.0005500067,0.00011507832,0.00019764491,0.0009185421,0.000099108525,0.0001425287,0.0012051057,0.0047850935,0.0055640335,0.091263495,0.8947929,0.00036642127],"about_ca_topic_score_codex":0.00015118139,"about_ca_topic_score_gemma":0.000011532482,"teacher_disagreement_score":0.7145545,"about_ca_system_score_codex":0.0013834476,"about_ca_system_score_gemma":0.000091867994,"threshold_uncertainty_score":0.99983066},"labels":[],"label_agreement":null},{"id":"W6920632261","doi":"10.6084/m9.figshare.14190234.v1","title":"Additional file 2 of Waist circumference prediction for epidemiological research using gradient boosted trees","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto","funders":"","keywords":"Circumference; Decision tree; Waist; Tree (set theory); Variable (mathematics)","score_opus":0.6877278544306521,"score_gpt":0.5092984696801275,"score_spread":0.1784293847505246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920632261","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006008047,0.00002529981,0.0005966143,0.000021269407,0.000010344423,0.0003071407,0.9972372,0.00012660057,0.0016154634],"genre_scores_gemma":[0.002565786,0.0000013798738,0.07187178,0.000023819122,0.00010398763,0.0020858708,0.92290914,0.00001798921,0.00042023024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870634,0.00015912672,0.00033022344,0.00027326256,0.00025868483,0.000272357],"domain_scores_gemma":[0.9834311,0.015152632,0.00015574318,0.00026386054,0.00093205116,0.00006458501],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015050561,0.000108507506,0.00024493152,0.00006932919,0.00011972578,0.000014082289,0.00015079654,0.00014212559,0.9550471],"category_scores_gemma":[0.08429934,0.0000983936,0.000098510216,0.00024298162,0.000035432367,0.000107634354,0.00012626265,0.00021734112,0.000063507636],"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":[0.0000068217787,0.000060033733,0.0000019343595,0.0001370107,0.000009241261,0.000004955946,0.000016889215,0.000004530031,0.0003839067,0.0013102605,0.9973916,0.000672851],"study_design_scores_gemma":[0.00017529879,0.0002927396,0.0010614557,0.007722105,0.000011262874,0.00004139595,0.00015723078,0.005546486,0.008126479,0.34094113,0.6356813,0.0002431535],"about_ca_topic_score_codex":0.0000011242549,"about_ca_topic_score_gemma":0.0000105604895,"teacher_disagreement_score":0.95498353,"about_ca_system_score_codex":0.00010945049,"about_ca_system_score_gemma":0.00017079376,"threshold_uncertainty_score":0.923414},"labels":[],"label_agreement":null},{"id":"W6920817604","doi":"10.6084/m9.figshare.14926918","title":"Additional file 1 of Comparing regression modeling strategies for predicting hometime","year":2021,"lang":"en","type":"article","venue":"Open MIND","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":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; University of Calgary","funders":"","keywords":"Calibration; Data set; Set (abstract data type); Regression analysis; Regression; Test set; Linear regression; Statistical model","score_opus":0.3198960684744691,"score_gpt":0.4457362568877681,"score_spread":0.12584018841329897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920817604","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":[0.031238424,0.00004758704,0.4140216,0.0000639901,0.00007648487,0.0013585427,0.38718054,0.000056140816,0.16595669],"genre_scores_gemma":[0.03609239,0.0000010367974,0.95125604,0.0000037638433,0.000040697883,0.00023008154,0.0112515725,0.000015723588,0.0011087261],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99930525,0.000022468137,0.00025537168,0.00017562711,0.00011878308,0.00012250355],"domain_scores_gemma":[0.99776465,0.0016724368,0.00015833626,0.00018080024,0.00019654943,0.000027246433],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011998705,0.00008488241,0.00022093793,0.000029978339,0.00006871272,0.00006848225,0.00018096,0.00005108508,0.39037153],"category_scores_gemma":[0.0013685441,0.00007858942,0.000042131418,0.00008148713,0.000023950397,0.00034332232,0.00018790098,0.00008198852,0.000011386271],"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":[0.000056157907,0.0002194012,0.000010374842,0.00015526831,0.000067220295,0.000010177631,0.000772945,0.0014673986,0.004897252,0.0072823935,0.95272416,0.032337222],"study_design_scores_gemma":[0.0004918884,0.0001377986,0.0000070232254,0.004583519,0.000048983493,0.000024168741,0.0069381706,0.33582297,0.04365117,0.54189795,0.06597546,0.00042090507],"about_ca_topic_score_codex":0.0000022299403,"about_ca_topic_score_gemma":0.000016852708,"teacher_disagreement_score":0.88674873,"about_ca_system_score_codex":0.000020660886,"about_ca_system_score_gemma":0.00015918826,"threshold_uncertainty_score":0.61018574},"labels":[],"label_agreement":null},{"id":"W6920865536","doi":"10.6084/m9.figshare.25909997.v1","title":"Additional file 1 of Metabolome-wide Mendelian randomization for age at menarche and age at natural menopause","year":2024,"lang":"en","type":"dataset","venue":"Figshare","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":"Université de Montréal","funders":"","keywords":"Menarche; Mendelian randomization; Menopause; Natural (archaeology); Mendelian inheritance; Population","score_opus":0.11167110633416645,"score_gpt":0.3665287887164694,"score_spread":0.25485768238230294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920865536","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.812462e-7,0.00027672187,0.0000043595087,0.000018263352,0.0000406097,0.0011756272,0.99815613,0.00016339272,0.00016470997],"genre_scores_gemma":[5.307968e-7,0.000030451552,0.010730769,0.00009959937,0.000118851945,0.006426831,0.97823346,0.00006688802,0.0042926506],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830127,0.00007321425,0.0005088664,0.0004712104,0.0003552726,0.00029017913],"domain_scores_gemma":[0.99043226,0.008372594,0.00046587465,0.00046156175,0.00017907625,0.00008865981],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000086447486,0.00041160925,0.0007394821,0.00021043172,0.000104695304,0.000046824392,0.0003078131,0.00034919282,0.947632],"category_scores_gemma":[0.015278627,0.00035349585,0.00015146962,0.00015582147,0.00003708838,0.0001441043,0.00060272845,0.00034987947,0.0009857493],"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":[0.000108919055,0.000023053926,2.837083e-9,0.0020679743,0.00012366757,0.000042308002,0.000024308723,3.2677957e-7,0.000031423097,0.000018367444,0.9974944,0.00006524205],"study_design_scores_gemma":[0.00056095084,0.00006589588,5.4017625e-7,0.0039693266,0.00013846335,0.000012354885,0.0000071131317,0.000021035468,0.00049859117,0.010543753,0.98383546,0.00034648902],"about_ca_topic_score_codex":0.0000018335702,"about_ca_topic_score_gemma":0.00013955298,"teacher_disagreement_score":0.9466463,"about_ca_system_score_codex":0.00021516008,"about_ca_system_score_gemma":0.00007129488,"threshold_uncertainty_score":0.9998917},"labels":[],"label_agreement":null},{"id":"W6920889807","doi":"10.6084/m9.figshare.26695773","title":"Additional file 3 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Regression analysis; Regression; Binary data; Range (aeronautics); Sensitivity (control systems); Relation (database)","score_opus":0.42980216385569436,"score_gpt":0.4626210607415645,"score_spread":0.03281889688587014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920889807","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012369807,0.00007586063,0.001519541,0.000024487914,0.000012446411,0.003988846,0.98186666,0.00013578463,0.000006559007],"genre_scores_gemma":[0.4444115,3.398428e-7,0.07358331,0.000022330232,0.000112361085,0.030908156,0.45085996,0.00007560802,0.000026425112],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845433,0.00019801159,0.00047719103,0.00034868627,0.000354866,0.00016692356],"domain_scores_gemma":[0.98560536,0.0134397885,0.0003017045,0.00019548913,0.00037750194,0.000080131715],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005376121,0.00020410822,0.0004246843,0.00018083546,0.000069517606,0.000028804357,0.00007926837,0.0001437455,0.18145107],"category_scores_gemma":[0.016688243,0.00014996549,0.00006592309,0.00013950616,0.000029965562,0.00024370091,0.00003534278,0.00009722686,0.0000012534354],"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":[0.00071449263,0.0008631254,0.00008524131,0.003968371,0.00015419711,0.00008713896,0.001020844,0.00003260677,0.00014878274,0.000052549083,0.97576743,0.0171052],"study_design_scores_gemma":[0.0028621908,0.004252364,0.00096199353,0.0030324925,0.0004276825,0.000095648225,0.001565387,0.97575885,0.00043034993,0.009339266,0.00086084206,0.00041294636],"about_ca_topic_score_codex":7.593935e-7,"about_ca_topic_score_gemma":0.000015110971,"teacher_disagreement_score":0.97572625,"about_ca_system_score_codex":0.00005804456,"about_ca_system_score_gemma":0.00029531462,"threshold_uncertainty_score":0.9915946},"labels":[],"label_agreement":null},{"id":"W6920972916","doi":"10.6084/m9.figshare.26695770.v1","title":"Additional file 2 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Relation (database); Mediation; Binary data; Sensitivity (control systems); Component (thermodynamics)","score_opus":0.42631790204951725,"score_gpt":0.46249822641172494,"score_spread":0.036180324362207694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920972916","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012223887,0.000076585886,0.0014842299,0.000024485726,0.000012408956,0.003983871,0.9820519,0.00013594591,0.000006655933],"genre_scores_gemma":[0.43748724,3.4408322e-7,0.07311745,0.00002239661,0.00011292127,0.030967481,0.45819035,0.00007569012,0.0000261125],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984545,0.00019812047,0.00047719062,0.00034859244,0.00035472555,0.00016688136],"domain_scores_gemma":[0.98566854,0.013379933,0.00030204406,0.0001954294,0.00037390244,0.000080131365],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000535275,0.00020407702,0.0004247366,0.0001807855,0.000069527276,0.000028806797,0.00007927375,0.00014375694,0.18224183],"category_scores_gemma":[0.016519815,0.0001499564,0.0000659157,0.00013945729,0.000029963334,0.00024368164,0.000035360863,0.00009722483,0.0000012300255],"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":[0.0006969166,0.0008504602,0.00008156349,0.0038824044,0.0001520258,0.000086967615,0.0010064205,0.000032249096,0.00014184904,0.000052851476,0.9759767,0.017039588],"study_design_scores_gemma":[0.0028586937,0.004279112,0.00095825584,0.003020346,0.00043183635,0.00009709853,0.0015656376,0.9756482,0.0004221073,0.00942568,0.0008788251,0.00041417906],"about_ca_topic_score_codex":7.5849607e-7,"about_ca_topic_score_gemma":0.000015098742,"teacher_disagreement_score":0.975616,"about_ca_system_score_codex":0.00005785784,"about_ca_system_score_gemma":0.00029403027,"threshold_uncertainty_score":0.9917645},"labels":[],"label_agreement":null},{"id":"W6921023794","doi":"10.6084/m9.figshare.14926918.v1","title":"Additional file 1 of Comparing regression modeling strategies for predicting hometime","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; University of Calgary","funders":"","keywords":"Calibration; Data set; Set (abstract data type); Regression analysis; Regression; Test set; Linear regression; Statistical model","score_opus":0.32268717896311905,"score_gpt":0.407488843836682,"score_spread":0.08480166487356294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921023794","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042600193,0.000021075684,0.0028783833,0.00000400186,0.0000055832616,0.00012577914,0.9903134,0.00014784311,0.0064613125],"genre_scores_gemma":[0.0062906216,3.0055267e-7,0.16011049,0.000008799992,0.00006101105,0.00091710215,0.8323122,0.000020339448,0.00027914037],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934417,0.000015074263,0.00021734711,0.0001512996,0.00013582435,0.00013625498],"domain_scores_gemma":[0.9969221,0.0023893155,0.00015516624,0.00016590826,0.00033848797,0.000029070521],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000020707403,0.00009469202,0.00018761426,0.000035505604,0.000061581464,0.000025665735,0.00009891825,0.000066498375,0.96238506],"category_scores_gemma":[0.0069127674,0.00009039362,0.00006715074,0.00009227458,0.0000043117125,0.00021011851,0.000094327974,0.00009850113,0.000041858675],"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":[0.0000030758542,0.000018674986,2.6035713e-7,0.00028438465,0.000007811379,0.0000015058052,0.00004058721,0.00026209286,0.00009585653,0.0006018436,0.9984245,0.00025945908],"study_design_scores_gemma":[0.00029653616,0.00009743284,0.000012194864,0.04243306,0.000021169128,0.000023476869,0.0015766543,0.47886032,0.01078653,0.33037913,0.13503046,0.00048304675],"about_ca_topic_score_codex":3.7516003e-7,"about_ca_topic_score_gemma":0.000004032957,"teacher_disagreement_score":0.9623432,"about_ca_system_score_codex":0.000023215289,"about_ca_system_score_gemma":0.0001272681,"threshold_uncertainty_score":0.82757276},"labels":[],"label_agreement":null},{"id":"W6921090521","doi":"10.6084/m9.figshare.26729170.v1","title":"Additional file 18 of The IMPACT Survey: the economic impact of osteogenesis imperfecta in adults","year":2024,"lang":"en","type":"dataset","venue":"Figshare","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":"","keywords":"Pairwise comparison; Population; Osteogenesis imperfecta; Table (database); Consumables; Economic impact analysis","score_opus":0.11969234191489812,"score_gpt":0.40438553586444725,"score_spread":0.2846931939495491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921090521","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000083199324,0.000067009096,2.8848584e-8,0.0000026133157,0.000026756405,0.00061855244,0.999048,0.00003219058,0.00012167385],"genre_scores_gemma":[0.00048968714,0.000010522103,0.000034778353,0.0000066360262,0.00008218067,0.0008572019,0.9984293,0.00004705155,0.00004264092],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983974,0.00022284304,0.0005810933,0.00030837386,0.00022028403,0.0002699731],"domain_scores_gemma":[0.9907555,0.0072432193,0.00069090625,0.0011299249,0.00013453599,0.000045897374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001559249,0.0003842319,0.0005860025,0.00015434,0.000033455017,0.000027465925,0.0010404176,0.00032268686,0.9773402],"category_scores_gemma":[0.0085825445,0.0002087247,0.0005516937,0.0002791335,0.000040203537,0.00009265611,0.00049602747,0.0005289924,0.0016858288],"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":[0.000025496787,0.000024219347,0.0000030780939,0.0005115064,0.00009031829,0.000002596857,0.0000141011205,0.000027455297,8.9382377e-7,9.621003e-7,0.99921644,0.00008292113],"study_design_scores_gemma":[0.0002967244,0.0005356201,0.011040308,0.039755836,0.00008368241,0.000048404458,0.000032532327,0.00023346943,0.00033927982,0.0077976678,0.93893546,0.00090104365],"about_ca_topic_score_codex":0.0015239345,"about_ca_topic_score_gemma":0.0034359286,"teacher_disagreement_score":0.97565436,"about_ca_system_score_codex":0.00065806037,"about_ca_system_score_gemma":0.0012639738,"threshold_uncertainty_score":0.9997686},"labels":[],"label_agreement":null},{"id":"W6921117573","doi":"10.6084/m9.figshare.16755940","title":"Additional file 1 of Online clinical pathway for chronic kidney disease management in primary care: a retrospective cohort study","year":2021,"lang":"en","type":"article","venue":"Open MIND","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":true,"ca_institutions":"University of Toronto; University of Alberta; University of Calgary","funders":"","keywords":"Cohort; Diabetes mellitus; Albuminuria; Statin; Retrospective cohort study; Cohort study","score_opus":0.10847890803775403,"score_gpt":0.43066372938390596,"score_spread":0.3221848213461519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921117573","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016057463,0.000026141004,0.00081397756,0.00007232477,0.000065200984,0.0057447064,0.95606947,0.000014195781,0.021136511],"genre_scores_gemma":[0.017999608,0.000023051853,0.76848626,0.00014225052,0.00018378721,0.0059248516,0.20016699,0.00006102054,0.007012177],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9985665,0.00009374489,0.0005140363,0.0004303584,0.00023354955,0.00016181095],"domain_scores_gemma":[0.99801916,0.0010121841,0.00019714155,0.00045264087,0.00021174925,0.000107127315],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026396292,0.00012819692,0.0004025282,0.00004315828,0.000031746364,0.00002309617,0.0002748221,0.000048902646,0.25952888],"category_scores_gemma":[0.0019764174,0.00012806537,0.000085966516,0.00015703567,0.000058995993,0.00012651783,0.00042266826,0.00014407598,0.000019323552],"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":[0.00023493868,0.0058010872,0.008118192,0.00027563018,0.00028779183,0.00026761545,0.0002495187,0.0000017912838,0.00001555363,0.0011702176,0.92184085,0.061736826],"study_design_scores_gemma":[0.004320369,0.0016012529,0.46671775,0.0021836932,0.00031256917,0.0000036303866,0.0020661608,0.00013651555,0.00043520544,0.056647763,0.4648067,0.00076839107],"about_ca_topic_score_codex":0.0000019794904,"about_ca_topic_score_gemma":0.00013551323,"teacher_disagreement_score":0.7676723,"about_ca_system_score_codex":0.0004246522,"about_ca_system_score_gemma":0.0007453582,"threshold_uncertainty_score":0.741148},"labels":[],"label_agreement":null},{"id":"W6921337578","doi":"10.7507/1007-4848.202407072","title":"Causal inference in observational studies based on real-world data:Key points and case studies for target trial emulation","year":2024,"lang":"en","type":"article","venue":"University of Groningen research database (University of Groningen / Centre for Information Technology)","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":"","keywords":"Observational study; Emulation; Causal inference; Randomized controlled trial; Psychological intervention; Standardization; Inference; Outcome (game theory)","score_opus":0.4339196817246158,"score_gpt":0.4784768401883782,"score_spread":0.0445571584637624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921337578","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":[0.70870495,0.0004695687,0.26970145,0.0053356513,0.00022356407,0.006302268,0.008122523,0.0007497866,0.00039023164],"genre_scores_gemma":[0.5659196,0.0009162263,0.43063223,0.000016155755,0.000032284297,0.000005646829,0.0021703844,0.000025952002,0.00028151547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818957,0.00012629786,0.0003761566,0.00042984934,0.00045581625,0.00042233916],"domain_scores_gemma":[0.9941774,0.003633443,0.00035495503,0.00062602403,0.001134336,0.00007385732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020646558,0.00021145852,0.00051547954,0.0023308415,0.00048510692,0.000025820129,0.00061417476,0.00015691415,0.000020423355],"category_scores_gemma":[0.0038948548,0.00025688438,0.000069526184,0.001170979,0.0010152331,0.0025906968,0.0008214044,0.00039861348,0.0000031521213],"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":[0.0112175895,0.00037872008,0.0020141306,0.004656272,0.0007993078,0.00026172708,0.013215958,0.0006848942,0.00016629229,0.93949395,0.012593785,0.014517365],"study_design_scores_gemma":[0.035495978,0.0042786263,0.0005422918,0.005130184,0.0006854773,0.00002322632,0.217154,0.4864584,0.0019011839,0.19588232,0.05087668,0.0015716502],"about_ca_topic_score_codex":0.00033997398,"about_ca_topic_score_gemma":0.0042290078,"teacher_disagreement_score":0.74361163,"about_ca_system_score_codex":0.00054107956,"about_ca_system_score_gemma":0.00034534515,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"W6924496159","doi":"10.15468/dl.qmtg9m","title":"Occurrence Download","year":2024,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Ornithology; Biodiversity; National Museum of Natural History; Extant taxon; Natural history; Vertebrate; National museum; Conservation biology","score_opus":0.06659044662203663,"score_gpt":0.3279915673806469,"score_spread":0.2614011207586103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924496159","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059692764,0.000027116803,0.0001136628,0.000112352296,0.00052814005,0.0004817886,0.9976358,0.00073057914,0.00031088534],"genre_scores_gemma":[0.000004856353,0.000080999074,0.00006260417,0.0002459429,0.0000023391087,0.000013019738,0.9995899,3.599969e-8,2.6540317e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981073,0.000059830305,0.0005771075,0.00030264736,0.00059127447,0.000361855],"domain_scores_gemma":[0.9983526,0.00008360349,0.0003343681,0.00077272695,0.0002991279,0.00015755658],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00037676524,0.00042667778,0.00042280785,0.00014289218,0.00016482275,0.00020243137,0.0006633382,0.00053587,0.0018787868],"category_scores_gemma":[0.00061958755,0.000412129,0.00020650278,0.00040504255,0.00021216003,0.0011048748,0.0005901533,0.000602492,0.4337307],"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":[0.000019621657,0.000031399133,0.000035741486,0.0006849243,0.000038264712,0.0000060965035,0.00003772077,5.233118e-7,5.8258273e-8,0.000009541915,0.9981971,0.0009390134],"study_design_scores_gemma":[0.00011007824,0.000044016153,0.0000015695413,0.000017000793,0.00011435744,0.000009547469,0.00009199604,1.1406414e-7,0.000013520337,0.0014499205,0.99774456,0.00040332222],"about_ca_topic_score_codex":0.00010195433,"about_ca_topic_score_gemma":0.000016360904,"teacher_disagreement_score":0.43185192,"about_ca_system_score_codex":0.0005780008,"about_ca_system_score_gemma":0.00016503962,"threshold_uncertainty_score":0.99983305},"labels":[],"label_agreement":null},{"id":"W6926538345","doi":"10.25549/impa-m68313","title":"Missionary fathers building a wooden house, Canada, ca.1920-1940","year":2012,"lang":"fr","type":"dataset","venue":"University of Southern California Digital Library","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Period (music)","score_opus":0.025814856357586784,"score_gpt":0.22876133221277684,"score_spread":0.20294647585519004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926538345","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055404394,0.00069431495,0.0017179016,0.0005200816,0.000111057416,0.0005028989,0.98847884,0.00044052335,0.0019939383],"genre_scores_gemma":[0.007564291,0.0004144606,0.027126638,0.0006132816,0.00049592415,0.0000029326102,0.9484339,0.0006227033,0.014725919],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968475,0.00013426712,0.00064168486,0.0006668121,0.0007802168,0.00092951104],"domain_scores_gemma":[0.9965742,0.0006615397,0.00090985,0.0010076327,0.000101599486,0.00074512674],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00012278176,0.00085804536,0.001054599,0.00027589823,0.00033190244,0.00011692548,0.001537047,0.00076850416,0.010510043],"category_scores_gemma":[0.00015389519,0.00095015985,0.00038272375,0.00037076345,0.00067151187,0.001025719,0.0013180365,0.0009230491,0.007840279],"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":[0.00017709525,0.0003910489,0.0015571357,0.0007756009,0.00027106292,0.00039784441,0.00024036998,0.000019342464,0.000029801491,0.00020590934,0.9937016,0.0022331881],"study_design_scores_gemma":[0.00037565397,0.00007372033,0.0000049781124,0.0011191891,0.0002558167,0.000042874017,0.0037339823,0.00004379299,0.00016671605,0.006835845,0.98637384,0.00097358436],"about_ca_topic_score_codex":0.039211214,"about_ca_topic_score_gemma":0.007611849,"teacher_disagreement_score":0.040044997,"about_ca_system_score_codex":0.000471381,"about_ca_system_score_gemma":0.0014883057,"threshold_uncertainty_score":0.9992949},"labels":[],"label_agreement":null},{"id":"W6927175633","doi":"10.3205/18ebm045","title":"Absolute Effekte auf der Basis von gepoolten Hazard ratios: eine Analyse von mehr als 500 systematischen Übersichtsarbeiten im Krebsbereich","year":2018,"lang":"de","type":"article","venue":"German Medical Science (German Research Foundation)","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":"Cochrane","funders":"","keywords":"Hazard; Intervention (counseling); Hazard ratio","score_opus":0.1471346095077936,"score_gpt":0.49791964773762404,"score_spread":0.3507850382298304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927175633","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":[0.47300813,0.0054802154,0.38751265,0.043314517,0.0078375405,0.02200752,0.00029876205,0.0037471193,0.056793537],"genre_scores_gemma":[0.95886236,0.0006592658,0.027269896,0.0013289794,0.0046182736,0.0006915319,0.0003054852,0.00024681212,0.006017365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97302455,0.0028194312,0.0031709287,0.0026649865,0.014270385,0.0040497445],"domain_scores_gemma":[0.9824406,0.0038949605,0.0012356661,0.0034837069,0.0058516967,0.0030933982],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","insufficient_payload"],"category_scores_codex":[0.035113636,0.001116984,0.0017664846,0.0024244701,0.004031406,0.001948479,0.0054185227,0.000950313,0.012428548],"category_scores_gemma":[0.023943687,0.00096197217,0.00040000532,0.007037059,0.012633603,0.004337988,0.0029159007,0.003200115,0.015986625],"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":[0.0012162513,0.0036779644,0.0042427373,0.012313648,0.007990597,0.002840001,0.04431308,0.00003356466,0.075516015,0.32771543,0.21293987,0.30720082],"study_design_scores_gemma":[0.0069710133,0.006251707,0.01164099,0.019457173,0.005353392,0.00068511034,0.0021736755,0.26683453,0.09747882,0.4493202,0.12515663,0.008676765],"about_ca_topic_score_codex":0.0004134695,"about_ca_topic_score_gemma":0.0007368924,"teacher_disagreement_score":0.48585427,"about_ca_system_score_codex":0.0022107011,"about_ca_system_score_gemma":0.0046813157,"threshold_uncertainty_score":0.9999626},"labels":[],"label_agreement":null},{"id":"W6930612293","doi":"10.5281/zenodo.15217976","title":"FIGURE 40 in Revision of the western Nearctic species of Empis subgenus Enoplempis (Diptera: Empididae)","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear 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":"Canadian Food Inspection Agency","funders":"","keywords":"Subgenus; Nearctic ecozone; Taxonomy (biology); Holotype; Taxonomic key; Biogeography","score_opus":0.0900788398588798,"score_gpt":0.3378470182240885,"score_spread":0.24776817836520873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930612293","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014697646,0.00041512854,0.005617794,0.0005206619,0.00013633502,0.0016377617,0.0006270632,0.0008684778,0.988707],"genre_scores_gemma":[0.16568683,0.0017502623,0.0053329016,0.00018549422,0.0002632867,2.7009142e-7,0.0007131723,0.009205265,0.8168625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778414,0.0004820077,0.0005654409,0.00038577453,0.0004944822,0.0002881692],"domain_scores_gemma":[0.99785966,0.00011277217,0.0005294661,0.0010417664,0.00040105966,0.000055278448],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000583938,0.00025527668,0.0004913728,0.00047131142,0.0002229209,0.00009088874,0.001437169,0.00021335758,0.018938877],"category_scores_gemma":[0.0019089842,0.0002152874,0.000113979215,0.00076996355,0.00033162843,0.000087207336,0.0014888257,0.00047555228,0.0003870134],"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":[0.000055877787,0.00022928054,0.00006999292,0.0017658425,0.00007994433,0.000008585892,0.0014342782,0.0000033456668,0.0015367853,0.014757865,0.95411664,0.02594156],"study_design_scores_gemma":[0.00024811807,0.00011804254,0.00032861068,0.0017373957,0.00003280628,0.000006721271,0.00012748525,0.0000065280765,0.002199076,0.0029758452,0.99203086,0.00018849931],"about_ca_topic_score_codex":0.00008382908,"about_ca_topic_score_gemma":0.000009093479,"teacher_disagreement_score":0.1718445,"about_ca_system_score_codex":0.00015192953,"about_ca_system_score_gemma":0.000015826954,"threshold_uncertainty_score":0.981958},"labels":[],"label_agreement":null},{"id":"W6930681723","doi":"10.5281/zenodo.14071670","title":"Smart Hemp Oil Official Website, Reviews [2025] &amp; Price For Sale In New Zealand (AU, NZ)","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Product (mathematics); Order (exchange); Work (physics); Context (archaeology); Filter (signal processing); Natural (archaeology)","score_opus":0.1674605311708088,"score_gpt":0.3767397588006975,"score_spread":0.20927922762988868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930681723","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028343042,0.0011839708,0.029043267,0.0006033872,0.0002641953,0.0017255133,0.000531287,0.003271729,0.9633483],"genre_scores_gemma":[0.00002582093,0.0015480852,0.017597623,0.000112193266,0.0007254264,7.8398386e-7,0.0014531129,0.010115124,0.9684218],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997475,0.00027844126,0.00059699,0.0007096729,0.00036230736,0.0005775734],"domain_scores_gemma":[0.9983562,0.000088494395,0.00033223903,0.0008222918,0.00019336314,0.00020736516],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011000896,0.00038992765,0.0005922426,0.0006074193,0.00027245755,0.0003785509,0.0010219272,0.00029373248,0.022194806],"category_scores_gemma":[0.0026028424,0.00038949764,0.00013580413,0.00070031616,0.000110882356,0.00012634258,0.0009075938,0.0005894137,0.018486999],"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":[0.000035443103,0.000089061876,6.574846e-7,0.0009947541,0.000034941615,0.000007785572,0.00048185867,4.7437908e-7,0.00023460873,0.007654265,0.9597361,0.030730035],"study_design_scores_gemma":[0.00034097003,0.000117050775,0.0000023011655,0.0010936009,0.000042115764,0.00002513259,0.00002805903,0.000010070945,0.00005822015,0.010709434,0.98719424,0.00037877547],"about_ca_topic_score_codex":0.00012801554,"about_ca_topic_score_gemma":0.000107993124,"teacher_disagreement_score":0.030351259,"about_ca_system_score_codex":0.0004012993,"about_ca_system_score_gemma":0.000034067893,"threshold_uncertainty_score":0.9998557},"labels":[],"label_agreement":null},{"id":"W6930901235","doi":"10.5281/zenodo.3867155","title":"Thalassisobates littoralis","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear 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":"BC Research (Canada)","funders":"","keywords":"Mediterranean climate; Habitat; Biological dispersal; Intertidal zone; Mediterranean sea; Mediterranean Islands","score_opus":0.2360289313917183,"score_gpt":0.3930810454266384,"score_spread":0.15705211403492012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930901235","genre_codex":"other","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":[0.047516514,0.000068947746,0.04954174,0.0042091594,0.00022028999,0.00103248,0.00031297441,0.006628275,0.8904696],"genre_scores_gemma":[0.9867422,0.00007691336,0.007829571,0.00008560037,0.00018386809,8.138653e-8,0.00023301519,0.0017169046,0.0031318455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998767,0.00013311271,0.00020591562,0.00030504845,0.00027473713,0.00031418802],"domain_scores_gemma":[0.9981162,0.000047171143,0.00020989624,0.0010572828,0.0004408933,0.0001285436],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005770518,0.00013685881,0.00015875975,0.00010230979,0.003499327,0.0012766229,0.0015913746,0.00006930344,0.0073965597],"category_scores_gemma":[0.0034510496,0.00013452175,0.000050937095,0.00009807497,0.00025413604,0.00054231833,0.0014110679,0.00022586514,0.0028707432],"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":[0.00003802402,0.00018965112,0.000030740655,0.00010435837,0.000052145573,0.00002706129,0.0007802734,0.0000014218544,0.008646322,0.3536308,0.51488656,0.12161262],"study_design_scores_gemma":[0.00022347468,0.00012837707,0.00057755486,0.000050917348,0.000012665526,0.000045456873,0.000105960295,0.00006267754,0.005650557,0.09372452,0.8992201,0.00019771463],"about_ca_topic_score_codex":0.000012860688,"about_ca_topic_score_gemma":3.9312954e-7,"teacher_disagreement_score":0.9392257,"about_ca_system_score_codex":0.00010182544,"about_ca_system_score_gemma":0.0000019441384,"threshold_uncertainty_score":0.99976015},"labels":[],"label_agreement":null},{"id":"W6931685926","doi":"10.5281/zenodo.7003346","title":"Copelatus alternatus Sharp 1882","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear 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":"Laurentian University","funders":"","keywords":"Instar; Larva; Head (geology); Dorsum; Constriction; Table (database)","score_opus":0.1539937030446855,"score_gpt":0.3554595231368441,"score_spread":0.2014658200921586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931685926","genre_codex":"other","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":[0.06918097,0.0002791915,0.08016492,0.0017559374,0.00047049188,0.0021815135,0.0011917703,0.01153076,0.83324444],"genre_scores_gemma":[0.9838266,0.000059751408,0.0072427513,0.0003624927,0.00015606565,4.2254575e-7,0.0009681416,0.0026985835,0.0046851938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980443,0.00035550896,0.00027729408,0.00038484053,0.0005320542,0.000406001],"domain_scores_gemma":[0.9987637,0.00006649614,0.00014570312,0.0005963861,0.0002852063,0.00014255095],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00078116514,0.0001508948,0.00017066214,0.00020751779,0.0025477987,0.0002992458,0.0012583686,0.00003991221,0.04636271],"category_scores_gemma":[0.00092196366,0.0001707095,0.00005786472,0.00049787003,0.0001060563,0.00023200827,0.002652636,0.00054340286,0.0024796596],"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":[0.000093300565,0.00032416018,0.000005186008,0.00007011577,0.000056636432,0.00007470251,0.0013619972,0.00007499214,0.007984383,0.32901365,0.5824247,0.07851617],"study_design_scores_gemma":[0.00029788585,0.000284131,0.00003712553,0.00001251384,0.000011416044,0.00018425366,0.0003035351,0.00024870076,0.0012638759,0.04741203,0.949737,0.00020750047],"about_ca_topic_score_codex":0.000010364867,"about_ca_topic_score_gemma":1.584901e-7,"teacher_disagreement_score":0.9146456,"about_ca_system_score_codex":0.00034132777,"about_ca_system_score_gemma":0.000004150263,"threshold_uncertainty_score":0.99875075},"labels":[],"label_agreement":null},{"id":"W6931737912","doi":"10.5683/sp3/c11qwv","title":"Supplementary Information for Estimating Ancient Nuu-chah-nulth Fisheries Biomass at Shell Midden Sites on the Northwest Coast","year":2024,"lang":"en","type":"dataset","venue":"Borealis","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":"University of Victoria","funders":"","keywords":"Midden; Biomass (ecology); Fish <Actinopterygii>; Shell (structure); Fishing","score_opus":0.08837056643535036,"score_gpt":0.3561518207869787,"score_spread":0.26778125435162836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931737912","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015735951,0.000021919252,0.0029717756,0.00094858656,0.00020190787,0.0016850578,0.9936275,0.00025758368,0.00012834767],"genre_scores_gemma":[0.000029033587,0.00003862903,0.039111234,0.00078858115,0.00023270855,0.0009302845,0.9587887,0.00005205427,0.00002877531],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784595,0.00005508178,0.00080239255,0.0003532433,0.00047000666,0.00047333748],"domain_scores_gemma":[0.99689776,0.0012861673,0.0005503281,0.0009883152,0.00018577327,0.000091673246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054799335,0.0005322693,0.0004633585,0.00020556619,0.0003315089,0.00025309436,0.0006014358,0.00025368197,0.00041669898],"category_scores_gemma":[0.0008448764,0.0003740767,0.00017838509,0.00019161594,0.00014315877,0.0003100946,0.0004137802,0.000347287,0.000060325583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033652894,0.00004527135,0.000011878007,0.0011845775,0.00006993515,0.0000063938373,0.00036286592,0.0000048870365,0.000014063818,0.0017909991,0.9959466,0.0005288968],"study_design_scores_gemma":[0.00012146341,0.00024668744,0.0000083506475,0.0004292014,0.00018594034,0.00001097526,0.000353217,0.0004444982,0.0012419297,0.031314835,0.96522516,0.0004177291],"about_ca_topic_score_codex":0.011848366,"about_ca_topic_score_gemma":0.10495224,"teacher_disagreement_score":0.09310387,"about_ca_system_score_codex":0.0004063609,"about_ca_system_score_gemma":0.00009244692,"threshold_uncertainty_score":0.99987113},"labels":[],"label_agreement":null},{"id":"W6931892806","doi":"10.5683/sp3/bb2kda","title":"Can a social partner alleviate conditioned place aversion caused by isolation and pain in dairy calves?","year":2023,"lang":"en","type":"dataset","venue":"Borealis","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":"University of British Columbia","funders":"","keywords":"Social isolation; Conditioning; Isolation (microbiology); Social stress; Stressor; Social behaviour; Animal welfare; Social relation","score_opus":0.07699492643641458,"score_gpt":0.3729293038414213,"score_spread":0.2959343774050067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931892806","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001935867,0.000017647486,0.0008725295,0.00051341846,0.000029686566,0.00053298,0.99753517,0.00026356018,0.000041449377],"genre_scores_gemma":[0.00014772701,0.00022822981,0.0004112968,0.00021083807,0.00008086933,0.00017490383,0.99854046,0.000050431485,0.00015521818],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982651,0.00030520387,0.00043080444,0.00038824102,0.00029633674,0.00031430766],"domain_scores_gemma":[0.99853545,0.0006614424,0.00033364538,0.00032930687,0.00006116437,0.00007895878],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007574151,0.00031945392,0.00047386007,0.00019655537,0.00012303347,0.000045010274,0.00017274612,0.00051002775,0.000030723586],"category_scores_gemma":[0.00075532316,0.00032764097,0.00005564516,0.00017675839,0.000095216215,0.000120401106,0.00011455076,0.0004089349,0.000009566472],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020096344,0.00004034567,0.0000046059354,0.00017725324,0.000025777455,0.000027822665,0.0002035273,5.653178e-7,0.000052834293,0.0005447882,0.99876237,0.00014003176],"study_design_scores_gemma":[0.00080897025,0.00015260509,0.00017540771,0.0003424475,0.00010993935,0.0000023342136,0.00025395188,0.0001994518,0.00008900313,0.09398084,0.9031982,0.000686854],"about_ca_topic_score_codex":0.0152889695,"about_ca_topic_score_gemma":0.047210027,"teacher_disagreement_score":0.09556416,"about_ca_system_score_codex":0.0002457442,"about_ca_system_score_gemma":0.000076812605,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W6932086906","doi":"10.5683/sp3/jcoxpx","title":"Indicateurs de performance financière des entreprises canadiennes, 2000-2002","year":2025,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Statistical analysis; Work force","score_opus":0.04708391483540487,"score_gpt":0.3194062403264786,"score_spread":0.2723223254910737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6932086906","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026052431,0.0022664587,0.0017196623,0.00017768097,0.00018806272,0.00077121146,0.985541,0.00032828742,0.006402435],"genre_scores_gemma":[0.0002143106,0.01771248,0.02485808,0.0004740489,0.0002893564,0.0004076144,0.942111,0.00007609951,0.01385701],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962267,0.00019076574,0.0009194019,0.00081009616,0.00039039415,0.0014626421],"domain_scores_gemma":[0.9961191,0.00069167314,0.0006423031,0.0018644007,0.00028040048,0.0004021326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052108645,0.0008751433,0.0009728318,0.00043002583,0.0003973824,0.00010746897,0.0013903741,0.00093019963,0.0007867751],"category_scores_gemma":[0.0020356663,0.0009228571,0.00021050026,0.000566654,0.0007491358,0.0003388778,0.0004471562,0.0010599596,0.000050753853],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002715424,0.00021648731,0.0011639993,0.0021856106,0.000108500135,0.00017063385,0.00052246405,0.000024330075,0.000011478314,0.0041932994,0.95999104,0.031385016],"study_design_scores_gemma":[0.00022151352,0.00018177392,0.0013668726,0.00246211,0.00039664487,0.00008558891,0.00015488124,0.000096097836,0.0019174891,0.015734868,0.97654253,0.00083960005],"about_ca_topic_score_codex":0.15955116,"about_ca_topic_score_gemma":0.19115427,"teacher_disagreement_score":0.043429956,"about_ca_system_score_codex":0.0020255556,"about_ca_system_score_gemma":0.0016582153,"threshold_uncertainty_score":0.9993222},"labels":[],"label_agreement":null},{"id":"W6939467240","doi":"10.6084/m9.figshare.26695776.v1","title":"Additional file 4 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Mediation; Binary data; Empirical research; Binary relation; Relation (database)","score_opus":0.4314493148368384,"score_gpt":0.46305523481070243,"score_spread":0.03160591997386403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939467240","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012324968,0.00007613542,0.0015285938,0.000024458624,0.000012353732,0.003993474,0.9818975,0.00013600102,0.0000065466943],"genre_scores_gemma":[0.44836584,3.3729472e-7,0.07309732,0.000022183985,0.00011053665,0.030678311,0.447625,0.00007502483,0.000025428852],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845415,0.0001979888,0.00047734095,0.0003487169,0.00035484636,0.00016694018],"domain_scores_gemma":[0.9855895,0.013461734,0.00030173833,0.00019557278,0.0003713243,0.00008013247],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005379912,0.0002041207,0.00042477236,0.00018090935,0.000069548,0.000028817822,0.000079319594,0.00014375619,0.1792591],"category_scores_gemma":[0.016486498,0.00014999052,0.00006592757,0.0001394905,0.000029970292,0.0002437322,0.000035354617,0.00009722421,0.0000012309274],"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":[0.00072552357,0.00086890644,0.000085942615,0.0039657163,0.00015516364,0.00008795162,0.0010281372,0.00003240831,0.0001476958,0.00005456613,0.97564757,0.017200392],"study_design_scores_gemma":[0.002846685,0.004307455,0.00096415123,0.0030329248,0.00042966942,0.00009633191,0.0015665056,0.9756905,0.0004217485,0.009403835,0.00082800054,0.00041222063],"about_ca_topic_score_codex":7.5346765e-7,"about_ca_topic_score_gemma":0.000015165415,"teacher_disagreement_score":0.97565806,"about_ca_system_score_codex":0.00005784832,"about_ca_system_score_gemma":0.00029434238,"threshold_uncertainty_score":0.99179804},"labels":[],"label_agreement":null},{"id":"W6939649051","doi":"10.6084/m9.figshare.27932635.v1","title":"Additional file 1 of Investigation of treatment delay in a complex healthcare process using physician insurance claims data: an application to symptomatic carotid artery stenosis","year":2024,"lang":"en","type":"article","venue":"Figshare","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":"University of British Columbia","funders":"","keywords":"Stenosis; Process (computing); Health care; Carotid arteries; MEDLINE","score_opus":0.28656438753837693,"score_gpt":0.4250100997574115,"score_spread":0.13844571221903457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939649051","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012258473,0.000008781595,0.000171928,0.000024583811,0.0000033408726,0.0008084219,0.9865682,0.00012374952,0.000032483982],"genre_scores_gemma":[0.33576667,3.3506683e-7,0.015942171,0.000043469605,0.000030164654,0.0019071846,0.6462866,0.000021445301,0.0000019573865],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998985,0.000048819893,0.00036990916,0.00029174297,0.00017456817,0.00012998376],"domain_scores_gemma":[0.99855286,0.00058755884,0.00019441359,0.000437366,0.00017138793,0.00005639487],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003150004,0.00013818547,0.00024991573,0.00013345001,0.00002703301,0.000015635042,0.00020644092,0.000058831618,0.065021984],"category_scores_gemma":[0.00027278299,0.0001340614,0.00002657688,0.00044893546,0.000013627828,0.0004187348,0.000049370046,0.00007070318,0.000054515996],"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":[0.000015544018,0.00028083168,0.00021700482,0.0079315165,0.000062237996,0.0000048382662,0.0030762681,0.00054060045,0.0034680516,0.00040757898,0.9723099,0.011685617],"study_design_scores_gemma":[0.0010720504,0.003525561,0.04853291,0.18353397,0.00016194824,0.00006342378,0.00329026,0.4283785,0.04637373,0.25380027,0.028506396,0.0027609796],"about_ca_topic_score_codex":0.000023039624,"about_ca_topic_score_gemma":0.00016001992,"teacher_disagreement_score":0.9438035,"about_ca_system_score_codex":0.00021102132,"about_ca_system_score_gemma":0.00020444577,"threshold_uncertainty_score":0.93583274},"labels":[],"label_agreement":null},{"id":"W6939668081","doi":"10.6084/m9.figshare.14381684","title":"Confounding adjustment methods for multi-level treatment comparisons under lack of positivity and unknown model specification","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Covariate; Estimator; Context (archaeology); Observational study; Specification; Matching (statistics); Confounding; Variance (accounting); Propensity score matching","score_opus":0.8348849125377892,"score_gpt":0.5963865798411815,"score_spread":0.2384983326966077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939668081","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":[0.00035041614,0.0003177644,0.9573101,0.000077133234,0.000016364498,0.0006622759,0.040604353,0.00010187577,0.0005597643],"genre_scores_gemma":[0.022996148,0.000022807722,0.9679471,0.00004225902,0.000019683694,0.00040185018,0.007953548,0.000024256644,0.0005923094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924743,0.00007098185,0.00023776575,0.0002243677,0.00007221623,0.00014723865],"domain_scores_gemma":[0.9984848,0.00078969134,0.00017045092,0.00025819347,0.00024467293,0.000052181425],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000084820065,0.00014336187,0.00029344662,0.000034328415,0.000054903434,0.000017903394,0.00006097104,0.00007843193,0.0012706737],"category_scores_gemma":[0.0006423482,0.00013330128,0.00006471534,0.000066561726,0.000012177995,0.00009193405,0.00005956156,0.000056383364,0.0000050532526],"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":[0.000103390674,0.002509951,0.00004059029,0.0021796806,0.0004770409,0.0000058789046,0.0019919644,0.0011753285,0.10007493,0.69593674,0.058886636,0.13661788],"study_design_scores_gemma":[0.0014511693,0.00021844657,0.00095779536,0.0013492979,0.00014842191,0.000009470993,0.00035745473,0.24900323,0.5927926,0.14683159,0.0064040986,0.00047644568],"about_ca_topic_score_codex":0.0000022868014,"about_ca_topic_score_gemma":0.00002709646,"teacher_disagreement_score":0.5491051,"about_ca_system_score_codex":0.00016662315,"about_ca_system_score_gemma":0.00007646453,"threshold_uncertainty_score":0.9996423},"labels":[],"label_agreement":null},{"id":"W6939732679","doi":"10.6084/m9.figshare.21293449","title":"Additional file 1 of Examining evidence of time-dependent treatment effects: an illustration using regression methods","year":2022,"lang":"en","type":"article","venue":"Open MIND","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":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Regression analysis; Regression; Linear regression; Feature (linguistics)","score_opus":0.47572153659079625,"score_gpt":0.5298866037232873,"score_spread":0.054165067132491085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939732679","genre_codex":"empirical","genre_gemma":"methods","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":[0.36926085,0.00028009622,0.27006665,0.0000530686,0.00029588412,0.00927971,0.32779753,0.00011020369,0.02285602],"genre_scores_gemma":[0.010767891,0.0000020166724,0.9855885,0.000002899493,0.000017118458,0.00036199504,0.0021571142,0.000016199001,0.0010862643],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985804,0.0005337017,0.00031839023,0.00021850308,0.00024676762,0.00010226537],"domain_scores_gemma":[0.9940646,0.0050627477,0.00046478066,0.00030196694,0.000072068884,0.000033804627],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005701821,0.00011334743,0.0002696886,0.00006803301,0.000098697696,0.000016006275,0.0002489125,0.00003897738,0.55794156],"category_scores_gemma":[0.0013413244,0.00009905786,0.00003312399,0.0001254284,0.000045100933,0.000390497,0.00023537561,0.00008147037,0.0000065347253],"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":[0.00019335422,0.0008038009,0.00000913056,0.000096900534,0.00007447505,0.000021632834,0.0017868776,0.0005681325,0.40392175,0.00016729913,0.031652194,0.56070447],"study_design_scores_gemma":[0.0004889407,0.0047074985,0.000047614103,0.0030196987,0.000146326,0.000055229026,0.001602157,0.011449423,0.95093,0.016167149,0.0109627405,0.00042321288],"about_ca_topic_score_codex":0.000019933008,"about_ca_topic_score_gemma":0.000005071578,"teacher_disagreement_score":0.7155219,"about_ca_system_score_codex":0.00018788918,"about_ca_system_score_gemma":0.00013401768,"threshold_uncertainty_score":0.44246256},"labels":[],"label_agreement":null},{"id":"W6940043713","doi":"10.6084/m9.figshare.26695767.v1","title":"Additional file 1 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Binary number; Variance (accounting); Outcome (game theory); Estimator; Binary data; Confidence interval; Mediation; Relation (database); Range (aeronautics)","score_opus":0.43388011366608537,"score_gpt":0.4631154158349202,"score_spread":0.029235302168834854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6940043713","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012284088,0.00007547082,0.0015110977,0.000024574223,0.0000123354075,0.0039864494,0.98196363,0.0001358529,0.000006521137],"genre_scores_gemma":[0.43984094,3.346096e-7,0.07408924,0.000022277407,0.00011089992,0.0313173,0.45451772,0.00007538246,0.000025900514],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984543,0.00019817852,0.00047700413,0.000348819,0.00035480206,0.00016693454],"domain_scores_gemma":[0.9855057,0.01354224,0.00030163466,0.00019572822,0.00037457302,0.000080130216],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053782563,0.00020413341,0.00042464628,0.00018088838,0.000069522845,0.000028752585,0.0000793121,0.00014375622,0.18471782],"category_scores_gemma":[0.016692108,0.00014999899,0.000065926775,0.00013955154,0.000029963694,0.00024353668,0.000035365185,0.00009724428,0.0000012415421],"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":[0.0006939775,0.0008431059,0.0000831304,0.0038177338,0.00015066726,0.00008419282,0.0009967043,0.00003182831,0.00014495318,0.000051591738,0.97661215,0.016489988],"study_design_scores_gemma":[0.0028306327,0.0042616636,0.0009680374,0.003041052,0.00043149493,0.00009653041,0.0015734325,0.97578955,0.00042273148,0.009324424,0.0008471678,0.00041330306],"about_ca_topic_score_codex":7.51917e-7,"about_ca_topic_score_gemma":0.000015021529,"teacher_disagreement_score":0.97576493,"about_ca_system_score_codex":0.000057843445,"about_ca_system_score_gemma":0.00029517157,"threshold_uncertainty_score":0.99159074},"labels":[],"label_agreement":null},{"id":"W6949721409","doi":"10.5281/zenodo.15318810","title":"La révolution causale à l'ère de l'IA : Vers une approche hybride entre théorie scientifique et découverte automatisée","year":2025,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear 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":"University of Ottawa","funders":"","keywords":"Context (archaeology); Perspective (graphical); Identity (music); Identification (biology)","score_opus":0.04567019172075941,"score_gpt":0.32683687552926055,"score_spread":0.2811666838085011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949721409","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":[0.007293384,0.00050706737,0.5857328,0.0060463334,0.00041775152,0.0012828197,0.00045138862,0.0033018715,0.3949666],"genre_scores_gemma":[0.7218479,0.0021970577,0.06843569,0.0011469176,0.0003501083,0.0000023073364,0.002935521,0.0051376927,0.19794683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99606407,0.0013874675,0.0005390829,0.00070508115,0.0005155345,0.0007887545],"domain_scores_gemma":[0.99745613,0.000270893,0.00026097373,0.00084090536,0.00091654033,0.0002545771],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023570578,0.0003521138,0.00034276518,0.00043581912,0.0016798504,0.0009993187,0.0011895712,0.00028216062,0.0050137904],"category_scores_gemma":[0.0035299414,0.0004145397,0.00011503099,0.0016032229,0.00071572664,0.00067337544,0.0014727227,0.00088735885,0.0021271468],"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":[0.000044150675,0.00032339877,0.000006005498,0.00084694906,0.000099454686,0.00004274128,0.0031777802,0.00012186552,0.0069642034,0.39940205,0.5145206,0.0744508],"study_design_scores_gemma":[0.0005500067,0.00011507832,0.00019764491,0.0009185421,0.000099108525,0.0001425287,0.0012051057,0.0047850935,0.0055640335,0.091263495,0.8947929,0.00036642127],"about_ca_topic_score_codex":0.00015118139,"about_ca_topic_score_gemma":0.000011532482,"teacher_disagreement_score":0.7145545,"about_ca_system_score_codex":0.0013834476,"about_ca_system_score_gemma":0.000091867994,"threshold_uncertainty_score":0.99983066},"labels":[],"label_agreement":null},{"id":"W6950129411","doi":"10.5281/zenodo.7877767","title":"Rethinking Residual Confounding Bias Reduction: Why Vanilla hdPS Alone is No Longer Enough","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear 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 British Columbia","funders":"","keywords":"Confounding; Leverage (statistics); Estimator; Residual; Variance (accounting); Propensity score matching; Selection bias; Selection (genetic algorithm); Feature selection","score_opus":0.2736396246141182,"score_gpt":0.3759552686465703,"score_spread":0.10231564403245208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950129411","genre_codex":"other","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":[0.2256674,0.00022847056,0.058070272,0.013748215,0.0018132473,0.0041796225,0.00065775315,0.042870082,0.6527649],"genre_scores_gemma":[0.9309822,0.0006961494,0.031534787,0.0010504512,0.0019708378,8.264186e-7,0.0022568218,0.0073777405,0.024130234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972605,0.00040794432,0.00046979962,0.00057881244,0.00069597014,0.000586979],"domain_scores_gemma":[0.997675,0.0001627585,0.00023460278,0.0007635851,0.0009942381,0.00016981333],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017524583,0.00024276029,0.00027955108,0.00040328712,0.002520104,0.0008929377,0.00088601117,0.00015113296,0.011830833],"category_scores_gemma":[0.0034873013,0.00026028499,0.00007194566,0.0011793064,0.00029056115,0.00052055024,0.001211308,0.00053598237,0.012566987],"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":[0.00006571266,0.000077102275,0.0000017633322,0.0001630991,0.0000722594,0.000054659286,0.009469579,0.000012787475,0.018186865,0.06964203,0.89063776,0.011616391],"study_design_scores_gemma":[0.00035491484,0.00024825407,0.000023186023,0.00015464719,0.00002668165,0.00020833394,0.00078827987,0.00016985757,0.011162091,0.09028904,0.8962065,0.00036819215],"about_ca_topic_score_codex":0.000015680835,"about_ca_topic_score_gemma":3.9843093e-7,"teacher_disagreement_score":0.70531476,"about_ca_system_score_codex":0.00026650794,"about_ca_system_score_gemma":0.000009316108,"threshold_uncertainty_score":0.9999849},"labels":[],"label_agreement":null},{"id":"W6955111943","doi":"10.58066/01j0-7f44","title":"Interview with Ren Bowrun","year":2019,"lang":"en","type":"other","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Oral history; Interview; Data collection; Semi-structured interview; Perspective (graphical)","score_opus":0.09334983425806913,"score_gpt":0.3520457884284062,"score_spread":0.2586959541703371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6955111943","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018363132,0.0013596547,0.005103398,0.00017403932,0.00019653064,0.0008495713,0.000009685401,0.00065006624,0.9898207],"genre_scores_gemma":[0.0053131646,0.0007754505,0.010889285,0.000004592197,0.00019985152,0.000001740229,0.000011061352,0.00022552551,0.98257935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777603,0.0005617429,0.00014127791,0.00047458668,0.00067341747,0.00037292443],"domain_scores_gemma":[0.99816823,0.00051239785,0.00030636872,0.0005584895,0.00029993628,0.00015456793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077936496,0.00023516464,0.0005384419,0.00040998534,0.00024714443,0.000043797612,0.00046674738,0.0003666949,0.00046230582],"category_scores_gemma":[0.0001707449,0.00023709537,0.000067792884,0.00027518583,0.00046096175,0.00012009464,0.00033504167,0.0014246207,0.000056097055],"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":[0.00038163416,0.00031516867,0.0022641665,0.0048428425,0.00076512847,0.0004911904,0.0035352216,0.0000032574042,0.0018628171,0.014679465,0.96368104,0.007178055],"study_design_scores_gemma":[0.00040917727,0.0011453244,0.00009412679,0.0022779184,0.000047678153,0.000022672759,0.0018242425,0.000021002843,0.00013020229,0.00217402,0.9915462,0.00030739434],"about_ca_topic_score_codex":0.00044966696,"about_ca_topic_score_gemma":0.00012043856,"teacher_disagreement_score":0.027865186,"about_ca_system_score_codex":0.00012280188,"about_ca_system_score_gemma":0.00015177178,"threshold_uncertainty_score":0.9668469},"labels":[],"label_agreement":null},{"id":"W6958144574","doi":"10.6084/m9.figshare.18071026.v1","title":"Additional file 1 of Reporting of abstracts in studies that used routinely collected data for exploring drug treatment effects: a cross-sectional survey","year":2022,"lang":"en","type":"article","venue":"Figshare","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":"McMaster University; St Joseph's Health Centre","funders":"","keywords":"Drug treatment; MEDLINE; Data collection; Data file; Drug","score_opus":0.784504474706073,"score_gpt":0.5016852671014205,"score_spread":0.2828192076046525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958144574","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02063161,0.000030541436,0.0000037701288,0.0000021491364,0.000020164258,0.0006617497,0.9785079,0.000079655285,0.00006247115],"genre_scores_gemma":[0.105724975,0.0000010716982,0.0068541323,0.0000044945673,0.000022656784,0.010407322,0.8767375,0.000025460988,0.00022238334],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99811757,0.00009401161,0.0010208467,0.0002982455,0.0002948048,0.00017454982],"domain_scores_gemma":[0.97724813,0.020029658,0.0019850228,0.00041693955,0.0002958741,0.000024394563],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039619213,0.00014348967,0.0004327725,0.000110128385,0.0001136613,0.000011680019,0.00023950417,0.000030801442,0.4602839],"category_scores_gemma":[0.08635708,0.00014016975,0.0000688927,0.00026003786,0.000014050756,0.00023159951,0.00034558505,0.00011196194,0.0000032780242],"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":[0.00005683181,0.00020837554,0.001707223,0.00056299666,0.00008369028,0.000012302016,0.00025508658,0.000083689694,0.000043363485,0.00000846596,0.99689287,0.00008510195],"study_design_scores_gemma":[0.0020608823,0.00086652755,0.8988891,0.0070724105,0.000031422107,0.000033957942,0.000968139,0.00087686034,0.021960482,0.008546466,0.057925124,0.0007686304],"about_ca_topic_score_codex":0.000039974173,"about_ca_topic_score_gemma":0.00036730373,"teacher_disagreement_score":0.93896776,"about_ca_system_score_codex":0.0002704363,"about_ca_system_score_gemma":0.00019006453,"threshold_uncertainty_score":0.9213389},"labels":[],"label_agreement":null},{"id":"W6958213777","doi":"10.6084/m9.figshare.26695779","title":"Additional file 5 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Mediation; Term (time); Binary data; Relation (database); Binary relation","score_opus":0.42972097942281373,"score_gpt":0.46274144100888837,"score_spread":0.033020461586074634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958213777","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01237987,0.000076074786,0.0015248442,0.000024580586,0.000012357702,0.0039938004,0.9818459,0.00013604668,0.00000653849],"genre_scores_gemma":[0.4471814,3.385522e-7,0.07337066,0.000022280146,0.00011096616,0.030792687,0.44842067,0.00007531793,0.000025692438],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998454,0.00019813537,0.00047732765,0.00034875615,0.0003548649,0.00016693656],"domain_scores_gemma":[0.98560154,0.013447051,0.00030172864,0.00019554344,0.00037397363,0.00008014029],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053822907,0.00020413844,0.0004248364,0.00018090295,0.00006955081,0.000028806642,0.000079293386,0.0001437623,0.17922413],"category_scores_gemma":[0.016543789,0.00014999296,0.00006593539,0.00013953004,0.000029970419,0.00024373188,0.000035356188,0.00009723426,0.0000012236522],"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":[0.00071252923,0.0008652218,0.00008531303,0.0039496105,0.00015449621,0.000087569155,0.0010232279,0.000032620246,0.0001480273,0.0000543566,0.9757374,0.01714961],"study_design_scores_gemma":[0.0028558027,0.004272948,0.0009817713,0.0030461783,0.00043140812,0.00009669948,0.0015730422,0.97568256,0.00042620115,0.009395012,0.000824554,0.00041380667],"about_ca_topic_score_codex":7.594779e-7,"about_ca_topic_score_gemma":0.000015213282,"teacher_disagreement_score":0.97564995,"about_ca_system_score_codex":0.000057859437,"about_ca_system_score_gemma":0.000294633,"threshold_uncertainty_score":0.9917403},"labels":[],"label_agreement":null},{"id":"W6958357473","doi":"10.6084/m9.figshare.27932635","title":"Additional file 1 of Investigation of treatment delay in a complex healthcare process using physician insurance claims data: an application to symptomatic carotid artery stenosis","year":2024,"lang":"en","type":"article","venue":"Figshare","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":"University of British Columbia","funders":"","keywords":"Stenosis; Process (computing); Health care; Carotid arteries; MEDLINE","score_opus":0.28656438753837693,"score_gpt":0.4250100997574115,"score_spread":0.13844571221903457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958357473","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012258473,0.000008781595,0.000171928,0.000024583811,0.0000033408726,0.0008084219,0.9865682,0.00012374952,0.000032483982],"genre_scores_gemma":[0.33576667,3.3506683e-7,0.015942171,0.000043469605,0.000030164654,0.0019071846,0.6462866,0.000021445301,0.0000019573865],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998985,0.000048819893,0.00036990916,0.00029174297,0.00017456817,0.00012998376],"domain_scores_gemma":[0.99855286,0.00058755884,0.00019441359,0.000437366,0.00017138793,0.00005639487],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003150004,0.00013818547,0.00024991573,0.00013345001,0.00002703301,0.000015635042,0.00020644092,0.000058831618,0.065021984],"category_scores_gemma":[0.00027278299,0.0001340614,0.00002657688,0.00044893546,0.000013627828,0.0004187348,0.000049370046,0.00007070318,0.000054515996],"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":[0.000015544018,0.00028083168,0.00021700482,0.0079315165,0.000062237996,0.0000048382662,0.0030762681,0.00054060045,0.0034680516,0.00040757898,0.9723099,0.011685617],"study_design_scores_gemma":[0.0010720504,0.003525561,0.04853291,0.18353397,0.00016194824,0.00006342378,0.00329026,0.4283785,0.04637373,0.25380027,0.028506396,0.0027609796],"about_ca_topic_score_codex":0.000023039624,"about_ca_topic_score_gemma":0.00016001992,"teacher_disagreement_score":0.9438035,"about_ca_system_score_codex":0.00021102132,"about_ca_system_score_gemma":0.00020444577,"threshold_uncertainty_score":0.93583274},"labels":[],"label_agreement":null},{"id":"W6958460218","doi":"10.6084/m9.figshare.26577188.v1","title":"Additional file 1 of A method for generating synthetic longitudinal health data","year":2024,"lang":"en","type":"article","venue":"Figshare","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":"Institute of Health Economics; Children's Hospital of Eastern Ontario; University of Alberta","funders":"","keywords":"Longitudinal data; Data file; Health data","score_opus":0.504461716970461,"score_gpt":0.5126951724128155,"score_spread":0.008233455442354431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958460218","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.636518e-8,0.000106966356,0.030618835,0.00006230218,0.000010960005,0.00027358977,0.9682349,0.00024330054,0.0004490751],"genre_scores_gemma":[0.000009650256,3.0284386e-7,0.46609113,0.000029541361,0.00007500465,0.00092330895,0.5326075,0.000017115775,0.00024643997],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991312,0.00003539971,0.0002528242,0.000280958,0.00013312128,0.00016649628],"domain_scores_gemma":[0.99060845,0.008704607,0.00012526818,0.00042669842,0.00009189315,0.000043078962],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000111010486,0.00010243245,0.00018858076,0.000053217984,0.000053105636,0.0000304899,0.00026932382,0.00004681256,0.9729388],"category_scores_gemma":[0.013985494,0.00009377947,0.000052954085,0.00011111035,0.0000053139706,0.00016616835,0.00017962907,0.00010538573,0.00016028009],"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":[0.0000010667293,0.000013159521,6.7719492e-9,0.00090014725,0.000014270587,0.0000020046425,0.000019803292,0.0000017919155,0.000012220145,0.0011106926,0.9831628,0.014762007],"study_design_scores_gemma":[0.000022194681,0.00006464524,0.00000126152,0.0085861785,0.0000067440324,0.00001990153,0.000015412417,0.04038602,0.000317169,0.02960483,0.9208628,0.00011282992],"about_ca_topic_score_codex":0.0000017021129,"about_ca_topic_score_gemma":0.000009347412,"teacher_disagreement_score":0.9727785,"about_ca_system_score_codex":0.000041547468,"about_ca_system_score_gemma":0.00026878095,"threshold_uncertainty_score":0.99432015},"labels":[],"label_agreement":null},{"id":"W6958545144","doi":"10.6084/m9.figshare.26695779.v1","title":"Additional file 5 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Mediation; Term (time); Binary data; Relation (database); Binary relation","score_opus":0.42972097942281373,"score_gpt":0.46274144100888837,"score_spread":0.033020461586074634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958545144","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01237987,0.000076074786,0.0015248442,0.000024580586,0.000012357702,0.0039938004,0.9818459,0.00013604668,0.00000653849],"genre_scores_gemma":[0.4471814,3.385522e-7,0.07337066,0.000022280146,0.00011096616,0.030792687,0.44842067,0.00007531793,0.000025692438],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998454,0.00019813537,0.00047732765,0.00034875615,0.0003548649,0.00016693656],"domain_scores_gemma":[0.98560154,0.013447051,0.00030172864,0.00019554344,0.00037397363,0.00008014029],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053822907,0.00020413844,0.0004248364,0.00018090295,0.00006955081,0.000028806642,0.000079293386,0.0001437623,0.17922413],"category_scores_gemma":[0.016543789,0.00014999296,0.00006593539,0.00013953004,0.000029970419,0.00024373188,0.000035356188,0.00009723426,0.0000012236522],"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":[0.00071252923,0.0008652218,0.00008531303,0.0039496105,0.00015449621,0.000087569155,0.0010232279,0.000032620246,0.0001480273,0.0000543566,0.9757374,0.01714961],"study_design_scores_gemma":[0.0028558027,0.004272948,0.0009817713,0.0030461783,0.00043140812,0.00009669948,0.0015730422,0.97568256,0.00042620115,0.009395012,0.000824554,0.00041380667],"about_ca_topic_score_codex":7.594779e-7,"about_ca_topic_score_gemma":0.000015213282,"teacher_disagreement_score":0.97564995,"about_ca_system_score_codex":0.000057859437,"about_ca_system_score_gemma":0.000294633,"threshold_uncertainty_score":0.9917403},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W6958564969","doi":"10.6084/m9.figshare.18071026","title":"Additional file 1 of Reporting of abstracts in studies that used routinely collected data for exploring drug treatment effects: a cross-sectional survey","year":2022,"lang":"en","type":"article","venue":"Figshare","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":"McMaster University; St Joseph's Health Centre","funders":"","keywords":"Drug treatment; MEDLINE; Data collection; Data file; Drug","score_opus":0.784504474706073,"score_gpt":0.5016852671014205,"score_spread":0.2828192076046525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958564969","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02063161,0.000030541436,0.0000037701288,0.0000021491364,0.000020164258,0.0006617497,0.9785079,0.000079655285,0.00006247115],"genre_scores_gemma":[0.105724975,0.0000010716982,0.0068541323,0.0000044945673,0.000022656784,0.010407322,0.8767375,0.000025460988,0.00022238334],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99811757,0.00009401161,0.0010208467,0.0002982455,0.0002948048,0.00017454982],"domain_scores_gemma":[0.97724813,0.020029658,0.0019850228,0.00041693955,0.0002958741,0.000024394563],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039619213,0.00014348967,0.0004327725,0.000110128385,0.0001136613,0.000011680019,0.00023950417,0.000030801442,0.4602839],"category_scores_gemma":[0.08635708,0.00014016975,0.0000688927,0.00026003786,0.000014050756,0.00023159951,0.00034558505,0.00011196194,0.0000032780242],"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":[0.00005683181,0.00020837554,0.001707223,0.00056299666,0.00008369028,0.000012302016,0.00025508658,0.000083689694,0.000043363485,0.00000846596,0.99689287,0.00008510195],"study_design_scores_gemma":[0.0020608823,0.00086652755,0.8988891,0.0070724105,0.000031422107,0.000033957942,0.000968139,0.00087686034,0.021960482,0.008546466,0.057925124,0.0007686304],"about_ca_topic_score_codex":0.000039974173,"about_ca_topic_score_gemma":0.00036730373,"teacher_disagreement_score":0.93896776,"about_ca_system_score_codex":0.0002704363,"about_ca_system_score_gemma":0.00019006453,"threshold_uncertainty_score":0.9213389},"labels":[],"label_agreement":null},{"id":"W6958585884","doi":"10.6084/m9.figshare.26695776","title":"Additional file 4 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Outcome (game theory); Binary number; Mediation; Binary data; Empirical research; Binary relation; Relation (database)","score_opus":0.4314493148368384,"score_gpt":0.46305523481070243,"score_spread":0.03160591997386403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958585884","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012324968,0.00007613542,0.0015285938,0.000024458624,0.000012353732,0.003993474,0.9818975,0.00013600102,0.0000065466943],"genre_scores_gemma":[0.44836584,3.3729472e-7,0.07309732,0.000022183985,0.00011053665,0.030678311,0.447625,0.00007502483,0.000025428852],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845415,0.0001979888,0.00047734095,0.0003487169,0.00035484636,0.00016694018],"domain_scores_gemma":[0.9855895,0.013461734,0.00030173833,0.00019557278,0.0003713243,0.00008013247],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005379912,0.0002041207,0.00042477236,0.00018090935,0.000069548,0.000028817822,0.000079319594,0.00014375619,0.1792591],"category_scores_gemma":[0.016486498,0.00014999052,0.00006592757,0.0001394905,0.000029970292,0.0002437322,0.000035354617,0.00009722421,0.0000012309274],"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":[0.00072552357,0.00086890644,0.000085942615,0.0039657163,0.00015516364,0.00008795162,0.0010281372,0.00003240831,0.0001476958,0.00005456613,0.97564757,0.017200392],"study_design_scores_gemma":[0.002846685,0.004307455,0.00096415123,0.0030329248,0.00042966942,0.00009633191,0.0015665056,0.9756905,0.0004217485,0.009403835,0.00082800054,0.00041222063],"about_ca_topic_score_codex":7.5346765e-7,"about_ca_topic_score_gemma":0.000015165415,"teacher_disagreement_score":0.97565806,"about_ca_system_score_codex":0.00005784832,"about_ca_system_score_gemma":0.00029434238,"threshold_uncertainty_score":0.99179804},"labels":[],"label_agreement":null},{"id":"W6964369708","doi":"10.25384/sage.21150912","title":"sj-docx-3-mdm-10.1177_0272989X221121747 – Supplemental material for A Tutorial on Time-Dependent Cohort State-Transition Models in R Using a Cost-Effectiveness Analysis Example","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Cohort; Cohort study; Statistical analysis; MEDLINE","score_opus":0.22442915652199655,"score_gpt":0.4398183123919964,"score_spread":0.21538915586999988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964369708","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":[0.22637467,0.00007813074,0.695035,0.000055412896,0.00042020137,0.0038574454,0.073921666,0.00018796689,0.00006952905],"genre_scores_gemma":[0.94839686,0.00013599184,0.03412806,0.00013842255,0.0005106692,0.001441753,0.014960001,0.00017620085,0.0001120209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960704,0.00081113825,0.00090532337,0.0007333002,0.0008958634,0.0005840061],"domain_scores_gemma":[0.99753827,0.00065919646,0.0004720865,0.0010899892,0.00011806276,0.00012240392],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004631749,0.00035087953,0.0008086876,0.0006172104,0.00036075021,0.0001950709,0.00081568875,0.00008737964,0.011640369],"category_scores_gemma":[0.00013852838,0.00036665876,0.00016926299,0.00063764286,0.000036151607,0.0010678313,0.0006283692,0.00043048963,0.0000048793668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01965262,0.009733188,0.0019358705,0.00084807695,0.009099781,0.0012135853,0.0049523637,0.46161288,0.43646547,0.0022856586,0.023044165,0.029156327],"study_design_scores_gemma":[0.01157208,0.0021404647,0.00044318967,0.0009110859,0.0042267754,0.00019152714,0.0015622155,0.47180408,0.07247323,0.42864013,0.0034510428,0.0025841715],"about_ca_topic_score_codex":0.0007346043,"about_ca_topic_score_gemma":0.00019644995,"teacher_disagreement_score":0.7220222,"about_ca_system_score_codex":0.0010632862,"about_ca_system_score_gemma":0.0001503978,"threshold_uncertainty_score":0.9998785},"labels":[],"label_agreement":null},{"id":"W6977105027","doi":"10.6084/m9.figshare.14190234","title":"Additional file 2 of Waist circumference prediction for epidemiological research using gradient boosted trees","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto","funders":"","keywords":"Circumference; Decision tree; Waist; Tree (set theory); Variable (mathematics)","score_opus":0.6877278544306521,"score_gpt":0.5092984696801275,"score_spread":0.1784293847505246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977105027","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006008047,0.00002529981,0.0005966143,0.000021269407,0.000010344423,0.0003071407,0.9972372,0.00012660057,0.0016154634],"genre_scores_gemma":[0.002565786,0.0000013798738,0.07187178,0.000023819122,0.00010398763,0.0020858708,0.92290914,0.00001798921,0.00042023024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870634,0.00015912672,0.00033022344,0.00027326256,0.00025868483,0.000272357],"domain_scores_gemma":[0.9834311,0.015152632,0.00015574318,0.00026386054,0.00093205116,0.00006458501],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015050561,0.000108507506,0.00024493152,0.00006932919,0.00011972578,0.000014082289,0.00015079654,0.00014212559,0.9550471],"category_scores_gemma":[0.08429934,0.0000983936,0.000098510216,0.00024298162,0.000035432367,0.000107634354,0.00012626265,0.00021734112,0.000063507636],"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":[0.0000068217787,0.000060033733,0.0000019343595,0.0001370107,0.000009241261,0.000004955946,0.000016889215,0.000004530031,0.0003839067,0.0013102605,0.9973916,0.000672851],"study_design_scores_gemma":[0.00017529879,0.0002927396,0.0010614557,0.007722105,0.000011262874,0.00004139595,0.00015723078,0.005546486,0.008126479,0.34094113,0.6356813,0.0002431535],"about_ca_topic_score_codex":0.0000011242549,"about_ca_topic_score_gemma":0.0000105604895,"teacher_disagreement_score":0.95498353,"about_ca_system_score_codex":0.00010945049,"about_ca_system_score_gemma":0.00017079376,"threshold_uncertainty_score":0.923414},"labels":[],"label_agreement":null},{"id":"W6977162010","doi":"10.6084/m9.figshare.21293449.v1","title":"Additional file 1 of Examining evidence of time-dependent treatment effects: an illustration using regression methods","year":2022,"lang":"en","type":"article","venue":"Figshare","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":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Regression analysis; Regression; Linear regression; Feature (linguistics)","score_opus":0.4876346835237333,"score_gpt":0.4969911417975102,"score_spread":0.009356458273776902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977162010","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032752164,0.000043098866,0.00090906513,0.0000013478899,0.000008620497,0.00033251525,0.9979906,0.0000968118,0.00029040675],"genre_scores_gemma":[0.0046406393,0.00000108364,0.47704685,0.000009793488,0.00004080059,0.001985087,0.5158382,0.000033131073,0.00040437374],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99879235,0.00036295754,0.00026951235,0.00018534165,0.00028065566,0.00010916818],"domain_scores_gemma":[0.992175,0.0069480105,0.00045271852,0.00027353328,0.00011606067,0.00003468844],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011956088,0.00012153661,0.00022747142,0.00007824186,0.00008814445,0.000006439773,0.00014442716,0.00004772853,0.96227175],"category_scores_gemma":[0.006265483,0.0001091975,0.000048335292,0.00013633238,0.000009386328,0.0002475134,0.00012798351,0.0000965395,0.000016414986],"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":[0.000037442987,0.00023426289,8.9803757e-7,0.00044999085,0.00002808633,0.0000120226805,0.00034804145,0.0003554119,0.034510985,0.000044710974,0.9379377,0.026040481],"study_design_scores_gemma":[0.0007629743,0.008850526,0.00022625113,0.05723369,0.0001688322,0.00012956338,0.001083712,0.04359846,0.807851,0.030376483,0.048530336,0.0011881641],"about_ca_topic_score_codex":0.000003997262,"about_ca_topic_score_gemma":0.0000013345013,"teacher_disagreement_score":0.96225536,"about_ca_system_score_codex":0.00020583715,"about_ca_system_score_gemma":0.00010757642,"threshold_uncertainty_score":0.7500821},"labels":[],"label_agreement":null},{"id":"W6977361464","doi":"10.6084/m9.figshare.26695767","title":"Additional file 1 of An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"Figshare","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; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Binary number; Variance (accounting); Outcome (game theory); Estimator; Binary data; Confidence interval; Mediation; Relation (database); Range (aeronautics)","score_opus":0.43388011366608537,"score_gpt":0.4631154158349202,"score_spread":0.029235302168834854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977361464","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012284088,0.00007547082,0.0015110977,0.000024574223,0.0000123354075,0.0039864494,0.98196363,0.0001358529,0.000006521137],"genre_scores_gemma":[0.43984094,3.346096e-7,0.07408924,0.000022277407,0.00011089992,0.0313173,0.45451772,0.00007538246,0.000025900514],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984543,0.00019817852,0.00047700413,0.000348819,0.00035480206,0.00016693454],"domain_scores_gemma":[0.9855057,0.01354224,0.00030163466,0.00019572822,0.00037457302,0.000080130216],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053782563,0.00020413341,0.00042464628,0.00018088838,0.000069522845,0.000028752585,0.0000793121,0.00014375622,0.18471782],"category_scores_gemma":[0.016692108,0.00014999899,0.000065926775,0.00013955154,0.000029963694,0.00024353668,0.000035365185,0.00009724428,0.0000012415421],"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":[0.0006939775,0.0008431059,0.0000831304,0.0038177338,0.00015066726,0.00008419282,0.0009967043,0.00003182831,0.00014495318,0.000051591738,0.97661215,0.016489988],"study_design_scores_gemma":[0.0028306327,0.0042616636,0.0009680374,0.003041052,0.00043149493,0.00009653041,0.0015734325,0.97578955,0.00042273148,0.009324424,0.0008471678,0.00041330306],"about_ca_topic_score_codex":7.51917e-7,"about_ca_topic_score_gemma":0.000015021529,"teacher_disagreement_score":0.97576493,"about_ca_system_score_codex":0.000057843445,"about_ca_system_score_gemma":0.00029517157,"threshold_uncertainty_score":0.99159074},"labels":[],"label_agreement":null},{"id":"W6977530810","doi":"10.6084/m9.figshare.26650401.v1","title":"Additional file 1 of A blueprint for a multi-disease, multi-domain Bayesian adaptive platform trial incorporating adult and paediatric subgroups: the Staphylococcus aureus Network Adaptive Platform trial","year":2024,"lang":"en","type":"article","venue":"Figshare","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":"","keywords":"Blueprint; Bayesian network; Bayesian probability; Adaptive design; Staphylococcus aureus; Clinical trial","score_opus":0.165584257030611,"score_gpt":0.35069281041370465,"score_spread":0.18510855338309365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977530810","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014306423,0.00018434583,0.017227255,0.000017980286,0.000100645666,0.0058627976,0.9758769,0.00040280193,0.00018416805],"genre_scores_gemma":[0.017776407,0.0000067081414,0.462542,0.00010832763,0.0025609122,0.038506225,0.4780238,0.00019536485,0.00028024134],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974645,0.0000791096,0.000864516,0.0006124026,0.00045164427,0.00052783906],"domain_scores_gemma":[0.9870914,0.011231866,0.0006500703,0.00038668417,0.0004260724,0.00021390922],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026368783,0.0004716409,0.00055988954,0.00016347106,0.0002864344,0.0001170299,0.00036506975,0.00026827387,0.20680612],"category_scores_gemma":[0.009652023,0.0003613442,0.0003549686,0.00048227998,0.00007934607,0.00046284395,0.00031666431,0.00055028236,0.00005074357],"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":[0.020358682,0.00021832957,4.4814075e-7,0.0003412492,0.00015371095,0.000026916485,0.00037505195,0.00003763036,0.000002514048,0.0075283917,0.9676593,0.0032977588],"study_design_scores_gemma":[0.11217386,0.005643622,0.00010795722,0.016566513,0.0003686122,0.000012928999,0.0032391085,0.33335096,0.00012934557,0.45972094,0.0663833,0.0023028587],"about_ca_topic_score_codex":0.000008254944,"about_ca_topic_score_gemma":0.0001830904,"teacher_disagreement_score":0.901276,"about_ca_system_score_codex":0.00019879143,"about_ca_system_score_gemma":0.0005526695,"threshold_uncertainty_score":0.99988383},"labels":[],"label_agreement":null},{"id":"W6979860349","doi":"","title":"Amiodarone and the risk of pacemaker insertion in elderly patients with atrial fibrillation : analysis of time-dependent exposure using nested case-control and survival analysis methodologies","year":2003,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Amiodarone; Nested case-control study; Atrial fibrillation; Confounding; Proportional hazards model; Cohort; Cohort study; Adverse effect","score_opus":0.051780270791267874,"score_gpt":0.3305015553312274,"score_spread":0.2787212845399595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979860349","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":[0.99679697,0.00025265568,0.00045770465,0.0000017112658,0.000056111134,0.0012661204,0.0009596727,0.000068428984,0.00014062545],"genre_scores_gemma":[0.984228,0.00021511412,0.015148342,0.0000035488465,0.0000070333354,0.000020925521,0.00025046465,0.00006640014,0.000060183647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934681,0.0033453703,0.0014530534,0.00069831614,0.0007126914,0.00032247065],"domain_scores_gemma":[0.99183834,0.004071766,0.0025862583,0.00065768074,0.00076676847,0.00007917992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037023304,0.000577232,0.0022741247,0.0014184711,0.00028798747,0.000041609375,0.0001334626,0.00060718646,0.000024686637],"category_scores_gemma":[0.0047064205,0.00042964518,0.00047785317,0.0022964566,0.00017816569,0.00047469803,0.00005428442,0.0006273833,2.400855e-7],"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":[0.03035845,0.0006076914,0.609427,0.002297416,0.096195556,0.00023105962,0.0008797982,0.071925625,0.021120096,0.039632723,3.5684386e-7,0.12732427],"study_design_scores_gemma":[0.027833914,0.0027016182,0.49149567,0.0011529033,0.23775187,0.00007363535,0.0047753695,0.016063761,0.019357761,0.19494273,0.000012709926,0.0038380644],"about_ca_topic_score_codex":0.001523095,"about_ca_topic_score_gemma":0.010821021,"teacher_disagreement_score":0.15531,"about_ca_system_score_codex":0.00022017705,"about_ca_system_score_gemma":0.000032630345,"threshold_uncertainty_score":0.9998155},"labels":[],"label_agreement":null},{"id":"W6980169674","doi":"","title":"Bayesian causal inference with longitudinal data","year":2021,"lang":"","type":"dissertation","venue":"TSpace","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":"Canadian Institutes of Health Research; Hospital for Sick Children; Childhood Arthritis and Rheumatology Research Alliance","keywords":"Frequentist inference; Causal inference; Observational study; Bayesian probability; Marginal structural model; Bayesian statistics; Context (archaeology); Propensity score matching; Statistical inference","score_opus":0.21101959100071532,"score_gpt":0.48995238338930974,"score_spread":0.2789327923885944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980169674","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":[0.03335452,0.0016025,0.9262015,0.00048032467,0.0007404282,0.0020897547,0.00030318648,0.0010776776,0.034150112],"genre_scores_gemma":[0.6412642,0.0015968878,0.2991278,0.000101990176,0.0005345254,0.0002590575,0.011162069,0.0005398156,0.045413654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9935754,0.00028914283,0.0011308586,0.0024047433,0.0013917187,0.001208144],"domain_scores_gemma":[0.98985946,0.001313591,0.0013937639,0.0057944455,0.0011929481,0.0004457878],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00066087174,0.0015035738,0.0017610329,0.00031521556,0.00040349024,0.00047091584,0.0023994485,0.0010022699,0.0039508496],"category_scores_gemma":[0.0023566908,0.0014332131,0.00014045804,0.0010532597,0.00033830447,0.0009945177,0.0009217403,0.0021289273,0.0001400535],"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":[0.005750741,0.010042756,0.031314444,0.039040867,0.00994401,0.015643885,0.16130842,0.0007033736,0.03289347,0.5449588,0.04815921,0.10024002],"study_design_scores_gemma":[0.009512941,0.010237619,0.012214537,0.077500224,0.017035581,0.0021941327,0.28462416,0.045688573,0.21153305,0.26451537,0.031335913,0.033607915],"about_ca_topic_score_codex":0.0007175836,"about_ca_topic_score_gemma":0.0072478466,"teacher_disagreement_score":0.6270737,"about_ca_system_score_codex":0.00030262448,"about_ca_system_score_gemma":0.0019922017,"threshold_uncertainty_score":0.99977136},"labels":[],"label_agreement":null},{"id":"W6980602840","doi":"","title":"Commentary on Santibanez Yanez","year":2007,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","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":"Simon Fraser University","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.08780777428797758,"score_gpt":0.3437218309558868,"score_spread":0.25591405666790923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980602840","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":[0.97797674,0.000029521289,0.005979979,0.0018293937,0.00012021941,0.00035441652,0.000041778272,0.00039707473,0.013270876],"genre_scores_gemma":[0.9688655,0.000026867292,0.02834933,0.0010218115,0.00008369348,2.9521385e-7,0.000029346143,0.000045856217,0.0015772884],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979351,0.00013269509,0.00030511213,0.00045237792,0.0006102059,0.00056450925],"domain_scores_gemma":[0.9977262,0.0007529755,0.00033245067,0.00078308163,0.00016056812,0.00024473385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013833899,0.00030584514,0.00044708015,0.0003838485,0.00039108063,0.000016259364,0.00076014694,0.00029814124,0.0008892594],"category_scores_gemma":[0.0002482457,0.00036800202,0.00021471434,0.00042168266,0.00031837408,0.0005836637,0.00034017593,0.0006721603,0.0001679548],"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":[0.0055694715,0.003792669,0.42962146,0.00091013627,0.00093336886,0.0019589153,0.010763571,0.00003643653,0.22098567,0.16682126,0.12850167,0.030105392],"study_design_scores_gemma":[0.0056244703,0.0022209862,0.2198342,0.0011212166,0.0004582878,0.00011520486,0.00659406,0.000042344425,0.3527574,0.32611006,0.082428105,0.0026936966],"about_ca_topic_score_codex":0.00007005399,"about_ca_topic_score_gemma":0.00046768284,"teacher_disagreement_score":0.20978725,"about_ca_system_score_codex":0.00030726427,"about_ca_system_score_gemma":0.000030333793,"threshold_uncertainty_score":0.9998772},"labels":[],"label_agreement":null},{"id":"W6981383349","doi":"","title":"Effets d'un entraînement combiné en force et en endurance sur la performance en course à pied","year":2012,"lang":"fr","type":"other","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Context (archaeology); Work (physics); Falling (accident); Control (management)","score_opus":0.010824079880901276,"score_gpt":0.22543143681146705,"score_spread":0.21460735693056576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981383349","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":[0.26535964,0.029942466,0.039750908,0.0017994435,0.0023409214,0.0034864792,0.00039215968,0.0014481309,0.65547985],"genre_scores_gemma":[0.5492961,0.0036352708,0.015807975,0.00016669375,0.00043029882,0.00012821468,0.00011599113,0.00022744875,0.430192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99561226,0.0008993283,0.00070085475,0.0008000923,0.00097525434,0.001012205],"domain_scores_gemma":[0.9959237,0.0015869548,0.00079734076,0.0009432837,0.00023845899,0.00051026465],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00093398127,0.0009935115,0.000935936,0.00027979526,0.0020128915,0.00007077609,0.0009820453,0.0011211367,0.001161716],"category_scores_gemma":[0.00023368133,0.0011114132,0.00037816793,0.0002578763,0.00057130115,0.00082029577,0.00063757127,0.0012429212,0.0003167814],"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":false,"study_design_scores_codex":[0.00068894855,0.0024199428,0.026503155,0.0019960485,0.0021067923,0.0026456667,0.049571797,0.0014811,0.02334134,0.83471686,0.0068516373,0.04767672],"study_design_scores_gemma":[0.004474975,0.00043845788,0.063159585,0.0032655569,0.0016367857,0.0026563564,0.0037558286,0.0016219985,0.041236088,0.005207937,0.86982435,0.0027221066],"about_ca_topic_score_codex":0.0023697438,"about_ca_topic_score_gemma":0.0007644082,"teacher_disagreement_score":0.8629727,"about_ca_system_score_codex":0.0073595396,"about_ca_system_score_gemma":0.0014223354,"threshold_uncertainty_score":0.9997513},"labels":[],"label_agreement":null},{"id":"W6981661884","doi":"","title":"Essays in political economy","year":2004,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Liquation; Fusible alloy; Dysgeusia; Demotion; Hemopericardium","score_opus":0.014505821138513057,"score_gpt":0.22255010348214613,"score_spread":0.20804428234363306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981661884","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004525369,0.0001245439,0.0004874534,0.0014389954,0.00005409302,0.00022306359,0.0001852931,0.000044589025,0.9973967],"genre_scores_gemma":[0.21531191,0.0001915604,0.043907873,0.0035218399,0.0002596528,0.00011416158,0.000024496103,0.0006570986,0.7360114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843234,0.000034991233,0.00029917812,0.0002483519,0.00060826424,0.00037687342],"domain_scores_gemma":[0.99908423,0.00026647522,0.00017800741,0.00025764198,1.6745993e-7,0.00021350215],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000068436625,0.00025585754,0.00041910633,0.000052625343,0.00002398979,0.000009847743,0.00022500708,0.00007714479,0.00028950337],"category_scores_gemma":[0.000006399502,0.0002562974,0.000023775689,0.00004433425,0.00009754044,0.00011989369,0.00012786208,0.00022301788,2.7901725e-9],"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":[0.00002000312,0.000019342257,0.00052797917,0.00032163065,0.000023875627,0.00007877101,0.000007388971,6.233775e-7,0.00005543132,0.98334885,0.015155084,0.00044100414],"study_design_scores_gemma":[0.00024405627,0.000033468463,0.00017412339,0.00065818254,0.000013725445,0.000005421014,0.00033610404,0.000024548888,0.007973869,0.8299925,0.16019204,0.00035200757],"about_ca_topic_score_codex":0.0056100716,"about_ca_topic_score_gemma":0.10718247,"teacher_disagreement_score":0.26138532,"about_ca_system_score_codex":0.000025084904,"about_ca_system_score_gemma":0.0018382295,"threshold_uncertainty_score":0.9999889},"labels":[],"label_agreement":null},{"id":"W6981761447","doi":"","title":"Faciliter l'apprentissage : mémoire de l'Institut canadien d'éducation des adultes présenté au Ministère de l'éducation dans le cadre de sa consultation sur les régimes pédagogiques","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Data collection; Work (physics)","score_opus":0.043868091663253075,"score_gpt":0.3064908963608217,"score_spread":0.26262280469756866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981761447","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":[0.6187336,0.0051337895,0.12959099,0.007744835,0.0003422809,0.0022149277,0.002160762,0.0007717287,0.23330706],"genre_scores_gemma":[0.5648475,0.0009371963,0.044701964,0.00029553665,0.0005467426,0.0010216997,0.00049654586,0.0003962936,0.38675648],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946034,0.0011380798,0.001161967,0.0009945576,0.0010384663,0.0010635401],"domain_scores_gemma":[0.9883982,0.008531317,0.0012261721,0.0007147095,0.00051836565,0.0006112603],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012325065,0.0010341946,0.0008049728,0.0010960667,0.00063824054,0.00046799853,0.0009891378,0.0004914612,0.0025578497],"category_scores_gemma":[0.019992268,0.0011315915,0.00029480486,0.0007483908,0.0013861535,0.0011276272,0.000287364,0.0007435944,0.00010161942],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00030192535,0.0022093134,0.22466403,0.0032335685,0.00092321396,0.00008262192,0.363116,0.00072509015,0.009019212,0.14177611,0.24343994,0.010508986],"study_design_scores_gemma":[0.0035647629,0.00092955766,0.19686705,0.0071910406,0.0010907727,0.0007053219,0.04056163,0.005093405,0.022108983,0.0694453,0.648036,0.0044061807],"about_ca_topic_score_codex":0.6004989,"about_ca_topic_score_gemma":0.99473655,"teacher_disagreement_score":0.40459606,"about_ca_system_score_codex":0.053417463,"about_ca_system_score_gemma":0.17496124,"threshold_uncertainty_score":0.99911344},"labels":[],"label_agreement":null},{"id":"W6990555918","doi":"","title":"Do opportunities for low-income students at top colleges promote academic success? Evidence from Colombia's Ser Pilo Paga program","year":2023,"lang":"en","type":"other","venue":"Econstor (Econstor)","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Scholarship; Test (biology); Socioeconomic status; Government (linguistics); Higher education; Regression discontinuity design","score_opus":0.16604362345088727,"score_gpt":0.4146045638726884,"score_spread":0.24856094042180113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990555918","genre_codex":"empirical","genre_gemma":"other","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":[0.8557416,0.00699199,0.0015568169,0.0009240662,0.007010809,0.026818838,0.008345469,0.023135915,0.069474496],"genre_scores_gemma":[0.028521288,0.007033734,0.04174656,0.00026618768,0.001958252,0.013208195,0.00028710868,0.004504923,0.90247375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99419224,0.00026838286,0.0016230688,0.0016653143,0.0009821061,0.0012689104],"domain_scores_gemma":[0.99253035,0.003080004,0.0019292805,0.0016697989,0.00029486002,0.00049569074],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0011999859,0.0013590516,0.0021572271,0.00073451974,0.00032107782,0.00023884937,0.0021078885,0.0017499811,0.004421112],"category_scores_gemma":[0.0016365717,0.0013885738,0.00047670078,0.00034993145,0.0009509617,0.0006061343,0.0010009981,0.001194763,0.00043217858],"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":[0.00018452527,0.0004937355,0.25964695,0.0018351786,0.001088925,0.00023981422,0.0005558768,7.1098384e-7,0.00017574319,0.004171858,0.7270602,0.0045464924],"study_design_scores_gemma":[0.0059332787,0.0032622896,0.011670341,0.05098354,0.0021966056,0.00018264454,0.002239614,0.00011678145,0.008839726,0.09548716,0.8086643,0.01042371],"about_ca_topic_score_codex":0.00017172858,"about_ca_topic_score_gemma":0.002010413,"teacher_disagreement_score":0.8329992,"about_ca_system_score_codex":0.0013996849,"about_ca_system_score_gemma":0.0006889414,"threshold_uncertainty_score":0.999916},"labels":[],"label_agreement":null},{"id":"W6990707524","doi":"","title":"Effects of sparse follow-up on marginal structural models for time-to-event data","year":2012,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Missing data; Imputation (statistics); Proportional hazards model; Logistic regression; Confidence interval; Hazard ratio; Regression; Interval (graph theory)","score_opus":0.09454336714397679,"score_gpt":0.3606878515543809,"score_spread":0.26614448441040406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990707524","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":[0.95712733,0.000249673,0.00033810985,0.000015707268,0.0020144368,0.007934029,0.00989565,0.0010443414,0.021380741],"genre_scores_gemma":[0.91915727,0.000040887157,0.058779333,0.00012863231,0.00013992912,0.00090316246,0.0045888065,0.000606388,0.015655607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99500835,0.00027501586,0.00125509,0.0013396266,0.0010727072,0.0010492349],"domain_scores_gemma":[0.99373984,0.0017607141,0.0011638486,0.0023035512,0.0005775451,0.0004544979],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001122494,0.0011307547,0.001520369,0.0005078503,0.00043985833,0.00004574151,0.0019361916,0.0009100295,0.00023695546],"category_scores_gemma":[0.0030176823,0.0011140907,0.00042156634,0.0003677493,0.000054488308,0.0012633987,0.0004383507,0.0011601902,0.00018932078],"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":[0.002475034,0.0005724508,0.000002489947,0.005647634,0.0007082207,0.000029724008,0.000039864586,0.00013377305,0.1306305,0.7157919,0.00032376806,0.14364468],"study_design_scores_gemma":[0.0014428421,0.00070710026,0.00007799193,0.001955915,0.0008356399,0.000010639229,0.00004194115,0.0005586061,0.319473,0.6675722,0.005864733,0.0014593807],"about_ca_topic_score_codex":0.00004593271,"about_ca_topic_score_gemma":0.0001562,"teacher_disagreement_score":0.18884252,"about_ca_system_score_codex":0.000600859,"about_ca_system_score_gemma":0.0000709824,"threshold_uncertainty_score":0.9991309},"labels":[],"label_agreement":null},{"id":"W6990929614","doi":"","title":"Essays on Child Mental Health: Estimating Diagnostic Errors, Latent Risk, and Long-term Trajectories","year":2021,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Receipt; Mental health; Unemployment; Mental illness; Medical diagnosis; Educational attainment","score_opus":0.06374682333869622,"score_gpt":0.41943096214123937,"score_spread":0.3556841388025431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990929614","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":[0.92982495,0.013893529,0.04316212,0.0017165613,0.0030089333,0.004748079,0.00039224728,0.0010649939,0.0021885973],"genre_scores_gemma":[0.8439263,0.023982277,0.11956659,0.00032920286,0.0007373483,0.0010752492,0.004641232,0.00065901276,0.0050827903],"study_design_codex":"qualitative","study_design_gemma":"systematic_review","domain_scores_codex":[0.9951039,0.0005049577,0.0012690494,0.0012786391,0.0008448544,0.000998619],"domain_scores_gemma":[0.9937144,0.0027509572,0.001949194,0.0009114566,0.00024438792,0.0004295853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006974887,0.001252877,0.0016046661,0.0002690817,0.0012511923,0.00027567448,0.00035031905,0.00062064925,0.00047023204],"category_scores_gemma":[0.004742145,0.0013189219,0.0002520822,0.00039516093,0.00021226425,0.00026976995,0.00017181583,0.0020338187,0.000029684616],"study_design_candidate":"qualitative","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":[0.0013075038,0.007017474,0.07234228,0.04178461,0.0025057078,0.0010041365,0.53898567,0.0010924549,0.0014127679,0.076811336,0.0071922704,0.24854377],"study_design_scores_gemma":[0.013176079,0.019219236,0.24906667,0.2777547,0.00565637,0.001427397,0.16396463,0.0178581,0.09827978,0.13014665,0.00081751036,0.022632875],"about_ca_topic_score_codex":0.0004310152,"about_ca_topic_score_gemma":0.0015574931,"teacher_disagreement_score":0.37502107,"about_ca_system_score_codex":0.0005741078,"about_ca_system_score_gemma":0.00032738733,"threshold_uncertainty_score":0.99892604},"labels":[],"label_agreement":null},{"id":"W6991695571","doi":"","title":"Improved Inference for Causal Effects in Network-Based Observational Studies","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":"Carolina Population Center, University of North Carolina at Chapel Hill; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada; University of North Carolina at Chapel Hill; University of Glasgow; Compute Canada; CHU Sainte-Justine Foundation; McGill University","keywords":"Observational study; Inference; Causal inference; Causal model; Bayesian probability","score_opus":0.14566278497070215,"score_gpt":0.40536658937855846,"score_spread":0.25970380440785634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991695571","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":[0.9529565,0.0017931701,0.0011706222,0.00013750393,0.005676525,0.015663719,0.0032697737,0.0033258148,0.0160064],"genre_scores_gemma":[0.79032505,0.00026576617,0.1861543,0.0009444705,0.00018874888,0.009413696,0.00332618,0.0004571715,0.008924621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950332,0.00039780184,0.0015640234,0.0012894213,0.0006358101,0.0010797314],"domain_scores_gemma":[0.9863033,0.010255327,0.0010176988,0.0009111526,0.0013424059,0.00017010106],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015477262,0.0011357875,0.001702452,0.0005473926,0.0006579761,0.00006879934,0.00080946373,0.0011437407,0.00002747282],"category_scores_gemma":[0.018888582,0.0011971617,0.00040168475,0.00094451563,0.00007845819,0.00063739065,0.00017368676,0.0016767104,0.0000089439045],"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":[0.0004938544,0.00031817405,0.00011532422,0.005524626,0.00035607364,0.000028418812,0.000011829362,0.0002807821,0.009209193,0.9428148,0.00006989134,0.04077702],"study_design_scores_gemma":[0.001418938,0.00036235448,0.0004501601,0.0039499593,0.0003044659,0.0000012990993,0.00007551614,0.00058651535,0.049240537,0.9401869,0.0022191042,0.0012042546],"about_ca_topic_score_codex":0.00006994855,"about_ca_topic_score_gemma":0.0055695414,"teacher_disagreement_score":0.18498369,"about_ca_system_score_codex":0.0014338383,"about_ca_system_score_gemma":0.00031745277,"threshold_uncertainty_score":0.9990478},"labels":[],"label_agreement":null},{"id":"W6992591809","doi":"","title":"Map showing thickness of unconsolidated deposits in the western quarter of the Muncie and eastern quarter of the Lafayette 1:100,000 quadrangles, central Indiana","year":2000,"lang":"en","type":"other","venue":"IUScholarWorks (Indiana University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Period (music); Window (computing); Block (permutation group theory)","score_opus":0.03482545056237412,"score_gpt":0.2675815949386494,"score_spread":0.2327561443762753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992591809","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":[0.72512347,0.0024118545,0.004168353,0.0022478777,0.0010713437,0.007967425,0.0014104355,0.0005037141,0.2550955],"genre_scores_gemma":[0.9818633,0.00010387507,0.000615638,0.00019353374,0.00006609822,0.0000048079623,0.000013074722,0.00017575338,0.016963918],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99720716,0.0007583007,0.00055277743,0.00041768892,0.00056849467,0.0004955784],"domain_scores_gemma":[0.99732196,0.0003678574,0.0008833533,0.0012759428,0.0000692032,0.0000816509],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035010814,0.00046817894,0.0007536855,0.0005299221,0.00011748233,0.000046693436,0.0017250979,0.00068574306,0.00022240885],"category_scores_gemma":[0.000045774854,0.0003096958,0.00027138952,0.000890056,0.0005437821,0.00024589355,0.00024019786,0.001219696,0.0000029664066],"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":[0.0011525959,0.0030634964,0.738735,0.00809242,0.003501887,0.0010623621,0.094145454,0.0002038025,0.0038562703,0.025596641,0.10983119,0.010758851],"study_design_scores_gemma":[0.023488505,0.0021860383,0.347095,0.08570758,0.008772124,0.0005560092,0.07165425,0.00032826056,0.029728128,0.030279756,0.3883993,0.011805048],"about_ca_topic_score_codex":0.0010598651,"about_ca_topic_score_gemma":0.0101801995,"teacher_disagreement_score":0.39164004,"about_ca_system_score_codex":0.00008257758,"about_ca_system_score_gemma":0.00015607977,"threshold_uncertainty_score":0.9999355},"labels":[],"label_agreement":null},{"id":"W7009393705","doi":"","title":"Empirical applications of the local likelihood method","year":2007,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Nonparametric statistics; Endogeneity; Estimator; Unobservable; Capital asset pricing model; Matching (statistics); Average treatment effect; Propensity score matching; Parametric statistics","score_opus":0.06586044157958328,"score_gpt":0.38839628260470915,"score_spread":0.3225358410251259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009393705","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":[0.016972452,0.00016473862,0.966867,0.00044839617,0.00009583348,0.0009835757,0.000057239067,0.00014006702,0.01427069],"genre_scores_gemma":[0.85323364,0.00010641714,0.1384923,0.00005564818,0.00007475446,0.0000039802603,0.00008367206,0.00005240483,0.007897159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987192,0.00015548358,0.00027231543,0.00022856916,0.00041647995,0.00020791018],"domain_scores_gemma":[0.9971601,0.0008069328,0.00071379193,0.00089789636,0.0003714763,0.000049853865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006810919,0.00019906934,0.00042178648,0.00013826558,0.00019989918,0.0000041324533,0.0012025967,0.00034598197,0.00011945119],"category_scores_gemma":[0.00011009534,0.00015280076,0.00032127573,0.00057810574,0.00030102613,0.00007334232,0.00017362315,0.0005213815,0.000011814549],"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":[0.0015176914,0.0017910874,0.000932952,0.0046105953,0.0016003796,0.000023674162,0.042100366,0.00010363369,0.16493514,0.4549075,0.054267306,0.2732097],"study_design_scores_gemma":[0.00056044065,0.00017839858,0.017670924,0.00035733203,0.0014499468,0.00001310509,0.039814617,0.00025980987,0.028138593,0.8960115,0.014926294,0.0006190665],"about_ca_topic_score_codex":0.00022985257,"about_ca_topic_score_gemma":0.0006687966,"teacher_disagreement_score":0.8362612,"about_ca_system_score_codex":0.00009517512,"about_ca_system_score_gemma":0.00016883119,"threshold_uncertainty_score":0.6231034},"labels":[],"label_agreement":null},{"id":"W7010008906","doi":"","title":"Futurpreneur announces 2024 Canadian delegation for the G20 Young Entrepreneurs' Alliance Summit in Brazil","year":2024,"lang":"en","type":"other","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summit; Delegation; Alliance; Government (linguistics)","score_opus":0.06766321522002318,"score_gpt":0.3796711667029313,"score_spread":0.3120079514829081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7010008906","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003422602,0.006384704,0.019505767,0.0021252725,0.0022841378,0.0034089233,0.0007721907,0.0013451971,0.9641396],"genre_scores_gemma":[0.0017262631,0.0009976507,0.011463578,0.0003577953,0.0005569122,0.0007807429,0.000054708158,0.00054159935,0.98352075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982225,0.00003946152,0.00041834768,0.0005776198,0.00024953057,0.000492593],"domain_scores_gemma":[0.998534,0.00046232739,0.00018110116,0.00065601844,0.00006106829,0.000105457664],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029397412,0.0004098461,0.00037865687,0.00028332308,0.00005034034,0.00013883384,0.0005280647,0.00038565273,0.001090044],"category_scores_gemma":[0.00038590241,0.00029467558,0.00012111432,0.00032847727,0.00008178307,0.00010299881,0.000058374557,0.00040518696,0.00018139087],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044592407,0.000012024819,0.00031021718,0.0003262545,0.00004094725,0.000012959448,0.000113617076,0.000003343077,0.000010350561,0.06779941,0.93042594,0.0009404692],"study_design_scores_gemma":[0.00010937671,0.000033023513,0.000016499425,0.00059954735,0.00007707475,0.0000039791616,0.00019407173,0.00031028615,0.0002183463,0.239548,0.75847304,0.00041676243],"about_ca_topic_score_codex":0.04336954,"about_ca_topic_score_gemma":0.8949366,"teacher_disagreement_score":0.8515671,"about_ca_system_score_codex":0.00026382867,"about_ca_system_score_gemma":0.00024796498,"threshold_uncertainty_score":0.9999505},"labels":[],"label_agreement":null},{"id":"W7014274854","doi":"","title":"Optimal dynamic treatment regime structural nested mean models: improving efficiency through diagnostics and re-weighting and application to adaptive individual dosing","year":2013,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":"Department of Epidemiology, Biostatistics and Occupational Health, McGill University; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Estimator; Residual; Regression; Dosing; Sample (material); Sample size determination; Estimation","score_opus":0.05737955984033674,"score_gpt":0.3292449294087006,"score_spread":0.2718653695683638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7014274854","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":[0.9913939,0.00045045046,0.0017603134,0.00001009623,0.00015580624,0.0029689013,0.0005366459,0.0006573826,0.0020665037],"genre_scores_gemma":[0.85789084,0.00029760087,0.14013368,0.000043794484,0.00003020982,0.00064519583,0.00047411447,0.00022787234,0.0002566708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99583113,0.00021985956,0.0010280211,0.0014627121,0.000663075,0.0007952059],"domain_scores_gemma":[0.9964107,0.0010733502,0.0009911783,0.00075968896,0.00045082334,0.00031420562],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045055474,0.0010717865,0.000990586,0.00033968737,0.0011689701,0.00023163659,0.00044134786,0.00075673155,0.000010794622],"category_scores_gemma":[0.0008962944,0.001023993,0.00013228634,0.0004224551,0.00011328929,0.001486968,0.00027282294,0.0009380909,0.00000826718],"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":[0.00030326203,0.0002775455,0.000020320183,0.0008490005,0.00039291076,0.000044084558,0.0017574253,0.001196509,0.039622486,0.49922696,0.0000021216188,0.45630735],"study_design_scores_gemma":[0.0018138469,0.0021119458,0.0003956077,0.0020319896,0.001485587,0.00010970281,0.006619578,0.045819048,0.07964364,0.856193,0.00018123547,0.0035948427],"about_ca_topic_score_codex":0.0005726521,"about_ca_topic_score_gemma":0.0009062778,"teacher_disagreement_score":0.4527125,"about_ca_system_score_codex":0.0010888281,"about_ca_system_score_gemma":0.000055563945,"threshold_uncertainty_score":0.999221},"labels":[],"label_agreement":null},{"id":"W7015539084","doi":"","title":"Towards an accessible methodology in precision medicine: methods for censored data and non-regular inferences","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":"Fonds de recherche du Québec – Nature et technologies; McGill University Health Centre; Canadian Institutes of Health Research; Health Canada; McGill University; UNICEF","keywords":"Feature (linguistics); Bayesian probability; Data collection; Term (time); Estimation","score_opus":0.328821958760208,"score_gpt":0.5156193188424544,"score_spread":0.1867973600822464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015539084","genre_codex":"empirical","genre_gemma":"methods","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":[0.8070879,0.004297789,0.061744906,0.00071113487,0.0062086163,0.021422833,0.008987158,0.004573125,0.08496656],"genre_scores_gemma":[0.07533901,0.000977597,0.91849875,0.0001923624,0.00010333076,0.0006115122,0.0035392737,0.00029087532,0.00044726688],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923548,0.00194362,0.0018987665,0.002293948,0.00066440646,0.0008444451],"domain_scores_gemma":[0.990533,0.0050016255,0.0012629076,0.0021272416,0.0006194872,0.0004557472],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007470488,0.0011048117,0.0023426611,0.00079355953,0.00046818302,0.00010261416,0.0025966342,0.0015407748,0.00014548171],"category_scores_gemma":[0.026542382,0.0010003571,0.00015113653,0.00086639525,0.00020246752,0.0020438854,0.000794703,0.0018043648,0.000004288359],"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":[0.00071179797,0.00015102935,0.000023192084,0.0013758288,0.00014471478,0.000020983152,0.000118208074,0.0000014957974,0.070486456,0.23769517,0.000025223677,0.6892459],"study_design_scores_gemma":[0.000997754,0.00069826096,0.00040942477,0.0010016286,0.00035349297,0.0000122855745,0.00093075645,0.000746953,0.11556066,0.8650516,0.013254446,0.0009827272],"about_ca_topic_score_codex":0.00033071343,"about_ca_topic_score_gemma":0.0019152765,"teacher_disagreement_score":0.8567539,"about_ca_system_score_codex":0.00029718401,"about_ca_system_score_gemma":0.0001521712,"threshold_uncertainty_score":0.99975544},"labels":[],"label_agreement":null},{"id":"W7019432579","doi":"","title":"G-estimation of dynamic treatment regimes in the presence of shared parameters","year":2018,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":"McGill University","keywords":"Outcome (game theory); Focus (optics); Estimation; Personalized medicine; Decision rule; Basis (linear algebra); Sensitivity (control systems)","score_opus":0.07114378011410935,"score_gpt":0.3629481029300055,"score_spread":0.2918043228158962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019432579","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":[0.9843426,0.0000987747,0.000016501806,0.0000090941,0.00017515477,0.0016320482,0.0007062688,0.00015797856,0.012861634],"genre_scores_gemma":[0.9431853,0.00019709377,0.0543926,0.00001527715,0.000005443617,0.00041075697,0.0004998929,0.00010109381,0.001192537],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99657315,0.0004361764,0.0012393867,0.0006213014,0.0007249149,0.00040508897],"domain_scores_gemma":[0.99544585,0.0014483567,0.0014714104,0.0012274857,0.00033854382,0.00006833441],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009035156,0.0005859831,0.0009289578,0.00041749256,0.0001680242,0.000025648496,0.0008592407,0.0005339017,0.000060724222],"category_scores_gemma":[0.0028514725,0.0004624574,0.00027369361,0.0005684175,0.0001543764,0.0005493475,0.00006161215,0.00053744816,0.000014298887],"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":[0.00082293316,0.0018486701,0.000034447778,0.003056392,0.00049282477,0.000053597047,0.0007581213,0.00015954218,0.04195681,0.45542493,0.00002891092,0.49536282],"study_design_scores_gemma":[0.00059718295,0.00091506995,0.00045817113,0.0020263623,0.0002875422,0.000011506795,0.0010210082,0.0006364247,0.24373928,0.7493476,0.0003492479,0.00061061064],"about_ca_topic_score_codex":0.0002895279,"about_ca_topic_score_gemma":0.0013256769,"teacher_disagreement_score":0.4947522,"about_ca_system_score_codex":0.0005802739,"about_ca_system_score_gemma":0.000060706636,"threshold_uncertainty_score":0.99978274},"labels":[],"label_agreement":null},{"id":"W7020777066","doi":"","title":"Méthane dissous dans le système marin du Saint-Laurent","year":2021,"lang":"fr","type":"other","venue":"Sémaphore (Université du Québec à Rimouski)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Limiting; Decantation; Nucleofection","score_opus":0.02082806021085343,"score_gpt":0.2415939127381665,"score_spread":0.22076585252731307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020777066","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013974856,0.0069288607,0.14156896,0.006149486,0.0012256097,0.0022572645,0.00038198548,0.0019105884,0.8256024],"genre_scores_gemma":[0.18116036,0.0024650847,0.023082646,0.00029766484,0.0011729129,0.000091109905,0.00056555594,0.0013188212,0.7898458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99468905,0.0005668487,0.00086842146,0.0016329963,0.0008604542,0.001382213],"domain_scores_gemma":[0.9949305,0.00076222233,0.0010761706,0.0020724626,0.0004899924,0.00066866557],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.00043963987,0.0015678228,0.0019922373,0.0006545293,0.00068683235,0.00015803835,0.001759001,0.0013847772,0.049234398],"category_scores_gemma":[0.00057394424,0.0017993025,0.00090998685,0.00085049233,0.0010985725,0.00029480451,0.0014091533,0.0013869107,0.0010569945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011053709,0.0011488395,0.0035586827,0.0016425673,0.0009969061,0.0020121827,0.008423772,0.000045545963,0.002309859,0.89730525,0.06755753,0.014888303],"study_design_scores_gemma":[0.002024315,0.00055239553,0.0032285578,0.0032658542,0.0012803948,0.00091444113,0.011311941,0.0006693601,0.001968383,0.02480948,0.94665295,0.0033219396],"about_ca_topic_score_codex":0.21515091,"about_ca_topic_score_gemma":0.7477069,"teacher_disagreement_score":0.87909544,"about_ca_system_score_codex":0.008504403,"about_ca_system_score_gemma":0.002782025,"threshold_uncertainty_score":0.9999116},"labels":[],"label_agreement":null},{"id":"W7025253789","doi":"","title":"Towards a Long-term Preservation Infrastructure for Earth Science Data: Paper - iPRES 2012 - Digital Curation Institute, iSchool, Toronto","year":2012,"lang":"en","type":"article","venue":"Phaidra (Universität Wien)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.1450269430265068,"score_gpt":0.39613635193838814,"score_spread":0.2511094089118814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025253789","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":[0.008730059,0.00021334554,0.9842547,0.00016622359,0.0003566916,0.0007411301,0.00017070511,0.00032334993,0.0050437567],"genre_scores_gemma":[0.9375009,0.000045408782,0.060644876,0.000075243195,0.000309007,0.00002130896,0.00027418602,0.000028297087,0.001100751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837095,0.000019779274,0.00021906753,0.00042247688,0.00044843354,0.0005192899],"domain_scores_gemma":[0.99834424,0.00009427542,0.00020457855,0.00086720515,0.0002817733,0.00020794383],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00031504294,0.0002352523,0.00022233828,0.00011163233,0.00037655662,0.00019681541,0.00093718007,0.00011610756,0.00024809033],"category_scores_gemma":[0.00054898195,0.0002307675,0.00005292752,0.00030084554,0.0003040563,0.9416202,0.0006136182,0.00014571729,0.000012758455],"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":[0.00004221818,0.00008650448,0.00007581195,0.00006250435,0.000024632438,0.0000014627587,0.0007634364,0.0000065689806,0.003557356,0.982975,0.0001811983,0.012223298],"study_design_scores_gemma":[0.0006408881,0.00014516158,0.00087674125,0.00008259214,0.00009802821,0.000017346296,0.0004304115,0.00063761487,0.00034505015,0.9725573,0.023678903,0.000489951],"about_ca_topic_score_codex":0.000047381618,"about_ca_topic_score_gemma":0.00031096803,"teacher_disagreement_score":0.94142336,"about_ca_system_score_codex":0.00028421805,"about_ca_system_score_gemma":0.00019718776,"threshold_uncertainty_score":0.9410426},"labels":[],"label_agreement":null},{"id":"W7027096149","doi":"","title":"Causal quantile treatment effects at high and extreme quantile levels","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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":"Institut de Valorisation des Données; Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Quantile; Quantile regression; Term (time); Context (archaeology); Causality (physics)","score_opus":0.13020250003138095,"score_gpt":0.3598972338347665,"score_spread":0.22969473380338556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027096149","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":[0.9834295,0.00030191298,0.0000045040824,0.0000112906755,0.0012963918,0.0021001142,0.0018219353,0.0024004502,0.0086338995],"genre_scores_gemma":[0.9436381,0.000799034,0.00875014,0.00006477395,0.00008983694,0.0011167298,0.0013485461,0.0007716892,0.043421187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943392,0.00045353593,0.0012568566,0.001754542,0.0009888068,0.0012070285],"domain_scores_gemma":[0.994306,0.002512512,0.00095345924,0.0013940851,0.0003564443,0.0004774911],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0007149125,0.0015551047,0.001803405,0.0006020465,0.0011618002,0.00011726976,0.00058298,0.0013341546,0.0003054936],"category_scores_gemma":[0.0019895476,0.0014991991,0.00041228547,0.0005914287,0.000121245095,0.0006483269,0.00030733697,0.0011144107,0.0005939774],"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":[0.00045447564,0.0006932821,0.00006995852,0.002734201,0.000845553,0.0008134116,0.00008171618,0.0000047708145,0.20404406,0.6719852,0.00012132328,0.11815205],"study_design_scores_gemma":[0.0014781975,0.0010755397,0.0017596134,0.0015189651,0.00072565797,0.000058481008,0.00022181706,0.00002257981,0.49052593,0.49275112,0.007824692,0.0020373925],"about_ca_topic_score_codex":0.0006956731,"about_ca_topic_score_gemma":0.0061375657,"teacher_disagreement_score":0.2864819,"about_ca_system_score_codex":0.0018777954,"about_ca_system_score_gemma":0.00007195769,"threshold_uncertainty_score":0.99996233},"labels":[],"label_agreement":null},{"id":"W7033279466","doi":"","title":"Professionelle Simulation: Begriff - Ausdeutungen - Dimensionen - Handlungsfelder","year":2020,"lang":"de","type":"book-chapter","venue":"OPUS (Augsburg University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Demotion","score_opus":0.13338364586899812,"score_gpt":0.3298365050929562,"score_spread":0.19645285922395808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033279466","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004982912,0.0081873825,0.35172242,0.012087173,0.00860857,0.021186652,0.0026150427,0.011655275,0.5789546],"genre_scores_gemma":[0.10308375,0.002131216,0.023232939,0.000502479,0.0013664868,0.0000056117865,0.00073079875,0.00058245595,0.8683643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99589133,0.00017230386,0.00085133035,0.0014315008,0.0008959137,0.00075763674],"domain_scores_gemma":[0.99530566,0.0009563122,0.001066572,0.0013978541,0.0006139946,0.00065959734],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022060862,0.0012628238,0.0015129073,0.00072776305,0.00083927874,0.00009139535,0.001048466,0.0015597162,0.0033080424],"category_scores_gemma":[0.00022795671,0.0013955088,0.0007370047,0.00037415663,0.00045707825,0.0006623387,0.0013130307,0.0017524064,0.001784991],"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":[0.00053575175,0.00018117679,0.00004988916,0.0006300592,0.0013894903,0.0018257487,0.0011883219,0.001146029,0.00808541,0.97463477,0.007883335,0.002450028],"study_design_scores_gemma":[0.0014939462,0.0005381238,0.000007261618,0.0021569673,0.0025283236,0.000012794377,0.00057311804,0.0030036676,0.008755896,0.21556714,0.76300377,0.0023590222],"about_ca_topic_score_codex":0.000030654413,"about_ca_topic_score_gemma":8.060417e-7,"teacher_disagreement_score":0.7590676,"about_ca_system_score_codex":0.0006799662,"about_ca_system_score_gemma":0.00036735594,"threshold_uncertainty_score":0.9997365},"labels":[],"label_agreement":null},{"id":"W7037729294","doi":"","title":"The Effect of Taking a Paternity Leave on Men’s Career Outcomes","year":2020,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Parental leave; Perception; Agency (philosophy); Expectancy theory; Test (biology); Sample (material)","score_opus":0.06627739889284377,"score_gpt":0.357201921387949,"score_spread":0.2909245224951052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037729294","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011678014,0.000002476392,0.0033794472,0.00014522814,0.0002199411,0.002232952,0.0000638208,0.0008519584,0.9919364],"genre_scores_gemma":[0.041275702,0.00012081939,0.0035303258,0.000076930424,0.00012942633,0.00084757566,0.00001622145,0.0006980412,0.95330495],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99506867,0.0011396146,0.0007999909,0.0017014939,0.0007755442,0.0005146963],"domain_scores_gemma":[0.9895015,0.0038830256,0.0014624343,0.0049065086,0.00007765048,0.00016890535],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003336214,0.00074224634,0.0012600714,0.00017311273,0.00012831436,0.000077540484,0.0018731301,0.0005685021,0.1824448],"category_scores_gemma":[0.013309608,0.00053936243,0.00045015907,0.0001534269,0.00029672871,0.00006758909,0.0017161486,0.0010962621,0.16270643],"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":[0.0004926315,0.00029395823,0.034339055,0.002220208,0.0018970334,0.00009033806,0.0017913668,0.000027972037,0.0018788403,0.029035028,0.8830103,0.044923246],"study_design_scores_gemma":[0.0022703188,0.00006199126,0.00360671,0.003425396,0.0009991226,0.000027873259,0.00026302124,0.00016700824,0.17164409,0.1394073,0.6754746,0.002652536],"about_ca_topic_score_codex":0.0003603831,"about_ca_topic_score_gemma":0.0001671406,"teacher_disagreement_score":0.20753571,"about_ca_system_score_codex":0.000283889,"about_ca_system_score_gemma":0.00007272978,"threshold_uncertainty_score":0.9997058},"labels":[],"label_agreement":null},{"id":"W7037901270","doi":"","title":"Feet for FEAT, Ricky Atkinson Robyn Maynard","year":2017,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Thursday; Prison; AKA; Memoir; Heron; Politics","score_opus":0.03714818296415547,"score_gpt":0.29226477486677177,"score_spread":0.2551165919026163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037901270","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032877228,0.00018494761,0.00017706215,0.0001352641,0.00027845625,0.0013799684,0.00043005927,0.00075361767,0.9966573],"genre_scores_gemma":[0.00005944669,0.0003072214,0.07054072,0.00017042564,0.0002523091,0.00013617484,0.00018324298,0.00028603556,0.9280644],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803954,0.000051487594,0.000709376,0.00030119403,0.00043933635,0.00045904593],"domain_scores_gemma":[0.99665517,0.0003230088,0.0016069721,0.0010164491,0.00026779567,0.00013061153],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00036532208,0.00054608245,0.0008163766,0.00011955378,0.0001382551,0.00008585684,0.0007451956,0.00072939624,0.11439958],"category_scores_gemma":[0.0009092624,0.00053349236,0.00029120737,0.0000049235696,0.00019445247,4.930448e-7,0.00015690095,0.00032569625,0.0025079174],"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":[0.00006864127,0.000048529215,5.254358e-7,0.0012291308,0.00008107736,0.000011465603,0.000059358714,0.000008670015,4.553151e-7,0.0016967786,0.992946,0.0038493264],"study_design_scores_gemma":[0.00052745064,0.00023397052,6.401468e-7,0.0008106206,0.00010853667,0.000052407453,0.00003091887,0.000017509567,0.00007083944,0.0032145474,0.99437946,0.00055307575],"about_ca_topic_score_codex":0.0015259711,"about_ca_topic_score_gemma":0.0009147781,"teacher_disagreement_score":0.111891665,"about_ca_system_score_codex":0.0001060402,"about_ca_system_score_gemma":0.000046290515,"threshold_uncertainty_score":0.99971163},"labels":[],"label_agreement":null},{"id":"W7042528796","doi":"","title":"Pharmacological interventions in type 2 diabetes: observational studies and bias related issues","year":2008,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Observational study; Confounding; Type 2 diabetes; Cohort study; Metformin; Myocardial infarction; Residual risk; Cohort; Psychological intervention","score_opus":0.37878548603621753,"score_gpt":0.4573771715734495,"score_spread":0.07859168553723195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042528796","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":[0.9857352,0.005989883,2.3751745e-7,0.000047054415,0.00064155954,0.0009158003,0.0002093327,0.00063439936,0.005826541],"genre_scores_gemma":[0.9527182,0.016181303,0.015693784,0.00020719993,0.00004723588,0.00059014704,0.0009224019,0.00023153293,0.013408178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960843,0.00049258216,0.0014660422,0.00085435185,0.0005407297,0.00056201237],"domain_scores_gemma":[0.9965418,0.0014447778,0.00076108665,0.00037889025,0.0007194253,0.00015401478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010178701,0.00070472516,0.0011488169,0.0005030906,0.00051438285,0.00003707158,0.00041653748,0.0007902916,0.00024462532],"category_scores_gemma":[0.007230423,0.00067967793,0.0002814749,0.000780471,0.00017505795,0.00073161785,0.00020505184,0.0017187259,0.0000586358],"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":[0.0003624056,0.0016027397,0.0013504174,0.004837157,0.0022527052,0.00039580872,0.0002673244,0.000025292728,0.038342316,0.88977206,0.0006153736,0.060176402],"study_design_scores_gemma":[0.0007559744,0.000420916,0.0032440587,0.003460748,0.00039501584,0.000017226532,0.00063140184,0.000021829632,0.028355574,0.95513093,0.0064556478,0.0011106933],"about_ca_topic_score_codex":0.000024581377,"about_ca_topic_score_gemma":0.00048662402,"teacher_disagreement_score":0.065358855,"about_ca_system_score_codex":0.0005918537,"about_ca_system_score_gemma":0.000039815564,"threshold_uncertainty_score":0.9995654},"labels":[],"label_agreement":null},{"id":"W7071692116","doi":"","title":"Three Essays in Applied Micro-Econometrics","year":2022,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Medical prescription; Logistic regression; Opioid; Nonparametric statistics; Prescription drug; Pharmacoepidemiology; Consumption (sociology); Regression analysis","score_opus":0.06619181418996428,"score_gpt":0.2914325872298593,"score_spread":0.22524077303989504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071692116","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049173026,0.00009811379,0.006250233,0.000014470635,0.00023777962,0.00075185264,0.00005693155,0.00035569328,0.9873176],"genre_scores_gemma":[0.0148009425,0.00017797448,0.05260365,0.00008914202,0.00009357857,0.000045483896,0.0008184049,0.00028265972,0.93108815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981714,0.000052378677,0.00038972826,0.0006571207,0.00028814815,0.0004412431],"domain_scores_gemma":[0.99863,0.0002869535,0.00042703823,0.0005079749,0.00005611504,0.000091951915],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018966691,0.00045599625,0.0006344029,0.0010243919,0.00013064842,0.000044705186,0.000841658,0.00040319213,0.13814695],"category_scores_gemma":[0.00006190474,0.00058441574,0.00015130758,0.0016525032,0.00004371674,0.00017571331,0.00024945158,0.0009312155,0.000050361068],"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":[0.00047376432,0.00039602848,0.0012517204,0.00083388656,0.00016477486,0.00036712704,0.0015338009,0.000042984826,0.000894835,0.47726983,0.003538795,0.51323247],"study_design_scores_gemma":[0.0020156647,0.00021060002,0.0006837649,0.0002664578,0.0002785686,0.000007208067,0.016486356,0.000079138896,0.002999779,0.45152152,0.5233345,0.0021164708],"about_ca_topic_score_codex":0.000105959916,"about_ca_topic_score_gemma":0.003915504,"teacher_disagreement_score":0.51979566,"about_ca_system_score_codex":0.00085310254,"about_ca_system_score_gemma":0.00013505408,"threshold_uncertainty_score":0.99966073},"labels":[],"label_agreement":null},{"id":"W7071900186","doi":"","title":"Value search estimators of individualized treatment regimes using a new class of weights","year":2016,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","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; McGill University Health Centre","funders":"","keywords":"Class (philosophy); Estimator; Value (mathematics); Variation (astronomy); Feature (linguistics)","score_opus":0.11770364856513031,"score_gpt":0.3908484226601983,"score_spread":0.273144774095068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071900186","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":[0.959936,0.00024267532,0.000062226594,0.000008224908,0.0003496883,0.0016027285,0.0012623917,0.0004311137,0.036104906],"genre_scores_gemma":[0.7278552,0.0005694383,0.25657347,0.000024176983,0.000076436205,0.00016262026,0.00043105072,0.00058686547,0.013720735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9946497,0.00053082546,0.0017816505,0.0009742841,0.001289379,0.0007741583],"domain_scores_gemma":[0.99431777,0.0013323653,0.0018992865,0.0013892817,0.00069139054,0.0003699184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083230395,0.0010375,0.0019668257,0.00088150165,0.0003628716,0.000030381369,0.0008329466,0.0011085442,0.00024227003],"category_scores_gemma":[0.001377495,0.00085127284,0.0006173113,0.0006081077,0.00016798913,0.000640588,0.00016154283,0.0007304631,0.000025852147],"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":[0.0003764018,0.00048452045,0.00005115721,0.0011016866,0.0007402851,0.00003287701,0.00008466152,0.000009457983,0.114153534,0.81437826,0.00000687522,0.06858026],"study_design_scores_gemma":[0.0009507562,0.0003481797,0.000032457676,0.0020589647,0.00042935656,0.000013112466,0.00011718578,0.000017010403,0.5584477,0.43568072,0.0013444739,0.00056007574],"about_ca_topic_score_codex":0.0007489849,"about_ca_topic_score_gemma":0.0001722141,"teacher_disagreement_score":0.44429415,"about_ca_system_score_codex":0.00126033,"about_ca_system_score_gemma":0.000412138,"threshold_uncertainty_score":0.9993938},"labels":[],"label_agreement":null},{"id":"W70905468","doi":"10.1007/978-1-4614-6852-3_18","title":"Survival Analysis in Social Neuroscience and Public Health: A Research Exemplar from the Field of Cognitive Epidemiology","year":2013,"lang":"en","type":"book-chapter","venue":"","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":"University of Waterloo","funders":"","keywords":"Biostatistics; Confounding; Proportional hazards model; Cognition; Public health; Epidemiology; Psychology; Survival analysis; Event (particle physics); Association (psychology); Variable (mathematics); Field (mathematics); Cognitive psychology; Medicine; Data science; Clinical psychology; Psychiatry; Computer science; Psychotherapist; Pathology; Mathematics","score_opus":0.6960210118581102,"score_gpt":0.5617264515334086,"score_spread":0.13429456032470155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W70905468","genre_codex":"other","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":[0.0124948155,0.0014833972,0.3057232,0.060569007,0.0002434023,0.004682211,0.00076074497,0.0003957645,0.61364746],"genre_scores_gemma":[0.8220263,0.0055625495,0.037191994,0.015855204,0.0006953108,0.0004954508,0.00024601966,0.00023898995,0.117688194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99696344,0.00087118475,0.0007704459,0.00051497016,0.0003869252,0.00049304013],"domain_scores_gemma":[0.9563369,0.042431757,0.00044231792,0.0003441211,0.00034971684,0.000095173724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004585862,0.00021748617,0.0010519515,0.00044407838,0.00015954526,0.000023355387,0.00041472563,0.0003663965,0.0006534776],"category_scores_gemma":[0.017381158,0.00015123271,0.00012768127,0.0002924896,0.0008610336,0.000111213034,0.00041073086,0.0010571112,0.000005942113],"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":[0.000009770107,0.000027396534,0.001548767,0.000022345952,0.00007388709,0.000002476817,0.0004970343,5.2262887e-8,0.000008433867,0.9869605,0.0046027014,0.006246671],"study_design_scores_gemma":[0.00008348793,0.00015838117,0.0023174493,0.00008060974,0.00004333126,5.0322603e-7,0.00033091195,0.000069247544,0.000013225368,0.9953146,0.0014484149,0.00013982112],"about_ca_topic_score_codex":0.0024648067,"about_ca_topic_score_gemma":0.0036906314,"teacher_disagreement_score":0.80953145,"about_ca_system_score_codex":0.000061627776,"about_ca_system_score_gemma":0.00016988153,"threshold_uncertainty_score":0.99089587},"labels":[],"label_agreement":null},{"id":"W7092316930","doi":"","title":"Marginal Causal Effect Estimation with Continuous Instrumental Variables","year":2025,"lang":"","type":"article","venue":"ArXiv.org","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":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Covariate; Instrumental variable; Semiparametric regression; Categorical variable; Parametric statistics; Semiparametric model; Nonparametric statistics; Conditional probability distribution; Observational study; Tangent","score_opus":0.03893167561380536,"score_gpt":0.3455048819014478,"score_spread":0.30657320628764245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092316930","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":[0.7807207,0.00014590543,0.20787057,0.0002687241,0.0003803678,0.0014607576,0.000038397564,0.0005781068,0.008536461],"genre_scores_gemma":[0.93798625,0.000059668848,0.059000704,0.00020521812,0.00009030485,0.000245746,0.00005241771,0.00008404795,0.0022756138],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967114,0.00030101076,0.0008761802,0.00081035023,0.00046251898,0.00083859055],"domain_scores_gemma":[0.9970828,0.0010840718,0.0005061345,0.0009361274,0.00022498915,0.00016586835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007266603,0.00078133214,0.0010147645,0.00030057764,0.0003721723,0.00016124951,0.0004806946,0.00040202445,0.00044052312],"category_scores_gemma":[0.00074238237,0.0006878304,0.00013635968,0.0007449264,0.00047294996,0.0007479493,0.0003089364,0.0007838246,0.00014278313],"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":[0.0014013039,0.0010365742,0.8149026,0.0024854483,0.0010111805,0.0002550086,0.00067439186,0.00017507565,0.013508145,0.11283303,0.002433563,0.049283657],"study_design_scores_gemma":[0.013261105,0.011753619,0.12741047,0.014240773,0.004198773,0.00042778772,0.001316532,0.022529788,0.6213813,0.17400387,0.004783647,0.004692334],"about_ca_topic_score_codex":0.00010989328,"about_ca_topic_score_gemma":0.00004011872,"teacher_disagreement_score":0.68749213,"about_ca_system_score_codex":0.0005172744,"about_ca_system_score_gemma":0.00032943397,"threshold_uncertainty_score":0.99955726},"labels":[],"label_agreement":null},{"id":"W7095972670","doi":"","title":"DOI:10.1093/aje/kwn299 Practice of Epidemiology Instrumental Variable Analysis for Estimation of Treatment Effects With Dichotomous","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Instrumental variable; Estimation; Probit; Logistic regression; Confounding; Relative risk; Probit model; Ordinary least squares","score_opus":0.11487245325733503,"score_gpt":0.4224846246551371,"score_spread":0.30761217139780206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095972670","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":[0.10809755,0.000029131063,0.8849899,0.000044457207,0.000011746308,0.0009854374,0.000022242417,0.0001248765,0.0056946636],"genre_scores_gemma":[0.43020156,0.000025610172,0.5690956,0.000026322386,0.0000057547772,0.0001815881,0.000033042103,0.000012321665,0.00041820487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861115,0.00017460616,0.0005993638,0.00025663394,0.00012811348,0.00023015401],"domain_scores_gemma":[0.989999,0.008602699,0.0007122264,0.000412687,0.00021558834,0.00005779701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005315532,0.00019870115,0.0008232684,0.00019219087,0.00005411863,0.0000022420074,0.00010440411,0.00011184307,0.00014600847],"category_scores_gemma":[0.0037634315,0.00013848829,0.00012617043,0.00043868562,0.00015455177,0.0002663032,0.000026250264,0.00005934183,0.0000023613081],"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":[0.0031906108,0.00557931,0.02465213,0.0019434042,0.010602429,0.000031415726,0.002292325,0.024898231,0.011606017,0.88990086,0.0020052544,0.023298029],"study_design_scores_gemma":[0.0053139147,0.018631794,0.0010343065,0.00025764157,0.008141146,0.00018305393,0.00040359938,0.0822876,0.42254815,0.4586043,0.0016953299,0.0008991748],"about_ca_topic_score_codex":0.00033800132,"about_ca_topic_score_gemma":0.000026772947,"teacher_disagreement_score":0.43129653,"about_ca_system_score_codex":0.00019906915,"about_ca_system_score_gemma":0.00008834865,"threshold_uncertainty_score":0.56473887},"labels":[],"label_agreement":null},{"id":"W7096152232","doi":"","title":"Determinants of General Practitioner Utilization: Controlling for Unobserved Heterogeneity∗","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Nonparametric statistics; Socioeconomic status; Estimator; Parametric statistics; Kernel density estimation; Control (management); Longitudinal data; Semiparametric regression","score_opus":0.32197166175481706,"score_gpt":0.47722627791864947,"score_spread":0.1552546161638324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096152232","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":[0.29560032,0.000018442339,0.7027818,0.000013843103,0.000043916312,0.00038322335,0.000007919832,0.00013093278,0.0010195742],"genre_scores_gemma":[0.6357043,0.000007630127,0.36376527,0.0000701989,0.000049780425,0.000031005024,0.0000054563347,0.000017654995,0.00034871828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903697,0.00001872792,0.0004601949,0.00014816009,0.00013017427,0.00020580184],"domain_scores_gemma":[0.99864656,0.000559224,0.00025419952,0.0002178799,0.00027738002,0.000044781522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056506036,0.00011040468,0.00024333049,0.0000618966,0.000049505943,0.000009229899,0.000097281736,0.00008629999,0.00004923582],"category_scores_gemma":[0.0005660275,0.00009572545,0.00007844625,0.00009038537,0.000037789574,0.00018597316,0.000023082544,0.000044298573,0.0000013767797],"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":[0.00044842524,0.0005393111,0.01957615,0.0004575424,0.000089919486,0.000011474615,0.00020476666,0.00007701153,0.16289093,0.7937812,0.001195165,0.020728096],"study_design_scores_gemma":[0.00051399437,0.00012445907,0.00055462174,0.00003209207,0.000026926047,0.000005829463,0.00003904259,0.0029028633,0.83701104,0.1580257,0.000627066,0.00013637567],"about_ca_topic_score_codex":0.0000080286445,"about_ca_topic_score_gemma":0.00015109748,"teacher_disagreement_score":0.6741201,"about_ca_system_score_codex":0.000030181769,"about_ca_system_score_gemma":0.000020357553,"threshold_uncertainty_score":0.39035708},"labels":[],"label_agreement":null},{"id":"W7096490722","doi":"","title":"Explaining and Forecasting Results of the Self-Sufficiency Project,” research report, Social Research Demonstration Corporation, http://www.srdc.org","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Counterfactual conditional; Social research; Welfare; Corporation; Market research; Value (mathematics); Control (management); Variation (astronomy); Applied research; Estimation","score_opus":0.7019742623877581,"score_gpt":0.5339549103549789,"score_spread":0.16801935203277918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096490722","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":[0.820798,0.000026972632,0.01114999,0.0010056471,0.00009054294,0.0019211132,0.000009715467,0.00041236816,0.1645857],"genre_scores_gemma":[0.9352051,0.000005731385,0.06321359,0.0000067257647,0.00012487228,0.00009531211,0.000007536658,0.000023578543,0.0013175467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99586236,0.00081456016,0.0009131699,0.00041098087,0.0015335489,0.00046539897],"domain_scores_gemma":[0.99446,0.0017777835,0.0004886759,0.00048483064,0.0027136563,0.00007507124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016193971,0.0001409473,0.00024124736,0.00026710427,0.00064807327,0.00008433418,0.00030545524,0.0001722288,0.0000028231254],"category_scores_gemma":[0.019854458,0.00009932014,0.00003873012,0.0012211549,0.00052496244,0.00041405938,0.000369138,0.00070870086,0.0000025161105],"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":[0.00013861,0.00023052949,0.0037217427,0.000119470875,0.00001790094,0.000032257507,0.012033076,0.0000028662287,0.006417957,0.96005404,0.014678081,0.0025534667],"study_design_scores_gemma":[0.0014499384,0.0011022611,0.001693235,0.00033834277,0.000028154427,0.00028772323,0.03607154,0.012724214,0.040113457,0.90246004,0.0032308453,0.0005002714],"about_ca_topic_score_codex":0.0002430809,"about_ca_topic_score_gemma":0.00029264772,"teacher_disagreement_score":0.16326813,"about_ca_system_score_codex":0.0001951595,"about_ca_system_score_gemma":0.00095099985,"threshold_uncertainty_score":0.9884017},"labels":[],"label_agreement":null},{"id":"W7096775292","doi":"","title":"Assignment and Outcome Measurement in Field Experiments Strategies for Dealing with the Problem of Non-overlapping Units of Published by:","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Field (mathematics); Outcome (game theory); Unit (ring theory); Interpretation (philosophy); Range (aeronautics)","score_opus":0.19840938938600078,"score_gpt":0.39266774091391776,"score_spread":0.19425835152791698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096775292","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":[0.09670064,0.000029709397,0.8987408,0.0005393968,0.0000055680243,0.00086186564,0.000004052375,0.000032680426,0.0030852517],"genre_scores_gemma":[0.92835677,0.000005785249,0.071399055,0.00003155515,0.000002512717,0.0001287285,2.697281e-7,0.000009537841,0.000065778164],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991725,0.000017932907,0.0003197929,0.00012446358,0.00023460295,0.0001306954],"domain_scores_gemma":[0.9990765,0.00034716667,0.00019413784,0.00017155896,0.00019076306,0.000019869294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000547471,0.00010080234,0.00020972584,0.000033460477,0.000018927145,0.000017152262,0.00011067808,0.000039161634,0.000019116895],"category_scores_gemma":[0.00010687443,0.000047675665,0.000013616004,0.000056764024,0.00004323917,0.00023751361,0.000041098116,0.00004017922,4.5188383e-8],"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":[0.00012122238,0.0001403917,0.005964377,0.00041040537,0.000088177745,3.9176274e-7,0.0015915302,0.0000058280702,0.6066771,0.37666196,0.0011299893,0.0072085853],"study_design_scores_gemma":[0.0009063395,0.00049412006,0.00013976598,0.00051922636,0.000017106144,4.470838e-7,0.0029084953,0.00003910507,0.867673,0.12703805,0.00012087635,0.0001434916],"about_ca_topic_score_codex":0.00007361849,"about_ca_topic_score_gemma":0.00010703403,"teacher_disagreement_score":0.83165616,"about_ca_system_score_codex":0.000044477547,"about_ca_system_score_gemma":0.00004271392,"threshold_uncertainty_score":0.19441572},"labels":[],"label_agreement":null},{"id":"W7097889624","doi":"","title":"Practice of Epidemiology Immeasurable Time Bias in Observational Studies of Drug Effects on Mortality","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Observational study; Epidemiology; Confidence interval; Cohort study; Medical prescription; Rate ratio; Drug; Cohort; Incidence (geometry)","score_opus":0.61656767343931,"score_gpt":0.5529522668860143,"score_spread":0.06361540655329567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097889624","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":[0.9631704,0.00022582899,0.017266765,0.0005439238,0.000050138482,0.0005105897,0.000003822891,0.000108000095,0.018120501],"genre_scores_gemma":[0.7791325,0.000058928614,0.21985963,0.00043825663,0.000018685294,0.000020526775,0.0000037347618,0.000012759215,0.00045497168],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813986,0.00041785874,0.00084831467,0.00017551161,0.00020737843,0.00021110782],"domain_scores_gemma":[0.9532685,0.045525838,0.00054347573,0.00028661915,0.0003483568,0.000027165983],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008620761,0.00012209053,0.00058966957,0.000099441684,0.00001498346,7.4582783e-7,0.00011140292,0.00007386069,0.000026320702],"category_scores_gemma":[0.06693252,0.00009601779,0.00005285818,0.0002116586,0.00011855795,0.00017620242,0.00004964948,0.00015307603,0.0000056553736],"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":[0.00013615844,0.00048262562,0.053851545,0.00054134143,0.00014827735,0.000009345792,0.00049590383,0.00005437847,0.010736785,0.9292777,0.0028426442,0.0014232856],"study_design_scores_gemma":[0.00024243366,0.000195946,0.02580223,0.00024981285,0.000033053882,0.0000020269454,0.00026405102,0.00007485543,0.21582218,0.7570229,0.00016921427,0.00012129996],"about_ca_topic_score_codex":0.00010543663,"about_ca_topic_score_gemma":0.000073582974,"teacher_disagreement_score":0.2050854,"about_ca_system_score_codex":0.00008526679,"about_ca_system_score_gemma":0.000029958364,"threshold_uncertainty_score":0.9409271},"labels":[],"label_agreement":null},{"id":"W7099779233","doi":"","title":"6. Performing Organization Code","year":2001,"lang":"en","type":"article","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Crash; Visibility; Service (business); Highway system; Population; Unit (ring theory); Highway maintenance","score_opus":0.16120023130824954,"score_gpt":0.4118109641177616,"score_spread":0.25061073280951207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099779233","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":[0.17528036,0.0000030513806,0.7650651,0.0001497227,0.000021617465,0.00009140368,3.9708942e-7,0.0008821038,0.058506288],"genre_scores_gemma":[0.82816535,0.000022998234,0.16742924,0.000118847296,0.000032313135,0.00000392204,0.0000026677185,0.000019428011,0.0042052357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99962664,0.000006931353,0.000106877305,0.00007961184,0.000077586454,0.000102338025],"domain_scores_gemma":[0.99964255,0.00006952268,0.00003185729,0.00014440919,0.00008712545,0.000024558412],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007790589,0.00005665859,0.000067105786,0.000029829976,0.00004616708,0.000011916925,0.000070097994,0.00003613083,0.0013225251],"category_scores_gemma":[0.00036637753,0.0000476497,0.0000091814445,0.00017925906,0.00001278209,0.00015667654,0.000027671564,0.000050038157,0.00006684751],"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":[0.0000025575916,0.000051598257,0.0109344935,0.000015357797,0.0000060434763,0.00000895994,0.0002457197,0.0000031082625,0.010326184,0.96379596,0.0049452786,0.009664766],"study_design_scores_gemma":[0.000121759134,0.00004237573,0.00036661592,0.000023181803,0.000010461288,0.00007075861,0.0002079601,0.0005139719,0.12447173,0.8659867,0.007979317,0.00020518948],"about_ca_topic_score_codex":0.0000031231061,"about_ca_topic_score_gemma":0.000012127692,"teacher_disagreement_score":0.652885,"about_ca_system_score_codex":0.000032344407,"about_ca_system_score_gemma":0.000009374809,"threshold_uncertainty_score":0.9995904},"labels":[],"label_agreement":null},{"id":"W7103204351","doi":"","title":"Causal Inference with Groupwise Matching","year":2025,"lang":"","type":"article","venue":"ArXiv.org","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":"BC Innovation Council; University of British Columbia","funders":"","keywords":"Matching (statistics); Causal inference; Inference; Extrapolation; Regret; Synthetic data; Parametric statistics; Fiducial inference","score_opus":0.11097318758821531,"score_gpt":0.3973181470675166,"score_spread":0.2863449594793013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103204351","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":[0.6716743,0.0003225161,0.31269765,0.0006685224,0.00031928386,0.00081917335,0.000018367557,0.00078492734,0.012695267],"genre_scores_gemma":[0.96186733,0.00034559125,0.03130784,0.00077844155,0.00013463853,0.00017433909,0.000012284403,0.000113369526,0.0052661514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99595326,0.0002094466,0.0011106203,0.001044314,0.0005285795,0.0011537833],"domain_scores_gemma":[0.99563664,0.0014293778,0.00054117735,0.0016955032,0.00043643848,0.00026085047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006076467,0.00088714866,0.0010172747,0.00036949213,0.0004474494,0.00018069,0.0009220313,0.00046293487,0.00052334816],"category_scores_gemma":[0.00095530617,0.00079866976,0.0001655624,0.0011226186,0.0005348771,0.000930453,0.00066651806,0.0013676954,0.00035152864],"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":[0.00034188136,0.0010213733,0.4586804,0.0017338104,0.000598779,0.00032359728,0.0035436244,0.000119659344,0.013671119,0.5096609,0.0014594065,0.008845472],"study_design_scores_gemma":[0.002511057,0.0013284727,0.08851772,0.008094066,0.0010477237,0.00005900332,0.002790298,0.0006669793,0.06603798,0.8209288,0.0050467537,0.0029711553],"about_ca_topic_score_codex":0.00020791266,"about_ca_topic_score_gemma":0.00026961512,"teacher_disagreement_score":0.37016267,"about_ca_system_score_codex":0.00039061304,"about_ca_system_score_gemma":0.00054764573,"threshold_uncertainty_score":0.9994464},"labels":[],"label_agreement":null},{"id":"W7103389697","doi":"","title":"Identifiable Causal Inference with Noisy Treatment and No Side Information","year":2024,"lang":"en","type":"article","venue":"Aaltodoc (Aalto University)","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":"Artificial Intelligence in Medicine (Canada)","funders":"Horizon 2020 Framework Programme; Finnish Center for Artificial Intelligence","keywords":"Inference; Pattern recognition (psychology); Identification (biology); Noise (video); Complete information; Noisy data; Causality (physics); Interpretation (philosophy)","score_opus":0.05382096482297451,"score_gpt":0.32067245357116436,"score_spread":0.26685148874818987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103389697","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":[0.36281773,0.00020834802,0.28670484,0.0004935701,0.00042009322,0.0016783668,0.00013395073,0.0035971648,0.34394595],"genre_scores_gemma":[0.9469926,0.00050658564,0.031287424,0.00007886218,0.00006532405,0.00000977746,0.00004261615,0.000039509734,0.020977339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991402,0.00003664828,0.00016773508,0.00023815746,0.00015595963,0.00026127987],"domain_scores_gemma":[0.99907184,0.00032405506,0.000074487616,0.0002733869,0.000141525,0.00011471734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009713344,0.00021450633,0.0002112028,0.00034937143,0.00012767446,0.00014267063,0.00013824314,0.0000884282,0.00008307547],"category_scores_gemma":[0.00008508419,0.00018381991,0.000037440568,0.00041957115,0.00010919112,0.0018823213,0.0000911151,0.00014567062,0.00017726002],"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":[0.00013395715,0.00009352005,0.00061336416,0.0004345042,0.00018443342,0.00022639408,0.0018012325,0.000037269478,0.0014258098,0.9762994,0.0036502057,0.015099884],"study_design_scores_gemma":[0.001564409,0.0020437967,0.00037094438,0.00097612414,0.00046385874,0.00012614935,0.0016949312,0.0023622166,0.014395764,0.11472407,0.86000043,0.001277293],"about_ca_topic_score_codex":0.00025886818,"about_ca_topic_score_gemma":0.00020776915,"teacher_disagreement_score":0.86157537,"about_ca_system_score_codex":0.00031165665,"about_ca_system_score_gemma":0.00015090735,"threshold_uncertainty_score":0.7495959},"labels":[],"label_agreement":null},{"id":"W7103418229","doi":"","title":"Can Contemporary Large Language Models Provide the Domain Knowledge Needed for Causal Inference? Evaluating Automated Causal Graph Discovery Through an ASCVD Case Study","year":2025,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Institute of Population and Public Health","funders":"","keywords":"Causal inference; Directed acyclic graph; Inference; Consistency (knowledge bases); Population; Public health; Baseline (sea); Population health; Epidemiology","score_opus":0.5429744453255869,"score_gpt":0.6576209819113161,"score_spread":0.11464653658572921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103418229","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":[0.9190275,0.002945814,0.06841593,0.00018458562,0.00035006052,0.0058530904,0.00038841713,0.00068212044,0.002152504],"genre_scores_gemma":[0.9909105,0.00016321747,0.0068055736,0.00027612873,0.000116757954,0.0012367882,0.000049885002,0.00012653571,0.00031463115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994163,0.0015759675,0.0018555678,0.00084116025,0.00077083067,0.0007935002],"domain_scores_gemma":[0.992674,0.0033910354,0.0014543402,0.0014009533,0.0008686854,0.00021101747],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0051802723,0.00073801895,0.0014766845,0.0007331202,0.00093177706,0.0018164475,0.0028193202,0.00023374538,0.00019455273],"category_scores_gemma":[0.0021039986,0.00055179157,0.0002834586,0.0015393676,0.00025979528,0.006803197,0.0015494108,0.00081609515,0.0000011055528],"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":[0.0042429017,0.02324823,0.15638298,0.004319541,0.00770911,0.005603912,0.19003804,0.0025910262,0.18482877,0.25877523,0.14686471,0.015395555],"study_design_scores_gemma":[0.0035107257,0.00029158616,0.0022899902,0.0013352723,0.0005702736,0.0001368668,0.05052046,0.010657045,0.01468959,0.91457707,0.00019150894,0.001229586],"about_ca_topic_score_codex":0.0076153725,"about_ca_topic_score_gemma":0.0062681222,"teacher_disagreement_score":0.6558019,"about_ca_system_score_codex":0.00029835093,"about_ca_system_score_gemma":0.0011297337,"threshold_uncertainty_score":0.99969333},"labels":[],"label_agreement":null},{"id":"W7108076363","doi":"10.2196/76961","title":"Methodological Development and Assessing Prescribing Determinants Through Cumulative Drug Exposure in Hospitalized Patients: Proof-of-Concept Retrospective Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"MEDLINE; Drug; Risk assessment; Medication adherence","score_opus":0.17916804686598872,"score_gpt":0.46887480677739346,"score_spread":0.2897067599114047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108076363","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":[0.9083625,0.000030628347,0.08852349,0.00002309544,0.0000727975,0.0018267389,0.000002527999,0.00011371863,0.001044482],"genre_scores_gemma":[0.79515314,0.0000037773261,0.20447181,0.000085456864,0.000007856932,0.00023509219,0.000003969824,0.000011272114,0.000027645057],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966938,0.0003278848,0.0016270288,0.00021775265,0.0007893047,0.00034421677],"domain_scores_gemma":[0.99773526,0.0010641314,0.0005726545,0.0002904677,0.0002478353,0.00008964671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014978696,0.00028625556,0.0008369667,0.00016114552,0.000097857715,0.000045519017,0.0003059575,0.00023519131,0.000022525788],"category_scores_gemma":[0.0050765974,0.00021861916,0.000047064503,0.00043224264,0.00026972435,0.0008628651,0.0004459044,0.0005605848,3.8210317e-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":[0.00012203168,0.0032405911,0.51526576,0.001203343,0.00018034774,0.000034116558,0.3020784,0.000008750116,0.000006213409,0.012895798,0.00037156756,0.16459307],"study_design_scores_gemma":[0.011748115,0.002149681,0.3876902,0.0103304405,0.00017158,0.0000089758105,0.097610235,0.006823396,0.03795398,0.44341707,0.00028665754,0.0018096732],"about_ca_topic_score_codex":0.00000943061,"about_ca_topic_score_gemma":0.000021001297,"teacher_disagreement_score":0.43052128,"about_ca_system_score_codex":0.00022539933,"about_ca_system_score_gemma":0.00019671084,"threshold_uncertainty_score":0.8915031},"labels":[],"label_agreement":null},{"id":"W7108206144","doi":"10.2139/ssrn.5713122","title":"Data to DAGs to Dividends: A Scalable, LLM-Driven Pipeline for Causal Inference in Sustainability","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","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":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Causal inference; Directed acyclic graph; Causal model; Observational study; Pipeline (software); Causal structure; Causality (physics); Inference","score_opus":0.15915348638800397,"score_gpt":0.4593264446126412,"score_spread":0.30017295822463724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108206144","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":[0.0096637765,0.00092894176,0.96977687,0.008453788,0.0006182946,0.008374775,0.0015933593,0.00028280224,0.0003073729],"genre_scores_gemma":[0.8339609,0.008196209,0.14104058,0.0010201514,0.0012752098,0.0021423192,0.00050510286,0.00032636296,0.011533158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9808609,0.00088816567,0.00405764,0.0031319088,0.0013150817,0.00974629],"domain_scores_gemma":[0.98405147,0.0044933967,0.0015087605,0.0056111715,0.003390691,0.0009445136],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.016244583,0.0017687684,0.002832722,0.0019582047,0.0005473369,0.0005812444,0.0080163255,0.0011862243,0.00010879397],"category_scores_gemma":[0.047112323,0.0018655686,0.0004765117,0.0020264522,0.00022804725,0.0011478845,0.010485772,0.013240918,0.000035412668],"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":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.002803936,0.0036391858,0.003999759,0.003990988,0.0010814648,0.00006862327,0.0033480017,0.021044508,0.0004698225,0.7631503,0.0059183505,0.19048506],"study_design_scores_gemma":[0.0013469971,0.0017430767,0.000114963404,0.002791127,0.00041739232,0.00007647767,0.00333647,0.012287564,0.00028151507,0.9670777,0.008813799,0.0017129248],"about_ca_topic_score_codex":0.00081889,"about_ca_topic_score_gemma":0.039584916,"teacher_disagreement_score":0.8287363,"about_ca_system_score_codex":0.021469114,"about_ca_system_score_gemma":0.04269396,"threshold_uncertainty_score":0.9995058},"labels":[],"label_agreement":null},{"id":"W7108457069","doi":"10.1201/9781003504795","title":"Causal Inference and Machine Learning","year":2025,"lang":"en","type":"book","venue":"","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":"Dalhousie University","funders":"","keywords":"Causal inference; Raw data; Algorithmic learning theory; Deep learning; Inference; Artificial neural network; Computational learning theory; Active learning (machine learning); CLARITY","score_opus":0.12736591936775193,"score_gpt":0.40030138652418956,"score_spread":0.27293546715643763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108457069","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009628606,0.00029350026,0.122445546,0.00005383884,0.000047248664,0.00027986316,0.000018698493,0.0009595208,0.87589216],"genre_scores_gemma":[0.00041960884,0.0005159005,0.046113245,0.000093373135,0.000051741128,0.0000276993,0.00005076935,0.000044469267,0.9526832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988241,0.000055754113,0.00033537118,0.0003647311,0.0001933469,0.0002266493],"domain_scores_gemma":[0.99765754,0.0016454376,0.00018263493,0.00033978903,0.00010607569,0.00006850943],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023917443,0.00036096704,0.0005237026,0.00017713354,0.00009799599,0.00004485394,0.00019278743,0.00039409022,0.0005635664],"category_scores_gemma":[0.0013252068,0.00031797407,0.00005393677,0.00005372468,0.00010777349,0.000090037516,0.00034173724,0.0012490493,0.000020755379],"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":[0.0000045967067,0.000014596911,0.00005116109,0.0003557182,0.000039919145,0.000013897256,0.000060381954,5.738584e-7,0.000025590898,0.9662548,0.024919696,0.008259069],"study_design_scores_gemma":[0.000078557794,0.000086311265,0.000002224021,0.00041974406,0.00005482254,0.0000056310723,0.0000069206635,0.00012409444,0.00024128954,0.85058826,0.14808042,0.00031171786],"about_ca_topic_score_codex":0.000021056932,"about_ca_topic_score_gemma":0.000092432194,"teacher_disagreement_score":0.12316072,"about_ca_system_score_codex":0.00012312438,"about_ca_system_score_gemma":0.0002487854,"threshold_uncertainty_score":0.9999272},"labels":[],"label_agreement":null},{"id":"W7108721199","doi":"10.1182/blood-2025-6025","title":"Propensity score matching analysis comparing the efficacy and long-term outcomes of belumosudil to the best available treatment as a historical control, used as second-line therapy or beyond for chronic GVHD after steroid failure.","year":2025,"lang":"en","type":"article","venue":"Blood","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":true,"ca_institutions":"University of British Columbia; Hôpital Maisonneuve-Rosemont; University Health Network; Saskatchewan Cancer Agency; Princess Margaret Cancer Centre; University of Calgary; McMaster University; University of Toronto; Hamilton Health Sciences; Université de Montréal; Université Laval; BC Cancer Agency","funders":"","keywords":"Propensity score matching; Confounding; Randomized controlled trial; Clinical trial; Statistical significance; Sample size determination; Meta-analysis; Retrospective cohort study","score_opus":0.13267534313174487,"score_gpt":0.36915146620153577,"score_spread":0.2364761230697909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108721199","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":[0.98411983,0.00082398,0.011349121,0.0009407201,0.000037844093,0.0025213896,0.000026697167,0.000084527885,0.00009586376],"genre_scores_gemma":[0.9936146,0.000053561518,0.0028431197,0.00026933252,0.000037899932,0.0006534583,0.0000067138317,0.000027951655,0.0024933647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99851614,0.00010197501,0.00049526774,0.00037922323,0.00020520961,0.0003022015],"domain_scores_gemma":[0.9974922,0.00136378,0.00022644765,0.00072775886,0.00012536319,0.000064456464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036141058,0.00030754055,0.0009079876,0.00013006807,0.00020546601,0.00008056402,0.0003098512,0.00008180455,0.00015692269],"category_scores_gemma":[0.0001818846,0.00015336295,0.00019815746,0.0002918387,0.00007603409,0.000101746344,0.00012281866,0.00014745558,0.0000076179904],"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":[0.0035761322,0.0072837174,0.93211275,0.00071539223,0.016072473,0.00006955732,0.0066596535,0.00014566626,0.01771672,0.005555456,0.0006742517,0.009418221],"study_design_scores_gemma":[0.07699972,0.02509718,0.57346934,0.0014672879,0.036593217,0.00011412716,0.0009778296,0.0006556997,0.2223841,0.049961712,0.008715764,0.0035640087],"about_ca_topic_score_codex":0.0001390675,"about_ca_topic_score_gemma":0.0051270826,"teacher_disagreement_score":0.3586434,"about_ca_system_score_codex":0.00029138935,"about_ca_system_score_gemma":0.00013260933,"threshold_uncertainty_score":0.625396},"labels":[],"label_agreement":null},{"id":"W7113584415","doi":"","title":"MENTAL HEALTH ON THE MOVE: THE EFFECTS OF RELOCATION ON THE PSYCHOLOGICAL AND BEHAVIORAL HEALTH OF MILITARY CHILDREN","year":2025,"lang":"","type":"dissertation","venue":"Calhoun: The Naval Postgraduate School Institutional Archive (Naval Postgraduate School)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Relocation; Medical diagnosis; Mental health; Quarter (Canadian coin); Occupational safety and health; Suicide prevention; Military service","score_opus":0.06045519143712694,"score_gpt":0.3893842763711599,"score_spread":0.32892908493403294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7113584415","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":[0.9092001,0.0064007584,0.0010133747,0.060364433,0.0021376293,0.015859546,0.0039155865,0.00025543745,0.0008531589],"genre_scores_gemma":[0.96894705,0.016989706,0.0013211526,0.0074437815,0.00048571915,0.0009212258,0.0030011404,0.00017887318,0.00071135804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98335063,0.0055990396,0.0039174045,0.0021273808,0.003264006,0.001741528],"domain_scores_gemma":[0.98462695,0.007099303,0.003264803,0.0031958302,0.0010354868,0.000777629],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaepi_narrow","sts"],"category_scores_codex":[0.0051371427,0.0022248363,0.0023767897,0.0006648415,0.004847291,0.00017307988,0.0035717892,0.00063755875,0.000070357884],"category_scores_gemma":[0.0063043823,0.001143198,0.001268817,0.0015754516,0.004652257,0.00047428373,0.0008028221,0.006910696,0.00010356697],"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":[0.011280965,0.0072911135,0.0017704404,0.0036611413,0.002822195,0.00003550703,0.010924597,0.0007078295,0.0069868537,0.8282284,0.07295336,0.05333758],"study_design_scores_gemma":[0.006336102,0.02136393,0.24722476,0.02428531,0.00148448,0.00049129484,0.0070065404,0.002098453,0.015472807,0.6695442,0.0010419671,0.0036501475],"about_ca_topic_score_codex":0.003836137,"about_ca_topic_score_gemma":0.00059205707,"teacher_disagreement_score":0.24545433,"about_ca_system_score_codex":0.0012450098,"about_ca_system_score_gemma":0.0031805153,"threshold_uncertainty_score":0.9991018},"labels":[],"label_agreement":null},{"id":"W7115173317","doi":"10.1002/agj2.70260","title":"Improving causal inference from unreplicated on‐farm strip trials with propensity score matching: Application to plant growth regulator effects in wheat","year":2025,"lang":"en","type":"article","venue":"Agronomy Journal","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":"University of Guelph","funders":"Canada First Research Excellence Fund","keywords":"Propensity score matching; Covariate; Causal inference; Restricted randomization; Matching (statistics); Confounding; Replication (statistics); Benchmark (surveying); Inference; Randomization","score_opus":0.11446913192230342,"score_gpt":0.36258325031259675,"score_spread":0.24811411839029335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115173317","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":[0.5448229,0.00001851945,0.45334205,0.00024456883,0.000042579308,0.0011878589,0.000010766167,0.00011776628,0.0002130475],"genre_scores_gemma":[0.951349,0.000007717823,0.047987923,0.00022100545,0.00009389499,0.000246133,0.000017178592,0.000029853461,0.000047251076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976635,0.00032422284,0.00083942054,0.0004922978,0.00029190222,0.0003886687],"domain_scores_gemma":[0.9968532,0.0016942205,0.0005571615,0.00052024453,0.00019570642,0.00017948344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014191268,0.00033326933,0.00079397095,0.0003233741,0.0001662259,0.00016745095,0.00040109095,0.00015039933,0.000009999265],"category_scores_gemma":[0.001116486,0.00024457963,0.00007070225,0.0003976708,0.00004944586,0.000219308,0.00013514115,0.0007020217,0.00000795376],"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":[0.005503185,0.0016378259,0.12212627,0.00082813285,0.0006027575,0.00029517154,0.0023070753,0.0005833526,0.2658292,0.35632575,0.0024839079,0.24147739],"study_design_scores_gemma":[0.0027931263,0.0007002969,0.07017448,0.0027962683,0.0001828047,0.000047009562,0.00013853234,0.00030983295,0.217558,0.7044356,0.00012428791,0.00073981594],"about_ca_topic_score_codex":0.0005244724,"about_ca_topic_score_gemma":0.00044395178,"teacher_disagreement_score":0.4065262,"about_ca_system_score_codex":0.00049216277,"about_ca_system_score_gemma":0.0003403768,"threshold_uncertainty_score":0.9973667},"labels":[],"label_agreement":null},{"id":"W7115439340","doi":"","title":"Designing and Delivering Randomised Trials for Social Policy","year":2025,"lang":"en","type":"book","venue":"Research Portal (King's College London)","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":"Impact","funders":"","keywords":"Social policy; Public policy; Government (linguistics); Social care","score_opus":0.35671502083019047,"score_gpt":0.5101082543132096,"score_spread":0.15339323348301914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115439340","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039222382,0.0023410625,0.11292004,0.0015531275,0.00038699017,0.028322933,0.0024762268,0.0015187137,0.85008866],"genre_scores_gemma":[0.0032435104,0.0015156727,0.08920581,0.0002333029,0.0040561194,0.00500348,0.00030042228,0.0004606189,0.8959811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99357784,0.000993901,0.0017492827,0.0009785858,0.0013315902,0.0013688235],"domain_scores_gemma":[0.9812034,0.015884217,0.00082762516,0.0005856931,0.0012235959,0.0002755],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012560935,0.0007097169,0.0025675064,0.001703153,0.0009799276,0.00022530319,0.0007174086,0.0010060776,0.00016096649],"category_scores_gemma":[0.026106032,0.00069738954,0.0006469539,0.00057979074,0.00051541027,0.00027536225,0.0006548537,0.0015898795,0.000006898714],"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":[0.002911728,0.00008328107,0.000002344362,0.0025031178,0.00060010905,0.00022154381,0.00035447092,9.33009e-7,0.0014575779,0.7732468,0.2085374,0.010080654],"study_design_scores_gemma":[0.010605189,0.00031878086,0.0000020250427,0.0018055261,0.0002357541,0.000023025743,0.00019204314,0.00008587654,0.003955864,0.92037815,0.06162999,0.0007677528],"about_ca_topic_score_codex":0.00009553747,"about_ca_topic_score_gemma":0.00012649602,"teacher_disagreement_score":0.14713132,"about_ca_system_score_codex":0.00075286574,"about_ca_system_score_gemma":0.004202436,"threshold_uncertainty_score":0.9995477},"labels":[],"label_agreement":null},{"id":"W7115574149","doi":"10.3138/ptc-2023-0034-cc","title":"Commentary on Mandel et al.","year":2025,"lang":"en","type":"article","venue":"Physiotherapy Canada","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":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"","score_opus":0.04361432301448193,"score_gpt":0.4141295529163176,"score_spread":0.37051522990183566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115574149","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":[0.113119125,0.00043412196,0.11421514,0.63904,0.0014458754,0.002146027,0.00020126089,0.0015516592,0.12784682],"genre_scores_gemma":[0.30243692,0.00014112309,0.008928929,0.686204,0.000034411078,0.00007513799,0.000013660505,0.000039237722,0.0021265433],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993265,0.00003928421,0.00013366621,0.00016127709,0.00017562098,0.00016364966],"domain_scores_gemma":[0.99927765,0.00028146926,0.000045175442,0.00033415496,0.000027385053,0.00003416699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006821822,0.00013170023,0.00015947789,0.000049757018,0.000056557557,0.000011585184,0.00016309891,0.00001954198,0.00012567076],"category_scores_gemma":[0.000014539846,0.00011860246,0.000029462492,0.00012958726,0.000021032198,0.0000494421,0.000022146685,0.00013429754,0.0000012887638],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018163117,0.000047607693,0.00003370113,0.000013578193,0.000027891849,0.0000030064489,0.000018736666,0.00000792253,0.002853712,0.08544978,0.9082965,0.0032293652],"study_design_scores_gemma":[0.0003306719,0.00005788742,0.00008937743,0.00010589214,0.0000043447612,2.8771734e-7,0.000040218285,0.00015244095,0.02850644,0.36381343,0.60672015,0.00017886762],"about_ca_topic_score_codex":0.1747501,"about_ca_topic_score_gemma":0.32785344,"teacher_disagreement_score":0.3015764,"about_ca_system_score_codex":0.00029156174,"about_ca_system_score_gemma":0.00018588293,"threshold_uncertainty_score":0.83074534},"labels":[],"label_agreement":null},{"id":"W7115592647","doi":"10.3138/ptc-2023-0076-cc","title":"Commentary on Dhir et al.","year":2025,"lang":"en","type":"article","venue":"Physiotherapy Canada","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":true,"route_about_ca":false,"ca_institutions":"Canadian Physiotherapy Association","funders":"","keywords":"","score_opus":0.04247798333957591,"score_gpt":0.415432769188336,"score_spread":0.3729547858487601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115592647","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":[0.11543084,0.0004438296,0.07355979,0.68137753,0.0016262933,0.0021875957,0.00022181965,0.0017156707,0.123436645],"genre_scores_gemma":[0.29920998,0.00012156936,0.008680041,0.69016594,0.000037692338,0.00007777877,0.000013387543,0.00004055917,0.0016530318],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928516,0.000045416655,0.00014107942,0.00016951893,0.00018422877,0.00017458577],"domain_scores_gemma":[0.99918205,0.00034037285,0.000049242466,0.0003613182,0.000030070993,0.00003696654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000071992756,0.00013909572,0.00017034344,0.000052074905,0.000058741585,0.00001195,0.00017736696,0.000020509264,0.00013652204],"category_scores_gemma":[0.000020158615,0.00012605144,0.00003145146,0.00015250994,0.00002344494,0.000052562988,0.000016684786,0.00014514098,0.0000015315914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016974838,0.00004942001,0.000032116906,0.000013872106,0.000028911942,0.000002934688,0.000021803546,0.0000059551217,0.005697293,0.07987956,0.9107907,0.0034604701],"study_design_scores_gemma":[0.00026044852,0.000058445028,0.00008174171,0.000103646475,0.0000039036963,2.4651814e-7,0.000038695096,0.000073099654,0.05165184,0.29142222,0.65613407,0.00017162062],"about_ca_topic_score_codex":0.19792478,"about_ca_topic_score_gemma":0.3324743,"teacher_disagreement_score":0.25465658,"about_ca_system_score_codex":0.00031549178,"about_ca_system_score_gemma":0.00021939818,"threshold_uncertainty_score":0.8074163},"labels":[],"label_agreement":null},{"id":"W7116858593","doi":"10.1016/j.cjca.2025.12.016","title":"Probabilistic Quantitative Bias Analysis for Misclassification and Uncontrolled Confounding: A Methodological Tutorial Using Real-World Data","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Calgary; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Reliability (semiconductor); Probabilistic logic; Interpretation (philosophy); Statistical model; Estimation","score_opus":0.7201891238127621,"score_gpt":0.5461579239240665,"score_spread":0.17403119988869564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116858593","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":[0.039244905,0.00011292208,0.95831734,0.0003947876,0.00046551463,0.00040631546,0.000091666836,0.000014987631,0.00095155893],"genre_scores_gemma":[0.7430516,0.000022011991,0.2565115,0.000034896257,0.00027252495,0.000012701339,0.000017579248,0.000009021697,0.00006817842],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980901,0.00073026144,0.0006194223,0.00023778486,0.00007542615,0.00024699225],"domain_scores_gemma":[0.9921328,0.0062669134,0.00053383346,0.00036359628,0.0005259656,0.00017691402],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033456215,0.00013501434,0.0010623719,0.00080922473,0.00011868347,0.00004416565,0.00031891032,0.00010862107,0.0000032994137],"category_scores_gemma":[0.018963646,0.00011063235,0.00015824732,0.0005438783,0.0003531882,0.0001160615,0.000030486573,0.0001987174,1.0011048e-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":[0.0004564835,0.000005021653,0.019913595,0.00007324294,0.002943313,0.000027692848,0.00016047839,0.00213556,0.0010567213,0.96923774,0.0024265586,0.0015636153],"study_design_scores_gemma":[0.0013761837,0.00040594675,0.0077683106,0.00008780701,0.004478308,0.000039552688,0.00047906485,0.009333811,0.0001017726,0.9598695,0.015787298,0.0002724497],"about_ca_topic_score_codex":0.0007526664,"about_ca_topic_score_gemma":0.016359862,"teacher_disagreement_score":0.7038067,"about_ca_system_score_codex":0.0003074624,"about_ca_system_score_gemma":0.0010437233,"threshold_uncertainty_score":0.9893},"labels":[],"label_agreement":null},{"id":"W7117117856","doi":"10.54254/2753-8818/2026.ch30759","title":"Causal Inference with Observational Data via Propensity Score Matching: A Simple, Hands‑On Guide","year":2025,"lang":"","type":"article","venue":"Theoretical and Natural Science","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":"Dalhousie University","funders":"","keywords":"Propensity score matching; Causal inference; Observational study; Matching (statistics); Checklist; Replication (statistics); Workflow; Baseline (sea); Simple (philosophy)","score_opus":0.1522939937492116,"score_gpt":0.4137528535260652,"score_spread":0.2614588597768536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117117856","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":[0.8478291,0.00015798034,0.13995165,0.003044336,0.00020565442,0.0012347047,0.0000837576,0.00027278753,0.0072200308],"genre_scores_gemma":[0.9793907,0.000093760485,0.018746475,0.0012392971,0.000061030765,0.000019319546,0.000036380432,0.00001890222,0.00039416566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99553806,0.00015843041,0.00067975465,0.001463995,0.0012272157,0.0009325425],"domain_scores_gemma":[0.9952288,0.0019564417,0.00024001542,0.0015630859,0.00068122445,0.00033043296],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0023439925,0.00054971286,0.00064000837,0.00021776446,0.00095250964,0.00045212245,0.0021981746,0.00018700071,0.0001776426],"category_scores_gemma":[0.004104596,0.0003538269,0.000039605613,0.001654921,0.010008379,0.0013713662,0.0026677405,0.0010791441,0.000014521098],"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":[0.00035830028,0.00014188727,0.0020883412,0.00012812205,0.000021459275,0.00002078197,0.00012014999,0.0000060222005,0.004822222,0.97865,0.0002401999,0.0134025235],"study_design_scores_gemma":[0.0005123035,0.0007057298,0.014479792,0.0009350343,0.00009067697,0.000033256354,0.00004094979,0.013592495,0.01085814,0.95802385,0.00018395064,0.0005438074],"about_ca_topic_score_codex":0.00006252615,"about_ca_topic_score_gemma":0.00004843659,"teacher_disagreement_score":0.13156156,"about_ca_system_score_codex":0.00017607876,"about_ca_system_score_gemma":0.0010691119,"threshold_uncertainty_score":0.9998914},"labels":[],"label_agreement":null},{"id":"W7117304790","doi":"10.1002/cam4.71504","title":"The Impact of Distance and Income on Pediatric Solid Extracranial Tumors: A Report From <scp>CYP</scp> ‐C","year":2025,"lang":"en","type":"article","venue":"Cancer Medicine","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":true,"ca_institutions":"SickKids Foundation; McMaster University; Izaak Walton Killam Health Centre; Nova Scotia Health Authority; Dalhousie University","funders":"McMaster University; Pediatric Oncology Group of Ontario; Public Health Agency; IWK Health Centre; Mach-Gaensslen Foundation of Canada; Public Health Agency of Canada","keywords":"Low income; MEDLINE; Severity of illness; Middle income; Household income","score_opus":0.04880591475714174,"score_gpt":0.4349519950197374,"score_spread":0.38614608026259567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117304790","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":[0.958359,0.005588416,0.0295428,0.0005062795,0.00031861203,0.0005477391,0.000067084766,0.00018663969,0.004883415],"genre_scores_gemma":[0.9959003,0.0015155888,0.001057796,0.00007098918,0.0005075417,0.000098846525,0.0000060891352,0.000023138966,0.0008197527],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854237,0.000046176097,0.000593344,0.00028297587,0.00027961377,0.00025550288],"domain_scores_gemma":[0.9964741,0.002300633,0.00042383914,0.00056118146,0.00015449252,0.00008578822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042372016,0.00021507856,0.0005004932,0.00009859492,0.00009348545,0.000010913469,0.00023044519,0.00007943479,0.000029586017],"category_scores_gemma":[0.003237611,0.0001247405,0.0000615585,0.0003511933,0.0002916352,0.00007227162,0.00006665391,0.00027991706,7.536011e-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":[0.00078086834,0.00074128876,0.4911186,0.0019422425,0.0011542118,0.0012760691,0.009493003,0.00010455386,0.032547653,0.14121383,0.25806677,0.06156089],"study_design_scores_gemma":[0.001747261,0.00077375903,0.09816226,0.0021714377,0.0003082878,0.000032307293,0.00059176737,0.00037300828,0.0074170833,0.88600945,0.00222681,0.00018656036],"about_ca_topic_score_codex":0.00043835567,"about_ca_topic_score_gemma":0.00007876466,"teacher_disagreement_score":0.7447956,"about_ca_system_score_codex":0.00018297085,"about_ca_system_score_gemma":0.00020017645,"threshold_uncertainty_score":0.508677},"labels":[],"label_agreement":null},{"id":"W7117485707","doi":"10.1109/bdkcse67969.2025.11300540","title":"Learning Latent Trends: Artificial Intelligence-Augmented Difference-in-Differences Estimation","year":2025,"lang":"","type":"article","venue":"","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":"University of Manitoba","funders":"","keywords":"Interpretability; Inference; Counterfactual thinking; Robustness (evolution); Nonparametric statistics; Identification (biology); Representation (politics); Generative model; Data-driven","score_opus":0.14821754824035932,"score_gpt":0.41225730348491635,"score_spread":0.26403975524455703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117485707","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":[0.123739466,0.00027112322,0.8489531,0.0014652859,0.0006412381,0.00088281656,0.000010192431,0.0008649871,0.023171755],"genre_scores_gemma":[0.9417269,0.00058141304,0.0411461,0.000101142854,0.000053629698,0.0002100492,0.00003217438,0.000049008286,0.01609955],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941985,0.00049369864,0.002404128,0.0011260832,0.00066544453,0.0011121304],"domain_scores_gemma":[0.9967026,0.0014776008,0.0006247289,0.00074465637,0.00027472756,0.00017565279],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00086879137,0.0009000266,0.0012593282,0.0017439387,0.00035341879,0.00037376388,0.00075427454,0.0006035796,0.0027668169],"category_scores_gemma":[0.0015476906,0.0008336367,0.0002686089,0.0024748973,0.00039671976,0.00043342917,0.00042482934,0.0014689023,0.00012859661],"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":[0.00010067002,0.00068710715,0.0034783601,0.00023807366,0.00008376504,0.000014693888,0.0011641613,0.0010067441,0.0006466805,0.4000761,0.00007536507,0.59242827],"study_design_scores_gemma":[0.00016566445,0.00046973024,0.0045561623,0.0015514101,0.00012698513,0.0000026752334,0.0021410673,0.30824503,0.016884092,0.66514325,0.000039786162,0.0006741176],"about_ca_topic_score_codex":0.00022643796,"about_ca_topic_score_gemma":0.0005564069,"teacher_disagreement_score":0.81798744,"about_ca_system_score_codex":0.0006346128,"about_ca_system_score_gemma":0.0002392819,"threshold_uncertainty_score":0.99941146},"labels":[],"label_agreement":null},{"id":"W7124436614","doi":"10.1093/biomtc/ujaf174","title":"Estimating optimal dynamic treatment regimes with Gaussian process emulation","year":2025,"lang":"en","type":"article","venue":"Biometrics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperparameter optimization; Estimator; Emulation; Grid; Gaussian process; Process (computing); Parametric statistics; Noise (video); Gaussian; Estimation theory","score_opus":0.08512936259223094,"score_gpt":0.4365562607013978,"score_spread":0.35142689810916683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124436614","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":[0.15994292,0.00009749755,0.83552724,0.00013059059,0.000059615973,0.00042910106,0.000007430882,0.00050778064,0.003297837],"genre_scores_gemma":[0.5549725,0.0000074090603,0.44411567,0.000011837404,0.0000113794185,0.000055135308,0.000009198634,0.000015800195,0.00080104347],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905634,0.00002025622,0.00024309444,0.00025536199,0.00020511853,0.0002198064],"domain_scores_gemma":[0.99903804,0.00031385256,0.00016415198,0.0003042551,0.00013581714,0.00004389751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012804096,0.00018623055,0.00023038503,0.0010952785,0.00010121532,0.000052310723,0.00013566554,0.000090246474,0.000010923775],"category_scores_gemma":[0.00051609124,0.00013852012,0.000034132157,0.0034594678,0.000054157386,0.00016842404,0.000028418433,0.00007208777,0.000004594587],"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":[0.00033081783,0.0023558666,0.015077315,0.0020836543,0.0006251932,0.00010866244,0.0026155796,0.0065604197,0.0037437764,0.2694924,0.0011300273,0.6958763],"study_design_scores_gemma":[0.002973466,0.0028835386,0.0056876913,0.001418127,0.0005606976,0.000050070266,0.0010750438,0.42192286,0.055702034,0.5047301,0.0013507903,0.0016455505],"about_ca_topic_score_codex":0.000008717531,"about_ca_topic_score_gemma":0.0000047768544,"teacher_disagreement_score":0.69423074,"about_ca_system_score_codex":0.0003347691,"about_ca_system_score_gemma":0.00009457126,"threshold_uncertainty_score":0.5648686},"labels":[],"label_agreement":null},{"id":"W7124951972","doi":"10.1111/caje.70028","title":"On the role of the zero conditional mean assumption for causal inference in linear models","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Economics/Revue canadienne d économique","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causal inference; Causal model; Instrumental variable; Ambiguity; Conditional independence; Ordinary least squares; Linear model; Outcome (game theory); Independence (probability theory); Conditional expectation","score_opus":0.24624384784960943,"score_gpt":0.28613618031513305,"score_spread":0.03989233246552362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124951972","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":[0.9854032,0.00004333001,0.010722926,0.001638776,0.00036125578,0.0005585992,0.00028227625,0.0000057428615,0.0009839261],"genre_scores_gemma":[0.9972583,0.000018565428,0.0019561036,0.00043076766,0.000073562136,0.000059307742,0.0000064976643,0.000024067429,0.00017283771],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99851584,0.00008412321,0.0008171071,0.0001910226,0.0000052125206,0.00038668697],"domain_scores_gemma":[0.996644,0.0018192469,0.00062878587,0.00040108102,0.00025647634,0.00025037202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008563711,0.00019522508,0.00043258106,0.0004219415,0.00012453333,0.000032671986,0.0006370341,0.00015958818,0.000050637682],"category_scores_gemma":[0.0013945746,0.00016043527,0.00018249029,0.0001280098,0.0001969424,0.00025479915,0.000024844068,0.0004053705,9.750058e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033252163,0.0000119802235,0.00072256685,0.000023310042,0.0000461905,0.0000020281886,0.00034140548,0.017984133,0.00005035744,0.98002243,0.00030851553,0.000453854],"study_design_scores_gemma":[0.0002894427,0.00011728133,0.00016990377,0.0002475418,0.000025446214,0.000011308603,0.00023915485,0.014666827,0.0019623684,0.9813253,0.00080648845,0.00013893771],"about_ca_topic_score_codex":0.014818498,"about_ca_topic_score_gemma":0.8842846,"teacher_disagreement_score":0.8694661,"about_ca_system_score_codex":0.0014600487,"about_ca_system_score_gemma":0.0020876052,"threshold_uncertainty_score":0.9917419},"labels":[],"label_agreement":null},{"id":"W7128215162","doi":"10.5465/amj.2025.4004","title":"Compelling Empirics in Quantitative Studies","year":2025,"lang":"en","type":"article","venue":"Academy of Management Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"","score_opus":0.48466076019773907,"score_gpt":0.5545202349706227,"score_spread":0.06985947477288368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128215162","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":[0.2850161,0.009118302,0.6214898,0.01160763,0.0004010588,0.0013077625,0.000003847622,0.0002884007,0.07076708],"genre_scores_gemma":[0.5339054,0.008892704,0.45504582,0.00072431815,0.000028785664,0.000018109293,2.574232e-7,0.000017589236,0.00136702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988273,0.00008376516,0.0005658746,0.0001216807,0.00021317828,0.00018821243],"domain_scores_gemma":[0.999042,0.00053823646,0.00027468297,0.000069582515,0.000053899086,0.00002159939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010605342,0.00011663376,0.00030677303,0.00045640866,0.000059443097,0.0000126057785,0.00027379353,0.000055865115,0.000012411233],"category_scores_gemma":[0.0002600611,0.00010294449,0.00005488344,0.0003752472,0.00009064738,0.0001692634,0.00015868284,0.00044870705,0.0000027643225],"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":[0.000022488413,0.00006454147,0.0012080412,0.00028072434,0.00021335544,0.000011894082,0.00057313795,0.00009499815,0.00009222443,0.9866241,0.0050868243,0.005727626],"study_design_scores_gemma":[0.00029354187,0.00003157598,0.0008376595,0.0007900399,0.00005126678,0.000002589488,0.003093392,0.00013327441,0.001951262,0.99058586,0.0021417944,0.00008773984],"about_ca_topic_score_codex":4.4757425e-7,"about_ca_topic_score_gemma":0.0000011743151,"teacher_disagreement_score":0.24888931,"about_ca_system_score_codex":0.000100324905,"about_ca_system_score_gemma":0.00000806882,"threshold_uncertainty_score":0.41979545},"labels":[],"label_agreement":null},{"id":"W7132906676","doi":"","title":"Causal Inference using Electronic Health Records in Primary Care","year":2024,"lang":"","type":"dissertation","venue":"TSpace","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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Diabetes Action Research and Education Foundation","keywords":"Causal inference; Observational study; Inference; Marginal structural model; Randomized controlled trial; Instrumental variable; Estimation; Causality (physics); Health care; Propensity score matching","score_opus":0.0975769037204345,"score_gpt":0.48158313736556746,"score_spread":0.384006233645133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132906676","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":[0.84792984,0.052785806,0.058363706,0.00067827536,0.0029377472,0.0071452577,0.00011957341,0.002202611,0.027837176],"genre_scores_gemma":[0.90059674,0.014409834,0.06676297,0.0005108002,0.0005139745,0.00054129533,0.0023321398,0.0008991385,0.013433097],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935913,0.00040661782,0.0017000027,0.0014843307,0.0008419615,0.0019757927],"domain_scores_gemma":[0.99636066,0.0005978518,0.0011464594,0.0011723025,0.00044152857,0.00028117953],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00086017395,0.0012891665,0.0018815122,0.0010099241,0.00023154962,0.0002102627,0.0006799261,0.0010660931,0.00029538744],"category_scores_gemma":[0.00047139794,0.0014681447,0.00027815063,0.0014818215,0.0001230149,0.00038964793,0.000244249,0.0038025924,0.00012407122],"study_design_candidate":"qualitative","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":[0.0009912404,0.001101651,0.0013202181,0.10508915,0.00062576286,0.00048225693,0.56667924,0.000982693,0.019119702,0.18284415,0.0020518978,0.11871203],"study_design_scores_gemma":[0.0026106637,0.0060251397,0.0014107983,0.09193959,0.0012953366,0.00017817917,0.25077006,0.012380501,0.023603503,0.58958465,0.009949493,0.010252118],"about_ca_topic_score_codex":0.0046954635,"about_ca_topic_score_gemma":0.01654373,"teacher_disagreement_score":0.4067405,"about_ca_system_score_codex":0.01003349,"about_ca_system_score_gemma":0.008957076,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W7132970944","doi":"","title":"Generalized Variable Importance Metric: An approach to identify important predictors from machine learning models","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Metric (unit); Regression; Measure (data warehouse); Regression analysis; Black box; Variable (mathematics); Correlation; Generalized linear model; Instrumental variable","score_opus":0.12518113551008744,"score_gpt":0.4238559980188738,"score_spread":0.2986748625087864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132970944","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":[0.20613681,0.0038161662,0.75756484,0.00004388559,0.00080788863,0.0036526155,0.00048438564,0.0018155434,0.025677875],"genre_scores_gemma":[0.16029835,0.00197531,0.7824446,0.00021762672,0.00038312218,0.0014258863,0.011094357,0.00055976637,0.041600987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9904887,0.00068425585,0.0029285606,0.0027436158,0.0016641547,0.0014907075],"domain_scores_gemma":[0.99219143,0.00081700913,0.0026083896,0.0025549757,0.0009983132,0.00082987716],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0019136016,0.0019066305,0.0027767345,0.0013874791,0.00062433543,0.0005195802,0.0018436557,0.0016229813,0.0009251986],"category_scores_gemma":[0.0027283777,0.0020305363,0.00045355584,0.003161121,0.000074905605,0.0011548756,0.00043782173,0.0026159827,0.00002471341],"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":[0.0023945973,0.004681024,0.0076362756,0.0050713704,0.003950106,0.0001527801,0.073867366,0.11764958,0.08248516,0.6949135,0.0043765088,0.0028217505],"study_design_scores_gemma":[0.0015783848,0.0005600066,0.00030989366,0.0016045175,0.0022468276,0.000009534628,0.01046604,0.50558746,0.019433709,0.45336354,0.0013633362,0.0034767534],"about_ca_topic_score_codex":0.006349044,"about_ca_topic_score_gemma":0.00049967505,"teacher_disagreement_score":0.3879379,"about_ca_system_score_codex":0.00082970195,"about_ca_system_score_gemma":0.000874652,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W7132977956","doi":"","title":"Evaluating Machine Learning Methods for Estimating Heterogeneous Treatment Effects Within a Potential Outcomes Survival Analysis Framework","year":2025,"lang":"","type":"dissertation","venue":"TSpace","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":"Public Health Ontario; Toronto Public Health","funders":"Alliance de recherche numérique du Canada; University of Toronto; Innovation, Science and Economic Development Canada","keywords":"Causal inference; Observational study; Bayesian probability; Survival analysis; Outcome (game theory); Inference; Average treatment effect; Confounding; Bayesian inference; Oracle","score_opus":0.16999694995480655,"score_gpt":0.5791987256780909,"score_spread":0.4092017757232844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132977956","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":[0.08230521,0.0010666561,0.90967435,0.00007154409,0.0016317512,0.0042294757,0.000037599842,0.0008380338,0.00014541087],"genre_scores_gemma":[0.05783482,0.00008216267,0.9304379,0.000032796004,0.00017683518,0.0020593414,0.001034357,0.0002609432,0.008080836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909882,0.0029132701,0.0021515016,0.0018498132,0.00089148624,0.0012057112],"domain_scores_gemma":[0.97299033,0.021292377,0.003232592,0.0013705862,0.00084206735,0.00027205193],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0040157316,0.001922496,0.0042888545,0.0011832496,0.0011862598,0.0003962203,0.0006651913,0.0013467318,0.00018484727],"category_scores_gemma":[0.028763035,0.0017916245,0.0022321406,0.0016625837,0.00008174348,0.00016820201,0.00021418066,0.0015454974,0.000007676341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009280712,0.0008813924,0.0007674214,0.0066044834,0.023110295,0.00006853634,0.037503753,0.53401667,0.010553328,0.005076186,0.0000018377303,0.380488],"study_design_scores_gemma":[0.001042669,0.0018932935,0.000052443273,0.001679786,0.025122099,0.0000056657127,0.0016291488,0.86718166,0.033776335,0.06632346,0.000008703379,0.0012847375],"about_ca_topic_score_codex":0.00064348435,"about_ca_topic_score_gemma":0.00034722305,"teacher_disagreement_score":0.3792033,"about_ca_system_score_codex":0.0010730807,"about_ca_system_score_gemma":0.00050045294,"threshold_uncertainty_score":0.99994975},"labels":[],"label_agreement":null},{"id":"W7133034134","doi":"","title":"Causal Inference with Neural Network Predictions","year":2024,"lang":"","type":"dissertation","venue":"TSpace","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":"Public Health Ontario","funders":"","keywords":"Estimator; Causal inference; Inverse probability weighting; Average treatment effect; Weighting; Artificial neural network; Inverse probability; Outcome (game theory)","score_opus":0.08206922318757381,"score_gpt":0.4389688164016163,"score_spread":0.35689959321404247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133034134","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":[0.26446462,0.0069979904,0.53174156,0.0019553788,0.009246591,0.009083331,0.000246758,0.011875684,0.16438812],"genre_scores_gemma":[0.8506714,0.0009491199,0.05188797,0.00013185211,0.0016253865,0.0010717163,0.00084666384,0.0006078074,0.09220809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953495,0.00017994603,0.0009934104,0.0012740393,0.0009558517,0.0012472223],"domain_scores_gemma":[0.99580127,0.0011028734,0.0007517562,0.0013335136,0.00063940824,0.00037119252],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0003772136,0.0013214628,0.00118147,0.00031872754,0.000470425,0.00040492334,0.00065442396,0.0009601771,0.0012442837],"category_scores_gemma":[0.000503139,0.0011712236,0.00025063736,0.0013748654,0.00030702061,0.00043525585,0.00019269747,0.0027691054,0.00042756504],"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":[0.001716217,0.0011878209,0.001261075,0.01159393,0.0029830225,0.0012476821,0.11417924,0.04854073,0.0028473856,0.71776915,0.084988594,0.01168518],"study_design_scores_gemma":[0.0018260689,0.0076266187,0.001643672,0.02986125,0.008789433,0.0005075553,0.05087089,0.1466445,0.0071897455,0.71105623,0.024834225,0.009149811],"about_ca_topic_score_codex":0.00025883075,"about_ca_topic_score_gemma":0.0017366927,"teacher_disagreement_score":0.5862068,"about_ca_system_score_codex":0.000364454,"about_ca_system_score_gemma":0.00074312004,"threshold_uncertainty_score":0.9999537},"labels":[],"label_agreement":null},{"id":"W7133081946","doi":"","title":"Causal Variance Decompositions for Evaluating Healthcare Provider Performance","year":2023,"lang":"","type":"dissertation","venue":"TSpace","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":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Government of Ontario","keywords":"Variance (accounting); Quality (philosophy); Causal inference; Health care; Context (archaeology); Variation (astronomy); Variance decomposition of forecast errors; Inference","score_opus":0.26955459466488796,"score_gpt":0.5496522662516041,"score_spread":0.28009767158671617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133081946","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":[0.37271625,0.0016030548,0.5773352,0.006516355,0.0058444384,0.025036423,0.00060449046,0.0059256335,0.0044181435],"genre_scores_gemma":[0.28123626,0.0012057733,0.61042804,0.00038331287,0.0010155335,0.011795807,0.0036933532,0.00109097,0.08915094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994523,0.0002691897,0.0015358784,0.0013407612,0.00094147987,0.0013897121],"domain_scores_gemma":[0.99232316,0.0025624065,0.001633043,0.0012432671,0.0019262099,0.00031190136],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015416715,0.0010797442,0.0012851863,0.00039650997,0.001272028,0.00020811475,0.0006902706,0.00096805196,0.0002108855],"category_scores_gemma":[0.002422861,0.0012271699,0.00036031453,0.00084545027,0.00012271658,0.00049179315,0.00013710345,0.0012567855,0.0002710752],"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":[0.004053024,0.0020745443,0.0007132353,0.12804024,0.0020361491,0.0000858453,0.22874175,0.0041550715,0.089747,0.32080343,0.028798183,0.19075155],"study_design_scores_gemma":[0.004806586,0.010877485,0.0024652488,0.034667857,0.0030904424,0.00011130533,0.07218466,0.2652338,0.11093606,0.48333645,0.0036285487,0.00866153],"about_ca_topic_score_codex":0.0002939626,"about_ca_topic_score_gemma":0.00070836965,"teacher_disagreement_score":0.26107875,"about_ca_system_score_codex":0.00079743913,"about_ca_system_score_gemma":0.0013755499,"threshold_uncertainty_score":0.99901783},"labels":[],"label_agreement":null},{"id":"W7154048392","doi":"10.1145/3772318.3808999","title":"10.1145/3772318.3808999","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Health equity; Equity (law); Public health; MEDLINE","score_opus":0.058533600213292604,"score_gpt":0.31988099477624055,"score_spread":0.2613473945629479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154048392","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007932762,0.000015008623,0.0002344012,0.00017129799,0.0000013951186,0.00028784433,0.000010666816,0.0009515535,0.9975346],"genre_scores_gemma":[0.00030058468,5.5471287e-7,0.02125352,0.00007820508,0.00007356615,0.000053563635,0.0000055377773,0.000044761964,0.9781897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990021,0.000034346882,0.00023459399,0.00022825926,0.00019430372,0.00030642637],"domain_scores_gemma":[0.9991095,0.00017145541,0.000041983767,0.00048850913,0.000057196445,0.0001313766],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016648966,0.00017471478,0.00022783053,0.00006936506,0.000056381734,0.00002784419,0.00026850862,0.00008529184,0.99040776],"category_scores_gemma":[0.00018034397,0.00016680727,0.000056860874,0.00019344104,0.000038101865,0.00013767123,0.00005285238,0.00012957542,0.9490813],"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":[0.000043592863,0.00008533897,1.3317553e-7,0.00001581342,0.000014943509,0.0000103385755,0.000035634173,0.000010203763,0.00044349188,0.0008008269,0.31034172,0.688198],"study_design_scores_gemma":[0.00009556096,0.00014456792,0.0000030467165,0.000032777818,0.000013740331,0.000009183934,9.978637e-7,0.00006190972,0.001822391,0.020059403,0.9775373,0.00021913653],"about_ca_topic_score_codex":0.0000061722194,"about_ca_topic_score_gemma":1.8322116e-7,"teacher_disagreement_score":0.6879788,"about_ca_system_score_codex":0.000056441822,"about_ca_system_score_gemma":0.00002029468,"threshold_uncertainty_score":0.6802203},"labels":[],"label_agreement":null},{"id":"W7161794840","doi":"10.82308/12937","title":"Targeted maximum likelihood estimation for longitudinal data","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Causal inference; Robustness (evolution); Estimator; Inverse probability weighting; Likelihood function; Missing data; Confounding; Inference; Exponential family; Marginal structural model","score_opus":0.2025923458627461,"score_gpt":0.449120704485962,"score_spread":0.24652835862321587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161794840","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":[0.0029347492,0.00012500868,0.9825571,0.000066099165,0.000449143,0.0024903205,0.0003086886,0.0011993408,0.009869551],"genre_scores_gemma":[0.0077377968,0.000039111514,0.95166755,0.000033502285,0.00015016568,0.000783289,0.027746614,0.00014847744,0.011693501],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980822,0.000022474278,0.00057622767,0.0006490862,0.00029821007,0.00037177678],"domain_scores_gemma":[0.9971819,0.00043598245,0.00045853213,0.0014195702,0.0004200012,0.00008401938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003064556,0.00039921424,0.00049310306,0.00015914443,0.00009805423,0.00009662645,0.000798222,0.0004481707,0.00078528497],"category_scores_gemma":[0.0014473284,0.00035837176,0.00008434219,0.00012181032,0.000020375608,0.0006432281,0.00009530246,0.00027486152,0.00010773423],"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":[0.00017743971,0.000462782,0.000036395595,0.003757238,0.00035880742,0.0000057142693,0.0004517304,0.0000044598883,0.004236481,0.25676414,0.5113625,0.22238232],"study_design_scores_gemma":[0.00019617502,0.00010388015,0.00007564611,0.00021415453,0.0001754858,0.00000237522,0.00018725185,0.008080359,0.01271903,0.97661644,0.0011499308,0.00047927606],"about_ca_topic_score_codex":0.000054035703,"about_ca_topic_score_gemma":0.00029232237,"teacher_disagreement_score":0.71985227,"about_ca_system_score_codex":0.00008093496,"about_ca_system_score_gemma":0.00013131986,"threshold_uncertainty_score":0.9998868},"labels":[],"label_agreement":null},{"id":"W7161963721","doi":"10.82308/2506","title":"Amiodarone and the risk of pacemaker insertion in elderly patients with atrial fibrillation : analysis of time-dependent exposure using nested case-control and survival analysis methodologies","year":2003,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Amiodarone; Nested case-control study; Atrial fibrillation; Confounding; Proportional hazards model; Cohort; Cohort study; Adverse effect","score_opus":0.0631809756804065,"score_gpt":0.36906789267711354,"score_spread":0.30588691699670706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161963721","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":[0.91181535,0.00019783244,0.086922206,0.0000030553097,0.000020275047,0.00086579635,0.00009495421,0.000034389755,0.00004614736],"genre_scores_gemma":[0.9637967,0.0001399858,0.035764195,0.0000014444155,0.0000079979545,0.000008668949,0.00017981227,0.000025113759,0.00007607838],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964681,0.0016358114,0.00096300413,0.00036763403,0.00040451254,0.0001609094],"domain_scores_gemma":[0.99406457,0.0033303464,0.0017134522,0.0003806412,0.00048103978,0.000029957382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019272208,0.00032120902,0.001711126,0.0010205203,0.00006634808,0.000028079514,0.00005366458,0.00032749202,0.000027431142],"category_scores_gemma":[0.0017561726,0.00020446006,0.00027679492,0.001527334,0.000121844154,0.00017291706,0.000018632922,0.00020309971,4.503252e-8],"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":[0.0058845114,0.00006659332,0.9338037,0.00031616428,0.021939926,0.000013845629,0.0027960802,0.02802432,0.0006172063,0.0010876965,0.0000012264898,0.0054487507],"study_design_scores_gemma":[0.011489116,0.0011370336,0.7292392,0.00025502313,0.15617509,0.000012411536,0.007566068,0.06464341,0.0018060451,0.02656904,4.138392e-7,0.0011071581],"about_ca_topic_score_codex":0.0019469701,"about_ca_topic_score_gemma":0.0135372495,"teacher_disagreement_score":0.20456448,"about_ca_system_score_codex":0.000056917546,"about_ca_system_score_gemma":0.000041596486,"threshold_uncertainty_score":0.8337639},"labels":[],"label_agreement":null},{"id":"W7161968822","doi":"10.82308/39725","title":"Leveraging expert knowledge and public data to inform health interventions: Novel practical approaches for building causal directed acyclic graphs","year":2025,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Context (archaeology); Information scientist; Public policy; Knowledge production","score_opus":0.6146624171519397,"score_gpt":0.5468540298589458,"score_spread":0.06780838729299388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161968822","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":[0.003073586,0.0012822261,0.98356706,0.0020447606,0.0004329804,0.0036105462,0.00021186107,0.0015176487,0.004259328],"genre_scores_gemma":[0.020751104,0.00029934707,0.9673759,0.0002488321,0.000086027045,0.0015974377,0.0045266906,0.00010907047,0.005005591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997221,0.00006505689,0.0010571352,0.00084705907,0.0002458578,0.000563898],"domain_scores_gemma":[0.996398,0.0015290144,0.00049454335,0.0010142351,0.0003256246,0.0002386388],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010464455,0.00048400063,0.0008325842,0.00078769017,0.00033557118,0.0002620763,0.0006096993,0.00032084846,0.000026352107],"category_scores_gemma":[0.0067837336,0.0004587156,0.00014689936,0.0006349529,0.000033847653,0.00096553826,0.00050129916,0.0005023548,0.0000015513538],"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":[0.00009399295,0.0008515459,0.000019786705,0.006112927,0.0003473136,7.918612e-7,0.0036883266,2.6983e-7,0.00033450205,0.84152246,0.041789968,0.10523814],"study_design_scores_gemma":[0.0040612533,0.0015441638,0.00069357886,0.025876317,0.00090369664,0.00008636029,0.05423682,0.02420464,0.0070768697,0.73064613,0.14491324,0.005756945],"about_ca_topic_score_codex":0.00011231621,"about_ca_topic_score_gemma":0.0024482398,"teacher_disagreement_score":0.11087632,"about_ca_system_score_codex":0.000252623,"about_ca_system_score_gemma":0.00058133877,"threshold_uncertainty_score":0.99978644},"labels":[],"label_agreement":null},{"id":"W7162001184","doi":"10.82308/942","title":"Innovations and opportunities for primary health care after hospital discharge: an application of causal inference methods in health services research","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Health services; Primary health care; Primary care; Health care; Public health","score_opus":0.2555043268383185,"score_gpt":0.5826403002615346,"score_spread":0.3271359734232161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162001184","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":[0.19895533,0.0053310497,0.7575969,0.0036372258,0.00044681344,0.021335872,0.0020173418,0.00082352624,0.0098559335],"genre_scores_gemma":[0.34035426,0.001265577,0.6451608,0.00026256894,0.00008293366,0.0050179143,0.0061515085,0.0001273972,0.0015770232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735624,0.00034099998,0.0010071448,0.00050872436,0.0003643361,0.00042256352],"domain_scores_gemma":[0.99615103,0.00063308206,0.0010605548,0.0007903827,0.0012367684,0.00012816925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023655968,0.0002968745,0.0007572929,0.00062276353,0.00026155816,0.000081126636,0.00038886743,0.00029013102,0.000010878915],"category_scores_gemma":[0.0001971431,0.0002843567,0.000038666145,0.00019002926,0.0001326618,0.0005922067,0.00007680068,0.00048776073,2.2834928e-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":[0.00018770965,0.00040528225,0.0012107914,0.03371753,0.00004192694,0.0000010581589,0.042769715,4.021299e-7,0.00055196957,0.49167678,0.00021356576,0.42922327],"study_design_scores_gemma":[0.0009736275,0.0036100687,0.031662744,0.0050693545,0.000045166707,0.0000022115064,0.12988822,0.00028818604,0.006288362,0.8153261,0.0053804354,0.0014655436],"about_ca_topic_score_codex":0.0013730327,"about_ca_topic_score_gemma":0.009569901,"teacher_disagreement_score":0.42775774,"about_ca_system_score_codex":0.0003051423,"about_ca_system_score_gemma":0.0012267906,"threshold_uncertainty_score":0.99996084},"labels":[],"label_agreement":null},{"id":"W7162018817","doi":"10.82308/30565","title":"Methodological Advances to Address Measurement Error and Model Misspecification in HIV Research","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Covariate; Marginal structural model; Observational error; Human immunodeficiency virus (HIV); Cohort; Clinical trial; Cohort study; Hepatitis C; Disease","score_opus":0.8930019370217708,"score_gpt":0.6359384519547808,"score_spread":0.25706348506698995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162018817","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":[0.10472293,0.0106208855,0.73686695,0.005485629,0.0011760577,0.01760261,0.00008622423,0.0051683784,0.11827032],"genre_scores_gemma":[0.031516027,0.005549773,0.9316362,0.00007653368,0.000098730125,0.0028186091,0.0002000333,0.00017824316,0.027925823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99675333,0.00048668022,0.0005706226,0.00068191445,0.0010894042,0.0004180207],"domain_scores_gemma":[0.9970393,0.0015209251,0.00013242218,0.00044939047,0.0007360232,0.00012193234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005437264,0.00027103545,0.00051428814,0.0006055848,0.00008203852,0.00008460425,0.0003344413,0.00035964578,0.000054042757],"category_scores_gemma":[0.0055664005,0.00023199296,0.000044262462,0.0005506625,0.000046740333,0.00028237392,0.0000831517,0.0006712963,0.000040155017],"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":[0.0010645682,0.00056999974,0.000063288244,0.0029212208,0.000071706294,0.000038504277,0.013347523,0.00079091394,0.055406176,0.6908259,0.023052838,0.21184735],"study_design_scores_gemma":[0.00013226128,0.00009913827,0.0002968591,0.0010390915,0.000013681451,6.9096285e-7,0.010944497,0.0013911716,0.019727742,0.96518064,0.00079892756,0.0003752774],"about_ca_topic_score_codex":0.000024260728,"about_ca_topic_score_gemma":0.002176833,"teacher_disagreement_score":0.27435476,"about_ca_system_score_codex":0.0002990183,"about_ca_system_score_gemma":0.00009863301,"threshold_uncertainty_score":0.9460398},"labels":[],"label_agreement":null},{"id":"W7162035648","doi":"10.82308/23533","title":"The impact of human papillomavirus vaccination on adolescent health outcomes: an application of the regression discontinuity design","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Vaccination; Ile de france; Meningococcal disease; Human papillomavirus; Public health; Urban environment","score_opus":0.20533511706712784,"score_gpt":0.5326317074237812,"score_spread":0.32729659035665337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162035648","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":[0.8752826,0.0003678392,0.10318558,0.00031601847,0.00048912,0.013456615,0.00014270649,0.0006952653,0.0060642525],"genre_scores_gemma":[0.99624133,0.000060830916,0.002407087,0.000015554544,0.000032000586,0.00015921284,0.0001641907,0.00005678035,0.00086303113],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99747837,0.00047464896,0.000906417,0.00029654006,0.0006179606,0.00022604642],"domain_scores_gemma":[0.995485,0.0003284665,0.0023747035,0.0012325945,0.00050119247,0.00007800925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014087808,0.00035122436,0.0006219178,0.00009575777,0.00021801665,0.000022440576,0.0006245377,0.00023429451,0.000012304923],"category_scores_gemma":[0.0004700178,0.00015629022,0.0002331814,0.00019053393,0.000040361247,0.00013671242,0.000041943815,0.00038432635,0.000001226958],"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":[0.0015095897,0.0048722313,0.012520006,0.002166592,0.00039668285,4.862396e-7,0.01057849,0.00020446045,0.053965982,0.33619997,0.026762059,0.55082345],"study_design_scores_gemma":[0.0005291533,0.0015424012,0.17979328,0.0011594804,0.000072135954,6.261134e-7,0.0017256375,0.00033916644,0.06584779,0.74857336,0.000017724371,0.00039926983],"about_ca_topic_score_codex":0.0005282406,"about_ca_topic_score_gemma":0.0012775417,"teacher_disagreement_score":0.55042416,"about_ca_system_score_codex":0.00051160395,"about_ca_system_score_gemma":0.00027265414,"threshold_uncertainty_score":0.63733304},"labels":[],"label_agreement":null},{"id":"W7162134529","doi":"10.82308/32610","title":"Effects of sparse follow-up on marginal structural models for time-to-event data","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"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":"Missing data; Imputation (statistics); Proportional hazards model; Logistic regression; Confidence interval; Hazard ratio; Regression; Interval (graph theory)","score_opus":0.1386876719470322,"score_gpt":0.4221087123016835,"score_spread":0.2834210403546513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162134529","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":[0.22967468,0.00031538232,0.71333903,0.00008436156,0.002126769,0.015022264,0.0016715077,0.0014161316,0.036349848],"genre_scores_gemma":[0.38740504,0.000019785839,0.4808667,0.00011112272,0.00038165672,0.00087532547,0.008610815,0.00037453047,0.121355034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983091,0.000037696573,0.00046995678,0.000446083,0.00037360602,0.0003636096],"domain_scores_gemma":[0.9974691,0.00078967505,0.00038217197,0.0010539585,0.00018671635,0.00011837533],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024507078,0.00040771958,0.0006671277,0.00016979995,0.000043901564,0.000016008607,0.000726873,0.00029850475,0.00030256892],"category_scores_gemma":[0.0005016517,0.00033976923,0.00012991171,0.00008836772,0.000016043272,0.00029137862,0.000113313734,0.00021105513,0.000052065887],"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":[0.0035914164,0.0006188367,0.000007883034,0.013774448,0.00077763066,0.000009359336,0.001879431,0.00020598774,0.048223402,0.7401904,0.12362941,0.06709178],"study_design_scores_gemma":[0.0009923431,0.00070516294,0.000099992234,0.0013848128,0.0006175869,0.0000024399144,0.00009735142,0.008630123,0.1825704,0.803085,0.00087604986,0.0009386908],"about_ca_topic_score_codex":0.000017941753,"about_ca_topic_score_gemma":0.000055596956,"teacher_disagreement_score":0.23247236,"about_ca_system_score_codex":0.000080568374,"about_ca_system_score_gemma":0.000069085894,"threshold_uncertainty_score":0.9999054},"labels":[],"label_agreement":null},{"id":"W836196718","doi":"10.1007/s10985-015-9335-y","title":"Does Cox analysis of a randomized survival study yield a causal treatment effect?","year":2015,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":211,"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 Waterloo","funders":"","keywords":"Censoring (clinical trials); Statistics; Estimator; Econometrics; Causal inference; Proportional hazards model; Confounding; Regression; Inference; Randomized controlled trial; Survival analysis; Mathematics; Regression analysis; Randomized experiment; Hazard ratio; Computer science; Medicine; Confidence interval; Internal medicine; Artificial intelligence","score_opus":0.17248744099221144,"score_gpt":0.43685139860711714,"score_spread":0.2643639576149057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W836196718","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":[0.6739802,0.00018105886,0.31596482,0.000192602,0.00017564422,0.0036749868,0.0037122087,0.0007567296,0.0013617976],"genre_scores_gemma":[0.98687696,0.000040765844,0.010445746,0.000015010217,0.000057925823,0.00022702581,0.0016936439,0.000032246706,0.0006106965],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99528617,0.0014267185,0.0012382756,0.000837613,0.00086479314,0.00034640866],"domain_scores_gemma":[0.9892749,0.005908422,0.00072998833,0.0035713848,0.0002794345,0.00023587502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004699356,0.00046029792,0.004391096,0.0013832728,0.00006050034,0.00006700602,0.0009493832,0.00012670182,0.00041036314],"category_scores_gemma":[0.0060924413,0.00024335313,0.0009476576,0.0041951956,0.00017971765,0.0002961178,0.00047519148,0.00013760926,0.000015779462],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03474439,0.008237163,0.3427926,0.00012420616,0.5937582,0.00021757037,0.007479275,0.0018484733,0.00043221025,0.005150201,0.002681506,0.0025342102],"study_design_scores_gemma":[0.0731444,0.0023392092,0.002420574,0.0000576115,0.78021276,0.0000014926419,0.003196549,0.120965704,0.0031181802,0.012786132,0.00029330645,0.0014640813],"about_ca_topic_score_codex":0.004095732,"about_ca_topic_score_gemma":0.006113836,"teacher_disagreement_score":0.34037203,"about_ca_system_score_codex":0.00012883316,"about_ca_system_score_gemma":0.0000769425,"threshold_uncertainty_score":0.99236524},"labels":[],"label_agreement":null},{"id":"W939145883","doi":"10.1093/biostatistics/kxw049","title":"Inequality in treatment benefits: Can we determine if a new treatment benefits the many or the few?","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"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 Neurological Disorders and Stroke; Patient-Centered Outcomes Research Institute; U.S. Food and Drug Administration; National Institute on Aging; National Institutes of Health; Hamilton Health Sciences Foundation","keywords":"Randomized controlled trial; Estimator; Fraction (chemistry); Computer science; Statistics; Econometrics; Randomized response; Outcome (game theory); Mathematics; Medicine; Mathematical optimization; Mathematical economics","score_opus":0.2502387195907997,"score_gpt":0.4054696846381312,"score_spread":0.15523096504733153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W939145883","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":[0.59969634,0.0027699014,0.28918976,0.07818333,0.0010802641,0.0119621195,0.013507704,0.001963117,0.0016474839],"genre_scores_gemma":[0.89044607,0.0068498976,0.09357225,0.00048885855,0.00032784388,0.00059252995,0.000039095383,0.00013046752,0.007553008],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982081,0.00014635973,0.0005736999,0.00034972493,0.0002588545,0.000463231],"domain_scores_gemma":[0.9957225,0.0028930723,0.00025859944,0.000920674,0.000077241006,0.00012794306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021497897,0.0004007481,0.00041384925,0.00006667107,0.00013929348,0.000048530597,0.00033672148,0.00010943891,0.00013297715],"category_scores_gemma":[0.000755597,0.00013903064,0.00007307849,0.00021514262,0.00014290062,0.00006763846,0.00009097594,0.000083575884,0.000025585468],"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":[0.00012329694,0.0003348755,0.0013006963,0.000024572204,0.000072144685,0.000049558508,0.0019692737,0.000006724904,0.00021145157,0.21639727,0.001642969,0.7778672],"study_design_scores_gemma":[0.0060455995,0.0056861388,0.013727851,0.0011017014,0.0005380912,0.0001240198,0.00129407,0.00051194814,0.033937495,0.8852222,0.050303027,0.0015078353],"about_ca_topic_score_codex":0.0009943891,"about_ca_topic_score_gemma":0.012356794,"teacher_disagreement_score":0.7763593,"about_ca_system_score_codex":0.00078899553,"about_ca_system_score_gemma":0.00023295953,"threshold_uncertainty_score":0.6895381},"labels":[],"label_agreement":null},{"id":"W980728949","doi":"10.59170/stattrans-2013-016","title":"The effect of unemployment benefits on labour market behaviour in Luxembourg","year":2013,"lang":"en","type":"article","venue":"Statistics in Transition New Series","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":"Canadian Institute for International Peace and Security","funders":"","keywords":"Unemployment; Spell; Economics; Labour economics; Term (time); Demographic economics; Macroeconomics; Sociology","score_opus":0.030547993004667963,"score_gpt":0.3382962802949004,"score_spread":0.3077482872902324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W980728949","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":[0.94863784,0.00006971813,0.0465744,0.001057718,0.00015499836,0.0016670999,0.0005321898,0.0001483027,0.001157712],"genre_scores_gemma":[0.952812,0.00016875938,0.046215583,0.000043871147,0.000018635901,0.00013297155,0.000016752569,0.000032572167,0.0005588373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874246,0.00017295007,0.0004420176,0.0001613134,0.00024207479,0.00023919003],"domain_scores_gemma":[0.99802476,0.0015022397,0.000114162605,0.00024457474,0.000066315195,0.000047963662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038095601,0.00017744664,0.0002730893,0.00009917491,0.000052904474,0.000030831077,0.00013560367,0.00007639278,0.00024039528],"category_scores_gemma":[0.00035462118,0.00013497037,0.000028376817,0.00017401404,0.00010346581,0.00015039397,0.000015186299,0.00021011876,0.000006368378],"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":[0.00046532106,0.00013570393,0.0038460174,0.00032950327,0.000021818341,0.000022804668,0.0015512697,0.00031241373,0.00069237925,0.9613404,0.008561229,0.02272113],"study_design_scores_gemma":[0.00084343384,0.0011662955,0.02429375,0.00037076932,0.000019982333,0.0000044686226,0.00026803685,0.00013547737,0.03938033,0.9332065,0.0000850505,0.00022591412],"about_ca_topic_score_codex":0.0003332353,"about_ca_topic_score_gemma":0.0014738524,"teacher_disagreement_score":0.038687952,"about_ca_system_score_codex":0.000074656105,"about_ca_system_score_gemma":0.000026846043,"threshold_uncertainty_score":0.55039316},"labels":[],"label_agreement":null}]}