{"meta":{"query_hash":"f56fee51e210","filters":{"venue":"Journal of Clinical Epidemiology"},"cohort_total":1510,"direct_labels_cover":96,"predictions_cover":1510,"exported":1510,"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/f56fee51e210","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Clinical+Epidemiology"},"results":[{"id":"W1119174984","doi":"10.1016/j.jclinepi.2015.05.035","title":"Twelve recommendations for integrating existing systematic reviews into new reviews: EPC guidance","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Systematic review; Medicine; Medical physics; MEDLINE; Political science","score_opus":0.9805733784609232,"score_gpt":0.7447820311222758,"score_spread":0.23579134733864737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1119174984","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":[0.0003709709,0.074264675,0.88370275,0.031498995,0.0044622533,0.0027210554,0.000003553167,0.0000049398413,0.0029707782],"genre_scores_gemma":[0.002003805,0.00512023,0.9692837,0.010809299,0.0032804245,0.00012748179,0.0000058693427,0.000026018804,0.009343179],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.44205704,0.33778617,0.21487615,0.0016377129,0.0028367187,0.00080624444],"domain_scores_gemma":[0.07218708,0.66503465,0.24612297,0.005827638,0.008685541,0.0021421094],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.87176293,0.00045109694,0.031308427,0.0003461708,0.00015079473,0.0001887022,0.0029826553,0.0003210037,0.00068998826],"category_scores_gemma":[0.9856844,0.00018642412,0.009854549,0.0009364636,0.00013049645,0.00043838588,0.00017362589,0.00091459637,0.0015479384],"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":[0.000020572808,0.000044703174,0.0073967073,0.001681047,0.00017785723,0.0000013476453,0.0003022898,0.000030568073,0.0000013232101,0.0061829975,0.8984005,0.08576009],"study_design_scores_gemma":[0.00045513173,0.0003539943,0.00020950465,0.00681347,0.0005488354,0.00007857042,0.00051290845,0.0046168556,3.2354924e-7,0.12776318,0.85848194,0.000165265],"about_ca_topic_score_codex":0.000019093883,"about_ca_topic_score_gemma":0.000048841874,"teacher_disagreement_score":0.36986995,"about_ca_system_score_codex":0.00009859801,"about_ca_system_score_gemma":0.0004863676,"threshold_uncertainty_score":0.9992295},"labels":[],"label_agreement":null},{"id":"W112070606","doi":"10.1016/s0895-4356(00)00225-0","title":"The association between exposure to a rear-end collision and future neck or shoulder pain:","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Older Adults Driving Studies","field":"Health Professions","cited_by":93,"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":"Whiplash; Medicine; Neck pain; Physical therapy; Population; Motor vehicle crash; Injury prevention; Poison control; Cohort study; Crash; Relative risk; Physical medicine and rehabilitation; Internal medicine; Emergency medicine; Confidence interval; Pathology; Environmental health","score_opus":0.2513638326144226,"score_gpt":0.552866372814577,"score_spread":0.3015025402001544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W112070606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74729913,0.0006224425,0.00019483248,0.24885891,0.0017574778,0.00035462365,0.000009815882,0.000019208417,0.00088355795],"genre_scores_gemma":[0.8305098,0.033302967,0.007210834,0.06633219,0.035840943,0.00004906845,0.0000053203603,0.00007245545,0.026676463],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9763899,0.018016297,0.0044312705,0.0002595247,0.0002932855,0.0006097364],"domain_scores_gemma":[0.83695805,0.159702,0.0022998636,0.00025055872,0.00044783988,0.00034169853],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06479022,0.000169944,0.0018114778,0.000050977265,0.00081001705,0.000008346267,0.00028240567,0.0007599272,0.00034442157],"category_scores_gemma":[0.14939727,0.00008417099,0.0002646871,0.00017614612,0.00011032321,0.00009210115,0.00010585589,0.0022709682,0.00008677069],"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":[0.00024912748,0.000024119025,0.73783404,0.000019889212,0.00015548403,0.0000048232023,0.00037937553,0.000010883281,2.4425924e-7,0.000064641645,0.18677397,0.07448344],"study_design_scores_gemma":[0.0007101906,0.00088449044,0.5920902,0.00013618282,0.000052218544,0.0000028342176,0.00038929045,0.000013465612,6.6116264e-8,0.0011240307,0.40454167,0.000055377077],"about_ca_topic_score_codex":0.00002829698,"about_ca_topic_score_gemma":0.0003247919,"teacher_disagreement_score":0.21776772,"about_ca_system_score_codex":0.0001229588,"about_ca_system_score_gemma":0.00026709025,"threshold_uncertainty_score":0.98663527},"labels":[],"label_agreement":null},{"id":"W113797418","doi":"10.1016/s0895-4356(99)00206-1","title":"Methods for assessing responsiveness","year":2000,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1470,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Toronto; University of Waterloo","funders":"Medical Research Council","keywords":"Measure (data warehouse); Interpretation (philosophy); Medicine; Econometrics; Statistics; Computer science; Mathematics; Data mining","score_opus":0.9429768462523852,"score_gpt":0.7649698748019254,"score_spread":0.17800697145045985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W113797418","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":[0.0000070038964,0.84310645,0.14085954,0.009684587,0.0048659514,0.00073344115,0.000113748276,0.000012029852,0.0006172688],"genre_scores_gemma":[4.075716e-7,0.750371,0.23641874,0.008941501,0.003762604,0.000055436925,0.00002181807,0.000065080865,0.00036341726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8698812,0.053944666,0.07424815,0.001003718,0.00007608351,0.00084619044],"domain_scores_gemma":[0.48340353,0.44427317,0.0705972,0.0008450088,0.00028734998,0.0005937232],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5423663,0.00047670363,0.028367909,0.0007975267,0.00014637725,0.000044994613,0.0009915516,0.001838817,0.00045814549],"category_scores_gemma":[0.5745836,0.00044240183,0.0050064223,0.00023408752,0.00025724067,0.00039355955,0.00007111151,0.0017836222,0.00048337821],"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":[0.000058469304,0.00010082382,0.00043645396,0.0078220535,0.0005781566,0.0000030613014,0.000024105504,0.000022675249,1.2165868e-9,0.025054803,0.02606801,0.9398314],"study_design_scores_gemma":[0.00056259026,0.00025779696,0.00026391432,0.004580615,0.00022250769,0.00011400427,0.000019140725,0.00023410424,3.476674e-9,0.07285576,0.9205609,0.00032865154],"about_ca_topic_score_codex":0.000020542868,"about_ca_topic_score_gemma":0.0000018451061,"teacher_disagreement_score":0.9395027,"about_ca_system_score_codex":0.00043625408,"about_ca_system_score_gemma":0.0021071667,"threshold_uncertainty_score":0.99980277},"labels":[],"label_agreement":null},{"id":"W1145945895","doi":"10.1016/j.jclinepi.2015.05.036","title":"A taxonomy of rapid reviews links report types and methods to specific decision-making contexts","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":77,"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":"University of Alberta; Agency for Healthcare Research and Quality; Johns Hopkins University; University of Pennsylvania","keywords":"Categorization; Systematic review; Computer science; Data science; Management science; MEDLINE; Artificial intelligence; Biology","score_opus":0.9552108165864013,"score_gpt":0.7436871260479803,"score_spread":0.21152369053842102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1145945895","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007284007,0.7791947,0.21504852,0.00038442342,0.0025566223,0.0014451442,0.000008876686,0.0000013477243,0.001353075],"genre_scores_gemma":[0.0000024184235,0.6051494,0.39285472,0.0005466516,0.00093281385,0.000025458765,0.0000014873436,0.000018481725,0.0004685629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3411255,0.40449834,0.2469136,0.002767902,0.003939248,0.00075540564],"domain_scores_gemma":[0.072959535,0.6337842,0.27938315,0.006709473,0.005771877,0.0013917987],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.88702184,0.0008384952,0.097543135,0.0012249554,0.00006216318,0.00012390706,0.0036787263,0.0016694448,0.0029044638],"category_scores_gemma":[0.9409749,0.00033946967,0.019398052,0.0015152434,0.00036171085,0.00017026413,0.00062246015,0.002748101,0.0008032458],"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":[0.000025600142,0.00004052912,0.0005804397,0.0008138199,0.0005353167,0.00006246443,0.00001159804,0.0000030503065,1.358528e-8,0.0002643801,0.20187996,0.7957828],"study_design_scores_gemma":[0.00015638482,0.00040120006,0.00021878675,0.011617062,0.002003776,0.0015845519,0.000015640664,0.000025226367,8.141921e-9,0.013631399,0.97009546,0.00025052315],"about_ca_topic_score_codex":0.0000014827068,"about_ca_topic_score_gemma":0.0000027230972,"teacher_disagreement_score":0.7955323,"about_ca_system_score_codex":0.000064147534,"about_ca_system_score_gemma":0.0009360721,"threshold_uncertainty_score":0.9999747},"labels":[],"label_agreement":null},{"id":"W12233365","doi":"10.1016/s0895-4356(01)00453-x","title":"Benzodiazepine use and risk of dementiaA nested case–control study","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":127,"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; Jewish General Hospital","funders":"Fondation pour la Recherche Médicale","keywords":"Dementia; Odds ratio; Medicine; Nested case-control study; Confidence interval; Risk factor; Psychiatry; Benzodiazepine; Case-control study; Internal medicine; Disease","score_opus":0.2804106596273408,"score_gpt":0.5061870195001055,"score_spread":0.22577635987276468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W12233365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99427783,0.0011440513,0.0019259743,0.0018376583,0.00023771808,0.00046170145,0.000015350608,0.0000056713347,0.000094017116],"genre_scores_gemma":[0.99334866,0.0030674606,0.0020335657,0.0009733259,0.00038491495,0.0000040151517,6.874536e-7,0.000011402434,0.0001759419],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9887337,0.0064812084,0.0039166505,0.0002424003,0.00028237776,0.0003436834],"domain_scores_gemma":[0.97227603,0.024151113,0.0021993746,0.00023389168,0.0006700172,0.00046959982],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023262914,0.00015019978,0.0023266142,0.000199032,0.000053768916,0.000007063826,0.00009836018,0.00017304266,0.00080428127],"category_scores_gemma":[0.0832879,0.000099582525,0.00048474988,0.00013990945,0.00032934156,0.0001412958,0.00005953165,0.00093699933,0.000011077068],"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":[0.00091111707,0.0018613172,0.95389897,0.0000278282,0.0016474857,0.002063568,0.000047394587,0.0000070016035,0.000023360773,0.000025024246,0.0012925587,0.038194392],"study_design_scores_gemma":[0.011267738,0.011532596,0.970654,0.00005806996,0.0017824336,0.0024345824,0.00018909694,0.0011383605,0.000008964414,0.00022373554,0.00064112706,0.00006928904],"about_ca_topic_score_codex":0.00007378294,"about_ca_topic_score_gemma":0.000027746413,"teacher_disagreement_score":0.060024988,"about_ca_system_score_codex":0.000012532201,"about_ca_system_score_gemma":0.000052286607,"threshold_uncertainty_score":0.92443395},"labels":[],"label_agreement":null},{"id":"W12348700","doi":"10.1016/s0895-4356(01)00393-6","title":"Problems of HRQL assessment","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; University of Alberta","funders":"","keywords":"Medicine; Irritable bowel syndrome; Quality of life (healthcare); Affect (linguistics); Polycystic ovary; Variance (accounting); Analysis of variance; Clinical psychology; Psychology; Psychiatry; Obesity; Internal medicine","score_opus":0.8519738424354913,"score_gpt":0.6524841347330493,"score_spread":0.199489707702442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W12348700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6786535,0.0052149477,0.08922165,0.2065274,0.0046435264,0.00045685153,0.00004828938,0.000017201117,0.015216669],"genre_scores_gemma":[0.92254335,0.0044250716,0.043120682,0.02726216,0.0021146864,0.000010107697,0.000004893632,0.00002635055,0.00049267005],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96388155,0.004479211,0.030805424,0.00033857775,0.00009239901,0.00040282978],"domain_scores_gemma":[0.930695,0.040137827,0.028130509,0.0004349299,0.0002424575,0.00035928964],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22302274,0.00014319397,0.0048126425,0.0002641491,0.00004778636,0.0000065819218,0.0004277578,0.00035394414,0.0007195928],"category_scores_gemma":[0.13573319,0.00013911055,0.00074762304,0.00014097537,0.00021169244,0.00025951036,0.000052043055,0.0006872836,0.0002606624],"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":[0.000042661934,0.00023993308,0.8514527,0.000110787034,0.00015536834,0.0000030782787,0.00007248128,0.00084678055,9.519049e-7,0.12035349,0.025694722,0.0010270096],"study_design_scores_gemma":[0.0015986902,0.0008413552,0.59521925,0.00014602467,0.000016268332,0.00007114463,0.0001182429,0.0037731673,4.1854236e-7,0.19430415,0.20375508,0.00015620382],"about_ca_topic_score_codex":0.0001273846,"about_ca_topic_score_gemma":0.00002599569,"teacher_disagreement_score":0.25623348,"about_ca_system_score_codex":0.00014416878,"about_ca_system_score_gemma":0.00033785196,"threshold_uncertainty_score":0.8715469},"labels":[],"label_agreement":null},{"id":"W1414339606","doi":"10.1016/j.jclinepi.2015.05.023","title":"An analysis of protocols and publications suggested that most discontinuations of clinical trials were not based on preplanned interim analyses or stopping rules","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Interim; Interim analysis; Clinical trial; Medicine; Medical physics; Political science; Internal medicine; Law","score_opus":0.991223332521523,"score_gpt":0.818548953030905,"score_spread":0.17267437949061792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1414339606","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":[0.0040622796,0.7291369,0.20162088,0.009909052,0.002796555,0.04689506,0.004259522,0.000028286478,0.0012914662],"genre_scores_gemma":[0.006055161,0.9289081,0.057009704,0.0015577908,0.00170774,0.0022233182,0.00064597384,0.000102045655,0.0017901503],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.430344,0.40299687,0.16088872,0.001752638,0.0036028195,0.00041497304],"domain_scores_gemma":[0.14179146,0.58895916,0.2558194,0.006016278,0.0063381474,0.0010755254],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8214358,0.0007609502,0.10036721,0.0035171947,0.00008941505,0.00023030391,0.0039223516,0.0012836105,0.0023584978],"category_scores_gemma":[0.9247692,0.0002999809,0.02588134,0.0032340034,0.0007513938,0.00046628344,0.00021848203,0.0015751366,0.00003103316],"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":[0.0006882554,0.0013721256,0.06725593,0.0016776564,0.017011413,0.0000061682517,0.000043403914,0.00062099774,4.105595e-7,0.00089562853,0.0153761385,0.8950519],"study_design_scores_gemma":[0.0016285438,0.003246305,0.0411108,0.0075731743,0.06142759,0.000027493841,0.00026298154,0.03848413,3.0660888e-7,0.0012184045,0.84452945,0.0004908155],"about_ca_topic_score_codex":0.000018926346,"about_ca_topic_score_gemma":0.000091251786,"teacher_disagreement_score":0.89456105,"about_ca_system_score_codex":0.00004353274,"about_ca_system_score_gemma":0.0024793195,"threshold_uncertainty_score":0.9999452},"labels":[],"label_agreement":null},{"id":"W1415646865","doi":"10.1016/j.jclinepi.2015.08.024","title":"Enriched administrative data can be used to retrospectively identify all known cases of primary subarachnoid hemorrhage","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Intracranial Aneurysms: Treatment and Complications","field":"Medicine","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":"Hôpital de l'Enfant-Jésus; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Subarachnoid hemorrhage; Diagnosis code; Aneurysm; Retrospective cohort study; Radiology; Surgery; Population","score_opus":0.5117188084794448,"score_gpt":0.5205041157035374,"score_spread":0.008785307224092542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1415646865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94727236,0.0003793258,0.0014341996,0.048776604,0.00054384064,0.00033350298,0.0001257316,0.000017548218,0.0011168747],"genre_scores_gemma":[0.97652787,0.00004883478,0.01673268,0.0053151846,0.00086503354,0.000005520762,0.000107865024,0.00001723092,0.00037979652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99424165,0.0013208779,0.0033935227,0.0004045808,0.0003211631,0.00031820982],"domain_scores_gemma":[0.9857121,0.009660416,0.002270109,0.0007887889,0.0008210262,0.0007475415],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008213201,0.00020667272,0.0024897372,0.00013453097,0.000039090955,0.000005982512,0.0005440454,0.0002678821,0.00006730021],"category_scores_gemma":[0.059168305,0.00014775894,0.0003778236,0.00021510241,0.00029493283,0.00012726434,0.00017782804,0.00075850927,0.000021878952],"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":[0.009615154,0.004745212,0.91618085,0.00017664176,0.0010754056,0.0034793122,0.0007890167,0.000021131314,0.0047522984,0.006777712,0.04066526,0.011722024],"study_design_scores_gemma":[0.00444516,0.0105806105,0.9695034,0.000046301,0.0010168008,0.0034757634,0.00030205937,0.00022143983,0.00022434694,0.0055295154,0.004447684,0.00020689786],"about_ca_topic_score_codex":0.00013858116,"about_ca_topic_score_gemma":0.00015071442,"teacher_disagreement_score":0.05332259,"about_ca_system_score_codex":0.00012826832,"about_ca_system_score_gemma":0.0009703387,"threshold_uncertainty_score":0.9487567},"labels":[],"label_agreement":null},{"id":"W1454775445","doi":"10.1016/j.jclinepi.2015.09.006","title":"A number of factors explain why WHO guideline developers make strong recommendations inconsistent with GRADE guidance","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"St. Joseph’s Healthcare Hamilton; Hamilton Health Sciences; Health Sciences Centre; McMaster University","funders":"World Health Organization","keywords":"Certainty; Grading (engineering); Quality of evidence; Guideline; Medicine; MEDLINE; Evidence-based medicine; Medical education; Psychology; Family medicine; Alternative medicine; Meta-analysis; Political science; Pathology","score_opus":0.6642960561436178,"score_gpt":0.6126113030567385,"score_spread":0.051684753086879254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1454775445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7646907,0.00020077216,0.077264756,0.15531,0.0014145233,0.00038316238,0.000028921588,0.000020367326,0.00068680994],"genre_scores_gemma":[0.62635314,0.000432331,0.35227716,0.01972869,0.00095503085,0.000006061629,0.0000757821,0.000039621114,0.00013216626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98158157,0.003902238,0.0132812,0.00034858665,0.00049637747,0.00039002375],"domain_scores_gemma":[0.9520239,0.035585888,0.008597311,0.0004612161,0.0025151693,0.0008164869],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033442274,0.0002565374,0.0029393937,0.00014823863,0.00004487416,0.000006232531,0.00026352622,0.00031531247,0.0002853167],"category_scores_gemma":[0.2690859,0.00016902527,0.00056691107,0.00028807786,0.00038780668,0.00024351681,0.0001022858,0.0011939915,0.000014332677],"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":[0.0016817079,0.00047514876,0.8639704,0.00002756219,0.0005001537,0.00003704461,0.00014769498,0.00033222532,0.000011428816,0.0007626501,0.12078559,0.011268408],"study_design_scores_gemma":[0.021671243,0.00687503,0.5208999,0.0010246448,0.0015476446,0.0014049674,0.008173179,0.0026021095,0.00007622891,0.005529199,0.4296542,0.0005416649],"about_ca_topic_score_codex":0.0002953454,"about_ca_topic_score_gemma":0.00026077643,"teacher_disagreement_score":0.34307054,"about_ca_system_score_codex":0.00014453904,"about_ca_system_score_gemma":0.0015097864,"threshold_uncertainty_score":0.9952746},"labels":[],"label_agreement":null},{"id":"W1462373416","doi":"10.1016/j.jclinepi.2015.07.010","title":"A principal component analysis is conducted for a case series quality appraisal checklist","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":182,"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; Institute of Health Economics","funders":"Instituto de Salud Carlos III","keywords":"Checklist; Principal component analysis; Delphi method; Quality (philosophy); Series (stratigraphy); Delphi; Statistics; Confounding; Computer science; Psychology; Mathematics; Cognitive psychology","score_opus":0.9595818293892947,"score_gpt":0.7319207375962263,"score_spread":0.22766109179306837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1462373416","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":[0.8254893,0.0006532599,0.15355736,0.017464524,0.0018239816,0.000372835,0.00006992407,0.0000036489073,0.0005652145],"genre_scores_gemma":[0.91684526,0.000039494415,0.076140165,0.003510542,0.0010006212,0.000014872511,0.000010193693,0.000011438486,0.0024274397],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.81877196,0.11016304,0.06708659,0.0009750772,0.0025502832,0.00045304417],"domain_scores_gemma":[0.3012669,0.5532808,0.1223622,0.0059013288,0.014594376,0.0025944142],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7373809,0.00033569155,0.022118604,0.0005197764,0.00010587012,0.00013894607,0.0016370219,0.00039383018,0.0018088551],"category_scores_gemma":[0.87318206,0.0001516698,0.012927261,0.001358879,0.00043749218,0.00030083815,0.00017976681,0.0006730218,0.000211025],"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":[0.000722028,0.00039067148,0.7590719,0.000049346745,0.0068880254,0.0002695361,0.00052552304,0.0008592147,0.000007026626,0.010706014,0.214764,0.0057467166],"study_design_scores_gemma":[0.002887272,0.0013780105,0.20180182,0.000024548988,0.0060884184,0.004026882,0.002358939,0.031276647,0.000004067595,0.050990503,0.69873834,0.00042454104],"about_ca_topic_score_codex":0.00006403192,"about_ca_topic_score_gemma":0.0001702109,"teacher_disagreement_score":0.55727005,"about_ca_system_score_codex":0.000038660408,"about_ca_system_score_gemma":0.00043892526,"threshold_uncertainty_score":0.9991036},"labels":[],"label_agreement":null},{"id":"W1480653276","doi":"10.1016/j.jclinepi.2007.02.004","title":"Letter to the Editor","year":2007,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":73,"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 Health Network; Toronto Western Hospital","funders":"","keywords":"Scopus; Scope (computer science); Medicine; Cochrane collaboration; Clinical Practice; MEDLINE; Alternative medicine; Medical education; Family medicine; Computer science; Political science; Pathology; Law; Cochrane Library","score_opus":0.49316276107536733,"score_gpt":0.5625346945995177,"score_spread":0.06937193352415033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480653276","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":[0.00050681515,0.0009281206,0.0044030035,0.9616001,0.030961875,0.00019970755,0.000006135865,0.000009536238,0.001384675],"genre_scores_gemma":[0.00013342958,0.00017544959,0.0037863983,0.6116125,0.38320175,0.0000017717222,0.0000054776197,0.000019065177,0.0010641663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98962545,0.0027295456,0.0058686407,0.00036130854,0.00070124306,0.0007137928],"domain_scores_gemma":[0.958451,0.036094815,0.0036449824,0.00064790546,0.000705954,0.00045538513],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.040003456,0.0002871789,0.0038304555,0.0001848135,0.000055427357,0.0000086101345,0.0006866026,0.002290873,0.00026184903],"category_scores_gemma":[0.095792845,0.00014737454,0.0018011201,0.00017058212,0.00029223072,0.000051346822,0.00011088521,0.011472267,0.0003295732],"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":[0.0005022086,0.00001835473,0.012238657,0.000032128366,0.00022736742,0.0016002501,0.000011115939,0.000013426636,5.2645515e-7,0.000010940638,0.97865987,0.006685151],"study_design_scores_gemma":[0.00056838844,0.001673411,0.016578155,0.0004234137,0.00030179133,0.00092685735,0.0000065372074,0.00000789266,9.1469775e-7,0.00039398758,0.97898877,0.00012989018],"about_ca_topic_score_codex":0.00003941767,"about_ca_topic_score_gemma":0.000009132887,"teacher_disagreement_score":0.35223988,"about_ca_system_score_codex":0.00009881767,"about_ca_system_score_gemma":0.00047019124,"threshold_uncertainty_score":0.99900436},"labels":[],"label_agreement":null},{"id":"W1487942018","doi":"","title":"Developing and Testing a Tool for the Classification of Study Designs in Systematic Reviews of Interventions and Exposures","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Inter-rater reliability; Reliability (semiconductor); Psychological intervention; Systematic review; Computer science; Clinical study design; Test (biology); Medicine; Kappa; Classification scheme; Medical physics; MEDLINE; Data mining; Machine learning; Statistics; Clinical trial; Mathematics; Rating scale; Pathology; Nursing","score_opus":0.9825422283967272,"score_gpt":0.7296947615825049,"score_spread":0.2528474668142223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1487942018","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8001317,0.002848288,0.19396405,0.0011677571,0.0002644553,0.0016076636,0.0000010180559,3.302775e-7,0.000014774535],"genre_scores_gemma":[0.9229505,0.00025268696,0.07658375,0.000085101,0.000057187623,0.000041723764,8.34745e-8,0.0000027728868,0.000026205464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.76435155,0.1254419,0.10806274,0.0006660755,0.0012170491,0.00026068388],"domain_scores_gemma":[0.13474359,0.7877382,0.07354495,0.0015055023,0.0023588557,0.00010891319],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6908246,0.000112376074,0.008662137,0.00020708425,0.000044670745,0.000028984472,0.00064698845,0.00009899346,0.00003950362],"category_scores_gemma":[0.91196066,0.000040784416,0.0014344804,0.00035625516,0.00016333134,0.000091906,0.00006688717,0.00031913174,0.000001975],"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":[0.000017063488,0.00010493491,0.9709633,0.0026977705,0.00017386676,3.6063346e-7,0.00020148052,0.000012807172,0.00009468644,0.0039710365,0.00031102708,0.02145165],"study_design_scores_gemma":[0.0003659988,0.00045938572,0.97372776,0.0019020928,0.00048490035,0.0000282535,0.00089718634,0.00600557,0.0000012030307,0.015802149,0.00027933856,0.000046135774],"about_ca_topic_score_codex":0.000005244446,"about_ca_topic_score_gemma":0.00008905894,"teacher_disagreement_score":0.6622963,"about_ca_system_score_codex":0.0000047173676,"about_ca_system_score_gemma":0.000074914584,"threshold_uncertainty_score":0.59212637},"labels":[],"label_agreement":null},{"id":"W1510288999","doi":"10.1016/j.jclinepi.2015.05.004","title":"CONSORT extension for reporting N-of-1 trials (CENT) 2015 Statement","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":142,"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 Ottawa; Children's Hospital of Eastern Ontario; Ottawa Hospital; PolicyWise for Children & Families; University of Alberta","funders":"Faculty of Medicine and Dentistry, University of Alberta; Health Canada; Medical Research Council; Tufts University School of Medicine; University of Toronto; University of Ottawa; Fondation pour la Recherche Médicale; National Health and Medical Research Council; Ministry of Advanced Education, Government of Alberta; Cancer Research UK; Office of Science; Pfizer; Ottawa Hospital Research Institute; University of Alberta; Brown University","keywords":"Consolidated Standards of Reporting Trials; Checklist; Clinical trial; Medicine; CLARITY; Research design; Medical physics; Family medicine; Psychology; Statistics; Internal medicine; Mathematics","score_opus":0.9927653651543608,"score_gpt":0.7998251263897146,"score_spread":0.19294023876464617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510288999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.437264,0.00524498,0.521614,0.025713539,0.007673037,0.0012929006,0.000019248413,0.0000029999494,0.0011752851],"genre_scores_gemma":[0.7021507,0.00061359024,0.2886136,0.0034658257,0.0022838023,0.000015737536,0.0000058570527,0.000021871814,0.0028290113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.19152604,0.28998712,0.51073664,0.0013893628,0.00566239,0.0006984601],"domain_scores_gemma":[0.020410229,0.49747974,0.46765524,0.0024241046,0.011182768,0.0008479184],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9629849,0.000218264,0.030186262,0.000282058,0.000040549523,0.000042549455,0.0011130188,0.0002650223,0.0009820529],"category_scores_gemma":[0.99194914,0.0000865769,0.009522804,0.00031340605,0.00017713069,0.00016041558,0.00011524106,0.00040072025,0.00014468288],"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":[0.0003319012,0.00013519294,0.260062,0.000027064887,0.0005307699,0.0000150538535,0.000048090133,0.000563133,0.000020016812,0.0018798037,0.6966082,0.03977877],"study_design_scores_gemma":[0.0026361446,0.0014945903,0.056881156,0.00017031077,0.0010751775,0.00018244052,0.0005742931,0.0077786017,0.00001785328,0.21485949,0.7141521,0.0001778286],"about_ca_topic_score_codex":0.000007737545,"about_ca_topic_score_gemma":0.0000045842194,"teacher_disagreement_score":0.26488674,"about_ca_system_score_codex":0.00003011208,"about_ca_system_score_gemma":0.00066290714,"threshold_uncertainty_score":0.99993116},"labels":[],"label_agreement":null},{"id":"W1517002118","doi":"10.1016/s0895-4356(99)00238-3","title":"Canadian Acute Respiratory Illness and Flu Scale (CARIFS)","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Respiratory viral infections research","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Dalhousie University; Hospital for Sick Children; University of Toronto; SickKids Foundation","funders":"","keywords":"Medicine; Construct validity; Respiratory illness; Scale (ratio); Pediatrics; Respiratory system; Psychometrics; Internal medicine; Clinical psychology","score_opus":0.2422085582962583,"score_gpt":0.5395782077448407,"score_spread":0.29736964944858235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517002118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817999,0.0010589776,0.000074525466,0.009650227,0.0004947951,0.00016653548,0.0000080732725,0.000011475967,0.0067355176],"genre_scores_gemma":[0.9587619,0.002401905,0.0017936737,0.03196586,0.0023355237,0.000006830979,0.0000023643474,0.00003608901,0.0026958932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9929892,0.0029418804,0.0030450595,0.00028304438,0.00021618464,0.00052466884],"domain_scores_gemma":[0.99197,0.0051068785,0.0005802593,0.00036730603,0.00036832597,0.0016072502],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017422436,0.0001557649,0.0018886516,0.00034084384,0.00015036047,0.000010985577,0.00018733866,0.00053758,0.0019958045],"category_scores_gemma":[0.016425984,0.000112493995,0.00042534064,0.00024004365,0.0005565096,0.00014999116,0.000030397656,0.0017599036,0.00017243232],"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":[0.00071314437,0.00010736515,0.74697363,0.000022443866,0.0002685716,0.00043874973,0.000025436906,0.000023150726,0.00011747939,0.0002141758,0.025620636,0.22547524],"study_design_scores_gemma":[0.0016887536,0.0021592432,0.5925028,0.000068564616,0.00012078253,0.0008510964,0.00001875294,0.000108873704,0.00003878004,0.0010673022,0.4012666,0.00010844645],"about_ca_topic_score_codex":0.0038822999,"about_ca_topic_score_gemma":0.006113188,"teacher_disagreement_score":0.37564597,"about_ca_system_score_codex":0.00013793605,"about_ca_system_score_gemma":0.0012977757,"threshold_uncertainty_score":0.9989165},"labels":[],"label_agreement":null},{"id":"W1524110242","doi":"10.1016/j.jclinepi.2015.05.018","title":"CONSORT extension for reporting N-of-1 trials (CENT) 2015: explanation and elaboration","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":148,"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; McMaster University; Hospital for Sick Children; University of Toronto; SickKids Foundation; PolicyWise for Children & Families; Children's Hospital of Eastern Ontario; Ottawa Hospital; University of Ottawa","funders":"Faculty of Medicine and Dentistry, University of Alberta; Medical Research Council; Tufts University School of Medicine; Health Canada; Perelman School of Medicine, University of Pennsylvania; Office of Science; International Centre for Diarrhoeal Disease Research, Bangladesh; Sydney Medical School; University of Toronto; Alberta Innovates; University of Oxford; National Health and Medical Research Council; Cancer Research UK; Ministry of Advanced Education, Government of Alberta; McMaster University; Ottawa Hospital Research Institute; Central Michigan University; Fondation pour la Recherche Médicale; University of Ottawa; University of Pennsylvania; University of Alberta; University of California, Davis; Brown University; Hospital for Sick Children; Pfizer","keywords":"Checklist; Consolidated Standards of Reporting Trials; Clinical trial; Medicine; Research design; Protocol (science); Family medicine; Alternative medicine; Medical physics; Psychology; Statistics; Mathematics; Pathology","score_opus":0.9884392205384529,"score_gpt":0.7765456436924317,"score_spread":0.21189357684602117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524110242","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":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5801892,0.0031391126,0.40051726,0.012690884,0.0025326556,0.00059640716,0.000008181119,0.000001599205,0.00032466327],"genre_scores_gemma":[0.8817424,0.00045704108,0.115209386,0.0010718595,0.0010698929,0.0000063918355,0.0000059983718,0.0000079438805,0.00042905417],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.48675662,0.19860278,0.30940345,0.0011553222,0.0036733092,0.00040848562],"domain_scores_gemma":[0.054280408,0.49868608,0.43131918,0.0016439912,0.013448574,0.00062177196],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91249305,0.00013774076,0.014829796,0.0002533888,0.000038113496,0.000043171825,0.00039341973,0.0002460461,0.00018470436],"category_scores_gemma":[0.98762757,0.000059139868,0.0026103358,0.00027256948,0.00011245821,0.00023609548,0.000043411263,0.00024192773,0.000024940296],"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":[0.0004241708,0.0000959918,0.5378606,0.000036379475,0.00036024183,0.000007583842,0.000113329705,0.00043706698,0.00009445111,0.006873702,0.35851592,0.09518059],"study_design_scores_gemma":[0.0038922294,0.0018154661,0.31914845,0.00023322873,0.0014260169,0.00034123083,0.0011245646,0.038845405,0.00004562904,0.3711597,0.26170975,0.00025835386],"about_ca_topic_score_codex":0.000004391988,"about_ca_topic_score_gemma":0.0000058088567,"teacher_disagreement_score":0.43247622,"about_ca_system_score_codex":0.00001383033,"about_ca_system_score_gemma":0.0003041536,"threshold_uncertainty_score":0.9997961},"labels":[],"label_agreement":null},{"id":"W1551228934","doi":"10.1016/j.jclinepi.2015.09.001","title":"Extending the PRISMA statement to equity-focused systematic reviews (PRISMA-E 2012): explanation and elaboration","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":305,"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; Bruyère; University of Ottawa","funders":"University of Melbourne; Universiteit Stellenbosch; Pan American Health Organization; Hospital for Sick Children; Medical Research Council; London School of Hygiene and Tropical Medicine; Ottawa Hospital Research Institute; Rockefeller Foundation; University of Ottawa; Loyola University Chicago; World Health Organization; Canadian Institutes of Health Research","keywords":"Systematic review; Checklist; Guideline; Elaboration; Equity (law); Transparency (behavior); MEDLINE; Psychology; Accounting; Medicine; Business; Political science","score_opus":0.9661902199576733,"score_gpt":0.7178773149976785,"score_spread":0.2483129049599948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1551228934","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":[0.0801054,0.02964056,0.8072894,0.07391967,0.0040298714,0.003809092,0.000005735998,0.000005407249,0.0011948561],"genre_scores_gemma":[0.71637446,0.016002396,0.2201219,0.034084205,0.004607308,0.00033163882,0.000011104144,0.00006659801,0.008400392],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.565943,0.30879524,0.1181981,0.0011365806,0.0053031077,0.0006239496],"domain_scores_gemma":[0.5566696,0.30394623,0.12722962,0.0043963976,0.006113598,0.0016445935],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.85212433,0.00027238083,0.012084078,0.00033949406,0.00011463617,0.00024697863,0.0015568035,0.00019122024,0.00038252864],"category_scores_gemma":[0.8405932,0.00009589307,0.0017716475,0.00074465433,0.00009476842,0.00048167942,0.0002597934,0.00053572765,0.0009228562],"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":[0.00010976018,0.00012975874,0.03472159,0.0011917845,0.0004906766,0.000013173474,0.0010086255,0.0006154281,0.0000109586035,0.0135685075,0.8175286,0.1306111],"study_design_scores_gemma":[0.0013901722,0.0014725337,0.037723035,0.002385407,0.0012632001,0.00017877792,0.0017804657,0.0153470645,0.0000027595004,0.131253,0.80683273,0.00037085285],"about_ca_topic_score_codex":0.0000048491706,"about_ca_topic_score_gemma":0.000020725154,"teacher_disagreement_score":0.63626903,"about_ca_system_score_codex":0.00007098191,"about_ca_system_score_gemma":0.00018247144,"threshold_uncertainty_score":0.99985504},"labels":[],"label_agreement":null},{"id":"W1590792821","doi":"10.1016/s0895-4356(00)00227-4","title":"Reporting the study populations of clinical trials","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":50,"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; Dalhousie University; McGill University","funders":"Medical Research Council; Medical Research Council Canada; Dalhousie University","keywords":"Clinical trial; Scrutiny; Protocol (science); CLARITY; Medicine; Consolidated Standards of Reporting Trials; MEDLINE; Medical physics; Family medicine; Alternative medicine; Pathology","score_opus":0.9929770802811584,"score_gpt":0.8185548709961677,"score_spread":0.17442220928499064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590792821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973683,0.00067602686,0.0075691435,0.011828792,0.0024536098,0.000634434,0.0000031287886,0.000001584667,0.0031503076],"genre_scores_gemma":[0.9823586,0.00019929915,0.010955061,0.0017986199,0.0018831881,0.0000042064844,5.517926e-7,0.000007289065,0.0027932285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.022592044,0.58398145,0.3889224,0.000809782,0.0033740655,0.00032023824],"domain_scores_gemma":[0.005370457,0.6511006,0.33718842,0.003542051,0.0024184985,0.00037998264],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9779918,0.00022113175,0.03552688,0.00018981298,0.00012320398,0.00006348523,0.0023886648,0.0003227349,0.015880875],"category_scores_gemma":[0.9906691,0.00007115636,0.017611006,0.00074454397,0.00032387555,0.00014662264,0.000098407436,0.0012796207,0.0004545118],"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":[0.00007922479,0.0003107818,0.74978834,0.0000028141287,0.00046647587,0.000010556989,0.000053149353,0.00052171224,2.215723e-7,0.00069179904,0.042958375,0.20511653],"study_design_scores_gemma":[0.0006227841,0.00064641796,0.88617796,0.000027659888,0.00080298365,0.000064203356,0.0004005308,0.0025030507,1.0293845e-7,0.046053413,0.06263892,0.00006198236],"about_ca_topic_score_codex":0.000021933462,"about_ca_topic_score_gemma":0.000030013056,"teacher_disagreement_score":0.20505454,"about_ca_system_score_codex":0.0000069006537,"about_ca_system_score_gemma":0.00028709127,"threshold_uncertainty_score":0.9922274},"labels":[],"label_agreement":null},{"id":"W161603189","doi":"10.1016/s0895-4356(02)00434-1","title":"Total plasma homocysteine level and risk of cardiovascular disease","year":2002,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Folate and B Vitamins Research","field":"Medicine","cited_by":149,"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":"Medicine; Hyperhomocysteinemia; Relative risk; Internal medicine; Cohort; Risk factor; Stroke (engine); Meta-analysis; Disease; Causality (physics); Cohort study; Selection bias; Random effects model; Cardiology; Confidence interval; Pathology","score_opus":0.5213143784069701,"score_gpt":0.5358543770348123,"score_spread":0.014539998627842166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W161603189","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":[0.004808489,0.9935861,0.00018823157,0.0002494328,0.0005403654,0.00037346542,0.00010546217,0.000004908496,0.00014350914],"genre_scores_gemma":[0.00036853063,0.9957543,0.0013076119,0.00004862283,0.0017714406,0.000004891163,0.0000135399805,0.00004058658,0.00069046655],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.984017,0.007376027,0.007214054,0.00044047882,0.0005160162,0.00043639497],"domain_scores_gemma":[0.9691542,0.024638133,0.0039609517,0.00074727734,0.00041416293,0.0010852743],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.024938382,0.0003761177,0.014987116,0.00036144283,0.00003777797,0.0000040449518,0.00027312347,0.000942087,0.00011461969],"category_scores_gemma":[0.101875514,0.00021997123,0.00723485,0.0002175534,0.00062248635,0.00005497706,0.00016904967,0.0030858053,0.00003569972],"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":[0.00030696378,0.00029167478,0.005668354,0.008755259,0.0113347825,0.0008201603,0.000003686111,0.000019825273,1.9827823e-8,0.000029745075,0.0022234719,0.97054607],"study_design_scores_gemma":[0.0023040797,0.0022197368,0.009509211,0.009133824,0.018169602,0.0024473341,0.0000035864546,0.0002952938,4.6410026e-8,0.00009320516,0.9556403,0.00018374715],"about_ca_topic_score_codex":0.00004161087,"about_ca_topic_score_gemma":8.7721827e-7,"teacher_disagreement_score":0.9703623,"about_ca_system_score_codex":0.00004646132,"about_ca_system_score_gemma":0.00068843696,"threshold_uncertainty_score":0.9996364},"labels":[],"label_agreement":null},{"id":"W1669870","doi":"10.1016/s0895-4356(99)00152-3","title":"The UK IBDQ—A British version of the inflammatory bowel disease questionnaire","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":149,"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":"McMaster University","keywords":"Medicine; Cronbach's alpha; Inflammatory bowel disease; Quality of life (healthcare); Intraclass correlation; Reliability (semiconductor); Validity; Crohn's disease; Physical therapy; Disease; Psychometrics; Clinical psychology; Internal medicine; Nursing","score_opus":0.026852941265425007,"score_gpt":0.3547884052298292,"score_spread":0.3279354639644042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1669870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99392045,0.0021850287,0.000086075815,0.0023784565,0.0009876753,0.00012431706,0.000014431245,0.0000035714675,0.00030001768],"genre_scores_gemma":[0.9928352,0.0034321416,0.00009505459,0.0018585698,0.0010605494,0.0000033543467,0.000004263958,0.000014312394,0.00069655525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938069,0.0031041058,0.0024012057,0.0002139504,0.00019721656,0.0002766303],"domain_scores_gemma":[0.9962023,0.0011509316,0.0014946087,0.0005441513,0.00028027775,0.0003277461],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074845986,0.00013401471,0.0004922505,0.000015929689,0.0001797955,0.000009507345,0.0006575648,0.000274112,0.00012787644],"category_scores_gemma":[0.02413734,0.00008497601,0.0009182423,0.0000426921,0.00080322014,0.000007901059,0.000116123905,0.0004594222,0.000018548375],"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":[0.0019390299,0.00009506451,0.9536034,0.000028354432,0.00011380686,0.00008111743,0.000005671651,0.0010409806,0.00011977787,0.0003067076,0.02951506,0.013151061],"study_design_scores_gemma":[0.0008117984,0.00015437671,0.9607102,0.00012237478,0.000058668844,0.000050482544,0.00000834178,0.00011017176,0.000029467423,0.002238808,0.03561534,0.00008995432],"about_ca_topic_score_codex":0.000010319123,"about_ca_topic_score_gemma":0.00005770568,"teacher_disagreement_score":0.016652742,"about_ca_system_score_codex":0.000014899479,"about_ca_system_score_gemma":0.00049328245,"threshold_uncertainty_score":0.98408276},"labels":[],"label_agreement":null},{"id":"W1714052158","doi":"10.1016/s0895-4356(02)00521-8","title":"Clinical epidemiology","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":112,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"McGill University","keywords":"Epidemiology; Clinical epidemiology; Medicine; Critical appraisal; MEDLINE; Alternative medicine; Evidence-based medicine; Family medicine; Pathology; Political science","score_opus":0.5551674225453916,"score_gpt":0.5978644851116488,"score_spread":0.04269706256625716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1714052158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49962386,0.016990311,0.27715948,0.17748278,0.014995159,0.0007707053,0.000004365492,0.00009814256,0.012875199],"genre_scores_gemma":[0.8274838,0.036846925,0.050211634,0.07019816,0.012288261,0.000007586807,0.000007694115,0.00004612114,0.0029098266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9085987,0.0735016,0.016404908,0.0005008916,0.00027980533,0.0007140545],"domain_scores_gemma":[0.93626696,0.055575944,0.0055305734,0.0006567412,0.0005568323,0.0014129399],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26920846,0.00019721429,0.0065534753,0.00015580065,0.000061652754,0.0000017180458,0.00023129245,0.0011167716,0.0018702014],"category_scores_gemma":[0.34445024,0.000137733,0.004720313,0.00015986888,0.0005054198,0.00009025842,0.000060049275,0.0028066055,0.00063236634],"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":[0.00010536061,0.0005508168,0.543288,0.000060082682,0.0004449392,0.000106645275,0.000009157425,0.000011344826,0.0000010249399,0.0012989767,0.0392382,0.41488543],"study_design_scores_gemma":[0.0037270293,0.0028027094,0.75283086,0.00015979452,0.00028581187,0.0018321088,0.000012009006,0.0011791671,5.3111256e-7,0.007179191,0.22989343,0.000097337215],"about_ca_topic_score_codex":0.0000054643056,"about_ca_topic_score_gemma":0.0000013389647,"teacher_disagreement_score":0.4147881,"about_ca_system_score_codex":0.00004683501,"about_ca_system_score_gemma":0.00018440202,"threshold_uncertainty_score":0.99949396},"labels":[],"label_agreement":null},{"id":"W1733180905","doi":"10.1016/j.jclinepi.2015.09.003","title":"Senior GRADE methodologists encounter challenges as part of WHO guideline development panels: an inductive content analysis","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":22,"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; McMaster University","funders":"","keywords":"CLARITY; Content analysis; Grading (engineering); Psychology; MEDLINE; Medical education; Medicine; Political science; Sociology; Social science","score_opus":0.983259730561551,"score_gpt":0.8039201376495378,"score_spread":0.17933959291201318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1733180905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84959596,0.000366447,0.038364828,0.10778936,0.0027805052,0.0004804588,0.000023190256,0.000019310659,0.00057993026],"genre_scores_gemma":[0.59566367,0.0026212756,0.29935968,0.09831225,0.0034225397,0.00006162375,0.000012522081,0.00003306257,0.00051335513],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9273526,0.05485172,0.015883347,0.00046138704,0.00062695134,0.0008239861],"domain_scores_gemma":[0.88392216,0.09645734,0.01403579,0.0005661454,0.003458106,0.0015604555],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21935767,0.00022334486,0.003956756,0.0004688495,0.00015444044,0.00000249948,0.00063822523,0.00057716406,0.00033485433],"category_scores_gemma":[0.3459704,0.00014904304,0.00047113516,0.00046823846,0.0004848051,0.00028803313,0.00018393362,0.0015713196,0.00005987722],"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":[0.0010098233,0.00037425273,0.8864335,0.00012018647,0.0015882204,0.00003123757,0.025293438,0.00030435863,0.000041133902,0.004652941,0.027475815,0.052675117],"study_design_scores_gemma":[0.0028290998,0.0020691298,0.6506338,0.0001399592,0.00034398306,0.000024693818,0.019668592,0.00030637873,0.00003768512,0.010210576,0.31351376,0.00022236165],"about_ca_topic_score_codex":0.0005280153,"about_ca_topic_score_gemma":0.0005821906,"teacher_disagreement_score":0.28603792,"about_ca_system_score_codex":0.00023223259,"about_ca_system_score_gemma":0.0036485838,"threshold_uncertainty_score":0.8038356},"labels":[],"label_agreement":null},{"id":"W173882147","doi":"10.1016/s0895-4356(01)00508-x","title":"The effect of patient selection on comorbidity-adjusted operative mortality risk","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","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":"Institute of Health Services and Policy Research; University of Toronto; Toronto General Hospital","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Comorbidity; Medicine; Relative risk; Internal medicine; Demography; Confidence interval","score_opus":0.1790010153794394,"score_gpt":0.4825397720481519,"score_spread":0.3035387566687125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W173882147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990991,0.00055203715,0.000112907874,0.004997105,0.0008070219,0.0002244114,0.0000020113991,0.0000073175866,0.002306185],"genre_scores_gemma":[0.9951336,0.002720494,0.00017098647,0.0012342108,0.00053722126,0.0000031420973,8.958226e-7,0.000008523576,0.00019096653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98373497,0.012457765,0.003116707,0.00016858138,0.0002904829,0.00023146921],"domain_scores_gemma":[0.89606726,0.101194374,0.00206096,0.00022084398,0.00022123841,0.00023529967],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02051286,0.00015098379,0.0031606914,0.000053258347,0.00009135844,0.0000031970803,0.00010342785,0.00027166848,0.00010843732],"category_scores_gemma":[0.10817382,0.00006904001,0.0017241617,0.00012763162,0.0003326758,0.00003238777,0.000018510504,0.00121617,0.00002099883],"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":[0.001760377,0.00017315122,0.9584153,0.000015234746,0.00051045313,0.000053290358,0.000032611875,0.00023764235,0.0000048823795,0.00088488613,0.0025153065,0.035396855],"study_design_scores_gemma":[0.0024980628,0.013461151,0.9492426,0.0000673071,0.0004690826,0.00023765917,0.000021847203,0.0012521638,0.0001469755,0.00014466564,0.032392006,0.00006647029],"about_ca_topic_score_codex":0.000041449137,"about_ca_topic_score_gemma":0.0000083269715,"teacher_disagreement_score":0.08873661,"about_ca_system_score_codex":0.000037473448,"about_ca_system_score_gemma":0.000040122428,"threshold_uncertainty_score":0.8993384},"labels":[],"label_agreement":null},{"id":"W1749012442","doi":"10.1016/j.jclinepi.2015.09.014","title":"Significant discrepancies were found in pooled estimates of searching with Chinese indexes versus searching with English indexes","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Neonatal and fetal brain pathology","field":"Medicine","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 Ottawa; Ottawa Hospital","funders":"","keywords":"Statistics; Medicine; Mathematics; Econometrics; Demography; Sociology","score_opus":0.29409472786656166,"score_gpt":0.529125416107765,"score_spread":0.23503068824120332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1749012442","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":[0.034079574,0.96165085,0.0006550483,0.0008976338,0.0010365164,0.00093742606,0.00004576811,0.00003043768,0.0006667672],"genre_scores_gemma":[0.030533187,0.9515756,0.015398108,0.000261434,0.0019094567,0.000026615335,0.000065866276,0.0001257078,0.000104017745],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862714,0.0050351215,0.006547465,0.0006789597,0.0006632658,0.00080382486],"domain_scores_gemma":[0.93160164,0.06000393,0.006104589,0.0006176363,0.0008848304,0.00078734814],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.025166068,0.00070430234,0.013964121,0.00069864077,0.00005556397,0.00001394092,0.0006251422,0.00092542113,0.00002166275],"category_scores_gemma":[0.092839524,0.0003449263,0.0010986379,0.00061439985,0.0016250125,0.00021161833,0.0002817951,0.0053479113,0.0000055378423],"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":[0.019549664,0.0010604281,0.20892502,0.018966317,0.003356951,0.003975423,0.0007019514,0.00023401376,0.0000023600946,0.001370796,0.00019195938,0.7416651],"study_design_scores_gemma":[0.049639545,0.08258559,0.12955086,0.17499731,0.012578032,0.014778663,0.0016967376,0.00046937916,0.0000026274683,0.017567873,0.51290786,0.003225517],"about_ca_topic_score_codex":0.000100870064,"about_ca_topic_score_gemma":0.00011671562,"teacher_disagreement_score":0.7384396,"about_ca_system_score_codex":0.00013318167,"about_ca_system_score_gemma":0.002735069,"threshold_uncertainty_score":0.9999003},"labels":[],"label_agreement":null},{"id":"W1753146223","doi":"10.1016/j.jclinepi.2015.08.015","title":"Sample size calculations for stepped wedge and cluster randomised trials: a unified approach","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":241,"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":"Medical Research Council; National Institute for Health and Care Research","keywords":"Sample size determination; Cluster (spacecraft); Cluster randomised controlled trial; Wedge (geometry); Computer science; Cluster size; Statistics; Randomized controlled trial; Data mining; Mathematics; Medicine; Physics; Surgery","score_opus":0.733403766534936,"score_gpt":0.6107111935731112,"score_spread":0.12269257296182479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1753146223","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":[0.0045970115,0.00011219479,0.9899049,0.0033954456,0.0006841099,0.0006832602,0.000041641946,0.000010415128,0.00057101296],"genre_scores_gemma":[0.014302288,0.000056159784,0.9835397,0.0010726374,0.0009142085,0.000025951007,0.0000020583823,0.000015417852,0.0000716005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97814333,0.014910627,0.006262129,0.00023734153,0.00014912288,0.00029741836],"domain_scores_gemma":[0.32241756,0.6730393,0.0033186455,0.00021287627,0.0004981002,0.00051353563],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11797564,0.00016393512,0.003997862,0.00005987161,0.000053186508,0.000014257611,0.00018498233,0.0003631874,0.00003989553],"category_scores_gemma":[0.91295904,0.00010063171,0.0006534101,0.0000779876,0.00027240778,0.00006443853,0.000048373455,0.0005022063,0.0000014900695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016556326,0.00043997235,0.0051957304,0.00014610944,0.00043966837,0.0000037235377,0.00017236375,0.000023978397,0.000006125187,0.9037919,0.028922679,0.044301447],"study_design_scores_gemma":[0.029085454,0.00061423384,0.0026050915,0.00003611617,0.0003278318,0.00003611533,0.00007621702,0.017242039,0.0000012221157,0.94711894,0.0027466535,0.00011010976],"about_ca_topic_score_codex":0.000010018008,"about_ca_topic_score_gemma":0.0000021964886,"teacher_disagreement_score":0.7949834,"about_ca_system_score_codex":0.000020183605,"about_ca_system_score_gemma":0.0002484215,"threshold_uncertainty_score":0.9082297},"labels":[],"label_agreement":null},{"id":"W1753327060","doi":"10.1016/j.jclinepi.2015.08.008","title":"The proportion of all previous patients was a potential instrument for patients' actual prescriptions of nonsteroidal anti-inflammatory drugs","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory mediators and NSAID effects","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; Royal Victoria Regional Health Centre; McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Medical prescription; Nonsteroidal; Retrospective cohort study; Cohort; Multivariate statistics; Proportional hazards model; Pharmacoepidemiology; Cohort study; Multivariate analysis; Internal medicine; Pharmacology; Statistics","score_opus":0.10002087325722021,"score_gpt":0.40674648275159814,"score_spread":0.30672560949437794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1753327060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99420494,0.0001797656,0.00085191586,0.00078456075,0.0029589015,0.0009580522,0.000016147113,0.0000063629436,0.000039360468],"genre_scores_gemma":[0.9970526,0.00027214785,0.0015268554,0.00030893766,0.00075309735,0.000016245653,0.00002135736,0.000018181297,0.000030566745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99229676,0.0015381916,0.0051152324,0.00019289037,0.0005115636,0.00034538194],"domain_scores_gemma":[0.98810816,0.0041810316,0.005282916,0.00030247826,0.0016995952,0.00042579768],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01317651,0.00018000533,0.0018210527,0.00010804511,0.000052785974,0.0000034040827,0.00021412031,0.0003263046,0.0000073043516],"category_scores_gemma":[0.0389536,0.00010448936,0.00078024826,0.00005898558,0.00045209995,0.00012166424,0.00007145463,0.000509726,0.0000032496985],"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":[0.004735346,0.0012979475,0.9631522,0.00024513825,0.00042281862,0.0000055470628,0.0002834845,0.000058175316,0.00009630946,0.00026052372,0.0064063906,0.023036106],"study_design_scores_gemma":[0.016361257,0.015248902,0.95277226,0.0003946159,0.0006817205,0.00003094528,0.00014783189,0.00086847285,0.00048735534,0.0012180962,0.011622219,0.00016629935],"about_ca_topic_score_codex":0.0000059433632,"about_ca_topic_score_gemma":0.0000019947906,"teacher_disagreement_score":0.025777088,"about_ca_system_score_codex":0.000054406348,"about_ca_system_score_gemma":0.00055216835,"threshold_uncertainty_score":0.9691417},"labels":[],"label_agreement":null},{"id":"W1755991303","doi":"10.1016/s0895-4356(99)00234-6","title":"Iron stores and coronary artery disease","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Iron Metabolism and Disorders","field":"Medicine","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":"Montreal General Hospital","funders":"","keywords":"Coronary artery disease; Medicine; Interquartile range; Ferritin; Odds ratio; Internal medicine; Menopause; Cardiology","score_opus":0.13119529062985655,"score_gpt":0.45825310115060625,"score_spread":0.32705781052074967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1755991303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97614074,0.007515287,0.00012095206,0.014533103,0.00048774248,0.00007131799,0.0000028357863,0.00000747317,0.0011205283],"genre_scores_gemma":[0.967607,0.011536047,0.0020592487,0.016522931,0.0012308678,8.7137136e-7,0.0000033497033,0.000010992702,0.0010286605],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963405,0.0011778835,0.001982172,0.00016567305,0.0001158242,0.00021794793],"domain_scores_gemma":[0.9934022,0.0051176334,0.00055553927,0.00018191816,0.00005813591,0.00068457023],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005179236,0.000107606174,0.0013822269,0.00005477157,0.00003036456,0.0000021038272,0.00007714787,0.00015970715,0.0010616459],"category_scores_gemma":[0.012725434,0.00007094901,0.00035081437,0.000035136512,0.00036524495,0.000073645046,0.00001618401,0.00053249963,0.000044379114],"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":[0.0032903505,0.00024450527,0.8081946,0.000042560485,0.000030580748,0.00027592285,0.000018390474,0.000025083229,0.000004569127,0.00046425106,0.013959599,0.17344959],"study_design_scores_gemma":[0.00250805,0.00069951615,0.945632,0.00003922922,0.00019808125,0.00037348073,0.000021537422,0.00007379644,2.3194042e-7,0.004624135,0.045768883,0.0000610547],"about_ca_topic_score_codex":0.000003904819,"about_ca_topic_score_gemma":9.968917e-7,"teacher_disagreement_score":0.17338853,"about_ca_system_score_codex":0.0000060226166,"about_ca_system_score_gemma":0.00014615545,"threshold_uncertainty_score":0.9998515},"labels":[],"label_agreement":null},{"id":"W1829176824","doi":"10.1016/j.jclinepi.2015.05.030","title":"Contour plot assessment of existing meta-analyses confirms robust association of statin use and acute kidney injury risk","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Jewish General Hospital; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Robustness (evolution); Medicine; Forest plot; Systematic review; Statistics; Risk assessment; Statin; Computer science; Data mining; Econometrics; MEDLINE; Mathematics; Internal medicine","score_opus":0.9769347066636065,"score_gpt":0.7322601582572107,"score_spread":0.2446745484063958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1829176824","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":[0.7912976,0.0011749287,0.19692132,0.0071501387,0.001244406,0.0004974276,0.0004507074,0.0000033374529,0.001260102],"genre_scores_gemma":[0.8064263,0.0007610421,0.18917662,0.0016745979,0.00028321176,0.0000048376,0.0000070893675,0.0000138756,0.0016524441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6955504,0.21346895,0.08436448,0.0009456473,0.0052014915,0.00046906594],"domain_scores_gemma":[0.26579288,0.4686954,0.24714637,0.0025769316,0.01433905,0.0014493736],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6773094,0.00028725417,0.021938784,0.00036943742,0.000048545364,0.000088541216,0.0009692962,0.0003299721,0.0009201855],"category_scores_gemma":[0.9087536,0.00012409296,0.005903552,0.0005049901,0.000224018,0.00038657893,0.00015490771,0.0007953855,0.000017855838],"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":[0.000076247044,0.00012557252,0.8767213,0.000020881562,0.013916621,0.000004417356,0.000071279435,0.00071386213,0.000033516975,0.0013424713,0.10511535,0.0018584337],"study_design_scores_gemma":[0.0022261068,0.0020848825,0.8314103,0.00009128962,0.04532713,0.000034910492,0.0005765782,0.0393654,0.000028586415,0.038065698,0.04049222,0.00029690907],"about_ca_topic_score_codex":0.00012480638,"about_ca_topic_score_gemma":0.000020460777,"teacher_disagreement_score":0.4297575,"about_ca_system_score_codex":0.00005155083,"about_ca_system_score_gemma":0.00056733267,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W1917806591","doi":"10.1016/j.jclinepi.2015.09.007","title":"Migraineurs were reliably identified using administrative data","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Migraine and Headache Studies","field":"Medicine","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Migraine; Statistic; Medicine; Medical diagnosis; Diagnosis code; Population; Statistics; Internal medicine; Mathematics; Environmental health","score_opus":0.8748083062821352,"score_gpt":0.6536844929701522,"score_spread":0.22112381331198305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1917806591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9106119,0.0064115566,0.0040794117,0.070050105,0.001435269,0.00028103933,0.000034117194,0.000026028578,0.0070705735],"genre_scores_gemma":[0.93136585,0.0017582544,0.045278452,0.012383886,0.0058478564,0.0000011546155,0.000032145777,0.000031722047,0.003300658],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928085,0.0019144932,0.004315127,0.000338683,0.00027701052,0.00034614254],"domain_scores_gemma":[0.9809197,0.013452306,0.0030820528,0.0008302097,0.00084626855,0.0008694603],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026691334,0.00017683065,0.0028773767,0.00010556781,0.000048594862,0.000005265415,0.0003946032,0.00029683864,0.00005578541],"category_scores_gemma":[0.19301465,0.00011766927,0.0005308167,0.00012534152,0.00040423748,0.00015970966,0.00021710053,0.0011950167,0.00002936463],"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":[0.0011595363,0.00024163211,0.26584587,0.000034956938,0.0004392682,0.00030023008,0.000125915,0.000011848751,0.000031816344,0.00038461623,0.7304327,0.0009916354],"study_design_scores_gemma":[0.0072986553,0.0061414167,0.30490145,0.0004899305,0.0012858252,0.003100204,0.0022473556,0.003220101,0.000017319118,0.007403058,0.6635967,0.0002980167],"about_ca_topic_score_codex":0.000070373986,"about_ca_topic_score_gemma":0.000059994894,"teacher_disagreement_score":0.1663233,"about_ca_system_score_codex":0.000034475237,"about_ca_system_score_gemma":0.0010559789,"threshold_uncertainty_score":0.92507374},"labels":[],"label_agreement":null},{"id":"W1935691805","doi":"10.1016/j.jclinepi.2015.06.006","title":"Core domain and outcome measurement sets for shoulder pain trials are needed: systematic review of physical therapy trials","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Shoulder Injury and Treatment","field":"Medicine","cited_by":65,"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":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Health and Medical Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Medicine; Physical therapy; CINAHL; Rotator cuff; Clinical trial; Randomized controlled trial; Capsulitis; MEDLINE; Psychological intervention; Quality of life (healthcare); Physical medicine and rehabilitation; Range of motion; Surgery; Internal medicine","score_opus":0.8975749136389641,"score_gpt":0.6794231061986192,"score_spread":0.2181518074403449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935691805","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":[0.000027245102,0.98382837,0.001004049,0.004668366,0.0010046273,0.009317889,0.000120119454,0.000010730745,0.000018635157],"genre_scores_gemma":[0.000029053423,0.98878866,0.0021302255,0.0065898383,0.0019608815,0.0003710386,0.000036591104,0.00006305811,0.000030674644],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.88069415,0.082069,0.035176486,0.0005920514,0.0009842227,0.00048411542],"domain_scores_gemma":[0.6156579,0.32076174,0.059219588,0.0011591938,0.0021760683,0.0010255164],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.51934296,0.0008015354,0.081666596,0.0002479852,0.0000403046,0.000007000039,0.0003613908,0.0010908836,0.000033553428],"category_scores_gemma":[0.6481964,0.00035949098,0.012033805,0.00017983462,0.00026407643,0.000046141176,0.00005375,0.0013117149,0.0000040720793],"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":[0.0011775817,0.0008751354,0.00025738863,0.76092696,0.008582259,0.000044663382,0.000019495123,1.775062e-7,1.5001343e-7,0.00018676322,0.018785398,0.20914403],"study_design_scores_gemma":[0.0073942463,0.0068504256,0.000025155412,0.6601002,0.048504017,0.0004016574,0.000061471466,0.0000051244992,3.660078e-7,0.0038888135,0.27249357,0.0002748905],"about_ca_topic_score_codex":0.000003261852,"about_ca_topic_score_gemma":8.187139e-7,"teacher_disagreement_score":0.26503623,"about_ca_system_score_codex":0.00020513037,"about_ca_system_score_gemma":0.0012041955,"threshold_uncertainty_score":0.9998857},"labels":[],"label_agreement":null},{"id":"W1937285662","doi":"10.1016/j.jclinepi.2015.09.005","title":"High statistical heterogeneity is more frequent in meta-analysis of continuous than binary outcomes","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":139,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network; McMaster University","funders":"","keywords":"Meta-analysis; Binary number; Medicine; MEDLINE; Study heterogeneity; Sample size determination; Statistics; Randomized controlled trial; Continuous variable; Mathematics; Internal medicine; Biology","score_opus":0.9462331196270646,"score_gpt":0.6916570514577847,"score_spread":0.2545760681692799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1937285662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9394777,0.002646244,0.03886521,0.017721707,0.00075511204,0.00025149438,0.0001342204,0.000001637841,0.0001466937],"genre_scores_gemma":[0.9525709,0.000088718254,0.042183194,0.0046008974,0.00010096739,0.000005681,0.0000061344645,0.000009003254,0.0004344962],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7814882,0.13125975,0.081199884,0.0011132173,0.0044289893,0.0005099661],"domain_scores_gemma":[0.6403325,0.28617448,0.064208426,0.0040822537,0.004062227,0.0011401138],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.5900255,0.00038622163,0.047973834,0.001105957,0.00002605055,0.000047619564,0.0021816387,0.00038739498,0.0053569744],"category_scores_gemma":[0.64937645,0.00015377764,0.021974264,0.001569769,0.00043589176,0.0001718073,0.00021392475,0.0007781264,0.00019319229],"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":[0.00007090241,0.00027401926,0.9032766,0.000008276973,0.06558705,0.000057505273,0.00009451629,0.0023490845,0.0000010253714,0.0026749435,0.02469975,0.00090629206],"study_design_scores_gemma":[0.0006057729,0.0004872683,0.8752738,0.000005040599,0.081463635,0.000019022193,0.0002333671,0.0050732396,0.000001763129,0.033036783,0.003659232,0.00014105727],"about_ca_topic_score_codex":0.00020455076,"about_ca_topic_score_gemma":0.00017897814,"teacher_disagreement_score":0.15491472,"about_ca_system_score_codex":0.000038413167,"about_ca_system_score_gemma":0.00024149766,"threshold_uncertainty_score":0.99555224},"labels":[],"label_agreement":null},{"id":"W1945571774","doi":"10.1016/j.jclinepi.2015.03.005","title":"Dyadic validity of the Decisional Conflict Scale: common patient/physician measures of patient uncertainty were identified","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"Université Laval; Centre hospitalier universitaire de Québec; Hôpital Saint-François d'Assise","funders":"","keywords":"CLARITY; Dyad; Scale (ratio); Psychology; Clinical psychology; Medicine; Randomized controlled trial; Social psychology; Surgery","score_opus":0.7621220673955924,"score_gpt":0.5934880493828198,"score_spread":0.16863401801277256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1945571774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98266226,0.0019435587,0.00019584128,0.007745518,0.005917634,0.0007298911,0.00008383601,0.0000122233205,0.00070923887],"genre_scores_gemma":[0.9911932,0.00031063927,0.001476664,0.0065849773,0.0003564219,0.000020289506,0.000011134279,0.00002211354,0.000024561257],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9451902,0.040899243,0.012080353,0.0003034387,0.0009973714,0.00052942435],"domain_scores_gemma":[0.9068596,0.07027139,0.017157994,0.0014835031,0.0035991445,0.0006283992],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018820336,0.00024408534,0.0030287574,0.00014708767,0.0002946203,0.000002291906,0.0013633367,0.00068241067,0.00005890404],"category_scores_gemma":[0.11098902,0.00015160847,0.0009817292,0.00030607177,0.000885134,0.00014523741,0.0006600922,0.0028914164,0.00002290626],"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":[0.0013276316,0.0005310302,0.9437267,0.00013246093,0.00012825862,0.0000019350982,0.0030561003,0.0011485945,0.00002680945,0.0015332866,0.028552052,0.019835135],"study_design_scores_gemma":[0.0049599,0.005304535,0.82365656,0.0027021272,0.00025142176,0.000021964013,0.01353065,0.0014832926,0.00015710463,0.084755436,0.06280783,0.0003691575],"about_ca_topic_score_codex":0.0005798043,"about_ca_topic_score_gemma":0.0003612194,"teacher_disagreement_score":0.12007012,"about_ca_system_score_codex":0.00021399585,"about_ca_system_score_gemma":0.002056684,"threshold_uncertainty_score":0.99940896},"labels":[],"label_agreement":null},{"id":"W1946200177","doi":"10.1016/j.jclinepi.2015.08.012","title":"An international survey and modified Delphi approach revealed numerous rapid review methods","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Ottawa Hospital; McMaster University; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Delphi method; Limiting; Government (linguistics); Grey literature; Health care; Delphi; Quality (philosophy); Medicine; MEDLINE; Psychology; Computer science; Political science; Engineering","score_opus":0.9753474181125361,"score_gpt":0.7489619454767924,"score_spread":0.2263854726357437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1946200177","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"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":[0.04232761,0.041582406,0.89440614,0.011948962,0.003108132,0.00053996604,0.000014987335,0.0000044109697,0.0060673924],"genre_scores_gemma":[0.17828585,0.0255341,0.7784697,0.01541148,0.0013425867,0.000011237344,0.000021274032,0.000021804552,0.000901969],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.36669263,0.555226,0.07281792,0.0013714002,0.0034433603,0.00044865743],"domain_scores_gemma":[0.5094092,0.3934109,0.08105074,0.0051813414,0.008639828,0.002307995],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9021504,0.00028012702,0.015375063,0.00027165897,0.000045490127,0.00010364797,0.0028364726,0.00030810302,0.00089612335],"category_scores_gemma":[0.88897777,0.00012315129,0.002782521,0.00056087424,0.00023433327,0.00041003764,0.00016952216,0.00083406206,0.0001243279],"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":[0.00017142731,0.00026191171,0.5205824,0.00008531549,0.00071681483,0.000010912495,0.00008092309,0.00032151863,0.0000012385761,0.0027469872,0.17264652,0.30237404],"study_design_scores_gemma":[0.0016494053,0.0012214708,0.65395486,0.00029128217,0.0007002579,0.0008370881,0.00015873123,0.07155163,2.262841e-7,0.07377133,0.19548835,0.00037537242],"about_ca_topic_score_codex":0.000018021701,"about_ca_topic_score_gemma":0.0000053135172,"teacher_disagreement_score":0.30199867,"about_ca_system_score_codex":0.000023622364,"about_ca_system_score_gemma":0.00023982105,"threshold_uncertainty_score":0.9992427},"labels":[],"label_agreement":null},{"id":"W1952002227","doi":"10.1016/j.jclinepi.2015.08.010","title":"Competing risk bias in Kaplan–Meier risk estimates can be corrected","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":30,"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; Ottawa Hospital","funders":"University of Ottawa","keywords":"Medicine; Statistics; Econometrics; Mathematics","score_opus":0.7115208986786495,"score_gpt":0.5991455404469213,"score_spread":0.11237535823172828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1952002227","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":[0.83181775,0.00020590739,0.16277032,0.0023024345,0.0017688796,0.00011321583,0.00004961481,0.000023286108,0.00094860466],"genre_scores_gemma":[0.30510518,0.00034230712,0.69297856,0.001022306,0.0005080808,0.0000020846735,0.0000018244816,0.00001902757,0.000020626352],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97942317,0.014137246,0.005495802,0.00025915552,0.00023097772,0.00045366018],"domain_scores_gemma":[0.6818671,0.31152654,0.0052859155,0.0002780197,0.0004657302,0.000576698],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070086725,0.00020764329,0.0028643922,0.00012659177,0.000047314497,0.00001020504,0.00034676844,0.0003778786,0.00012127801],"category_scores_gemma":[0.84324664,0.00014009023,0.00033123945,0.00018571851,0.00033327373,0.000048895756,0.00010028413,0.002165408,0.000014383828],"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":[0.00029699062,0.00020855608,0.9435691,0.0000179273,0.00008717382,0.00005858901,0.0002119164,0.00019357284,0.0000015015225,0.013751825,0.006294919,0.0353079],"study_design_scores_gemma":[0.0016238858,0.00094470696,0.2614425,0.00015193563,0.00013988529,0.00009681152,0.00025064885,0.025634157,0.000006618483,0.7083145,0.0012380383,0.00015631414],"about_ca_topic_score_codex":0.00040952375,"about_ca_topic_score_gemma":0.00019185497,"teacher_disagreement_score":0.7731599,"about_ca_system_score_codex":0.00005322654,"about_ca_system_score_gemma":0.0002832726,"threshold_uncertainty_score":0.9575414},"labels":[],"label_agreement":null},{"id":"W1953543234","doi":"10.1016/j.jclinepi.2015.08.021","title":"Meta-analyses with industry involvement are massively published and report no caveats for antidepressants","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":106,"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","funders":"","keywords":"Meta-analysis; MEDLINE; Depression (economics); Medicine; Antidepressant; Psychiatry; Conflict of interest; Systematic review; Family medicine; Internal medicine; Business; Political science; Finance; Anxiety; Economics","score_opus":0.9745248118502634,"score_gpt":0.7688847640335387,"score_spread":0.20564004781672474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953543234","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":[0.00028931643,0.9871624,0.00015859422,0.00648867,0.0035197213,0.0013726627,0.00042469092,0.000027746732,0.00055620197],"genre_scores_gemma":[0.00021371798,0.9830102,0.0021273787,0.008442508,0.004265865,0.0001655223,0.00010490653,0.00008201488,0.0015879382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.964435,0.020686312,0.012187331,0.0011055999,0.00044096762,0.0011448116],"domain_scores_gemma":[0.91823375,0.053906508,0.02134652,0.00070120115,0.0027356176,0.0030763794],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.073386356,0.0009832759,0.019212304,0.00036248556,0.00023226808,0.000037644586,0.0009478034,0.008023826,0.0007205561],"category_scores_gemma":[0.06888641,0.00055713084,0.0032295077,0.00033965832,0.0011025296,0.00033025886,0.0002976009,0.017127698,0.000024736335],"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":[0.0033228192,0.0017471793,0.048078462,0.020036884,0.10713551,0.0055035325,0.00004640602,0.0001246384,8.7031725e-7,0.00061804045,0.3768781,0.43650752],"study_design_scores_gemma":[0.002065693,0.0011199098,0.00042122265,0.0013214801,0.06058949,0.002167852,0.000035093737,0.00006007045,0.0000016471807,0.0012941615,0.93044084,0.00048250947],"about_ca_topic_score_codex":0.000018854995,"about_ca_topic_score_gemma":0.00001079671,"teacher_disagreement_score":0.55356276,"about_ca_system_score_codex":0.00015672494,"about_ca_system_score_gemma":0.0027726542,"threshold_uncertainty_score":0.999688},"labels":[],"label_agreement":null},{"id":"W1963696901","doi":"10.1016/j.jclinepi.2013.05.005","title":"A survey of patient's perceptions of what is “adverse” in manual physiotherapy and predicting who is likely to say so","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Centre; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Adverse effect; Confidence interval; Poisson regression; Incidence (geometry); Rate ratio; Physical therapy; Manual therapy; Emergency medicine; Internal medicine; Alternative medicine; Population","score_opus":0.07082209664320421,"score_gpt":0.47010192431479414,"score_spread":0.3992798276715899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963696901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871356,0.00047915804,0.00027793917,0.011509741,0.00025921097,0.0003001549,0.0000057554103,0.0000023134533,0.00003013885],"genre_scores_gemma":[0.98791033,0.0020883502,0.0029392622,0.0068520596,0.00014523651,0.0000032893522,0.0000022240656,0.0000094487,0.0000498029],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99361515,0.0025558763,0.0032812122,0.00019077296,0.00017315673,0.00018381207],"domain_scores_gemma":[0.9833916,0.014227484,0.0014508995,0.00018836104,0.0004996973,0.00024195232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009513858,0.00010983111,0.001712679,0.00017505062,0.00001992456,0.0000030085826,0.00007829749,0.000245884,0.00028038523],"category_scores_gemma":[0.020043768,0.0000744363,0.00037000232,0.00015837203,0.0003302922,0.00018784382,0.00003255001,0.0004406901,0.0000063570983],"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":[0.0003030156,0.0002841237,0.9434486,0.00017743469,0.00008156409,5.5340854e-7,0.0016872544,0.000028839066,0.00067346427,0.000012539228,0.0021629576,0.051139627],"study_design_scores_gemma":[0.001321774,0.003239144,0.99186254,0.00074904016,0.000020528209,0.0000044149638,0.0010870144,0.0008690807,0.000013469674,0.0006323078,0.00014594421,0.000054750817],"about_ca_topic_score_codex":0.000731623,"about_ca_topic_score_gemma":0.000067501795,"teacher_disagreement_score":0.051084876,"about_ca_system_score_codex":0.000020574233,"about_ca_system_score_gemma":0.000104530554,"threshold_uncertainty_score":0.9882108},"labels":[],"label_agreement":null},{"id":"W1963778617","doi":"10.1016/s0895-4356(99)00192-4","title":"Hormone replacement therapy and endometrial cancer in Ontario, Canada","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Estrogen and related hormone effects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Cancer Care Ontario","keywords":"Endometrial cancer; Medicine; Hormone therapy; Regimen; Estrogen; Progestogen; Hormone replacement therapy (female-to-male); Population; Internal medicine; Cancer; Gynecology; Oncology; Breast cancer; Testosterone (patch)","score_opus":0.08068853645641398,"score_gpt":0.39811918790131945,"score_spread":0.31743065144490545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963778617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98364925,0.014036629,0.000012360004,0.0012817312,0.0005335543,0.00009439114,0.0000024669973,9.370331e-7,0.00038866574],"genre_scores_gemma":[0.9587952,0.037696358,0.0003437657,0.001919023,0.0005668456,0.0000037226844,0.000004008083,0.000009026548,0.00066203653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996647,0.001133051,0.0016664928,0.00021376614,0.00009490765,0.0002447581],"domain_scores_gemma":[0.99772745,0.0013146385,0.00057433965,0.00014232585,0.00004864556,0.00019262565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004993307,0.000120684366,0.00087352446,0.000040885963,0.000023827799,0.0000027410233,0.0001280127,0.00031263754,0.00024078917],"category_scores_gemma":[0.0025379953,0.00008499395,0.00017717073,0.00005614749,0.00009558456,0.0000032460873,0.000023581732,0.00062162365,9.164398e-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":[0.012362832,0.00020169522,0.83153766,0.0000039707247,0.00045848635,0.000081687154,0.000025308856,0.00067147077,0.003500322,0.00003808333,0.023204908,0.1279136],"study_design_scores_gemma":[0.009893595,0.004171371,0.76465267,0.000028118051,0.000030232879,0.00014130164,0.000010047126,0.00005303229,0.00059655413,0.00022454753,0.22002143,0.00017708831],"about_ca_topic_score_codex":0.40166184,"about_ca_topic_score_gemma":0.55647403,"teacher_disagreement_score":0.19681652,"about_ca_system_score_codex":0.000052507414,"about_ca_system_score_gemma":0.0009939321,"threshold_uncertainty_score":0.6023225},"labels":[],"label_agreement":null},{"id":"W1965364964","doi":"10.1016/j.jclinepi.2009.03.014","title":"Response shift was identified over multiple occasions with a structural equation modeling framework","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","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; University of Saskatchewan; University of Manitoba","funders":"University of Manitoba","keywords":"Structural equation modeling; Observational study; Identification (biology); Measure (data warehouse); Computer science; Key (lock); Confidence interval; Mental health; Data mining; Psychology; Statistics; Machine learning; Mathematics; Psychiatry","score_opus":0.5506461619325485,"score_gpt":0.6251469033359897,"score_spread":0.0745007414034412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965364964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8996741,0.00039917044,0.08005445,0.017626867,0.0017544222,0.00024944372,0.000005886416,0.00001917282,0.00021644465],"genre_scores_gemma":[0.968377,0.00008142674,0.02314464,0.007105426,0.0010356597,0.000004394552,0.0000039907777,0.00001719519,0.00023024972],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9820792,0.012013449,0.004348129,0.00041445697,0.00041552697,0.0007292203],"domain_scores_gemma":[0.94046265,0.0561571,0.0019598606,0.00053152745,0.00024300796,0.0006458575],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03267817,0.0002034391,0.0015778098,0.00022210334,0.00015598169,0.0000148227355,0.00045583912,0.0006660418,0.0011085527],"category_scores_gemma":[0.09827693,0.00013861155,0.0004110306,0.00021554998,0.00020527178,0.00018351022,0.000052304393,0.002572611,0.0001260775],"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":[0.09564246,0.0009849404,0.7752247,0.000045577508,0.00048479604,0.0007749415,0.0027746987,0.011573669,0.00007757652,0.05167994,0.010365295,0.050371423],"study_design_scores_gemma":[0.0034367314,0.004762246,0.80696833,0.00022253163,0.000047846625,0.00020544631,0.00024035787,0.060243096,0.0000027255444,0.122200474,0.0014717502,0.00019847292],"about_ca_topic_score_codex":0.00006791836,"about_ca_topic_score_gemma":0.000026786696,"teacher_disagreement_score":0.092205726,"about_ca_system_score_codex":0.00009943027,"about_ca_system_score_gemma":0.000323583,"threshold_uncertainty_score":0.99980456},"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":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1965701788","doi":"10.1016/j.jclinepi.2006.05.003","title":"Preparing a research protocol to improve chances for success","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Checklist; Protocol (science); sort; Advice (programming); Clinical Practice; Inference; Medical education; Research design; Medicine; Psychology; Engineering ethics; Alternative medicine; Computer science; Family medicine; Sociology; Pathology; Cognitive psychology; Engineering; Artificial intelligence; Social science; Information retrieval","score_opus":0.9596535315268899,"score_gpt":0.7802309512011207,"score_spread":0.1794225803257692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965701788","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":[0.2216645,0.00048449944,0.5455328,0.052464508,0.004591687,0.15062799,0.000023910443,0.000010065303,0.024600035],"genre_scores_gemma":[0.6824372,0.000019738174,0.23355514,0.004984945,0.012838669,0.04514902,0.0000017682338,0.000046424044,0.020967089],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.694584,0.17958088,0.11564973,0.002104853,0.006714959,0.0013655619],"domain_scores_gemma":[0.47889602,0.4692651,0.039757684,0.0029735942,0.008441151,0.0006664232],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8373669,0.00020301984,0.010784812,0.00053783396,0.00014908971,0.00018520563,0.002839274,0.00027245685,0.0007348819],"category_scores_gemma":[0.8357261,0.00008530866,0.004575707,0.0008897827,0.00019841398,0.00021957455,0.00023278163,0.0007432027,0.00041723557],"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":[0.0004919552,0.00024080966,0.27434537,0.000110587025,0.00019355131,0.000005278301,0.00003464539,0.0006964221,0.000059070302,0.013538565,0.6150086,0.09527516],"study_design_scores_gemma":[0.0006604782,0.0012204984,0.060189705,0.000058558384,0.000058776608,0.000017037888,0.000047517657,0.0041635777,0.000024656252,0.205909,0.7275523,0.00009790827],"about_ca_topic_score_codex":0.000032356642,"about_ca_topic_score_gemma":0.00009337569,"teacher_disagreement_score":0.4607727,"about_ca_system_score_codex":0.00003216937,"about_ca_system_score_gemma":0.00027616826,"threshold_uncertainty_score":0.80464417},"labels":[],"label_agreement":null},{"id":"W1965768884","doi":"10.1016/j.jclinepi.2006.12.006","title":"Systematic reviewers neglect bias that results from trials stopped early for benefit","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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","funders":"","keywords":"Systematic review; Medicine; Meta-analysis; MEDLINE; Cochrane Library; Publication bias; Randomized controlled trial; Systematic error; Neglect; Statistics; Surgery; Internal medicine; Psychiatry; Mathematics","score_opus":0.9859782993171283,"score_gpt":0.7455648000033752,"score_spread":0.2404134993137531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965768884","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003651639,0.95107466,0.03368513,0.0010490082,0.007689494,0.0056530456,0.00041384838,0.0000054640614,0.00039283079],"genre_scores_gemma":[0.000009757528,0.96608466,0.024625182,0.0014152892,0.0041936557,0.0000944197,0.000058077032,0.000067280314,0.0034516973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.06887488,0.53905374,0.3808668,0.0030277069,0.006988022,0.0011888524],"domain_scores_gemma":[0.0132794995,0.66939956,0.30721572,0.005681398,0.0035399585,0.0008838818],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.95365757,0.0014935258,0.22299255,0.0015858052,0.00016015641,0.0004249721,0.007790494,0.002613848,0.0014331078],"category_scores_gemma":[0.98946816,0.00055378367,0.09804108,0.0016207518,0.0002847406,0.00028858063,0.00027827537,0.0027012394,0.0021068982],"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":[0.00023114124,0.00010433839,0.00026240337,0.04136265,0.007412056,0.00003198467,0.00003499115,0.0000096039485,9.876387e-9,0.0007307254,0.119104676,0.8307154],"study_design_scores_gemma":[0.0010055212,0.0005304308,0.00015441347,0.097947486,0.01985433,0.00009684886,0.000032742737,0.00008193539,1.2924956e-8,0.015129885,0.86477566,0.0003907142],"about_ca_topic_score_codex":0.000024979388,"about_ca_topic_score_gemma":0.000021425429,"teacher_disagreement_score":0.8303247,"about_ca_system_score_codex":0.00014778182,"about_ca_system_score_gemma":0.0009821904,"threshold_uncertainty_score":0.99978137},"labels":[],"label_agreement":null},{"id":"W1966358706","doi":"10.1016/j.jclinepi.2009.01.003","title":"The wizard of WOS—or the art of the task force","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Health Centre","funders":"","keywords":"Wizard; Task force; Task (project management); Wizard of oz; Library science; Political science; Management; Computer science; Public administration; World Wide Web; Human–computer interaction; Economics","score_opus":0.597124992548279,"score_gpt":0.6416029184344885,"score_spread":0.04447792588620947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966358706","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":[0.3015506,0.0006360969,0.004978059,0.6888208,0.0024304416,0.00052047154,0.0000067553697,0.0000063422485,0.001050461],"genre_scores_gemma":[0.9516801,0.0026429715,0.0032193249,0.039718762,0.001523736,0.0000016795934,0.000001622633,0.000011270824,0.001200508],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9841395,0.0050141434,0.009966949,0.00016579624,0.00042612804,0.0002875084],"domain_scores_gemma":[0.80167234,0.18594821,0.010491732,0.0008124715,0.00088895764,0.00018629947],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05483919,0.00013012043,0.0017064953,0.000034050612,0.00009280816,0.0000035457676,0.0005782874,0.00022845846,0.00010315313],"category_scores_gemma":[0.47154975,0.00004099316,0.0011105338,0.00020802104,0.0007579048,0.000082077095,0.00008683378,0.0014213306,0.000009967161],"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":[0.01203794,0.00087122567,0.2810788,0.000048696842,0.00067016075,0.000022280634,0.00013239708,0.0003774292,0.0006488379,0.007521028,0.4003633,0.29622793],"study_design_scores_gemma":[0.0034883937,0.0047391546,0.707297,0.00018529648,0.0006616991,0.00038995637,0.00035232003,0.0008030558,0.00010023359,0.0320453,0.24986494,0.0000726203],"about_ca_topic_score_codex":0.00001433209,"about_ca_topic_score_gemma":0.000037227343,"teacher_disagreement_score":0.6501295,"about_ca_system_score_codex":0.00002376467,"about_ca_system_score_gemma":0.0005675856,"threshold_uncertainty_score":0.9732419},"labels":[],"label_agreement":null},{"id":"W1967329689","doi":"10.1016/j.jclinepi.2005.11.008","title":"Small-scale randomized controlled trials need more powerful methods of mediational analysis than the Baron–Kenny method","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Physical Activity and Health","field":"Medicine","cited_by":73,"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":"Psychology; Psychological intervention; Randomized controlled trial; Intervention (counseling); Freedman; Scale (ratio); Clinical psychology; Medicine; Psychiatry","score_opus":0.33764630051881644,"score_gpt":0.5975004980153429,"score_spread":0.25985419749652644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967329689","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":[0.24394076,0.0018208014,0.64983135,0.10104113,0.0009351472,0.0011475141,0.000018056528,0.000012578374,0.0012526623],"genre_scores_gemma":[0.6309372,0.001192084,0.35565814,0.0067969235,0.004961583,0.000028130984,0.000023269615,0.00002260674,0.00038002033],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8865863,0.09610454,0.016006054,0.00033731313,0.00051505206,0.00045072957],"domain_scores_gemma":[0.45661816,0.5287371,0.013157385,0.00038139537,0.0007303733,0.00037553872],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.34542894,0.0002682045,0.029795416,0.00037234792,0.000067290996,0.000005664629,0.00031710765,0.0005329652,0.00027190056],"category_scores_gemma":[0.42606226,0.00011841699,0.011541513,0.00054011034,0.0007569418,0.00007009463,0.0000523945,0.0015620865,0.000003871986],"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":[0.800788,0.004410362,0.1063551,0.00012808338,0.034876022,0.000026123053,0.00025803127,0.0045358357,0.0013476822,0.024062417,0.0048701717,0.018342199],"study_design_scores_gemma":[0.45816,0.0018611974,0.32404143,0.00010568953,0.033532616,0.0000722329,0.00015133538,0.042825576,0.00024613703,0.13715479,0.0016286632,0.0002203457],"about_ca_topic_score_codex":0.00027588033,"about_ca_topic_score_gemma":0.000043822358,"teacher_disagreement_score":0.4326326,"about_ca_system_score_codex":0.00004631535,"about_ca_system_score_gemma":0.0007039525,"threshold_uncertainty_score":0.99835765},"labels":[],"label_agreement":null},{"id":"W1967929637","doi":"10.1016/j.jclinepi.2004.07.010","title":"The standard gamble demonstrated lower reliability than the feeling thermometer","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 Toronto; McMaster University","funders":"Medical Research Council Canada","keywords":"Intraclass correlation; Reliability (semiconductor); Statistics; Psychology; Variance (accounting); Feeling; Audiology; Physical therapy; Medicine; Mathematics; Psychometrics; Social psychology","score_opus":0.6268485298520915,"score_gpt":0.5692764832966586,"score_spread":0.05757204655543291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967929637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5527825,0.0041659228,0.009657843,0.42839593,0.0027588245,0.00029321777,0.00002918795,0.000014355418,0.0019022112],"genre_scores_gemma":[0.95179784,0.002259078,0.007195708,0.035007868,0.0032396924,0.000012420139,0.000001486429,0.000025475449,0.00046045624],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.96772903,0.009263587,0.021792732,0.00043705397,0.00013752341,0.0006400456],"domain_scores_gemma":[0.8437537,0.13818705,0.01635168,0.0009622004,0.00037268884,0.0003726961],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.339422,0.00019446661,0.0028304537,0.00009064657,0.0003845377,0.000048137656,0.00081145356,0.00037265176,0.00031257863],"category_scores_gemma":[0.26812968,0.00011723322,0.00089465175,0.00014963589,0.00057545624,0.00030773602,0.0000750647,0.0012902906,0.0005492723],"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":[0.0007115377,0.00023450176,0.76278156,0.000048946727,0.00044518983,0.0000031859624,0.000333844,0.0044317194,0.0000010869543,0.08828888,0.1315675,0.011152067],"study_design_scores_gemma":[0.0011513985,0.00059410406,0.27614734,0.0000607218,0.00002520943,0.00004084818,0.00028746316,0.008323399,0.0000013196482,0.11383569,0.5993305,0.00020203473],"about_ca_topic_score_codex":0.0000757183,"about_ca_topic_score_gemma":0.00010856655,"teacher_disagreement_score":0.4866342,"about_ca_system_score_codex":0.00025080002,"about_ca_system_score_gemma":0.00038065715,"threshold_uncertainty_score":0.73803514},"labels":[],"label_agreement":null},{"id":"W1967986797","doi":"10.1016/j.jclinepi.2013.09.003","title":"Complex interventions–how should systematic reviews of their impact differ from reviews of simple or complicated interventions?","year":2013,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Ottawa","keywords":"Psychological intervention; Systematic review; Simple (philosophy); MEDLINE; Medicine; Biology; Nursing; Epistemology; Philosophy","score_opus":0.9679954754962593,"score_gpt":0.7230819548930575,"score_spread":0.24491352060320182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967986797","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050207563,0.19757648,0.19901788,0.0054248683,0.5754461,0.014597822,0.0025254374,0.000014267308,0.00037636896],"genre_scores_gemma":[0.0404609,0.21836536,0.078698695,0.0025796373,0.64030415,0.0010768794,0.002214624,0.00041028197,0.015889479],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.37637752,0.3884348,0.2277626,0.0018387146,0.0048443936,0.00074196846],"domain_scores_gemma":[0.040734917,0.5877077,0.35238445,0.008449246,0.009850664,0.0008730114],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.6569844,0.0012719837,0.10602555,0.0010416793,0.000091965434,0.00021292293,0.007987479,0.0018713945,0.040594026],"category_scores_gemma":[0.9291396,0.00043996336,0.07719563,0.0012734965,0.0006733839,0.0003694519,0.00070730824,0.0030569283,0.00097109674],"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":[0.000113326016,0.0005315483,0.0035556788,0.028380811,0.0032713315,0.0000031148033,0.000035998222,0.0000085810725,0.000007942787,0.000052850246,0.95863444,0.005404379],"study_design_scores_gemma":[0.0010618465,0.0018156865,0.008986617,0.05284168,0.005855158,0.000028598934,0.00011960157,0.0012686979,7.3145003e-7,0.012608718,0.9149722,0.00044047993],"about_ca_topic_score_codex":0.00011593352,"about_ca_topic_score_gemma":0.000117918564,"teacher_disagreement_score":0.3356426,"about_ca_system_score_codex":0.00012224815,"about_ca_system_score_gemma":0.0004090199,"threshold_uncertainty_score":0.99980676},"labels":[],"label_agreement":null},{"id":"W1968322257","doi":"10.1016/s0895-4356(00)00319-x","title":"The association between neck pain intensity, physical functioning, depressive symptomatology and time-to-claim-closure after whiplash","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":149,"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; University of Alberta; Institute for Work & Health; University of Toronto","funders":"","keywords":"Whiplash; Closure (psychology); Medicine; Cohort; Neck pain; Physical therapy; Cohort study; Psychiatry; Poison control; Internal medicine; Medical emergency; Alternative medicine","score_opus":0.043278600337056994,"score_gpt":0.39976168868219836,"score_spread":0.35648308834514136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968322257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94722253,0.0002004115,0.0010665433,0.050190635,0.0006286569,0.00021048498,0.0000012369734,0.000015741263,0.00046374783],"genre_scores_gemma":[0.9890569,0.00019456519,0.00076569605,0.0059552356,0.0030946552,0.000008096093,0.000004215371,0.000014889537,0.00090574427],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99189955,0.005079454,0.0021758543,0.0002587332,0.00023549485,0.00035093635],"domain_scores_gemma":[0.94003236,0.05721552,0.0015672413,0.00020722288,0.0005886321,0.0003890378],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022794588,0.00015565472,0.0017860773,0.00008554609,0.00011178613,0.000010561516,0.00010738921,0.00045095594,0.00005759144],"category_scores_gemma":[0.14798585,0.00008913445,0.00059475657,0.00013467859,0.00024351306,0.000070526556,0.000072294555,0.0010566933,0.00010587717],"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":[0.00078413024,0.00009689936,0.9630492,0.000032524207,0.00037896784,0.0000060130383,0.00005676345,0.000012323165,0.000019550844,0.00009139346,0.020126967,0.015345273],"study_design_scores_gemma":[0.0011775285,0.002235301,0.96391773,0.00015007614,0.00021498406,0.000055489832,0.00003194015,0.0007901609,0.0000013383537,0.004999327,0.026345251,0.00008085309],"about_ca_topic_score_codex":0.000005376584,"about_ca_topic_score_gemma":0.000005508062,"teacher_disagreement_score":0.12519127,"about_ca_system_score_codex":0.00007341322,"about_ca_system_score_gemma":0.00008883475,"threshold_uncertainty_score":0.859191},"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":"W1969177955","doi":"10.1016/j.jclinepi.2007.03.009","title":"Manitoba and Saskatchewan administrative health care utilization databases are used differently to answer epidemiologic research questions","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"GlaxoSmithKline (Canada); University of Waterloo; University of Toronto; Memorial University of Newfoundland; Children's Hospital of Eastern Ontario","funders":"","keywords":"Database; MEDLINE; Medicine; Environmental health; Gerontology; Political science; Computer science","score_opus":0.9631184409650447,"score_gpt":0.7669054104845843,"score_spread":0.19621303048046046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969177955","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":null,"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":[0.0017283565,0.9837951,0.0055613737,0.004768073,0.0027848643,0.0010094288,0.00016868746,0.000026418355,0.00015768311],"genre_scores_gemma":[0.00045957795,0.97559935,0.018187106,0.0028945114,0.0025685905,0.00002785428,0.00006121095,0.000030773394,0.00017104215],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.44513917,0.5432344,0.008767726,0.0009832929,0.0005841893,0.001291188],"domain_scores_gemma":[0.5091566,0.48299396,0.00517726,0.00043831393,0.0010285879,0.0012052906],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.49570733,0.00044587394,0.008907556,0.00079362723,0.000786603,0.000021297543,0.0007717695,0.0016556694,0.00007541651],"category_scores_gemma":[0.73686045,0.00031687654,0.0010578346,0.00083025417,0.0021931238,0.00014800881,0.0002319541,0.0041680136,0.00002816775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001086705,0.0002068943,0.041592978,0.0009891182,0.00018768621,0.00006170126,0.0013611502,5.723384e-7,1.2331278e-8,0.0039168643,0.007921561,0.94267476],"study_design_scores_gemma":[0.00020898083,0.0012580588,0.072376244,0.004934256,0.00016456614,0.000055178352,0.012995235,2.416666e-7,2.65304e-8,0.0015663458,0.9062031,0.000237797],"about_ca_topic_score_codex":0.0024805663,"about_ca_topic_score_gemma":0.05921505,"teacher_disagreement_score":0.94243693,"about_ca_system_score_codex":0.00040077142,"about_ca_system_score_gemma":0.009765192,"threshold_uncertainty_score":0.99992836},"labels":[],"label_agreement":null},{"id":"W1969468904","doi":"10.1016/j.jclinepi.2011.11.013","title":"Formatting modifications in GRADE evidence profiles improved guideline panelists comprehension and accessibility to information. A randomized trial","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":59,"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":"Disk formatting; Randomized controlled trial; Guideline; Medicine; MEDLINE; Comprehension; Computer science; Surgery; Pathology; Biology","score_opus":0.9260169381358974,"score_gpt":0.6930870795120997,"score_spread":0.23292985862379767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969468904","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":[0.80303746,0.0014135046,0.17655057,0.01566628,0.0011801133,0.0020161737,0.000004118292,0.0000027877431,0.00012901702],"genre_scores_gemma":[0.9031436,0.00025784073,0.09244026,0.0035661384,0.000496383,0.000048069858,0.0000023804237,0.0000037169077,0.000041611616],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.5615575,0.23556608,0.19671352,0.0010385615,0.0040696403,0.0010547355],"domain_scores_gemma":[0.29682395,0.61337626,0.08029255,0.0030006552,0.0052101817,0.0012963912],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7724423,0.00022603615,0.011761251,0.0005455043,0.00008620885,0.00015376144,0.0011989309,0.00024343109,0.00036709063],"category_scores_gemma":[0.9233419,0.00009779235,0.0025278649,0.0007167256,0.00019537337,0.0019379758,0.00024608357,0.00060707587,0.00012812577],"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":[0.2835716,0.00087709166,0.42781588,0.00022174927,0.0005432208,0.000002029461,0.0021977676,0.0019104821,0.00007689134,0.006390154,0.07894402,0.1974491],"study_design_scores_gemma":[0.35247204,0.00055605924,0.34820226,0.00036581306,0.0005263913,0.00006922053,0.0007482981,0.23609096,0.0000049864725,0.033679582,0.026913926,0.00037045596],"about_ca_topic_score_codex":0.00002548461,"about_ca_topic_score_gemma":0.000007437298,"teacher_disagreement_score":0.37781018,"about_ca_system_score_codex":0.00003236084,"about_ca_system_score_gemma":0.00016184624,"threshold_uncertainty_score":0.8039756},"labels":[],"label_agreement":null},{"id":"W1969562628","doi":"10.1016/j.jclinepi.2013.07.022","title":"An efficient strategy allowed English-speaking reviewers to identify foreign-language articles eligible for a systematic review","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":18,"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 Work & Health; Canada Research Chairs; Hospital for Sick Children; Canadian Memorial Chiropractic College; University of Regina; Canadian Chiropractic Association; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"English language; Systematic review; Limiting; MEDLINE; Medicine; Randomized controlled trial; Computer science; Natural language processing; Linguistics; Psychology; Mathematics education; Pathology","score_opus":0.873056859627309,"score_gpt":0.7127758321373653,"score_spread":0.16028102748994366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969562628","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":[0.000040610907,0.9324669,0.057753015,0.0003104672,0.001570494,0.0074090646,0.000028085125,0.00000879004,0.0004125492],"genre_scores_gemma":[0.00014922519,0.9804059,0.012778195,0.0041106786,0.0018112196,0.00033669316,0.00001826655,0.00007047052,0.0003193039],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.4987149,0.30143237,0.1905793,0.0027143285,0.0052921064,0.0012670214],"domain_scores_gemma":[0.2995354,0.45968142,0.21664825,0.011642179,0.010051386,0.0024413618],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.80847585,0.0011940211,0.109457426,0.0010141818,0.00014875838,0.00044136558,0.007228193,0.00089118443,0.0011356605],"category_scores_gemma":[0.9188324,0.00049324054,0.03493658,0.001814387,0.0001674345,0.00023879361,0.0002549558,0.0014989878,0.001415037],"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":[0.000016929042,0.00017529882,0.000035453537,0.69499916,0.0015869059,0.000023006796,0.00011718382,0.00022478504,7.875685e-8,0.0018739107,0.0396389,0.26130837],"study_design_scores_gemma":[0.00021917201,0.0006342096,0.00001173063,0.4080758,0.011496353,0.00013079701,0.0001544852,0.0009301178,2.0743704e-8,0.0011330978,0.57682234,0.00039186922],"about_ca_topic_score_codex":0.0000040523946,"about_ca_topic_score_gemma":0.000008705397,"teacher_disagreement_score":0.53718346,"about_ca_system_score_codex":0.00011493121,"about_ca_system_score_gemma":0.00062563166,"threshold_uncertainty_score":0.99977744},"labels":[],"label_agreement":null},{"id":"W1970786793","doi":"10.1016/s0895-4356(02)00398-0","title":"Assessing the quality of drug detailing","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":26,"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; University of Toronto; McMaster University; Hamilton Health Sciences","funders":"Medical Research Council","keywords":"Medicine; Quality (philosophy); Family medicine; Quality Score; Quality assessment; Medical physics; External quality assessment; Pathology; Operations management","score_opus":0.9356265295613185,"score_gpt":0.761912922359577,"score_spread":0.17371360720174156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970786793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314982,0.004730191,0.00058771303,0.05549199,0.0038078243,0.00014866532,0.0000085542015,0.0000148969075,0.0037119584],"genre_scores_gemma":[0.97483975,0.0025108838,0.000977604,0.01941425,0.0019274664,0.000002355064,8.545981e-7,0.000011902937,0.00031490784],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9592908,0.031940848,0.007655076,0.0002586387,0.00024044218,0.0006141891],"domain_scores_gemma":[0.8845199,0.108924046,0.005110835,0.0002899391,0.0004865246,0.0006687746],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0874004,0.00019360811,0.0021700163,0.00007292569,0.00023229903,0.000008081056,0.00067604333,0.0009544935,0.0022594314],"category_scores_gemma":[0.07241628,0.00011896658,0.0008732006,0.00020365579,0.0011194899,0.0002302082,0.00010306465,0.0067360085,0.000054432006],"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":[0.0004143594,0.00075771403,0.8516157,0.00014306538,0.00043526344,0.000042974163,0.0003059434,0.0008659671,0.0005710218,0.008616934,0.020161446,0.1160696],"study_design_scores_gemma":[0.0061303945,0.0007820998,0.56935686,0.00020122249,0.00071427244,0.000346165,0.0012711004,0.02243441,0.0017471983,0.031720757,0.36479688,0.0004986304],"about_ca_topic_score_codex":0.000017021515,"about_ca_topic_score_gemma":0.0000063451985,"teacher_disagreement_score":0.34463543,"about_ca_system_score_codex":0.00003521933,"about_ca_system_score_gemma":0.00015394654,"threshold_uncertainty_score":0.99865264},"labels":[],"label_agreement":null},{"id":"W1970929827","doi":"10.1016/j.jclinepi.2011.12.013","title":"Methodologists and context experts disagreed regarding managing conflicts of interest of clinical practice guidelines panels","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University","funders":"","keywords":"Content analysis; Context (archaeology); Guideline; Psychology; Quality (philosophy); MEDLINE; Attrition; Public relations; Medical education; Medicine; Political science; Sociology; Social science","score_opus":0.9320101384011162,"score_gpt":0.7240665264182771,"score_spread":0.20794361198283917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970929827","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":[0.8556934,0.006672861,0.04457899,0.087832026,0.0042587193,0.000426966,0.00000829874,0.000016541908,0.0005121702],"genre_scores_gemma":[0.7653596,0.008680606,0.20220934,0.021002362,0.0026772888,0.0000021409733,0.000005201713,0.000025204043,0.00003826075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9564296,0.014684432,0.02750019,0.00043387886,0.0004147555,0.00053716946],"domain_scores_gemma":[0.38015896,0.56990206,0.041970573,0.00092964206,0.005704324,0.001334435],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17995255,0.00027720656,0.0056544123,0.00019380299,0.00003689004,0.0000054221264,0.00028118165,0.0005542045,0.00009251327],"category_scores_gemma":[0.9236094,0.000193647,0.0011502887,0.00016583705,0.000974816,0.00063699996,0.0002741335,0.0014640942,0.0000047007347],"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":[0.0070101037,0.00083294534,0.49793974,0.00017539843,0.0010869285,0.00005833966,0.00031016718,0.000012366629,0.00043524225,0.0022046338,0.010072369,0.4798618],"study_design_scores_gemma":[0.02170543,0.009863871,0.6515954,0.0021395648,0.00439054,0.0045612,0.012840513,0.0012909941,0.000619515,0.0066643637,0.28375962,0.0005689334],"about_ca_topic_score_codex":0.00017151839,"about_ca_topic_score_gemma":0.000014068185,"teacher_disagreement_score":0.7436568,"about_ca_system_score_codex":0.000027876096,"about_ca_system_score_gemma":0.00028428316,"threshold_uncertainty_score":0.84441143},"labels":[],"label_agreement":null},{"id":"W1970961445","doi":"10.1016/j.jclinepi.2005.04.012","title":"Print format and sender recognition were related to survey completion rate","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; Canadian Association of Emergency Physicians","keywords":"Communication source; Respondent; Confidence interval; Medicine; Odds ratio; Odds; Demography; Statistics; Logistic regression; Internal medicine; Mathematics","score_opus":0.7488789514921543,"score_gpt":0.616519128791947,"score_spread":0.1323598227002073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970961445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97701246,0.00013373475,0.008188598,0.011942866,0.0015399462,0.00011332443,0.000007708982,0.000013292508,0.0010480981],"genre_scores_gemma":[0.98428434,0.0006535313,0.011396392,0.0028543037,0.00048709245,0.000001576961,0.00001218045,0.00000724836,0.0003033463],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.74871397,0.24669497,0.0037465093,0.00025691502,0.00016165541,0.0004259783],"domain_scores_gemma":[0.7880298,0.21010013,0.001253213,0.00008394759,0.0003224948,0.00021042879],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.44646898,0.000092181705,0.0011071016,0.000109696644,0.00018456337,0.000008122928,0.0001390961,0.0004773126,0.0001530403],"category_scores_gemma":[0.4124883,0.000072951785,0.0002013136,0.00015803041,0.00043964307,0.0001350699,0.000037700745,0.0006654032,0.000053254178],"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":[0.006372783,0.00010541313,0.9633703,0.0000045992165,0.000056425168,0.000017578826,0.00027331745,0.00006263183,0.000032362354,0.003144129,0.009178409,0.017382028],"study_design_scores_gemma":[0.00056265737,0.000325789,0.9335656,0.000019733801,0.000016338437,0.000030262045,0.00011919103,0.000035737834,0.000004757124,0.05180688,0.013435334,0.00007771124],"about_ca_topic_score_codex":0.00092745636,"about_ca_topic_score_gemma":0.0018986949,"teacher_disagreement_score":0.048662752,"about_ca_system_score_codex":0.000030208326,"about_ca_system_score_gemma":0.00016094345,"threshold_uncertainty_score":0.5924605},"labels":[],"label_agreement":null},{"id":"W1970971885","doi":"10.1016/j.jclinepi.2011.10.019","title":"A confidence interval approach to sample size estimation for interobserver agreement studies with multiple raters and outcomes","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":131,"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; York University","funders":"","keywords":"Confidence interval; Triage; Sample size determination; Reliability (semiconductor); Medicine; Estimation; Medical physics; Sample (material); Interval estimation; Statistics; Scale (ratio); Mathematics; Psychiatry; Power (physics)","score_opus":0.7278829789470725,"score_gpt":0.5892656106725227,"score_spread":0.13861736827454985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970971885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5510898,0.00021653275,0.4377364,0.009640635,0.0009378351,0.0003496362,0.0000052715254,0.0000034124268,0.000020464518],"genre_scores_gemma":[0.7412383,0.000052657768,0.25461778,0.003840247,0.00017331465,0.000019500561,3.9343047e-7,0.000004288615,0.0000535332],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912939,0.002782632,0.004568639,0.0003588049,0.00061785383,0.0003781493],"domain_scores_gemma":[0.6780325,0.31531006,0.0039408077,0.0005730192,0.0015092379,0.00063433225],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090695836,0.0001803115,0.002053035,0.00009117781,0.0000845443,0.000032034313,0.00047776164,0.00010881442,0.000027110376],"category_scores_gemma":[0.53522193,0.000089277244,0.00038261423,0.00012186735,0.00032151854,0.00036790594,0.00016256984,0.00029087608,0.000010835931],"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":[0.0011038019,0.0003167372,0.9745274,0.00003082355,0.00025387557,3.5719765e-7,0.00068008684,0.001985873,0.000007718636,0.001437612,0.0053834654,0.014272238],"study_design_scores_gemma":[0.0022373649,0.0028781104,0.9346225,0.00012928038,0.00009984955,0.000015531436,0.002355095,0.004781458,0.000017428785,0.04831425,0.004381427,0.00016765641],"about_ca_topic_score_codex":0.000017589427,"about_ca_topic_score_gemma":0.0000239838,"teacher_disagreement_score":0.44452614,"about_ca_system_score_codex":0.000051516865,"about_ca_system_score_gemma":0.000049445098,"threshold_uncertainty_score":0.93632},"labels":[],"label_agreement":null},{"id":"W1971077001","doi":"10.1016/j.jclinepi.2013.03.013","title":"Impact of definitions of loss to follow-up (LTFU) in antiretroviral therapy program evaluation: variation in the definition can have an appreciable impact on estimated proportions of LTFU","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":67,"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 Allergy and Infectious Diseases; Canadian Institutes of Health Research","keywords":"Medicine; Antiretroviral therapy; Demography; Statistics; Human immunodeficiency virus (HIV); Family medicine; Mathematics; Viral load","score_opus":0.4862726728048399,"score_gpt":0.5896331523011656,"score_spread":0.10336047949632576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971077001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953129,0.00007161502,0.0005904423,0.0016959348,0.000064010186,0.0015657041,0.00012942178,0.000004997797,0.00056494615],"genre_scores_gemma":[0.99490786,0.00024245087,0.004307279,0.00012330976,0.000101287915,0.00014479329,0.00014687472,0.000011901517,0.000014271885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9906094,0.004386809,0.003988056,0.00019614685,0.00047326653,0.00034633421],"domain_scores_gemma":[0.9893114,0.0063438215,0.0022325017,0.00038118046,0.001463624,0.0002674865],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015709266,0.00015688334,0.0015252855,0.00058919616,0.000034286535,0.0000073984643,0.00022786336,0.0002430211,0.0010209603],"category_scores_gemma":[0.045544505,0.00008935738,0.0009433159,0.00061107415,0.0002639608,0.00020051505,0.000018808116,0.0007676882,0.000006457919],"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":[0.0025034624,0.005694006,0.9331439,0.00004718102,0.00030853454,0.0000068472846,0.00042944762,0.0021161463,0.0006460074,0.0007255076,0.0031312613,0.05124766],"study_design_scores_gemma":[0.0034169077,0.04823921,0.92185193,0.0004901705,0.000073042036,0.000038718827,0.0001373004,0.013691497,0.000040969848,0.011950106,0.000008422355,0.00006170234],"about_ca_topic_score_codex":0.0022567476,"about_ca_topic_score_gemma":0.0003538441,"teacher_disagreement_score":0.051185958,"about_ca_system_score_codex":0.00014499333,"about_ca_system_score_gemma":0.001018311,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W1971344453","doi":"10.1016/j.jclinepi.2007.01.005","title":"Empty systematic reviews: hidden perils and lessons learned","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":111,"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 Royal University; University of Ottawa","funders":"","keywords":"Systematic review; MEDLINE; Medicine; Data science; Computer science; Political science","score_opus":0.8123737798754366,"score_gpt":0.7065440867311087,"score_spread":0.10582969314432789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971344453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42500272,0.043624457,0.051095746,0.424907,0.005776748,0.003953382,0.0000054110515,0.0001775914,0.045456935],"genre_scores_gemma":[0.90793806,0.0559397,0.02773557,0.004053707,0.0027415217,0.000014053257,3.6843247e-7,0.000022078659,0.0015549556],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9666295,0.02473688,0.007109158,0.00029131226,0.0005204302,0.00071272353],"domain_scores_gemma":[0.8706856,0.12388955,0.003934421,0.00032267085,0.00046409928,0.00070369866],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33225122,0.000119770724,0.0028514348,0.00015791744,0.00018955654,0.000020701653,0.000620672,0.0004979381,0.00011471288],"category_scores_gemma":[0.5299141,0.00008080824,0.000544174,0.00022737424,0.0010962978,0.00015347931,0.00010378758,0.0012528956,0.000046925117],"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":[0.00058473356,0.0004848512,0.28464767,0.00554972,0.0003636215,0.00041582133,0.0035404554,0.000002532999,0.00007341914,0.22767681,0.07765924,0.39900112],"study_design_scores_gemma":[0.0015966977,0.001846525,0.15678005,0.008682831,0.00028598076,0.00035665857,0.0070357807,0.00009471795,0.000012746034,0.30483738,0.5178945,0.0005760909],"about_ca_topic_score_codex":0.00013901973,"about_ca_topic_score_gemma":0.00021480164,"teacher_disagreement_score":0.4829353,"about_ca_system_score_codex":0.00007438368,"about_ca_system_score_gemma":0.00030175922,"threshold_uncertainty_score":0.6875879},"labels":[],"label_agreement":null},{"id":"W1971672914","doi":"10.1016/j.jclinepi.2006.01.012","title":"Testing multiple statistical hypotheses resulted in spurious associations: a study of astrological signs and health","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Paranormal Experiences and Beliefs","field":"Psychology","cited_by":137,"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; Women's College Hospital; University of Toronto; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Cohort; Spurious relationship; Cohort study; Demography; Epidemiology; Sign (mathematics); Statistics; Internal medicine; Mathematics","score_opus":0.5524845001395152,"score_gpt":0.5784867502226196,"score_spread":0.026002250083104417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971672914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951608,0.0006392951,0.0021258083,0.0010508442,0.00037482058,0.00019977998,0.000019186487,0.000008088338,0.00042136706],"genre_scores_gemma":[0.99152786,0.000036315087,0.007336215,0.00071958685,0.0003390242,0.0000069158436,0.0000023789253,0.0000071007976,0.000024592191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863458,0.006913949,0.0058371164,0.00029231363,0.00017289232,0.00043788244],"domain_scores_gemma":[0.91514206,0.08098797,0.0034260955,0.00014085135,0.00014140426,0.00016162003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0213978,0.00013636336,0.0023201443,0.00013918836,0.00005335888,0.0000045184142,0.00018065599,0.0002509609,0.000045479504],"category_scores_gemma":[0.07767251,0.000096580465,0.00012620825,0.00020738122,0.0002946935,0.00005257199,0.0000466725,0.00076282583,0.0000041689577],"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":[0.0005592142,0.002307135,0.9844039,0.0000048263105,0.000049827893,0.00006814076,0.0002590016,0.00041607604,0.000014359155,0.0019672494,0.00072597,0.009224287],"study_design_scores_gemma":[0.0026276747,0.0093030855,0.9827811,0.000027015516,0.000015112486,0.00006196716,0.00062013493,0.00046400222,2.3652565e-7,0.0037697589,0.00025473093,0.00007516856],"about_ca_topic_score_codex":0.0031581768,"about_ca_topic_score_gemma":0.0007414372,"teacher_disagreement_score":0.074074015,"about_ca_system_score_codex":0.000031746105,"about_ca_system_score_gemma":0.00013700123,"threshold_uncertainty_score":0.9300966},"labels":[],"label_agreement":null},{"id":"W1971721633","doi":"10.1016/j.jclinepi.2004.10.018","title":"The development of a comorbidity index with physical function as the outcome","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Nutrition and Health in Aging","field":"Medicine","cited_by":1205,"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 Toronto; SickKids Foundation; Institute for Work & Health; Toronto Public Health; Queen's University","funders":"Canadian Arthritis Network; Health Canada","keywords":"Comorbidity; Medicine; Index (typography); Psychological intervention; Medical diagnosis; Physical therapy; Gerontology; Internal medicine; Psychiatry","score_opus":0.6455773912205373,"score_gpt":0.6370778808733751,"score_spread":0.00849951034716212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971721633","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":[0.00071998645,0.9805337,0.0014785844,0.014867957,0.0012890532,0.00055693137,0.0000019428344,0.000008902796,0.0005428997],"genre_scores_gemma":[0.0009604225,0.9893883,0.002198593,0.003964644,0.0032682118,0.000013737642,0.0000042435,0.000021193046,0.00018064248],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98746485,0.003978357,0.0076831407,0.00020242875,0.00035256406,0.00031867417],"domain_scores_gemma":[0.9514946,0.039750926,0.0077296486,0.00037086956,0.00035542616,0.00029857605],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028423287,0.00024519346,0.0061827856,0.00008838774,0.00016389512,0.000004137056,0.00031328734,0.00041908064,0.00004028815],"category_scores_gemma":[0.017300745,0.000089067595,0.0012979707,0.00016226337,0.0004948397,0.000027414259,0.000060103474,0.0033452879,0.000036653277],"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":[0.0005498377,0.00027454525,0.0070426934,0.0019671354,0.00045195647,0.000009050709,0.000030743624,0.0000011623913,1.0437962e-8,0.0009337106,0.0019747596,0.9867644],"study_design_scores_gemma":[0.0009992312,0.0009363559,0.015402583,0.004665649,0.00082574895,0.0004651215,0.000030049456,0.00001830863,2.4482109e-8,0.00082578504,0.9757527,0.00007840582],"about_ca_topic_score_codex":0.0000031343661,"about_ca_topic_score_gemma":0.000013362391,"teacher_disagreement_score":0.986686,"about_ca_system_score_codex":0.00010196436,"about_ca_system_score_gemma":0.0018710955,"threshold_uncertainty_score":0.99895406},"labels":[],"label_agreement":null},{"id":"W1972320894","doi":"10.1016/j.jclinepi.2009.12.003","title":"The quality of eight health status measures were compared for chronic opioid dependence","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Opioid Use Disorder Treatment","field":"Medicine","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":"University of British Columbia; Université de Montréal; Vancouver Coastal Health; Centre for Advancing Health Outcomes","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Medicine; Opioid; Quality (philosophy); Chronic pain; Physical therapy; Internal medicine; Physics","score_opus":0.31794270238995753,"score_gpt":0.5632161794712534,"score_spread":0.24527347708129582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972320894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93427706,0.01348886,0.0049322075,0.04316409,0.003178246,0.00075750373,0.000047405618,0.000011777108,0.00014287917],"genre_scores_gemma":[0.97668695,0.00875418,0.011650247,0.0018616201,0.0009391564,0.000012631691,0.000011222898,0.000017089764,0.00006687293],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9898418,0.0027484314,0.0062317937,0.00025833017,0.00034106348,0.0005785877],"domain_scores_gemma":[0.95281154,0.04048353,0.0049845683,0.000546609,0.0006418048,0.0005319212],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031270407,0.00017298464,0.0029640687,0.00005496914,0.00011952781,0.000004103428,0.00030606557,0.00027111883,0.000043627908],"category_scores_gemma":[0.06829042,0.00009345138,0.0009486492,0.00006815175,0.00050439086,0.000046518264,0.000044622222,0.0012400213,0.0000056419326],"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":[0.0036214099,0.0009929348,0.8895466,0.00035307807,0.00069013616,0.0000044806634,0.00018142104,0.000040070285,0.00029262644,0.006716804,0.0096795475,0.087880924],"study_design_scores_gemma":[0.005407174,0.0038809767,0.9001978,0.000114886905,0.000111642454,0.000039507326,0.00014655778,0.00024509453,0.00006940972,0.010047899,0.07965716,0.00008190915],"about_ca_topic_score_codex":0.000225422,"about_ca_topic_score_gemma":0.00070126867,"teacher_disagreement_score":0.08779902,"about_ca_system_score_codex":0.000098109966,"about_ca_system_score_gemma":0.0025994626,"threshold_uncertainty_score":0.99751097},"labels":[],"label_agreement":null},{"id":"W1972425547","doi":"10.1016/s0895-4356(02)00389-x","title":"A comparison of published head and neck stage groupings in laryngeal cancer using data from two countries","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Head and Neck Cancer Studies","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; University of Toronto; Queen's University; Kingston General Hospital","funders":"","keywords":"Medicine; Head and neck cancer; Ranking (information retrieval); Stage (stratigraphy); Population; Hazard ratio; Head and neck; Consistency (knowledge bases); Demography; Statistics; Cancer; Surgery; Internal medicine; Mathematics; Confidence interval; Artificial intelligence; Environmental health; Computer science","score_opus":0.5756150618656891,"score_gpt":0.5928453991152514,"score_spread":0.017230337249562244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972425547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96073157,0.026334118,0.00017810184,0.011805224,0.00061721005,0.000093081995,0.00006167949,0.000004474153,0.00017452534],"genre_scores_gemma":[0.9802633,0.010518206,0.0051346025,0.0030700024,0.0009679049,8.1620556e-7,0.000007040745,0.000010830978,0.000027312853],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99432015,0.0009555221,0.0039187637,0.00031008,0.00019633224,0.00029916107],"domain_scores_gemma":[0.9871299,0.010136024,0.0019848458,0.00032553755,0.00019501014,0.00022868197],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074189585,0.00014044227,0.003796614,0.000111017696,0.00003424045,0.0000062067784,0.00022773774,0.00020211266,0.00033211173],"category_scores_gemma":[0.022618482,0.000100222256,0.0001516746,0.00012246676,0.00041102985,0.00026075533,0.00018217797,0.00093686546,0.0000015166364],"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":[0.0007468473,0.00020055081,0.9865759,0.000081483,0.00019260471,0.000038623202,0.0002685495,0.000043653603,0.00002855246,0.0000828598,0.008260522,0.003479874],"study_design_scores_gemma":[0.0058050277,0.00089635747,0.9454463,0.0006997205,0.00017543886,0.000025333926,0.00014511825,0.028742215,0.0000070708456,0.00043405136,0.017530397,0.00009293794],"about_ca_topic_score_codex":0.0021028805,"about_ca_topic_score_gemma":0.0013312937,"teacher_disagreement_score":0.041129548,"about_ca_system_score_codex":0.00004835857,"about_ca_system_score_gemma":0.00016616202,"threshold_uncertainty_score":0.9856144},"labels":[],"label_agreement":null},{"id":"W1972607753","doi":"10.1016/s0895-4356(00)00306-1","title":"Changing rates of cancer","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sarcoma Diagnosis and Treatment","field":"Medicine","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":"Mount Sinai Hospital; University of Toronto","funders":"National Cancer Institute; Medical Research Council; Cancer Care Ontario","keywords":"Soft tissue sarcoma; Medicine; Sarcoma; Epidemiology; Cancer; Soft tissue; Incidence (geometry); Population; Cancer registry; Surveillance, Epidemiology, and End Results; Confidence interval; Linear regression; Surgery; Statistics; Demography; Internal medicine; Pathology; Mathematics; Environmental health","score_opus":0.3767795799958881,"score_gpt":0.5743902938223706,"score_spread":0.1976107138264825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972607753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9700285,0.009081574,0.0002216162,0.019479327,0.00065678323,0.000063120766,0.0000012825112,0.0000031652805,0.00046462813],"genre_scores_gemma":[0.9775,0.014687344,0.0022848588,0.0043410086,0.0010488434,0.0000030381239,7.7092886e-7,0.0000073039873,0.000126788],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99650615,0.00060841313,0.002469129,0.00010519609,0.0000982496,0.00021287717],"domain_scores_gemma":[0.9862826,0.011526367,0.0016606444,0.00013049813,0.00020801896,0.00019188016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006393089,0.000081281105,0.0018611455,0.00011604861,0.0000155618,7.431646e-7,0.00007009523,0.00014295265,0.00034098126],"category_scores_gemma":[0.01518322,0.00004842615,0.0006085641,0.000116580035,0.0001141938,0.000027016125,0.000021291447,0.000306774,0.000008662393],"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":[0.00036914437,0.00040727315,0.9173745,0.000013364092,0.0002932395,0.00016005045,0.000018263,0.000023363738,0.000015168629,0.0003748919,0.00152235,0.07942843],"study_design_scores_gemma":[0.0021445996,0.0009068792,0.9790928,0.00023193873,0.00024301297,0.00028608565,0.00004575234,0.00011772659,0.00015421594,0.0014204541,0.015318493,0.00003807038],"about_ca_topic_score_codex":0.00003539421,"about_ca_topic_score_gemma":0.00000803909,"teacher_disagreement_score":0.079390354,"about_ca_system_score_codex":0.000022358152,"about_ca_system_score_gemma":0.00011875177,"threshold_uncertainty_score":0.9931123},"labels":[],"label_agreement":null},{"id":"W1973232037","doi":"10.1016/j.jclinepi.2007.03.008","title":"A systematic review identified few methods and strategies describing when and how to update systematic reviews","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":94,"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 of Population and Public Health; Ottawa Hospital; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"University of Ottawa","keywords":"PsycINFO; Systematic review; MEDLINE; Meta-analysis; Computer science; Health care; Medicine; Data science; Data mining; Medical physics","score_opus":0.9661257411541672,"score_gpt":0.7395959021125518,"score_spread":0.2265298390416154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973232037","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001570399,0.81938964,0.16935548,0.0018823385,0.001214302,0.008026103,0.000007792591,0.000004612594,0.00011816909],"genre_scores_gemma":[9.1973305e-7,0.8675868,0.12725084,0.003394535,0.0004180145,0.00020030711,0.0000032818525,0.000046398534,0.0010989375],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.15357335,0.6476741,0.19108222,0.0027006848,0.0039419704,0.0010277298],"domain_scores_gemma":[0.11507431,0.6255709,0.24588966,0.0077629546,0.003655718,0.0020464915],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.9230813,0.0015144404,0.17753556,0.0014668854,0.00017130289,0.0011765611,0.0044553,0.0011118533,0.00042837622],"category_scores_gemma":[0.9362876,0.0005851013,0.019335832,0.0016764428,0.0003397518,0.0006310816,0.00070081436,0.0022694059,0.0007320268],"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":[0.0000034941124,0.000021270645,0.00001620335,0.82842547,0.0017042698,0.000032015967,0.000030826126,2.400843e-7,2.2275293e-8,0.0019434445,0.022160187,0.14566255],"study_design_scores_gemma":[0.00008968939,0.000121263074,0.0000048002903,0.6097373,0.019601619,0.0012110262,0.0001163889,0.000032857144,4.012946e-9,0.004975938,0.36379126,0.00031790833],"about_ca_topic_score_codex":0.0000028193067,"about_ca_topic_score_gemma":0.000011217907,"teacher_disagreement_score":0.34163105,"about_ca_system_score_codex":0.00008722613,"about_ca_system_score_gemma":0.0004942819,"threshold_uncertainty_score":0.9998603},"labels":[],"label_agreement":null},{"id":"W1973427646","doi":"10.1016/j.jclinepi.2014.02.022","title":"Letter reply to Kris Doggen et al.: The right indicator for the job: Different levels of rigor may be appropriate for the development of quality indicators","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","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 Toronto; St. Michael's Hospital; University of Calgary","funders":"","keywords":"Quality (philosophy); Context (archaeology); Rigour; Computer science; Psychology; Mathematics; Epistemology; Geography","score_opus":0.2759194628690502,"score_gpt":0.4911603444272784,"score_spread":0.21524088155822818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973427646","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":[0.028210739,0.00037758998,0.11848207,0.8493008,0.002001242,0.001508196,0.00007717193,0.000009537485,0.00003267363],"genre_scores_gemma":[0.070461206,0.00013246464,0.0087237265,0.91522074,0.004935463,0.00023203585,0.000015908761,0.000050656887,0.00022779117],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865823,0.0043850364,0.0072955866,0.0005274892,0.00066934753,0.0005402485],"domain_scores_gemma":[0.88049495,0.10871657,0.009200553,0.00094840856,0.00044610063,0.00019341339],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055295046,0.0004017625,0.0037753321,0.00023735927,0.00021353865,0.000010159489,0.0009806843,0.00087715936,0.00006325627],"category_scores_gemma":[0.040119253,0.00015593402,0.001947706,0.00017018273,0.0006296214,0.000028690838,0.00017551557,0.0034591022,0.0000024264198],"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":[0.0063080317,0.00008742674,0.007059911,0.0002589026,0.0018868687,0.000002283534,0.00034462652,0.000016495524,0.000022075228,0.00010457737,0.9525147,0.0313941],"study_design_scores_gemma":[0.0016480739,0.0027080341,0.15499896,0.00020161596,0.0006767789,0.000033989592,0.00002851824,0.00005516005,0.00027805177,0.0008113341,0.83840555,0.00015390819],"about_ca_topic_score_codex":0.000053029475,"about_ca_topic_score_gemma":0.000046464826,"teacher_disagreement_score":0.14793904,"about_ca_system_score_codex":0.00010841722,"about_ca_system_score_gemma":0.0006671214,"threshold_uncertainty_score":0.99884},"labels":[],"label_agreement":null},{"id":"W197423303","doi":"10.1016/s0895-4356(01)00347-x","title":"When should an effective treatment be used?","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"University of Waterloo; McMaster University","funders":"H2020 European Research Council","keywords":"Number needed to treat; Medicine; Adverse effect; Event (particle physics); Relative risk; Confidence interval; Internal medicine; Physics","score_opus":0.8740002476166959,"score_gpt":0.6452133560052685,"score_spread":0.2287868916114274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197423303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7657379,0.0021933562,0.012678887,0.21378963,0.0027880103,0.00048085197,0.00004937378,0.000023251672,0.0022587336],"genre_scores_gemma":[0.86229396,0.003126368,0.020196231,0.106182724,0.0069733076,0.000052275405,0.000018769502,0.000059603328,0.00109679],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9724725,0.008228357,0.018171104,0.0005240806,0.00008300744,0.00052096095],"domain_scores_gemma":[0.9262038,0.05930096,0.013124149,0.00055333285,0.00014387202,0.0006739292],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15547608,0.0002327461,0.00510361,0.00027638252,0.00010151646,0.000018058043,0.00039713213,0.00051601906,0.00085316127],"category_scores_gemma":[0.12608384,0.00021171392,0.0008586331,0.00009215109,0.00020040224,0.00049082487,0.00003506796,0.0006094706,0.00057003],"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":[0.00020058389,0.00055861345,0.91211426,0.000026813357,0.00032502538,0.000018086377,0.00060446974,0.0003996161,4.7204526e-7,0.053196706,0.025984587,0.0065707853],"study_design_scores_gemma":[0.0025653462,0.0034241404,0.41650042,0.00004345396,0.00003277085,0.00011331664,0.00022647205,0.002682953,8.0208883e-7,0.13802652,0.43615204,0.00023177534],"about_ca_topic_score_codex":0.00053922087,"about_ca_topic_score_gemma":0.00021877745,"teacher_disagreement_score":0.4956138,"about_ca_system_score_codex":0.00046578152,"about_ca_system_score_gemma":0.0002033233,"threshold_uncertainty_score":0.93415177},"labels":[],"label_agreement":null},{"id":"W1974682148","doi":"10.1016/j.jclinepi.2003.11.010","title":"Three independent factors predicted adherence in a randomized controlled trial of resistance exercise training among prostate cancer survivors","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":146,"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; Ottawa Regional Cancer Foundation; University of Alberta","funders":"National Cancer Institute; Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Medicine; Randomized controlled trial; Prostate cancer; Quality of life (healthcare); Physical therapy; Physical fitness; Multivariate analysis; Internal medicine; Cancer","score_opus":0.14277708082061838,"score_gpt":0.43641890933130734,"score_spread":0.293641828510689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974682148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98829496,0.0028518746,0.00087910896,0.0016088886,0.0034018578,0.0027221951,0.00001650164,0.000014430197,0.00021015678],"genre_scores_gemma":[0.9939816,0.004573738,0.00036315434,0.00023569871,0.00053090544,0.00016567315,0.0000045859656,0.000023797427,0.00012084152],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.98560995,0.0034071554,0.009547764,0.0003818869,0.0005595241,0.0004937193],"domain_scores_gemma":[0.9675248,0.024434676,0.0067111035,0.00031654476,0.0005853869,0.00042745812],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03643436,0.00030113786,0.01195815,0.00030005115,0.000029355455,0.0000052963724,0.00027487884,0.0005582001,0.0001009137],"category_scores_gemma":[0.07440179,0.00018738068,0.002277247,0.00031547947,0.00074989884,0.00012206262,0.000040023042,0.0015611004,5.833987e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.70855045,0.000306561,0.2870333,0.000075392134,0.00038421055,0.000058657046,0.0012938807,0.0002932942,0.0000049514965,0.0001256948,0.000032716613,0.0018409106],"study_design_scores_gemma":[0.81681556,0.0014156082,0.1724274,0.0018827606,0.0005510159,0.000006233796,0.0006587754,0.00009110773,0.000011472971,0.0059629274,0.000043111377,0.00013404562],"about_ca_topic_score_codex":0.0044706604,"about_ca_topic_score_gemma":0.043874316,"teacher_disagreement_score":0.114605896,"about_ca_system_score_codex":0.00013295187,"about_ca_system_score_gemma":0.0015743439,"threshold_uncertainty_score":0.9921936},"labels":[],"label_agreement":null},{"id":"W1975012984","doi":"10.1016/j.jclinepi.2014.09.025","title":"The special case of the 2 × 2 table: asymptotic unconditional McNemar test can be used to estimate sample size even for analysis based on GEE","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"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; Institute for Clinical Evaluative Sciences; University Health Network; University of Toronto; SickKids Foundation; Hospital for Sick Children; Women's College Hospital","funders":"Canadian Institutes of Health Research","keywords":"McNemar's test; Mathematics; Sample size determination; Statistics; Generalized estimating equation","score_opus":0.2801607696838403,"score_gpt":0.5476459757565667,"score_spread":0.2674852060727264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975012984","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":[0.025979443,0.0000032970845,0.94978595,0.022281317,0.00083929417,0.0002791522,0.0006580168,0.0000054692905,0.00016806708],"genre_scores_gemma":[0.26092264,0.0000024449303,0.7340625,0.0033250772,0.001615201,0.000013396486,0.0000041058056,0.000016599897,0.000038082475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99165094,0.0040174522,0.0034420132,0.00024481525,0.00027692853,0.00036784163],"domain_scores_gemma":[0.4502286,0.54656047,0.0021829088,0.0003943057,0.0004029601,0.00023074799],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027167806,0.00018257885,0.0020105545,0.000076901015,0.00021513447,0.000014398221,0.00047374214,0.0002027464,0.00029057945],"category_scores_gemma":[0.78316087,0.00009181898,0.0008672945,0.0003625014,0.00038108398,0.000022511296,0.00005831845,0.00054256857,0.0000014626287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090064947,0.0007811738,0.17044632,0.00011680442,0.0009999947,0.000043366905,0.00006415643,0.0042641275,0.000019226283,0.7606765,0.03693975,0.024747914],"study_design_scores_gemma":[0.0009819296,0.0013771963,0.08023569,0.000068283385,0.0008700886,0.000049075043,0.000014893239,0.040307388,0.000017225842,0.87348074,0.0024819057,0.0001155745],"about_ca_topic_score_codex":0.000054066346,"about_ca_topic_score_gemma":0.0006488046,"teacher_disagreement_score":0.755993,"about_ca_system_score_codex":0.00004442557,"about_ca_system_score_gemma":0.0003238196,"threshold_uncertainty_score":0.9415874},"labels":[],"label_agreement":null},{"id":"W1975481312","doi":"10.1016/s0895-4356(99)00113-4","title":"Measurement properties of the Activities Scale for Kids","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cerebral Palsy and Movement Disorders","field":"Medicine","cited_by":303,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Rasch model; Ask price; Ceiling effect; Construct validity; Medicine; Physical therapy; Scale (ratio); Psychometrics; Activities of daily living; Computerized adaptive testing; Correlation; Quality of life (healthcare); Psychology; Clinical psychology; Developmental psychology; Alternative medicine; Nursing","score_opus":0.3865245471939048,"score_gpt":0.44811578554747045,"score_spread":0.06159123835356567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975481312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9758735,0.001396864,0.00023189909,0.020585591,0.0005297612,0.00028282724,0.0000027085334,0.0000037236339,0.0010931704],"genre_scores_gemma":[0.9913575,0.0006946025,0.000582992,0.0062552565,0.00042957198,0.000005078973,2.0881438e-7,0.0000074559516,0.0006673334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99637103,0.00079120684,0.0023254834,0.00010742177,0.00021871927,0.00018612658],"domain_scores_gemma":[0.99742526,0.0011176665,0.0009479677,0.00019054004,0.00021244612,0.000106128675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010969232,0.000088980225,0.0013294334,0.0000293708,0.000039262184,0.0000013051385,0.00014270202,0.00014203548,0.00014474451],"category_scores_gemma":[0.013628643,0.00004358318,0.0008809319,0.0000454926,0.00035601028,0.000045697623,0.000016819304,0.00034142085,0.0000018457837],"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":[0.0068730684,0.0012852319,0.8050813,0.00050517113,0.0006692931,0.0000016469361,0.00023036853,0.00018018532,0.004447749,0.00068542344,0.017780181,0.16226035],"study_design_scores_gemma":[0.008989464,0.004978842,0.8507685,0.0017415097,0.000619219,0.00006799966,0.00046479548,0.0002807416,0.005055778,0.008425378,0.118435636,0.00017211253],"about_ca_topic_score_codex":0.000014447238,"about_ca_topic_score_gemma":0.000020302285,"teacher_disagreement_score":0.16208823,"about_ca_system_score_codex":0.000021218597,"about_ca_system_score_gemma":0.00024030171,"threshold_uncertainty_score":0.99468},"labels":[],"label_agreement":null},{"id":"W1976004150","doi":"10.1016/j.jclinepi.2006.09.016","title":"PsycINFO search strategies identified methodologically sound therapy studies and review articles for use by clinicians and researchers","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"U.S. National Library of Medicine","keywords":"PsycINFO; MEDLINE; Gold standard (test); Medicine; Systematic review; Sensitivity (control systems); Medical physics; Internal medicine","score_opus":0.9945290621338916,"score_gpt":0.7988806157544007,"score_spread":0.19564844637949086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976004150","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","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":[0.64852947,0.25952566,0.068495005,0.022347333,0.00032957236,0.00070497906,0.00000822529,0.0000027017866,0.000057026486],"genre_scores_gemma":[0.123347886,0.7491562,0.11438901,0.011427301,0.00033317483,0.00002037836,0.0000011706833,0.000013921309,0.0013109634],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8177623,0.14474759,0.0341574,0.00094147085,0.0018903733,0.00050086534],"domain_scores_gemma":[0.17828909,0.7951821,0.019286588,0.0017107202,0.0048387675,0.00069275167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7016942,0.0002625949,0.0123416735,0.0001874085,0.00022067709,0.00013538956,0.0009626924,0.00025702937,0.00025764183],"category_scores_gemma":[0.8118145,0.00010767477,0.0024778654,0.00042250197,0.0014384007,0.00047402846,0.00015136196,0.0007531377,0.00002870947],"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":[0.00055224914,0.00014968295,0.31949222,0.00039629478,0.0019210282,0.000027708009,0.00042329615,0.000025738846,0.00004095105,0.003257207,0.46257952,0.21113409],"study_design_scores_gemma":[0.002610404,0.0037312254,0.34003323,0.00075816765,0.0006498708,0.00046951792,0.0047926395,0.0012981517,0.0000062913896,0.4829124,0.16232845,0.00040965353],"about_ca_topic_score_codex":0.00000862783,"about_ca_topic_score_gemma":0.000015198533,"teacher_disagreement_score":0.6504345,"about_ca_system_score_codex":0.000012895109,"about_ca_system_score_gemma":0.00019169129,"threshold_uncertainty_score":0.8436521},"labels":[],"label_agreement":null},{"id":"W1976216986","doi":"10.1016/j.jclinepi.2011.08.001","title":"“Might” or “suggest”? No wording approach was clearly superior in conveying the strength of recommendation","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":26,"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; McMaster University","funders":"","keywords":"Action (physics); Guideline; Health benefits; Medicine; Intervention (counseling); Randomized controlled trial; Nursing; Surgery; Traditional medicine","score_opus":0.7871142849024128,"score_gpt":0.5886885309263855,"score_spread":0.19842575397602724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976216986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9519783,0.0011368517,0.0014921664,0.026219495,0.0055436413,0.0013720264,0.000019401408,0.00003655141,0.012201566],"genre_scores_gemma":[0.9634873,0.0014181893,0.029960664,0.0043522986,0.0005568599,0.000041820116,0.00000977823,0.00002583989,0.00014720575],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9601865,0.02959899,0.009217108,0.00026845833,0.00017895027,0.00054998643],"domain_scores_gemma":[0.91173524,0.07964502,0.006877893,0.00068798056,0.00079584535,0.00025799277],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028070409,0.00017708268,0.0019817303,0.00019788038,0.00028015417,0.0000023255875,0.0008806417,0.0006101829,0.0008747308],"category_scores_gemma":[0.1123719,0.000102391416,0.0003246092,0.00029661992,0.000345255,0.00024958697,0.00027242507,0.0037946766,0.000050920484],"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":[0.001623892,0.00027606805,0.97040135,0.00020056841,0.000063719825,0.0000024518308,0.0061467797,0.0000074197337,0.000004605805,0.0030886505,0.0026165026,0.015567979],"study_design_scores_gemma":[0.0039000693,0.0017896681,0.9368482,0.0010473286,0.0000675117,0.000024526405,0.019854795,0.0036530523,0.000006038693,0.0048189266,0.027761767,0.0002280934],"about_ca_topic_score_codex":0.00063266093,"about_ca_topic_score_gemma":0.00018621514,"teacher_disagreement_score":0.084301494,"about_ca_system_score_codex":0.00012783518,"about_ca_system_score_gemma":0.0008378843,"threshold_uncertainty_score":0.9985036},"labels":[],"label_agreement":null},{"id":"W1976419447","doi":"10.1016/j.jclinepi.2006.08.009","title":"Study of observed and self-reported HRQL in older frail adults found group-level congruence and individual-level differences","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","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 Alberta; Institute of Health Economics; McGill University; University of Calgary; Institute for Clinical Evaluative Sciences; University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Congruence (geometry); Gerontology; Psychology; Medicine; Demography; Clinical psychology; Social psychology","score_opus":0.5743340047614847,"score_gpt":0.5499821916442228,"score_spread":0.024351813117261867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976419447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99539655,0.0008297594,0.00030188166,0.0011479927,0.0017758554,0.00046804678,0.0000099023155,0.0000107569895,0.00005925141],"genre_scores_gemma":[0.99508077,0.0007159115,0.0031101534,0.0006194851,0.00041144693,0.0000050861026,0.0000026757243,0.000011860531,0.00004259133],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98715276,0.0047661304,0.0069055865,0.00036618477,0.00027798736,0.00053134246],"domain_scores_gemma":[0.9435482,0.05075145,0.0046998668,0.00023275195,0.0004173704,0.0003503501],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03445229,0.00020166686,0.0025316179,0.00024280653,0.00013527415,0.0000040436344,0.00023486285,0.00061654707,0.000031694428],"category_scores_gemma":[0.03101027,0.00014234625,0.00015405573,0.00022825696,0.00026981538,0.00012579157,0.00014625491,0.0015976739,0.000001400536],"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":[0.000721099,0.0009651717,0.9821338,0.000093683055,0.00022106472,0.00007436045,0.0052533266,5.4844367e-7,0.0000041485046,0.00008792313,0.00070993725,0.009734944],"study_design_scores_gemma":[0.006550018,0.0023195895,0.97699285,0.00035030273,0.0001755878,0.000044674907,0.011223104,0.000015699761,3.8847028e-7,0.0021010374,0.000104158855,0.00012261233],"about_ca_topic_score_codex":0.0014714532,"about_ca_topic_score_gemma":0.004520831,"teacher_disagreement_score":0.045985322,"about_ca_system_score_codex":0.0000360823,"about_ca_system_score_gemma":0.00025868425,"threshold_uncertainty_score":0.99423456},"labels":[],"label_agreement":null},{"id":"W1976653722","doi":"10.1016/j.jclinepi.2007.01.010","title":"A comprehensive appropriateness of prescribing questionnaire was validated by nominal consensus group","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Electronic Health Records Systems","field":"Health Professions","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":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Reimbursement; Inter-rater reliability; Medicine; Nominal group technique; Family medicine; Reliability (semiconductor); MEDLINE; Physical therapy; Psychology; Health care; Knowledge management; Computer science","score_opus":0.6557847159412883,"score_gpt":0.6532832261666663,"score_spread":0.0025014897746219455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976653722","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":[0.001056277,0.98166054,0.0048229196,0.000837026,0.009164753,0.002070365,0.000082055274,0.000039004084,0.00026703515],"genre_scores_gemma":[0.00023908795,0.9904252,0.0036364156,0.0012466761,0.0039389892,0.000058424605,0.00006987067,0.00012147507,0.0002638362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87447923,0.08815964,0.034264416,0.0007955281,0.0005175979,0.001783576],"domain_scores_gemma":[0.80264324,0.15714562,0.03687386,0.00073941477,0.0016685205,0.00092932885],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09937283,0.0007902642,0.021934938,0.00051518815,0.0002922427,0.0000035876783,0.0010431319,0.0046815793,0.00008371187],"category_scores_gemma":[0.09364162,0.00054692855,0.0027384027,0.0005059635,0.0006814207,0.00007130286,0.00024328544,0.0109905945,0.00010912123],"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":[0.0007538471,0.0004931803,0.004335687,0.07399973,0.0013216118,0.00012389738,0.000118987904,0.0000049154505,0.0000018839391,0.0021055096,0.04023657,0.8765042],"study_design_scores_gemma":[0.0016880484,0.0014404614,0.00039112428,0.060692713,0.00092185795,0.0004918683,0.00013365489,0.000042055864,1.3917223e-7,0.00063846976,0.9332042,0.00035543804],"about_ca_topic_score_codex":0.0007186314,"about_ca_topic_score_gemma":0.000055039436,"teacher_disagreement_score":0.8929676,"about_ca_system_score_codex":0.0008029262,"about_ca_system_score_gemma":0.006618584,"threshold_uncertainty_score":0.9996982},"labels":[],"label_agreement":null},{"id":"W1976724957","doi":"10.1016/j.jclinepi.2015.04.006","title":"A systematic review identifies shortcomings in the reporting of crossover trials in chronic painful conditions","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Crossover study; Medicine; Adverse effect; MEDLINE; Randomization; Randomized controlled trial; Crossover; Double blind; Systematic review; Family medicine; Alternative medicine; Internal medicine; Pathology","score_opus":0.9765257711436098,"score_gpt":0.777439614325029,"score_spread":0.19908615681858088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976724957","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007077864,0.9932134,0.0005399896,0.0011907185,0.0009655996,0.0036819598,0.000023284136,0.0000010168627,0.00031320975],"genre_scores_gemma":[0.00011569306,0.9971493,0.00045532794,0.0011587306,0.00048274593,0.0001469415,0.000009924381,0.000017737004,0.00046362597],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.024518643,0.55292964,0.4171618,0.00095344987,0.0039661783,0.00047028754],"domain_scores_gemma":[0.0055628377,0.5450763,0.44332993,0.0036317704,0.0021958111,0.00020333253],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9805187,0.00066552375,0.17634507,0.0011109242,0.000048965238,0.00015385155,0.004967092,0.0008290019,0.001156412],"category_scores_gemma":[0.9923898,0.0002212223,0.035655744,0.0022936955,0.0003912717,0.00025315495,0.00023018621,0.0024530399,0.00024966957],"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":[0.000012456103,0.00016893241,0.0018619947,0.82087886,0.0021538376,0.0002129191,0.00012437877,0.0000318867,3.049465e-8,0.0013776349,0.13248646,0.040690627],"study_design_scores_gemma":[0.00032662082,0.00015830534,0.00034833627,0.62065774,0.010137451,0.0007541228,0.00014997832,0.00007773663,4.4376227e-9,0.015825983,0.35135615,0.00020757169],"about_ca_topic_score_codex":0.000016363228,"about_ca_topic_score_gemma":0.000068774476,"teacher_disagreement_score":0.2188697,"about_ca_system_score_codex":0.00021490773,"about_ca_system_score_gemma":0.0024765355,"threshold_uncertainty_score":0.99984837},"labels":[],"label_agreement":null},{"id":"W1976776379","doi":"10.1016/j.jclinepi.2010.12.006","title":"Selecting participants that raise a clinical trial’s population attributable fraction can increase the treatment effect within the trial and reduce the required sample size","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"McMaster University","funders":"","keywords":"Sample size determination; Randomized controlled trial; Medicine; Attributable risk; Population; Relative risk; Epidemiology; Clinical trial; Internal medicine; Statistics; Environmental health; Confidence interval","score_opus":0.9098661758104728,"score_gpt":0.6814465334604112,"score_spread":0.22841964235006162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976776379","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9762058,0.00017051835,0.008403231,0.006513317,0.006086231,0.0024972807,0.000025596795,0.000032903117,0.000065081935],"genre_scores_gemma":[0.8907371,0.0007189848,0.10098689,0.0017297565,0.0056069847,0.00012850929,0.0000013753157,0.000044283093,0.00004609776],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8723277,0.11256974,0.012996132,0.0006986398,0.00057323725,0.00083456293],"domain_scores_gemma":[0.058307614,0.9284309,0.011420577,0.001024013,0.00028820903,0.00052867347],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26891547,0.00041414305,0.004973471,0.000044631095,0.00053005596,0.000048201564,0.00067002996,0.00074741506,0.00012544503],"category_scores_gemma":[0.9487704,0.000158995,0.0014319471,0.00024899503,0.0010544116,0.00012986234,0.00013997532,0.0022367379,0.000005785686],"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":[0.6801327,0.0026121107,0.19961128,0.000047592173,0.0020465772,0.000033578082,0.0005462885,0.000020123558,0.0000063829725,0.011062288,0.003573068,0.100308],"study_design_scores_gemma":[0.11789768,0.01869971,0.07658799,0.00011566647,0.0023411696,0.000060384587,0.0001661022,0.0008007784,0.000040910356,0.7824205,0.0006450616,0.00022400686],"about_ca_topic_score_codex":0.0011331077,"about_ca_topic_score_gemma":0.0002054208,"teacher_disagreement_score":0.81586117,"about_ca_system_score_codex":0.00012076304,"about_ca_system_score_gemma":0.00034904468,"threshold_uncertainty_score":0.9717638},"labels":[],"label_agreement":null},{"id":"W1976863236","doi":"10.1016/j.jclinepi.2007.10.009","title":"No consensus exists on search reporting methods for systematic reviews","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":64,"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; Children's Hospital of Eastern Ontario","funders":"U.S. Public Health Service","keywords":"Systematic review; MEDLINE; Medicine; Evidence-based medicine; Information retrieval; Computer science; Data science; Political science","score_opus":0.9856285468048307,"score_gpt":0.7921058423660167,"score_spread":0.19352270443881403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976863236","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07082978,0.013214188,0.87799466,0.011961034,0.007321639,0.0060096835,0.0000066636962,0.000009115174,0.01265325],"genre_scores_gemma":[0.024471095,0.0014156189,0.95000154,0.0071016075,0.0019751189,0.000070691574,0.0000013000353,0.000027086566,0.01493596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.15983744,0.5545552,0.27997884,0.0015214401,0.0033077083,0.00079936936],"domain_scores_gemma":[0.015739037,0.7546987,0.2194821,0.003604991,0.0058218497,0.00065331004],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.94055635,0.00036734634,0.038848303,0.00039855763,0.00019194269,0.000056679117,0.001936884,0.00038324815,0.0010119148],"category_scores_gemma":[0.99286777,0.00014193624,0.014739587,0.000587141,0.0003174841,0.00007814606,0.00010529559,0.0010304494,0.0017324917],"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":[0.00043904598,0.0004624242,0.1367553,0.009931973,0.0018291656,0.00023867885,0.00025026954,0.0005162962,0.00004659829,0.010333829,0.7680673,0.07112909],"study_design_scores_gemma":[0.0019014484,0.0033827792,0.038662896,0.008726897,0.0013804841,0.0053962204,0.00023934814,0.04257323,0.000013059748,0.063555144,0.8335243,0.0006442138],"about_ca_topic_score_codex":0.0000029257983,"about_ca_topic_score_gemma":0.0000010848403,"teacher_disagreement_score":0.20014352,"about_ca_system_score_codex":0.000040360388,"about_ca_system_score_gemma":0.00032517992,"threshold_uncertainty_score":0.9999013},"labels":[],"label_agreement":null},{"id":"W1977498299","doi":"10.1016/j.jclinepi.2014.10.011","title":"World Health Organization strong recommendations based on low-quality evidence (study quality) are frequent and often inconsistent with GRADE guidance","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Health Sciences Centre; McMaster University","funders":"World Health Organization","keywords":"Medicine; Guideline; Confidence interval; MEDLINE; Quality of evidence; Evidence-based medicine; Family medicine; Psychological intervention; Evidence-based practice; Public health; Meta-analysis; Alternative medicine; Nursing; Pathology","score_opus":0.8346255341279041,"score_gpt":0.7038898275032235,"score_spread":0.1307357066246806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977498299","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":[0.001669698,0.6933161,0.037573107,0.2607595,0.002283342,0.0042169285,0.00007648386,0.00006554139,0.000039304676],"genre_scores_gemma":[0.005269428,0.940379,0.020075887,0.032351732,0.0016226704,0.000031677384,0.00013643291,0.000082160484,0.000050962415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93176425,0.042304374,0.023872916,0.00090466655,0.0006810615,0.00047275508],"domain_scores_gemma":[0.69623214,0.25744274,0.04246776,0.0011754755,0.0017080246,0.00097384385],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11178157,0.00054987444,0.011103481,0.00048308884,0.00015419614,0.000026415353,0.00035294058,0.00043136612,0.000107711836],"category_scores_gemma":[0.4855426,0.00035908222,0.0009008403,0.00075178064,0.00030366564,0.00020737019,0.00011927399,0.0030461384,0.000015895168],"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":[0.00091091933,0.0028001585,0.3065647,0.010033281,0.00096511224,0.000042329488,0.000041061572,0.00012434175,5.447703e-8,0.00064991857,0.009122273,0.6687459],"study_design_scores_gemma":[0.009069474,0.015671467,0.27530962,0.09671645,0.0052454686,0.00027726946,0.00052254327,0.000302683,9.549652e-8,0.00043792772,0.5955922,0.00085478346],"about_ca_topic_score_codex":0.00024914436,"about_ca_topic_score_gemma":0.0006820081,"teacher_disagreement_score":0.6678911,"about_ca_system_score_codex":0.0005057078,"about_ca_system_score_gemma":0.0027761722,"threshold_uncertainty_score":0.9998861},"labels":[],"label_agreement":null},{"id":"W1977570892","doi":"10.1016/s0895-4356(01)00356-0","title":"Original Article Underweight, overweight and obesity","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":148,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Fitness and Lifestyle Research Institute; York University","funders":"Health Canada; Heart and Stroke Foundation of Canada","keywords":"Underweight; Overweight; Medicine; Obesity; Hazard ratio; Demography; Population; Proportional hazards model; Body mass index; Gerontology; Internal medicine; Environmental health; Confidence interval","score_opus":0.16457051682407106,"score_gpt":0.46680242362617136,"score_spread":0.3022319068021003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977570892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824198,0.00035120788,0.0011743115,0.013032361,0.00057239586,0.00010019408,0.0000012948883,0.00001854196,0.0023299123],"genre_scores_gemma":[0.987534,0.0011670901,0.0040570106,0.0045778216,0.0023084076,7.841441e-7,8.8533244e-7,0.00001474407,0.0003392705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99505895,0.0015877399,0.002378932,0.0002998165,0.0002510759,0.0004234786],"domain_scores_gemma":[0.9841634,0.013247841,0.0012989895,0.00028078994,0.00024270968,0.0007662896],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007965989,0.00018398755,0.0023973463,0.0000834706,0.00006311278,0.0000070410324,0.00014593324,0.00031764733,0.00027004487],"category_scores_gemma":[0.015343341,0.00012571452,0.0005691985,0.00015853424,0.0004735334,0.00019661996,0.00009454943,0.0013155234,0.00008417019],"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":[0.00050444296,0.0041671656,0.97416395,0.000029249746,0.00016766522,0.00029102407,0.000009955515,0.0000045121624,0.0000577437,0.013313171,0.0030508728,0.0042402237],"study_design_scores_gemma":[0.002107341,0.0020224438,0.89614516,0.00006271992,0.00019114488,0.0011060127,0.000011557445,0.000508927,0.000048017548,0.074250616,0.02344116,0.00010490069],"about_ca_topic_score_codex":0.000022418706,"about_ca_topic_score_gemma":0.00001124841,"teacher_disagreement_score":0.078018814,"about_ca_system_score_codex":0.000051703966,"about_ca_system_score_gemma":0.0001639738,"threshold_uncertainty_score":0.99295086},"labels":[],"label_agreement":null},{"id":"W1977784123","doi":"10.1016/s0895-4356(00)00340-1","title":"The association between antiulcer medication and initiation of cobalamin replacement in older persons","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Folate and B Vitamins Research","field":"Medicine","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":"Queen Elizabeth II Health Sciences Centre; Ottawa Hospital; Dalhousie University; University of Ottawa","funders":"","keywords":"Cobalamin; Medicine; Confidence interval; Odds ratio; Internal medicine; Proton-pump inhibitor; Antiulcer drug; Discontinuation; Gastroenterology; Psychiatry; Drug; Vitamin B12","score_opus":0.22426047761411672,"score_gpt":0.5279681929586529,"score_spread":0.3037077153445362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977784123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97609246,0.00043900424,0.00026321455,0.02223485,0.00014969769,0.000121152334,7.987769e-7,0.0000017610129,0.0006970539],"genre_scores_gemma":[0.993237,0.005369556,0.00027821178,0.0004509803,0.00031118921,0.0000015446059,0.000004299955,0.000004119618,0.00034307377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953944,0.0017139087,0.0023236875,0.00010961647,0.00027031745,0.00018804766],"domain_scores_gemma":[0.9787541,0.019028548,0.0017211103,0.00011833526,0.0002565794,0.00012135234],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030623425,0.000056523557,0.0008270097,0.00010409337,0.000034964254,0.0000025594675,0.000071727096,0.0002426136,0.00002875561],"category_scores_gemma":[0.05272696,0.000033511013,0.00013777809,0.00012919116,0.00010965651,0.000056786008,0.000020215177,0.0006083359,0.0000026369846],"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":[0.00042579378,0.00009320571,0.97787005,0.000013635184,0.000117816126,0.0000061522205,0.00008650945,0.0000012764144,0.00005324853,0.00015156406,0.0012681703,0.019912582],"study_design_scores_gemma":[0.0021001564,0.0008955812,0.9922639,0.00008653438,0.000076434444,0.000026965106,0.00014770379,0.00033275064,0.00002701084,0.00059864577,0.0034182286,0.00002607827],"about_ca_topic_score_codex":0.000026200298,"about_ca_topic_score_gemma":0.000031496187,"teacher_disagreement_score":0.022103535,"about_ca_system_score_codex":0.000068935486,"about_ca_system_score_gemma":0.00015259368,"threshold_uncertainty_score":0.9981772},"labels":[],"label_agreement":null},{"id":"W1978018534","doi":"10.1016/j.jclinepi.2007.10.014","title":"Willingness to go through surgery again validated the WOMAC clinically important difference from THR/TKR surgery","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":134,"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; London Health Sciences Centre; University Health Network; Western University","funders":"","keywords":"WOMAC; Medicine; Surgery; Osteoarthritis; Alternative medicine; Pathology","score_opus":0.3098081201889088,"score_gpt":0.46092930033132345,"score_spread":0.15112118014241466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978018534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93931365,0.0011283611,0.0048086625,0.04957801,0.004687062,0.0002803786,0.000023805145,0.000055992277,0.00012407964],"genre_scores_gemma":[0.9426205,0.0071151857,0.007273333,0.039714865,0.0028206387,0.0000079995,0.000020431187,0.000058051257,0.00036900013],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97690356,0.005854141,0.0149688665,0.0006917973,0.0006514913,0.00093014404],"domain_scores_gemma":[0.7342548,0.25610262,0.006882644,0.0011173747,0.0006180424,0.0010245654],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032347817,0.00046714008,0.007117344,0.00013748962,0.00018810463,0.000012089974,0.0005245878,0.0007077886,0.00033914548],"category_scores_gemma":[0.28035042,0.0002635008,0.002912213,0.00044287884,0.001117279,0.00016960017,0.00021044306,0.0023344306,0.00023449548],"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":[0.0022198216,0.00046505008,0.954175,0.000018217717,0.000493017,0.0011263934,0.00015919784,0.00003890011,0.00006765199,0.00009579292,0.035653602,0.005487384],"study_design_scores_gemma":[0.0012133473,0.0007436129,0.9694236,0.00033659584,0.0002041592,0.0011042239,0.0000552985,0.0001183551,0.000037525315,0.0035002101,0.02299336,0.00026970467],"about_ca_topic_score_codex":0.0001291109,"about_ca_topic_score_gemma":0.00003249908,"teacher_disagreement_score":0.25024846,"about_ca_system_score_codex":0.00006321673,"about_ca_system_score_gemma":0.0012694875,"threshold_uncertainty_score":0.9999817},"labels":[],"label_agreement":null},{"id":"W1978202493","doi":"10.1016/j.jclinepi.2007.08.009","title":"Increased risks of neonatal and postneonatal mortality associated with teenage pregnancy had different explanations","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Pregnancy; Obstetrics; Demography; Biology; Genetics","score_opus":0.6557350900705481,"score_gpt":0.603789883924446,"score_spread":0.051945206146102096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978202493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99237716,0.0013409619,0.0022907055,0.0025905566,0.0007235019,0.00039967877,0.00007015177,0.000016598415,0.00019065634],"genre_scores_gemma":[0.99542314,0.0022228719,0.00070362986,0.00092882663,0.000503624,0.0000068226555,0.000025000814,0.0000161597,0.00016990789],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9859554,0.008540248,0.004423488,0.000339746,0.00028666027,0.00045446126],"domain_scores_gemma":[0.97228736,0.021086872,0.005282733,0.00028911803,0.0006063561,0.00044755713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0076065683,0.00019901106,0.0023071552,0.00011671346,0.000364681,6.6901623e-7,0.00019372122,0.00046941816,0.000089377616],"category_scores_gemma":[0.04184259,0.000113800765,0.00023327603,0.00013040291,0.0007858446,0.00012087308,0.00010357023,0.0020913195,0.0000042553843],"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":[0.0004864231,0.00059284375,0.99479896,0.0001183,0.00024628628,0.00007155,0.00038582532,0.000008552901,0.000009055369,0.0006526247,0.0010091189,0.0016204788],"study_design_scores_gemma":[0.0026821804,0.0012108152,0.9929887,0.0007362254,0.0000857491,0.00007878618,0.00037179884,0.000078588826,0.0000041303733,0.0012531714,0.00040033826,0.000109510824],"about_ca_topic_score_codex":0.00031374465,"about_ca_topic_score_gemma":0.00017619935,"teacher_disagreement_score":0.034236025,"about_ca_system_score_codex":0.00005001294,"about_ca_system_score_gemma":0.00056708104,"threshold_uncertainty_score":0.96622837},"labels":[],"label_agreement":null},{"id":"W1978339369","doi":"10.1016/j.jclinepi.2005.08.014","title":"A gradient of acute gastroenteritis was characterized, to assess risk of long-term health sequelae after drinking bacterial-contaminated water","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","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":"Western University; McMaster University","funders":"Ontario Ministry of Health and Long-Term Care; Kidney Foundation of Canada","keywords":"Acute gastroenteritis; Medicine; Environmental health; Term (time); Contamination; Pediatrics; Biology","score_opus":0.11147910906407167,"score_gpt":0.3891961609843152,"score_spread":0.27771705192024354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978339369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99285614,0.00018619705,0.00045483778,0.0046553933,0.001413653,0.0002619577,0.00013911794,0.000014312052,0.000018412595],"genre_scores_gemma":[0.9947048,0.0009841302,0.0012577149,0.0017149346,0.001170682,0.000011143436,0.0001019782,0.000004831877,0.00004981211],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98460543,0.0068181828,0.006989634,0.00048500832,0.00022348261,0.00087823835],"domain_scores_gemma":[0.98839444,0.0055681416,0.0050057108,0.00018801945,0.00039586527,0.00044783077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014403451,0.00033140837,0.0040314416,0.00007827754,0.000069870905,0.000011090396,0.00057659065,0.00041181204,0.00040237946],"category_scores_gemma":[0.0023046497,0.0001280132,0.0012260416,0.00017120565,0.00032764915,0.00014595859,0.00021140689,0.00066952495,0.000012920089],"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":[0.0019030861,0.00035577765,0.92946565,0.000028724915,0.00027458055,0.00007521816,0.00003861221,0.0000069427974,0.054302946,0.000031069212,0.00030379504,0.01321357],"study_design_scores_gemma":[0.0008614664,0.004030112,0.99106294,0.00022179524,0.00014146285,0.00027817208,0.000014141678,0.0000082957295,0.0015245898,0.00075009844,0.00094087987,0.00016602769],"about_ca_topic_score_codex":0.00048469097,"about_ca_topic_score_gemma":0.00048932864,"teacher_disagreement_score":0.06159728,"about_ca_system_score_codex":0.000058591573,"about_ca_system_score_gemma":0.00004485098,"threshold_uncertainty_score":0.52202266},"labels":[],"label_agreement":null},{"id":"W1978381357","doi":"10.1016/j.jclinepi.2007.12.006","title":"Exposure to environmental tobacco smoke in Chinese new mothers decreased during pregnancy","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Smoking Behavior and Cessation","field":"Medicine","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 Ottawa","funders":"","keywords":"Pregnancy; Tobacco smoke; Medicine; Confidence interval; Environmental health; Passive smoking; Cross-sectional study; Smoke; Tobacco control; Demography; Public health; Internal medicine","score_opus":0.17144409709240932,"score_gpt":0.4467334176145762,"score_spread":0.27528932052216687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978381357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99593955,0.00031411258,0.00022007938,0.0027186514,0.000535393,0.00014697299,0.000001298944,0.00000855027,0.00011541178],"genre_scores_gemma":[0.9956476,0.0006391325,0.0012862949,0.0014526014,0.0007243635,0.0000024461426,0.000002905048,0.000016165246,0.00022847374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99618614,0.00069369463,0.0024508417,0.00020998516,0.00019953976,0.00025979656],"domain_scores_gemma":[0.9962169,0.0021975602,0.00081388355,0.00022917554,0.000023664446,0.000518829],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021387865,0.00014037972,0.0013531258,0.0001530338,0.00003206094,0.0000014961533,0.00012991727,0.0002859098,0.0003167609],"category_scores_gemma":[0.012650778,0.000100515754,0.0004070033,0.000112785325,0.00008870448,0.00007824878,0.000028638018,0.0007050939,0.000008164876],"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":[0.0007491589,0.00030881434,0.9879751,0.0000067042106,0.000034827717,0.00040101237,0.00015984349,0.00011298584,0.00027546778,0.0000045870142,0.00025826303,0.009713223],"study_design_scores_gemma":[0.004125244,0.0010442226,0.99316967,0.00023874057,0.00004425504,0.0008729506,0.000040896066,0.0000069809444,0.000041000014,0.00018184776,0.00015165517,0.000082550854],"about_ca_topic_score_codex":0.00005428172,"about_ca_topic_score_gemma":0.000008602387,"teacher_disagreement_score":0.010511992,"about_ca_system_score_codex":0.00009024435,"about_ca_system_score_gemma":0.00015638454,"threshold_uncertainty_score":0.9956661},"labels":[],"label_agreement":null},{"id":"W1978884830","doi":"10.1016/j.jclinepi.2010.04.007","title":"Diabetics can be identified in an electronic medical record using laboratory tests and prescriptions","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Ottawa Hospital; Toronto Western Hospital; University of Toronto; University Health Network; Statistics Canada; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Medical prescription; Medical record; Electronic medical record; Diabetes mellitus; Family medicine; MEDLINE; Predictive value; Emergency medicine; Pediatrics; Internal medicine; Nursing","score_opus":0.1852224660473834,"score_gpt":0.5136758622002351,"score_spread":0.3284533961528517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978884830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536215,0.00020051922,0.012106014,0.031487964,0.0024818783,0.000070666036,0.000001436516,0.000018622313,0.000011420566],"genre_scores_gemma":[0.9471494,0.00026727354,0.046288405,0.0054100687,0.0008658271,0.0000015454062,7.115222e-7,0.000010461612,0.0000063046223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895293,0.00630018,0.0030205825,0.00035706905,0.0002735221,0.00051934435],"domain_scores_gemma":[0.97825485,0.018255379,0.0017687386,0.0005477567,0.000371593,0.00080165995],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033021715,0.00012927706,0.00111013,0.0001858451,0.000075158525,0.000026284937,0.00090727565,0.0005304425,0.000033854198],"category_scores_gemma":[0.1120827,0.00010723449,0.00011796723,0.00025415522,0.00028010903,0.00028423255,0.00019422617,0.0042925924,0.0000012934839],"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":[0.000018643117,0.00009549771,0.9649062,0.000015195415,0.000012286749,0.00004581713,0.00007878018,0.00008511776,0.00019625018,0.012370503,0.00021325628,0.021962414],"study_design_scores_gemma":[0.0007645683,0.0007868529,0.8277281,0.00006026637,0.000012488929,0.00018753884,0.000010971355,0.14104831,0.0000046042055,0.02469988,0.004561145,0.00013527164],"about_ca_topic_score_codex":0.00022139226,"about_ca_topic_score_gemma":0.0043228385,"teacher_disagreement_score":0.1409632,"about_ca_system_score_codex":0.00004159026,"about_ca_system_score_gemma":0.0013815582,"threshold_uncertainty_score":0.99800456},"labels":[],"label_agreement":null},{"id":"W1979088035","doi":"10.1016/s0895-4356(03)00160-4","title":"Validity of a modified standard gamble elicited from parents of a hospital-based cohort of children","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Childhood Cancer Survivors' Quality of Life","field":"Medicine","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":"Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Discriminant validity; Medicine; Construct validity; Visual analogue scale; Cohort; Childhood cancer; Psychometrics; Physical therapy; Cancer; Clinical psychology; Internal medicine","score_opus":0.18736767080769842,"score_gpt":0.474951453407325,"score_spread":0.2875837825996266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979088035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98607934,0.00055484066,0.008909358,0.0027671098,0.0008951572,0.0003813248,0.00021944431,0.000009050286,0.00018436112],"genre_scores_gemma":[0.9866256,0.00047825588,0.0112785855,0.0011958327,0.00035794827,0.0000024978278,0.000029868981,0.000023779083,0.0000076214606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9834105,0.006005927,0.009124584,0.0003645481,0.0007399998,0.00035447025],"domain_scores_gemma":[0.96677047,0.02203154,0.008983905,0.0006787801,0.001087517,0.0004477734],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022906201,0.00024784185,0.006074982,0.00017635208,0.000020005657,0.0000014645989,0.0003284247,0.0005036106,0.00015881174],"category_scores_gemma":[0.120554864,0.00019382697,0.0014788659,0.00024013742,0.0006172616,0.000060567992,0.000043588658,0.0009205441,0.0000019144782],"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":[0.002810141,0.0014341169,0.99154663,0.000118341566,0.00092992885,0.000009095832,0.00009520414,0.0003086044,0.00008059783,0.0002374713,0.002063445,0.00036642235],"study_design_scores_gemma":[0.008893833,0.0067435834,0.9763224,0.000723398,0.00066882325,0.00001634676,0.000058356334,0.00019178397,0.0019744057,0.0040165135,0.00024513027,0.0001454255],"about_ca_topic_score_codex":0.00069709774,"about_ca_topic_score_gemma":0.000025285502,"teacher_disagreement_score":0.09764866,"about_ca_system_score_codex":0.000054239314,"about_ca_system_score_gemma":0.0010036038,"threshold_uncertainty_score":0.8868531},"labels":[],"label_agreement":null},{"id":"W1979230852","doi":"10.1016/j.jclinepi.2004.08.019","title":"Reliability and validity of the PORPUS, a combined psychometric and utility-based quality-of-life instrument for prostate cancer","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; York University; Ontario Institute for Cancer Research; Cancer Care Ontario; University of Toronto; University Health Network","funders":"National Cancer Institute","keywords":"Prostate cancer; Quality of life (healthcare); Prostatectomy; Reliability (semiconductor); Construct validity; Psychometrics; Medicine; Physical therapy; Medical physics; Clinical psychology; Cancer; Internal medicine; Nursing","score_opus":0.7485148137773086,"score_gpt":0.5884029595586324,"score_spread":0.16011185421867613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979230852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88403577,0.0023364904,0.003760213,0.10808884,0.00085502636,0.00062092906,0.00025644444,0.000003613745,0.000042665546],"genre_scores_gemma":[0.9734833,0.001292402,0.0130896885,0.011768337,0.00029938392,0.000023697095,0.0000023795435,0.000011259074,0.000029510495],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9746728,0.0053652166,0.019148864,0.00041095092,0.00010263662,0.00029950996],"domain_scores_gemma":[0.92036945,0.057718143,0.020742133,0.0004976488,0.00034574643,0.00032687176],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19493797,0.00015805686,0.0039120065,0.00021893634,0.00008087081,0.0000064400297,0.00028390737,0.00028423656,0.00005723736],"category_scores_gemma":[0.2689964,0.00012573732,0.0005259107,0.00020385814,0.0005530746,0.00016380427,0.00006076585,0.00043349122,0.0000021394476],"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":[0.00048827392,0.00027009388,0.9839592,0.0006029114,0.00008196551,1.9078952e-8,0.000094823896,0.00022373785,9.509201e-7,0.008850781,0.0030028517,0.0024243856],"study_design_scores_gemma":[0.0035477288,0.0005911904,0.9288972,0.00008972667,0.000021548554,0.0000012552247,0.000053216227,0.007704896,0.000003368188,0.042845804,0.01613609,0.00010798001],"about_ca_topic_score_codex":0.00040031955,"about_ca_topic_score_gemma":0.000100120815,"teacher_disagreement_score":0.09632051,"about_ca_system_score_codex":0.00010587563,"about_ca_system_score_gemma":0.00051616743,"threshold_uncertainty_score":0.82898074},"labels":[],"label_agreement":null},{"id":"W1979327418","doi":"10.1016/j.jclinepi.2005.08.017","title":"A systematic review identifies a lack of standardization in methods for handling missing variance data","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":298,"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; University of Ottawa; Montreal Children's Hospital; Children's Hospital of Eastern Ontario; McGill University; University of Alberta","funders":"","keywords":"Missing data; Nonparametric statistics; MEDLINE; Computer science; Statistics; Variance (accounting); Standardization; Meta-analysis; Consistency (knowledge bases); Medicine; Machine learning; Mathematics; Artificial intelligence","score_opus":0.9756991473629063,"score_gpt":0.7978861926427433,"score_spread":0.177812954720163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979327418","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.447818e-8,0.52629954,0.47110838,0.00036984804,0.0006772035,0.0014524172,0.00005115334,7.256169e-7,0.00004066379],"genre_scores_gemma":[3.0534423e-7,0.76630795,0.23252222,0.00036047574,0.00032113487,0.00003081195,0.000037453792,0.000020854304,0.00039877664],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.2174782,0.504162,0.27235696,0.0021344577,0.0032508895,0.0006174914],"domain_scores_gemma":[0.0635518,0.667417,0.25714242,0.0074994676,0.0041180435,0.00027129226],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9026502,0.0005938682,0.10607516,0.00080681266,0.000058773385,0.00014523626,0.006008268,0.0007233489,0.00023896583],"category_scores_gemma":[0.9585953,0.00025576333,0.014306403,0.0016502502,0.00019157841,0.00035121894,0.00038436326,0.0010179686,0.00003704249],"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":[0.0000082787765,0.000058332516,0.000068954534,0.6590729,0.0010340086,0.000004636426,0.0000070629676,0.000033809065,2.4144658e-8,0.00040320173,0.023395464,0.31591335],"study_design_scores_gemma":[0.00017519752,0.00006618532,0.000010624892,0.45744032,0.009903,0.00008182705,0.0000075897588,0.00260879,1.2435998e-8,0.014760909,0.51479626,0.00014928909],"about_ca_topic_score_codex":0.0000054906573,"about_ca_topic_score_gemma":0.000010169372,"teacher_disagreement_score":0.4914008,"about_ca_system_score_codex":0.000078678204,"about_ca_system_score_gemma":0.0011735366,"threshold_uncertainty_score":0.99998945},"labels":[],"label_agreement":null},{"id":"W1979334594","doi":"10.1016/j.jclinepi.2010.10.006","title":"Development and use of reporting guidelines for assessing the quality of validation studies of health administrative data","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":365,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; SickKids Foundation; University of Toronto; Statistics Canada; Institute for Clinical Evaluative Sciences; Children's Hospital of Eastern Ontario; Hospital for Sick Children; University of Ottawa","funders":"Canadian Institutes of Health Research; Institut pour la Recherche en Santé Publique; Hospital for Sick Children; Canadian Child Health Clinician Scientist Program; Child and Family Research Institute; Public Health Agency of Canada; American College of Gastroenterology","keywords":"Checklist; Medicine; Identification (biology); Data quality; MEDLINE; Confidence interval; Data collection; Health care; Statistics; Psychology; Operations management; Internal medicine","score_opus":0.9939552576276779,"score_gpt":0.8131323764978747,"score_spread":0.18082288112980316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979334594","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"reporting","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":[0.006584713,0.96247405,0.012489969,0.015984898,0.0012760255,0.00083200925,0.00034789482,0.0000023327343,0.000008121643],"genre_scores_gemma":[0.0001801833,0.786468,0.21156432,0.0012358993,0.00045025465,0.000012812503,0.000059644837,0.000015944941,0.000012886549],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.78829813,0.016847193,0.19339517,0.0008367273,0.00019769368,0.00042505865],"domain_scores_gemma":[0.18027669,0.3090928,0.5067549,0.0014070022,0.0022579022,0.0002107521],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58672863,0.00023715933,0.016684504,0.00021458462,0.00010481224,0.000011105928,0.0005475552,0.00046890444,0.000005304351],"category_scores_gemma":[0.8474439,0.00017029195,0.0007360994,0.00010978912,0.00045318043,0.00034079314,0.00020309605,0.00068327045,9.252164e-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":[0.00005205443,0.00031939804,0.08849149,0.077410385,0.0028933047,5.7694797e-7,0.00096831843,0.000029925179,1.4036564e-7,0.029649368,0.015274156,0.78491086],"study_design_scores_gemma":[0.0004398256,0.00025737242,0.01474826,0.009851909,0.00016256367,0.000024451401,0.0009050778,0.00017610204,3.189575e-7,0.006571776,0.96666837,0.00019395382],"about_ca_topic_score_codex":0.00011522299,"about_ca_topic_score_gemma":0.00006384278,"teacher_disagreement_score":0.95139426,"about_ca_system_score_codex":0.00010584837,"about_ca_system_score_gemma":0.0030579246,"threshold_uncertainty_score":0.99791384},"labels":[],"label_agreement":null},{"id":"W1979620045","doi":"10.1016/j.jclinepi.2007.01.004","title":"Nutrition screen showed good agreement when self- and interviewer administered","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Nutrition and Health in Aging","field":"Medicine","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 Guelph","funders":"","keywords":"Intraclass correlation; Inter-rater reliability; Kappa; Interview; Medicine; Telephone interview; Cohen's kappa; Limits of agreement; Confidence interval; Psychology; Physical therapy; Psychometrics; Clinical psychology; Statistics; Rating scale; Internal medicine; Developmental psychology","score_opus":0.39569914459681543,"score_gpt":0.5581533733576493,"score_spread":0.16245422876083382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979620045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69950885,0.009971664,0.024617728,0.253337,0.0035709115,0.0009642925,0.000010334879,0.0000646319,0.007954616],"genre_scores_gemma":[0.7805588,0.008418049,0.14428864,0.062052026,0.0042699696,0.0000038299663,0.000011049275,0.00002137313,0.00037622286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934648,0.0012707368,0.0045251227,0.00020809768,0.00018258634,0.0003486142],"domain_scores_gemma":[0.9889766,0.007976481,0.0017990341,0.00018348251,0.000343743,0.00072066044],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03031778,0.00012945243,0.001817071,0.00017366816,0.00004650802,0.00000438565,0.00009869294,0.00030939226,0.0002548778],"category_scores_gemma":[0.00982281,0.000094615025,0.00038919077,0.00006308747,0.00013476849,0.000068569105,0.000047077458,0.0009342854,0.000019487929],"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":[0.00435006,0.0023509315,0.8041805,0.0009562311,0.000395331,0.00035772938,0.00020203965,1.2937642e-7,0.0000841906,0.004479295,0.07933467,0.10330888],"study_design_scores_gemma":[0.009031982,0.00474198,0.6009193,0.0012100859,0.00020124813,0.0011071925,0.00016426023,0.00010409325,0.000029538107,0.008242926,0.37413424,0.000113133916],"about_ca_topic_score_codex":0.0000072295693,"about_ca_topic_score_gemma":0.000015455369,"teacher_disagreement_score":0.29479957,"about_ca_system_score_codex":0.000053963526,"about_ca_system_score_gemma":0.0001103514,"threshold_uncertainty_score":0.9985179},"labels":[],"label_agreement":null},{"id":"W1979857362","doi":"10.1016/j.jclinepi.2009.01.015","title":"Changes in surrogate outcomes can be translated into clinical outcomes using a Monte Carlo model","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","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 Ottawa; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Monte Carlo method; Medicine; Computer science; Statistics; Mathematics","score_opus":0.5763994889375792,"score_gpt":0.5813060965327912,"score_spread":0.004906607595211998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979857362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8176728,0.0002639879,0.0011775473,0.17949286,0.0010038483,0.00029276745,0.0000033754106,0.00002631783,0.00006647431],"genre_scores_gemma":[0.95779413,0.00093977485,0.016801814,0.023023462,0.0009812089,4.8854145e-7,0.0000033776096,0.000023328845,0.0004323993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98897463,0.0024981345,0.007240756,0.00040569832,0.00034316984,0.00053762103],"domain_scores_gemma":[0.9826005,0.013602131,0.0026660878,0.0003713062,0.0002531814,0.00050680834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021029834,0.00033252416,0.0055865166,0.00041687067,0.000054553584,0.000008893829,0.00026604976,0.000659973,0.00003683263],"category_scores_gemma":[0.03744298,0.00022362755,0.0019709503,0.00026406205,0.00022600398,0.00013401738,0.000045854922,0.0013021402,0.000003900934],"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":[0.001377255,0.00009740711,0.97580403,0.00002024241,0.00036153835,0.00011390489,0.00015453859,0.006193922,0.000014367214,0.00032181834,0.00035048506,0.015190467],"study_design_scores_gemma":[0.0068995217,0.0011249784,0.93911093,0.0000978705,0.00042321024,0.00002835895,0.0000593974,0.045922842,0.0000021531437,0.0043444755,0.0017945346,0.00019174973],"about_ca_topic_score_codex":0.00013723735,"about_ca_topic_score_gemma":0.00062937406,"teacher_disagreement_score":0.1564694,"about_ca_system_score_codex":0.000081626036,"about_ca_system_score_gemma":0.00029094244,"threshold_uncertainty_score":0.97066504},"labels":[],"label_agreement":null},{"id":"W1980110976","doi":"10.1016/j.jclinepi.2004.06.015","title":"A cohort study found that white blood cell count and endocrine markers predicted preterm birth in symptomatic women","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","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":"Western University; University of Toronto; Lawson Health Research Institute","funders":"","keywords":"Medicine; Endocrine system; Cohort study; Cohort; Obstetrics; White blood cell; Gynecology; Physiology; Internal medicine; Hormone","score_opus":0.06285150656778912,"score_gpt":0.3927476907366815,"score_spread":0.3298961841688923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980110976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949439,0.00068625045,0.000054294575,0.0022723477,0.00043533277,0.0007029576,0.000011930266,0.000021885548,0.0008710669],"genre_scores_gemma":[0.9924248,0.002520285,0.0013606006,0.002519876,0.0007377599,0.000030094605,0.000003583531,0.000023362187,0.0003796397],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9921695,0.0024404726,0.0040226863,0.00038972814,0.0003451837,0.00063244865],"domain_scores_gemma":[0.9895978,0.007320952,0.0018384326,0.00036236708,0.0001499548,0.0007304674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013345028,0.0002586128,0.0029019439,0.00024615054,0.00003948645,0.000012185387,0.00020982683,0.00024924974,0.0003177949],"category_scores_gemma":[0.010874008,0.00018816424,0.0002793231,0.0001387749,0.00025041422,0.00016975013,0.00009109844,0.0012227485,0.0000063175316],"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":[0.0017633921,0.001013078,0.99178445,0.00012872068,0.00041113593,0.00041092164,0.00031437006,0.000012810265,0.000008551581,0.000005696814,0.00058331783,0.0035635782],"study_design_scores_gemma":[0.01212571,0.006610576,0.9756141,0.0002097911,0.00029252615,0.0012074523,0.00030356634,0.0009497333,0.0000029678301,0.00027522023,0.0022621523,0.00014624871],"about_ca_topic_score_codex":0.000016621072,"about_ca_topic_score_gemma":0.000040153755,"teacher_disagreement_score":0.016170371,"about_ca_system_score_codex":0.000104986015,"about_ca_system_score_gemma":0.00024608895,"threshold_uncertainty_score":0.9974578},"labels":[],"label_agreement":null},{"id":"W1980138066","doi":"10.1016/s0895-4356(99)00215-2","title":"Selection bias in studies of major depression using clinical subjects","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":47,"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 Calgary","funders":"University of Calgary","keywords":"Selection bias; Depression (economics); Selection (genetic algorithm); Medicine; Odds; Cross-sectional study; Odds ratio; Sample size determination; Psychology; Psychiatry; Demography; Statistics; Clinical psychology; Logistic regression; Internal medicine; Mathematics; Pathology","score_opus":0.7504920193914262,"score_gpt":0.6978420006848062,"score_spread":0.052650018706620005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980138066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98485965,0.0028856301,0.00025080028,0.0073914407,0.0032555668,0.00025992037,0.000002725997,0.000012818017,0.0010814533],"genre_scores_gemma":[0.93879837,0.018126935,0.010911237,0.02864254,0.0030472986,0.000005713501,0.0000016516935,0.000025770594,0.00044051325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9596683,0.025278462,0.013879647,0.00031187353,0.00022462073,0.00063710025],"domain_scores_gemma":[0.8797404,0.11299042,0.0061080856,0.00025786608,0.00057490164,0.00032828716],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07122474,0.0001813814,0.0043681744,0.00023888912,0.00018180661,9.08869e-7,0.0002737514,0.00094711286,0.0006157775],"category_scores_gemma":[0.107381955,0.0001229566,0.0007213201,0.00029765329,0.00030272087,0.00016771587,0.0000929445,0.0032048689,0.00004364753],"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":[0.0014921656,0.00019257171,0.93623257,0.00017684622,0.000112978,0.000018408922,0.0001450322,0.00008941143,0.000009238209,0.00012392114,0.013236906,0.048169963],"study_design_scores_gemma":[0.003500673,0.0009458776,0.96920407,0.00059466576,0.000097259246,0.000032705924,0.00023531068,0.00041353758,0.0000039973543,0.006943674,0.017916383,0.00011183598],"about_ca_topic_score_codex":0.00023683417,"about_ca_topic_score_gemma":0.0003848852,"teacher_disagreement_score":0.08771195,"about_ca_system_score_codex":0.0002249635,"about_ca_system_score_gemma":0.0020504387,"threshold_uncertainty_score":0.9990948},"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":"W1980776335","doi":"10.1016/j.jclinepi.2009.11.007","title":"The art and science of knowledge synthesis","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":195,"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; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Comparability; Systematic review; Transparency (behavior); Computer science; Management science; Diversity (politics); External validity; Knowledge management; Data science; Psychology; MEDLINE; Sociology; Political science; Mathematics; Engineering; Social psychology","score_opus":0.8994117524120242,"score_gpt":0.68878973338765,"score_spread":0.21062201902437416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980776335","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95526713,0.0017376227,0.0057211732,0.02011286,0.003333038,0.0001433258,0.0000016973095,8.2748653e-7,0.013682315],"genre_scores_gemma":[0.9840011,0.00046675032,0.013202443,0.0003446417,0.00040215306,0.0000015170725,1.9815447e-8,0.0000031063776,0.0015782898],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8078956,0.10278088,0.083080456,0.0011823955,0.0043700696,0.0006906279],"domain_scores_gemma":[0.065379634,0.8773085,0.048804767,0.0031851109,0.0047030607,0.0006189351],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8301256,0.00012266463,0.007350891,0.00022094799,0.00016632419,0.000079644844,0.0026179312,0.00015047802,0.0009491884],"category_scores_gemma":[0.949663,0.000038933344,0.0023314834,0.0006355981,0.0022889448,0.00015269774,0.00019632255,0.00072505564,0.00034632804],"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":[0.000035444085,0.00008678029,0.50526166,0.000012908246,0.00016145252,0.000002221675,0.000049894534,0.0000069656976,0.0002637792,0.05091747,0.12077409,0.32242736],"study_design_scores_gemma":[0.00013030486,0.00015395696,0.49014747,0.000028016948,0.00015149912,0.0001040008,0.00008786695,0.0028825486,0.000042020638,0.082568616,0.42364225,0.000061441286],"about_ca_topic_score_codex":0.0000011096098,"about_ca_topic_score_gemma":0.000021564312,"teacher_disagreement_score":0.7745276,"about_ca_system_score_codex":0.000004076782,"about_ca_system_score_gemma":0.00033282686,"threshold_uncertainty_score":0.99996406},"labels":[],"label_agreement":null},{"id":"W1980903642","doi":"10.1016/j.jclinepi.2006.10.020","title":"Methodologic discussions for using and interpreting composite endpoints are limited, but still identify major concerns","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":216,"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; McMaster University","funders":"","keywords":"MEDLINE; Meaning (existential); Medicine; Sample size determination; Intervention (counseling); Citation; Disadvantage; Psychology; Statistics; Computer science; Psychotherapist; Library science; Political science; Psychiatry","score_opus":0.9820017511959729,"score_gpt":0.7767224192234639,"score_spread":0.20527933197250903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980903642","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":[0.00048091833,0.6536315,0.3420566,0.0005957017,0.0022930484,0.0007728734,0.00007690546,0.0000026076366,0.00008982637],"genre_scores_gemma":[0.00014846816,0.78869796,0.20768297,0.0011923059,0.001485009,0.0000115154435,0.000008288295,0.000037003516,0.00073651044],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6048127,0.27273223,0.11704843,0.002139569,0.0023465536,0.0009205312],"domain_scores_gemma":[0.1988628,0.6565056,0.13915516,0.0023719792,0.002233669,0.00087077875],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.74105257,0.0008378412,0.057865404,0.0010162848,0.00018925617,0.00031727657,0.0032790042,0.0014548328,0.00068633445],"category_scores_gemma":[0.8745716,0.00032351786,0.02061383,0.0007566609,0.00056246296,0.00034145705,0.000674891,0.0023962504,0.00009954193],"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":[0.00007800314,0.00008690723,0.007825508,0.0028457078,0.00218112,0.00006525014,0.000038260623,0.000022314476,6.7068436e-7,0.0011972343,0.0066644885,0.97899455],"study_design_scores_gemma":[0.00039604632,0.0002600097,0.001037401,0.010971347,0.006649748,0.0008793289,0.00024620045,0.0014510555,1.00545684e-7,0.013318865,0.964427,0.00036289467],"about_ca_topic_score_codex":0.0000051259517,"about_ca_topic_score_gemma":0.0000086591745,"teacher_disagreement_score":0.9786316,"about_ca_system_score_codex":0.000083748244,"about_ca_system_score_gemma":0.00028878334,"threshold_uncertainty_score":0.9999217},"labels":[],"label_agreement":null},{"id":"W1981098513","doi":"10.1016/j.jclinepi.2006.11.002","title":"Author reply: the role of pragmatism in publishing","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pituitary Gland Disorders and Treatments","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pragmatism; Publishing; Medicine; Library science; Psychology; Epistemology; Philosophy; Political science; Computer science; Law","score_opus":0.16929981800902796,"score_gpt":0.4887059979140413,"score_spread":0.3194061799050133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981098513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94562626,0.0038973948,0.00083316944,0.04315828,0.00051808055,0.0001228775,0.0000015676871,0.0000038876647,0.005838478],"genre_scores_gemma":[0.990735,0.00030332897,0.0036120524,0.004872509,0.00036715527,6.5899985e-7,0.0000021035976,0.0000058554406,0.00010136628],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99478394,0.0010166834,0.0036609333,0.00012442794,0.00016189477,0.00025213393],"domain_scores_gemma":[0.97700095,0.020226823,0.0021501237,0.0002460257,0.00016034415,0.00021573863],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034972016,0.000082478546,0.0013872067,0.000115193936,0.000020579128,0.0000034703517,0.00015750599,0.00020913835,0.000046254256],"category_scores_gemma":[0.087359324,0.000041361396,0.00038731424,0.00013326532,0.00014348493,0.00015021375,0.000035338115,0.0008329663,0.0000036003],"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":[0.000666862,0.00036167548,0.9178381,0.000009150669,0.000090600384,0.00009308012,0.000072592265,0.000008975795,0.000006715413,0.00314666,0.0031236736,0.07458194],"study_design_scores_gemma":[0.0023126663,0.00083951023,0.9205097,0.0000990033,0.000068450296,0.00021332382,0.00024328878,0.00013011428,0.000010187911,0.054233238,0.021309229,0.00003129347],"about_ca_topic_score_codex":0.0001872996,"about_ca_topic_score_gemma":0.00007325843,"teacher_disagreement_score":0.07455065,"about_ca_system_score_codex":0.000021280415,"about_ca_system_score_gemma":0.00017441598,"threshold_uncertainty_score":0.9936994},"labels":[],"label_agreement":null},{"id":"W1981114551","doi":"10.1016/j.jclinepi.2008.07.006","title":"Bayesian statistical inference enhances the interpretation of contemporary randomized controlled trials","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":178,"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. Michael's Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Toronto General Hospital; University of Toronto","funders":"","keywords":"Randomized controlled trial; Interpretation (philosophy); Statistical inference; Inference; Bayesian probability; Bayesian inference; Bayesian statistics; Computer science; Statistics; Econometrics; Artificial intelligence; Medicine; Machine learning; Mathematics; Internal medicine","score_opus":0.7954584011993118,"score_gpt":0.678490372859101,"score_spread":0.1169680283402108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981114551","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012870123,0.0006946984,0.9766692,0.004090431,0.0028881752,0.0013429306,0.000034135235,0.000015094799,0.0013952282],"genre_scores_gemma":[0.6006829,0.0012151967,0.39622667,0.0009526445,0.00083058374,0.000030527393,6.9937937e-7,0.000014216207,0.00004653822],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6180377,0.31822675,0.061542217,0.0005703026,0.0010354759,0.0005875734],"domain_scores_gemma":[0.021892544,0.9482471,0.028058479,0.000473542,0.0010038407,0.00032451574],"candidate_categories":["metaresearch","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4546899,0.00032203196,0.030457415,0.00014155528,0.00008110636,0.000009002053,0.0007188786,0.00056469475,0.00052207883],"category_scores_gemma":[0.99292433,0.00014167809,0.0044832206,0.00015313667,0.0035400242,0.000108643864,0.00009431402,0.0015516109,0.000008721194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.48884597,0.00078711344,0.005275751,0.00012907707,0.0038630662,0.00007070564,0.00027072857,0.0000638211,0.00003338903,0.472519,0.011599673,0.016541673],"study_design_scores_gemma":[0.13457058,0.00093377696,0.0011635018,0.00023158669,0.0008302222,0.00004069316,0.00004291292,0.0077133817,0.000031887994,0.8542461,0.000078875484,0.00011651161],"about_ca_topic_score_codex":0.000013253393,"about_ca_topic_score_gemma":0.0000017965847,"teacher_disagreement_score":0.6300203,"about_ca_system_score_codex":0.000019573597,"about_ca_system_score_gemma":0.000771356,"threshold_uncertainty_score":0.9991718},"labels":[],"label_agreement":null},{"id":"W1981680557","doi":"10.1016/j.jclinepi.2010.07.017","title":"GRADE guidelines: 4. Rating the quality of evidence—study limitations (risk of bias)","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2834,"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":"Observational study; Randomized controlled trial; Medicine; Systematic review; Intensive care medicine; Publication bias; MEDLINE; Meta-analysis; Internal medicine","score_opus":0.9975478483593986,"score_gpt":0.7887250727249735,"score_spread":0.20882277563442508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981680557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9308282,0.0022363644,0.05746386,0.007328039,0.0009970107,0.00046235463,0.000005469833,0.0000012538035,0.0006774172],"genre_scores_gemma":[0.944542,0.0010123614,0.05305917,0.00085103046,0.00030810924,0.000004491326,1.7127314e-7,0.0000053458593,0.00021735304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.29325265,0.49981904,0.19972205,0.0009826076,0.0057829367,0.00044070004],"domain_scores_gemma":[0.050279554,0.78446054,0.1524043,0.0034181478,0.0091787,0.00025878428],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8761842,0.00020957658,0.013157518,0.0002520678,0.0000929722,0.000021512775,0.002785247,0.00018263096,0.0009808359],"category_scores_gemma":[0.98329544,0.00006555521,0.0069522983,0.0008791857,0.00043962314,0.00021407065,0.00017209035,0.00074433855,0.00008327192],"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":[0.000058064372,0.0002984766,0.9493183,0.000016714992,0.000610795,0.0000013230064,0.0008253413,0.00025889333,0.0000075767216,0.0019303435,0.015654346,0.031019825],"study_design_scores_gemma":[0.0003229131,0.0008098763,0.93362737,0.00010211141,0.00069089554,0.000010184911,0.004388734,0.0014373956,0.0000048218603,0.05642437,0.002112878,0.00006843171],"about_ca_topic_score_codex":0.00015585504,"about_ca_topic_score_gemma":0.0001839252,"teacher_disagreement_score":0.28464147,"about_ca_system_score_codex":0.000008413252,"about_ca_system_score_gemma":0.00025726965,"threshold_uncertainty_score":0.9999324},"labels":[],"label_agreement":null},{"id":"W1981688711","doi":"10.1016/s0895-4356(02)00593-0","title":"Sex difference in hospitalization due to asthma in relation to age","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":139,"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; Compute Canada","keywords":"Asthma; Medicine; Incidence (geometry); Demography; Pediatrics; Population; Epidemiology; Sex ratio; Age groups; Cumulative incidence; Hospital discharge; Internal medicine; Environmental health; Cohort","score_opus":0.12086958356164815,"score_gpt":0.45636193088926136,"score_spread":0.33549234732761324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981688711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835001,0.00019156381,0.0110362265,0.004202317,0.0003953016,0.00019122245,7.1690846e-7,0.0000045106967,0.00047802107],"genre_scores_gemma":[0.98765135,0.000058358102,0.003310303,0.008551452,0.00024514474,0.0000036884371,0.0000015146294,0.000008961103,0.0001692228],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99433255,0.00235347,0.0027449194,0.00020212612,0.00013467918,0.0002322668],"domain_scores_gemma":[0.9946572,0.0040351106,0.00060678594,0.00015590688,0.00009852727,0.00044642147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007720709,0.0001026044,0.0014041164,0.00026458697,0.000013263162,0.0000023895961,0.00008215029,0.00024345286,0.000053302978],"category_scores_gemma":[0.086622335,0.00007422805,0.00019679384,0.00028071686,0.000050401613,0.00004575214,0.000018875298,0.0004915811,0.00002643715],"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":[0.00032458524,0.0002715232,0.9789369,0.0000135751,0.000008638423,0.00042052823,0.000087546934,0.0010497174,0.000050140286,0.0010919758,0.0006404989,0.017104387],"study_design_scores_gemma":[0.0011983174,0.0015518299,0.9874885,0.0002078189,0.00000985574,0.00006171337,0.000047599275,0.00013728735,0.000009817299,0.0026349935,0.006583111,0.000069148206],"about_ca_topic_score_codex":0.00001088183,"about_ca_topic_score_gemma":0.0000402737,"teacher_disagreement_score":0.078901626,"about_ca_system_score_codex":0.000059529906,"about_ca_system_score_gemma":0.00018998695,"threshold_uncertainty_score":0.9210714},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W1981722553","doi":"10.1016/j.jclinepi.2004.08.006","title":"A cohort study showed that health insurance databases were accurate to distinguish chronic obstructive pulmonary disease from asthma and classify disease severity","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","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":"Hôpital du Sacré-Cœur de Montréal; Université de Montréal; McGill University","funders":"","keywords":"Medicine; Asthma; Pulmonary disease; Cohort; Disease; Cohort study; Intensive care medicine; Internal medicine; Database; Computer science","score_opus":0.1804399465860853,"score_gpt":0.48099533607278655,"score_spread":0.30055538948670124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981722553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9621324,0.0078007453,0.00046500258,0.025628535,0.0008133339,0.0018265742,0.0011906979,0.000042960004,0.00009978367],"genre_scores_gemma":[0.98808146,0.0019049798,0.0021782084,0.003648141,0.0037704369,0.000058219764,0.0001490187,0.000059986327,0.00014953222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9867871,0.0058154967,0.004177984,0.0013000546,0.0008853892,0.0010340202],"domain_scores_gemma":[0.9786428,0.012131151,0.00247208,0.0011122912,0.0005223964,0.00511924],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008682416,0.0005311948,0.00387643,0.0002303706,0.0002441185,0.000026030386,0.00051459786,0.00017129593,0.00037104634],"category_scores_gemma":[0.04892875,0.00042167958,0.0007052255,0.0002814635,0.00085374236,0.00045979026,0.00057852955,0.0021045534,0.000035106277],"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":[0.00822685,0.0020415974,0.9206115,0.0002507534,0.00044037795,0.0012288905,0.000049614126,0.0001329961,0.000003185422,0.000065226515,0.0018951229,0.06505388],"study_design_scores_gemma":[0.0031597575,0.00077888434,0.9816509,0.0004971249,0.00024372492,0.00011639478,0.00022472392,0.0031821518,5.1797645e-7,0.0008115034,0.009006724,0.0003275767],"about_ca_topic_score_codex":0.00034754237,"about_ca_topic_score_gemma":0.00029352386,"teacher_disagreement_score":0.0647263,"about_ca_system_score_codex":0.00087413046,"about_ca_system_score_gemma":0.0030471592,"threshold_uncertainty_score":0.9998235},"labels":[],"label_agreement":null},{"id":"W1982430029","doi":"10.1016/j.jclinepi.2012.06.017","title":"Prevention and self-management interventions are top priorities for osteoarthritis systematic reviews","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","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":"Cochrane; Ottawa Hospital; University of Ottawa; Institute of Population and Public Health","funders":"","keywords":"Osteoarthritis; Psychological intervention; Medicine; Systematic review; Alternative medicine; MEDLINE; Physical therapy; Intensive care medicine; Political science; Nursing; Pathology","score_opus":0.2660285009592275,"score_gpt":0.49741404519665766,"score_spread":0.23138554423743019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982430029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.687785,0.2723962,0.02035817,0.004916235,0.0058860853,0.007650786,0.000015431478,0.00006512095,0.0009269233],"genre_scores_gemma":[0.779564,0.0593417,0.1511098,0.0021641206,0.0032874972,0.00046499918,0.000015803662,0.000047171117,0.0040049106],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9936863,0.0018342673,0.0039514443,0.00014465388,0.00010049237,0.00028283577],"domain_scores_gemma":[0.9919863,0.004676655,0.002712175,0.00018281907,0.00014535284,0.00029673148],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016349752,0.00014438308,0.0027510428,0.000107090615,0.000054556804,0.000006142392,0.0000653511,0.00017925269,0.00002752638],"category_scores_gemma":[0.01395059,0.00009872951,0.0012537615,0.00004779769,0.000059084476,0.0001604864,0.00003816863,0.00023638952,0.000014442521],"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":[0.0013560583,0.0038963328,0.39318627,0.14872503,0.0020053093,0.00010454233,0.00046393045,6.9661417e-7,0.000038635084,0.047513086,0.007578159,0.39513195],"study_design_scores_gemma":[0.062643684,0.090848744,0.26194254,0.30187014,0.021116266,0.0066830525,0.0026647751,0.000069709145,0.00014419226,0.04406826,0.20684549,0.0011031713],"about_ca_topic_score_codex":2.8202356e-7,"about_ca_topic_score_gemma":0.0000037059885,"teacher_disagreement_score":0.39402878,"about_ca_system_score_codex":0.000032552056,"about_ca_system_score_gemma":0.000026637083,"threshold_uncertainty_score":0.9943553},"labels":[],"label_agreement":null},{"id":"W1982575448","doi":"10.1016/s0895-4356(02)00445-6","title":"Patient versus injury factors as predictors of pain and disability six months after a distal radius fracture","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","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":"Western University; McMaster University","funders":"American Society for Surgery of the Hand","keywords":"Medicine; Wrist; Physical therapy; Distal radius fracture; Wrist pain; Hand strength; Grip strength; Range of motion; Prospective cohort study; Physical medicine and rehabilitation; Surgery","score_opus":0.07596431993929703,"score_gpt":0.4073056139138439,"score_spread":0.33134129397454687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982575448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99141914,0.0009902724,0.000099557445,0.0055649006,0.0015812682,0.00018209915,0.000014822226,0.0000077963105,0.00014013589],"genre_scores_gemma":[0.9973484,0.000424348,0.00046169476,0.0011445053,0.00057252817,0.0000030654812,0.000004308473,0.000010611813,0.000030537787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99207205,0.0037967265,0.0034145252,0.00024338288,0.00024096256,0.00023237744],"domain_scores_gemma":[0.9463138,0.05120838,0.0016216076,0.00023947426,0.00015857295,0.00045814493],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009918864,0.00016939304,0.0018426956,0.00006387735,0.000027522401,0.000001959265,0.00005465959,0.00044426727,0.00045190536],"category_scores_gemma":[0.14232045,0.000101602316,0.0007300641,0.00008952865,0.0009237429,0.00010100209,0.00003252402,0.0008522984,0.0000024115209],"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":[0.004893786,0.00070743466,0.9283466,0.00006939791,0.00018803263,0.00002261471,0.00037271422,0.000012049278,0.000006880117,0.000011831529,0.0014343442,0.06393431],"study_design_scores_gemma":[0.0015294558,0.010894645,0.9684906,0.00012178973,0.00017424344,0.000022384376,0.00028895558,0.00017103353,0.000011052676,0.00033677535,0.017873898,0.000085175074],"about_ca_topic_score_codex":0.00002535987,"about_ca_topic_score_gemma":0.0000051900715,"teacher_disagreement_score":0.1324016,"about_ca_system_score_codex":0.00004070154,"about_ca_system_score_gemma":0.00006012093,"threshold_uncertainty_score":0.86490417},"labels":[],"label_agreement":null},{"id":"W1982831088","doi":"10.1016/j.jclinepi.2003.12.008","title":"Time-dependent bias was common in survival analyses published in leading clinical journals","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":339,"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 Ottawa; Ottawa Hospital","funders":"","keywords":"Observational study; Medicine; Publication bias; Covariate; Annals; Meta-analysis; Baseline (sea); MEDLINE; New england; Survival analysis; Demography; Internal medicine; Statistics; History","score_opus":0.981357319774874,"score_gpt":0.7718018576263995,"score_spread":0.20955546214847443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982831088","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013859615,0.9867155,0.001527016,0.0027051554,0.0050496166,0.0009000332,0.000019348605,0.0000042859797,0.0016930654],"genre_scores_gemma":[0.0006103484,0.99088085,0.003932522,0.00086635724,0.0018946705,0.00001337932,0.000012631906,0.00006075873,0.0017285022],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.10146012,0.57947725,0.30713072,0.0029982855,0.0074618063,0.0014718401],"domain_scores_gemma":[0.084705055,0.6819171,0.22302152,0.005955645,0.002782967,0.0016177384],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9196405,0.0013367849,0.1379826,0.0047220374,0.0000913505,0.0006447439,0.00904159,0.0030902042,0.011202004],"category_scores_gemma":[0.92711353,0.00059235597,0.042108547,0.0044405,0.0006837619,0.00079919735,0.0007368034,0.010309759,0.003968892],"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":[0.00007030844,0.0007737022,0.1940223,0.0013557198,0.0020756174,0.0006595808,0.00002716284,0.0013151505,2.4527276e-8,0.00025943623,0.024703376,0.7747376],"study_design_scores_gemma":[0.0017756809,0.0006246046,0.020107334,0.021597581,0.0033958724,0.00070659554,0.0000941285,0.0008028958,1.5874555e-8,0.027506242,0.92264724,0.00074182183],"about_ca_topic_score_codex":0.00005564449,"about_ca_topic_score_gemma":0.0002829756,"teacher_disagreement_score":0.89794385,"about_ca_system_score_codex":0.00038738485,"about_ca_system_score_gemma":0.0028125108,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W1983613778","doi":"10.1016/s0895-4356(99)00156-0","title":"Likelihood and clinical trials","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Bruyère; The Sisters of Charity of Ottawa","funders":"","keywords":"Bayesian probability; Orthodoxy; Statistics; Statistical hypothesis testing; Statistical theory; Econometrics; Epistemology; Medicine; Mathematics; History; Philosophy","score_opus":0.9249743914661306,"score_gpt":0.7590140087416808,"score_spread":0.1659603827244498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983613778","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7184719,0.0020236857,0.21393557,0.038360316,0.015515588,0.0012804655,0.00008166712,0.00013235571,0.010198462],"genre_scores_gemma":[0.022155583,0.009974517,0.95175815,0.006977035,0.008663894,0.0000042763604,4.2468184e-7,0.000046716457,0.0004194119],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7559032,0.18946248,0.052113444,0.0009216905,0.00060617924,0.000993001],"domain_scores_gemma":[0.03918696,0.9476937,0.010725243,0.00066578545,0.00040555588,0.0013227401],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5553469,0.0003260004,0.012803746,0.000100673824,0.00006930928,0.00001830878,0.0006156265,0.0013444766,0.0036582497],"category_scores_gemma":[0.97337884,0.00020718508,0.0029332687,0.00016217823,0.001218893,0.0001131321,0.0001090976,0.0029245345,0.00011890192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019999212,0.0007624148,0.086426094,0.000042097403,0.00068046176,0.00007101131,0.000011116189,0.0000012474793,0.0000014482019,0.038631793,0.03298678,0.83838564],"study_design_scores_gemma":[0.004399283,0.0022921343,0.06371593,0.0001424114,0.00065992185,0.00014451407,0.000013051245,0.00023709453,0.0000021995,0.90602493,0.022179717,0.00018881987],"about_ca_topic_score_codex":0.0000050085873,"about_ca_topic_score_gemma":0.0000029044434,"teacher_disagreement_score":0.86739314,"about_ca_system_score_codex":0.000019704336,"about_ca_system_score_gemma":0.0002796476,"threshold_uncertainty_score":0.99995196},"labels":[{"model":"gemma","categories":[],"domain":null,"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":"low"}],"label_agreement":"agree"},{"id":"W1983806852","doi":"10.1016/j.jclinepi.2007.09.012","title":"Published randomized controlled trials of drug therapy for dementia often lack complete data on harm","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Baycrest Hospital; Institute for Clinical Evaluative Sciences; University of Toronto; Providence Health Care; University of British Columbia; Queen's University; St. Paul's Hospital","funders":"Canadian Institutes of Health Research; Canadian Diabetes Association","keywords":"Harm; Medicine; Randomized controlled trial; Adverse effect; Clinical trial; Dementia; MEDLINE; Psychiatry; Intensive care medicine; Psychology; Pharmacology; Internal medicine; Disease","score_opus":0.978307086267411,"score_gpt":0.7413738633891948,"score_spread":0.23693322287821628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983806852","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008261956,0.95875454,0.022130292,0.005970815,0.0038760814,0.008264584,0.00044816124,0.0000024243466,0.0005448594],"genre_scores_gemma":[0.000012267701,0.9757296,0.01730505,0.0031994765,0.0022878647,0.00016178952,0.00015991168,0.000038992028,0.0011050376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.08380543,0.616505,0.2930286,0.0018756934,0.0042151394,0.0005701227],"domain_scores_gemma":[0.0067198016,0.6804289,0.30278715,0.0059762713,0.0036657082,0.0004221412],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.96078956,0.0010961548,0.34605998,0.0013247791,0.00011188322,0.00022736879,0.011486488,0.0010279842,0.006204479],"category_scores_gemma":[0.98643273,0.0003446708,0.11797557,0.000773481,0.0007186041,0.0003228194,0.00040703904,0.0017232182,0.00026010378],"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":[0.021116855,0.00025309998,0.00006523059,0.00059090863,0.024046266,0.000004475493,0.000007927247,0.000008864418,1.3152947e-8,0.0012694154,0.55773526,0.39490166],"study_design_scores_gemma":[0.12045715,0.00032866842,0.0000129541895,0.0019699535,0.01468751,0.000032537602,0.0000085517395,0.00094785687,8.187456e-9,0.014105435,0.8472395,0.00020986197],"about_ca_topic_score_codex":0.0000058883893,"about_ca_topic_score_gemma":0.0000028058564,"teacher_disagreement_score":0.3946918,"about_ca_system_score_codex":0.000027269876,"about_ca_system_score_gemma":0.0014580785,"threshold_uncertainty_score":0.9999005},"labels":[],"label_agreement":null},{"id":"W1984272022","doi":"10.1016/j.jclinepi.2005.01.021","title":"Modeling cumulative dose and exposure duration provided insights regarding the associations between benzodiazepines and injuries","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Safe Handling of Antineoplastic Drugs","field":"Health Professions","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal General Hospital; McGill University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Temazepam; Flurazepam; Akaike information criterion; Medicine; Benzodiazepine; Cumulative dose; Weighting; Nitrazepam; Adverse effect; Cumulative incidence; Statistics; Pharmacology; Internal medicine; Diazepam; Mathematics","score_opus":0.28353474601736706,"score_gpt":0.5286039795637231,"score_spread":0.245069233546356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984272022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97194356,0.00078867615,0.0075859902,0.018349133,0.00077485625,0.0002637753,0.000010021094,0.000018225326,0.00026577857],"genre_scores_gemma":[0.99176854,0.00034151546,0.0036762378,0.0011000707,0.0029989663,0.0000053817316,0.000009886225,0.000013716126,0.00008567615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98860914,0.0057607368,0.004910727,0.00022471837,0.00017596332,0.00031869675],"domain_scores_gemma":[0.9083169,0.087118104,0.0036593212,0.00015510719,0.0006072861,0.00014326438],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017807256,0.00015501105,0.0014986361,0.00010938574,0.0006849635,0.000011046582,0.0001296328,0.0004416226,0.00000548842],"category_scores_gemma":[0.09965868,0.00009084212,0.00016825492,0.00010865381,0.00019860925,0.00025594627,0.00010602027,0.0014083859,0.000003981934],"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":[0.00012601558,0.000024275047,0.98706996,0.000027257036,0.0000954543,0.0000019321883,0.000770582,0.0010066039,0.0000080490145,0.00868793,0.0010488629,0.0011330734],"study_design_scores_gemma":[0.0014476271,0.00023734843,0.9151267,0.00021966173,0.00014419155,0.0000038292887,0.00045568278,0.012059538,0.0000014270647,0.06938599,0.00082291564,0.000095138705],"about_ca_topic_score_codex":0.00021451998,"about_ca_topic_score_gemma":0.00021263077,"teacher_disagreement_score":0.08185143,"about_ca_system_score_codex":0.000032988155,"about_ca_system_score_gemma":0.00038635236,"threshold_uncertainty_score":0.90792525},"labels":[],"label_agreement":null},{"id":"W1984295229","doi":"10.1016/s0895-4356(00)00369-3","title":"The association between exposure to a rear-end collision and future health complaints","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":111,"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":"Whiplash; Medicine; Neck pain; Physical therapy; Occupational safety and health; Injury prevention; Poison control; Cohort study; Epidemiology; Whiplash injury; Cohort; Crash; Emergency medicine; Internal medicine","score_opus":0.12427385047708213,"score_gpt":0.4901626584925829,"score_spread":0.3658888080155008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984295229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7065033,0.00083531335,0.00059025217,0.29085076,0.00071367586,0.0002066784,0.0000018114704,0.000005367598,0.00029287022],"genre_scores_gemma":[0.9692276,0.006987158,0.004838745,0.012985178,0.0054560006,0.000002224499,0.000005741811,0.000010550445,0.00048677807],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99214625,0.0043978705,0.0027774004,0.00016253926,0.00024937704,0.0002665689],"domain_scores_gemma":[0.96164113,0.035526287,0.001874279,0.0001660887,0.00031145962,0.00048073087],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0420866,0.00009181517,0.0013656358,0.000060945178,0.000144152,0.0000061272285,0.00008295482,0.00028961233,0.000019032344],"category_scores_gemma":[0.05673169,0.00004845892,0.00031251574,0.00013553257,0.00009745017,0.000040508367,0.000026809244,0.0007651874,0.000014839903],"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":[0.00042373722,0.000057799974,0.87620234,0.000037785165,0.00010574454,0.0000029875566,0.000074330404,0.000007065473,0.0000065660934,0.0005845024,0.017980723,0.10451644],"study_design_scores_gemma":[0.0009868831,0.003309296,0.809279,0.00009611607,0.000028547274,0.00002722746,0.00013300143,0.000025356507,1.9136358e-7,0.0016426701,0.18443772,0.000033940636],"about_ca_topic_score_codex":0.000017014552,"about_ca_topic_score_gemma":0.00001863104,"teacher_disagreement_score":0.27786556,"about_ca_system_score_codex":0.000107619795,"about_ca_system_score_gemma":0.00015113143,"threshold_uncertainty_score":0.9863734},"labels":[],"label_agreement":null},{"id":"W1984961948","doi":"10.1016/j.jclinepi.2004.04.013","title":"Short-acting inhaled beta-2-agonists increased the mortality from chronic obstructive pulmonary disease in observational designs","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":26,"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; Royal Victoria Regional Health Centre; Royal Victoria Hospital","funders":"","keywords":"Observational study; Medicine; Pulmonary disease; BETA (programming language); Internal medicine; Intensive care medicine","score_opus":0.34619625348550953,"score_gpt":0.4940305484411004,"score_spread":0.14783429495559086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984961948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9764905,0.004076915,0.0006469547,0.017163353,0.0005055381,0.0005839898,0.0000890468,0.000020178677,0.00042353937],"genre_scores_gemma":[0.9899042,0.0005229016,0.0025263522,0.0021062326,0.004707971,0.000031763815,0.000101254234,0.000040109677,0.00005917883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98613983,0.006346456,0.005273921,0.0006725918,0.00077734975,0.00078987505],"domain_scores_gemma":[0.96483517,0.030868964,0.0018280854,0.0007542643,0.0005554701,0.0011580396],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014607824,0.00036919906,0.0026123293,0.0001909,0.00015376172,0.000015682699,0.00061039964,0.00039153988,0.00066632003],"category_scores_gemma":[0.042983666,0.00025300225,0.0011856414,0.00036847673,0.0010778807,0.0003851699,0.00021957909,0.002750164,0.000034416033],"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":[0.0018860702,0.00074149435,0.9368665,0.00007659665,0.00043168152,0.0010807856,0.000032601565,0.0011360195,0.00010367285,0.0005543113,0.00025524944,0.056835014],"study_design_scores_gemma":[0.0018865842,0.00016690389,0.97083133,0.0002007886,0.00037246122,0.00014572869,0.00007687588,0.016466247,0.000014870078,0.0074249497,0.0022124983,0.00020077429],"about_ca_topic_score_codex":0.00036499178,"about_ca_topic_score_gemma":0.00014805667,"teacher_disagreement_score":0.05663424,"about_ca_system_score_codex":0.0010167325,"about_ca_system_score_gemma":0.0027991098,"threshold_uncertainty_score":0.9999922},"labels":[],"label_agreement":null},{"id":"W1984975790","doi":"10.1016/j.jclinepi.2013.09.020","title":"World Health Organization recommendations are often strong based on low confidence in effect estimates","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":80,"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; Health Canada; McMaster University","funders":"University of Toronto; University of Oxford","keywords":"Confidence interval; Grading (engineering); Guideline; Low Confidence; Medicine; MEDLINE; Statistics; Psychology; Political science; Mathematics; Internal medicine; Social psychology","score_opus":0.6255112058171864,"score_gpt":0.6792330395737398,"score_spread":0.05372183375655337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984975790","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":[0.000109269364,0.73580384,0.06518847,0.18989421,0.0057224906,0.0030159322,0.00006300229,0.00006645757,0.00013634244],"genre_scores_gemma":[0.00051611016,0.9588537,0.015379594,0.022868544,0.001832527,0.00001646763,0.0004136012,0.00007920229,0.00004022752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96136993,0.018574419,0.018666865,0.00056528585,0.00035244875,0.00047102183],"domain_scores_gemma":[0.5956243,0.37612945,0.026241397,0.00067083514,0.00070982176,0.0006241792],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.077626556,0.00046175346,0.012011264,0.0007530834,0.000064224056,0.000014232874,0.00034649202,0.0006417547,0.00040555702],"category_scores_gemma":[0.6337612,0.00032088681,0.0012596939,0.0007660111,0.00016673637,0.00013014466,0.000066121145,0.003702454,0.00010049197],"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":[0.0002975413,0.00046066876,0.035746183,0.006235429,0.00019700512,0.000043765434,0.0000040134455,0.0002873844,1.7524862e-8,0.00024392612,0.026105678,0.9303784],"study_design_scores_gemma":[0.005307904,0.006188362,0.01681565,0.08059409,0.0019124898,0.00028535497,0.000019360432,0.00432327,1.7244186e-7,0.00056488276,0.8836049,0.00038356555],"about_ca_topic_score_codex":0.000050349223,"about_ca_topic_score_gemma":0.00010409352,"teacher_disagreement_score":0.9299948,"about_ca_system_score_codex":0.00041869175,"about_ca_system_score_gemma":0.0022239995,"threshold_uncertainty_score":0.9999243},"labels":[],"label_agreement":null},{"id":"W1985180472","doi":"10.1016/j.jclinepi.2003.11.018","title":"Incidence-based measures of birth, growth restriction, and death can free perinatal epidemiology from erroneous concepts of risk","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Birth, Development, and Health","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Izaak Walton Killam Health Centre","funders":"Health Canada","keywords":"Incidence (geometry); Epidemiology; Gestational age; Medicine; Birth rate; Mortality rate; Pediatrics; Obstetrics; Pregnancy; Population; Mathematics; Research methodology; Surgery; Internal medicine; Biology","score_opus":0.23304978805694734,"score_gpt":0.46035077249729073,"score_spread":0.22730098444034338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985180472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724749,0.0040294044,0.009266232,0.013032067,0.00080445193,0.00018255346,0.00009240758,0.000013467612,0.00010454156],"genre_scores_gemma":[0.8589233,0.09522264,0.042017043,0.003214979,0.00059282075,0.0000022856223,0.000007412815,0.000017489045,0.0000020442228],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98769677,0.0043863365,0.0067316866,0.00041363004,0.0002932142,0.00047836875],"domain_scores_gemma":[0.9547303,0.036568694,0.0066546416,0.0004409293,0.0008954683,0.00071001804],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020254996,0.00025390592,0.004352248,0.00026155717,0.00008034754,0.0000013033538,0.00031224103,0.0007281041,0.000048016114],"category_scores_gemma":[0.23168576,0.0001838915,0.00054368784,0.00017481485,0.0009898185,0.000059391317,0.000079645026,0.0015776907,0.0000020289694],"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":[0.0019215962,0.00022902779,0.9615449,0.00012413642,0.00024682411,0.00007892808,0.00016661521,0.00018161199,0.00005055396,0.03263755,0.0004980768,0.0023201886],"study_design_scores_gemma":[0.0048557064,0.0024943228,0.7177824,0.00029968692,0.00016067088,0.00020048884,0.00007164934,0.000053489646,0.0001050444,0.2736908,0.00018894575,0.00009682747],"about_ca_topic_score_codex":0.0049842466,"about_ca_topic_score_gemma":0.00072715094,"teacher_disagreement_score":0.24376252,"about_ca_system_score_codex":0.00011887,"about_ca_system_score_gemma":0.0022027239,"threshold_uncertainty_score":0.77478606},"labels":[],"label_agreement":null},{"id":"W1985352766","doi":"10.1016/j.jclinepi.2015.01.017","title":"The choice of the noninferiority margin in clinical trials was driven by baseline risk, type of primary outcome, and benefits of new treatment","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"National Institute for Materials Science","keywords":"Medicine; Randomized controlled trial; Baseline (sea); Clinical trial; Margin (machine learning); Population; Randomization; Vignette; Research design; Physical therapy; Surgery; Internal medicine; Psychology; Statistics","score_opus":0.9121244771619215,"score_gpt":0.7014994537019636,"score_spread":0.21062502345995782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985352766","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523654,0.0025501077,0.0094852885,0.0077413,0.0037364159,0.0008646922,0.00018991945,0.000006336303,0.0001894267],"genre_scores_gemma":[0.22460663,0.020301351,0.75043035,0.0012665418,0.0029458406,0.000008322985,0.0000026565315,0.00006529489,0.0003729882],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85925674,0.10220266,0.03680734,0.0005197432,0.00069629,0.000517238],"domain_scores_gemma":[0.1078478,0.8683419,0.021629041,0.00087092636,0.00077425624,0.0005360471],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30797362,0.0002738437,0.009265704,0.000066341025,0.000036495465,0.0000045913785,0.00073425256,0.0007555008,0.000035219487],"category_scores_gemma":[0.9600183,0.00012788139,0.0014828913,0.00025440814,0.0012580135,0.0000498855,0.00026680596,0.00151652,0.0000016151936],"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":[0.0029276574,0.0008659083,0.89499664,0.000058176698,0.00041059716,0.0000017136925,0.000030563577,0.00006456751,0.0000071757054,0.0043246616,0.007231572,0.08908075],"study_design_scores_gemma":[0.009578381,0.004075265,0.7021829,0.00024718948,0.0008213633,0.000007881816,0.0000333283,0.00038098992,0.000045455865,0.27922842,0.0032717271,0.00012709964],"about_ca_topic_score_codex":0.00019739884,"about_ca_topic_score_gemma":0.00011366781,"teacher_disagreement_score":0.76613927,"about_ca_system_score_codex":0.000066347406,"about_ca_system_score_gemma":0.0008540802,"threshold_uncertainty_score":0.71258676},"labels":[],"label_agreement":null},{"id":"W1985589038","doi":"10.1016/s0895-4356(00)00315-2","title":"Stability of indicators of the metabolic syndrome from childhood and adolescence to young adulthood","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":251,"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; York University","funders":"Medical Research Council; Abbott Laboratories","keywords":"Metabolic syndrome; Young adult; Medicine; Cholesterol; High-density lipoprotein; Internal medicine; Endocrinology; Trunk; Obesity; Biology","score_opus":0.06849339627234459,"score_gpt":0.38170036164407267,"score_spread":0.3132069653717281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985589038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906689,0.0050985725,0.0006477787,0.002600758,0.0005717383,0.0003079971,0.000018547924,0.000004829116,0.000080856866],"genre_scores_gemma":[0.9924875,0.0026854386,0.0031781162,0.001226408,0.00040179942,0.0000023439243,0.0000010593313,0.0000126197365,0.0000047540307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99280965,0.0027475352,0.0035388868,0.00027708875,0.00035343098,0.00027338642],"domain_scores_gemma":[0.99232835,0.004125907,0.0022245294,0.00064637745,0.00024370805,0.00043110462],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013261224,0.00015800167,0.0036582027,0.000120419914,0.000028680934,0.0000018451807,0.00031996876,0.00028958608,0.000055523527],"category_scores_gemma":[0.05699712,0.00009252778,0.0012818596,0.0003111578,0.0005003326,0.000057705136,0.0001238737,0.00088872935,0.0000026826253],"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":[0.000264823,0.00037020835,0.8942369,0.00003278629,0.0005690375,0.000014764852,0.00014030623,0.0000060748703,0.000030036088,0.000054571894,0.0000651628,0.1042153],"study_design_scores_gemma":[0.0018472701,0.00089090504,0.9931729,0.00036040696,0.00056836405,0.00027377505,0.000098547636,0.000007868634,0.00028632316,0.0012040144,0.0012162259,0.00007340314],"about_ca_topic_score_codex":0.0007611811,"about_ca_topic_score_gemma":0.00007442519,"teacher_disagreement_score":0.1041419,"about_ca_system_score_codex":0.00001364689,"about_ca_system_score_gemma":0.00024441685,"threshold_uncertainty_score":0.9509462},"labels":[],"label_agreement":null},{"id":"W1986028233","doi":"10.1016/s0895-4356(01)00436-x","title":"Utilization of lipid-lowering drugs in men and women","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","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 British Columbia","funders":"Ministry of Health, British Columbia","keywords":"Medicine; Medical prescription; Statin; Coronary heart disease; Randomized controlled trial; Population; Internal medicine; Physical therapy; Pharmacology; Environmental health","score_opus":0.20595149103292024,"score_gpt":0.45689016587011694,"score_spread":0.2509386748371967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986028233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99167496,0.002593445,0.0006822126,0.0030481927,0.0002355964,0.000109465356,4.426495e-7,0.0000031042694,0.0016525949],"genre_scores_gemma":[0.98680496,0.010315347,0.0011447257,0.0009815414,0.0006685723,0.0000017663939,2.9064105e-7,0.0000071805835,0.00007563185],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957977,0.0010428304,0.0026661048,0.00012811825,0.00015384595,0.00021142191],"domain_scores_gemma":[0.99590534,0.0025873268,0.0009831571,0.00017226419,0.00010926093,0.0002426435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020536704,0.00007244222,0.0018718782,0.00010989302,0.0000116001775,0.0000010037935,0.000057275356,0.00019919197,0.00012098432],"category_scores_gemma":[0.018149268,0.00005093853,0.00029291425,0.00010538732,0.0001089127,0.000049363396,0.000027344702,0.0004734076,0.0000022543702],"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":[0.0004896173,0.0002940362,0.63974124,0.0002219619,0.00021988097,0.00003205901,0.00073317287,0.000043246066,0.000034196735,0.00031850702,0.001050077,0.35682198],"study_design_scores_gemma":[0.005102338,0.0019525089,0.9773998,0.00029771443,0.000060497463,0.0002611375,0.00041200707,0.0022088524,0.00003569938,0.0016975407,0.010495255,0.0000766335],"about_ca_topic_score_codex":0.000023861605,"about_ca_topic_score_gemma":0.0000013462463,"teacher_disagreement_score":0.35674536,"about_ca_system_score_codex":0.000038237846,"about_ca_system_score_gemma":0.00005768028,"threshold_uncertainty_score":0.9901213},"labels":[],"label_agreement":null},{"id":"W1986036750","doi":"10.1016/j.jclinepi.2014.12.011","title":"Guideline panels should not GRADE good practice statements","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Guideline; Scopus; Certainty; Medicine; Evidence-based medicine; MEDLINE; Family medicine; Psychology; Medical physics; Alternative medicine; Mathematics; Pathology; Political science","score_opus":0.9681503662717942,"score_gpt":0.7472951200853079,"score_spread":0.22085524618648633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986036750","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012698678,0.00084719365,0.13662803,0.852536,0.006040661,0.00043181918,0.000032592456,0.0000037822335,0.0033528944],"genre_scores_gemma":[0.00052389695,0.0010117005,0.06904317,0.897602,0.018629597,0.000007861218,0.000037390724,0.000047455746,0.01309692],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.22407477,0.5101251,0.2479024,0.00271457,0.013832523,0.0013506712],"domain_scores_gemma":[0.0997045,0.64670193,0.2376357,0.006357443,0.008870685,0.0007297509],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.87904185,0.0009323817,0.043591227,0.0007954721,0.00011909716,0.00029901948,0.007037708,0.002917614,0.010248682],"category_scores_gemma":[0.95220435,0.00040138233,0.017570687,0.00068439206,0.00038538742,0.0005975658,0.00040943132,0.009375308,0.005512195],"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":[0.00005549111,0.00010760533,0.0053783897,0.000058247617,0.001784249,0.00035386742,0.000015736301,0.00014572273,7.245242e-7,0.00041464777,0.977894,0.013791321],"study_design_scores_gemma":[0.000634061,0.000624277,0.0013858293,0.000120781784,0.0019491029,0.0005952472,0.000039301252,0.0013645226,3.7744448e-7,0.029733071,0.9632333,0.00032012013],"about_ca_topic_score_codex":0.000022812434,"about_ca_topic_score_gemma":0.0000029398577,"teacher_disagreement_score":0.13657685,"about_ca_system_score_codex":0.0000692534,"about_ca_system_score_gemma":0.00055764185,"threshold_uncertainty_score":0.9998438},"labels":[],"label_agreement":null},{"id":"W1986041813","doi":"10.1016/j.jclinepi.2008.07.008","title":"Varied definitions of hospital volume did not alter the conclusions of volume–outcome analyses","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":38,"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. Michael's Hospital; Institute for Clinical Evaluative Sciences; University Health Network; University of Toronto","funders":"","keywords":"Volume (thermodynamics); Medicine; Outcome (game theory); Odds ratio; Odds; Bootstrapping (finance); Confidence interval; Emergency medicine; Internal medicine; Econometrics; Logistic regression; Mathematics","score_opus":0.6983093158687241,"score_gpt":0.5725415723542889,"score_spread":0.1257677435144352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986041813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9559637,0.0008279672,0.0010097921,0.04068846,0.0007740521,0.0001697004,0.000033806664,0.0000057662505,0.0005267766],"genre_scores_gemma":[0.9852904,0.003708614,0.004927407,0.0054868846,0.00045233002,0.000006095233,0.0000086816435,0.000013059291,0.00010651413],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99227226,0.0015535557,0.0054273508,0.00020213111,0.00028243524,0.0002622682],"domain_scores_gemma":[0.96927637,0.02568663,0.0036584407,0.00045388457,0.00063853816,0.00028614647],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005422792,0.00016925737,0.003208055,0.00011927938,0.000102996375,0.0000013879582,0.00023039564,0.00025768136,0.0005437154],"category_scores_gemma":[0.05032369,0.00008959464,0.0018002485,0.00017676191,0.0010118701,0.000052538144,0.00009498986,0.00066511997,0.000027826021],"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":[0.0002581124,0.0018175405,0.98100704,0.00001587057,0.00093204074,0.00008735629,0.00009518353,0.00008599124,0.000050129354,0.0016995702,0.013441316,0.00050984556],"study_design_scores_gemma":[0.002347724,0.0043117376,0.9874128,0.00008625393,0.0010107503,0.00021867233,0.00007260701,0.0002444284,0.00012260118,0.0018268031,0.002272001,0.000073630596],"about_ca_topic_score_codex":0.00011373604,"about_ca_topic_score_gemma":0.00000652805,"teacher_disagreement_score":0.044900898,"about_ca_system_score_codex":0.0000318622,"about_ca_system_score_gemma":0.00028598605,"threshold_uncertainty_score":0.9576758},"labels":[],"label_agreement":null},{"id":"W1986334969","doi":"10.1016/j.jclinepi.2012.02.010","title":"The importance of measuring strength-of-preference scores for health care options in preference-sensitive care","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 British Columbia","funders":"National Institute on Aging; Dartmouth College","keywords":"Preference; Categorical variable; Medicine; Health care; Population; Psychology; Family medicine; Statistics; Environmental health; Mathematics; Economics","score_opus":0.8242383951360375,"score_gpt":0.5898029715006616,"score_spread":0.23443542363537584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986334969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93786526,0.036280774,0.004221282,0.01878906,0.0016116628,0.000596111,0.000259949,0.0000050451895,0.00037088714],"genre_scores_gemma":[0.9831757,0.0026757696,0.011292275,0.0022161321,0.0005857134,0.00002110806,0.000008127158,0.000013041508,0.000012120364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9784015,0.0035325116,0.017172553,0.00027735112,0.00008578187,0.00053031754],"domain_scores_gemma":[0.9414093,0.039365266,0.018088065,0.00040340828,0.00045745913,0.00027648814],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08653789,0.00014496919,0.00315008,0.00019045033,0.00010856431,0.000005141279,0.00036778083,0.00024364828,0.000013230793],"category_scores_gemma":[0.12237598,0.00012381113,0.00046756404,0.00011523276,0.0002502351,0.00024487125,0.000052931355,0.0005238083,0.00000872761],"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":[0.00012418686,0.00007846812,0.9189207,0.0003861692,0.00007419932,1.1959987e-7,0.00246621,0.00045032846,2.9217534e-7,0.07469458,0.0011826335,0.0016221305],"study_design_scores_gemma":[0.0010625405,0.00056373986,0.9761755,0.00039342383,0.000011685474,0.0000035785206,0.0050637037,0.00042041152,0.0000047480207,0.010668745,0.0055058044,0.00012614996],"about_ca_topic_score_codex":0.00019379656,"about_ca_topic_score_gemma":0.00095156534,"teacher_disagreement_score":0.064025834,"about_ca_system_score_codex":0.00028693094,"about_ca_system_score_gemma":0.00063726,"threshold_uncertainty_score":0.94060147},"labels":[],"label_agreement":null},{"id":"W1986439447","doi":"10.1016/s0895-4356(02)00586-3","title":"Irritable bowel syndrome: are incentives useful for improving survey response rates?","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Gastrointestinal motility and disorders","field":"Medicine","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 Calgary","funders":"","keywords":"Incentive; Irritable bowel syndrome; Medicine; Psychiatry; Economics; Microeconomics","score_opus":0.29419776382088814,"score_gpt":0.48980414418023926,"score_spread":0.19560638035935113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986439447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770184,0.0007029124,0.015362279,0.005729722,0.00080988416,0.00027690476,0.000016011969,0.000011940438,0.00007193013],"genre_scores_gemma":[0.9768395,0.00007709798,0.01970229,0.0028648668,0.0001216861,0.0000042712913,0.0000046881773,0.000020149178,0.00036547327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98334473,0.011889616,0.0037273415,0.00033789466,0.00015979778,0.0005405908],"domain_scores_gemma":[0.87434244,0.12009168,0.0035487956,0.0003631951,0.0009829893,0.0006708994],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.088871546,0.00019121154,0.0023646313,0.00013282192,0.00008038275,0.000007984034,0.0001725486,0.00029878967,0.00008303267],"category_scores_gemma":[0.67394537,0.0001435258,0.00075827003,0.00014771573,0.00034488444,0.0001343762,0.000032274853,0.0009725897,0.000013946369],"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":[0.016517386,0.00048283435,0.9793884,0.000099890756,0.00009282078,0.00010947672,0.000010203787,0.00004086207,0.00005563974,0.0001431446,0.0026062198,0.00045308052],"study_design_scores_gemma":[0.0042134095,0.0046479413,0.98289853,0.0002002779,0.00010993515,0.0014159108,0.00015307825,0.00022420626,0.0000149482,0.0034188193,0.0026053684,0.00009759697],"about_ca_topic_score_codex":0.000034246797,"about_ca_topic_score_gemma":0.000031594183,"teacher_disagreement_score":0.5850738,"about_ca_system_score_codex":0.00004990865,"about_ca_system_score_gemma":0.0005877414,"threshold_uncertainty_score":0.9381985},"labels":[],"label_agreement":null},{"id":"W1987451225","doi":"10.1016/j.jclinepi.2011.12.004","title":"Two methods provide similar signals for the need to update systematic reviews","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"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; Ottawa Hospital","funders":"National Heart, Lung, and Blood Institute; Agency for Healthcare Research and Quality; University of Ottawa","keywords":"Systematic review; Computer science; Data mining; Range (aeronautics); Subject-matter expert; Machine learning; Data science; Medical physics; Artificial intelligence; Medicine; MEDLINE; Expert system","score_opus":0.9621215353201487,"score_gpt":0.7559763864476546,"score_spread":0.20614514887249402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987451225","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016175791,0.030913815,0.9159504,0.044377767,0.0033159028,0.0035587274,0.0000040480923,0.0000024199833,0.00025930212],"genre_scores_gemma":[0.034083705,0.0019061056,0.90480673,0.052320216,0.0041989437,0.00032772354,0.0000010899637,0.00003321523,0.002322273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.3147703,0.53974867,0.14031827,0.0010257639,0.0030067663,0.0011302239],"domain_scores_gemma":[0.052222513,0.8559545,0.083260894,0.0044716997,0.0029268835,0.0011634654],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.9389195,0.00040535184,0.028489908,0.0003112565,0.00016269299,0.00014252111,0.0037650648,0.00024579564,0.0017524592],"category_scores_gemma":[0.96349275,0.00012528698,0.012547221,0.00086889224,0.00014582179,0.0003303904,0.00021612001,0.0007222277,0.0018700286],"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":[0.00017862977,0.00024751356,0.05151975,0.0030372231,0.002150853,0.000002793834,0.00027726553,0.0012237763,0.00004645901,0.025157653,0.8093184,0.10683967],"study_design_scores_gemma":[0.00047230543,0.0003387518,0.0043454166,0.0008848742,0.0021920137,0.00009697928,0.0003091003,0.0074906135,0.000006729569,0.049199983,0.93446356,0.00019969101],"about_ca_topic_score_codex":0.0000028537286,"about_ca_topic_score_gemma":0.0000041716817,"teacher_disagreement_score":0.3162059,"about_ca_system_score_codex":0.000030425515,"about_ca_system_score_gemma":0.0001334125,"threshold_uncertainty_score":0.99916005},"labels":[],"label_agreement":null},{"id":"W1987452905","doi":"10.1016/j.jclinepi.2005.03.001","title":"The role of clinical epidemiology in health equity: Let's take action!","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Disadvantaged; Health equity; Socioeconomic status; Social epidemiology; Social determinants of health; Epidemiology; Equity (law); Environmental health; Race and health; Global health; Action (physics); Medicine; Public health; Economic growth; Political science; Economics; Population; Nursing","score_opus":0.829484883307106,"score_gpt":0.7571928300512152,"score_spread":0.07229205325589083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987452905","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":[0.000025441157,0.9159986,0.00026025053,0.06577162,0.012884789,0.0012941123,0.000052476604,0.000024160585,0.0036885433],"genre_scores_gemma":[0.000023600496,0.9265132,0.003093462,0.05686681,0.012501451,0.0000637439,0.000028983319,0.000078249934,0.00083049777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.64380366,0.25141737,0.099717245,0.0012081534,0.0006024188,0.0032511228],"domain_scores_gemma":[0.4145953,0.5178745,0.06438594,0.0012605716,0.00060387666,0.0012798127],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4349536,0.00079064246,0.038321856,0.0005239732,0.0006001473,0.0000036055808,0.0023093452,0.0052725067,0.00043787362],"category_scores_gemma":[0.45651475,0.00044568832,0.0068860403,0.00051473174,0.0012324743,0.00017165966,0.0009778601,0.020999104,0.00029852206],"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":[0.00032361763,0.0002221822,0.0573038,0.005134995,0.00036069658,0.000010867902,0.000028880419,0.0000041359413,1.6853416e-9,0.009586654,0.07288399,0.85414016],"study_design_scores_gemma":[0.0013249207,0.0012730042,0.018721696,0.0068101375,0.00029839043,0.00007849472,0.0001428374,0.000022209051,1.0756148e-9,0.020798152,0.95027244,0.00025770598],"about_ca_topic_score_codex":0.00059829646,"about_ca_topic_score_gemma":0.0018074787,"teacher_disagreement_score":0.8773885,"about_ca_system_score_codex":0.0012218079,"about_ca_system_score_gemma":0.032032903,"threshold_uncertainty_score":0.9997995},"labels":[],"label_agreement":null},{"id":"W1987534771","doi":"10.1016/j.jclinepi.2006.08.008","title":"Racial/ethnic differences in preferences for the EQ-5D health states: results from the U.S. valuation study","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":75,"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 of Health Economics; University of Alberta","funders":"Agency for Healthcare Research and Quality; U.S. Public Health Service; Canada Research Chairs","keywords":"Ethnic group; Demography; Respondent; Socioeconomic status; Health equity; Race and health; Population; Race (biology); Valuation (finance); Medicine; Gerontology; Public health; Psychology; Sociology; Economics; Political science","score_opus":0.9046725709789157,"score_gpt":0.6150404262562622,"score_spread":0.28963214472265353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987534771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73472357,0.008059,0.014699538,0.23866276,0.0022685195,0.0012434112,0.00028175785,0.000007992185,0.00005347371],"genre_scores_gemma":[0.973079,0.0025293394,0.002100784,0.019528903,0.0025756357,0.00006712352,0.00003074326,0.000013468698,0.00007495573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95331365,0.015503405,0.029852992,0.0006027073,0.00016494698,0.0005623247],"domain_scores_gemma":[0.68894094,0.28670886,0.023430293,0.0005706905,0.00019712685,0.0001520978],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32521567,0.00018301333,0.0033771528,0.00013377858,0.00022049356,0.000031858584,0.000739746,0.00022060126,0.000051185594],"category_scores_gemma":[0.20009902,0.00011402359,0.00042285523,0.00017512622,0.00022273842,0.00021521121,0.000051907835,0.0007516847,0.000060203474],"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":[0.0003556704,0.00041001124,0.9503674,0.000020572437,0.00013744287,3.5982364e-7,0.0024604632,0.0027175026,2.1428955e-8,0.0089116795,0.029828247,0.004790646],"study_design_scores_gemma":[0.0020653903,0.00086670666,0.74432933,0.00005170366,0.000013419174,7.8293687e-7,0.0020137369,0.0075020357,2.3140206e-8,0.23795226,0.0051216376,0.000082939536],"about_ca_topic_score_codex":0.00939203,"about_ca_topic_score_gemma":0.011599361,"teacher_disagreement_score":0.27120546,"about_ca_system_score_codex":0.00019461954,"about_ca_system_score_gemma":0.0005129851,"threshold_uncertainty_score":0.99720454},"labels":[],"label_agreement":null},{"id":"W1987609279","doi":"10.1016/j.jclinepi.2008.10.012","title":"An evidence-based practice guideline for the peer review of electronic search strategies","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":627,"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; Institute of Population and Public Health; Children's Hospital of Eastern Ontario","funders":"University of Ottawa","keywords":"Systematic review; Checklist; Computer science; Guideline; MEDLINE; Quality (philosophy); Resource (disambiguation); Information retrieval; Peer review; Knowledge management; Data science; Medicine; Psychology; Political science","score_opus":0.9673765442294219,"score_gpt":0.7858036557685306,"score_spread":0.18157288846089126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987609279","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.263364e-7,0.7793129,0.15632176,0.061916396,0.0005751691,0.0016388351,0.000015954833,0.0000015108885,0.00021721177],"genre_scores_gemma":[0.0000038257654,0.9365493,0.04370797,0.017435756,0.0016733804,0.000033492506,0.000016441627,0.000023936247,0.0005558761],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.21530896,0.53772265,0.23112318,0.0021077641,0.012509556,0.0012279006],"domain_scores_gemma":[0.037283592,0.77261776,0.15406384,0.00589038,0.029685697,0.00045873824],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9413009,0.00070529256,0.05527131,0.00046717116,0.00011970725,0.00020520294,0.00810604,0.0008178233,0.0024803635],"category_scores_gemma":[0.9706985,0.00023313638,0.02833861,0.0014606124,0.00039113866,0.0007167083,0.000102362545,0.0029606372,0.00018813611],"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":[0.0000434069,0.00010811961,0.000014722399,0.009125702,0.0007838032,0.0000036135568,0.0000030856897,0.00016732371,1.0345789e-8,0.0035763343,0.3032942,0.6828797],"study_design_scores_gemma":[0.00016681489,0.0016314916,0.000020820004,0.03987585,0.009038013,0.00015511832,0.00006157651,0.0015044296,1.0997654e-8,0.007288707,0.94008166,0.00017552085],"about_ca_topic_score_codex":0.00000934656,"about_ca_topic_score_gemma":0.0000061155456,"teacher_disagreement_score":0.68270415,"about_ca_system_score_codex":0.00008646508,"about_ca_system_score_gemma":0.007967058,"threshold_uncertainty_score":0.9993396},"labels":[],"label_agreement":null},{"id":"W1987629986","doi":"10.1016/j.jclinepi.2007.01.001","title":"Probabilistic threshold technique showed that patients' preferences for specific trade-offs between pain relief and each side effect of treatment in osteoarthritis varied","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC; Arthritis Society","keywords":"Medicine; Osteoarthritis; Bleed; Adverse effect; Physical therapy; Locus of control; Migraine; Randomized controlled trial; Internal medicine; Surgery; Psychology; Alternative medicine","score_opus":0.12562121203317012,"score_gpt":0.4046832705326977,"score_spread":0.2790620584995276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987629986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929281,0.0012498175,0.0021142662,0.0006080111,0.00034993465,0.002513495,0.00002949833,0.000014007264,0.00019287768],"genre_scores_gemma":[0.99117696,0.00077246985,0.0073439023,0.00012589245,0.0004067122,0.00007703526,0.000046411536,0.000023999446,0.00002661855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99330944,0.0021841002,0.0034813923,0.00038419262,0.00018180828,0.0004590661],"domain_scores_gemma":[0.9586167,0.039189912,0.0015323685,0.00023765529,0.00009752863,0.00032587323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024612295,0.00029575365,0.0034018257,0.00022108138,0.000037747497,0.000004578293,0.00011680291,0.00056742557,0.0000120833465],"category_scores_gemma":[0.012445884,0.00019165836,0.00058627006,0.00010974067,0.0002876459,0.000074374606,0.000025859197,0.00051137427,6.63535e-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":[0.00337943,0.0004197116,0.6986227,0.00010430169,0.00007994826,0.000028948214,0.000050337847,9.741584e-7,0.00025715007,0.00026267848,0.00006186264,0.29673192],"study_design_scores_gemma":[0.024121953,0.197083,0.75550586,0.001145719,0.0005098977,0.00006328633,0.000056786015,0.000012426383,0.004656864,0.014142724,0.0024547537,0.0002467491],"about_ca_topic_score_codex":0.000011878277,"about_ca_topic_score_gemma":0.000057218946,"teacher_disagreement_score":0.2964852,"about_ca_system_score_codex":0.00011463832,"about_ca_system_score_gemma":0.00013023829,"threshold_uncertainty_score":0.9958727},"labels":[],"label_agreement":null},{"id":"W1987725716","doi":"10.1016/j.jclinepi.2008.11.011","title":"The Lower Extremity Functional Scale could be an alternative to the Western Ontario and McMaster Universities Osteoarthritis Index physical function scale","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":121,"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":"Osteoarthritis; Scale (ratio); Index (typography); Physical therapy; Function (biology); Medicine; Physical medicine and rehabilitation; Alternative medicine; Geography; Computer science; Biology; Cartography; Pathology; World Wide Web","score_opus":0.09583945788283012,"score_gpt":0.38419011313157486,"score_spread":0.28835065524874476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987725716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96350896,0.00026879224,0.0014199021,0.03232512,0.001395678,0.00023932493,0.0000063805765,0.000010995088,0.0008248566],"genre_scores_gemma":[0.9789245,0.00018205491,0.00029443746,0.014473565,0.0021807891,0.0000032088226,0.000006601789,0.000010375885,0.003924474],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99701816,0.0009870018,0.0011005403,0.00028266167,0.00029664495,0.00031499827],"domain_scores_gemma":[0.99524236,0.003184533,0.0006319383,0.00022963842,0.0003094047,0.00040213094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003413374,0.00018940642,0.0010180898,0.00005670465,0.00024091236,0.00002289707,0.00014388878,0.0002041811,0.00009916488],"category_scores_gemma":[0.0006410499,0.00010264373,0.00034664947,0.00007417703,0.00032461056,0.00022986076,0.0000533372,0.00093726435,0.000014116709],"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":[0.015660405,0.0011210445,0.3775955,0.0000045934817,0.00019976591,0.000110744324,0.0011573267,0.00009921769,0.0001574882,0.0010138303,0.004978185,0.5979019],"study_design_scores_gemma":[0.0064222193,0.027242303,0.85623205,0.00010957496,0.00030481737,0.0005369961,0.000825592,0.00011607017,0.000030271394,0.0054687806,0.102560215,0.00015110118],"about_ca_topic_score_codex":0.00014217242,"about_ca_topic_score_gemma":0.005736705,"teacher_disagreement_score":0.5977508,"about_ca_system_score_codex":0.00011030675,"about_ca_system_score_gemma":0.00024664614,"threshold_uncertainty_score":0.418569},"labels":[],"label_agreement":null},{"id":"W1987826691","doi":"10.1016/j.jclinepi.2014.07.005","title":"Adding a “GRADE” to the quality appraisal of rheumatoid arthritis guidelines identifies limitations beyond AGREE-II","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":19,"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 Health Network; Mount Sinai Hospital; University of Calgary; University of Toronto","funders":"","keywords":"Rheumatoid arthritis; Medicine; Quality (philosophy); Critical appraisal; Intensive care medicine; Physical therapy; Family medicine; Alternative medicine; Internal medicine; Pathology; Epistemology","score_opus":0.6899436384191389,"score_gpt":0.6432126376440979,"score_spread":0.046731000775041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987826691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6555816,0.0009513029,0.05418259,0.2849345,0.003595008,0.00035316852,0.000020152906,0.000020227695,0.00036145092],"genre_scores_gemma":[0.88428295,0.0064276736,0.08012679,0.02610933,0.0029224418,0.00001037043,0.000022067008,0.000026030062,0.00007233141],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97372466,0.0069767013,0.017919697,0.0003715647,0.0006105713,0.00039678777],"domain_scores_gemma":[0.54909503,0.4267353,0.01693623,0.0012801812,0.004997356,0.0009559092],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09591557,0.00021589402,0.0029222153,0.00019208019,0.00016008236,0.00001181617,0.00041469935,0.000303589,0.00011648751],"category_scores_gemma":[0.8336582,0.00013863563,0.0011272744,0.0003171445,0.00039676682,0.00023310487,0.00021261329,0.0011408228,0.000044873283],"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":[0.001714346,0.00080037076,0.20641468,0.000066900815,0.0006897513,0.000012344794,0.00043840767,0.0010488417,0.0005409636,0.013871746,0.3202342,0.45416743],"study_design_scores_gemma":[0.005649933,0.004250014,0.47840527,0.0006139969,0.0002496762,0.00046526417,0.0014372424,0.002148847,0.00006983966,0.017406521,0.4890498,0.00025359457],"about_ca_topic_score_codex":0.00019165345,"about_ca_topic_score_gemma":0.00052361406,"teacher_disagreement_score":0.73774266,"about_ca_system_score_codex":0.000027461876,"about_ca_system_score_gemma":0.0003805411,"threshold_uncertainty_score":0.93094516},"labels":[],"label_agreement":null},{"id":"W1987916785","doi":"10.1016/j.jclinepi.2008.05.003","title":"Commentary on “Alternative graphs for diagnostic tests: the agreement chart and the receiver operating characteristic curve”","year":2008,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Receiver operating characteristic; Computer science; Chart; Perception; Feature (linguistics); Artificial intelligence; Information retrieval; Statistics; Psychology; Mathematics; Machine learning; Linguistics","score_opus":0.49507110752261396,"score_gpt":0.520213486178791,"score_spread":0.025142378656177078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987916785","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.01384038,0.0011473614,0.00176267,0.9758306,0.0058453297,0.0013130372,0.000080899954,0.000004370229,0.00017534035],"genre_scores_gemma":[0.011438186,0.009475777,0.00067455485,0.9665728,0.011382324,0.00009098307,0.000019341505,0.000020535608,0.0003254642],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9590475,0.02757781,0.010045779,0.0008494858,0.0018431729,0.00063625246],"domain_scores_gemma":[0.44451317,0.54509443,0.008301892,0.0009150272,0.0010155838,0.00015988962],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14348626,0.00046157461,0.003771098,0.00017621757,0.00058471353,0.000104827704,0.002232592,0.0006052018,0.00018367839],"category_scores_gemma":[0.47795868,0.00018118533,0.0016088955,0.00017704625,0.0021937152,0.00014480045,0.00027082665,0.0048009786,0.00004684435],"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":[0.00040164095,0.0001288394,0.030110864,0.000019738321,0.00035422665,0.000055497145,0.00019738528,0.00010889401,3.0661562e-7,0.0003494783,0.95736283,0.010910309],"study_design_scores_gemma":[0.002905281,0.0019108343,0.05329249,0.0003751136,0.0002093101,0.00007202749,0.00010625293,0.0007369848,7.509389e-7,0.08815455,0.8520125,0.00022389651],"about_ca_topic_score_codex":0.000054517994,"about_ca_topic_score_gemma":0.000012773465,"teacher_disagreement_score":0.5175166,"about_ca_system_score_codex":0.00008541581,"about_ca_system_score_gemma":0.00014307884,"threshold_uncertainty_score":0.997495},"labels":[],"label_agreement":null},{"id":"W1988176578","doi":"10.1016/j.jclinepi.2008.12.004","title":"Strengthening the reporting of genetic association studies (STREGA)—an extension of the strengthening the reporting of observational studies in epidemiology (STROBE) statement","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":102,"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; Cancer Care Ontario; Lunenfeld-Tanenbaum Research Institute; Robarts Clinical Trials; Western University; McGill University and Génome Québec Innovation Centre; Public Health Ontario; SickKids Foundation; University of Toronto; University of Ottawa","funders":"","keywords":"Observational study; Strengthening the reporting of observational studies in epidemiology; Statement (logic); Epidemiology; Association (psychology); Medicine; Extension (predicate logic); MEDLINE; Family medicine; Environmental health; Actuarial science; Psychology; Computer science; Business; Political science; Internal medicine","score_opus":0.4981194986637789,"score_gpt":0.5447800585540408,"score_spread":0.046660559890261855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988176578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9785906,0.007007804,0.0011744285,0.01213535,0.0008103053,0.00024517236,0.0000076096094,0.0000028338936,0.000025891819],"genre_scores_gemma":[0.9769287,0.0045521464,0.016507285,0.0013868251,0.0005438951,0.0000075825546,0.000009055757,0.000013004866,0.0000514941],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9454081,0.014009287,0.038845416,0.00059550186,0.00043398308,0.0007077159],"domain_scores_gemma":[0.81512743,0.047498494,0.1336688,0.0010501948,0.0025413658,0.00011370905],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.124441296,0.00026783173,0.0034347926,0.00008515688,0.000172636,0.0000023051582,0.00059271324,0.00044695212,0.000004089984],"category_scores_gemma":[0.66532844,0.00013660667,0.0009576373,0.00025171644,0.00067149213,0.000015727039,0.0002555644,0.0008264084,1.6581706e-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":[0.00013108237,0.0001475833,0.9491997,0.000035026424,0.00066134194,0.0000026482412,0.00043798913,0.036325198,0.0024337787,0.0004322958,0.0015477922,0.008645564],"study_design_scores_gemma":[0.00060902326,0.0011707172,0.978883,0.00023919526,0.00020276832,0.000044883753,0.0026068732,0.0015031408,0.00050028006,0.013685108,0.00043952532,0.000115457755],"about_ca_topic_score_codex":0.00005695642,"about_ca_topic_score_gemma":0.00011984407,"teacher_disagreement_score":0.5408871,"about_ca_system_score_codex":0.00008900865,"about_ca_system_score_gemma":0.0003776194,"threshold_uncertainty_score":0.9015719},"labels":[],"label_agreement":null},{"id":"W1988493763","doi":"10.1016/j.jclinepi.2011.02.010","title":"McMaster Premium LiteratUre Service (PLUS) performed well for identifying new studies for updated Cochrane reviews","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Systematic review; Meta-analysis; Medicine; Confidence interval; MEDLINE; Cochrane collaboration; Odds ratio; Cochrane Library; Internal medicine","score_opus":0.9580667101852316,"score_gpt":0.6984676785914552,"score_spread":0.2595990315937764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988493763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063500196,0.18176855,0.703405,0.030182676,0.012645913,0.006069182,0.0000759992,0.000013743386,0.0023386837],"genre_scores_gemma":[0.02749568,0.043355897,0.8323184,0.0412963,0.008330091,0.00016041272,0.000037978414,0.00008623176,0.046918962],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8797327,0.05193306,0.06509418,0.0011666991,0.0014293498,0.00064398465],"domain_scores_gemma":[0.49092266,0.35705635,0.131703,0.004366171,0.01463048,0.0013213396],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5787074,0.0004442961,0.021020941,0.00031402032,0.00016855884,0.00012455271,0.0023793208,0.00047894518,0.0038935654],"category_scores_gemma":[0.73840606,0.0001844873,0.0089308275,0.00076155324,0.00011969541,0.0004987783,0.00016625033,0.000860837,0.00057176506],"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":[0.0007766761,0.0000970461,0.027346753,0.0007944705,0.0015850695,0.0000037672482,0.0014164302,0.00004221392,0.000012840755,0.0010857,0.9319333,0.03490575],"study_design_scores_gemma":[0.0023316978,0.0008912665,0.017783297,0.0010843582,0.0020254222,0.000093281305,0.0005387286,0.005782459,0.000010065434,0.10531631,0.86386824,0.00027485573],"about_ca_topic_score_codex":0.000004530442,"about_ca_topic_score_gemma":0.00004126482,"teacher_disagreement_score":0.38881007,"about_ca_system_score_codex":0.000034104254,"about_ca_system_score_gemma":0.00021850855,"threshold_uncertainty_score":0.997017},"labels":[],"label_agreement":null},{"id":"W1988547111","doi":"10.1016/s0895-4356(00)00257-2","title":"The relationship between health-related quality of life and frequency of spells in patients with syncope","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiovascular Syncope and Autonomic Disorders","field":"Medicine","cited_by":221,"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":"Syncope (phonology); Medicine; Psychosocial; Quality of life (healthcare); Population; Physical therapy; Health related quality of life; Pediatrics; Internal medicine; Psychiatry; Disease; Environmental health","score_opus":0.2048567036051325,"score_gpt":0.4524069820701616,"score_spread":0.2475502784650291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988547111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99048215,0.0025715714,0.00006464519,0.00589361,0.00008613809,0.0001706614,0.0000044681688,0.000001430035,0.00072535325],"genre_scores_gemma":[0.9980331,0.0006835177,0.0006932018,0.00045634244,0.000063372136,2.341523e-7,0.0000030093497,0.0000068282634,0.000060382383],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99086916,0.0033180073,0.0053517343,0.00013109836,0.00015998815,0.00016998089],"domain_scores_gemma":[0.9719383,0.024726344,0.002732336,0.00026517053,0.00013534803,0.0002024678],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023014514,0.000085934465,0.0023976755,0.0000623334,0.000020097825,0.0000011292368,0.00009684689,0.00017439139,0.00005794166],"category_scores_gemma":[0.032556556,0.000048807866,0.0004006752,0.00012972679,0.00040718907,0.00004776044,0.000013469241,0.0006137991,0.00000696384],"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":[0.000683777,0.00012062128,0.97078097,0.00004182214,0.0002737921,0.0000010367017,0.00003949728,0.00004647792,1.0756229e-7,0.0004899872,0.0001936547,0.02732824],"study_design_scores_gemma":[0.0046306974,0.0010313268,0.98937815,0.0001739487,0.00005770114,0.000004055852,0.00003119702,0.000005072298,1.7137694e-7,0.0043534297,0.00029395297,0.000040318468],"about_ca_topic_score_codex":0.00025591024,"about_ca_topic_score_gemma":0.000039786344,"teacher_disagreement_score":0.027287921,"about_ca_system_score_codex":0.000021718253,"about_ca_system_score_gemma":0.00039337546,"threshold_uncertainty_score":0.9755926},"labels":[],"label_agreement":null},{"id":"W1988565914","doi":"10.1016/j.jclinepi.2012.10.013","title":"Medication initiation rates are not directly comparable across secondary fracture prevention programs: reporting standards based on a systematic review","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","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":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Psychological intervention; Medicine; Comparability; Inclusion (mineral); Inclusion and exclusion criteria; Fragility fracture; Osteoporosis; Physical therapy; Alternative medicine; Internal medicine; Psychology; Pathology; Nursing; Mathematics","score_opus":0.49210532395670525,"score_gpt":0.6386006728730715,"score_spread":0.14649534891636629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988565914","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":[0.000090284564,0.9873602,0.00067309523,0.0058119004,0.00065473217,0.0052101943,0.000033806748,0.000030770927,0.00013503068],"genre_scores_gemma":[0.00029792867,0.98575187,0.0014552161,0.010570422,0.00094192644,0.00041971877,0.0003340243,0.000057477362,0.00017142277],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9479026,0.01927934,0.029965358,0.00064903684,0.001433309,0.0007703487],"domain_scores_gemma":[0.8571729,0.042748857,0.09419102,0.0011706937,0.0034269295,0.0012895688],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.15556061,0.0005207234,0.020904033,0.00024723756,0.000175811,0.000022449336,0.00035448463,0.0014537513,0.0003191463],"category_scores_gemma":[0.4252535,0.00030114304,0.0031057962,0.00039249423,0.00027054455,0.00015660217,0.000053464246,0.005230549,0.000056197045],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017324861,0.0004155595,0.0011494596,0.7914213,0.00030555102,0.00009656122,0.000008628896,0.0000013993784,2.2943029e-8,0.0000034119425,0.010441984,0.19598287],"study_design_scores_gemma":[0.0010286534,0.0021351557,0.0018905774,0.7445746,0.0022975253,0.0006984147,0.00001892365,0.00013634993,2.4243786e-7,0.000063774794,0.24697043,0.00018532314],"about_ca_topic_score_codex":0.000017656836,"about_ca_topic_score_gemma":0.000008568652,"teacher_disagreement_score":0.2696929,"about_ca_system_score_codex":0.00046197072,"about_ca_system_score_gemma":0.0068002115,"threshold_uncertainty_score":0.9999441},"labels":[],"label_agreement":null},{"id":"W1988778209","doi":"10.1016/j.jclinepi.2010.12.019","title":"A framework for applying unfamiliar trial designs in studies of rare diseases","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":107,"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 General Hospital; St. Michael's Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Medicine; Computer science; Psychology; Biology","score_opus":0.9745532133838114,"score_gpt":0.7769818490013579,"score_spread":0.19757136438245348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988778209","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":[0.000008855862,0.7532113,0.23842998,0.000101319216,0.005399761,0.0026463727,0.00016560334,0.000012079689,0.00002468299],"genre_scores_gemma":[0.000001149779,0.52021074,0.47694468,0.00013505212,0.002441887,0.00020317268,0.0000011031733,0.000050390765,0.000011786778],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9077554,0.052356433,0.03790985,0.0008164262,0.00037274978,0.0007891672],"domain_scores_gemma":[0.056542065,0.9135009,0.027938224,0.0008552167,0.00070309953,0.00046048197],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13347289,0.0006805238,0.03689309,0.00038375036,0.00004544479,0.0000052201044,0.0012625016,0.002578467,0.00008211458],"category_scores_gemma":[0.97968704,0.00042491208,0.00726903,0.00030147386,0.0011739493,0.00005940012,0.00027726844,0.0033647942,0.0000062105332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011032108,0.000943801,0.0001563184,0.020868547,0.0019843346,0.00003382351,0.000029353136,7.031312e-7,4.1886135e-9,0.20288807,0.0024798934,0.75958306],"study_design_scores_gemma":[0.009506418,0.002985227,0.00001787748,0.02921886,0.0045183683,0.000015802165,0.000036379977,0.000004599006,4.262469e-8,0.8490817,0.104329534,0.00028519979],"about_ca_topic_score_codex":0.0000022640052,"about_ca_topic_score_gemma":0.0000019068019,"teacher_disagreement_score":0.8611445,"about_ca_system_score_codex":0.00010111541,"about_ca_system_score_gemma":0.0010327518,"threshold_uncertainty_score":0.9998203},"labels":[],"label_agreement":null},{"id":"W1988953504","doi":"10.1016/j.jclinepi.2012.07.013","title":"Experience with GRADE","year":2012,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University","funders":"","keywords":"Guideline; Framing (construction); Quality of evidence; Medicine; Health care; Psychology; Grading (engineering); Medical education; Randomized controlled trial; Surgery; Engineering; Political science","score_opus":0.7518121300574013,"score_gpt":0.6568858881763046,"score_spread":0.09492624188109677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988953504","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":[0.01947442,0.00070173794,0.00488866,0.97042614,0.003812224,0.0002973987,0.0000072132493,0.000018490317,0.000373731],"genre_scores_gemma":[0.011416052,0.0010808866,0.03219233,0.9110863,0.04352658,0.0000073974206,0.000059259357,0.00006200708,0.00056916015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97829354,0.0058008055,0.014081264,0.00043939144,0.0006693898,0.0007156004],"domain_scores_gemma":[0.8597384,0.12341685,0.014664832,0.00071333535,0.000893923,0.0005726237],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.03240682,0.00037586724,0.0054645687,0.00019391053,0.000040556584,0.000007121254,0.00038325967,0.0019496663,0.00079897104],"category_scores_gemma":[0.25059637,0.00022670708,0.0013056225,0.00015377942,0.00065076014,0.00025488168,0.00008422477,0.010237623,0.00011084306],"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":[0.0007914236,0.00018689428,0.2247961,0.000084059684,0.00038904088,0.0008697522,0.000029281704,0.000003311414,0.0000019264046,0.000027157055,0.76342565,0.009395431],"study_design_scores_gemma":[0.0027457876,0.0029693632,0.07442406,0.00029898182,0.0011108612,0.004179491,0.000046329114,0.000025941254,0.0000021066708,0.00074914977,0.91324574,0.00020218574],"about_ca_topic_score_codex":0.000042029504,"about_ca_topic_score_gemma":0.000004653858,"teacher_disagreement_score":0.21818955,"about_ca_system_score_codex":0.00008479807,"about_ca_system_score_gemma":0.00087129814,"threshold_uncertainty_score":0.999346},"labels":[],"label_agreement":null},{"id":"W1989165950","doi":"10.1016/j.jclinepi.2010.08.005","title":"Individuals with diabetes preferred that future trials use patient-important outcomes and provide pragmatic inferences","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":68,"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; Glycemic; Odds ratio; Confidence interval; Logistic regression; Research design; Clinical trial; MEDLINE; Family medicine; Odds; Diabetes mellitus; Randomized controlled trial; Internal medicine","score_opus":0.6126332003297688,"score_gpt":0.5759318997485973,"score_spread":0.03670130058117149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989165950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9837647,0.0003680533,0.00004405331,0.009242526,0.0049820924,0.001422105,0.00006753657,0.000016936774,0.00009199635],"genre_scores_gemma":[0.9619357,0.0009135384,0.015577543,0.01999641,0.0013012093,0.000095010604,0.000050902567,0.000023558248,0.00010615922],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97247744,0.01589404,0.010167965,0.00031823613,0.00040541848,0.00073689234],"domain_scores_gemma":[0.87113345,0.11353799,0.013824874,0.00034283407,0.0002989351,0.0008618995],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059114,0.00028480892,0.0039765583,0.00015134524,0.00030448104,0.000012294126,0.0002543452,0.00068768364,0.00025924854],"category_scores_gemma":[0.0706755,0.00014056287,0.00032261774,0.00008878431,0.0002699884,0.00034701583,0.00011881174,0.0028254427,0.000012786177],"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":[0.000358955,0.00022212783,0.98363745,0.00039490344,0.00020098466,0.0000046363616,0.0005838158,8.071184e-7,0.000003801258,0.0010010268,0.0027267186,0.010864786],"study_design_scores_gemma":[0.0030834677,0.003063684,0.94519055,0.00070041866,0.00015679694,0.000004686129,0.0008978606,0.00003291756,0.0000046126047,0.007103302,0.039602563,0.0001591187],"about_ca_topic_score_codex":0.000053105705,"about_ca_topic_score_gemma":0.0003893093,"teacher_disagreement_score":0.10134398,"about_ca_system_score_codex":0.000024514864,"about_ca_system_score_gemma":0.00076865597,"threshold_uncertainty_score":0.99947506},"labels":[],"label_agreement":null},{"id":"W1989344401","doi":"10.1016/j.jclinepi.2014.10.006","title":"Reporting and methodological quality of sample size calculations in cluster randomized trials could be improved: a review","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":67,"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; Ottawa Hospital; University of Ottawa","funders":"Medical Research Council","keywords":"Sample size determination; Cluster (spacecraft); Randomized controlled trial; Quality (philosophy); Sample (material); Cluster randomised controlled trial; Statistics; Medicine; Medical physics; Computer science; Mathematics; Physics; Surgery","score_opus":0.9907899032094817,"score_gpt":0.8139492127919865,"score_spread":0.17684069041749517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989344401","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051005045,0.9070958,0.08384692,0.005208064,0.0008403901,0.0027814398,0.000030601583,0.0000015396282,0.0001442313],"genre_scores_gemma":[0.000014596181,0.8319719,0.16395938,0.00334167,0.00047707823,0.000055586348,0.0000055149217,0.000014364171,0.00015993715],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.012814458,0.6614824,0.32236475,0.0011175304,0.0018752086,0.00034565333],"domain_scores_gemma":[0.00022244285,0.63609755,0.35958898,0.0020248003,0.0017457582,0.0003204883],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.990004,0.00072070013,0.26126406,0.00050283084,0.00005459871,0.000061502265,0.001911258,0.0014872827,0.0024196284],"category_scores_gemma":[0.99952805,0.0002580231,0.052620243,0.0010137405,0.00069287774,0.00011597853,0.00035782874,0.002431581,0.000019803125],"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":[0.0014088217,0.00012832685,0.0026657826,0.024265649,0.002451124,0.000008150313,0.000014887699,0.000011627774,9.304343e-8,0.0021671257,0.017276414,0.949602],"study_design_scores_gemma":[0.01059803,0.00017077924,0.0006990559,0.0188544,0.009495008,0.00017079161,0.000012181861,0.0005309711,6.439804e-9,0.051344037,0.90784526,0.0002794757],"about_ca_topic_score_codex":0.0000610401,"about_ca_topic_score_gemma":0.000028240833,"teacher_disagreement_score":0.9493225,"about_ca_system_score_codex":0.000039323142,"about_ca_system_score_gemma":0.00069038715,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W1989844406","doi":"10.1016/j.jclinepi.2013.03.014","title":"Addressing continuous data for participants excluded from trial analysis: a guide for systematic reviewers","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":140,"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 Toronto; McMaster University","funders":"Instituto de Salud Carlos III; Canadian Institutes of Health Research","keywords":"Missing data; Imputation (statistics); Meta-analysis; Confidence interval; Data collection; Statistics; Systematic review; Medicine; Computer science; MEDLINE; Econometrics; Data mining; Mathematics","score_opus":0.9802182328684395,"score_gpt":0.742188426636827,"score_spread":0.2380298062316124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989844406","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":[0.094922066,0.0106869405,0.8722835,0.009269434,0.0039651887,0.00844006,0.0002442161,0.000006343476,0.0001822592],"genre_scores_gemma":[0.43034127,0.00093356613,0.54093975,0.013363452,0.008031456,0.0011691153,0.00019859745,0.00007364091,0.0049491716],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.71708536,0.14129171,0.13581195,0.0018945221,0.0030014873,0.00091498136],"domain_scores_gemma":[0.04483922,0.79744935,0.13870537,0.010406444,0.0075052967,0.0010942918],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.75146574,0.00040863303,0.039338138,0.00045649137,0.00013759924,0.00037534712,0.0055825217,0.00041101687,0.0022935285],"category_scores_gemma":[0.959924,0.00017206566,0.01342622,0.0008525244,0.00018616857,0.0005486997,0.00028784922,0.0004458363,0.00040060762],"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":[0.0021286476,0.00033084548,0.043103967,0.0018764879,0.015244734,0.0000050828453,0.00008041469,0.0002719278,0.0000078856365,0.0005525309,0.9219745,0.014422984],"study_design_scores_gemma":[0.045028202,0.0030914885,0.039087377,0.008155906,0.077093154,0.000026644582,0.001723744,0.4383849,0.0000017185541,0.1537915,0.23259096,0.001024421],"about_ca_topic_score_codex":0.000040205912,"about_ca_topic_score_gemma":0.000048018283,"teacher_disagreement_score":0.6893835,"about_ca_system_score_codex":0.000028970517,"about_ca_system_score_gemma":0.0002994704,"threshold_uncertainty_score":0.99979776},"labels":[],"label_agreement":null},{"id":"W1990029283","doi":"10.1016/j.jclinepi.2009.03.019","title":"Systematic review of cross-cultural adaptations of McGill Pain Questionnaire reveals a paucity of clinimetric testing","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":86,"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":"Medicine; Physical therapy; Physical medicine and rehabilitation","score_opus":0.3576179168132342,"score_gpt":0.5777462657621457,"score_spread":0.22012834894891153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990029283","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":[0.0003512823,0.99625283,0.00064842746,0.00049240794,0.0003613698,0.0017209952,0.000033633496,0.000009136297,0.00012989243],"genre_scores_gemma":[0.0026620668,0.9798578,0.016288586,0.0007449278,0.00033706112,0.000016699645,0.000021904892,0.000023587872,0.000047342004],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.93563,0.031043692,0.032051645,0.00039702439,0.0005664943,0.00031109757],"domain_scores_gemma":[0.7141662,0.22370152,0.054255098,0.0009053227,0.0065147276,0.00045709402],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12810901,0.00040539584,0.022429176,0.00049499184,0.000041477117,0.0000019906813,0.000380057,0.000972153,0.000021940412],"category_scores_gemma":[0.8624182,0.00022776717,0.005904195,0.0011972612,0.00078145164,0.00011676115,0.000045160687,0.0015453261,0.0000038740372],"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":[0.000031199397,0.0003560816,0.0034727438,0.8108479,0.00055925426,0.00000403905,0.000005062711,0.000003932956,0.0000010885283,0.00035258016,0.0002710515,0.18409508],"study_design_scores_gemma":[0.0005094926,0.0037131477,0.028016241,0.95880014,0.0049371296,0.00013687891,0.00000766471,0.000047123907,9.093852e-8,0.0011918109,0.0024849947,0.00015531227],"about_ca_topic_score_codex":0.000031501317,"about_ca_topic_score_gemma":0.0000017957714,"teacher_disagreement_score":0.7343092,"about_ca_system_score_codex":0.00009737662,"about_ca_system_score_gemma":0.0006970557,"threshold_uncertainty_score":0.9920839},"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":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1990501193","doi":"10.1016/s0895-4356(99)00136-5","title":"Using medical services claims to assess injuries in the elderly sensitivity of diagnostic and procedure codes for injury ascertainment","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":141,"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; Royal Victoria Hospital","funders":"","keywords":"Medicine; Diagnosis code; Medical record; Injury prevention; Emergency department; Poison control; Occupational safety and health; Emergency medicine; Medical emergency; Surgery; Population; Pathology; Environmental health","score_opus":0.17747662963090013,"score_gpt":0.5181440213462379,"score_spread":0.3406673917153378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990501193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9700543,0.0012109086,0.0005488127,0.02760835,0.0002235151,0.00028445217,0.000012599586,0.0000027812962,0.000054229655],"genre_scores_gemma":[0.98256797,0.004926994,0.0026120497,0.009276838,0.00059402135,0.000006748686,0.0000017710047,0.000007037777,0.000006550727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948731,0.0020699862,0.0023922096,0.00018073144,0.0002467914,0.00023720326],"domain_scores_gemma":[0.92090267,0.07753785,0.00084764784,0.00016660271,0.00030664454,0.00023861344],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020838723,0.00012912505,0.0017115417,0.0000627062,0.000053243293,0.000002434394,0.00011285948,0.00024474235,0.00003701409],"category_scores_gemma":[0.079862006,0.000071844384,0.0002572874,0.00011223237,0.0002868288,0.0000549092,0.000037195343,0.0005499509,5.291145e-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":[0.002129933,0.00047265392,0.91479564,0.00056631456,0.00030693642,0.000081378246,0.0008575561,0.000082660605,0.00010893258,0.0005711638,0.0036533826,0.07637344],"study_design_scores_gemma":[0.001990447,0.007791314,0.9686769,0.0018372008,0.00046741296,0.00038091448,0.002121912,0.001478451,0.000087930406,0.007683634,0.00731023,0.00017363552],"about_ca_topic_score_codex":0.00005236597,"about_ca_topic_score_gemma":0.00017122738,"teacher_disagreement_score":0.07619981,"about_ca_system_score_codex":0.000013880496,"about_ca_system_score_gemma":0.00018565159,"threshold_uncertainty_score":0.9278887},"labels":[],"label_agreement":null},{"id":"W1991118253","doi":"10.1016/s0895-4356(00)00188-8","title":"What contributions do languages other than English make on the results of meta-analyses?","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":453,"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; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Medical Research Council","keywords":"Meta-analysis; Replicate; Randomized controlled trial; Psychological intervention; Meta-regression; Systematic review; Set (abstract data type); Logistic regression; Intervention (counseling); MEDLINE; Medicine; Statistics; Psychology; Clinical psychology; Computer science; Machine learning; Mathematics; Pathology; Psychiatry","score_opus":0.9290449561915868,"score_gpt":0.700577514897942,"score_spread":0.22846744129364482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991118253","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":[0.6938526,0.028718445,0.0057071247,0.20235379,0.004455319,0.0012359174,0.0003972556,0.000010419466,0.06326911],"genre_scores_gemma":[0.96632546,0.0019852188,0.0021476746,0.010714404,0.0014009248,0.00000861046,0.0000029724567,0.000012998625,0.01740172],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6974773,0.22608551,0.07108923,0.0009875544,0.0038487972,0.0005116085],"domain_scores_gemma":[0.24154851,0.6845705,0.062305365,0.0058025806,0.0052535986,0.00051945617],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.6553523,0.00028754247,0.016549967,0.00023325534,0.00009007351,0.00017198364,0.0023907758,0.00031047268,0.02771577],"category_scores_gemma":[0.8279387,0.00008770917,0.014944371,0.0007076445,0.00038203,0.00021114222,0.00006131486,0.0009051977,0.00079742377],"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":[0.0009212919,0.0007288941,0.0267748,0.000017889097,0.027451029,0.00003931,0.00075632986,0.004209393,0.000014733743,0.043332424,0.8163762,0.07937767],"study_design_scores_gemma":[0.0009455226,0.0005950415,0.030707998,0.00007809984,0.007099993,0.00003129446,0.0013550827,0.0005494951,0.000021584045,0.04771271,0.91075015,0.00015302512],"about_ca_topic_score_codex":0.000020427802,"about_ca_topic_score_gemma":0.00004153886,"teacher_disagreement_score":0.45848498,"about_ca_system_score_codex":0.000013869345,"about_ca_system_score_gemma":0.00010619842,"threshold_uncertainty_score":0.99998057},"labels":[],"label_agreement":null},{"id":"W1991246128","doi":"10.1016/j.jclinepi.2013.11.011","title":"Blinded interpretation of study results can feasibly and effectively diminish interpretation bias","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":149,"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":"Interpretation (philosophy); Set (abstract data type); Randomized controlled trial; Statement (logic); Computer science; Medicine; Epistemology; Surgery","score_opus":0.8840886958881351,"score_gpt":0.6637032553514349,"score_spread":0.22038544053670017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991246128","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":[0.90224093,0.00012713652,0.09285329,0.0025921725,0.00066895905,0.0004162202,0.0000052435253,0.0000015913362,0.0010944642],"genre_scores_gemma":[0.9936207,0.0000352747,0.00518033,0.0007924097,0.00022016263,0.000003899677,0.0000010746958,0.0000068326385,0.00013931772],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.69676286,0.23608224,0.06341374,0.0010235254,0.0024221097,0.00029553135],"domain_scores_gemma":[0.395951,0.52030325,0.077334076,0.0020199153,0.0039226306,0.00046914676],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6424221,0.00022559718,0.010390928,0.00048799618,0.000047087375,0.000072529125,0.0009860083,0.0002147368,0.00010059059],"category_scores_gemma":[0.89311486,0.00010448475,0.0023023393,0.00048878643,0.00023345742,0.000191916,0.00011848437,0.00056487025,0.00004230663],"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":[0.0011735569,0.00029044683,0.738409,0.000031099044,0.0005098865,0.0000033203842,0.001112948,0.00047088863,0.000008362695,0.0007234318,0.004171144,0.25309595],"study_design_scores_gemma":[0.0018044597,0.0035790189,0.9155616,0.00014138647,0.00038155605,0.000028212304,0.00074118335,0.053812362,0.0000036001009,0.022732181,0.0011199442,0.00009445991],"about_ca_topic_score_codex":0.000019706298,"about_ca_topic_score_gemma":0.000086710024,"teacher_disagreement_score":0.30081186,"about_ca_system_score_codex":0.000017078484,"about_ca_system_score_gemma":0.00009495919,"threshold_uncertainty_score":0.71030307},"labels":[],"label_agreement":null},{"id":"W1991489967","doi":"10.1016/j.jclinepi.2011.10.013","title":"Studies of stroke rehabilitation therapies should report blinding and rationalize use of outcome measurement instruments","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","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":"McMaster University","funders":"","keywords":"Blinding; Rehabilitation; Stroke (engine); Medicine; Physical medicine and rehabilitation; Physical therapy; Clinical trial; Internal medicine","score_opus":0.8056811958358272,"score_gpt":0.6147142118846389,"score_spread":0.19096698395118827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991489967","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":[0.026302045,0.96913165,0.00023008358,0.0015178066,0.002169726,0.00060053816,0.00001724002,0.000004562574,0.000026370633],"genre_scores_gemma":[0.007903062,0.97132736,0.019871343,0.00018960398,0.0005603637,0.000011373903,0.000008574904,0.00002240549,0.00010589153],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.980589,0.004771503,0.013494145,0.0002792083,0.00064656796,0.0002196191],"domain_scores_gemma":[0.9057955,0.07558246,0.016103027,0.00039537557,0.0018743968,0.00024920772],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042387992,0.00029530362,0.009872799,0.00047777998,0.000029301535,0.0000029280372,0.00010540501,0.00062703603,0.00002985736],"category_scores_gemma":[0.2512839,0.00017284267,0.002386863,0.00013666946,0.0007377593,0.00016816202,0.00006289089,0.0009153092,0.0000011743111],"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":[0.00028793415,0.0003381303,0.64279443,0.012075453,0.0030641814,0.000006100441,0.0000949288,0.000001684409,0.0000023457094,0.0005021445,0.00029638733,0.3405363],"study_design_scores_gemma":[0.0022279778,0.004349001,0.20207174,0.017952284,0.00572852,0.000719659,0.00047765064,0.0000045062325,0.000001100307,0.00076573377,0.76546794,0.00023391246],"about_ca_topic_score_codex":0.000006539003,"about_ca_topic_score_gemma":0.0000029091912,"teacher_disagreement_score":0.7651715,"about_ca_system_score_codex":0.0001945835,"about_ca_system_score_gemma":0.0004461716,"threshold_uncertainty_score":0.98606306},"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":"W1992019735","doi":"10.1016/j.jclinepi.2005.01.004","title":"An analysis of general medical and specialist journals that endorse CONSORT found that reporting was not enforced consistently","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Institute for Work & Health; University of Toronto; McMaster University","funders":"","keywords":"Consolidated Standards of Reporting Trials; Medicine; Confidence interval; Odds ratio; Randomization; Family medicine; Randomized controlled trial; Publication bias; Meta-analysis; Specialty; Internal medicine","score_opus":0.9294382177594025,"score_gpt":0.6905933087837071,"score_spread":0.23884490897569544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992019735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96482664,0.0016442793,0.020462532,0.01014123,0.0009485446,0.00019385175,0.000013946089,0.000002718668,0.0017662777],"genre_scores_gemma":[0.9689462,0.0013423978,0.020923864,0.0062864157,0.0016529873,0.0000019478207,0.000004389633,0.000012140754,0.00082966365],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7530807,0.09928821,0.13667898,0.0015230749,0.00862688,0.0008021543],"domain_scores_gemma":[0.4420187,0.27269906,0.2736681,0.0043992717,0.004526194,0.0026886666],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.71263176,0.00040076266,0.024886325,0.0011623413,0.00014769698,0.00020957389,0.0019521306,0.00060553674,0.015158008],"category_scores_gemma":[0.7882567,0.00018996221,0.009935977,0.0009926193,0.0009196721,0.0005066209,0.00018243688,0.0011739708,0.00004864116],"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":[0.00012095001,0.00013813634,0.9501906,0.0000144709675,0.0036237969,0.00014372225,0.00009481892,0.0011878863,0.00003767146,0.0024515497,0.007324303,0.034672093],"study_design_scores_gemma":[0.0009623847,0.00033530846,0.8916458,0.000093114526,0.0048396587,0.0012372553,0.00050199253,0.06265829,0.00002380642,0.00387842,0.033592522,0.00023146158],"about_ca_topic_score_codex":0.000051723346,"about_ca_topic_score_gemma":0.00025571033,"teacher_disagreement_score":0.311062,"about_ca_system_score_codex":0.000041465024,"about_ca_system_score_gemma":0.0004642741,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W1992205884","doi":"10.1016/j.jclinepi.2013.11.013","title":"Developing Core Outcome Measurement Sets for Clinical Trials: OMERACT Filter 2.0","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":784,"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","funders":"","keywords":"Outcome (game theory); Medicine; Health care; Set (abstract data type); Core (optical fiber); Standardization; Voting; Process (computing); Computer science; Political science; Mathematics","score_opus":0.9713478092818285,"score_gpt":0.7772782648495306,"score_spread":0.19406954443229796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992205884","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":[0.053577255,0.0006658373,0.6543523,0.27149433,0.014107371,0.0017371573,0.000013368499,0.00010618511,0.003946218],"genre_scores_gemma":[0.6643741,0.0036939483,0.29313466,0.02530454,0.013031351,0.00005907871,0.0000034351995,0.00005524453,0.000343625],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.90199316,0.0740212,0.020822443,0.0006034874,0.0014030046,0.0011567172],"domain_scores_gemma":[0.41341308,0.5684077,0.0127637675,0.000673157,0.003488872,0.001253431],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7080917,0.00020172766,0.0047224816,0.00019092005,0.0002668872,0.000030352032,0.0011782399,0.00095836463,0.00016134212],"category_scores_gemma":[0.9054617,0.00014184538,0.002291661,0.00019304772,0.0009179014,0.00017707839,0.0001335138,0.0018350573,0.00004713652],"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":[0.0009265302,0.00022408804,0.48134166,0.00003972572,0.00027367703,0.0000102692475,0.000089902394,0.000010748854,0.0000037079826,0.041352544,0.14189604,0.3338311],"study_design_scores_gemma":[0.0017603835,0.0010467974,0.11286841,0.00013346579,0.00008604949,0.000009691476,0.00013969686,0.00051698775,0.0000033293184,0.14049658,0.74274486,0.00019376626],"about_ca_topic_score_codex":0.000085661886,"about_ca_topic_score_gemma":0.00013584764,"teacher_disagreement_score":0.61079687,"about_ca_system_score_codex":0.00022095825,"about_ca_system_score_gemma":0.0014329224,"threshold_uncertainty_score":0.7972513},"labels":[],"label_agreement":null},{"id":"W1992698943","doi":"10.1016/j.jclinepi.2008.11.005","title":"Estimating risk difference from relative association measures in meta-analysis can infrequently pose interpretational challenges","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Counterintuitive; Relative risk; Pooling; Confidence interval; Meta-analysis; Statistics; Point estimation; Medicine; Odds ratio; Frequency; Interval estimation; Baseline (sea); Absolute risk reduction; Demography; Mathematics; Internal medicine; Computer science; Physics; Biology","score_opus":0.917954279776513,"score_gpt":0.6479797634782578,"score_spread":0.2699745162982552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992698943","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":[0.48967558,0.02019349,0.41272897,0.073246814,0.0014346609,0.00045603554,0.000103169616,0.000006730072,0.0021545691],"genre_scores_gemma":[0.92225605,0.00054485153,0.07439191,0.0021389967,0.00034318463,0.0000046313417,0.000005391102,0.00000499123,0.00030999785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7536554,0.18952607,0.051526576,0.0010396593,0.0038587172,0.00039359852],"domain_scores_gemma":[0.38999847,0.50164,0.10230931,0.001975021,0.0036149265,0.00046225506],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.5674513,0.0003387388,0.02163966,0.00081530126,0.000075186246,0.00010770721,0.001565156,0.00043321986,0.0019441008],"category_scores_gemma":[0.87304825,0.00015504651,0.01433538,0.0010798264,0.00008540086,0.00031746647,0.00006299705,0.0014759373,0.00010714271],"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":[0.000050848404,0.00016847308,0.8686962,0.0000028077195,0.06393697,0.00001161034,0.0007516282,0.01486125,0.0000020969615,0.0032404114,0.0015245164,0.046753146],"study_design_scores_gemma":[0.00019948123,0.00014455867,0.6123098,0.000010296014,0.03321611,0.000002244696,0.00008194051,0.03430172,2.442824e-7,0.31939647,0.0002493464,0.00008780614],"about_ca_topic_score_codex":0.000114635564,"about_ca_topic_score_gemma":0.0007437232,"teacher_disagreement_score":0.43258047,"about_ca_system_score_codex":0.00012663468,"about_ca_system_score_gemma":0.0001750155,"threshold_uncertainty_score":0.99896824},"labels":[],"label_agreement":null},{"id":"W1993102131","doi":"10.1016/s0895-4356(99)00172-9","title":"Health care seeking behavior following a health survey","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","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":"University of Manitoba","funders":"","keywords":"Medicine; Population; Incidence (geometry); Health care; Family medicine; Diabetes mellitus; Epidemiology; Public health; Survey methodology; Gerontology; Environmental health; Demography; Pathology","score_opus":0.3223106709787246,"score_gpt":0.5814488959908342,"score_spread":0.25913822501210954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993102131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92809564,0.014182678,0.021402836,0.032780398,0.0024714142,0.0006628299,0.000010461079,0.000037661448,0.00035609986],"genre_scores_gemma":[0.9614122,0.0046187886,0.005861139,0.026649728,0.001143924,0.0000049911173,0.0000458843,0.000024204246,0.00023914219],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9561975,0.036304932,0.0062698633,0.000300063,0.0003500455,0.000577592],"domain_scores_gemma":[0.9928049,0.0036720876,0.0020006949,0.0003182226,0.00021816388,0.0009859607],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13198215,0.0001436169,0.0036544125,0.000107585045,0.00012793634,0.0000038597254,0.00012030122,0.00028926294,0.00029575266],"category_scores_gemma":[0.013851232,0.00011179275,0.0021281014,0.00016600585,0.00006505779,0.00007179708,0.000017381119,0.0012966024,0.000052016534],"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":[0.0000965109,0.00018319517,0.3506673,0.000092233146,0.00014814135,0.000048930964,0.00012103281,0.00001019616,3.35139e-7,0.000011365425,0.0029425116,0.6456782],"study_design_scores_gemma":[0.0026819655,0.002460811,0.9704818,0.00038276118,0.00008240654,0.0005272958,0.0000640439,0.000029765159,1.9256083e-7,0.00005873697,0.023160867,0.000069324604],"about_ca_topic_score_codex":0.00038276214,"about_ca_topic_score_gemma":0.00014009725,"teacher_disagreement_score":0.6456089,"about_ca_system_score_codex":0.00019467255,"about_ca_system_score_gemma":0.0016775521,"threshold_uncertainty_score":0.9944555},"labels":[],"label_agreement":null},{"id":"W1993349052","doi":"10.1016/j.jclinepi.2013.03.003","title":"Testing the Newcastle Ottawa Scale showed low reliability between individual reviewers","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":446,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa; University of Alberta","funders":"University of Alberta","keywords":"Confidence interval; Reliability (semiconductor); Medicine; Meta-analysis; Odds ratio; Kappa; Cohort; Scale (ratio); Statistics; Cohort study; Demography; Internal medicine; Mathematics; Geography; Cartography","score_opus":0.9347665164969218,"score_gpt":0.6547938755714102,"score_spread":0.27997264092551155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993349052","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9254113,0.0018343956,0.014630707,0.05067459,0.0019335288,0.0008618233,0.000010266448,0.000004983956,0.0046383957],"genre_scores_gemma":[0.90742314,0.00015722448,0.07731826,0.009996674,0.0030090478,0.00001782482,0.0000024036467,0.000018903016,0.002056506],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.66993225,0.2289099,0.09433719,0.0012740616,0.0047783996,0.00076820934],"domain_scores_gemma":[0.030419057,0.87247944,0.0825381,0.006027647,0.0074379346,0.0010978093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.79096603,0.0003186971,0.014408288,0.00017359815,0.00017854953,0.00021845057,0.0041065677,0.00036566792,0.0071353107],"category_scores_gemma":[0.93860334,0.000109689376,0.006148599,0.0010500007,0.00056962663,0.00036203876,0.0003105048,0.0015445896,0.0034218838],"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":[0.0000027525673,0.000032433367,0.6452075,0.00001557258,0.000121420024,0.0000011409109,0.000023728704,0.000074116986,0.0000014958516,0.00006423008,0.26183927,0.09261633],"study_design_scores_gemma":[0.00020513505,0.00020978396,0.8413873,0.00008577811,0.00031887984,0.00003253178,0.00010387157,0.0010956957,4.777834e-7,0.039783992,0.11667817,0.000098413],"about_ca_topic_score_codex":0.00004578269,"about_ca_topic_score_gemma":0.000009388273,"teacher_disagreement_score":0.6435696,"about_ca_system_score_codex":0.000024669402,"about_ca_system_score_gemma":0.00024071393,"threshold_uncertainty_score":0.9973541},"labels":[],"label_agreement":null},{"id":"W1993370148","doi":"10.1016/j.jclinepi.2011.01.001","title":"Administrative database research infrequently used validated diagnostic or procedural codes","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":176,"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; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Diagnosis code; Medicine; Confidence interval; Medical diagnosis; Code (set theory); MEDLINE; Current Procedural Terminology; Statistics; Data mining; Computer science; Internal medicine; Surgery; Mathematics; Pathology; Population; Environmental health; Programming language; Set (abstract data type)","score_opus":0.970072185892032,"score_gpt":0.7783446361477604,"score_spread":0.19172754974427164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993370148","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":[0.00014153338,0.9816145,0.0012896728,0.0043904874,0.006206604,0.0028998516,0.00027340945,0.00004854648,0.0031353969],"genre_scores_gemma":[0.0000628055,0.98679316,0.0033406895,0.00414266,0.004174953,0.0001756542,0.00025034088,0.000049310387,0.001010419],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8794377,0.0909698,0.026840365,0.00051955617,0.0007584637,0.0014741392],"domain_scores_gemma":[0.35860345,0.61051506,0.025191156,0.00097537355,0.0026084762,0.0021064817],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.23618364,0.0005096289,0.012199395,0.00062879524,0.00066925894,0.0000096586045,0.0013162681,0.002921479,0.0029699004],"category_scores_gemma":[0.79629326,0.0002682489,0.0012429806,0.00063953956,0.0008805885,0.0003008501,0.0003335288,0.017579895,0.0015431728],"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":[0.0010822224,0.0004429865,0.0053766165,0.065775216,0.0005525716,0.00023648528,0.00082425715,3.7418778e-7,1.7130658e-8,0.010779044,0.44490585,0.47002438],"study_design_scores_gemma":[0.0010366556,0.0022039032,0.0005293027,0.04692689,0.00040099025,0.00012634494,0.00024384451,0.000016464694,2.5348239e-8,0.0020827807,0.9462131,0.00021967947],"about_ca_topic_score_codex":0.00009309265,"about_ca_topic_score_gemma":0.00009716341,"teacher_disagreement_score":0.5601096,"about_ca_system_score_codex":0.00031939617,"about_ca_system_score_gemma":0.02020565,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W1993768037","doi":"10.1016/j.jclinepi.2013.10.023","title":"The refinement of topics for systematic reviews: lessons and recommendations from the Effective Health Care Program","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital","funders":"","keywords":"Stakeholder; Scope (computer science); Systematic review; Transparency (behavior); Health care; Nomination; Computer science; Agency (philosophy); Management science; Relevance (law); MEDLINE; Public relations; Political science; Sociology; Engineering","score_opus":0.9007626647879244,"score_gpt":0.7214252730181473,"score_spread":0.17933739176977714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993768037","genre_codex":"commentary","genre_gemma":"empirical","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":[0.011621937,0.076619856,0.21733446,0.67892665,0.0030558037,0.011955366,0.00005674744,0.0000037927205,0.00042539716],"genre_scores_gemma":[0.470854,0.048383683,0.4170702,0.0520089,0.0069505502,0.0025609445,0.000045604404,0.000060530816,0.0020655761],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.66699386,0.26761955,0.063043326,0.0006529341,0.0013179653,0.00037236194],"domain_scores_gemma":[0.2858486,0.6560229,0.05413355,0.0020326898,0.001760114,0.00020216304],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6201228,0.0001533892,0.009895761,0.000046114867,0.0002360727,0.00006761793,0.0011466758,0.000101902595,0.0000546668],"category_scores_gemma":[0.80135995,0.000043059972,0.0028401057,0.00019494857,0.00018163712,0.00004561093,0.00008667241,0.00035015173,0.000014734623],"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":[0.000024450324,0.00005879284,0.014879239,0.0012891479,0.0004280611,7.562454e-8,0.0004071164,0.000009822089,1.5460236e-7,0.016906697,0.15153657,0.81445986],"study_design_scores_gemma":[0.00039665724,0.0010949004,0.030703226,0.0019752618,0.00044678303,0.0000062358927,0.0013317474,0.0017121836,2.1702913e-7,0.0361419,0.92613184,0.00005904733],"about_ca_topic_score_codex":0.000016486434,"about_ca_topic_score_gemma":0.0001654077,"teacher_disagreement_score":0.81440085,"about_ca_system_score_codex":0.000021287413,"about_ca_system_score_gemma":0.00008913226,"threshold_uncertainty_score":0.6764544},"labels":[],"label_agreement":null},{"id":"W1993809841","doi":"10.1016/j.jclinepi.2004.11.026","title":"The problem of imperfect reference standards","year":2005,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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":"Gold standard (test); Imperfect; Class (philosophy); Latent class model; Standard error; Statistics; Scopus; Computer science; Econometrics; Mathematics; MEDLINE; Artificial intelligence; Philosophy; Linguistics; Political science","score_opus":0.6177846126145073,"score_gpt":0.5901486659943236,"score_spread":0.02763594662018376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993809841","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":[0.0032895997,0.002716842,0.0022385542,0.98351675,0.0026018785,0.00028451212,0.00006105661,0.0000054145216,0.0052853613],"genre_scores_gemma":[0.011942791,0.017057812,0.019414566,0.9202157,0.026149422,0.000013282913,0.000007650794,0.00004651521,0.0051522166],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9091976,0.047289524,0.033962145,0.0010777568,0.0073482227,0.0011247075],"domain_scores_gemma":[0.63948995,0.32944342,0.023696532,0.0015482698,0.0055719437,0.0002498728],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.40660533,0.00033752384,0.0050662933,0.00019653616,0.00016258624,0.00005470199,0.0036038393,0.0016679718,0.00065899827],"category_scores_gemma":[0.36856198,0.00014474851,0.002248474,0.00028533518,0.0013410837,0.00014644895,0.00026912117,0.007253008,0.000067184556],"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":[0.00022274084,0.000056168064,0.012585777,0.000022147844,0.00015377361,0.000019166235,0.000012876832,0.00012189999,0.0000019180218,0.0003970875,0.86223435,0.1241721],"study_design_scores_gemma":[0.00043075587,0.0013508808,0.0072246976,0.00016355861,0.0000755478,0.000033244673,0.000021892807,0.00003554542,0.0000029184127,0.11139904,0.87913924,0.00012265598],"about_ca_topic_score_codex":0.000014625609,"about_ca_topic_score_gemma":0.00002544061,"teacher_disagreement_score":0.2821539,"about_ca_system_score_codex":0.00013162526,"about_ca_system_score_gemma":0.0015612944,"threshold_uncertainty_score":0.99962807},"labels":[],"label_agreement":null},{"id":"W1993828216","doi":"10.1016/s0895-4356(00)00313-9","title":"Sources of heterogeneity in the meta-analysis of observational studies The example of SIDS and sleeping position","year":2001,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Neuroscience of respiration and sleep","field":"Neuroscience","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":"McMaster University","funders":"","keywords":"Observational study; Meta-analysis; Sudden infant death syndrome; Odds ratio; Medicine; Association (psychology); Study heterogeneity; Position (finance); Odds; Demography; Logistic regression; Pediatrics; Psychology; Pathology; Internal medicine","score_opus":0.890112464590886,"score_gpt":0.6123017595266478,"score_spread":0.2778107050642382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993828216","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":[0.060610082,0.93581426,0.00044699953,0.0025265987,0.00025351695,0.00028509414,0.00003225601,0.0000017312235,0.000029478975],"genre_scores_gemma":[0.020864395,0.976064,0.0002706022,0.0026916435,0.00008715702,0.000006874946,0.0000012626863,0.000006087059,0.000007972986],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9739202,0.017634463,0.0074064815,0.00035633627,0.0004889296,0.00019356755],"domain_scores_gemma":[0.8761354,0.112379014,0.010785853,0.00039067405,0.00025121798,0.000057829882],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03428085,0.00020541355,0.007993157,0.00038427275,0.000071452225,0.000006737261,0.0008033111,0.00020585202,0.000016855563],"category_scores_gemma":[0.08102633,0.00008932391,0.00362698,0.0011804325,0.0013277347,0.00011314955,0.000116984775,0.00068894966,2.7127476e-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":[0.0005776006,0.0030240512,0.12608278,0.008168846,0.10339216,0.00016212634,0.0015547074,0.013700616,0.00045091292,0.07556733,0.00080635404,0.66651255],"study_design_scores_gemma":[0.0016864775,0.005221023,0.10461753,0.001868493,0.413241,0.00089481584,0.00037211497,0.002690291,0.0002703455,0.014503076,0.4537342,0.0009006307],"about_ca_topic_score_codex":0.00002399897,"about_ca_topic_score_gemma":0.00003328131,"teacher_disagreement_score":0.66561186,"about_ca_system_score_codex":0.000011389576,"about_ca_system_score_gemma":0.00012805112,"threshold_uncertainty_score":0.9944111},"labels":[],"label_agreement":null},{"id":"W1994034662","doi":"10.1016/j.jclinepi.2005.09.002","title":"Systematic review of qualitative studies exploring parental beliefs and attitudes toward childhood vaccination identifies common barriers to vaccination","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":378,"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 General Hospital; University Health Network; University of Toronto; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Distrust; Qualitative research; Vaccination; Harm; Medicine; Focus group; Vaccination schedule; Trustworthiness; Systematic review; Family medicine; MEDLINE; Psychology; Social psychology; Psychotherapist; Political science; Immunology","score_opus":0.5609113100203705,"score_gpt":0.6220821144349724,"score_spread":0.061170804414601876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994034662","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":[0.00039844145,0.9936866,0.00007240162,0.0033425083,0.0011340986,0.0012627117,0.000012723484,0.00001186831,0.000078603785],"genre_scores_gemma":[0.0019341977,0.99544835,0.0004250952,0.00087637955,0.001156329,0.00008110099,0.0000063582597,0.000021386168,0.00005083033],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.96482784,0.023293437,0.010640215,0.00038601767,0.0004954037,0.00035706663],"domain_scores_gemma":[0.94197917,0.04566394,0.010712488,0.0002691011,0.0009105812,0.00046470802],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06311983,0.00036197447,0.011800964,0.00033683405,0.0002277775,0.000020576144,0.0005746696,0.00038505284,0.00009297045],"category_scores_gemma":[0.2828631,0.00025522447,0.0015245178,0.00036976513,0.00005622696,0.000526786,0.00016145466,0.00083283434,0.000011826161],"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":[0.00001883455,0.00013922714,0.0015625793,0.7590296,0.0019344043,0.000010610915,0.02050636,0.00000176007,7.4036337e-9,0.0036846688,0.0025480187,0.21056393],"study_design_scores_gemma":[0.00049695914,0.000736152,0.007838243,0.9400681,0.00447213,0.000039042414,0.012695547,4.7450413e-7,8.738051e-8,0.0035419376,0.029662652,0.0004486269],"about_ca_topic_score_codex":0.000032341955,"about_ca_topic_score_gemma":0.00018404116,"teacher_disagreement_score":0.21974328,"about_ca_system_score_codex":0.00024504718,"about_ca_system_score_gemma":0.0005926133,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W1994065729","doi":"10.1016/j.jclinepi.2005.05.004","title":"A checklist to evaluate a report of a nonpharmacological trial (CLEAR NPT) was developed using consensus","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":310,"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; University of Ottawa; Children's Hospital of Eastern Ontario","funders":"","keywords":"Checklist; Blinding; Delphi method; Medicine; Systematic review; Randomized controlled trial; Likert scale; MEDLINE; Research design; Family medicine; Psychology; Computer science; Surgery; Statistics","score_opus":0.9610962505196035,"score_gpt":0.7367829161171107,"score_spread":0.2243133344024928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994065729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9581827,0.00038895963,0.01806958,0.019139023,0.0018716311,0.0006804488,0.00000428435,0.0000024595556,0.0016609174],"genre_scores_gemma":[0.73673683,0.000064892134,0.2530951,0.0059583597,0.002168584,0.0000063287953,6.813677e-7,0.000013574346,0.0019556314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.67863834,0.17203704,0.1414967,0.0015806672,0.0054264287,0.0008208386],"domain_scores_gemma":[0.51202595,0.34402063,0.12886983,0.0037912743,0.009506384,0.0017859265],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73939466,0.0003209221,0.018111771,0.0004299881,0.00008196017,0.000053949985,0.0017916718,0.00042231407,0.0060761217],"category_scores_gemma":[0.8830053,0.00014327673,0.0065441458,0.0009365378,0.0003524906,0.00009763585,0.00025929307,0.0009000362,0.0005797345],"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":[0.049607452,0.0020470368,0.15954846,0.00009001121,0.004064955,0.0014993281,0.00040266928,0.01912238,0.0007277354,0.0022871299,0.58831424,0.1722886],"study_design_scores_gemma":[0.0259119,0.0039335,0.059302356,0.00017966064,0.002095898,0.0034297418,0.00022994261,0.060400665,0.00003692593,0.012777528,0.8311987,0.0005031859],"about_ca_topic_score_codex":0.000011021639,"about_ca_topic_score_gemma":0.000013550942,"teacher_disagreement_score":0.24288446,"about_ca_system_score_codex":0.00006558524,"about_ca_system_score_gemma":0.0010397754,"threshold_uncertainty_score":0.9964654},"labels":[],"label_agreement":null},{"id":"W1994325409","doi":"10.1016/j.jclinepi.2006.08.006","title":"Three methods for minimally important difference: no relationship was found with the net proportion of patients improving","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","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":"St. Michael's Hospital; Lunenfeld-Tanenbaum Research Institute; Hôpital du Saint-Sacrement; Institute for Work & Health; Mount Sinai Hospital","funders":"","keywords":"Medicine; Psychosocial; Randomized controlled trial; Mood; Quality of life (healthcare); Physical therapy; Visual analogue scale; Breast cancer; Significant difference; Clinical psychology; Cancer; Internal medicine; Psychiatry; Nursing","score_opus":0.17030311927832212,"score_gpt":0.4835469342620061,"score_spread":0.31324381498368403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994325409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.859477,0.00047385873,0.13484731,0.0038195278,0.0008155508,0.00040299495,0.0000071434574,0.0000056673657,0.00015096781],"genre_scores_gemma":[0.94164264,0.000042292268,0.05620119,0.0008376013,0.0010827824,0.00001475931,0.000017498372,0.000016052936,0.00014518344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99485457,0.0009581297,0.003554251,0.00019320093,0.0002026823,0.00023715144],"domain_scores_gemma":[0.97419745,0.019711591,0.004604973,0.00025755703,0.0011019282,0.00012648101],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016036535,0.00013386048,0.0014472967,0.000060214952,0.000057701876,0.000003914875,0.00014338405,0.0002508433,0.00002362505],"category_scores_gemma":[0.030067313,0.000065927394,0.0005059888,0.00010204708,0.0002799564,0.00005058377,0.000024450646,0.0006263942,5.5902933e-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":[0.0028921051,0.00017691268,0.9728306,0.000079910154,0.00008273265,0.000002510131,0.00002475054,0.000009260156,0.00004899436,0.0014219264,0.001224767,0.021205535],"study_design_scores_gemma":[0.002068349,0.0044071935,0.9756261,0.00008393559,0.00033056393,0.000020728288,0.000032047337,0.0008243166,0.000013673602,0.013146562,0.0033757633,0.00007073794],"about_ca_topic_score_codex":0.00016303173,"about_ca_topic_score_gemma":0.0005789366,"teacher_disagreement_score":0.082165666,"about_ca_system_score_codex":0.00003920626,"about_ca_system_score_gemma":0.00037127058,"threshold_uncertainty_score":0.97810286},"labels":[],"label_agreement":null},{"id":"W1994466426","doi":"10.1016/j.jclinepi.2012.07.005","title":"Testing the Risk of Bias tool showed low reliability between individual reviewers and across consensus assessments of reviewer pairs","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":171,"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; Ottawa Hospital; McMaster University; University of Alberta","funders":"Agency for Healthcare Research and Quality","keywords":"Inter-rater reliability; Reliability (semiconductor); Publication bias; Meta-analysis; Systematic review; Randomized controlled trial; Medicine; Psychology; MEDLINE; Clinical psychology; Surgery; Internal medicine; Biology","score_opus":0.9364054554289195,"score_gpt":0.6789392139059987,"score_spread":0.25746624152292086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994466426","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98412484,0.010021725,0.0024191646,0.0017037386,0.0009608764,0.0005065898,0.000059694412,0.0000011866236,0.00020218026],"genre_scores_gemma":[0.9597334,0.0022549666,0.036604267,0.000729894,0.00057698146,0.0000038363733,0.0000011974024,0.000008571144,0.00008687121],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5463022,0.34338883,0.10370238,0.0009887216,0.0047735567,0.00084427715],"domain_scores_gemma":[0.039750434,0.8289953,0.120269224,0.0036331946,0.006798995,0.0005528507],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8714682,0.00029459415,0.016352894,0.00010741717,0.00011242372,0.000039401013,0.001638131,0.00031610948,0.00042994117],"category_scores_gemma":[0.9688113,0.00010756671,0.0044323877,0.0007757334,0.0009972559,0.00017510205,0.00034160962,0.0011019838,0.000039886956],"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":[0.000020174566,0.00007891562,0.8887021,0.00017127144,0.0004905308,5.930596e-7,0.00008022108,0.000028337037,0.0000014933815,0.000054659835,0.019474298,0.0908974],"study_design_scores_gemma":[0.0003313044,0.00030082726,0.971778,0.00038056116,0.0010372797,0.000020754394,0.00022816747,0.00023340345,0.000001492128,0.005116096,0.020480204,0.000091957154],"about_ca_topic_score_codex":0.000018941122,"about_ca_topic_score_gemma":0.0000027668145,"teacher_disagreement_score":0.5065518,"about_ca_system_score_codex":0.000015579299,"about_ca_system_score_gemma":0.00018237854,"threshold_uncertainty_score":0.99825037},"labels":[],"label_agreement":null},{"id":"W1994824286","doi":"10.1016/j.jclinepi.2012.04.012","title":"GRADE guidelines: 10. Considering resource use and rating the quality of economic evidence","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":284,"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":"Medical Research Council","keywords":"Grading (engineering); Resource (disambiguation); Quality (philosophy); Management science; Evidence-based practice; Actuarial science; Computer science; Risk analysis (engineering); Medicine; Business; Alternative medicine; Economics","score_opus":0.9764380239027354,"score_gpt":0.7198236227551228,"score_spread":0.2566144011476126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994824286","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":[0.0012367502,0.9748431,0.001133799,0.02041412,0.0015771209,0.00057872536,0.000093800336,0.000009239485,0.00011337388],"genre_scores_gemma":[0.00029642732,0.9789306,0.01062961,0.006714958,0.0031777332,0.000019528148,0.0000069743546,0.000050391816,0.0001738015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8945243,0.026324647,0.07748096,0.0008054992,0.00014140423,0.0007232009],"domain_scores_gemma":[0.44801018,0.45130932,0.09854005,0.0012392974,0.00032639786,0.0005747341],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45077968,0.00046262424,0.016866583,0.00033644552,0.00014496678,0.000044789183,0.000862929,0.0009693104,0.0002335714],"category_scores_gemma":[0.6182592,0.00035742376,0.0020737643,0.000115545285,0.0006866486,0.0006857868,0.00026653032,0.0016282374,0.0002403492],"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":[0.00019707737,0.00030155256,0.20252539,0.043078184,0.0032398072,0.0000075175067,0.0006904604,0.0006118415,1.02738255e-7,0.18115549,0.16384442,0.40434816],"study_design_scores_gemma":[0.00037642478,0.00014650066,0.004113732,0.00712061,0.00022488537,0.00011803157,0.000114888484,0.00019423045,2.0967944e-8,0.006188975,0.98108846,0.00031325588],"about_ca_topic_score_codex":0.00035769344,"about_ca_topic_score_gemma":0.000059639326,"teacher_disagreement_score":0.81724405,"about_ca_system_score_codex":0.0003136335,"about_ca_system_score_gemma":0.0008676869,"threshold_uncertainty_score":0.99988776},"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":"W1995355289","doi":"10.1016/j.jclinepi.2011.01.002","title":"Systematic mixed-methods reviews are not ready to be assessed with the available tools","year":2011,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Systematic review; Medicine; MEDLINE; Data science; Computer science; Political science","score_opus":0.9489080651941432,"score_gpt":0.679468114308772,"score_spread":0.2694399508853712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995355289","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019961374,0.009557186,0.14114697,0.8363852,0.004782488,0.0031512284,0.000039343216,0.000005890397,0.0047320714],"genre_scores_gemma":[0.0000437543,0.0014159752,0.13615544,0.8170024,0.004986427,0.00014155405,0.000009092455,0.000057651898,0.04018769],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.186763,0.6664771,0.13688776,0.002447933,0.0062313164,0.001192886],"domain_scores_gemma":[0.09165546,0.6784057,0.2117411,0.011303409,0.0061408193,0.0007534814],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8895199,0.0011322041,0.06854446,0.0007008478,0.00020357463,0.0005366015,0.009830203,0.002012103,0.009553503],"category_scores_gemma":[0.9212839,0.00034157053,0.014180495,0.0013750474,0.0004380815,0.00034389918,0.00043684986,0.0069308947,0.010622322],"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":[0.00004664855,0.000056514033,0.0016264908,0.003164391,0.0014077475,0.0001331808,0.0000515275,0.000009583602,6.8495797e-7,0.00019511879,0.9899959,0.0033121966],"study_design_scores_gemma":[0.0002330276,0.0006225891,0.0019748274,0.005029793,0.003148025,0.00041322582,0.00013821879,0.000099458004,5.992209e-7,0.0016723669,0.986297,0.00037087168],"about_ca_topic_score_codex":0.000015010261,"about_ca_topic_score_gemma":0.000033061737,"teacher_disagreement_score":0.09510755,"about_ca_system_score_codex":0.00007442662,"about_ca_system_score_gemma":0.00053826225,"threshold_uncertainty_score":0.9999036},"labels":[],"label_agreement":null},{"id":"W1995520341","doi":"10.1016/j.jclinepi.2007.08.007","title":"Searching PsycINFO just got easier","year":2008,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","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 Ottawa; Institute of Population and Public Health","funders":"","keywords":"PsycINFO; Scopus; MEDLINE; Bibliographic database; Audience measurement; Epidemiology; Relation (database); Scientific literature; Information retrieval; Medical literature; Medicine; Library science; Computer science; Database; Political science; Pathology","score_opus":0.8463989785633426,"score_gpt":0.7283117125583015,"score_spread":0.11808726600504105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995520341","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":[0.00992616,0.0008265227,0.0007031461,0.9576244,0.020804947,0.0004835871,0.000013034342,0.000019049223,0.00959918],"genre_scores_gemma":[0.00067026966,0.009557656,0.0048744874,0.88630325,0.08767983,0.000020792715,0.000031823187,0.0000394943,0.0108223865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94045156,0.043594666,0.012129274,0.0005528349,0.0009892695,0.0022824095],"domain_scores_gemma":[0.80533105,0.1823121,0.009013908,0.0006670936,0.0013027462,0.0013731014],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.10130377,0.00031948058,0.00418769,0.00054548937,0.0008304178,0.0000068609666,0.0013357752,0.003632248,0.0016743647],"category_scores_gemma":[0.28986877,0.00021337594,0.0010792275,0.00036352983,0.00087214384,0.00022640722,0.00020257346,0.03350733,0.0015969219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011902816,0.00004766055,0.07820824,0.00037766708,0.00006029725,0.00019304332,0.00031816305,0.000008162581,2.0706398e-7,0.000088218934,0.91347224,0.007107107],"study_design_scores_gemma":[0.00063303806,0.00066652405,0.07562212,0.00054082705,0.000023637187,0.00012341197,0.00018398455,0.000108664506,3.350201e-8,0.0033843738,0.9185597,0.00015368406],"about_ca_topic_score_codex":0.00045480407,"about_ca_topic_score_gemma":0.000034182398,"teacher_disagreement_score":0.188565,"about_ca_system_score_codex":0.0003297093,"about_ca_system_score_gemma":0.01172609,"threshold_uncertainty_score":0.99923825},"labels":[],"label_agreement":null},{"id":"W1995649061","doi":"10.1016/j.jclinepi.2003.11.008","title":"Female specialists were more likely to respond to a postal questionnaire about drug treatments for Alzheimer disease","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Respondent; Medicine; Logistic regression; Specialty; Demography; Family medicine; Non-response bias; Disease; Gerontology; Internal medicine","score_opus":0.5707315724253721,"score_gpt":0.6303974941762068,"score_spread":0.05966592175083474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995649061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89444053,0.0010529831,0.005803018,0.09422345,0.0037571169,0.0005383629,0.00004351116,0.000020512223,0.00012049327],"genre_scores_gemma":[0.8991632,0.00045303392,0.06357686,0.028813675,0.006080687,0.000046786903,0.000008273891,0.000036624424,0.0018208529],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9593871,0.03654503,0.0026813082,0.00045026993,0.0002874154,0.0006488663],"domain_scores_gemma":[0.9116666,0.08473471,0.0011651724,0.00029614064,0.00048198272,0.0016554224],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12736666,0.00020485754,0.0015822608,0.00021059572,0.00035319812,0.000015838012,0.00050313363,0.00037319888,0.00009311786],"category_scores_gemma":[0.4794338,0.00016271223,0.0008357139,0.0002534084,0.0005370735,0.0001663269,0.00006799063,0.00046634595,0.00008238497],"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":[0.15798528,0.0013004894,0.7183006,0.000014731911,0.00085981464,0.00051655265,0.011530562,0.0010202333,0.000023073011,0.023877366,0.022554047,0.062017236],"study_design_scores_gemma":[0.0016285446,0.0009763074,0.9266418,0.0001297075,0.00021776406,0.000012071944,0.00045249044,0.0000014768044,0.000012043854,0.01569954,0.054056242,0.00017200281],"about_ca_topic_score_codex":0.0004058409,"about_ca_topic_score_gemma":0.0010278214,"teacher_disagreement_score":0.35206714,"about_ca_system_score_codex":0.00013467627,"about_ca_system_score_gemma":0.0014908854,"threshold_uncertainty_score":0.8985597},"labels":[],"label_agreement":null},{"id":"W1995835325","doi":"10.1016/s0895-4356(03)00179-3","title":"Rasch analysis of the western ontariomcmaster (WOMAC) osteoarthritis index: results from community and arthroplasty samples","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Health Sciences Centre; Arthritis Research Centre of Canada; Hospital for Sick Children; University of British Columbia; St. Michael's Hospital; Institute for Work & Health; SickKids Foundation; University Health Network; University of Toronto; Sunnybrook Health Science Centre; Toronto Rehabilitation Institute","funders":"","keywords":"Rasch model; WOMAC; Differential item functioning; Physical therapy; Osteoarthritis; Medicine; Psychometrics; Physical medicine and rehabilitation; Statistics; Item response theory; Clinical psychology; Mathematics","score_opus":0.7731182734792174,"score_gpt":0.5772165807063969,"score_spread":0.19590169277282043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995835325","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":[0.97960085,0.00065405725,0.015438746,0.0019436659,0.00160082,0.00006621442,0.000063461026,0.000003810893,0.0006283549],"genre_scores_gemma":[0.97912407,0.00026890048,0.018877678,0.0014919185,0.00013117967,5.4723347e-7,0.0000015785624,0.000005272017,0.00009886811],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94436496,0.04577375,0.008522321,0.00037434942,0.0006503774,0.00031421892],"domain_scores_gemma":[0.3104348,0.6782411,0.009189343,0.0012033051,0.00065478263,0.00027667978],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14520681,0.00017030936,0.0033996317,0.00047659647,0.00018608688,0.00003280949,0.00096691964,0.00034072934,0.00014793359],"category_scores_gemma":[0.8349911,0.00008821024,0.0010543264,0.0017452056,0.0008312055,0.0001453371,0.00030498518,0.0016513608,0.0000031821678],"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":[0.0002793502,0.00007568577,0.9116936,0.0000010525706,0.00034714205,0.0000034831316,0.00017460885,0.0003704074,0.0000042624933,0.00010671004,0.00072464166,0.08621906],"study_design_scores_gemma":[0.0016413402,0.0004653557,0.95027214,0.00003630191,0.00023422118,0.000030547497,0.00042666274,0.0001804094,0.0000048707034,0.034827467,0.01180241,0.00007825053],"about_ca_topic_score_codex":0.0012612035,"about_ca_topic_score_gemma":0.003243341,"teacher_disagreement_score":0.6897843,"about_ca_system_score_codex":0.00001514259,"about_ca_system_score_gemma":0.00015034428,"threshold_uncertainty_score":0.8801895},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W1995866728","doi":"10.1016/j.jclinepi.2011.04.013","title":"Health burden in chronic disease: multimorbidity is associated with self-rated health more than medical comorbidity alone","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":106,"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 Arthritis and Musculoskeletal and Skin Diseases; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Multimorbidity; Comorbidity; Medicine; Disease; Chronic disease; Gerontology; Burden of disease; Psychiatry; Family medicine; Internal medicine","score_opus":0.3234522397145654,"score_gpt":0.5157836278393771,"score_spread":0.19233138812481176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995866728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82887465,0.0045818845,0.0007009298,0.16337855,0.00089225505,0.00093359675,0.00005588804,0.00012646423,0.0004558041],"genre_scores_gemma":[0.97232485,0.007954162,0.0013644015,0.017002458,0.0010828674,0.000010354245,0.000093318806,0.0000433824,0.00012421011],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9866155,0.0053429836,0.0055526705,0.0005902277,0.00087204314,0.0010265721],"domain_scores_gemma":[0.9868376,0.00507013,0.004639871,0.000616003,0.0003222889,0.0025140992],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026459007,0.0003781689,0.004588375,0.0002546171,0.00009033376,0.000007145312,0.00048719143,0.00040315153,0.0010914247],"category_scores_gemma":[0.024009611,0.00026551716,0.00062028883,0.0004265855,0.0006937969,0.00016723211,0.00015257773,0.002221202,0.000026378377],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033088066,0.0034706069,0.9140152,0.0006953609,0.0015350532,0.002260831,0.0005856771,0.000109624365,3.1466968e-7,0.00060451415,0.064728595,0.008685422],"study_design_scores_gemma":[0.010533173,0.0040706275,0.9710448,0.0016666387,0.00021109908,0.00010609401,0.0001264936,0.0072528594,4.6429767e-7,0.0010437821,0.003736153,0.00020780943],"about_ca_topic_score_codex":0.0018837105,"about_ca_topic_score_gemma":0.000971688,"teacher_disagreement_score":0.14637609,"about_ca_system_score_codex":0.0011669641,"about_ca_system_score_gemma":0.010549317,"threshold_uncertainty_score":0.9999797},"labels":[],"label_agreement":null},{"id":"W1995944163","doi":"10.1016/j.jclinepi.2011.12.011","title":"Author’s specialty and conflicts of interest contribute to conflicting guidelines for screening mammography","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Global Cancer Incidence and Screening","field":"Medicine","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":"McMaster University","funders":"Agency for Healthcare Research and Quality","keywords":"Guideline; Medicine; Mammography; Specialty; Odds ratio; Family medicine; MEDLINE; Confidence interval; Breast cancer; Pathology; Internal medicine; Cancer","score_opus":0.7982592491668776,"score_gpt":0.6249572275200881,"score_spread":0.17330202164678954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995944163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8649199,0.0034478472,0.092007026,0.037613474,0.0014505426,0.0003365492,0.0000222677,0.00001013538,0.00019227446],"genre_scores_gemma":[0.8613706,0.00026794535,0.117859356,0.016088262,0.0043240413,0.0000036873944,0.0000035226044,0.000014060685,0.00006851922],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935753,0.0006476955,0.0048908032,0.00019762927,0.0001877437,0.00050086406],"domain_scores_gemma":[0.9771152,0.016168706,0.0032222758,0.00021884192,0.0020797648,0.0011951708],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035226673,0.00016510629,0.002598783,0.00018089915,0.000050183782,0.000005004409,0.00015714929,0.00029868342,0.000028061997],"category_scores_gemma":[0.19736612,0.00011984065,0.00068047276,0.00014430328,0.00022180492,0.00013566006,0.00008159142,0.00055310945,0.0000017326092],"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":[0.0026584882,0.000060533526,0.94033337,0.00006242647,0.00029248357,0.000008764743,0.00011614663,0.00002213981,0.00018797537,0.0035865635,0.019722398,0.03294873],"study_design_scores_gemma":[0.0032795686,0.0029941818,0.69289666,0.0009147214,0.00035157744,0.00041365414,0.0003206977,0.00029536846,0.00019988845,0.0010533491,0.29713437,0.0001459293],"about_ca_topic_score_codex":0.00005748895,"about_ca_topic_score_gemma":0.000025230833,"teacher_disagreement_score":0.27741197,"about_ca_system_score_codex":0.000017363713,"about_ca_system_score_gemma":0.00008254336,"threshold_uncertainty_score":0.9934372},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W1995969428","doi":"10.1016/j.jclinepi.2011.12.012","title":"Decisions about lumping vs. splitting of the scope of systematic reviews of complex interventions are not well justified: A case study in systematic reviews of health care professional reminders","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Scope (computer science); Psychological intervention; Systematic review; Medicine; Health care; Meta-analysis; MEDLINE; Psychology; Nursing; Computer science; Economics; Political science","score_opus":0.8963614236741357,"score_gpt":0.7043973155346066,"score_spread":0.19196410813952913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995969428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93811995,0.038033616,0.0040615904,0.0053433664,0.0022330207,0.012134809,0.00002752056,0.000004445246,0.000041701896],"genre_scores_gemma":[0.98447555,0.0043467786,0.009525445,0.0013723668,0.00019621955,0.0000453297,0.0000053199,0.00001962018,0.00001334008],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8732343,0.06079115,0.06435783,0.0003596923,0.0007793613,0.0004777108],"domain_scores_gemma":[0.7697198,0.15221848,0.07500176,0.0011612083,0.001580291,0.0003184745],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20558093,0.00025428276,0.012253903,0.00030758994,0.00007297025,0.000002144067,0.00045235475,0.00024306882,0.00008771633],"category_scores_gemma":[0.66494465,0.00014341407,0.0023883265,0.0005035008,0.00030204694,0.0001597226,0.00024426717,0.0012926493,0.000004209745],"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":[0.0006689593,0.0032989425,0.36677602,0.61784905,0.0005268159,0.00003074748,0.002704267,0.000062218474,0.000064177126,0.000115050425,0.0019227173,0.005981046],"study_design_scores_gemma":[0.0051392335,0.0027286313,0.27561456,0.66227007,0.00351198,0.0011973089,0.048638653,0.00048021102,0.000010626296,0.00009041619,0.00014670445,0.00017160209],"about_ca_topic_score_codex":0.0003297793,"about_ca_topic_score_gemma":0.0004918844,"teacher_disagreement_score":0.45936373,"about_ca_system_score_codex":0.00015054239,"about_ca_system_score_gemma":0.0005929693,"threshold_uncertainty_score":0.8376523},"labels":[],"label_agreement":null},{"id":"W1995977203","doi":"10.1016/j.jclinepi.2005.05.009","title":"Summary measures were a useful alternative for analyzing therapeutic clinical trial data","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":6,"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":"Physicians' Services Incorporated Foundation","keywords":"Medicine; Randomized controlled trial; Placebo; Clinical trial; Internal medicine; Area under the curve; Disease; Pathology","score_opus":0.6173709782944102,"score_gpt":0.6079110607500117,"score_spread":0.009459917544398566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995977203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8788009,0.0041840766,0.086649135,0.023307456,0.003895792,0.0015330936,0.00006489177,0.000025709462,0.0015389132],"genre_scores_gemma":[0.9678184,0.0031716202,0.0075257393,0.005873723,0.01432976,0.000017712391,0.000104798775,0.000038039776,0.0011202059],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9847386,0.0065193544,0.0070910747,0.00057678885,0.000483566,0.00059062376],"domain_scores_gemma":[0.93297464,0.061315242,0.0034521283,0.0007420347,0.0010185429,0.0004974001],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07685661,0.00021583769,0.0031994244,0.00019442385,0.000079936406,0.000017285318,0.0006963884,0.0003987329,0.00012508828],"category_scores_gemma":[0.085486166,0.00014110799,0.0014678815,0.00013122594,0.0005589329,0.00019739862,0.00020136106,0.0015064562,0.000017267368],"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":[0.069740005,0.0015488807,0.80088454,0.000032311265,0.0011859672,0.00008987315,0.0000035279375,0.0000061222063,0.000015078787,0.00055936846,0.032036465,0.09389783],"study_design_scores_gemma":[0.09416394,0.015015525,0.7364844,0.0002140716,0.0012142097,0.00012428004,0.000037461017,0.0020348225,0.000015931868,0.024540065,0.12597169,0.0001835749],"about_ca_topic_score_codex":0.000034417466,"about_ca_topic_score_gemma":0.00002418865,"teacher_disagreement_score":0.09393523,"about_ca_system_score_codex":0.000038136503,"about_ca_system_score_gemma":0.0007452254,"threshold_uncertainty_score":0.9505704},"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":"W1997415588","doi":"10.1016/j.jclinepi.2004.09.005","title":"Breast cancer survivors accurately reported key treatment and prognostic characteristics","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":72,"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; Hôpital du Saint-Sacrement; Centre hospitalier universitaire de Québec","funders":"","keywords":"Medicine; Breast cancer; Medical record; Mastectomy; Population; Radiation therapy; Survivorship curve; Cancer registry; Telephone interview; Cancer; Breast reconstruction; Surgery; Internal medicine","score_opus":0.27648790385838407,"score_gpt":0.49873232773329,"score_spread":0.22224442387490595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997415588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96839947,0.002030753,0.00016500577,0.02736986,0.0015975662,0.00016333812,0.000033906956,0.000015766142,0.00022432151],"genre_scores_gemma":[0.9810137,0.011402491,0.00055262155,0.0031598185,0.003483311,0.000008263983,0.000008596168,0.000019015943,0.0003521474],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946431,0.0010189253,0.0036013655,0.00027253188,0.00014071322,0.0003233505],"domain_scores_gemma":[0.98941946,0.006923544,0.0024367664,0.00023571395,0.00043461553,0.0005499246],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005399325,0.00019967924,0.0023528836,0.00008456667,0.000039459963,0.0000071779605,0.00008299667,0.00030729998,0.00024051643],"category_scores_gemma":[0.009811786,0.00012788663,0.00046604485,0.000100017896,0.0002210871,0.00008391349,0.000028288689,0.00057524384,0.000009160012],"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":[0.0010852512,0.00023641998,0.77928275,0.0000290221,0.00031712078,0.00012680716,0.00009995615,0.000004763192,0.000013042802,0.000065982706,0.0006196696,0.2181192],"study_design_scores_gemma":[0.0017060394,0.0012566362,0.94407886,0.0001648487,0.00050151075,0.003329823,0.000053291722,0.00021138659,0.0000072614876,0.00013035044,0.04844936,0.00011060811],"about_ca_topic_score_codex":0.0005613997,"about_ca_topic_score_gemma":0.0012443644,"teacher_disagreement_score":0.2180086,"about_ca_system_score_codex":0.00010509623,"about_ca_system_score_gemma":0.00047108278,"threshold_uncertainty_score":0.998529},"labels":[],"label_agreement":null},{"id":"W1997476966","doi":"10.1016/j.jclinepi.2008.10.013","title":"Indirect comparison: relative risk fallacies and odds solution","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relative risk; Odds; Odds ratio; Medicine; Fallacy; Internal medicine; Confidence interval; Epistemology","score_opus":0.45877949373645094,"score_gpt":0.5651662699587094,"score_spread":0.1063867762222585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997476966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304131,0.00723232,0.0087569,0.050105464,0.0004717524,0.00022205504,0.0000044481467,0.000020638736,0.0027733035],"genre_scores_gemma":[0.96733785,0.017370345,0.012742699,0.0016010392,0.000831493,9.597504e-7,0.000001206574,0.0000055030955,0.00010888724],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9921141,0.0038943153,0.0031776924,0.00021817372,0.0002512705,0.0003444096],"domain_scores_gemma":[0.96771413,0.028978791,0.002333985,0.00017344595,0.00038884665,0.00041081288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021876741,0.0001400829,0.0028446286,0.00014167685,0.000106910615,0.000004354852,0.00010359023,0.00029266957,0.000032480166],"category_scores_gemma":[0.19764982,0.000089020294,0.00045192713,0.00011830762,0.0005450861,0.00011047247,0.00005999341,0.001770367,0.000012753291],"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":[0.0010789437,0.00023105876,0.86854357,0.000012860294,0.00036640876,0.000017517159,0.00016784963,0.000019172794,0.000062797095,0.00057022105,0.010760646,0.11816898],"study_design_scores_gemma":[0.0022596612,0.0040680612,0.9778258,0.00011960916,0.00015981775,0.00007996364,0.00009107223,0.001830641,0.0000118576,0.004916062,0.0085681155,0.00006934405],"about_ca_topic_score_codex":0.000012288817,"about_ca_topic_score_gemma":0.000010459171,"teacher_disagreement_score":0.17577308,"about_ca_system_score_codex":0.000045494857,"about_ca_system_score_gemma":0.00011078132,"threshold_uncertainty_score":0.80910873},"labels":[],"label_agreement":null},{"id":"W1997610764","doi":"10.1016/j.jclinepi.2004.01.021","title":"The number needed to treat (NNT) can be adjusted for bias when the outcome is measured with error","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"McMaster University","funders":"","keywords":"Number needed to treat; Outcome (game theory); Statistics; Medicine; Mathematics; Econometrics; Confidence interval; Relative risk; Mathematical economics","score_opus":0.923124085653857,"score_gpt":0.6858614348184507,"score_spread":0.2372626508354062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997610764","genre_codex":"commentary","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":[0.09584417,0.00007674702,0.34315836,0.55533004,0.0030968762,0.0016306879,0.000118432225,0.000045843313,0.00069886865],"genre_scores_gemma":[0.04573427,0.000086962624,0.8914349,0.059415616,0.002319897,0.00007250024,7.395483e-7,0.00008028387,0.00085483573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9762203,0.011947876,0.009928926,0.00048182264,0.0005984913,0.0008225509],"domain_scores_gemma":[0.36018366,0.6324499,0.004776875,0.0009417887,0.0009820758,0.00066570885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.101660594,0.00038227762,0.00432976,0.000053868724,0.0002863385,0.000034839635,0.0012069884,0.0006042308,0.00014905419],"category_scores_gemma":[0.86416733,0.00015673901,0.001437681,0.0002304393,0.0008931976,0.000054328353,0.00013080891,0.0016054986,0.00002713833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02143816,0.0015074726,0.10544088,0.00026071002,0.0027991445,0.00010394499,0.0015414935,0.0004287441,0.000024002362,0.46774957,0.34228128,0.056424607],"study_design_scores_gemma":[0.005904447,0.0020333428,0.009498664,0.00013945739,0.000751519,0.00011773414,0.00037074523,0.000058153877,0.00006140167,0.964554,0.016278476,0.00023207604],"about_ca_topic_score_codex":0.00013817783,"about_ca_topic_score_gemma":0.00027679323,"teacher_disagreement_score":0.7625067,"about_ca_system_score_codex":0.00012037011,"about_ca_system_score_gemma":0.00047503857,"threshold_uncertainty_score":0.92502946},"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":"W1997797837","doi":"10.1016/j.jclinepi.2006.04.004","title":"BLISS index for analyzing knee osteoarthritis trials data","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","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":"Ottawa Hospital; University of Ottawa; Université de Montréal; McMaster University; University of Toronto; Sunnybrook Health Science Centre; Health Sciences Centre","funders":"","keywords":"BLISS; Medicine; WOMAC; Osteoarthritis; Physical therapy; Randomized controlled trial; Surgery; Alternative medicine; Pathology","score_opus":0.39029547766395845,"score_gpt":0.5238889597727744,"score_spread":0.13359348210881594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997797837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8671061,0.01938929,0.075004816,0.024697224,0.008987368,0.00216806,0.00033269412,0.00007624618,0.0022382126],"genre_scores_gemma":[0.91512656,0.0008085478,0.06574754,0.003351625,0.012961959,0.000020017129,0.0003396422,0.00005407741,0.001590026],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98920614,0.0026053118,0.007148481,0.00039965683,0.0001974225,0.0004429793],"domain_scores_gemma":[0.95867145,0.036161903,0.0038381186,0.0006298813,0.0003598784,0.00033879408],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047159974,0.0002063003,0.0048476392,0.00020075572,0.00006492565,0.000011867075,0.0002986051,0.00049067684,0.00016176072],"category_scores_gemma":[0.1134494,0.00014403599,0.0012510888,0.00012358213,0.00015824845,0.0002025682,0.00009394864,0.00060614763,0.00002104272],"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":[0.0048598866,0.00056952646,0.30799058,0.00005144127,0.00035841778,0.00024534698,0.0000065263307,0.000020338779,0.00029264842,0.0041780625,0.031943545,0.6494837],"study_design_scores_gemma":[0.11257134,0.06184769,0.16342135,0.0014331316,0.0046205535,0.0029848088,0.00011517551,0.0010633438,0.0003708922,0.1273181,0.5235169,0.00073672447],"about_ca_topic_score_codex":0.00002016939,"about_ca_topic_score_gemma":0.00005362971,"teacher_disagreement_score":0.64874697,"about_ca_system_score_codex":0.000027851527,"about_ca_system_score_gemma":0.0003198585,"threshold_uncertainty_score":0.9811493},"labels":[],"label_agreement":null},{"id":"W1998155248","doi":"10.1016/j.jclinepi.2014.06.008","title":"Adherence measurement and patient recruitment methods are poor in intervention trials to improve patient adherence","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Medication Adherence and Compliance","field":"Medicine","cited_by":49,"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; McMaster University; Dalhousie University","funders":"","keywords":"Interquartile range; Medicine; Confidence interval; Psychological intervention; Physical therapy; Intervention (counseling); Randomized controlled trial; Sample size determination; Clinical trial; Internal medicine; Nursing; Statistics","score_opus":0.835637202726603,"score_gpt":0.6673302852979196,"score_spread":0.16830691742868342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998155248","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":[0.00027978906,0.9762597,0.014678889,0.0021362326,0.003289853,0.0032018435,0.000010100813,0.000009910933,0.00013369037],"genre_scores_gemma":[0.0003226974,0.9619741,0.032565545,0.003956967,0.00055965333,0.000496969,0.000005753029,0.000027487022,0.000090843314],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94534457,0.032589898,0.01999092,0.00086525636,0.0006855305,0.0005238109],"domain_scores_gemma":[0.9425794,0.02891735,0.025331957,0.00081765826,0.0011048773,0.0012487741],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090960026,0.00048419824,0.014197689,0.00035056067,0.00003048315,0.000011269306,0.000367727,0.000771764,0.0003423007],"category_scores_gemma":[0.25952992,0.00030077665,0.0021025978,0.00027048713,0.00015838786,0.00005707063,0.00017666537,0.001940303,0.0001351757],"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":[0.0003677409,0.0004374632,0.00053434254,0.0033576328,0.00032401405,0.000025418716,0.000027674758,8.3115197e-7,0.0000016059888,0.000058830818,0.0065605,0.98830396],"study_design_scores_gemma":[0.0018479489,0.011475229,0.0014179634,0.059492566,0.00095281703,0.00014663498,0.000086823835,0.000029931849,0.000003362736,0.001007077,0.9232875,0.0002521309],"about_ca_topic_score_codex":0.00002935725,"about_ca_topic_score_gemma":0.000010778956,"teacher_disagreement_score":0.98805183,"about_ca_system_score_codex":0.00029224827,"about_ca_system_score_gemma":0.00082099636,"threshold_uncertainty_score":0.99994445},"labels":[],"label_agreement":null},{"id":"W1999444257","doi":"10.1016/j.jclinepi.2009.06.002","title":"A substantial and confusing variation exists in handling of baseline covariates in randomized controlled trials: a review of trials published in leading medical journals","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":163,"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; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Medicine; Baseline (sea); Randomized controlled trial; MEDLINE; Demography; Family medicine; Internal medicine; Statistics","score_opus":0.9368720615197206,"score_gpt":0.7286312066149652,"score_spread":0.2082408549047554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999444257","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021729464,0.9699278,0.022142584,0.0031348963,0.0010617683,0.0033911634,0.000011528942,8.254679e-7,0.00011217044],"genre_scores_gemma":[0.0006934082,0.990959,0.006843511,0.00071065465,0.00070589304,0.000041061347,0.0000075594303,0.000016187554,0.00002274291],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.011372466,0.6804151,0.3029082,0.0009250231,0.0039440896,0.00043509618],"domain_scores_gemma":[0.0024132305,0.7256635,0.26828927,0.001010108,0.0022707316,0.00035314498],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.98944145,0.00072115427,0.3035981,0.0039996365,0.000025910347,0.00014575798,0.0018908365,0.0016169942,0.0047813463],"category_scores_gemma":[0.9975184,0.0002929713,0.032429643,0.002578702,0.00035357568,0.00035572393,0.00012354016,0.0027267574,0.0000064988417],"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":[0.020498443,0.0004934901,0.0013036814,0.021373983,0.0038069983,0.00011553391,0.000110724446,0.000070125854,6.9407787e-7,0.002674988,0.0018303286,0.947721],"study_design_scores_gemma":[0.26510364,0.00040855035,0.0004782217,0.6235097,0.018278165,0.0003699789,0.000043135213,0.012255603,1.2859418e-7,0.038944185,0.040095437,0.00051325076],"about_ca_topic_score_codex":0.00005882833,"about_ca_topic_score_gemma":0.000088312976,"teacher_disagreement_score":0.94720775,"about_ca_system_score_codex":0.000069571375,"about_ca_system_score_gemma":0.0027632983,"threshold_uncertainty_score":0.99995226},"labels":[],"label_agreement":null},{"id":"W2000165621","doi":"10.1016/j.jclinepi.2009.06.010","title":"Quantifying the magnitude of risk for balance impairment on falls in community-dwelling older adults: a systematic review and meta-analysis","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":277,"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; Western University","funders":"","keywords":"Meta-analysis; Balance (ability); Medicine; Gerontology; Falls in older adults; Poison control; Injury prevention; Physical medicine and rehabilitation; Environmental health; Internal medicine","score_opus":0.4660100141185683,"score_gpt":0.5964347190229105,"score_spread":0.13042470490434216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000165621","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":[0.00015705056,0.9930524,0.0009713386,0.0009401518,0.00025826186,0.004478285,0.000112674614,0.000006421489,0.000023385117],"genre_scores_gemma":[0.0005434028,0.9925838,0.001988007,0.0043135225,0.0001838924,0.00028726124,0.0000329239,0.00002650785,0.000040682036],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.8823854,0.09848975,0.018044244,0.00034656771,0.00023806201,0.00049603474],"domain_scores_gemma":[0.7966315,0.17534946,0.026583921,0.0008452532,0.00042866284,0.00016115532],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16474688,0.00048641855,0.031452235,0.0003479243,0.0002896002,0.000004557175,0.0008680484,0.000950333,0.000018155926],"category_scores_gemma":[0.08262058,0.00023131329,0.008285715,0.00049879734,0.00015386938,0.00006377165,0.00011186685,0.0061822208,0.0000096371],"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":[0.000101332254,0.0008995686,0.0015310409,0.945171,0.042421643,0.000003274721,0.0002245855,0.0000056171352,4.2221084e-9,0.0003422712,0.00053273473,0.008766949],"study_design_scores_gemma":[0.0011726397,0.0007410966,0.008917582,0.3568481,0.6249256,0.0000142509825,0.0002746777,0.00011726156,5.389979e-10,0.0011851856,0.0055669597,0.00023663022],"about_ca_topic_score_codex":0.000105877785,"about_ca_topic_score_gemma":0.00023741828,"teacher_disagreement_score":0.5883229,"about_ca_system_score_codex":0.000085815154,"about_ca_system_score_gemma":0.00027418547,"threshold_uncertainty_score":0.99611056},"labels":[],"label_agreement":null},{"id":"W2000190131","doi":"10.1016/j.jclinepi.2010.10.005","title":"Randomized controlled trials of herbal interventions underreport important details of the intervention","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Complementary and Alternative Medicine Studies","field":"Medicine","cited_by":38,"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; University of Toronto","funders":"","keywords":"Randomized controlled trial; Psychological intervention; Medicine; Intervention (counseling); Traditional medicine; Alternative medicine; Internal medicine; Psychiatry; Pathology","score_opus":0.7559503582615328,"score_gpt":0.6518600769277969,"score_spread":0.10409028133373588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000190131","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":[0.00088204036,0.98863155,0.0024665042,0.0005885589,0.0044347984,0.0025262171,0.000026078125,0.0000034840436,0.00044077545],"genre_scores_gemma":[0.0034070073,0.9942171,0.00060054596,0.0001006018,0.0012399738,0.000047213434,0.000012807181,0.000018120569,0.00035665024],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8915544,0.045182183,0.062350933,0.00029372392,0.0003563181,0.00026239955],"domain_scores_gemma":[0.57458943,0.25378475,0.16898273,0.00088266504,0.0014364902,0.00032393003],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.23250087,0.00040174887,0.06424122,0.00031692686,0.000032830154,0.0000014418905,0.00043090337,0.0002032826,0.0008610513],"category_scores_gemma":[0.5207469,0.00015550369,0.048883084,0.00015848268,0.0011937661,0.00003713984,0.00020128263,0.0014176288,0.0000013948493],"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":[0.11513601,0.002072456,0.017181333,0.021872308,0.06313919,0.000067857036,0.00005784305,5.310151e-7,2.8565358e-7,0.0056862826,0.0018197274,0.77296615],"study_design_scores_gemma":[0.49819928,0.005263463,0.0025142804,0.15262215,0.10008781,0.000899539,0.00016824866,0.000011203818,0.0000012617255,0.013428582,0.22657819,0.00022599744],"about_ca_topic_score_codex":0.00004664653,"about_ca_topic_score_gemma":0.000020661088,"teacher_disagreement_score":0.7727402,"about_ca_system_score_codex":0.000043353513,"about_ca_system_score_gemma":0.00055887626,"threshold_uncertainty_score":0.9606421},"labels":[],"label_agreement":null},{"id":"W2000208858","doi":"10.1016/j.jclinepi.2006.03.015","title":"An absence of pediatric randomized controlled trials in general medical journals, 1985–2004","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical studies and practices","field":"Medicine","cited_by":106,"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; Hospital for Sick Children; SickKids Foundation","funders":"","keywords":"Medicine; Jadad scale; Randomized controlled trial; Medical journal; Confidence interval; Family medicine; MEDLINE; Sample size determination; Pediatrics; Internal medicine","score_opus":0.6279068035414472,"score_gpt":0.6722536784583004,"score_spread":0.044346874916853185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000208858","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":[0.00040537538,0.9891645,0.00071924494,0.0047979183,0.0027528543,0.0016548282,0.000014430335,0.000007186672,0.0004836643],"genre_scores_gemma":[0.00018863882,0.9806062,0.0022717982,0.0020110633,0.014758261,0.00003604573,0.000010652966,0.00003658687,0.000080754835],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7546949,0.16761321,0.07440857,0.00069634,0.0016027766,0.0009842257],"domain_scores_gemma":[0.2647613,0.668487,0.06378922,0.0005110612,0.0008662633,0.0015851394],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.5018004,0.00064504193,0.104913004,0.00074483175,0.000046525114,0.000012370771,0.00072659866,0.0021161598,0.0009530773],"category_scores_gemma":[0.8043935,0.00030265996,0.016752474,0.0004774573,0.00072944444,0.00014297215,0.00010051647,0.0062385844,0.000013165944],"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":[0.17551306,0.0022731263,0.007455231,0.0056768064,0.0072361943,0.0011549739,0.00000971283,0.00003604258,1.3388944e-7,0.0005606641,0.011170572,0.7889135],"study_design_scores_gemma":[0.33586895,0.001343065,0.00078444846,0.0075236713,0.02288987,0.0011479481,0.000005111971,0.000449588,3.1121875e-8,0.002195404,0.62749255,0.0002993868],"about_ca_topic_score_codex":0.00007881897,"about_ca_topic_score_gemma":0.000010991503,"teacher_disagreement_score":0.7886141,"about_ca_system_score_codex":0.00009055673,"about_ca_system_score_gemma":0.0028904297,"threshold_uncertainty_score":0.9999602},"labels":[],"label_agreement":null},{"id":"W2000617030","doi":"10.1016/j.jclinepi.2005.01.014","title":"Systematically reviewing qualitative studies complements survey design: An exploratory study of barriers to paediatric immunisations","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":49,"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 General Hospital; Institute of Population and Public Health; Mount Sinai Hospital; McMaster University Medical Centre","funders":"University of Toronto","keywords":"Distrust; Qualitative research; Harm; Medicine; Exploratory research; Family medicine; Psychology; Social psychology","score_opus":0.8542032211335062,"score_gpt":0.6862358399672657,"score_spread":0.16796738116624055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000617030","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":[0.0010540517,0.99284285,0.0024525654,0.00042915528,0.0012367037,0.0019113377,0.00002607101,0.000010212414,0.000037044345],"genre_scores_gemma":[0.0018304369,0.9907636,0.0054396805,0.000456549,0.001390288,0.000058040736,0.000006050697,0.000029146682,0.000026174212],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7427,0.23898488,0.016692186,0.00045626072,0.0006338473,0.0005328519],"domain_scores_gemma":[0.78071094,0.20189342,0.0137402285,0.0006039896,0.0020614837,0.0009899656],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27101386,0.000400232,0.013776571,0.00042844823,0.00039116436,0.000015243467,0.0011400329,0.0004429941,0.00012953946],"category_scores_gemma":[0.4732702,0.0002783855,0.0013437342,0.0007788124,0.00013328614,0.00032720677,0.00018989411,0.001155641,0.000029700246],"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":[0.0002272451,0.002101091,0.017455202,0.012341772,0.0069698095,0.000053383068,0.19496359,0.00015436097,1.3349823e-8,0.003145489,0.023435442,0.7391526],"study_design_scores_gemma":[0.001985652,0.010741113,0.004018707,0.026768085,0.006295847,0.000011739315,0.33702078,0.0000060317775,4.0764627e-9,0.0021778413,0.6099877,0.0009865094],"about_ca_topic_score_codex":0.00009038346,"about_ca_topic_score_gemma":0.0012038482,"teacher_disagreement_score":0.7381661,"about_ca_system_score_codex":0.00021567338,"about_ca_system_score_gemma":0.0023529886,"threshold_uncertainty_score":0.99996686},"labels":[],"label_agreement":null},{"id":"W2001309417","doi":"10.1016/j.jclinepi.2008.08.002","title":"Systematic reviewers commonly contact study authors but do so with limited rigor","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":70,"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":"Systematic review; Cochrane Library; MEDLINE; Medicine; Family medicine; Cochrane collaboration; Alternative medicine; Pathology","score_opus":0.9344619821562419,"score_gpt":0.6945616561750576,"score_spread":0.23990032598118427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001309417","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002358151,0.9870924,0.0032914742,0.0005775908,0.0028990798,0.0053377002,0.00002410909,0.0000075219928,0.0005343468],"genre_scores_gemma":[0.00016388147,0.9907945,0.004620672,0.0009866151,0.0011238775,0.00010412121,0.0000073043166,0.00007412943,0.0021249051],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.2193659,0.5536797,0.21562764,0.0024670553,0.007895219,0.00096447335],"domain_scores_gemma":[0.17144923,0.5434149,0.2688622,0.009186855,0.005565768,0.0015210639],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.7767741,0.0016897401,0.17106232,0.00150654,0.00031078418,0.00044228937,0.008306876,0.0014874715,0.0018586373],"category_scores_gemma":[0.86959934,0.0005749146,0.037906144,0.0025505407,0.0005852032,0.00030204796,0.000378965,0.0047332714,0.0031639782],"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":[0.00013425805,0.001635866,0.019844431,0.10266033,0.02402344,0.0013194206,0.00021634047,0.00002677048,3.3255914e-9,0.00092716736,0.21905386,0.6301581],"study_design_scores_gemma":[0.00069175864,0.0023542163,0.0008133207,0.082014985,0.015656197,0.00318465,0.0003216014,0.000077734556,8.554042e-10,0.0005507702,0.8938161,0.0005186689],"about_ca_topic_score_codex":0.000014317589,"about_ca_topic_score_gemma":0.000022275584,"teacher_disagreement_score":0.67476225,"about_ca_system_score_codex":0.00014992675,"about_ca_system_score_gemma":0.0019293749,"threshold_uncertainty_score":0.9998088},"labels":[],"label_agreement":null},{"id":"W2001673070","doi":"10.1016/j.jclinepi.2006.06.006","title":"Forming research questions","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Aging, Elder Care, and Social Issues","field":"Health Professions","cited_by":118,"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; Health Sciences Centre; McMaster University Medical Centre","funders":"","keywords":"Medicine; Library science; Computer science","score_opus":0.5985921634937823,"score_gpt":0.6878335476894518,"score_spread":0.08924138419566952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001673070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90157676,0.0021497519,0.00967963,0.024336752,0.0053024916,0.0002888731,0.0000042956694,0.00004140296,0.05662006],"genre_scores_gemma":[0.9671092,0.0009773273,0.006931674,0.0072663617,0.013758506,0.0000105598665,0.000003407678,0.000022026372,0.003920932],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97727054,0.016163029,0.0053345095,0.00019135863,0.0002871098,0.00075345306],"domain_scores_gemma":[0.90209097,0.09388434,0.0023209322,0.00022457141,0.0012045291,0.000274684],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08252669,0.000102602215,0.001652063,0.00017181931,0.00074197113,0.0000031916493,0.0003264161,0.0006845467,0.0002521734],"category_scores_gemma":[0.1124592,0.00007409946,0.0004934159,0.00019356555,0.00043765522,0.00012915593,0.000106206004,0.0040318845,0.00020223806],"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":[0.00009307105,0.000111004214,0.7696163,0.000038145205,0.000038746923,0.000030926883,0.0007791463,0.000017373535,0.0000063471007,0.09316032,0.13040085,0.00570775],"study_design_scores_gemma":[0.0007691052,0.0003714232,0.37359455,0.00025668624,0.000028927272,0.000009816037,0.0034506358,0.00006366012,0.0000010029509,0.37958395,0.24178433,0.00008588523],"about_ca_topic_score_codex":0.0012447278,"about_ca_topic_score_gemma":0.0005595685,"teacher_disagreement_score":0.39602175,"about_ca_system_score_codex":0.00010050197,"about_ca_system_score_gemma":0.0006936499,"threshold_uncertainty_score":0.99826586},"labels":[],"label_agreement":null},{"id":"W2002196618","doi":"10.1016/j.jclinepi.2006.08.003","title":"Author's response: using structural equation modeling to evaluate response shift","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University","funders":"","keywords":"Scopus; Structural equation modeling; Conceptualization; Health related quality of life; Medicine; Psychology; Gerontology; Computer science; Mathematics; MEDLINE; Political science; Statistics; Internal medicine; Artificial intelligence; Law","score_opus":0.5805402598364955,"score_gpt":0.6258050251110916,"score_spread":0.04526476527459611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002196618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8006916,0.0001916703,0.031589113,0.16478795,0.002530441,0.00012716824,0.0000027801887,0.000013275281,0.000066015105],"genre_scores_gemma":[0.9697789,0.000021470734,0.018701712,0.008712708,0.0023943556,0.0000012441393,5.168959e-7,0.00001170016,0.00037739155],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9574929,0.03599836,0.004943619,0.00026608224,0.0005224707,0.0007766089],"domain_scores_gemma":[0.9351575,0.061999902,0.0016701525,0.00018768411,0.00040884523,0.0005759107],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16997468,0.00013406815,0.001368961,0.00018609075,0.0004364466,0.00002742248,0.00035130972,0.00042063463,0.000141917],"category_scores_gemma":[0.27967015,0.00010611617,0.00046591833,0.00022803561,0.00021429463,0.00022728949,0.00005389817,0.00068575895,0.000020962818],"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":[0.02997636,0.00008442138,0.5673917,0.00003357007,0.00007144851,0.000062549225,0.00282572,0.3364977,0.000037454945,0.048417408,0.007588361,0.007013309],"study_design_scores_gemma":[0.0008584352,0.00044634324,0.75467455,0.00011368374,0.000050742758,0.000013461113,0.0006859133,0.12598838,0.0000012023337,0.09893785,0.018043295,0.0001861292],"about_ca_topic_score_codex":0.0036453903,"about_ca_topic_score_gemma":0.000620656,"teacher_disagreement_score":0.2105093,"about_ca_system_score_codex":0.0002527031,"about_ca_system_score_gemma":0.0017380206,"threshold_uncertainty_score":0.8546857},"labels":[],"label_agreement":null},{"id":"W2002492790","doi":"10.1016/j.jclinepi.2004.07.001","title":"A national study showed that diagnoses varied by age group in nursing home residents under age 65","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":false,"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; Toronto Rehabilitation Institute","funders":"Centers for Medicare and Medicaid Services; Institute for Clinical Evaluative Sciences","keywords":"Medical diagnosis; Medicine; Minimum Data Set; Gerontology; Quarter (Canadian coin); Age groups; Population; Nursing homes; Family medicine; Demography; Pediatrics; Environmental health; Nursing","score_opus":0.3588171836388284,"score_gpt":0.5955858416924635,"score_spread":0.23676865805363512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002492790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97433263,0.0010648655,0.0006765373,0.017547479,0.004140995,0.00048071082,0.000009797995,0.000024378203,0.0017226095],"genre_scores_gemma":[0.99024475,0.00060935767,0.0015754076,0.004560738,0.002437639,0.000016736862,0.000017065458,0.000026261989,0.0005120294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98027176,0.012880762,0.0052642464,0.0003827109,0.00050010945,0.00070041855],"domain_scores_gemma":[0.93895406,0.057660595,0.002637503,0.00023207931,0.0001870539,0.00032868842],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030230401,0.0002249612,0.002354996,0.00032585047,0.00022918012,0.000009566194,0.00040682303,0.00064829434,0.0003051015],"category_scores_gemma":[0.027011652,0.0001745702,0.00043030138,0.00025750927,0.00024206514,0.00022505793,0.00007766166,0.0024585312,0.00005086782],"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":[0.0010321114,0.0022958661,0.805354,0.000020930334,0.000119180455,0.000124822,0.0018775199,0.000109255656,0.0000133546155,0.0012782478,0.17861502,0.009159713],"study_design_scores_gemma":[0.0046922257,0.0008990416,0.9577238,0.00034301393,0.00007085063,0.00001627842,0.0025518017,0.00003209203,3.728936e-7,0.028758187,0.004755131,0.00015720517],"about_ca_topic_score_codex":0.0002694443,"about_ca_topic_score_gemma":0.0010321515,"teacher_disagreement_score":0.1738599,"about_ca_system_score_codex":0.00038859356,"about_ca_system_score_gemma":0.0003859411,"threshold_uncertainty_score":0.9998428},"labels":[],"label_agreement":null},{"id":"W2002501104","doi":"10.1016/s0895-4356(02)00612-1","title":"Convergence of health ratings across nephrologists, nurses, and patients with end-stage renal disease","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":5,"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 General Hospital; University Health Network","funders":"University of Calgary","keywords":"Medicine; Dialysis; Emergency department; Diabetes mellitus; Prospective cohort study; Kidney disease; Internal medicine; Disease; Physical therapy; Emergency medicine; Psychiatry","score_opus":0.18727444304747784,"score_gpt":0.5303659947908335,"score_spread":0.3430915517433556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002501104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9768682,0.0012226959,0.00075759494,0.019774288,0.00100749,0.00017042799,0.000028041419,0.0000056875133,0.00016558862],"genre_scores_gemma":[0.9805474,0.0022853748,0.0022284596,0.014582586,0.00017219187,0.0000015054266,0.0000018792657,0.0000061469045,0.00017445527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9887097,0.0070927567,0.003139839,0.00019716656,0.00027122998,0.0005893158],"domain_scores_gemma":[0.9810701,0.014120726,0.0035578278,0.00013964361,0.00028786098,0.00082384126],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029527035,0.00011020229,0.001501103,0.00002821633,0.0002720028,0.000007356472,0.00019303619,0.00016348952,0.00017129218],"category_scores_gemma":[0.0708809,0.00007386869,0.00019117526,0.000101890815,0.0014085891,0.00014212722,0.00002466107,0.00047353687,0.0000014226327],"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":[0.00023670607,0.00011817216,0.9588609,0.000054533448,0.000023525363,0.0000053051494,0.0005256108,0.000017661827,2.8031732e-8,0.034219924,0.0016018935,0.0043357885],"study_design_scores_gemma":[0.00092964224,0.0005799729,0.9034812,0.00007123901,0.000011000328,0.0000012729982,0.00062549213,0.000008581091,1.6267337e-7,0.0025213817,0.09170506,0.00006503056],"about_ca_topic_score_codex":0.0013012385,"about_ca_topic_score_gemma":0.000542311,"teacher_disagreement_score":0.090103164,"about_ca_system_score_codex":0.000041290994,"about_ca_system_score_gemma":0.0013606255,"threshold_uncertainty_score":0.99930614},"labels":[],"label_agreement":null},{"id":"W2002541423","doi":"10.1016/j.jclinepi.2007.10.016","title":"Systematic reviews and original articles differ in relevance, novelty, and use in an evidence-based service for physicians: PLUS project","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"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":"Canadian Institutes of Health Research; McMaster University","keywords":"Systematic review; Observational study; Relevance (law); Novelty; Medicine; MEDLINE; Family medicine; Psychology; Medical education; Internal medicine; Social psychology","score_opus":0.948207793787354,"score_gpt":0.6642309441293712,"score_spread":0.28397684965798276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002541423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.970677,0.009427047,0.01406213,0.00376319,0.0002456463,0.0018142416,0.000003542889,0.0000014409287,0.0000057727284],"genre_scores_gemma":[0.89865685,0.0096404245,0.079557225,0.011318476,0.0004331092,0.00015359494,0.0000013055011,0.000020072917,0.0002189705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8526908,0.09745235,0.047039557,0.001025467,0.0013268383,0.00046497153],"domain_scores_gemma":[0.5092789,0.45779955,0.029326057,0.0017842376,0.0014925274,0.00031876328],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41381735,0.00028436974,0.014953761,0.0004626881,0.00005998955,0.00009347827,0.00079164415,0.00020689749,0.000037659265],"category_scores_gemma":[0.728806,0.00012748466,0.0013465413,0.0009179169,0.00020238654,0.0008578123,0.000060573675,0.00050984276,0.0000254127],"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":[0.00033580686,0.00020188729,0.98504776,0.0036568658,0.00007669491,0.000030056428,0.00029939564,0.00028041992,0.000018632127,0.0005065232,0.0040923054,0.0054536792],"study_design_scores_gemma":[0.0028207314,0.001237603,0.7882837,0.016450671,0.00043235495,0.00022918425,0.0002991775,0.16795,0.0000020364369,0.010546972,0.011411363,0.00033616225],"about_ca_topic_score_codex":0.000043843385,"about_ca_topic_score_gemma":0.00054190354,"teacher_disagreement_score":0.3603472,"about_ca_system_score_codex":0.000040241765,"about_ca_system_score_gemma":0.0002287384,"threshold_uncertainty_score":0.99967027},"labels":[],"label_agreement":null},{"id":"W2002976768","doi":"10.1016/j.jclinepi.2010.01.023","title":"A prospective cohort study found that provider and information continuity was low after patient discharge from hospital","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":52,"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; St. Michael's Hospital; University of Toronto; Ottawa Hospital; University of Calgary; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Physicians' Services Incorporated Foundation","keywords":"Continuity of care; Medicine; IT service continuity; Prospective cohort study; Cohort study; Emergency medicine; Hospital discharge; Cohort; Medical emergency; Intensive care medicine; Health care; Surgery; Internal medicine","score_opus":0.17104538521882168,"score_gpt":0.5522727215604147,"score_spread":0.38122733634159306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002976768","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":[0.060753234,0.910767,0.00015268577,0.0034047656,0.014283565,0.009539208,0.00030669026,0.000036439364,0.0007564179],"genre_scores_gemma":[0.004418956,0.9810416,0.0006184109,0.010663437,0.002495014,0.0005633907,0.000064982116,0.000040125393,0.00009404994],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9739291,0.01246836,0.011931403,0.0005051163,0.00041870648,0.0007473294],"domain_scores_gemma":[0.9352801,0.04772872,0.015094258,0.0005803563,0.00068035675,0.0006362057],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.022940239,0.0005484579,0.010859564,0.00021023887,0.00027333488,0.000017725495,0.0004029945,0.0020476035,0.00026902452],"category_scores_gemma":[0.043663632,0.000323229,0.0012715689,0.00011014006,0.00027815846,0.00088167033,0.0004610458,0.008415562,0.00016838616],"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":[0.0002015713,0.00024638214,0.6770051,0.0018783407,0.00037974122,0.00001708966,0.00061368075,1.0320813e-8,7.1827233e-10,0.00007636929,0.0042987606,0.31528297],"study_design_scores_gemma":[0.00092400843,0.00096863654,0.46925053,0.0016953112,0.0006260188,0.000007454839,0.00016432432,5.478234e-7,1.1535736e-9,0.0007408698,0.5254484,0.00017390506],"about_ca_topic_score_codex":0.0002485812,"about_ca_topic_score_gemma":0.00030498623,"teacher_disagreement_score":0.52114964,"about_ca_system_score_codex":0.0004095624,"about_ca_system_score_gemma":0.0034257385,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W2003619839","doi":"10.1016/j.jclinepi.2005.01.002","title":"The PEDro scale provides a more comprehensive measure of methodological quality than the Jadad Scale in stroke rehabilitation literature","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":225,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Western University","funders":"Canadian Stroke Network","keywords":"Jadad scale; Rehabilitation; Blinding; Pearson product-moment correlation coefficient; Physical therapy; Medicine; Scale (ratio); Descriptive statistics; Stroke (engine); Habilitation; Statistics; Physical medicine and rehabilitation; Randomized controlled trial; Mathematics; Surgery; Cartography; Geography; Humanities; Engineering","score_opus":0.5071457534768637,"score_gpt":0.6058297306676128,"score_spread":0.09868397719074906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003619839","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":[0.010349057,0.96373564,0.00022001473,0.022495508,0.0016017893,0.0013993514,0.000054749606,0.000010636145,0.00013323806],"genre_scores_gemma":[0.00042955045,0.97839445,0.01771051,0.0010448024,0.0020520631,0.000043369007,0.000016967688,0.000029812905,0.00027847855],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9270989,0.057904854,0.013159955,0.000604505,0.00070845406,0.0005233556],"domain_scores_gemma":[0.6535516,0.3356238,0.008475398,0.00078893686,0.0012772987,0.00028297293],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07697809,0.0004839114,0.010767896,0.0002875138,0.0001079733,0.000015973676,0.0006364007,0.0017131862,0.000025868072],"category_scores_gemma":[0.28522828,0.00019472203,0.0058276644,0.0005007801,0.0020013584,0.000100553814,0.00011923385,0.004909489,0.0000055930504],"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":[0.0014261117,0.0004883779,0.045385793,0.005253583,0.0005267176,0.0000092308965,0.00037471193,0.000020671145,0.0000016192618,0.0003643797,0.0026980916,0.9434507],"study_design_scores_gemma":[0.0013452872,0.0022269634,0.18838687,0.014774637,0.0008358112,0.00035337725,0.0007859917,0.000021384036,1.7435619e-7,0.001323572,0.7897636,0.00018230827],"about_ca_topic_score_codex":0.000018401834,"about_ca_topic_score_gemma":0.000056787438,"teacher_disagreement_score":0.9432684,"about_ca_system_score_codex":0.00016609555,"about_ca_system_score_gemma":0.00107238,"threshold_uncertainty_score":0.9995828},"labels":[],"label_agreement":null},{"id":"W2003774556","doi":"10.1016/j.jclinepi.2006.01.007","title":"Errors in search strategies were identified by type and frequency","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":144,"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; University of Ottawa; Children's Hospital of Eastern Ontario","funders":"","keywords":"MEDLINE; Cochrane Library; Interquartile range; Medicine; Systematic review; Randomized controlled trial; Evidence-based medicine; Alternative medicine; Surgery; Pathology","score_opus":0.8938970071046008,"score_gpt":0.6803107360019218,"score_spread":0.21358627110267903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003774556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97711396,0.0048730546,0.005553983,0.006840816,0.00079776224,0.00013033702,0.0000033300564,0.0000011556198,0.0046855775],"genre_scores_gemma":[0.99022245,0.00040679582,0.006267921,0.00065126544,0.0003016951,8.976996e-7,0.0000017488693,0.000005696484,0.0021415052],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8529399,0.09055577,0.05310203,0.0008080468,0.0021422242,0.0004520286],"domain_scores_gemma":[0.82485634,0.14980574,0.021449726,0.0015353259,0.002005818,0.00034706117],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51517844,0.00017389492,0.008247527,0.00029999146,0.000041931824,0.0001369812,0.0010629427,0.00027993164,0.00236087],"category_scores_gemma":[0.38128853,0.00007881351,0.0013698448,0.00066260673,0.00026619917,0.00029394048,0.000075764336,0.0007896713,0.00031500778],"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":[0.0000255866,0.000067374815,0.84182125,0.000012779397,0.000066589506,0.000022564147,0.000021919912,0.00020288672,0.00004350196,0.0110560935,0.14228076,0.004378688],"study_design_scores_gemma":[0.0003811329,0.00023025338,0.69915587,0.000034971286,0.000061020564,0.000055551962,0.00041112353,0.0011287164,0.0000013998388,0.2793782,0.019070888,0.000090851216],"about_ca_topic_score_codex":0.00014781168,"about_ca_topic_score_gemma":0.00023281157,"teacher_disagreement_score":0.2683221,"about_ca_system_score_codex":0.000014538183,"about_ca_system_score_gemma":0.00022138459,"threshold_uncertainty_score":0.99855113},"labels":[],"label_agreement":null},{"id":"W2004226958","doi":"10.1016/s0895-4356(02)00400-6","title":"Determinants of discontinuation of new courses of antihypertensive medications","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Blood Pressure and Hypertension Studies","field":"Medicine","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":"Institute of Health Economics; Merck Canada Inc. (Canada); Université Laval; The Quebec Population Health Research Network; McGill University; TransCanada (Canada)","funders":"Merck Canada","keywords":"Discontinuation; Medicine; Hazard ratio; Confidence interval; Proportional hazards model; Cohort; Prospective cohort study; Internal medicine; Pharmacy; Cohort study; Antihypertensive drug; Blood pressure; Emergency medicine; Family medicine","score_opus":0.38539944587193625,"score_gpt":0.5079303169838386,"score_spread":0.12253087111190236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004226958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9680238,0.014710371,0.0003914112,0.015711078,0.0005808127,0.00011361811,0.0000072286994,0.0000030457813,0.0004586789],"genre_scores_gemma":[0.98538065,0.007430362,0.00458278,0.0019112526,0.00042930085,4.251782e-7,8.1699454e-7,0.0000065840563,0.00025782984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946367,0.0006148438,0.0042725457,0.000119846445,0.0002197979,0.00013626942],"domain_scores_gemma":[0.9822683,0.011423403,0.004722285,0.00024223645,0.0011684453,0.00017532779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040035374,0.000093774164,0.0035453103,0.000120336335,0.000016128502,3.6315532e-7,0.000121199264,0.00020848257,0.0001279069],"category_scores_gemma":[0.038140416,0.00005853407,0.0005330989,0.0001055852,0.0005039258,0.00005170033,0.000036617388,0.00031043607,0.0000029514533],"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":[0.00031296714,0.00072543474,0.8917297,0.00007672262,0.00087512186,0.000022434202,0.00022841108,0.0000053587205,0.0006511692,0.00022322882,0.064702906,0.04044654],"study_design_scores_gemma":[0.003060422,0.0026041237,0.9807679,0.00066917704,0.0026051595,0.00026686475,0.00028382044,0.00048989145,0.0010740688,0.0010786508,0.0070317267,0.000068168054],"about_ca_topic_score_codex":0.00004456877,"about_ca_topic_score_gemma":0.000010989463,"teacher_disagreement_score":0.089038216,"about_ca_system_score_codex":0.0000019894262,"about_ca_system_score_gemma":0.0001298816,"threshold_uncertainty_score":0.96996176},"labels":[],"label_agreement":null},{"id":"W2004544084","doi":"10.1016/j.jclinepi.2006.02.006","title":"Interrater reliability of measurements of comorbid illness should be reported","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; Queen's University","funders":"Cancer Care Ontario","keywords":"Inter-rater reliability; Intraclass correlation; Medicine; Reliability (semiconductor); Rating scale; Comorbidity; Physical therapy; Psychometrics; Statistics; Psychiatry; Clinical psychology","score_opus":0.7802261328157349,"score_gpt":0.5869670242980766,"score_spread":0.19325910851765837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004544084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735734,0.00019610419,0.008541066,0.012205254,0.0028968835,0.00020632082,0.000010195643,0.000005623547,0.0023651654],"genre_scores_gemma":[0.9925303,0.000052625735,0.005791944,0.0010882826,0.000336233,0.000001971002,0.0000020150997,0.000007775091,0.00018886331],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95847356,0.013246404,0.02447588,0.00063569995,0.002738953,0.00042952268],"domain_scores_gemma":[0.9320835,0.043728016,0.017746508,0.0014126492,0.0047648293,0.00026448784],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23719656,0.00021501684,0.0037759547,0.00022741384,0.000052696167,0.000010654765,0.0012600612,0.00041454064,0.000707714],"category_scores_gemma":[0.32174549,0.00012484074,0.001502039,0.00040454417,0.0010142839,0.0002259124,0.0001841061,0.0008228759,0.0000099208355],"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":[0.0006809109,0.00097392546,0.9587648,0.00002925989,0.000102891834,0.000007685612,0.000043225613,0.0018344288,0.00088863826,0.0002822942,0.030881494,0.0055104685],"study_design_scores_gemma":[0.0015279579,0.0013367429,0.8491168,0.00014163667,0.00011793443,0.000029337918,0.00014125096,0.00031808615,0.0027449494,0.12697586,0.017384084,0.00016537376],"about_ca_topic_score_codex":0.0001835824,"about_ca_topic_score_gemma":0.000060767903,"teacher_disagreement_score":0.12669358,"about_ca_system_score_codex":0.000054714274,"about_ca_system_score_gemma":0.00027838617,"threshold_uncertainty_score":0.7854667},"labels":[],"label_agreement":null},{"id":"W2004635095","doi":"10.1016/j.jclinepi.2011.02.002","title":"Rasch analysis informed modifications to the Work Instability Scale for Rheumatoid Arthritis for use in work-related upper limb disorders","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Workplace Health and Well-being","field":"Health Professions","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":"Mount Sinai Hospital; University of Toronto; University Health Network; Institute for Work & Health; Public Health Ontario; St. Michael's Hospital","funders":"Workplace Safety and Insurance Board","keywords":"Rasch model; Guttman scale; Differential item functioning; Physical therapy; Psychology; Rating scale; Polytomous Rasch model; Statistics; Psychometrics; Item response theory; Clinical psychology; Medicine; Mathematics; Developmental psychology","score_opus":0.2727562057311985,"score_gpt":0.5167018562507215,"score_spread":0.243945650519523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004635095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9119649,0.00048620437,0.049626842,0.033535294,0.0018162744,0.0022259688,0.00002256086,0.00002263929,0.00029932128],"genre_scores_gemma":[0.9533119,0.0044414266,0.03383931,0.0074447864,0.0002715671,0.0004740739,0.000019995334,0.000026774975,0.00017014396],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98443615,0.005671435,0.008385262,0.00037467416,0.00014085925,0.0009916446],"domain_scores_gemma":[0.8784705,0.116966896,0.0029284477,0.00056413875,0.00047662738,0.00059342745],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039393622,0.00020983926,0.0023861236,0.00040408442,0.00056323205,0.0000061853207,0.0004795446,0.00081160833,0.00017140155],"category_scores_gemma":[0.13035291,0.00013860787,0.0012189939,0.001271817,0.00022834801,0.00021146829,0.00008996222,0.0019618175,0.000045259596],"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":[0.0027745776,0.00025088713,0.9633944,0.000037766655,0.00018535327,2.715883e-7,0.0014904126,0.0009324307,5.8961422e-8,0.001505908,0.0093429545,0.020084955],"study_design_scores_gemma":[0.0024105352,0.00047758076,0.94448626,0.00033871908,0.000102303326,7.936023e-7,0.0006744062,0.00082635524,1.8653289e-7,0.013254219,0.037288014,0.00014059884],"about_ca_topic_score_codex":0.00028694764,"about_ca_topic_score_gemma":0.0057551493,"teacher_disagreement_score":0.11129546,"about_ca_system_score_codex":0.00012445307,"about_ca_system_score_gemma":0.0008644301,"threshold_uncertainty_score":0.9891464},"labels":[],"label_agreement":null},{"id":"W2004859490","doi":"10.1016/j.jclinepi.2008.08.013","title":"The practicalists' response","year":2009,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","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":"McMaster University; Western University","funders":"","keywords":"Viewpoints; Agreement; Psychology; Epistemology; Physics; Philosophy; Linguistics","score_opus":0.2176724633977542,"score_gpt":0.5148065334182115,"score_spread":0.2971340700204573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004859490","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":[0.003215151,0.0020357498,0.00018217742,0.99109566,0.002187267,0.00019912393,0.0000059427625,0.000014017248,0.0010649113],"genre_scores_gemma":[0.0018310199,0.004576063,0.00072736497,0.96649456,0.023926353,0.0000028620348,0.000016528376,0.0000320635,0.0023931882],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9739622,0.018575942,0.0060315165,0.0003359647,0.00053093414,0.0005634829],"domain_scores_gemma":[0.84643036,0.14719632,0.004502526,0.0008569817,0.00058093056,0.00043287303],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04593033,0.00028754125,0.003857041,0.00011026987,0.00010252095,0.000017693208,0.00043077974,0.0015108929,0.00016263618],"category_scores_gemma":[0.32991654,0.00014653329,0.0040099346,0.00008896378,0.000637994,0.00005742052,0.000050806168,0.0077356636,0.00009795438],"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":[0.0033716434,0.00012774758,0.012099225,0.000029392484,0.0006508456,0.000915133,0.0000035150715,0.0000010404468,6.2869594e-7,0.00008743707,0.9645651,0.018148297],"study_design_scores_gemma":[0.0012114104,0.002120627,0.13686442,0.00019707141,0.00082389626,0.003335583,0.000010076671,0.000008169369,4.938427e-7,0.0021432631,0.85317326,0.000111718786],"about_ca_topic_score_codex":0.0000029261184,"about_ca_topic_score_gemma":7.838517e-7,"teacher_disagreement_score":0.2839862,"about_ca_system_score_codex":0.00006080032,"about_ca_system_score_gemma":0.0012269007,"threshold_uncertainty_score":0.99978536},"labels":[],"label_agreement":null},{"id":"W2004979239","doi":"10.1016/j.jclinepi.2014.12.010","title":"A statistical model to predict one-year risk of death in patients with cystic fibrosis","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cystic Fibrosis Research Advances","field":"Medicine","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":"St. Michael's Hospital; McGill University; Ottawa Hospital; University of Ottawa","funders":"Cystic Fibrosis Canada; Cystic Fibrosis Foundation","keywords":"Medicine; Cystic fibrosis; Exacerbation; Cystic fibrosis-related diabetes; Internal medicine; Proportional hazards model; Body mass index; National Death Index; Intensive care medicine; Obesity; Hazard ratio; Confidence interval; Impaired glucose tolerance","score_opus":0.11424798781292954,"score_gpt":0.46082826923929454,"score_spread":0.346580281426365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004979239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76722693,0.000037363032,0.23144451,0.00077351363,0.00008631569,0.00023833978,0.00006070738,0.0000047808257,0.0001275465],"genre_scores_gemma":[0.71320206,0.00006121814,0.2861856,0.00036623797,0.00014675627,0.000003426993,0.000005845021,0.000014233925,0.0000145981485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924966,0.0026343914,0.0035706807,0.00029447235,0.0005532475,0.00045058446],"domain_scores_gemma":[0.9574889,0.03918615,0.0015761493,0.00036352756,0.00059287285,0.00079239864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013356191,0.00015684996,0.0026403072,0.0002342667,0.000019874293,0.0000027819278,0.00021774197,0.00019785146,0.000056681016],"category_scores_gemma":[0.26209474,0.000100750716,0.00023165008,0.00017570802,0.00030169613,0.00007314268,0.00007906764,0.0010692604,0.000013928805],"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":[0.013422843,0.0007038196,0.96993184,0.00009271136,0.00012628564,0.0000051662573,0.000017238679,0.0078468425,0.000013162942,0.001161487,0.0007960037,0.00588258],"study_design_scores_gemma":[0.0056645335,0.014502966,0.94797015,0.0004931572,0.00015405515,0.0000058674077,0.0000059851122,0.022165315,0.000005067834,0.008711286,0.00024115604,0.00008046855],"about_ca_topic_score_codex":0.00004087982,"about_ca_topic_score_gemma":0.000017581746,"teacher_disagreement_score":0.24873853,"about_ca_system_score_codex":0.00006511597,"about_ca_system_score_gemma":0.0003179284,"threshold_uncertainty_score":0.74412096},"labels":[],"label_agreement":null},{"id":"W2005159922","doi":"10.1016/j.jclinepi.2011.08.002","title":"Administrative database research has unique characteristics that can risk biased results","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":235,"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; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Observational study; Database; Computer science; MEDLINE; Health care; Medical prescription; Data science; Medicine; Data mining; Nursing; Political science","score_opus":0.978490436321102,"score_gpt":0.764329112763572,"score_spread":0.21416132355753004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005159922","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":[0.00015434083,0.9594496,0.0025800392,0.013436051,0.010841578,0.002844157,0.0034870699,0.000053995976,0.0071532014],"genre_scores_gemma":[0.00014061018,0.98615134,0.0034411848,0.0032911035,0.0054889363,0.00006221623,0.0005905774,0.000047698955,0.0007863054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8311744,0.13946371,0.026784694,0.0005556643,0.0006775964,0.0013439379],"domain_scores_gemma":[0.5430184,0.40514407,0.04590332,0.001404456,0.0022492176,0.0022805536],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.37068483,0.00050477346,0.011993697,0.00066539994,0.0011007447,0.00001180597,0.001274529,0.003538831,0.0006433549],"category_scores_gemma":[0.675068,0.00030413954,0.0014651233,0.0004193241,0.0010964833,0.00015090434,0.00034611535,0.027121274,0.00065427524],"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":[0.0010588589,0.00018269422,0.003839236,0.014341881,0.0002596944,0.00008840746,0.0006511527,8.4206526e-8,2.1285378e-9,0.0029717654,0.23582265,0.7407836],"study_design_scores_gemma":[0.0011059392,0.0015558613,0.0029776653,0.03037403,0.0003704326,0.000046879082,0.00018021087,0.00003129755,1.1201565e-8,0.0015962366,0.96154684,0.00021458538],"about_ca_topic_score_codex":0.0004242925,"about_ca_topic_score_gemma":0.00018041283,"teacher_disagreement_score":0.740569,"about_ca_system_score_codex":0.00035571097,"about_ca_system_score_gemma":0.017790416,"threshold_uncertainty_score":0.99994105},"labels":[],"label_agreement":null},{"id":"W2005679951","doi":"10.1016/j.jclinepi.2010.08.006","title":"Development quality criteria to evaluate nontherapeutic studies of incidence, prevalence, or risk factors of chronic diseases: pilot study of new checklists","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":133,"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 Canada","funders":"","keywords":"Medicine; Incidence (geometry); Environmental health; Risk factor; Epidemiology; Quality (philosophy); Internal medicine","score_opus":0.9407859623052889,"score_gpt":0.725828573631878,"score_spread":0.21495738867341085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005679951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99277174,0.0019992257,0.0024727867,0.00033848468,0.0015710989,0.0007967838,0.000017712691,0.0000013855052,0.00003076696],"genre_scores_gemma":[0.9856935,0.00063962897,0.012628477,0.00015880297,0.000264214,0.000009054399,4.2393853e-7,0.000009390721,0.0005964678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7864877,0.10925693,0.09684019,0.0012695392,0.005593342,0.0005522803],"domain_scores_gemma":[0.5730166,0.29170135,0.12061503,0.0046873046,0.008834504,0.0011452659],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48361266,0.0003725654,0.017712649,0.00046761776,0.0000714086,0.000022052887,0.0026158749,0.00015515754,0.0032562572],"category_scores_gemma":[0.7393859,0.00015329647,0.0022876838,0.0008928543,0.00042299763,0.0001896456,0.00035982093,0.0006811529,0.00004662833],"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":[0.00068827457,0.0016686468,0.97050023,0.00030886248,0.002054787,0.000002302711,0.0017017741,0.00020020297,0.00020344093,0.00007172634,0.0036704098,0.018929336],"study_design_scores_gemma":[0.0010759789,0.007311787,0.98251367,0.00021837313,0.0011877397,0.0000044354324,0.0014318335,0.00026055812,0.000027574824,0.0037946524,0.0020317663,0.0001416477],"about_ca_topic_score_codex":0.00009836874,"about_ca_topic_score_gemma":0.00080790947,"teacher_disagreement_score":0.25577328,"about_ca_system_score_codex":0.00004600615,"about_ca_system_score_gemma":0.001358497,"threshold_uncertainty_score":0.9976549},"labels":[],"label_agreement":null},{"id":"W2006373459","doi":"10.1016/j.jclinepi.2004.08.005","title":"A cohort study found the RAND-12 and Health Utilities Index Mark 3 demonstrated construct validity in high-risk primary care patients","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","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 Alberta; Institute of Health Economics","funders":"","keywords":"Health Utilities Index; Context (archaeology); Construct validity; Medicine; Cohort; Gerontology; Health care; Primary care; Mental health; Psychometrics; Psychology; Family medicine; Clinical psychology; Psychiatry; Health related quality of life; Pathology; Disease","score_opus":0.21399756673573106,"score_gpt":0.47436578035422017,"score_spread":0.2603682136184891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006373459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911125,0.0012207208,0.000087300024,0.0047413646,0.0005692054,0.0011223924,0.00001652427,0.000013859111,0.0011161723],"genre_scores_gemma":[0.99363196,0.0021121153,0.0004533316,0.0032547438,0.00046965538,0.000010324661,0.000018647166,0.000013307272,0.000035900983],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9890933,0.0056437845,0.0041468684,0.00034898976,0.00034569536,0.0004213418],"domain_scores_gemma":[0.9872765,0.009426259,0.0023993244,0.00034593345,0.00022157513,0.00033039518],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020068865,0.00022489285,0.0025825594,0.00014207525,0.000106054635,0.000014905698,0.00019794503,0.00018254097,0.000070911556],"category_scores_gemma":[0.008858413,0.0001384486,0.00029055148,0.00012337473,0.00073983026,0.00013566251,0.00011869132,0.0012685009,0.0000031926827],"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":[0.0015144494,0.00068187073,0.96522945,0.00013563891,0.00035730508,0.000029509712,0.00014542752,0.00007102635,2.159656e-8,0.00016954898,0.00205166,0.029614102],"study_design_scores_gemma":[0.0128398035,0.002425956,0.97997195,0.00015387774,0.00032080692,0.000026712618,0.0017294643,0.00017268334,3.8995456e-8,0.0013825021,0.0008787117,0.000097500146],"about_ca_topic_score_codex":0.0005615503,"about_ca_topic_score_gemma":0.0007734048,"teacher_disagreement_score":0.029516602,"about_ca_system_score_codex":0.00027991884,"about_ca_system_score_gemma":0.0009540014,"threshold_uncertainty_score":0.9994904},"labels":[],"label_agreement":null},{"id":"W2007157716","doi":"10.1016/j.jclinepi.2013.04.018","title":"Diagnostic probability function for acute coronary heart disease garnered from experts' tacit knowledge","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"McGill University","funders":"","keywords":"Tacit knowledge; Diagnostic test; Medicine; Set (abstract data type); Intensive care medicine; Computer science; Emergency medicine; Knowledge management","score_opus":0.1941329512350133,"score_gpt":0.49129977954003595,"score_spread":0.2971668283050226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007157716","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":[0.95011646,0.0027165527,0.009060038,0.03364207,0.003274678,0.0009744431,0.000040922925,0.000038860686,0.00013595818],"genre_scores_gemma":[0.9678692,0.00078569155,0.012103863,0.014854445,0.0036483207,0.00013533888,0.00008062629,0.000033552315,0.00048891205],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.991865,0.0020996237,0.004812292,0.0005293893,0.00020004633,0.0004936613],"domain_scores_gemma":[0.28976566,0.70340794,0.0024045403,0.0007920811,0.00124827,0.0023815092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008122078,0.00026230118,0.0030963377,0.000069958965,0.00007132925,0.000011198983,0.00019934234,0.0005033882,0.0008015032],"category_scores_gemma":[0.7989446,0.00017617081,0.00151045,0.000094371724,0.0004541878,0.00013649078,0.000075985154,0.0008071524,0.000166975],"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":[0.0037614503,0.0017373329,0.816569,0.000027140484,0.00044754604,0.000040484007,0.00002110915,0.000020206113,0.000020156851,0.00029073746,0.14771184,0.029353034],"study_design_scores_gemma":[0.0045290412,0.0037859096,0.8971776,0.00078668544,0.0011298602,0.000061144936,0.000021024041,0.0007984949,0.0000025282552,0.08104906,0.010507412,0.00015123094],"about_ca_topic_score_codex":0.000053961743,"about_ca_topic_score_gemma":0.0000051562774,"teacher_disagreement_score":0.7908225,"about_ca_system_score_codex":0.000065306616,"about_ca_system_score_gemma":0.0006094429,"threshold_uncertainty_score":0.87758976},"labels":[],"label_agreement":null},{"id":"W2007312769","doi":"10.1016/j.jclinepi.2011.08.008","title":"Combining longitudinal studies showed prevalence of disease differed throughout older adulthood","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":6,"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 Institutes of Health Research","keywords":"Demography; Medicine; Longitudinal study; Ageing; Disease; Gerontology; Prevalence; Epidemiology; Pooling; Age groups; Young adult; Pathology; Internal medicine","score_opus":0.5355551850532341,"score_gpt":0.5792510658510168,"score_spread":0.04369588079778275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007312769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9695375,0.01209385,0.0008643086,0.01266248,0.0036266758,0.00021015525,0.000011693883,0.000017506945,0.0009758068],"genre_scores_gemma":[0.9726593,0.021007076,0.0023601395,0.0029875264,0.00077388907,0.0000035679918,3.2857042e-7,0.000009128017,0.00019903481],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98854566,0.006094575,0.004214421,0.00024271522,0.00032827712,0.00057435443],"domain_scores_gemma":[0.9652316,0.029915826,0.0032827936,0.00024299664,0.00059936196,0.00072744174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023603747,0.00015264006,0.0022534572,0.00006599588,0.00020114565,0.000003981872,0.000507364,0.00023719763,0.00026295832],"category_scores_gemma":[0.118123606,0.000107012,0.00070693437,0.00011321452,0.0013083048,0.00024219179,0.00009991711,0.0006316392,0.0000066844873],"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":[0.00042334147,0.00025724134,0.96314985,0.0004265451,0.00013227198,0.000018227782,0.0036553727,0.0000020317716,7.645636e-8,0.02703133,0.0010605664,0.0038431452],"study_design_scores_gemma":[0.00082448113,0.00037690616,0.9695318,0.00042861677,0.0001410313,0.0000041021867,0.0023036427,0.000011603215,0.0000010007152,0.025491584,0.0007855086,0.00009977114],"about_ca_topic_score_codex":0.00022972091,"about_ca_topic_score_gemma":0.00010529037,"teacher_disagreement_score":0.09451986,"about_ca_system_score_codex":0.00004520779,"about_ca_system_score_gemma":0.0005565702,"threshold_uncertainty_score":0.8893048},"labels":[],"label_agreement":null},{"id":"W2007814375","doi":"10.1016/s0895-4356(03)00090-8","title":"International differences in major depression prevalence: What do they mean?","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":35,"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":"Depression (economics); Set (abstract data type); International comparisons; Medicine; Prevalence; Psychiatry; Epidemiology; Environmental health; Psychology; Economics; Pathology; Computer science","score_opus":0.2911796696833357,"score_gpt":0.5620994203499656,"score_spread":0.27091975066662993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007814375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9718667,0.007043204,0.00012939898,0.0025903366,0.009679375,0.00016781747,0.0000022857803,0.000006143351,0.008514728],"genre_scores_gemma":[0.98607904,0.010148546,0.0010092679,0.0015642819,0.00056074763,0.000011498732,0.0000014431214,0.000008729068,0.00061647507],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98965424,0.005983009,0.0035022967,0.00031242293,0.00019091472,0.00035712955],"domain_scores_gemma":[0.9832309,0.014193199,0.0020514508,0.00021520855,0.00008755322,0.0002217202],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014276229,0.0001529868,0.0012576132,0.00014927094,0.00004794938,0.000017934615,0.00046014585,0.00034901203,0.00275611],"category_scores_gemma":[0.007228782,0.00009571644,0.00031477632,0.000067545836,0.0001235627,0.00032650246,0.000043546668,0.0007954251,0.000087582914],"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":[0.0005022708,0.0005449704,0.8958647,0.000016575468,0.000081539925,0.000057075715,0.00021152623,0.00000250737,0.0000015821983,0.0045805667,0.000766601,0.09737009],"study_design_scores_gemma":[0.002927018,0.0005180773,0.961697,0.00036894123,0.000032683285,0.00011915612,0.00053729035,0.000014706844,0.0000054547145,0.029893765,0.00378987,0.000096030235],"about_ca_topic_score_codex":0.000035814403,"about_ca_topic_score_gemma":0.000025330664,"teacher_disagreement_score":0.09727406,"about_ca_system_score_codex":0.000042846612,"about_ca_system_score_gemma":0.00004340788,"threshold_uncertainty_score":0.99815553},"labels":[],"label_agreement":null},{"id":"W2008044240","doi":"10.1016/j.jclinepi.2007.11.014","title":"Bootstrap model selection had similar performance for selecting authentic and noise variables compared to backward variable elimination: a simulation study","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":49,"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":"Statistics; Feature selection; Resampling; Regression analysis; Variables; Mathematics; Selection (genetic algorithm); Monte Carlo method; Outcome (game theory); Linear regression; Variable (mathematics); Bootstrap aggregating; Model selection; Regression; Computer science; Econometrics; Artificial intelligence","score_opus":0.5966149628403579,"score_gpt":0.5651412350333136,"score_spread":0.03147372780704427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008044240","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":[0.4217852,0.000010482584,0.57739425,0.00028232211,0.00018791338,0.0002836433,0.0000033856911,0.000011168868,0.000041621628],"genre_scores_gemma":[0.52175224,0.000019157646,0.4777045,0.00025718976,0.00020700859,0.0000091817965,5.096482e-7,0.000010015143,0.000040208986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942614,0.0016762118,0.0032491405,0.00029657432,0.00019065688,0.00032604966],"domain_scores_gemma":[0.9383258,0.059013776,0.0015004574,0.00013839574,0.0007835966,0.00023793435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018351087,0.00017704265,0.0016356873,0.00011827054,0.00022638918,0.0000114032,0.00015155812,0.00020029876,0.000026958469],"category_scores_gemma":[0.13394658,0.00014098057,0.00015274368,0.00019630093,0.00008556472,0.00013796396,0.00004062908,0.0004894332,0.0000015126441],"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":[0.0023938597,0.0020268133,0.2373572,0.00034657613,0.00041348982,0.0000052592754,0.001331447,0.6921391,0.00017941157,0.04554539,0.0023802584,0.015881184],"study_design_scores_gemma":[0.0011703835,0.0019368803,0.04506295,0.0000676635,0.00014708488,0.000037865175,0.000053817086,0.81168574,0.000009075625,0.1395942,0.00011355104,0.00012077138],"about_ca_topic_score_codex":0.0000057154007,"about_ca_topic_score_gemma":0.000002565704,"teacher_disagreement_score":0.19229424,"about_ca_system_score_codex":0.00004207209,"about_ca_system_score_gemma":0.00018566979,"threshold_uncertainty_score":0.87334853},"labels":[],"label_agreement":null},{"id":"W2008212615","doi":"10.1016/j.jclinepi.2005.12.011","title":"Summaries of findings, descriptions of interventions, and information about adverse effects would make reviews more informative","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Institute for Work & Health","funders":"","keywords":"Psychological intervention; Medicine; Adverse effect; MEDLINE; Systematic review; Relevance (law); Presentation (obstetrics); Quality (philosophy); Family medicine; Medical physics; Internal medicine; Surgery; Nursing","score_opus":0.8865150227928861,"score_gpt":0.6769721907125935,"score_spread":0.20954283208029256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008212615","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":[0.000207187,0.97976,0.016747147,0.00025130832,0.0010352241,0.0012582557,0.00011434699,0.0000014941987,0.00062506465],"genre_scores_gemma":[0.000047996993,0.98651034,0.012462095,0.0003569884,0.00015022751,0.000026046906,0.00005467136,0.000008859526,0.0003827987],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.74576294,0.08942704,0.16159068,0.0005411864,0.0022687213,0.00040946156],"domain_scores_gemma":[0.59390205,0.18119268,0.21853667,0.0024737457,0.0034933782,0.00040147002],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.44186476,0.0005446646,0.042586062,0.0013934216,0.00007315728,0.00006197051,0.0017076174,0.0011552982,0.00042258453],"category_scores_gemma":[0.68709546,0.00024194713,0.01959091,0.0010817988,0.0006651589,0.0010172796,0.0002887434,0.0018541297,0.00016345968],"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":[0.000015974148,0.000078057965,0.006311997,0.027492817,0.0008435548,0.0000017000065,0.00010967123,0.000013142955,1.1090191e-8,0.004095404,0.059355438,0.90168226],"study_design_scores_gemma":[0.00028616388,0.00029954533,0.009562493,0.022758694,0.003339811,0.00006468141,0.000084223546,0.00007042134,4.1870745e-8,0.002332651,0.96105003,0.000151223],"about_ca_topic_score_codex":0.0000111301715,"about_ca_topic_score_gemma":0.000011295584,"teacher_disagreement_score":0.9016946,"about_ca_system_score_codex":0.000043270313,"about_ca_system_score_gemma":0.0003457527,"threshold_uncertainty_score":0.99022764},"labels":[],"label_agreement":null},{"id":"W2008369163","doi":"10.1016/s0895-4356(02)00435-3","title":"A critical look at transition ratings","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":299,"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":"Medical Research Council","keywords":"Correlation; Regression analysis; Regression; Statistics; Rating scale; Psychology; Explained variation; Quality of life (healthcare); Medicine; Clinical psychology; Mathematics","score_opus":0.806608978472828,"score_gpt":0.6067383126335734,"score_spread":0.1998706658392546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008369163","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":[0.3284996,0.0070771966,0.050782666,0.6022668,0.003929764,0.00026215758,0.00006194858,0.000028463335,0.00709144],"genre_scores_gemma":[0.8247302,0.0014722149,0.024428153,0.14464378,0.003870892,0.000010553532,0.000004477913,0.00003256879,0.0008071201],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9716789,0.0050760144,0.022283854,0.00040638348,0.00008398665,0.00047085783],"domain_scores_gemma":[0.91408163,0.07467158,0.010119559,0.00036136166,0.00020683845,0.00055904797],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.13899925,0.0001611514,0.0038151108,0.00020246879,0.00012919519,0.000014242253,0.00029068056,0.00045373224,0.003946167],"category_scores_gemma":[0.33401126,0.00016658372,0.00080803316,0.00009446913,0.00033436232,0.0004122336,0.000035199686,0.0007436393,0.0029737276],"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":[0.00016151274,0.0006008742,0.23617668,0.00028301164,0.00022541393,0.000026974812,0.0011365443,0.00044899975,0.0000028252655,0.2663156,0.49259418,0.0020273682],"study_design_scores_gemma":[0.004859862,0.0023782402,0.17297463,0.00033378915,0.00007023949,0.000607725,0.00043522124,0.06804696,0.0000026602595,0.38277915,0.36679608,0.000715435],"about_ca_topic_score_codex":0.000037463084,"about_ca_topic_score_gemma":0.000012811201,"teacher_disagreement_score":0.49623066,"about_ca_system_score_codex":0.00022705847,"about_ca_system_score_gemma":0.00006207966,"threshold_uncertainty_score":0.99780256},"labels":[],"label_agreement":null},{"id":"W2008821955","doi":"10.1016/j.jclinepi.2010.05.002","title":"Prospectively screening for eligible patients was inaccurate in predicting patient recruitment of orthopedic randomized trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Hip and Femur Fractures","field":"Medicine","cited_by":16,"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":"Canada Research Chairs","keywords":"Medicine; Interquartile range; Clinical trial; Randomized controlled trial; Confidence interval; Prospective cohort study; Retrospective cohort study; Orthopedic surgery; Trial registration; Surgery; Pediatrics; Internal medicine","score_opus":0.4621486157438112,"score_gpt":0.5629279845803274,"score_spread":0.10077936883651623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008821955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859013,0.00030146888,0.0068843947,0.0023146023,0.0017788647,0.0025655276,0.0000136454855,0.000007806749,0.00023242278],"genre_scores_gemma":[0.96754295,0.00041068633,0.029654937,0.0012922031,0.00096512196,0.000080221216,0.000009211837,0.000018478006,0.000026223375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98216844,0.005491711,0.011389526,0.0002866213,0.00028495592,0.0003787781],"domain_scores_gemma":[0.85342586,0.13051859,0.014038157,0.0003177418,0.0012348391,0.00046484466],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08338629,0.00019291574,0.0071425713,0.00026258134,0.00003743656,0.0000034602856,0.00013591009,0.00046549115,0.000046070854],"category_scores_gemma":[0.5483271,0.00011218351,0.0015919361,0.00013476833,0.00027200827,0.000094399955,0.00004522836,0.0014292944,0.0000011687945],"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":[0.12279671,0.0006583683,0.8074755,0.00006563453,0.0003605184,0.000009885703,0.00022189543,0.000057849527,0.000090570495,0.00040287734,0.0006027595,0.0672574],"study_design_scores_gemma":[0.28745037,0.0069996985,0.68732524,0.000698487,0.00072928256,0.000041401407,0.00011899304,0.0016205251,0.00032632396,0.008830458,0.005687875,0.00017131111],"about_ca_topic_score_codex":0.00003576358,"about_ca_topic_score_gemma":0.000019313773,"teacher_disagreement_score":0.4649408,"about_ca_system_score_codex":0.000027339252,"about_ca_system_score_gemma":0.00028987738,"threshold_uncertainty_score":0.9438467},"labels":[],"label_agreement":null},{"id":"W2008967730","doi":"10.1016/j.jclinepi.2007.07.009","title":"Comorbidity information in older patients at an emergency visit: self-report vs. administrative data had poor agreement but similar predictive validity","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Mary's Hospital; McGill University","funders":"Faculty of Medicine, McGill University","keywords":"Intraclass correlation; Medicine; Comorbidity; Predictive validity; Confidence interval; Emergency department; Receiver operating characteristic; National Comorbidity Survey; Gerontology; Demography; Psychiatry; Psychometrics; Clinical psychology; Internal medicine","score_opus":0.3548823099867327,"score_gpt":0.5032012387152897,"score_spread":0.14831892872855695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008967730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902986,0.00025275783,0.0009393496,0.0044670627,0.0026007176,0.0004384891,0.00018418007,0.000018278168,0.00080051564],"genre_scores_gemma":[0.9819278,0.011512879,0.0023558822,0.0026759712,0.000931573,0.0000071454656,0.0005126434,0.000010367971,0.000065743596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99023074,0.0021317247,0.006375349,0.00037982952,0.00048909103,0.0003932933],"domain_scores_gemma":[0.9910434,0.0026595106,0.004000381,0.0006572365,0.0011759849,0.000463526],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010771907,0.0002621469,0.002167712,0.0001284215,0.0001575043,0.0000017435069,0.00037595187,0.00035138667,0.0003636611],"category_scores_gemma":[0.042859666,0.00019155456,0.00040280214,0.0001567499,0.0002488668,0.0007961852,0.0003239613,0.001011183,0.000023015855],"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":[0.0012296619,0.0012881368,0.8948387,0.00004700387,0.00036826424,0.00030460602,0.00045440355,0.000018877283,0.0000013067986,0.000011368008,0.100619055,0.0008185956],"study_design_scores_gemma":[0.0027783846,0.0045797797,0.96865904,0.000074487645,0.0002587687,0.00032957183,0.00019990916,0.0007477458,0.000012372158,0.00023108681,0.0219731,0.00015576843],"about_ca_topic_score_codex":0.000060603266,"about_ca_topic_score_gemma":0.000094413124,"teacher_disagreement_score":0.07864596,"about_ca_system_score_codex":0.00013831296,"about_ca_system_score_gemma":0.00039954766,"threshold_uncertainty_score":0.96520275},"labels":[],"label_agreement":null},{"id":"W2009208932","doi":"10.1016/j.jclinepi.2006.04.002","title":"Exploring design-related bias in clinical studies on receptor genetic polymorphism of hypertension","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Renin-Angiotensin System Studies","field":"Medicine","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":"St. Joseph’s Healthcare Hamilton; McMaster University; St. Joseph's Hospital","funders":"","keywords":"Pharmacogenetics; Candidate gene; Allele; Bioinformatics; Medicine; Meta-analysis; Selection bias; Clinical study design; Placebo; Genetics; Gene; Clinical trial; Internal medicine; Computational biology; Genotype; Biology; Pathology","score_opus":0.9141237260434599,"score_gpt":0.590891529207405,"score_spread":0.323232196836055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009208932","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":[0.015660744,0.97357565,0.000061831095,0.0014966193,0.008207326,0.00091762026,0.000004677915,0.000019997118,0.000055534474],"genre_scores_gemma":[0.0010127204,0.9827713,0.0124621745,0.0004863011,0.002978948,0.000023155031,0.000006475402,0.000103031096,0.00015591683],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93606794,0.02646121,0.035297025,0.0008970418,0.00058386044,0.000692944],"domain_scores_gemma":[0.8180395,0.15861973,0.021069475,0.00086514733,0.0009858842,0.00042026624],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.061323848,0.0008215488,0.0329579,0.0009802195,0.000049145285,0.000002390565,0.0004394,0.0018323355,0.000014390994],"category_scores_gemma":[0.26793832,0.00048726966,0.0061310935,0.000613745,0.0009987858,0.00006926353,0.00021728373,0.003995092,0.00009087791],"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":[0.0010620881,0.0010456991,0.04740255,0.003047824,0.0055815647,0.0013117227,0.000057097026,0.00014734708,0.0000010287972,0.00006800821,0.019371927,0.92090315],"study_design_scores_gemma":[0.01065207,0.021832665,0.23507991,0.24471208,0.013615179,0.00494054,0.000107174536,0.000100984464,0.0000028210077,0.0012545725,0.4663928,0.0013092161],"about_ca_topic_score_codex":0.000033545628,"about_ca_topic_score_gemma":0.0000043598316,"teacher_disagreement_score":0.91959393,"about_ca_system_score_codex":0.00022122085,"about_ca_system_score_gemma":0.0008982447,"threshold_uncertainty_score":0.9997579},"labels":[],"label_agreement":null},{"id":"W2009264530","doi":"10.1016/j.jclinepi.2004.06.006","title":"An analysis of data from two general health surveys found that increased incidence and duration contributed to elevated prevalence of major depression in persons with chronic medical conditions","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac Health and Mental Health","field":"Medicine","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":"University of Calgary","funders":"","keywords":"Incidence (geometry); Depression (economics); Medicine; Demography; Epidemiology; Internal medicine","score_opus":0.189941625419753,"score_gpt":0.549398949946343,"score_spread":0.35945732452658996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009264530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9778558,0.0014041986,0.011390474,0.008250884,0.00008807647,0.00038187797,0.00062109606,0.00000476657,0.0000027984288],"genre_scores_gemma":[0.9869502,0.0022179226,0.006218417,0.00367224,0.00037835946,0.0000037081484,0.00054867583,0.000007617618,0.0000028306952],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9866625,0.0082005765,0.0039430093,0.00038903402,0.00044723114,0.0003576299],"domain_scores_gemma":[0.983319,0.012027439,0.002600128,0.00049061753,0.00025458948,0.0013082662],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0376725,0.00013322689,0.0027328043,0.0003311284,0.00004651938,0.0000020896898,0.00022939294,0.00022446467,0.00014691411],"category_scores_gemma":[0.017069602,0.00009350089,0.00016179515,0.0004156571,0.00025399966,0.00022374543,0.00006702886,0.0006504196,7.2190994e-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":[0.0016497709,0.0003065104,0.99204874,0.00014602914,0.00021931976,0.000016423777,0.0000553968,0.00029306582,0.00022815132,0.000015103394,0.00017872434,0.0048427396],"study_design_scores_gemma":[0.0052555893,0.0021491852,0.94640017,0.00062104856,0.00053084,0.00008251619,0.000040554987,0.044762008,0.000026679816,0.000026075271,0.000043470332,0.00006188021],"about_ca_topic_score_codex":0.009553852,"about_ca_topic_score_gemma":0.019960076,"teacher_disagreement_score":0.045648612,"about_ca_system_score_codex":0.00020707682,"about_ca_system_score_gemma":0.002554121,"threshold_uncertainty_score":0.9979231},"labels":[],"label_agreement":null},{"id":"W2009326492","doi":"10.1016/j.jclinepi.2011.04.014","title":"GRADE guidelines: 8. Rating the quality of evidence—indirectness","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1855,"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 Agency for Drugs and Technologies in Health; McMaster University","funders":"","keywords":"Psychological intervention; Presumption; Intervention (counseling); Psychology; Quality (philosophy); Outcome (game theory); Medicine; Psychiatry","score_opus":0.9831617344430363,"score_gpt":0.7198006129394486,"score_spread":0.2633611215035877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009326492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7111171,0.013518768,0.04544884,0.22078025,0.0057023135,0.0005269612,0.000039167404,0.0000210357,0.0028455604],"genre_scores_gemma":[0.8980152,0.0027133657,0.054528445,0.04178186,0.0026497382,0.000014099505,0.000001668898,0.00002771497,0.0002679006],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93090844,0.014622324,0.053334653,0.00046654904,0.00017203933,0.00049597706],"domain_scores_gemma":[0.7341378,0.19790201,0.065564156,0.0010531669,0.00091849273,0.0004243984],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4894687,0.00017704259,0.004922801,0.00018215418,0.000107232154,0.0000075744983,0.00085077406,0.00035874522,0.000473748],"category_scores_gemma":[0.6730403,0.0001209444,0.0009933733,0.00017831706,0.00044568174,0.00037996468,0.00008788788,0.000779913,0.00021406781],"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":[0.00011942934,0.00014933833,0.8674528,0.0001652256,0.00020420522,0.0000013537573,0.0007284978,0.00012258744,0.0000021454614,0.09966017,0.029615676,0.0017785607],"study_design_scores_gemma":[0.00084830093,0.0004317546,0.8037723,0.00032993694,0.000025572399,0.000027366319,0.00083271036,0.0009819326,0.0000082729,0.17623857,0.016310252,0.00019308015],"about_ca_topic_score_codex":0.0009344367,"about_ca_topic_score_gemma":0.00009939416,"teacher_disagreement_score":0.19677067,"about_ca_system_score_codex":0.00009269932,"about_ca_system_score_gemma":0.00038912304,"threshold_uncertainty_score":0.52569944},"labels":[],"label_agreement":null},{"id":"W2009687712","doi":"10.1016/j.jclinepi.2015.03.002","title":"Elements of informed consent and decision quality were poorly correlated in informed consent documents","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; McGill University; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Conformity; Concordance; Quality (philosophy); Variance (accounting); Informed consent; Psychology; Scale (ratio); Moderation; Medicine; Family medicine; Statistics; Social psychology; Business; Accounting; Alternative medicine; Mathematics; Internal medicine","score_opus":0.8929962363137206,"score_gpt":0.7650794805225375,"score_spread":0.1279167557911831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009687712","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":[0.017254135,0.9745885,0.00013797583,0.0021984254,0.002459439,0.0016533022,0.000056767723,0.0000114011045,0.00164006],"genre_scores_gemma":[0.0005522325,0.98885703,0.008105698,0.0016707272,0.00033702736,0.000012469967,0.000047725298,0.00003899407,0.00037808417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.947068,0.010363364,0.038953543,0.00070119963,0.0019764549,0.0009374318],"domain_scores_gemma":[0.14110419,0.83117545,0.022137156,0.0010905303,0.002621271,0.001871399],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.17773233,0.000572568,0.017387945,0.00077497173,0.00003785179,0.000012786384,0.0007792703,0.0040334086,0.00020662168],"category_scores_gemma":[0.8799556,0.0003672201,0.002078241,0.0004451833,0.001955678,0.00014473876,0.0006915187,0.011120148,0.000059950522],"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":[0.0036751316,0.0008751132,0.17525324,0.028596913,0.001369307,0.0002394024,0.0000506278,0.0000025591767,1.1499387e-7,0.0018141904,0.01124886,0.77687454],"study_design_scores_gemma":[0.015449369,0.0064738994,0.028188655,0.12731051,0.0014296452,0.0007530591,0.00016766846,0.000027617614,1.5638769e-7,0.05230774,0.76742727,0.0004643927],"about_ca_topic_score_codex":0.00020698943,"about_ca_topic_score_gemma":0.001168787,"teacher_disagreement_score":0.8208121,"about_ca_system_score_codex":0.0005412331,"about_ca_system_score_gemma":0.03461335,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W2009747117","doi":"10.1016/j.jclinepi.2007.10.003","title":"Surveillance search techniques identified the need to update systematic reviews","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":86,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Institute of Population and Public Health; University of Ottawa; Children's Hospital of Eastern Ontario","funders":"U.S. Public Health Service; Agency for Healthcare Research and Quality; University of Ottawa","keywords":"MEDLINE; Systematic review; Medicine; Data science; Information retrieval; Computer science; Political science","score_opus":0.9471942346932516,"score_gpt":0.6961125033642479,"score_spread":0.2510817313290037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009747117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32209867,0.022930596,0.5104772,0.12954351,0.00532163,0.0066671884,0.000013350999,0.00001952424,0.0029283424],"genre_scores_gemma":[0.8780225,0.012418,0.068503425,0.030227028,0.0024258797,0.00010706458,0.000001974426,0.000036164092,0.008257956],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.32911807,0.5249938,0.13814797,0.0013271756,0.0056079268,0.00080507813],"domain_scores_gemma":[0.3212479,0.581926,0.08182669,0.008469235,0.005442519,0.0010876996],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8660256,0.00032676212,0.024180338,0.00039034136,0.00020780953,0.0001210718,0.0046807434,0.0002582203,0.0015221335],"category_scores_gemma":[0.8915908,0.00010582927,0.007773069,0.001344364,0.00032134206,0.00018389573,0.00027969686,0.0010373614,0.0050012087],"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":[0.00006863533,0.000100385325,0.24672872,0.00093163515,0.00047987295,0.00004985054,0.00016555493,0.00013876459,0.000015828058,0.0031790158,0.7380323,0.010109482],"study_design_scores_gemma":[0.0005313614,0.00074756483,0.25696364,0.002324734,0.00049155945,0.0017009089,0.00038786625,0.0030107487,0.00001640116,0.032087956,0.7012555,0.00048179127],"about_ca_topic_score_codex":0.000009225447,"about_ca_topic_score_gemma":0.000015247532,"teacher_disagreement_score":0.5559238,"about_ca_system_score_codex":0.000028782539,"about_ca_system_score_gemma":0.00015415752,"threshold_uncertainty_score":0.9993906},"labels":[],"label_agreement":null},{"id":"W2009927614","doi":"10.1016/j.jclinepi.2005.02.004","title":"Ensuring high accuracy of data abstracted from patient charts: the use of a standardized medical record as a training tool","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":72,"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 Institutes of Health Research; Canada Research Chairs; University of Toronto","funders":"","keywords":"Medical record; Gold standard (test); Reliability (semiconductor); Medicine; Data collection; Abstraction; Data quality; Quality (philosophy); Computer science; Medical physics; Statistics; Surgery; Operations management; Internal medicine","score_opus":0.718822314643314,"score_gpt":0.6262285129930409,"score_spread":0.09259380165027309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009927614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9585845,0.00068185665,0.00270892,0.034307882,0.00272868,0.0006478818,0.00022376349,0.000017588225,0.00009894639],"genre_scores_gemma":[0.96369576,0.0036888304,0.018140009,0.010234462,0.004103848,0.00001687248,0.00003340379,0.000038681435,0.000048128277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9521667,0.026189217,0.01926572,0.0004788712,0.0009026904,0.0009968448],"domain_scores_gemma":[0.6495474,0.3291778,0.018418206,0.0013225669,0.00089604536,0.00063799386],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.072193414,0.00023899938,0.0042515486,0.00012341795,0.00018547213,0.0000034615114,0.0012048174,0.0010094146,0.0014876835],"category_scores_gemma":[0.4635095,0.00014308981,0.00047535045,0.00017573123,0.00035522153,0.0004225998,0.00037129672,0.00476383,0.000033381246],"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":[0.0044183913,0.00045181825,0.1186636,0.0002592883,0.0007756794,0.00004329836,0.0024393848,0.00012395583,0.000067248635,0.0008975155,0.035044048,0.8368158],"study_design_scores_gemma":[0.007941276,0.0027100272,0.16328137,0.0041080527,0.00023571681,0.000089854824,0.0011911901,0.005308481,0.000013495282,0.0032059955,0.8116249,0.00028966097],"about_ca_topic_score_codex":0.0029192006,"about_ca_topic_score_gemma":0.00092189113,"teacher_disagreement_score":0.8365261,"about_ca_system_score_codex":0.00017238749,"about_ca_system_score_gemma":0.0062063136,"threshold_uncertainty_score":0.99942756},"labels":[],"label_agreement":null},{"id":"W2010149513","doi":"10.1016/j.jclinepi.2010.09.012","title":"GRADE guidelines: 2. Framing the question and deciding on important outcomes","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":1918,"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":"Outcome (game theory); Framing (construction); Guideline; Population; Medicine; Evidence-based medicine; Psychology; Actuarial science; Alternative medicine; Economics; Pathology","score_opus":0.6328557886014028,"score_gpt":0.6686296993919846,"score_spread":0.03577391079058179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010149513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7792367,0.00019139146,0.0040611634,0.21365973,0.0026124106,0.00016813226,0.0000015919461,0.000012361551,0.000056522917],"genre_scores_gemma":[0.8889254,0.0015334694,0.052151226,0.054229457,0.003086692,0.000002738905,0.0000038358457,0.00002015201,0.000047076217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9867179,0.0021120002,0.0102925515,0.0002697118,0.0003295038,0.00027832485],"domain_scores_gemma":[0.8080731,0.18192905,0.007935394,0.0005606433,0.0009805497,0.0005212369],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07751492,0.00017337009,0.0017375113,0.00010203339,0.00009432991,0.000011556051,0.00017693112,0.00036347532,0.00007697881],"category_scores_gemma":[0.6886438,0.00008928261,0.0005371995,0.000094041236,0.00029650884,0.00014134485,0.0000637845,0.0026080955,0.000010829408],"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":[0.0004543454,0.0001503192,0.92317164,0.000010846964,0.00013769361,0.000041865016,0.000018701872,0.000011629022,0.00031120077,0.005626669,0.0067983223,0.06326675],"study_design_scores_gemma":[0.002452701,0.0012934372,0.9414906,0.000106193016,0.00031558966,0.0007586355,0.00014722723,0.0020368432,0.000019284453,0.018896721,0.032389183,0.00009356515],"about_ca_topic_score_codex":0.00006809022,"about_ca_topic_score_gemma":0.00007389822,"teacher_disagreement_score":0.61112887,"about_ca_system_score_codex":0.000019494973,"about_ca_system_score_gemma":0.00025644674,"threshold_uncertainty_score":0.9996929},"labels":[],"label_agreement":null},{"id":"W2010232135","doi":"10.1016/j.jclinepi.2007.06.008","title":"Qualiveen, a urinary-disorder specific instrument: 0.5 corresponds to the minimal important difference","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","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":"McMaster University; Western University","funders":"Coloplast","keywords":"Interpretability; Quality of life (healthcare); Likert scale; Feeling; Correlation; Psychological intervention; Medicine; Scale (ratio); Physical therapy; Clinical psychology; Psychology; Mathematics; Psychiatry; Developmental psychology; Social psychology; Artificial intelligence","score_opus":0.44217375434235145,"score_gpt":0.5107723014757584,"score_spread":0.0685985471334069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010232135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93861717,0.0025437889,0.001019091,0.056174915,0.00094324676,0.00034427448,0.000009509803,0.000012014487,0.00033596813],"genre_scores_gemma":[0.9654461,0.02131903,0.004772427,0.005807081,0.001842292,0.000014346619,0.0000023585383,0.00002001149,0.0007763492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895892,0.003538269,0.0052383402,0.0003831628,0.00059449224,0.00065650884],"domain_scores_gemma":[0.9677098,0.028422598,0.0019453996,0.0005858154,0.00053564645,0.0008007496],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01745774,0.00024069373,0.0026954953,0.00019207966,0.00019775386,0.000005355404,0.0005199154,0.00023541668,0.00032809874],"category_scores_gemma":[0.10457566,0.00012613261,0.0008505867,0.00028509396,0.00084826304,0.000053420725,0.0002867759,0.001640173,0.000098036355],"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":[0.0051580532,0.0007414987,0.92113477,0.000019324209,0.00026521817,0.00037812168,0.00039412084,0.000014750268,0.00013808125,0.0002571224,0.045658715,0.025840197],"study_design_scores_gemma":[0.0025113758,0.005295691,0.86507106,0.00010770453,0.000035952602,0.0010961903,0.00021883297,0.00023447914,0.000006831842,0.00019690771,0.12512171,0.00010328025],"about_ca_topic_score_codex":0.000036123995,"about_ca_topic_score_gemma":0.000016998163,"teacher_disagreement_score":0.08711791,"about_ca_system_score_codex":0.000061349405,"about_ca_system_score_gemma":0.00037850632,"threshold_uncertainty_score":0.90296686},"labels":[],"label_agreement":null},{"id":"W2010243325","doi":"10.1016/j.jclinepi.2004.08.020","title":"For randomized controlled trials, the quality of reports of complementary and alternative medicine was as good as reports of conventional medicine","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa; GlaxoSmithKline (Canada); University of Alberta","funders":"","keywords":"Jadad scale; Randomized controlled trial; Medicine; Quality Score; Psychological intervention; English language; Quality (philosophy); MEDLINE; Alternative medicine; Physical therapy; Family medicine; Internal medicine; Psychology; Pathology; Psychiatry","score_opus":0.9158228444043196,"score_gpt":0.7270282215373655,"score_spread":0.18879462286695414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010243325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72035897,0.027056023,0.059128463,0.17942916,0.004062421,0.0062232227,0.00003291717,0.0000018998095,0.003706946],"genre_scores_gemma":[0.9868324,0.0013764888,0.0071950713,0.0025451966,0.0012726727,0.000029506156,0.000008282565,0.0000065103286,0.0007339015],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.25552008,0.39271215,0.34287816,0.0011996675,0.0072569354,0.0004330242],"domain_scores_gemma":[0.045465827,0.7017466,0.24634533,0.0013546168,0.004845889,0.00024175971],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.92255604,0.0002679275,0.06200607,0.00031737582,0.000050931692,0.0000064926744,0.00067538134,0.00017461127,0.0070349313],"category_scores_gemma":[0.9608601,0.00008287697,0.010256496,0.00023881457,0.0018563863,0.00009444917,0.00008749808,0.00036376866,0.0000022638858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.22667384,0.0013049392,0.2544691,0.0005394418,0.04219654,0.00009324048,0.0013617465,0.00068131427,0.0004917424,0.17836429,0.27090043,0.022923362],"study_design_scores_gemma":[0.20730563,0.002343994,0.022838093,0.0006003686,0.007234079,0.00069857115,0.0010602971,0.0025186196,0.00003354212,0.72679263,0.028441576,0.00013261383],"about_ca_topic_score_codex":0.00018775153,"about_ca_topic_score_gemma":0.000027885415,"teacher_disagreement_score":0.54842836,"about_ca_system_score_codex":0.000013343402,"about_ca_system_score_gemma":0.0002594499,"threshold_uncertainty_score":0.99965554},"labels":[],"label_agreement":null},{"id":"W2010491313","doi":"10.1016/j.jclinepi.2007.03.011","title":"Symbols were superior to numbers for presenting strength of recommendations to health care consumers: a randomized trial","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"McMaster University","funders":"","keywords":"Randomized controlled trial; Medicine; MEDLINE; Physical therapy; Family medicine; Surgery","score_opus":0.5589265813132646,"score_gpt":0.6404153806652908,"score_spread":0.08148879935202624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010491313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6163135,0.0032154992,0.030244386,0.31755352,0.015032519,0.016250279,0.0003010405,0.0000641231,0.0010251357],"genre_scores_gemma":[0.758586,0.0007026292,0.20811436,0.030078629,0.0018073273,0.000437992,0.00006609105,0.000055620734,0.00015136294],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9515845,0.028100122,0.01848307,0.0004273906,0.00031756613,0.001087362],"domain_scores_gemma":[0.74042845,0.24705318,0.008686638,0.00073128997,0.0019418449,0.0011585889],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05737793,0.00022897232,0.0050280397,0.00037383227,0.00050049915,0.0000038526246,0.00072755886,0.0005311132,0.00015248312],"category_scores_gemma":[0.34085488,0.00018384667,0.0010957555,0.00029350203,0.00021999364,0.000118100965,0.0002520651,0.0018136285,0.000023734285],"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":[0.7302568,0.00045442506,0.12747408,0.0009552933,0.0004890148,0.0000018954622,0.0236959,0.000059657817,0.000005344401,0.0062088245,0.068781905,0.041616876],"study_design_scores_gemma":[0.74130726,0.0048812474,0.009946097,0.0021074915,0.00020820076,0.000007689505,0.05696887,0.00014678336,0.000008171835,0.0032009091,0.1808508,0.00036646155],"about_ca_topic_score_codex":0.00071220606,"about_ca_topic_score_gemma":0.00100536,"teacher_disagreement_score":0.28747487,"about_ca_system_score_codex":0.000299017,"about_ca_system_score_gemma":0.0023552063,"threshold_uncertainty_score":0.9706278},"labels":[],"label_agreement":null},{"id":"W2011972975","doi":"10.1016/j.jclinepi.2010.03.001","title":"Comparative Effectiveness Research: Challenges for Medical Journals","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Psychological intervention; Health care; Medicine; Alternative medicine; MEDLINE; Health policy; Family medicine; Public health; Gerontology; Medical education; Nursing; Political science","score_opus":0.961326602968233,"score_gpt":0.7454667716360986,"score_spread":0.21585983133213438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011972975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6053317,0.014199118,0.020687757,0.34695736,0.008851925,0.0008081003,0.0000583429,0.00001592298,0.0030897579],"genre_scores_gemma":[0.95741004,0.005332832,0.016302748,0.012223524,0.008546017,0.0000633062,0.00000349132,0.000032523436,0.00008554024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9498414,0.02274673,0.02560213,0.0006329252,0.00031202834,0.00086483336],"domain_scores_gemma":[0.4963215,0.48356584,0.016936397,0.0006147421,0.0012511149,0.0013104137],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6863953,0.00018002422,0.0063350657,0.0005026637,0.00020072059,0.000022422502,0.00083689706,0.00091351994,0.0006975141],"category_scores_gemma":[0.68302464,0.00016428382,0.0008788819,0.00013980849,0.0006805992,0.00032877535,0.000087405635,0.003100357,0.00043446815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066695316,0.00073757593,0.19019943,0.000509915,0.00064985134,0.000011539577,0.0009973593,0.000083948566,0.000007651227,0.73141396,0.0697717,0.0049500903],"study_design_scores_gemma":[0.0022649511,0.0010614304,0.34547052,0.00023787374,0.000010187554,0.00010652661,0.0004515207,0.0018786635,0.0000033778688,0.45415318,0.19418864,0.0001731271],"about_ca_topic_score_codex":0.000037913727,"about_ca_topic_score_gemma":0.00012487912,"teacher_disagreement_score":0.4608191,"about_ca_system_score_codex":0.00011372709,"about_ca_system_score_gemma":0.00079958874,"threshold_uncertainty_score":0.9991995},"labels":[],"label_agreement":null},{"id":"W2012099691","doi":"10.1016/j.jclinepi.2012.06.007","title":"A valid cross-culturally adapted simplified Chinese version of the Quebec Back Pain Disability Scale","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":15,"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":"Intraclass correlation; Cronbach's alpha; Construct validity; Physical therapy; Visual analogue scale; Oswestry Disability Index; Low back pain; Medicine; Discriminative model; Confidence interval; Psychology; Psychometrics; Clinical psychology; Internal medicine; Artificial intelligence; Computer science","score_opus":0.10308495466222939,"score_gpt":0.4792957067796393,"score_spread":0.3762107521174099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012099691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802646,0.00022196847,0.00055566966,0.017031709,0.0012290383,0.00026995665,0.0000037416128,0.0000066013617,0.00041669697],"genre_scores_gemma":[0.9937116,0.00005149852,0.0023874056,0.0023886247,0.0011132059,0.0000014043403,0.000005239671,0.000009532659,0.00033149036],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98736477,0.008081022,0.003786985,0.00017919092,0.00027267155,0.00031537734],"domain_scores_gemma":[0.96289563,0.033357218,0.00237604,0.0004654202,0.00048449083,0.00042120402],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04206905,0.00016014015,0.0018029921,0.000028777518,0.000056990088,0.00000288765,0.00021929068,0.00040685496,0.00032149057],"category_scores_gemma":[0.16304187,0.000071528506,0.0015850726,0.00017673784,0.0012144672,0.00016294602,0.00007429029,0.0008406085,0.000023438773],"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":[0.0010163852,0.00065803516,0.98892,0.00029920644,0.00008387895,2.9632267e-7,0.00011418907,0.00005499519,0.0009930577,0.00012694622,0.0023678294,0.0053652218],"study_design_scores_gemma":[0.0018488751,0.00080920075,0.99236614,0.00019355376,0.00005859238,0.000015408208,0.0000903852,0.0002957321,0.000021326749,0.0011814317,0.003048995,0.00007036748],"about_ca_topic_score_codex":0.00020799263,"about_ca_topic_score_gemma":0.00011149663,"teacher_disagreement_score":0.120972835,"about_ca_system_score_codex":0.00007771137,"about_ca_system_score_gemma":0.00013467284,"threshold_uncertainty_score":0.9863915},"labels":[],"label_agreement":null},{"id":"W2012186713","doi":"10.1016/j.jclinepi.2012.04.014","title":"Rasch analysis of the PedsQL: an increased understanding of the properties of a rating scale","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Childhood Cancer Survivors' Quality of Life","field":"Medicine","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":"Children's Hospital of Eastern Ontario; SickKids Foundation; University of Toronto; McMaster University; University of British Columbia; Hospital for Sick Children","funders":"","keywords":"Rasch model; Rating scale; Scale (ratio); Medicine; Statistics; Mathematics; Geography; Cartography","score_opus":0.4836941673955156,"score_gpt":0.5120679355898631,"score_spread":0.028373768194347504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012186713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898813,0.0010605274,0.0011609137,0.006978542,0.00056598533,0.00016296747,0.000006097801,0.0000034130446,0.00018030134],"genre_scores_gemma":[0.9960369,0.0001278038,0.0012211716,0.0020302276,0.0005550575,8.9717054e-7,7.003485e-7,0.000011172489,0.00001610233],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9855385,0.008179315,0.00538466,0.00014633033,0.00047859916,0.0002725912],"domain_scores_gemma":[0.97844523,0.012974576,0.0072795725,0.0006591953,0.00038440624,0.0002570402],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03977684,0.00013527164,0.0031817872,0.00015485162,0.000061558756,0.0000016571096,0.00041772053,0.00023223872,0.000049483562],"category_scores_gemma":[0.06941752,0.000064056236,0.00168566,0.00057612226,0.00093092263,0.00011470255,0.00012567143,0.00078881386,2.910468e-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":[0.0006805576,0.00044982356,0.9932074,0.00016848996,0.0014180007,2.7791154e-7,0.0012241115,0.00016568133,0.0015199074,0.0007686784,0.0001875933,0.00020950279],"study_design_scores_gemma":[0.0013294229,0.00053625874,0.9892801,0.00059811724,0.0027323193,0.000024646411,0.0023884191,0.00082966103,0.0014182542,0.0007311046,0.00006660527,0.00006510893],"about_ca_topic_score_codex":0.00049098145,"about_ca_topic_score_gemma":0.00020346015,"teacher_disagreement_score":0.029640678,"about_ca_system_score_codex":0.00005762387,"about_ca_system_score_gemma":0.00043146632,"threshold_uncertainty_score":0.9887518},"labels":[],"label_agreement":null},{"id":"W2012251049","doi":"10.1016/j.jclinepi.2003.08.005","title":"Osteoporosis Health Belief Scale: Minor changes were required after telephone administration among women","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":35,"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. Michael's Hospital; Institute for Work & Health; Sunnybrook Health Science Centre; Women's College Hospital; University of Toronto; Health Sciences Centre","funders":"","keywords":"Medicine; Construct validity; Scale (ratio); Health belief model; Exploratory factor analysis; Confirmatory factor analysis; Osteoporosis; Confounding; Psychometrics; Clinical psychology; Physical therapy; Gerontology; Structural equation modeling; Health education; Public health; Statistics; Internal medicine","score_opus":0.15639616009119983,"score_gpt":0.4909496486264131,"score_spread":0.3345534885352133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012251049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86092544,0.001945234,0.00018125531,0.13551103,0.00084019854,0.00042034712,0.000012825707,0.00002044467,0.00014321634],"genre_scores_gemma":[0.9574884,0.0049801203,0.0072517307,0.027497154,0.0022129915,0.000045546407,0.00001506613,0.0000325389,0.00047644964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99003106,0.0023429664,0.0055004926,0.0004462762,0.0005326743,0.0011465113],"domain_scores_gemma":[0.9891344,0.0044964585,0.0030996425,0.0004527291,0.00048018387,0.0023366257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026408812,0.0002576204,0.0034413033,0.00026190968,0.00011649724,0.000010897422,0.00021773022,0.0006639289,0.00037193068],"category_scores_gemma":[0.020486781,0.0001877032,0.00053224235,0.0002642326,0.00059161766,0.00015236628,0.00006929622,0.0017514771,0.00006564114],"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":[0.009963728,0.0015208942,0.8846847,0.0006250658,0.00017844838,0.00032252667,0.0007408435,0.000009384829,0.00009712528,0.00006521757,0.0087545775,0.09303753],"study_design_scores_gemma":[0.005758746,0.018600991,0.9589865,0.00051929924,0.000045168526,0.00048119354,0.00044859247,0.0000110138835,0.00007591584,0.0011965203,0.013727892,0.0001481703],"about_ca_topic_score_codex":0.0001833592,"about_ca_topic_score_gemma":0.00078711484,"teacher_disagreement_score":0.108013876,"about_ca_system_score_codex":0.0003942102,"about_ca_system_score_gemma":0.002607809,"threshold_uncertainty_score":0.98776406},"labels":[],"label_agreement":null},{"id":"W2012385126","doi":"10.1016/j.jclinepi.2008.07.014","title":"In a review of stroke rehabilitation studies, concealed allocation was under reported","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":9,"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; Parkwood Institute; St Joseph's Health Care","funders":"","keywords":"Rehabilitation; Stroke (engine); Medicine; Physical medicine and rehabilitation; Physical therapy; Engineering","score_opus":0.9062153126127016,"score_gpt":0.7678106705513097,"score_spread":0.1384046420613919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012385126","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":[0.00007790437,0.9728909,0.00014542822,0.023917867,0.0012964468,0.0013779917,0.0000074398577,0.0000064035607,0.0002795997],"genre_scores_gemma":[0.000011599848,0.9831519,0.009362577,0.005800172,0.0010066879,0.000039371862,0.000025533896,0.000041843596,0.0005603091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91697603,0.032006323,0.047686655,0.0010059185,0.001672026,0.00065303134],"domain_scores_gemma":[0.10874212,0.8490288,0.033153236,0.0016525248,0.006765559,0.000657729],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.20349087,0.00039922612,0.023197304,0.00048492488,0.000027911537,0.0000014027099,0.00052378455,0.0025624027,0.00010960754],"category_scores_gemma":[0.9266989,0.00025778377,0.0041840626,0.00065862725,0.0019145978,0.00009243038,0.00017321254,0.010380618,0.000022052369],"study_design_candidate":"systematic_review","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":[0.00068093947,0.0014691589,0.013439921,0.46556705,0.0050474904,0.00064600835,0.000048669146,0.0000074220384,2.1406875e-7,0.007072714,0.036848888,0.46917152],"study_design_scores_gemma":[0.0016170986,0.0034498773,0.003174047,0.41421425,0.0018802666,0.0011262355,0.000031701846,0.000007493767,4.722133e-8,0.017101398,0.55722404,0.00017352839],"about_ca_topic_score_codex":0.000021706715,"about_ca_topic_score_gemma":0.000026317266,"teacher_disagreement_score":0.8170225,"about_ca_system_score_codex":0.00045809892,"about_ca_system_score_gemma":0.007425017,"threshold_uncertainty_score":0.9999874},"labels":[],"label_agreement":null},{"id":"W2012422915","doi":"10.1016/j.jclinepi.2012.12.009","title":"Sensibility of five at-work productivity measures was endorsed by patients with osteoarthritis or rheumatoid arthritis","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Workplace Health and Well-being","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of British Columbia; University Health Network; University of Toronto; Institute for Work & Health; Arthritis Research Centre of Canada; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Rheumatoid arthritis; Sensibility; Osteoarthritis; Medicine; Physical therapy; Productivity; Work productivity; Alternative medicine; Internal medicine; Pathology; Economics; Political science","score_opus":0.10281693861687452,"score_gpt":0.4463159265531324,"score_spread":0.3434989879362579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012422915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854692,0.0009814021,0.0002755026,0.009389525,0.00198572,0.0013797606,0.00003111082,0.000023651946,0.00046410965],"genre_scores_gemma":[0.9909105,0.0022734583,0.003060234,0.002518317,0.0005666231,0.000042256655,0.00001518556,0.000034853834,0.0005786042],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97304434,0.017288517,0.0076991427,0.00052202196,0.00045035468,0.0009956178],"domain_scores_gemma":[0.93529165,0.054329846,0.007223599,0.000582599,0.0017189579,0.000853326],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.025338318,0.00029847017,0.0037114478,0.00009833684,0.0003450983,0.0000031715042,0.00028254144,0.00075585104,0.0007288076],"category_scores_gemma":[0.09728869,0.00018481411,0.00040303296,0.00026554868,0.00061674474,0.0002476006,0.00015133448,0.0026347742,0.00013919375],"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":[0.004042503,0.0003961017,0.86488694,0.00011645008,0.00007530638,0.0000076733395,0.00025482234,0.000020023932,0.0000062039007,0.00003505868,0.07553269,0.054626238],"study_design_scores_gemma":[0.00959886,0.0040865946,0.959142,0.001724175,0.00002840582,0.000035955123,0.00024037597,0.00001741578,0.00002410003,0.0027559435,0.022084402,0.0002617339],"about_ca_topic_score_codex":0.0004382606,"about_ca_topic_score_gemma":0.00045008282,"teacher_disagreement_score":0.09425511,"about_ca_system_score_codex":0.00013227887,"about_ca_system_score_gemma":0.00088524056,"threshold_uncertainty_score":0.9996662},"labels":[],"label_agreement":null},{"id":"W2012611494","doi":"10.1016/j.jclinepi.2009.11.006","title":"Community controls were preferred to hospital controls in a case–control study where the cases are derived from the hospital","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pneumonia and Respiratory Infections","field":"Medicine","cited_by":24,"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; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Logistic regression; Case-control study; Medicine; Community-acquired pneumonia; Community hospital; Demography; Selection bias; Pneumonia; Gerontology; Statistics; Internal medicine; Psychiatry; Pathology","score_opus":0.14540843305753529,"score_gpt":0.45521733338777065,"score_spread":0.30980890033023534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012611494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8804285,0.00032723142,0.00017352465,0.11511822,0.0022385626,0.0015654782,0.00008273092,0.000015322246,0.000050434584],"genre_scores_gemma":[0.9822936,0.00005729805,0.000070707916,0.015536727,0.0019197449,0.00006814663,0.0000012342475,0.000023186456,0.000029324761],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98235,0.012857557,0.0038018643,0.0002760666,0.00023012942,0.00048441885],"domain_scores_gemma":[0.9068763,0.088800356,0.0023825825,0.0009495359,0.00047727366,0.0005139377],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01854068,0.00029959562,0.0030178456,0.00008275183,0.0003919822,0.000027078084,0.00057410815,0.00046885465,0.00016642966],"category_scores_gemma":[0.12718712,0.00014032672,0.00088892685,0.00015342183,0.0005548105,0.000107804,0.00012147172,0.006040076,0.000035516383],"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":[0.0010069555,0.0025170625,0.98720336,0.000005088986,0.0008065672,0.0024231859,0.00072674226,0.000049421447,0.00046902316,0.000025460311,0.0022657674,0.0025013695],"study_design_scores_gemma":[0.010724785,0.009132488,0.9660049,0.000101332545,0.00057816796,0.0020504904,0.0049056252,0.00010009755,0.0000019134427,0.00032589425,0.005926855,0.0001474434],"about_ca_topic_score_codex":0.0011402708,"about_ca_topic_score_gemma":0.0101144845,"teacher_disagreement_score":0.10864643,"about_ca_system_score_codex":0.0000439361,"about_ca_system_score_gemma":0.00029361708,"threshold_uncertainty_score":0.996253},"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":"W2012944180","doi":"10.1016/j.jclinepi.2009.04.007","title":"Systematic review data extraction: cross-sectional study showed that experience did not increase accuracy","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":80,"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; Capital District Health Authority","funders":"Agency for Healthcare Research and Quality","keywords":"Data extraction; Meta-analysis; Systematic review; Extraction (chemistry); Statistics; Medicine; MEDLINE; Mathematics","score_opus":0.9550334104217747,"score_gpt":0.7403269771706922,"score_spread":0.21470643325108252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012944180","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8746344,0.041098982,0.050404515,0.019738905,0.007080878,0.0052335933,0.000058539572,0.000020144369,0.0017300848],"genre_scores_gemma":[0.97763914,0.003656298,0.004100247,0.0124937575,0.0009976275,0.000021827425,0.000007809467,0.000010161925,0.0010731218],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5788396,0.26716024,0.14138216,0.0026928806,0.009169185,0.000755931],"domain_scores_gemma":[0.22986306,0.60374236,0.14453118,0.015275864,0.0051996373,0.0013878824],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.76162755,0.00044545863,0.022352776,0.000296527,0.00021757661,0.00038707623,0.0073863342,0.00029989207,0.0056794994],"category_scores_gemma":[0.9374485,0.00019348878,0.005155437,0.00082267827,0.00023194977,0.001457883,0.0003880688,0.0012834205,0.0010540592],"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":[0.00014189568,0.000813436,0.95848185,0.0026949476,0.0006479097,0.00008710922,0.00006387361,0.00004070612,0.0000026898624,0.00030609185,0.034283996,0.002435486],"study_design_scores_gemma":[0.0006108264,0.0006116188,0.9821105,0.0039083613,0.0010631519,0.00087784865,0.0002403821,0.0015973,3.7959927e-7,0.0028817363,0.0058772694,0.00022060647],"about_ca_topic_score_codex":0.000011775246,"about_ca_topic_score_gemma":0.000010120223,"teacher_disagreement_score":0.34897655,"about_ca_system_score_codex":0.000045681176,"about_ca_system_score_gemma":0.00026844794,"threshold_uncertainty_score":0.99972373},"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":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2013689668","doi":"10.1016/j.jclinepi.2009.01.023","title":"A physiatrist's view of response shift","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sleep and Work-Related Fatigue","field":"Psychology","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 British Columbia","funders":"","keywords":"Biopsychosocial model; Conceptualization; Paradigm shift; Medicine; Perspective (graphical); Rehabilitation; MEDLINE; Physical medicine and rehabilitation; Gerontology; Psychology; Physical therapy; Psychiatry; Computer science; Political science","score_opus":0.24206144701583007,"score_gpt":0.5390872570955771,"score_spread":0.29702581007974704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013689668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95264184,0.0064330455,0.0026364166,0.030160362,0.0032710542,0.0001266257,0.0000047514004,0.000019585286,0.004706316],"genre_scores_gemma":[0.9880776,0.0005962552,0.003084743,0.0070980387,0.0010332401,0.0000010512624,0.0000010144498,0.000012183635,0.00009589822],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9812199,0.0118480865,0.006072843,0.0002753437,0.00016195042,0.00042191046],"domain_scores_gemma":[0.95482564,0.040132347,0.0041133766,0.00045316966,0.00018115136,0.00029431412],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033385243,0.00018255875,0.002670051,0.00016989402,0.000032444343,0.0000024672845,0.00048804109,0.00072025554,0.0007262498],"category_scores_gemma":[0.03654126,0.0001321162,0.0012139165,0.00025835136,0.00028295323,0.000069049005,0.000026136217,0.0015025177,0.00016820923],"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":[0.02237942,0.0020691953,0.2165413,0.000008449456,0.0009941176,0.0003262551,0.000561891,0.00012010909,0.000042915053,0.0559512,0.07614523,0.6248599],"study_design_scores_gemma":[0.0032250667,0.0050547114,0.9524699,0.00022493821,0.00019347946,0.00008497076,0.00005499281,0.000009595608,0.000006891255,0.019772058,0.018743796,0.00015958668],"about_ca_topic_score_codex":0.0000126941495,"about_ca_topic_score_gemma":0.000001457935,"teacher_disagreement_score":0.7359286,"about_ca_system_score_codex":0.000016975137,"about_ca_system_score_gemma":0.00013229887,"threshold_uncertainty_score":0.9953333},"labels":[],"label_agreement":null},{"id":"W2013856227","doi":"10.1016/j.jclinepi.2009.12.004","title":"Logistic regression had superior performance compared with regression trees for predicting in-hospital mortality in patients hospitalized with heart failure","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"Health Sciences Centre; Public Health Ontario; University Health Network; University of Toronto; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Logistic regression; Acute decompensated heart failure; Medicine; Regression analysis; Statistics; Regression; Linear regression; Heart failure; Stepwise regression; Internal medicine; Mathematics","score_opus":0.19399118302493243,"score_gpt":0.47396618953846636,"score_spread":0.2799750065135339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013856227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933994,0.00006201838,0.000046649813,0.0052635563,0.0005349441,0.00066112785,0.0000070696356,0.000010691399,0.000014578674],"genre_scores_gemma":[0.98786527,0.000105840525,0.011190906,0.0004662512,0.00028014134,0.00003963079,0.000024305416,0.000022089513,0.0000055508194],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99560726,0.0005665098,0.0027631784,0.00037938327,0.00028011575,0.00040353002],"domain_scores_gemma":[0.99274164,0.0046437928,0.0016590023,0.00032117456,0.00033848998,0.00029589413],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0046434933,0.0002582705,0.0026233487,0.00014156396,0.000055582386,0.0000067443357,0.00013743147,0.00034439916,0.000024064539],"category_scores_gemma":[0.0129855815,0.00012626569,0.0002950475,0.00014128783,0.00031529876,0.00015331806,0.000032198812,0.0011001447,0.000001462085],"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":[0.0045317556,0.0023834605,0.9908224,0.00005909049,0.000103858096,0.000037022204,0.000060222577,0.00008409381,0.000008409093,0.000014196049,0.0007015418,0.001193986],"study_design_scores_gemma":[0.016145078,0.0151261315,0.96527016,0.0017204026,0.00015388863,0.00003495975,0.000054947406,0.0008635709,0.00002962467,0.00008398881,0.0003845304,0.00013269659],"about_ca_topic_score_codex":0.00007642479,"about_ca_topic_score_gemma":0.00035894368,"teacher_disagreement_score":0.025552183,"about_ca_system_score_codex":0.00006215553,"about_ca_system_score_gemma":0.00020525086,"threshold_uncertainty_score":0.9953285},"labels":[],"label_agreement":null},{"id":"W2014553305","doi":"10.1016/j.jclinepi.2013.03.009","title":"Combining follow-up and change data is valid in meta-analyses of continuous outcomes: a meta-epidemiological study","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":152,"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; Hospital for Sick Children","funders":"","keywords":"Meta-analysis; Medicine; Confidence interval; Epidemiology; Randomized controlled trial; Clinical trial; Osteoarthritis; Physical therapy; Internal medicine; Pathology; Alternative medicine","score_opus":0.9193273334621059,"score_gpt":0.64845111810582,"score_spread":0.2708762153562859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014553305","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":[0.004204709,0.99047524,0.00004955361,0.0015819046,0.0010542059,0.0024478096,0.00013475367,0.000013012216,0.000038837214],"genre_scores_gemma":[0.0017849838,0.98784786,0.0066649024,0.0026003402,0.00046595346,0.00018500297,0.00009402903,0.000057591384,0.00029934282],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9580654,0.021910097,0.01774178,0.0011383572,0.00046866664,0.0006757228],"domain_scores_gemma":[0.9009152,0.08263008,0.013896465,0.0015753098,0.00036541023,0.0006175379],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.06411214,0.0011098591,0.07048707,0.00057972077,0.000040303246,0.000010732565,0.00093574927,0.0014041369,0.0005673637],"category_scores_gemma":[0.12165653,0.00048426006,0.0105005205,0.00030254433,0.0003882307,0.00022316616,0.00068526535,0.0025301785,0.000020256426],"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":[0.00043194706,0.0033238176,0.067644015,0.0029447016,0.18098804,0.0010255694,0.00016817135,2.4904702e-7,5.4189746e-7,0.00020027855,0.0029660384,0.7403066],"study_design_scores_gemma":[0.013649418,0.025564825,0.0045038234,0.0035365168,0.69766146,0.0011108107,0.00028463823,0.000016479578,3.9355285e-7,0.0019372352,0.25106514,0.00066927966],"about_ca_topic_score_codex":0.00024997236,"about_ca_topic_score_gemma":0.000057023586,"teacher_disagreement_score":0.7396374,"about_ca_system_score_codex":0.00004121239,"about_ca_system_score_gemma":0.00030598958,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W2014574840","doi":"10.1016/j.jclinepi.2012.11.013","title":"An equity lens can ensure an equity-oriented approach to agenda setting and priority setting of Cochrane Reviews","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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 Ottawa; Cochrane; Ottawa Hospital","funders":"","keywords":"Equity (law); Prioritization; Systematic review; Through-the-lens metering; Medicine; MEDLINE; Actuarial science; Business; Political science; Process management; Lens (geology); Engineering","score_opus":0.5864795069791776,"score_gpt":0.6479290284492589,"score_spread":0.061449521470081314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014574840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9397194,0.0011665118,0.012756391,0.035709735,0.0007829484,0.0015429909,0.000021822983,0.00006275129,0.008237467],"genre_scores_gemma":[0.888584,0.0025064233,0.10466601,0.0029026596,0.001252272,0.000017455406,0.0000046480095,0.000019168696,0.000047370937],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96867245,0.023876822,0.0052214037,0.00052698783,0.0007531654,0.0009491945],"domain_scores_gemma":[0.975288,0.018090896,0.003687576,0.0005772556,0.0012175592,0.0011387361],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19020598,0.00020844293,0.0027099606,0.00018145476,0.00030937963,0.00003963278,0.0011008542,0.00060608983,0.00007627365],"category_scores_gemma":[0.21612732,0.00016323692,0.00038459,0.00041989962,0.000943189,0.00048556557,0.0005304065,0.0018044665,0.0000063402003],"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":[0.00017959006,0.0008243711,0.44309062,0.0003559593,0.00009460162,0.000015722724,0.005387763,0.000058086687,0.0011146596,0.010373421,0.017191442,0.5213138],"study_design_scores_gemma":[0.0018866508,0.0055741672,0.8496378,0.0010292329,0.00019280589,0.00013252732,0.0067644124,0.0033053788,0.00009861851,0.048715487,0.08178669,0.00087621034],"about_ca_topic_score_codex":0.0025527726,"about_ca_topic_score_gemma":0.0008591844,"teacher_disagreement_score":0.5204376,"about_ca_system_score_codex":0.00011509339,"about_ca_system_score_gemma":0.0006029391,"threshold_uncertainty_score":0.83385336},"labels":[],"label_agreement":null},{"id":"W2015108607","doi":"10.1016/j.jclinepi.2013.07.013","title":"Cross-cultural adaptation of the Health Education Impact Questionnaire: experimental study showed expert committee, not back-translation, added value","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Education and Validation","field":"Social Sciences","cited_by":351,"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 Work & Health; St. Michael's Hospital","funders":"","keywords":"Content validity; Metric (unit); Psychology; Face validity; Confirmatory factor analysis; Index (typography); Medicine; Psychometrics; Clinical psychology; Applied psychology; Mathematics; Social psychology; Natural language processing; Physical therapy; Statistics; Computer science; Structural equation modeling","score_opus":0.503309901258871,"score_gpt":0.6514578225306431,"score_spread":0.14814792127177212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015108607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9334806,0.00063953333,0.00072452176,0.060312185,0.003750366,0.0008004722,0.0000021492067,0.000009966376,0.00028021168],"genre_scores_gemma":[0.9909282,0.00025225463,0.0023544878,0.004983129,0.001290382,0.000024627183,0.0000058401833,0.000008384022,0.00015273441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9788627,0.016379053,0.003865542,0.00019539188,0.00039559262,0.00030170972],"domain_scores_gemma":[0.9879073,0.0063813077,0.0038668804,0.0002336817,0.0012017847,0.00040908292],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023590269,0.00013046192,0.0008892598,0.0000797183,0.00041563783,0.00003906376,0.0003657976,0.00021682456,0.00057953264],"category_scores_gemma":[0.029070841,0.0000824487,0.00041648,0.00026944463,0.00050286116,0.0006883779,0.000019043799,0.00047340593,0.000029995788],"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":[0.00018257108,0.0025332368,0.8705977,0.00001643221,0.00006509067,7.595661e-8,0.03167884,0.0004179384,0.00003891902,0.0036003853,0.020166773,0.070702024],"study_design_scores_gemma":[0.0008857395,0.0010934795,0.97122675,0.00007876379,0.000010808036,0.000003650994,0.016950577,0.0005055685,0.000018195798,0.00088201516,0.008256163,0.00008825985],"about_ca_topic_score_codex":0.016081842,"about_ca_topic_score_gemma":0.00056519755,"teacher_disagreement_score":0.10062907,"about_ca_system_score_codex":0.0002653474,"about_ca_system_score_gemma":0.0033031532,"threshold_uncertainty_score":0.9904702},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2015871180","doi":"10.1016/j.jclinepi.2008.04.010","title":"Special physical examination tests for superior labrum anterior posterior shoulder tears are clinically limited and invalid: a diagnostic systematic review","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Shoulder Injury and Treatment","field":"Medicine","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 British Columbia","funders":"","keywords":"Critical appraisal; Medicine; Labrum; Physical examination; Confidence interval; Meta-analysis; Glenoid labrum; MEDLINE; Physical therapy; Medical physics; Surgery; Arthroscopy; Pathology; Alternative medicine","score_opus":0.3139434249788374,"score_gpt":0.546083043196728,"score_spread":0.23213961821789053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015871180","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":[0.0018867375,0.9873797,0.000057901136,0.0035054807,0.0015487439,0.0054722773,0.00007582968,0.000025923124,0.000047353413],"genre_scores_gemma":[0.00024848204,0.9812777,0.001486962,0.0070539624,0.009421477,0.00021330173,0.00005053932,0.00008253985,0.00016503537],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.97414327,0.009386666,0.014607184,0.0008298622,0.00042009845,0.00061293045],"domain_scores_gemma":[0.8619152,0.124244474,0.011689047,0.00073030894,0.00065791106,0.00076308666],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.023231816,0.0008470158,0.026908642,0.00030910238,0.00008562697,0.000027585396,0.00040675618,0.001261462,0.000045123124],"category_scores_gemma":[0.34045056,0.00050845335,0.004737684,0.00027025043,0.00038562587,0.00013396027,0.000116099945,0.0019949998,0.000031703792],"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":[0.0003572071,0.001188455,0.0012420049,0.46645305,0.001399719,0.000491493,0.00002225478,6.7612575e-8,1.3256253e-7,0.000023021228,0.003484644,0.52533793],"study_design_scores_gemma":[0.0032391034,0.01270413,0.017907469,0.8052167,0.04824821,0.0049976064,0.000021647316,0.000011076978,1.2275895e-7,0.00023460033,0.106908806,0.00051052385],"about_ca_topic_score_codex":0.0000012163706,"about_ca_topic_score_gemma":0.0000025124782,"teacher_disagreement_score":0.5248274,"about_ca_system_score_codex":0.00015459971,"about_ca_system_score_gemma":0.0007067965,"threshold_uncertainty_score":0.9997367},"labels":[],"label_agreement":null},{"id":"W2015929254","doi":"10.1016/j.jclinepi.2014.11.010","title":"Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis (TRIPOD): the TRIPOD statement","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":303,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Albert-Ludwigs-Universität Freiburg; ZonMw; University of Oxford; National Institute for Health and Care Research; University College London; University of North Carolina at Chapel Hill; Cancer Research UK; Medical Research Council; University of Ottawa; Memorial Sloan-Kettering Cancer Center","keywords":"Tripod (photography); Checklist; Statement (logic); Medicine; Computer science; Psychology; Engineering","score_opus":0.9790934224689305,"score_gpt":0.7082666694618389,"score_spread":0.2708267530070916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015929254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19706368,0.0012461945,0.78068113,0.017503832,0.0015881547,0.0016584427,0.00012254454,0.0000037658806,0.00013222327],"genre_scores_gemma":[0.8628246,0.0004275419,0.13418189,0.0011506618,0.0005718453,0.00018816732,0.0000072016583,0.000014116926,0.00063397805],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.74099827,0.06323958,0.18926214,0.0010602692,0.0048226044,0.0006171642],"domain_scores_gemma":[0.3160237,0.35725433,0.3145018,0.002886344,0.008372199,0.0009616192],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7836594,0.0002534072,0.011440935,0.00023728266,0.0000947537,0.00006719368,0.0016170351,0.00027366518,0.00033096888],"category_scores_gemma":[0.8844853,0.00008756111,0.0048053125,0.00055760157,0.00018742982,0.00023987051,0.00009649443,0.00053791585,0.000011842936],"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":[0.0005393419,0.00058663235,0.6808407,0.00006864983,0.0012507939,0.0000044247117,0.0007358858,0.04932953,0.0000017267531,0.00051177584,0.21008629,0.05604429],"study_design_scores_gemma":[0.003159972,0.0026503073,0.08628216,0.00024555155,0.0024786803,0.00006486063,0.0012320995,0.7717086,0.000019632296,0.056062534,0.07591117,0.00018444183],"about_ca_topic_score_codex":0.000014091047,"about_ca_topic_score_gemma":0.000021519545,"teacher_disagreement_score":0.7223791,"about_ca_system_score_codex":0.000042199805,"about_ca_system_score_gemma":0.00074010744,"threshold_uncertainty_score":0.7820794},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2016242508","doi":"10.1016/j.jclinepi.2010.12.001","title":"The difference between reliability and agreement","year":2011,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":93,"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":"Scopus; Inter-rater reliability; Intraclass correlation; Reliability (semiconductor); Kappa; Cohen's kappa; Statistics; Psychology; Medicine; Mathematics; MEDLINE; Physics; Psychometrics; Political science","score_opus":0.6917992205636752,"score_gpt":0.5490965920628558,"score_spread":0.14270262850081938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016242508","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":[0.03808391,0.001321954,0.0051259855,0.9488102,0.0052436832,0.00033475054,0.000017311591,0.000006484633,0.0010557229],"genre_scores_gemma":[0.03287585,0.008884266,0.00660981,0.91987073,0.025358975,0.000016647014,0.000006767917,0.000037137786,0.006339813],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9308183,0.04178641,0.022028076,0.0012870965,0.0030885243,0.0009915679],"domain_scores_gemma":[0.5006245,0.4758477,0.018300792,0.0024824105,0.002227405,0.00051725784],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.29836318,0.0004179197,0.0049178526,0.00015859165,0.0002974881,0.000093269206,0.0032785386,0.0016731332,0.00029065693],"category_scores_gemma":[0.48132014,0.0001817077,0.0016474816,0.00020336782,0.0020815318,0.00011783543,0.0005648548,0.0072759176,0.00013399884],"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":[0.00006318836,0.000034193465,0.35788372,0.000013403757,0.00010436449,0.000016394744,0.000018037903,0.00000147778,1.8907208e-7,0.000097937176,0.55782825,0.08393882],"study_design_scores_gemma":[0.00020756433,0.0005425882,0.32198378,0.00004897955,0.00007399208,0.00000903469,0.0000120552795,0.0000092346345,5.966838e-7,0.21733142,0.45968404,0.00009669408],"about_ca_topic_score_codex":0.000045142664,"about_ca_topic_score_gemma":0.000015826383,"teacher_disagreement_score":0.43406126,"about_ca_system_score_codex":0.00006771901,"about_ca_system_score_gemma":0.00036662386,"threshold_uncertainty_score":0.9996229},"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":"W2016285752","doi":"10.1016/j.jclinepi.2005.11.016","title":"A new preference-based analysis for randomized trials can estimate treatment acceptability and effect in compliant patients","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":22,"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; McMaster University","funders":"","keywords":"Preference; Randomized controlled trial; Medicine; Protocol (science); Outcome (game theory); Treatment effect; Treatment and control groups; Intention-to-treat analysis; Statistics; Alternative medicine; Mathematics; Surgery; Internal medicine","score_opus":0.547970402933054,"score_gpt":0.4506015172826536,"score_spread":0.09736888565040042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016285752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9477634,0.00046663338,0.049435996,0.0012373606,0.0002670676,0.0006418717,0.00006364903,0.000002443634,0.00012160244],"genre_scores_gemma":[0.9861203,0.00019423597,0.013227509,0.00021801815,0.00013507655,0.00003129148,0.000036512505,0.0000063355037,0.00003072475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.990724,0.0021823144,0.0065858318,0.00029367718,0.000019887268,0.00019423671],"domain_scores_gemma":[0.95843416,0.036759336,0.004524797,0.00014375799,0.000017482036,0.00012044067],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042285077,0.00014558593,0.006036019,0.00021039582,0.000026788728,0.000009459798,0.000093133276,0.00017520858,0.00020762379],"category_scores_gemma":[0.027732955,0.00010636882,0.0013598405,0.00007654477,0.000113569244,0.00006292513,0.000013964439,0.00012777596,0.0000060523944],"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":[0.0068988893,0.00018084214,0.97541744,0.000008690218,0.0003496381,2.3084893e-7,0.000009056384,0.008740785,1.204754e-7,0.0015264377,0.00009116334,0.0067766914],"study_design_scores_gemma":[0.07930362,0.0007289462,0.8436126,0.0000059280687,0.000278868,1.8998497e-7,0.0000012105663,0.018698528,0.0000023862253,0.057165504,0.00012647138,0.000075732074],"about_ca_topic_score_codex":0.001261762,"about_ca_topic_score_gemma":0.00032966767,"teacher_disagreement_score":0.13180484,"about_ca_system_score_codex":0.00016561606,"about_ca_system_score_gemma":0.000041529653,"threshold_uncertainty_score":0.98616904},"labels":[],"label_agreement":null},{"id":"W2016435156","doi":"10.1016/j.jclinepi.2009.01.001","title":"A landmark randomized health care trial: the Burlington trial of the nurse practitioner","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Nursing Roles and Practices","field":"Health Professions","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":"Hamilton Health Sciences","funders":"","keywords":"Randomized controlled trial; Landmark; Medicine; Nursing; Family medicine; Health care; Geography; Surgery; Cartography; Political science","score_opus":0.28722772386565315,"score_gpt":0.6295113671403404,"score_spread":0.34228364327468724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016435156","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":[0.226107,0.003446805,0.0007335875,0.73449254,0.024639232,0.0032733658,0.000008711926,0.000016185377,0.007282541],"genre_scores_gemma":[0.9075566,0.004072636,0.0023775802,0.071198896,0.013656842,0.000035309233,0.000005223856,0.000024184934,0.0010727082],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.91842645,0.072704524,0.007944136,0.00018850996,0.00031225663,0.00042412273],"domain_scores_gemma":[0.80678916,0.17601083,0.01608499,0.00045842212,0.00046748933,0.00018912548],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10834991,0.00015023084,0.0034397172,0.000056540044,0.00050080573,0.00000461128,0.00047665834,0.00046371506,0.00016866447],"category_scores_gemma":[0.22884409,0.00006126801,0.0013124066,0.00014454754,0.00030023625,0.000115121176,0.000023341898,0.0032054677,0.000011509408],"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":[0.92454153,0.00031360664,0.0014082525,0.000027428829,0.000116223484,0.00000114974,0.0013687931,0.000032981596,5.693674e-7,0.0044695996,0.055570766,0.012149103],"study_design_scores_gemma":[0.7667191,0.0035569414,0.006002415,0.00036718856,0.00024739592,0.0000106553025,0.0018566338,0.00003816335,3.5257938e-7,0.014289297,0.20684734,0.000064523454],"about_ca_topic_score_codex":0.00015054949,"about_ca_topic_score_gemma":0.00004526166,"teacher_disagreement_score":0.6814496,"about_ca_system_score_codex":0.00006631072,"about_ca_system_score_gemma":0.0016708893,"threshold_uncertainty_score":0.9990942},"labels":[],"label_agreement":null},{"id":"W2016477006","doi":"10.1016/j.jclinepi.2005.07.003","title":"Note on “Moving beyond floccinaucinihilipilification: enhancing the utility of systematic reviews”","year":2005,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Otolaryngology and Infectious Diseases","field":"Medicine","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Witness; Meaning (existential); Expert witness; History; Linguistics; Psychology; Philosophy","score_opus":0.17132311564533542,"score_gpt":0.49853840842170316,"score_spread":0.32721529277636774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016477006","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":[0.005812124,0.03332944,0.0014121693,0.006395398,0.94839513,0.0020412526,0.000036697955,0.000026595617,0.0025511929],"genre_scores_gemma":[0.04838564,0.024698202,0.0007666496,0.003809688,0.92179024,0.000035035104,0.000030488389,0.00004231292,0.00044173814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9673875,0.016180377,0.014957079,0.00048896484,0.0005809684,0.00040512843],"domain_scores_gemma":[0.6799328,0.29345652,0.022629302,0.0017434603,0.0017371011,0.00050082116],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.08311557,0.0004198627,0.010144378,0.00019785018,0.00011510916,0.000005188072,0.0005911264,0.0021210755,0.00030402548],"category_scores_gemma":[0.6773111,0.00022207397,0.0028194606,0.00017839135,0.00059819716,0.00008351109,0.00007918785,0.004946224,0.00009013147],"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":[0.0009446625,0.0006235137,0.0069913105,0.019332055,0.000535482,0.000021251017,0.000044878234,0.000006106895,0.0000048793036,0.000097046934,0.9686003,0.0027985184],"study_design_scores_gemma":[0.0031899742,0.0062682186,0.05844898,0.044304654,0.0058919988,0.0003213757,0.000048501253,0.00037193295,0.00002272898,0.0018273355,0.87890756,0.00039675934],"about_ca_topic_score_codex":0.000010585821,"about_ca_topic_score_gemma":0.000019895111,"teacher_disagreement_score":0.59419554,"about_ca_system_score_codex":0.00009430925,"about_ca_system_score_gemma":0.0014267106,"threshold_uncertainty_score":0.99917436},"labels":[],"label_agreement":null},{"id":"W2016503353","doi":"10.1016/j.jclinepi.2007.09.008","title":"Probit structural equation regression model: general depressive symptoms predicted post-myocardial infarction mortality after controlling for somatic symptoms of depression","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac Health and Mental Health","field":"Medicine","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 Health Network; York University; University of Toronto; Jewish General Hospital","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Killip class; Depression (economics); Medicine; Confounding; Structural equation modeling; Myocardial infarction; Internal medicine; Risk factor; Statistics","score_opus":0.15134011049930193,"score_gpt":0.48105264983699597,"score_spread":0.32971253933769407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016503353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97028524,0.0008049001,0.024949735,0.0009127854,0.0016722836,0.0012550835,0.000068566995,0.000021883596,0.000029528881],"genre_scores_gemma":[0.9880293,0.00045667848,0.0067822533,0.002515599,0.0020218429,0.000059146943,0.00008675867,0.000027662418,0.000020744474],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99110556,0.0019457357,0.0056005786,0.00036467912,0.0004549306,0.000528544],"domain_scores_gemma":[0.98824435,0.0054202974,0.004279124,0.000331578,0.0009943732,0.00073024636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070034843,0.000255573,0.003102656,0.00018381378,0.00013243806,0.0000026645484,0.00011494141,0.00063910184,0.000014868722],"category_scores_gemma":[0.017790731,0.00016849795,0.001249572,0.000103052065,0.00025381983,0.0002132525,0.000047910733,0.00084856007,8.786472e-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":[0.01130178,0.00016743591,0.9716103,0.00042870318,0.000296541,0.000017558548,0.00013735383,0.0055352487,0.0005702628,0.00004732471,0.00019430101,0.009693211],"study_design_scores_gemma":[0.008197857,0.0028139094,0.8064347,0.00059701275,0.00047668134,0.00047662342,0.000011406827,0.17931251,0.00011421563,0.0014254195,0.000029177403,0.0001104713],"about_ca_topic_score_codex":0.00006715213,"about_ca_topic_score_gemma":0.0000043698647,"teacher_disagreement_score":0.17377725,"about_ca_system_score_codex":0.00015308302,"about_ca_system_score_gemma":0.0010491317,"threshold_uncertainty_score":0.9904828},"labels":[],"label_agreement":null},{"id":"W2017152199","doi":"10.1016/s0895-4356(01)00361-4","title":"Health-related quality of life with coronary heart disease prevention and treatment","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McGill University; Montreal General Hospital","funders":"","keywords":"Dyslipidemia; Medicine; Coronary heart disease; Quality of life (healthcare); Internal medicine; Physical therapy; Disease; Cardiology","score_opus":0.7650861053307717,"score_gpt":0.6026448946659823,"score_spread":0.16244121066478945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017152199","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81492347,0.008055238,0.0024177374,0.17374982,0.00039329389,0.00029767744,0.00003531923,0.000006990884,0.00012044839],"genre_scores_gemma":[0.974531,0.0035012814,0.005137684,0.016206043,0.00034952446,0.000008970515,0.000009939447,0.000014776366,0.00024081055],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97158694,0.0071315886,0.020564083,0.0003448279,0.00007046893,0.00030209965],"domain_scores_gemma":[0.95839626,0.021403102,0.018980552,0.00032395188,0.00011413042,0.00078198995],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10582817,0.00015227549,0.004753399,0.00016058963,0.00007127142,0.000005073366,0.00012691219,0.00018824998,0.0001657002],"category_scores_gemma":[0.06281332,0.0001315786,0.00040004283,0.000093848816,0.00025178463,0.00021580976,0.000023349374,0.00029289996,0.000049406583],"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":[0.00090022525,0.00039781324,0.97602123,0.000097451535,0.00018411563,0.0000022811935,0.00008898292,0.00024386388,6.9935496e-8,0.01746541,0.0031565658,0.001441977],"study_design_scores_gemma":[0.0026144094,0.0023883935,0.9443289,0.00010903585,0.000014600928,0.000037951766,0.00009160331,0.000511314,2.163455e-8,0.041765556,0.00803523,0.00010295397],"about_ca_topic_score_codex":0.0006486063,"about_ca_topic_score_gemma":0.00012380509,"teacher_disagreement_score":0.1596075,"about_ca_system_score_codex":0.00018107577,"about_ca_system_score_gemma":0.0007228315,"threshold_uncertainty_score":0.945081},"labels":[],"label_agreement":null},{"id":"W2017265038","doi":"10.1016/j.jclinepi.2013.12.002","title":"Defining consensus: A systematic review recommends methodologic criteria for reporting of Delphi studies","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":3552,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; University of Toronto; Hospital for Sick Children","funders":"Division of Graduate Education; Canadian Institutes of Health Research; Canadian Liver Foundation","keywords":"Systematic review; Delphi method; Delphi; MEDLINE; Medicine; Computer science; Statistics; Political science; Mathematics","score_opus":0.9434568903010523,"score_gpt":0.7896438436165414,"score_spread":0.1538130466845109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017265038","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":[9.670412e-7,0.98337513,0.004286055,0.0075786533,0.0019076759,0.0023169236,0.00001428294,0.000030057468,0.0004902444],"genre_scores_gemma":[0.0000036422691,0.8556099,0.14192373,0.0013418087,0.0008024056,0.00019734145,0.000003669918,0.000036538488,0.000080980215],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.74022275,0.18211314,0.07493159,0.00079416385,0.0008065728,0.0011317723],"domain_scores_gemma":[0.1203859,0.73127234,0.14332075,0.0009134344,0.003664878,0.00044266888],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68460345,0.00045047613,0.040137906,0.00040091414,0.00020627145,0.000013387273,0.001540588,0.0013798552,0.00004099191],"category_scores_gemma":[0.9758203,0.00027947922,0.0061217234,0.000499473,0.0014855085,0.000058279034,0.0002954635,0.0021734675,0.0000076959595],"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":[0.000022972521,0.000044431345,0.000035310877,0.7819424,0.0011512204,0.000030785362,0.00007787504,2.0352203e-7,1.1728777e-8,0.006397912,0.03573627,0.17456058],"study_design_scores_gemma":[0.00011433896,0.0005343811,8.1962094e-7,0.5367388,0.0032251247,0.000189602,0.0003100855,0.0000045777056,2.1460318e-8,0.016320894,0.44238237,0.00017897025],"about_ca_topic_score_codex":0.00003110075,"about_ca_topic_score_gemma":0.000018742969,"teacher_disagreement_score":0.61983687,"about_ca_system_score_codex":0.00020448762,"about_ca_system_score_gemma":0.0018531182,"threshold_uncertainty_score":0.9999657},"labels":[],"label_agreement":null},{"id":"W2017939102","doi":"10.1016/j.jclinepi.2012.08.007","title":"Patient-level compared with study-level meta-analyses demonstrate consistency of D-dimer as predictor of venous thromboembolic recurrences","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","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":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Poisson regression; Medicine; Proportional hazards model; Meta-analysis; Hazard ratio; Meta-regression; Venous thromboembolism; Population; D-dimer; Regression analysis; Regression; Internal medicine; Statistics; Confidence interval; Thrombosis; Mathematics","score_opus":0.5575213485582176,"score_gpt":0.5100325951709211,"score_spread":0.04748875338729641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017939102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99256736,0.002383805,0.00036856552,0.002042288,0.00051287975,0.000958542,0.000034396813,0.000010237384,0.0011219162],"genre_scores_gemma":[0.98820025,0.0008859788,0.009363113,0.0012767497,0.00017825165,0.000031485346,0.0000060731145,0.00002197365,0.000036104575],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9878685,0.0031235972,0.0075117773,0.00041546693,0.00063853525,0.0004421243],"domain_scores_gemma":[0.9796676,0.010008234,0.0077165067,0.0006047627,0.0015413734,0.00046150215],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0076500643,0.0003540945,0.009767695,0.0002747581,0.000059095688,0.000006851103,0.00036090479,0.00024127107,0.0009143767],"category_scores_gemma":[0.01450924,0.0001958176,0.0015398106,0.00029404418,0.0009370665,0.00015493167,0.00010924732,0.00072525564,0.000024786148],"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":[0.0012059298,0.022882272,0.87206584,0.00037452107,0.06531025,0.00012399071,0.0010998092,0.00047158287,0.00028783904,0.0011740405,0.015963485,0.01904047],"study_design_scores_gemma":[0.0029974962,0.020785715,0.95249647,0.00024202921,0.018289462,0.00010666271,0.0016362664,0.000089479756,0.00016189381,0.002713042,0.00030677617,0.00017468314],"about_ca_topic_score_codex":0.001028354,"about_ca_topic_score_gemma":0.00007723088,"teacher_disagreement_score":0.08043068,"about_ca_system_score_codex":0.000023742043,"about_ca_system_score_gemma":0.00058770605,"threshold_uncertainty_score":0.9999989},"labels":[],"label_agreement":null},{"id":"W2018193498","doi":"10.1016/j.jclinepi.2008.08.015","title":"Why we will remain pragmatists: four problems with the impractical mechanistic framework and a better solution","year":2009,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":35,"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 Hospital; Institute for Clinical Evaluative Sciences; University of Victoria; Canadian College of Naturopathic Medicine","funders":"","keywords":"Pragmatism; Scopus; Epistemology; Medicine; Alternative medicine; Ideal (ethics); Clinical trial; MEDLINE; Focus (optics); Psychology; Philosophy; Political science; Pathology","score_opus":0.5746042778282816,"score_gpt":0.526787245823019,"score_spread":0.04781703200526266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018193498","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":[0.0004153816,0.0031260287,0.24142152,0.75304025,0.001229537,0.0005209969,0.00005747749,0.000013903076,0.0001749202],"genre_scores_gemma":[0.0010189922,0.0025037748,0.06163037,0.92199343,0.012546875,0.000031577652,0.000017151686,0.00005947756,0.00019836705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9656456,0.012877859,0.01949901,0.000871694,0.00022847051,0.000877384],"domain_scores_gemma":[0.84212387,0.12672909,0.02978032,0.00077803544,0.0002589347,0.00032973778],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16455458,0.0004777779,0.006615116,0.00032238878,0.00022974664,0.00007859061,0.0006771684,0.00257195,0.00024320275],"category_scores_gemma":[0.20300259,0.0003468779,0.00066150655,0.00015402123,0.00053814787,0.00046763427,0.00009094303,0.0076211016,0.00016695821],"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":[0.00007766955,0.000057446894,0.0031240568,0.0003796608,0.00035232026,0.000053408774,0.000100581674,0.000033563847,5.340477e-8,0.028414348,0.96670187,0.0007050057],"study_design_scores_gemma":[0.00054417626,0.00088913157,0.003303902,0.0006040278,0.00008431144,0.00048449586,0.000026351878,0.0012784778,1.1414232e-8,0.3510247,0.6415017,0.000258708],"about_ca_topic_score_codex":0.0001144997,"about_ca_topic_score_gemma":0.000057507346,"teacher_disagreement_score":0.32520014,"about_ca_system_score_codex":0.0003197851,"about_ca_system_score_gemma":0.00040424618,"threshold_uncertainty_score":0.9998983},"labels":[],"label_agreement":null},{"id":"W2018263176","doi":"10.1016/j.jclinepi.2008.05.006","title":"Radiographs of hip fractures were digitally altered to mask surgeons to the type of implant without compromising the reliability of quality ratings or making the rating process more difficult","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":22,"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 General Hospital; McMaster University; Western University","funders":"","keywords":"Medicine; Radiography; Blinding; Reliability (semiconductor); Subtraction; Orthopedic surgery; Inter-rater reliability; Surgery; Orthodontics; Randomized controlled trial; Rating scale","score_opus":0.1987573113529931,"score_gpt":0.5062857307834927,"score_spread":0.3075284194304996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018263176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98879385,0.00031301862,0.0023520095,0.007075521,0.00089140196,0.00042056158,0.00004940507,0.000008866962,0.00009534265],"genre_scores_gemma":[0.9942793,0.000065989996,0.0018207973,0.0035354597,0.00025553015,0.000003999674,0.0000023125035,0.000016930433,0.000019674962],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9893021,0.0036100103,0.0058289804,0.0003381417,0.00052642403,0.000394324],"domain_scores_gemma":[0.9620436,0.030498689,0.0057475674,0.00069714064,0.00084605574,0.00016693752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01861492,0.00024423053,0.0022236302,0.00012020044,0.00023593279,0.0000181427,0.0010626292,0.00017929873,0.00003401552],"category_scores_gemma":[0.061004378,0.00010229394,0.0010366881,0.00070983096,0.0009795252,0.00015012149,0.00016774503,0.0010857264,0.0000013392626],"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":[0.0023755045,0.00022308157,0.984722,0.00012560732,0.0002783639,0.00001788513,0.002142917,0.002342011,0.00045647434,0.00007663325,0.0054894895,0.001750027],"study_design_scores_gemma":[0.0006406618,0.00053225376,0.9937989,0.0003683059,0.00010798435,0.00060380244,0.0016747987,0.00038804437,0.00037086167,0.00092342804,0.00046390854,0.0001270361],"about_ca_topic_score_codex":0.00018459899,"about_ca_topic_score_gemma":0.00006862051,"teacher_disagreement_score":0.042389456,"about_ca_system_score_codex":0.000016351185,"about_ca_system_score_gemma":0.00021057518,"threshold_uncertainty_score":0.9469052},"labels":[],"label_agreement":null},{"id":"W2018314121","doi":"10.1016/j.jclinepi.2014.12.006","title":"A review of the use of covariates in cluster randomized trials uncovers marked discrepancies between guidance and practice","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa; Women's College Hospital; University of Toronto","funders":"","keywords":"Covariate; CRTS; Randomization; Medicine; Randomized controlled trial; Cluster (spacecraft); Cluster randomised controlled trial; Statistics; Surgery; Computer science; Mathematics","score_opus":0.9623569045144317,"score_gpt":0.727645619232574,"score_spread":0.2347112852818577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018314121","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000121849325,0.97834367,0.010690972,0.007308584,0.0008973899,0.0025180378,0.00004112293,5.356058e-7,0.00018751594],"genre_scores_gemma":[0.000010452227,0.96739256,0.0284159,0.0034495068,0.00037300543,0.000020455904,0.0000026728549,0.000014780406,0.00032065916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.04736339,0.77190566,0.17725192,0.00083254336,0.0023444237,0.00030208597],"domain_scores_gemma":[0.0036418505,0.74620646,0.2452102,0.0025064675,0.0022536889,0.00018134288],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9515753,0.0005853846,0.15180795,0.00043251435,0.000033539094,0.00006069886,0.0027097221,0.00072825677,0.0004560117],"category_scores_gemma":[0.99679905,0.00017973379,0.031821214,0.001160967,0.0009637655,0.00030965236,0.0004472483,0.0013784282,0.000023531942],"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":[0.0049697463,0.00014846839,0.0069674244,0.08085585,0.008173022,0.000004939414,0.000036695074,0.00002924415,1.9812784e-8,0.0034657123,0.1570583,0.73829055],"study_design_scores_gemma":[0.0064160624,0.00009210642,0.00033304063,0.08841347,0.01419729,0.000062139865,0.000007809079,0.000058832393,5.8940097e-9,0.004562185,0.88573253,0.00012452801],"about_ca_topic_score_codex":0.0000404391,"about_ca_topic_score_gemma":0.000011296443,"teacher_disagreement_score":0.73816603,"about_ca_system_score_codex":0.00003151255,"about_ca_system_score_gemma":0.00094126083,"threshold_uncertainty_score":0.9778749},"labels":[],"label_agreement":null},{"id":"W2018430725","doi":"10.1016/j.jclinepi.2005.06.013","title":"The SCREEN I (Seniors in the Community: Risk Evaluation for Eating and Nutrition) index adequately represents nutritional risk","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Nutrition and Health in Aging","field":"Medicine","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":"University of Guelph","funders":"Health Canada","keywords":"Construct (python library); Structural equation modeling; Exploratory factor analysis; Risk factor; Index (typography); Construct validity; Risk assessment; Gerontology; Measure (data warehouse); Adaptation (eye); Medicine; Computer science; Psychology; Psychometrics; Data mining; Clinical psychology; Machine learning; Pathology","score_opus":0.3786937907103555,"score_gpt":0.559035046578287,"score_spread":0.18034125586793143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018430725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444869,0.002962495,0.0037340706,0.0469349,0.000359933,0.0010739296,0.000030897143,0.000007761546,0.00040911822],"genre_scores_gemma":[0.9798251,0.005728093,0.008480739,0.003859956,0.0019815448,0.000060535403,0.000033497006,0.000010422213,0.000020116095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97940135,0.016031059,0.0037512237,0.00015696444,0.0003561749,0.00030324614],"domain_scores_gemma":[0.9016174,0.09480464,0.0026601355,0.000258994,0.0005332019,0.00012564546],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.099590704,0.00011202615,0.00096468185,0.00011099972,0.0006963702,0.000018939922,0.00019484811,0.00024217503,0.000013469399],"category_scores_gemma":[0.08862941,0.00006372545,0.00032976997,0.00014927959,0.00034896043,0.000083190054,0.000032223325,0.0023815068,0.0000015346748],"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":[0.0017578023,0.00061555934,0.95858335,0.00007669256,0.000048971535,0.0000043294085,0.00005060037,0.00006009296,0.0000018137521,0.0014101147,0.012006942,0.025383752],"study_design_scores_gemma":[0.007233817,0.000823485,0.7649678,0.00033026427,0.00012307054,0.00013941126,0.0005280676,0.01005759,9.744821e-7,0.2067274,0.00902079,0.00004733273],"about_ca_topic_score_codex":0.00065189425,"about_ca_topic_score_gemma":0.0002892199,"teacher_disagreement_score":0.20531729,"about_ca_system_score_codex":0.000052131243,"about_ca_system_score_gemma":0.00015399962,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W2018803201","doi":"10.1016/s0895-4356(99)00160-2","title":"Randomized trials versus observational studies in adolescent pregnancy prevention","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":94,"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":"Observational study; Randomized controlled trial; Medicine; Psychological intervention; CINAHL; PsycINFO; Pregnancy; MEDLINE; Family medicine; Psychiatry; Surgery; Internal medicine","score_opus":0.9380215926437274,"score_gpt":0.7360098352874899,"score_spread":0.20201175735623755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018803201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095352,0.021401737,0.0015257892,0.044811234,0.01838167,0.002795219,0.000006712345,0.00002970165,0.0015126801],"genre_scores_gemma":[0.78691846,0.14878437,0.013041874,0.015580771,0.020785011,0.0002140157,0.000025581652,0.00006459543,0.014585335],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.8795796,0.1023109,0.016858045,0.000401983,0.00028082414,0.0005686444],"domain_scores_gemma":[0.6621632,0.32159957,0.014226069,0.00046972866,0.0010971909,0.00044425094],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17700537,0.00019164498,0.007367685,0.00012894135,0.00017217828,9.952893e-7,0.0002116023,0.00047991943,0.0008701438],"category_scores_gemma":[0.41809028,0.0001115708,0.0010825901,0.00017477009,0.00048607154,0.00015106848,0.00004963954,0.002277213,0.00011457706],"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":[0.47690928,0.001945216,0.3827553,0.000774741,0.00085166417,0.00003201828,0.0010067645,0.00040912116,0.000002331863,0.009457876,0.021923915,0.10393176],"study_design_scores_gemma":[0.38966817,0.0012670159,0.5075793,0.005719026,0.00025461506,0.000010177884,0.00086093205,0.00016475447,6.55908e-7,0.072980575,0.021285426,0.0002093402],"about_ca_topic_score_codex":0.000012045725,"about_ca_topic_score_gemma":0.000020224834,"teacher_disagreement_score":0.2410849,"about_ca_system_score_codex":0.00014822994,"about_ca_system_score_gemma":0.00079741643,"threshold_uncertainty_score":0.98934835},"labels":[{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2018964975","doi":"10.1016/s0895-4356(00)00263-8","title":"The Cooperative Familial Registry for Breast Cancer Studies","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"BRCA gene mutations in cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; Mount Sinai Hospital; Cancer Care Ontario","funders":"National Cancer Institute; Cancer Care Ontario; U.S. Department of Health and Human Services","keywords":"Family history; Breast cancer; Medicine; Etiology; Cancer registry; Family medicine; Cancer; Telephone interview; Epidemiology; Gynecology; Oncology; Gerontology; Internal medicine","score_opus":0.22374319965609157,"score_gpt":0.5316886640941004,"score_spread":0.30794546443800885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018964975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8458776,0.03584227,0.018141221,0.09063049,0.008652205,0.0003822792,0.0001276822,0.0000069518724,0.000339329],"genre_scores_gemma":[0.8802462,0.0910986,0.0049501816,0.009460714,0.011645972,0.00007410763,0.000007913507,0.000031021573,0.002485254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99636775,0.0011237971,0.0019278207,0.00023015123,0.00008215467,0.00026831552],"domain_scores_gemma":[0.99111205,0.0061163544,0.0014163853,0.00026825722,0.0009821209,0.00010481121],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008069683,0.000126461,0.00080459303,0.000018112016,0.0001694611,0.000006493333,0.00034208727,0.00025091076,0.000012140197],"category_scores_gemma":[0.03056564,0.00007358322,0.0004454182,0.00006054949,0.00063497154,0.000004548611,0.00007194608,0.00031558843,0.0000020144987],"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":[0.006141003,0.00018935204,0.18186802,0.000032708176,0.0028151732,0.000015874775,0.0000953423,0.0048667956,0.0029318386,0.0021583352,0.5906167,0.20826887],"study_design_scores_gemma":[0.0026921874,0.0015605476,0.1026312,0.000061532795,0.000167299,0.00056446687,0.0006685584,0.00027882433,0.0005283239,0.00609457,0.88452065,0.0002318678],"about_ca_topic_score_codex":0.0000064990445,"about_ca_topic_score_gemma":0.000104738916,"teacher_disagreement_score":0.29390395,"about_ca_system_score_codex":0.000047796315,"about_ca_system_score_gemma":0.0005922619,"threshold_uncertainty_score":0.97760034},"labels":[],"label_agreement":null},{"id":"W2019056155","doi":"10.1016/j.jclinepi.2009.08.022","title":"Patient preferences before and after total knee arthroplasty","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; Women's College Hospital; McMaster University; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Canadian Institutes of Health Research","keywords":"WOMAC; Medicine; Kneeling; Physical therapy; Osteoarthritis; Arthroplasty; Total knee arthroplasty; Surgery","score_opus":0.07549364021078125,"score_gpt":0.4063708288231985,"score_spread":0.3308771886124173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019056155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98340005,0.0008427207,0.00016463052,0.013686168,0.001394499,0.00013445083,0.0000034195016,0.000014360574,0.00035972823],"genre_scores_gemma":[0.98613393,0.00027883533,0.00592615,0.0065019596,0.0009505705,0.0000014978057,0.0000011254309,0.0000086673235,0.00019727323],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99501,0.0010526608,0.003151956,0.00024553336,0.00020287409,0.0003369588],"domain_scores_gemma":[0.9925464,0.0052345414,0.0013279609,0.00020388994,0.00017189336,0.00051533047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003956067,0.0001836232,0.0020855858,0.000101449055,0.000038671755,0.000005543743,0.00003830482,0.00029863536,0.00017340473],"category_scores_gemma":[0.024661215,0.00011284419,0.0005095989,0.00006957273,0.00035109525,0.00013343373,0.00004612995,0.0010423337,0.000031665157],"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":[0.0011158377,0.00021013919,0.78420436,0.000012779028,0.00008985205,0.000143374,0.00009928181,0.000008032811,0.0000046619475,0.00019072718,0.0012437116,0.21267721],"study_design_scores_gemma":[0.0019889625,0.0128927855,0.9714364,0.00013284801,0.0000950137,0.0017223584,0.00006686229,0.000058819558,0.00000287446,0.005101332,0.0064133625,0.00008839728],"about_ca_topic_score_codex":0.0000027540195,"about_ca_topic_score_gemma":0.000015804766,"teacher_disagreement_score":0.21258882,"about_ca_system_score_codex":0.00001782802,"about_ca_system_score_gemma":0.00013855513,"threshold_uncertainty_score":0.9835545},"labels":[],"label_agreement":null},{"id":"W2019928099","doi":"10.1016/s0895-4356(01)00433-4","title":"Multiple imputation versus data enhancement for dealing with missing data in observational health care outcome analyses","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":132,"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; University of Calgary","funders":"","keywords":"Missing data; Observational study; Imputation (statistics); Computer science; Statistics; Data mining; Medicine; Mathematics","score_opus":0.932162341780281,"score_gpt":0.7061193995434054,"score_spread":0.2260429422368756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019928099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006727126,0.00061060284,0.9848945,0.0070003294,0.00040737705,0.0001735675,0.0001510969,0.0000053306403,0.000030048726],"genre_scores_gemma":[0.08414852,0.00017628096,0.91426724,0.0009658904,0.00032633063,0.000002128257,0.00009992179,0.000010906251,0.0000028020147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99298817,0.00182473,0.004326463,0.00036780583,0.00020155331,0.00029130094],"domain_scores_gemma":[0.86254776,0.13342884,0.0029392838,0.000645549,0.00025962893,0.00017893672],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017751312,0.00013198194,0.0016160582,0.00006227482,0.00006832036,0.0000114888335,0.00062528375,0.00011963672,0.00006389225],"category_scores_gemma":[0.25468013,0.00009054428,0.00009979592,0.00008336877,0.00009818356,0.00020234277,0.00014087286,0.00042698148,0.0000012576971],"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":[0.0016701305,0.0004454182,0.3131005,0.00044483884,0.00032529494,0.000021583262,0.00021349036,0.000259426,0.00000796249,0.054520242,0.0039512324,0.62503994],"study_design_scores_gemma":[0.008205194,0.0028376551,0.11484885,0.00051281316,0.00029384735,0.000025164909,0.00031666664,0.6381967,0.000004701219,0.23120342,0.0032285876,0.00032636125],"about_ca_topic_score_codex":0.000059450675,"about_ca_topic_score_gemma":0.00018446817,"teacher_disagreement_score":0.6379373,"about_ca_system_score_codex":0.000057111356,"about_ca_system_score_gemma":0.00016156449,"threshold_uncertainty_score":0.751598},"labels":[],"label_agreement":null},{"id":"W2020049366","doi":"10.1016/j.jclinepi.2006.09.006","title":"Not all “quality-adjusted life years” are equal","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":103,"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; McGill University Health Centre; Montreal General Hospital; St. Paul's Hospital; Vancouver Coastal Health; Vancouver Coastal Health Research Institute; University of British Columbia; Arthritis Research Centre of Canada","funders":"","keywords":"Quality-adjusted life year; Infliximab; Medicine; Cost–utility analysis; Health Utilities Index; Quality of life (healthcare); Statistics; Cost effectiveness; Econometrics; Actuarial science; Mathematics; Health related quality of life; Internal medicine; Economics","score_opus":0.8663123896947132,"score_gpt":0.6203724980696802,"score_spread":0.24593989162503305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020049366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7426689,0.0042845206,0.021019371,0.22381172,0.0050400994,0.00032291014,0.00016407052,0.000042022428,0.002646334],"genre_scores_gemma":[0.84695053,0.00041871183,0.011004443,0.13463695,0.0062575773,0.000008429131,0.000016893491,0.000040050803,0.00066642364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.954544,0.008771526,0.035265476,0.00057854265,0.00015047437,0.00068994873],"domain_scores_gemma":[0.8965198,0.06661428,0.03528736,0.00063692307,0.00025701147,0.000684671],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23030005,0.000237519,0.0060678143,0.0003389937,0.000073483134,0.000024105975,0.000592566,0.00069535075,0.0005911264],"category_scores_gemma":[0.28699675,0.00025529822,0.0010765753,0.00014755473,0.00025999692,0.0003369986,0.00008359542,0.0011108773,0.0018262061],"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":[0.00012350923,0.0002591097,0.6264616,0.00009421513,0.00018319099,0.000011479985,0.00006178069,0.00080322655,0.0000011638202,0.22064398,0.15106456,0.00029213793],"study_design_scores_gemma":[0.0016857182,0.0002878913,0.7555761,0.000054231212,0.000017925831,0.000022215238,0.00011364891,0.00073503156,4.5716186e-7,0.08108403,0.16019763,0.000225144],"about_ca_topic_score_codex":0.00076056534,"about_ca_topic_score_gemma":0.00012889219,"teacher_disagreement_score":0.13955995,"about_ca_system_score_codex":0.00020684367,"about_ca_system_score_gemma":0.000344104,"threshold_uncertainty_score":0.9999899},"labels":[],"label_agreement":null},{"id":"W2020681400","doi":"10.1016/j.jclinepi.2003.07.012","title":"Modeling recurrence in colorectal cancer","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":41,"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; Ligue Contre le Cancer; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Colorectal cancer; Medicine; Cancer; Oncology; Internal medicine","score_opus":0.27460392420191504,"score_gpt":0.5153615333101835,"score_spread":0.2407576091082685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020681400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743287,0.0015442237,0.014668723,0.0075754235,0.0015098746,0.000082975625,8.454825e-7,0.000010578598,0.00027868786],"genre_scores_gemma":[0.98917246,0.0016387575,0.0068032523,0.0013085338,0.0010544214,0.000004650892,4.9584855e-7,0.000007753498,0.000009676094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99617714,0.000613694,0.002636278,0.00019004726,0.00013869951,0.00024413633],"domain_scores_gemma":[0.99621624,0.0024980952,0.00075804075,0.00008503007,0.00021312924,0.0002294953],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009016837,0.00009871636,0.001477078,0.00014321858,0.000021654321,0.0000020948576,0.000092909744,0.00026563738,0.000031970325],"category_scores_gemma":[0.026865862,0.0000732608,0.00039695643,0.00020131485,0.000097816664,0.00007117175,0.000024006276,0.00123043,0.000005822181],"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":[0.018347332,0.00035627166,0.7189636,0.00004432924,0.00011285299,0.00017154729,0.00011995711,0.1425497,0.00017192491,0.00065592147,0.00018579874,0.11832073],"study_design_scores_gemma":[0.010417054,0.015138559,0.86054754,0.0013572464,0.00015007133,0.0012824478,0.00009703962,0.07930419,0.0003306834,0.030377395,0.00075336796,0.00024441764],"about_ca_topic_score_codex":0.00052407285,"about_ca_topic_score_gemma":0.00052979204,"teacher_disagreement_score":0.14158389,"about_ca_system_score_codex":0.00015521776,"about_ca_system_score_gemma":0.00064170413,"threshold_uncertainty_score":0.9813312},"labels":[],"label_agreement":null},{"id":"W2020721502","doi":"10.1016/j.jclinepi.2008.03.009","title":"Patients' gender affected physicians' clinical decisions when presented with standardized patients but not for matching paper patients","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":43,"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; Toronto Western Hospital; St. Michael's Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; University Health Network; University of Toronto; Institute of Population and Public Health; Women's College Hospital; University of Ottawa","funders":"","keywords":"Medicine; Referral; Odds ratio; Confidence interval; Orthopedic surgery; Propensity score matching; Matching (statistics); Physical therapy; Internal medicine; Osteoarthritis; Odds; Family medicine; Surgery; Logistic regression; Alternative medicine; Pathology","score_opus":0.14081807668790414,"score_gpt":0.45747756012424856,"score_spread":0.3166594834363444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020721502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97502285,0.000050459967,0.016395187,0.005041771,0.0019776763,0.0012030631,0.00011312483,0.0000431871,0.00015267229],"genre_scores_gemma":[0.9410079,0.00014115982,0.038933605,0.01863773,0.0009924755,0.000009170105,0.00009639251,0.00005777986,0.00012378002],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9875028,0.0030769636,0.007138467,0.0006474237,0.0008383383,0.00079597486],"domain_scores_gemma":[0.9572794,0.034656182,0.004501136,0.00060464325,0.0021677166,0.0007909619],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007890712,0.0004439968,0.0046213423,0.00019162416,0.00015149007,0.000016052858,0.00034311152,0.00059784454,0.00008023203],"category_scores_gemma":[0.117432594,0.00028270483,0.0017973768,0.00016462283,0.00037251684,0.00036907714,0.00009705178,0.001566361,0.000025973315],"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":[0.014754301,0.0035666355,0.8794447,0.0000228748,0.00061029795,0.000015060545,0.00008398877,0.000049122405,0.000008457572,0.00009562911,0.016491925,0.08485696],"study_design_scores_gemma":[0.03906663,0.015252071,0.9337952,0.00032881155,0.0005219953,0.000010071667,0.000033252352,0.000114364455,0.000007894519,0.0031119573,0.0074980943,0.00025965177],"about_ca_topic_score_codex":0.0000075253392,"about_ca_topic_score_gemma":0.000009336719,"teacher_disagreement_score":0.10954188,"about_ca_system_score_codex":0.00009560461,"about_ca_system_score_gemma":0.0003002984,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W2020923405","doi":"10.1016/j.jclinepi.2006.04.008","title":"Millennium Cohort: The 2001–2003 baseline prevalence of mental disorders in the U.S. military","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Posttraumatic Stress Disorder Research","field":"Psychology","cited_by":218,"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 Armed Forces","funders":"","keywords":"Cohort; Baseline (sea); Medicine; Millennium Cohort Study (United States); Cohort study; Epidemiology; Environmental health; Demography; Internal medicine; Political science","score_opus":0.20820340814370647,"score_gpt":0.5180881188348272,"score_spread":0.3098847106911207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020923405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9030592,0.03200332,0.0007926636,0.052592777,0.0020971303,0.0009397635,0.00006184249,0.000007314491,0.008445992],"genre_scores_gemma":[0.98465276,0.010829327,0.00087865756,0.0025400068,0.0005533953,0.000034984507,0.0000075877933,0.000019213867,0.0004840685],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97137463,0.021185065,0.0058694836,0.00035531208,0.0004943637,0.0007211596],"domain_scores_gemma":[0.9519722,0.045375373,0.0016332999,0.00069902214,0.0002101551,0.00010996446],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058070004,0.00019840915,0.0014695456,0.00013813446,0.00006714851,0.0000028076126,0.0013701811,0.0003103137,0.001239734],"category_scores_gemma":[0.035772018,0.00010166908,0.00052844186,0.00040483646,0.0012830367,0.00006850778,0.000088318564,0.0015611963,0.00004106116],"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":[0.0004897355,0.0010683199,0.8574351,0.000044608325,0.00012622151,0.000014299843,0.0002516483,0.00014509528,0.0000028986437,0.0020699045,0.1303939,0.007958274],"study_design_scores_gemma":[0.0015883654,0.00070395763,0.975606,0.00007325012,0.000064839674,0.00008743385,0.0005355735,0.00062290067,0.0000010801592,0.008388675,0.01223664,0.00009126232],"about_ca_topic_score_codex":0.0017596752,"about_ca_topic_score_gemma":0.0011550335,"teacher_disagreement_score":0.11817094,"about_ca_system_score_codex":0.000027893544,"about_ca_system_score_gemma":0.00016734615,"threshold_uncertainty_score":0.99967325},"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":"W2021610782","doi":"10.1016/j.jclinepi.2014.04.010","title":"Pragmatic trials can be designed as optimal medical care: principles and methods of care trials","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":88,"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; University of Alberta Hospital; Université de Montréal; Hôpital Notre-Dame","funders":"Cancer Research UK","keywords":"Clinical trial; Medicine; Simple (philosophy); Randomized controlled trial; Medical care; Health care; Alternative medicine; MEDLINE; Research design; Bureaucracy; Intensive care medicine; Nursing; Surgery","score_opus":0.8337137284114794,"score_gpt":0.6767624370862243,"score_spread":0.1569512913252551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021610782","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47507483,0.028393202,0.2657021,0.22114345,0.0055212774,0.0016484514,0.0002141949,0.000028006412,0.002274503],"genre_scores_gemma":[0.42891213,0.005005539,0.5229684,0.038159188,0.0047115926,0.000050076793,0.000027353333,0.000062659055,0.00010303225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7943952,0.13202396,0.07185787,0.0007609856,0.0002885481,0.00067343784],"domain_scores_gemma":[0.22198553,0.70099014,0.07401555,0.0008754535,0.0007097485,0.0014235722],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7132435,0.00026330302,0.015650319,0.00036760618,0.00009667636,0.000018455421,0.0005596782,0.0009163542,0.0005277193],"category_scores_gemma":[0.93072444,0.00022391905,0.0013307644,0.00011463269,0.00045030066,0.00016415399,0.00011190482,0.0008310203,0.000030587813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017723937,0.0004238296,0.2939275,0.0036636887,0.0022880617,0.000012183437,0.008538904,0.0021295373,0.000012559433,0.6066496,0.017938623,0.06264315],"study_design_scores_gemma":[0.030296663,0.013549838,0.16075376,0.0021443854,0.0010067509,0.00040517023,0.011617687,0.020642763,0.000091930415,0.22722125,0.5306241,0.0016456997],"about_ca_topic_score_codex":0.00028286918,"about_ca_topic_score_gemma":0.00008050676,"teacher_disagreement_score":0.5724097,"about_ca_system_score_codex":0.00016986238,"about_ca_system_score_gemma":0.0011690906,"threshold_uncertainty_score":0.99896336},"labels":[],"label_agreement":null},{"id":"W2021817747","doi":"10.1016/j.jclinepi.2009.05.007","title":"Trial sample size, but not trial quality, is associated with positive study outcome","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"National Center for Research Resources","keywords":"Medicine; Jadad scale; Randomized controlled trial; Sample size determination; Blinding; Logistic regression; Internal medicine; Clinical trial; Placebo; Outcome (game theory); Psychological intervention; Physical therapy; Alternative medicine; Statistics; Psychiatry; Pathology","score_opus":0.9570125176928788,"score_gpt":0.7341961162636582,"score_spread":0.22281640142922055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021817747","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96836764,0.00006666405,0.008206325,0.018964062,0.0021076864,0.0015418608,0.000042379535,0.0000041124117,0.00069928233],"genre_scores_gemma":[0.9743255,0.000020121506,0.0058949944,0.016046956,0.0016968092,0.0000066485263,0.000001713525,0.000010206081,0.001997068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6046496,0.28605,0.101324975,0.0013127989,0.006020228,0.0006424251],"domain_scores_gemma":[0.049708392,0.8457143,0.09680794,0.0028908965,0.0040944736,0.0007840358],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7728609,0.00043225626,0.027673371,0.00028110703,0.00014652479,0.00018157736,0.0023838612,0.00048394012,0.0035889493],"category_scores_gemma":[0.9632195,0.00017457831,0.008670684,0.0008503341,0.00020691352,0.00024403578,0.00011070746,0.0014071771,0.0002875309],"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":[0.24908097,0.0049279416,0.6735462,0.0000047745243,0.0035844613,0.00009862449,0.00037498522,0.00007034239,0.0000022605857,0.0016026759,0.047577493,0.019129248],"study_design_scores_gemma":[0.17714581,0.023615263,0.7537899,0.000033474815,0.0012433575,0.000022478984,0.00044990893,0.00020709918,6.665963e-7,0.040553972,0.0026783077,0.0002597366],"about_ca_topic_score_codex":0.000048967388,"about_ca_topic_score_gemma":0.00006004672,"teacher_disagreement_score":0.55966425,"about_ca_system_score_codex":0.00005778539,"about_ca_system_score_gemma":0.00033846791,"threshold_uncertainty_score":0.9973219},"labels":[],"label_agreement":null},{"id":"W2022735106","doi":"10.1016/j.jclinepi.2003.11.003","title":"Response shift influenced estimates of change in health-related quality of life poststroke","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","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":"Jewish General Hospital; William Osler Health System; Institut national de psychiatrie légale Philippe-Pinel; Royal Victoria Hospital","funders":"","keywords":"Medicine; Stroke (engine); Recall bias; Physical therapy; Quality of life (healthcare); Recall; Interpretability; Test (biology); Activities of daily living; Physical medicine and rehabilitation; Gerontology; Psychology","score_opus":0.3567227040387957,"score_gpt":0.5558226583862469,"score_spread":0.1990999543474512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022735106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9364718,0.0018955064,0.00023449355,0.06063118,0.0005192088,0.00020981868,0.000007681148,0.000005647867,0.000024637291],"genre_scores_gemma":[0.984152,0.00062893215,0.010149615,0.004936742,0.00011343637,0.0000021064573,0.0000017438955,0.00000838074,0.000007014496],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9831442,0.0058062994,0.0103828665,0.00017775077,0.00022404768,0.0002647827],"domain_scores_gemma":[0.93482554,0.057970025,0.006246755,0.00024234274,0.00031377617,0.0004015369],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048051555,0.000121047255,0.0037640943,0.00033030432,0.000012790911,6.8114423e-7,0.0001295771,0.00039070172,0.00006444517],"category_scores_gemma":[0.32884645,0.00008472022,0.0007829898,0.00022672488,0.00049714226,0.000077773904,0.000028504548,0.0008131458,0.000004656712],"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":[0.01396696,0.00054775225,0.98076576,0.00025462094,0.00011139066,0.000010498879,0.00040347615,0.0003783933,0.00035994875,0.0011554637,0.00004498916,0.0020007605],"study_design_scores_gemma":[0.006070991,0.004971114,0.98103875,0.0008046028,0.000020303003,0.00003559777,0.000102316604,0.000044799348,0.00003573111,0.0067186947,0.00010385904,0.000053250304],"about_ca_topic_score_codex":0.00067711185,"about_ca_topic_score_gemma":0.000031673302,"teacher_disagreement_score":0.28079492,"about_ca_system_score_codex":0.000078887606,"about_ca_system_score_gemma":0.0010667823,"threshold_uncertainty_score":0.9802312},"labels":[],"label_agreement":null},{"id":"W2022885125","doi":"10.1016/s0895-4356(02)00595-4","title":"The utility of the international child and adolescent overweight guidelines for predicting coronary heart disease risk factors","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":81,"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; Queen's University","funders":"National Institutes of Health","keywords":"Overweight; Medicine; Percentile; Risk factor; Obesity; Risk assessment; Framingham Risk Score; Blood pressure; Demography; Pediatrics; Disease; Internal medicine; Gerontology","score_opus":0.20739345442275134,"score_gpt":0.47324604881552745,"score_spread":0.2658525943927761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022885125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9592942,0.00068589416,0.00033499504,0.037642624,0.001579011,0.0002776884,0.00004057819,0.0000049311543,0.00014008378],"genre_scores_gemma":[0.99337655,0.0007102199,0.0007273553,0.0042064316,0.0009341715,0.0000021199303,0.0000016130853,0.0000096449085,0.000031885796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949659,0.0018448913,0.0024925305,0.00021147284,0.00026950258,0.00021569432],"domain_scores_gemma":[0.9747363,0.021934183,0.0020983308,0.00029937606,0.0006252832,0.00030657288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011545149,0.00013566039,0.0011052206,0.00002313815,0.00014655449,0.0000044163,0.00022723703,0.0001278284,0.000020422543],"category_scores_gemma":[0.22815636,0.000062395695,0.00078871055,0.00004826716,0.0005057412,0.00006399203,0.000111799985,0.0008702477,4.67108e-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":[0.0006163652,0.0013224576,0.9852265,0.000034020937,0.0001640935,0.0000010901938,0.0000073238725,0.000015360374,0.000003448851,0.00075142534,0.010807299,0.0010505822],"study_design_scores_gemma":[0.0011016558,0.00042822977,0.956376,0.00016232967,0.00021568559,0.000031832908,0.000034051962,0.0025436815,0.000022835087,0.018700868,0.020335505,0.00004731799],"about_ca_topic_score_codex":0.000008695462,"about_ca_topic_score_gemma":0.000004670044,"teacher_disagreement_score":0.2166112,"about_ca_system_score_codex":0.000022949078,"about_ca_system_score_gemma":0.00017960939,"threshold_uncertainty_score":0.7783452},"labels":[],"label_agreement":null},{"id":"W2023216389","doi":"10.1016/j.jclinepi.2014.09.003","title":"Statistical approaches to harmonize data on cognitive measures in systematic reviews are rarely reported","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":51,"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; Institut Universitaire de Gériatrie de Montréal; University of Victoria; McGill University Health Centre; Health and Social Services Centre University Institute of Geriatrics of Sherbrooke; McMaster University","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Harmonization; Comparability; Standardization; Meta-analysis; Computer science; Cognition; Context (archaeology); Data science; Data mining; Medicine; Mathematics; Pathology; Geography","score_opus":0.9572108892539244,"score_gpt":0.6799543988296927,"score_spread":0.2772564904242317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023216389","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":[0.36977,0.022827016,0.43625256,0.1115999,0.017204722,0.016836304,0.00046151323,0.000109408924,0.024938585],"genre_scores_gemma":[0.9535727,0.0015008446,0.018129792,0.023819912,0.0020660341,0.00017102256,0.000053504846,0.00005677845,0.00062942156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.92778546,0.05882911,0.011391682,0.0007565809,0.0004885599,0.000748639],"domain_scores_gemma":[0.80745,0.18195935,0.007506582,0.0015927964,0.0002737949,0.0012174987],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16443561,0.00023961955,0.0049212268,0.00024902532,0.000049374885,0.000010222832,0.0009315051,0.00041534472,0.0002453384],"category_scores_gemma":[0.6209811,0.00015769145,0.00025842368,0.00022281845,0.0002507454,0.00008062139,0.00021364409,0.0021294954,0.0005106574],"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":[0.008143345,0.0033703842,0.5550655,0.014532908,0.0008539137,0.00135397,0.00054263946,0.000033303328,0.0000014313969,0.044353835,0.17310889,0.19863988],"study_design_scores_gemma":[0.0046236077,0.005650486,0.9267232,0.016268993,0.00025170232,0.00055929774,0.0005695458,0.0015324568,0.0000011851698,0.012615824,0.030813524,0.00039017244],"about_ca_topic_score_codex":0.000057803,"about_ca_topic_score_gemma":0.00008412242,"teacher_disagreement_score":0.5838027,"about_ca_system_score_codex":0.00008141511,"about_ca_system_score_gemma":0.00016495222,"threshold_uncertainty_score":0.9251716},"labels":[],"label_agreement":null},{"id":"W2023232710","doi":"10.1016/j.jclinepi.2008.07.009","title":"Using the entire cohort in the receiver operating characteristic analysis maximizes precision of the minimal important difference","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Toronto; SickKids Foundation; Hospital for Sick Children; St. Michael's Hospital; McMaster University","funders":"Canadian Institutes of Health Research; European Commission","keywords":"Receiver operating characteristic; Cutoff; Medicine; Cohort; Minimal clinically important difference; Area under the curve; Prospective cohort study; Rating scale; Statistics; Rating curve; Cohort study; Internal medicine; Mathematics","score_opus":0.14398181312583216,"score_gpt":0.42314520121119087,"score_spread":0.2791633880853587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023232710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997613,0.0002816123,0.0009502386,0.0006398278,0.00030967608,0.00016330385,0.000009199952,8.018923e-7,0.00003229706],"genre_scores_gemma":[0.99707043,0.00071012956,0.0007529107,0.0010739517,0.00035215708,0.0000032688472,0.0000045342995,0.0000069209746,0.000025680223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9910887,0.005202428,0.003054545,0.00022456456,0.00021057164,0.00021922296],"domain_scores_gemma":[0.9937273,0.0029689225,0.0025137528,0.000519064,0.0002004556,0.00007045614],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012305685,0.0001380257,0.0009123664,0.000046613888,0.00012686018,0.0000056401414,0.00070610485,0.0002156103,0.000023575843],"category_scores_gemma":[0.027840273,0.000059643182,0.00084596593,0.00016890763,0.00051062263,0.000005933079,0.00014099573,0.00050448,5.052355e-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":[0.00036604961,0.00008444406,0.99496466,0.0000055096275,0.00027757353,0.000049078106,0.00007106971,0.0006800575,0.0030356448,0.000027226424,0.000121759214,0.00031690422],"study_design_scores_gemma":[0.0003973792,0.00012827248,0.9955099,0.00002766662,0.00029226582,0.000106484535,0.00007133751,0.0030424988,0.00010666761,0.00012676431,0.00012419162,0.00006656893],"about_ca_topic_score_codex":0.00002041204,"about_ca_topic_score_gemma":0.00003213945,"teacher_disagreement_score":0.015534588,"about_ca_system_score_codex":0.000011459074,"about_ca_system_score_gemma":0.00023971374,"threshold_uncertainty_score":0.98034865},"labels":[],"label_agreement":null},{"id":"W2023707099","doi":"10.1016/j.jclinepi.2009.07.011","title":"BLISS index using WOMAC index detects between-group differences at low-intensity symptom states in osteoarthritis","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","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; Ottawa Hospital; Université de Montréal; Sunnybrook Health Science Centre; McMaster University; Institute of Population and Public Health; University of Toronto; Health Sciences Centre","funders":"","keywords":"BLISS; WOMAC; Medicine; Physical therapy; Osteoarthritis; Pathology","score_opus":0.125352145583745,"score_gpt":0.4186027946877969,"score_spread":0.29325064910405185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023707099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99402374,0.0011164052,0.0010392466,0.0024852327,0.0009286076,0.00028685515,0.000008334075,0.000024103721,0.000087474284],"genre_scores_gemma":[0.9928145,0.0007139483,0.0016134874,0.0036864686,0.0010735526,0.0000019620086,0.000013092353,0.000019695732,0.00006329075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9927135,0.0016213158,0.0041725244,0.00044402512,0.00033572523,0.0007129149],"domain_scores_gemma":[0.9893023,0.0074201743,0.0020211248,0.00030603085,0.00027745048,0.000672957],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0065494585,0.00033415636,0.004033861,0.00034047905,0.0000850664,0.00001189261,0.0002131567,0.0007114895,0.00009859517],"category_scores_gemma":[0.010196829,0.0002506361,0.00071168033,0.00023865637,0.0002897618,0.00017936314,0.00008697175,0.0013603682,0.000018879755],"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":[0.0020422768,0.0003127814,0.9131231,0.000018591796,0.000070500566,0.000720873,0.00005910157,0.000017385037,0.00048512162,0.00005441247,0.000109467095,0.0829864],"study_design_scores_gemma":[0.0105490815,0.012507223,0.96385306,0.00091919716,0.00015930651,0.0007532621,0.00009706083,0.00041175267,0.00025429955,0.010040643,0.00023670503,0.00021841515],"about_ca_topic_score_codex":0.000042765332,"about_ca_topic_score_gemma":0.0001536493,"teacher_disagreement_score":0.082767986,"about_ca_system_score_codex":0.00016873729,"about_ca_system_score_gemma":0.00018487033,"threshold_uncertainty_score":0.9999946},"labels":[],"label_agreement":null},{"id":"W2024038163","doi":"10.1016/j.jclinepi.2013.06.017","title":"Assessing the applicability of findings in systematic reviews of complex interventions can enhance the utility of reviews for decision making","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":81,"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; Institute of Population and Public Health; Bruyère; University of Ottawa","funders":"","keywords":"Terminology; Psychological intervention; Systematic review; Context (archaeology); Management science; Resource (disambiguation); Population; Intervention (counseling); Documentation; Process (computing); Computer science; Risk analysis (engineering); Data science; MEDLINE; Psychology; Medicine; Engineering","score_opus":0.9613032131429035,"score_gpt":0.7463036265293126,"score_spread":0.21499958661359087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024038163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3686784,0.020331692,0.59787744,0.005127347,0.0005911621,0.0070551974,0.000011737535,8.63685e-7,0.0003261834],"genre_scores_gemma":[0.9569625,0.0011244282,0.041249778,0.0004456942,0.000065595166,0.000111813046,4.4694264e-7,0.0000050854896,0.000034645032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.55648494,0.258172,0.18153635,0.00097235286,0.0023505974,0.00048377094],"domain_scores_gemma":[0.059133742,0.78109485,0.15065855,0.005105919,0.0038377177,0.00016925113],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.78364384,0.00023756063,0.021389237,0.00019595708,0.000075472795,0.00004967418,0.0029428548,0.0001792076,0.0017780904],"category_scores_gemma":[0.8914343,0.00007505685,0.010717834,0.0008690702,0.0005710893,0.00019811916,0.00020795254,0.00056814775,0.000026235834],"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":[0.000094422976,0.00088089047,0.53283256,0.04257684,0.0006142076,5.339401e-7,0.00073072733,0.00013751895,0.00016473167,0.0034846326,0.06772924,0.35075366],"study_design_scores_gemma":[0.00039072844,0.00037577463,0.8008755,0.029171968,0.0009983393,0.000022455843,0.000982729,0.0253613,0.000009813074,0.131007,0.010651022,0.00015337883],"about_ca_topic_score_codex":0.000026812624,"about_ca_topic_score_gemma":0.00008976051,"teacher_disagreement_score":0.58828413,"about_ca_system_score_codex":0.000023689356,"about_ca_system_score_gemma":0.000100479345,"threshold_uncertainty_score":0.99918956},"labels":[],"label_agreement":null},{"id":"W2024256095","doi":"10.1016/j.jclinepi.2008.05.015","title":"Quantile regression and restricted cubic splines are useful for exploring relationships between continuous variables","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":326,"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":"Quantile regression; Ordinary least squares; Quantile; Regression; Linear regression; Statistics; Mathematics; Regression analysis; Continuous variable; Econometrics; Variables; Variable (mathematics); Multivariate adaptive regression splines; Polynomial regression","score_opus":0.7754066535483083,"score_gpt":0.576074492354978,"score_spread":0.1993321611933303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024256095","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":[0.5865539,0.00023290668,0.40897113,0.003574844,0.00042098577,0.00013746534,0.000014686044,0.000016980812,0.00007710477],"genre_scores_gemma":[0.3926066,0.00046677067,0.6058664,0.00021137034,0.00080008735,0.000003936096,0.0000015990292,0.0000103077755,0.00003299821],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9919781,0.0035235244,0.0038523288,0.00023636628,0.00012273647,0.000286955],"domain_scores_gemma":[0.7859841,0.2101057,0.0030776947,0.00019909625,0.0003689448,0.00026446144],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018530631,0.00015786894,0.0022230807,0.00009935015,0.00011692783,0.000011359486,0.00017905701,0.0003605254,0.00001424182],"category_scores_gemma":[0.52179986,0.00010289834,0.0002576358,0.00011264359,0.00013307993,0.0001174302,0.0000326815,0.00091105397,0.0000014235701],"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":[0.00034850466,0.00013648868,0.6630611,0.00006759726,0.00007332896,0.00001374679,0.000042416665,0.0000059017284,0.000022605562,0.2869366,0.0048995945,0.044392135],"study_design_scores_gemma":[0.00052721996,0.0005924153,0.4634402,0.0002549223,0.00008762491,0.000015786309,0.000042872405,0.00045514424,0.0000071350546,0.53354645,0.00096284156,0.000067383204],"about_ca_topic_score_codex":0.0000022477495,"about_ca_topic_score_gemma":0.0000010062655,"teacher_disagreement_score":0.50326926,"about_ca_system_score_codex":0.000012046936,"about_ca_system_score_gemma":0.000056677392,"threshold_uncertainty_score":0.6422384},"labels":[],"label_agreement":null},{"id":"W2024260605","doi":"10.1016/j.jclinepi.2013.05.017","title":"Measuring quality of care: considering conceptual approaches to quality indicator development and evaluation","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":97,"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; St. Michael's Hospital; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Quality (philosophy); Process management; Computer science; Performance indicator; Risk analysis (engineering); Quality management; Management science; Quality policy; Conceptual framework; Conceptual model; Operations management; Medicine; Business; Engineering","score_opus":0.9847785708335519,"score_gpt":0.7784890966531682,"score_spread":0.20628947418038368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024260605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741677,0.00014762429,0.00401313,0.019851387,0.00061584613,0.0008245242,0.0000052693968,0.000007417388,0.00036712023],"genre_scores_gemma":[0.93950206,0.000024969624,0.04731169,0.012775523,0.0003032683,0.00006431903,0.000001212093,0.0000069918015,0.000009938049],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9501097,0.036060993,0.012274084,0.00032213825,0.0006648757,0.00056819955],"domain_scores_gemma":[0.8270867,0.15719774,0.012414839,0.00040665397,0.0016218367,0.0012722352],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16305599,0.00012574813,0.001905382,0.00015643617,0.00023849958,0.0000032090013,0.00024273898,0.00028146262,0.00029169026],"category_scores_gemma":[0.27881458,0.00009633877,0.00012787501,0.00014377967,0.000418884,0.00018496974,0.00016472867,0.0008859157,0.000062653264],"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":[0.000085181295,0.000025709323,0.94398516,0.00023756217,0.000038204496,1.695036e-7,0.017479504,0.000037368314,0.000053130643,0.004302628,0.0009950538,0.032760322],"study_design_scores_gemma":[0.0014070263,0.00019356843,0.97737193,0.00010381852,0.000013153825,0.0000017279406,0.01340969,0.00004763124,0.000048678674,0.0018464656,0.0054654623,0.0000908492],"about_ca_topic_score_codex":0.0003216713,"about_ca_topic_score_gemma":0.00018527311,"teacher_disagreement_score":0.12302302,"about_ca_system_score_codex":0.00020565529,"about_ca_system_score_gemma":0.0029736427,"threshold_uncertainty_score":0.86180997},"labels":[],"label_agreement":null},{"id":"W2024389833","doi":"10.1016/j.jclinepi.2015.02.017","title":"Although not consistently superior, the absolute approach to framing the minimally important difference has advantages over the relative approach","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; University of Toronto; McMaster University","funders":"","keywords":"Pooling; Statistics; Cognition; Absolute (philosophy); Absolute deviation; Mean difference; Correlation; Mathematics; Medicine; Confidence interval; Computer science; Artificial intelligence","score_opus":0.76941782062422,"score_gpt":0.550179838640537,"score_spread":0.21923798198368305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024389833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46020135,0.008442269,0.073866256,0.4483617,0.0031532599,0.0014262606,0.000117207695,0.000023385384,0.004408311],"genre_scores_gemma":[0.7742979,0.0010998816,0.04579207,0.17489482,0.0029526392,0.00009831188,0.0000089373425,0.000056615238,0.00079884706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97017926,0.009992772,0.018192751,0.0006668514,0.00023954961,0.000728798],"domain_scores_gemma":[0.90398693,0.079171985,0.014778894,0.0011284256,0.00031929466,0.00061445864],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21355624,0.0003104325,0.0035019221,0.00012905392,0.0004489464,0.00008513971,0.0013954907,0.00040568132,0.000034484852],"category_scores_gemma":[0.21882208,0.00016761833,0.00082403305,0.00022541067,0.0010356841,0.00030371576,0.00024115309,0.0017932355,0.00015280278],"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":[0.00056522357,0.0005425975,0.47322652,0.000121154226,0.0009280285,0.0000063786993,0.009506416,0.0030518312,0.0000014500947,0.3832945,0.12765607,0.001099844],"study_design_scores_gemma":[0.0015117839,0.0006467434,0.70851386,0.000066315886,0.00007338098,0.00015949439,0.0036546728,0.025588471,2.3898426e-7,0.05004902,0.20941009,0.0003259049],"about_ca_topic_score_codex":0.0002868881,"about_ca_topic_score_gemma":0.000040446383,"teacher_disagreement_score":0.33324546,"about_ca_system_score_codex":0.00022834454,"about_ca_system_score_gemma":0.00075034215,"threshold_uncertainty_score":0.8098093},"labels":[],"label_agreement":null},{"id":"W2024445668","doi":"10.1016/j.jclinepi.2014.09.010","title":"A systematic review identifies valid comorbidity indices derived from administrative health data","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":356,"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; Arthritis Research Centre of Canada","funders":"","keywords":"Comorbidity; Medicine; Statistic; MEDLINE; Population; Statistics; Internal medicine; Environmental health","score_opus":0.7579636439800639,"score_gpt":0.6604261795886774,"score_spread":0.09753746439138644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024445668","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":[0.0000056497584,0.9885023,0.0007896935,0.005705739,0.0018720627,0.0025078226,0.00030737917,0.000030101983,0.00027922154],"genre_scores_gemma":[0.000017176779,0.98697096,0.0011804083,0.0082684085,0.0020922783,0.00003761506,0.0012484066,0.000052444215,0.00013229785],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.94663733,0.029042276,0.022149276,0.00095282495,0.0006418892,0.00057641533],"domain_scores_gemma":[0.8220785,0.11547149,0.056366574,0.0041784095,0.00048264884,0.0014223551],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065213814,0.00071150437,0.03716339,0.00022533399,0.00008081409,0.000034523528,0.0020451944,0.00064430945,0.00038687684],"category_scores_gemma":[0.20573027,0.00043310312,0.0034063556,0.0002446398,0.00059157173,0.0002171683,0.00067117607,0.0025463619,0.00018087678],"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":[0.00004237214,0.0002630921,0.000060653943,0.89523226,0.00472351,0.00019177824,0.000008272336,1.03856536e-7,2.1739706e-9,0.00018508117,0.0689279,0.030365001],"study_design_scores_gemma":[0.0006175352,0.0007083417,0.00022654324,0.6581698,0.019603023,0.0002507909,0.00003876598,0.000010721999,3.8160626e-9,0.00070341537,0.31945994,0.00021111438],"about_ca_topic_score_codex":0.00007373665,"about_ca_topic_score_gemma":0.000041236286,"teacher_disagreement_score":0.25053206,"about_ca_system_score_codex":0.00019805516,"about_ca_system_score_gemma":0.004701215,"threshold_uncertainty_score":0.99981207},"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":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2024714258","doi":"10.1016/j.jclinepi.2014.11.011","title":"Flexible modeling of disease activity measures improved prognosis of disability progression in relapsing–remitting multiple sclerosis","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":6,"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; Royal Victoria Hospital; McGill University Health Centre; Royal Victoria Regional Health Centre","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Proportional hazards model; Medicine; Multiple sclerosis; Hazard ratio; Expanded Disability Status Scale; Disease; Population; Multivariate statistics; Generalization; Physical therapy; Internal medicine; Confidence interval; Statistics; Psychiatry; Mathematics","score_opus":0.4598301803758694,"score_gpt":0.5128448233976028,"score_spread":0.05301464302173342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024714258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802655,0.00058664,0.013704331,0.004538399,0.0002757354,0.0005597931,0.000008483486,0.000014704703,0.000046414883],"genre_scores_gemma":[0.9807013,0.0014070563,0.017369447,0.000104817664,0.00036787585,0.000020095533,0.0000016616585,0.000022249966,0.0000054775037],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868757,0.005809138,0.0056943893,0.0004673354,0.000600601,0.0005528459],"domain_scores_gemma":[0.9568961,0.036343906,0.0042925877,0.0006123004,0.0011542962,0.0007008106],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044917025,0.00024044281,0.003737263,0.0001827309,0.00006439394,0.0000037622979,0.0002933781,0.00033293274,0.000011559741],"category_scores_gemma":[0.40152463,0.0001631648,0.001043102,0.00029777296,0.0010697872,0.00017343952,0.00024155689,0.0013952372,6.781722e-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":[0.00751696,0.0017744851,0.8172813,0.000514148,0.00014053994,9.771986e-7,0.00005652291,0.0018999879,0.007251982,0.000016082296,0.000041971336,0.16350503],"study_design_scores_gemma":[0.003716859,0.0015997714,0.7701284,0.0021786487,0.00010643518,0.0000017164153,0.000046857884,0.22056024,0.0011184197,0.00042075771,0.000026586016,0.00009526501],"about_ca_topic_score_codex":0.0002046283,"about_ca_topic_score_gemma":0.000055339937,"teacher_disagreement_score":0.35660762,"about_ca_system_score_codex":0.000118872886,"about_ca_system_score_gemma":0.0003046954,"threshold_uncertainty_score":0.98345894},"labels":[],"label_agreement":null},{"id":"W2024728015","doi":"10.1016/j.jclinepi.2012.04.011","title":"Application of the Knowledge-to-Action and Medical Research Council frameworks in the development of an osteoporosis clinical decision support tool","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":46,"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":"Knowledge translation; Psychological intervention; Action (physics); Medicine; Process (computing); Action research; Clinical decision support system; Knowledge management; Health care; Medical research; Health informatics; Decision support system; Computer science; Psychology; Nursing; Public health; Artificial intelligence; Political science; Pathology","score_opus":0.9123999649971976,"score_gpt":0.791196065872704,"score_spread":0.12120389912449359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024728015","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":[0.95698464,0.000051753672,0.018358514,0.0222632,0.0014117584,0.00067062717,0.0000035832102,0.0000027324713,0.00025317864],"genre_scores_gemma":[0.95959806,0.00021587007,0.02461273,0.0144683095,0.001033463,0.000047959762,6.8953e-7,0.00000795862,0.00001494187],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91377825,0.06286715,0.018892143,0.00041281007,0.002939119,0.0011105266],"domain_scores_gemma":[0.46732968,0.5171991,0.0081979055,0.0011142625,0.004790382,0.0013686547],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53081894,0.00010237308,0.0012504727,0.00015041122,0.00031244007,0.0000022669615,0.0008464928,0.0009808219,0.00016975775],"category_scores_gemma":[0.52422583,0.000053490287,0.00014996239,0.0006272563,0.0006740062,0.00018385144,0.0002969933,0.004253616,0.000037711125],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026096017,0.00026289758,0.7253167,0.000052683663,0.000008397399,2.0317354e-7,0.0077334493,0.0000031349575,0.0000071830973,0.0007867756,0.006762145,0.25880545],"study_design_scores_gemma":[0.00084741955,0.00045121094,0.8850823,0.00017260633,0.000008452189,0.000008352262,0.002684048,0.00027978903,0.0000031408333,0.002342954,0.10807764,0.00004206759],"about_ca_topic_score_codex":0.00009232825,"about_ca_topic_score_gemma":0.0013555412,"teacher_disagreement_score":0.45433196,"about_ca_system_score_codex":0.00028609214,"about_ca_system_score_gemma":0.008271475,"threshold_uncertainty_score":0.9980436},"labels":[],"label_agreement":null},{"id":"W2025236314","doi":"10.1016/j.jclinepi.2006.05.005","title":"Finding information about the burden of disease","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","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 Ottawa; Institute of Population and Public Health","funders":"","keywords":"Epidemiology; Clinical epidemiology; Medicine; Clinical Practice; MEDLINE; Disease; Data science; Family medicine; Intensive care medicine; Computer science; Pathology; Political science","score_opus":0.3255503702633889,"score_gpt":0.6006289123668296,"score_spread":0.2750785421034407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025236314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59242976,0.0020443758,0.009169325,0.3668528,0.0076078866,0.0005821813,0.00003854012,0.000025536618,0.021249585],"genre_scores_gemma":[0.9319355,0.0011751734,0.0017576729,0.05843296,0.0059884344,0.000007841848,0.0000128997835,0.000009222935,0.00068027904],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868503,0.0053597395,0.007168423,0.00007446992,0.00018237479,0.00036465505],"domain_scores_gemma":[0.9401396,0.05277503,0.006218756,0.00024444488,0.00041093215,0.00021122291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027907923,0.00009197165,0.0013480597,0.00009625616,0.00022158634,0.0000015774041,0.0003242542,0.00027782778,0.00026360547],"category_scores_gemma":[0.047459036,0.000049634626,0.0004822356,0.00009971331,0.00017386857,0.0002299456,0.00008474931,0.0014078565,0.0000848341],"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":[0.0005242402,0.000030064188,0.6390067,0.00019034393,0.000033975826,0.0000030847914,0.00022330014,0.00038603347,8.972577e-7,0.019541308,0.32711703,0.012943065],"study_design_scores_gemma":[0.00070508133,0.00012994575,0.62445176,0.00008895304,0.00004048675,0.0000019614822,0.0001519598,0.00018995635,1.4388704e-7,0.020844026,0.353358,0.000037723723],"about_ca_topic_score_codex":0.00038914997,"about_ca_topic_score_gemma":0.000016183067,"teacher_disagreement_score":0.33950576,"about_ca_system_score_codex":0.00008225525,"about_ca_system_score_gemma":0.0015983105,"threshold_uncertainty_score":0.9672385},"labels":[],"label_agreement":null},{"id":"W2025434594","doi":"10.1016/s0895-4356(99)00191-2","title":"Occurrence and risk factors of oral candidiasis treated with oral antifungals in seniors using inhaled steroids","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Antifungal resistance and susceptibility","field":"Medicine","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":"Université de Montréal; Hôpital du Sacré-Cœur de Montréal","funders":"Université de Montréal","keywords":"Medicine; Incidence (geometry); Asthma; Drug; Risk factor; Internal medicine; Pharmacology","score_opus":0.1952096465301551,"score_gpt":0.467313150949183,"score_spread":0.2721035044190279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025434594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99893904,0.0004532982,0.00012362874,0.0001779877,0.00008016553,0.00014359016,0.00003876319,0.0000050957046,0.00003844954],"genre_scores_gemma":[0.9952534,0.0024404817,0.0020599568,0.00015953262,0.00004770373,3.580665e-7,0.0000059306385,0.0000070593005,0.000025601506],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9932872,0.002663339,0.0032336537,0.00029216363,0.00018995797,0.00033370414],"domain_scores_gemma":[0.9912399,0.006351477,0.0016372367,0.00023227082,0.00021178953,0.00032734743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00828318,0.00019609804,0.0030553713,0.00014543108,0.00003125523,0.000003935185,0.00010121039,0.00031953564,0.00017952766],"category_scores_gemma":[0.01282153,0.000116652875,0.00032071536,0.0002503201,0.0006536563,0.00014440862,0.000017405036,0.0009403366,0.0000019210838],"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":[0.003966179,0.00026920115,0.98385143,0.000043485892,0.00016766613,0.00012168643,0.00008481333,0.00009870577,0.00010376159,0.0000028972572,0.00008344647,0.01120671],"study_design_scores_gemma":[0.0032086945,0.0023271698,0.99268895,0.00025583478,0.00029569166,0.00014796667,0.00018929425,0.00051563425,0.00009828928,0.000075602096,0.00009372507,0.000103152415],"about_ca_topic_score_codex":0.0008496319,"about_ca_topic_score_gemma":0.00037335354,"teacher_disagreement_score":0.011103557,"about_ca_system_score_codex":0.000041599065,"about_ca_system_score_gemma":0.00028165168,"threshold_uncertainty_score":0.9954939},"labels":[],"label_agreement":null},{"id":"W2025550817","doi":"10.1016/s0895-4356(02)00430-4","title":"Body mass index (BMI) and waist circumference (WC) as screening tools for cardiovascular risk factors in Guadeloupean women","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":102,"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":"","keywords":"Waist; Body mass index; Circumference; Medicine; Body volume index; Obesity; Index (typography); Internal medicine; Fat mass; Classification of obesity; Mathematics; Computer science","score_opus":0.22160571634326995,"score_gpt":0.4081393245759234,"score_spread":0.18653360823265344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025550817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610457,0.0069147525,0.029674876,0.00081435125,0.0005832403,0.00053511496,0.000014848701,0.000020585268,0.00039657843],"genre_scores_gemma":[0.9855905,0.0068512405,0.0052432367,0.00080457656,0.001353348,0.000022690663,0.000006087035,0.000040456616,0.00008782562],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9914385,0.003059898,0.0037252794,0.0005459145,0.00043735973,0.0007930302],"domain_scores_gemma":[0.9827086,0.014209614,0.0014535607,0.0006193455,0.0002751588,0.00073377433],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03057623,0.00032416932,0.0050762696,0.0002718068,0.00008950975,0.0000267412,0.00028098666,0.00062619086,0.00011640728],"category_scores_gemma":[0.1078171,0.00024412684,0.0031509928,0.00019157254,0.00037501272,0.00025672864,0.00007101919,0.0017370858,0.000010282636],"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":[0.0004004832,0.0001652299,0.6237588,0.000083281186,0.002903108,0.00012056951,0.000107001775,0.0004836628,0.0000041288527,0.00006954813,0.00039130435,0.37151286],"study_design_scores_gemma":[0.0073117907,0.0021179786,0.9421786,0.00023476801,0.00072889886,0.00017775416,0.00040958298,0.0023591318,0.0000120599625,0.004156599,0.040038597,0.00027424053],"about_ca_topic_score_codex":0.0007542759,"about_ca_topic_score_gemma":0.00002018399,"teacher_disagreement_score":0.37123862,"about_ca_system_score_codex":0.00009362359,"about_ca_system_score_gemma":0.000105775944,"threshold_uncertainty_score":0.99822575},"labels":[],"label_agreement":null},{"id":"W2026724598","doi":"10.1016/j.jclinepi.2005.03.010","title":"In a retrospective study of chronic obstructive pulmonary disease inpatients, respiratory comorbidities were significantly associated with prognosis","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Health Canada; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Pulmonary disease; Comorbidity; Retrospective cohort study; COPD; Internal medicine; Intensive care medicine; Respiratory system; Respiratory disease; Epidemiology; Lung","score_opus":0.12353136564313483,"score_gpt":0.43124790648805794,"score_spread":0.3077165408449231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026724598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940431,0.0017524688,0.000016694237,0.0023206717,0.00030487534,0.0012214313,0.00006519833,0.000015675241,0.0002598757],"genre_scores_gemma":[0.9977865,0.00018768218,0.00018295333,0.00065164216,0.0009734515,0.00005253015,0.000010604361,0.000046106918,0.000108534805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9875134,0.0054819924,0.0048053246,0.00063338503,0.00088957674,0.0006763184],"domain_scores_gemma":[0.9865031,0.007255545,0.0037295043,0.0005055856,0.0011894795,0.0008167485],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008501583,0.00035493562,0.0035295852,0.0005067084,0.00006998953,0.000005429272,0.000388713,0.0003124575,0.00024529966],"category_scores_gemma":[0.030817313,0.00026179574,0.0005755604,0.00056487747,0.0011316674,0.00043992916,0.00015148535,0.0021859526,0.000007089564],"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":[0.0073292158,0.009894375,0.97388387,0.00015047514,0.00069706317,0.001297847,0.00020430698,0.00040304018,0.00003250543,0.00020189874,0.00048349603,0.0054219035],"study_design_scores_gemma":[0.0073021096,0.0079331035,0.9800735,0.0005532242,0.00040497252,0.000046603178,0.001151056,0.00082691235,0.000016156557,0.001109601,0.00037496068,0.00020777408],"about_ca_topic_score_codex":0.000070770526,"about_ca_topic_score_gemma":0.0001780111,"teacher_disagreement_score":0.02231573,"about_ca_system_score_codex":0.0014021342,"about_ca_system_score_gemma":0.0021037548,"threshold_uncertainty_score":0.99998343},"labels":[],"label_agreement":null},{"id":"W2026841764","doi":"10.1016/j.jclinepi.2013.07.009","title":"The Quick Mild Cognitive Impairment screen correlated with the Standardized Alzheimer's Disease Assessment Scale–cognitive section in clinical trials","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Clinical Dementia Rating; Dementia; Cog; Medicine; Clinical trial; Cognition; Alzheimer's disease; Rating scale; Internal medicine; Disease; Psychology; Psychiatry; Developmental psychology","score_opus":0.24406116336658146,"score_gpt":0.5594586465419924,"score_spread":0.31539748317541094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026841764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9313113,0.0016109614,0.0056172437,0.055880886,0.0010829922,0.003617977,0.000034842615,0.000019125175,0.00082466454],"genre_scores_gemma":[0.988083,0.0031976404,0.00047617595,0.0060415505,0.0016895445,0.00017284829,0.000029031296,0.000032953834,0.00027727743],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94824564,0.04124804,0.008124058,0.00055490015,0.0009816501,0.0008457264],"domain_scores_gemma":[0.7443987,0.24007733,0.00852825,0.00061899953,0.004286347,0.0020903712],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14542665,0.000357966,0.0036310423,0.00018514601,0.00028929758,0.000058272955,0.00031741464,0.0003961025,0.0005008194],"category_scores_gemma":[0.0831774,0.0001531147,0.0015694315,0.0003829757,0.0018141423,0.00025585416,0.0001495462,0.0036612668,0.00005727124],"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":[0.03434719,0.0013463652,0.8845566,0.000013103466,0.002454813,0.00014137,0.000033723656,0.000006898711,0.0000024902777,0.000053619904,0.008628137,0.068415664],"study_design_scores_gemma":[0.022284996,0.011237409,0.95888716,0.000753656,0.0023114728,0.00011878706,0.0012300058,0.00077369175,0.0000073303554,0.0010800243,0.0011485954,0.00016685098],"about_ca_topic_score_codex":0.00011400604,"about_ca_topic_score_gemma":0.00008545305,"teacher_disagreement_score":0.20384693,"about_ca_system_score_codex":0.00010812908,"about_ca_system_score_gemma":0.0017662732,"threshold_uncertainty_score":0.9986373},"labels":[],"label_agreement":null},{"id":"W2028150310","doi":"10.1016/j.jclinepi.2008.06.011","title":"The Internet is valid and reliable for child-report: An example using the Activities Scale for Kids (ASK) and the Pediatric Quality of Life Inventory (PedsQL)","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thames Valley Children's Centre; Holland Bloorview Kids Rehabilitation Hospital; Janeway Children's Health and Rehabilitation Centre; University of British Columbia; Children's Hospital of Eastern Ontario; McGill University; Institute for Clinical Evaluative Sciences; Laurentian University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Intraclass correlation; Quality of life (healthcare); Medicine; Ask price; Reliability (semiconductor); Scale (ratio); Physical therapy; Cerebral palsy; Psychometrics; Clinical psychology; Nursing","score_opus":0.580051033306023,"score_gpt":0.6133626250648447,"score_spread":0.0333115917588217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028150310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9712717,0.0011006425,0.013454681,0.011968298,0.0012014227,0.0008670541,0.000022088334,0.0000058561136,0.000108292465],"genre_scores_gemma":[0.96831876,0.0035729622,0.004347734,0.021537054,0.0019433358,0.000052443018,0.000004532509,0.000012219537,0.00021098174],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9813893,0.009103365,0.008738916,0.00020051283,0.0001699972,0.00039793501],"domain_scores_gemma":[0.8800744,0.10880783,0.009738788,0.00046645533,0.0006072967,0.00030523996],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11555642,0.00012788572,0.001431174,0.000047624875,0.0012283857,0.000008934613,0.000310684,0.00030799542,0.000022758823],"category_scores_gemma":[0.06525769,0.000054828062,0.00033019355,0.00007872362,0.0009888401,0.00046639703,0.00012221115,0.001102951,3.6309507e-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":[0.0020811006,0.000058716487,0.9797485,0.0003719328,0.000040192543,1.421335e-7,0.0039155167,0.000010076667,2.7928218e-7,0.0022695314,0.010532625,0.0009713834],"study_design_scores_gemma":[0.006884846,0.0008087353,0.8012208,0.00013672096,0.00013957219,0.0000847962,0.0047499244,0.020308098,0.0000022438737,0.030948892,0.13454354,0.00017186203],"about_ca_topic_score_codex":0.0008623708,"about_ca_topic_score_gemma":0.00008134669,"teacher_disagreement_score":0.17852773,"about_ca_system_score_codex":0.000028909091,"about_ca_system_score_gemma":0.0007898536,"threshold_uncertainty_score":0.9447874},"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":"W2029038720","doi":"10.1016/j.jclinepi.2007.10.022","title":"A five-point change in Modified Mini-Mental State Examination was clinically meaningful in community-dwelling elderly people","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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":"Queen Elizabeth II Health Sciences Centre; Dalhousie University","funders":"Canadian Institutes of Health Research; Dalhousie University; Dalhousie Medical Research Foundation","keywords":"Gerontology; Population; Medicine; Cognition; Mental state; Demography; Psychology; Psychiatry","score_opus":0.29598610813365317,"score_gpt":0.4993879334600362,"score_spread":0.203401825326383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029038720","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99162376,0.00026216052,0.0007655868,0.0058389306,0.00041144402,0.00050026807,0.0000047577987,0.000010181571,0.00058292836],"genre_scores_gemma":[0.99007034,0.004450235,0.0016429899,0.00324071,0.00036311892,0.000020828917,0.000018668798,0.000020193906,0.00017289222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9787689,0.013321996,0.006404245,0.00031589612,0.00046417813,0.00072480034],"domain_scores_gemma":[0.9725225,0.024594946,0.00179836,0.00028021281,0.0003950513,0.00040890815],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061405465,0.00021213506,0.0024846396,0.00039499855,0.00011104701,0.0000061946566,0.00030420514,0.00033541824,0.0001117716],"category_scores_gemma":[0.041580033,0.00017059117,0.00052073185,0.00034678524,0.0003943394,0.00024184896,0.00015318686,0.0034103717,0.000027019063],"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":[0.0022697495,0.0020537989,0.92565703,0.00006123289,0.00008491927,0.00046472647,0.0046263356,0.00003685698,0.000027959208,0.000026077854,0.00019123896,0.064500086],"study_design_scores_gemma":[0.008629639,0.008728922,0.9745054,0.00044515723,0.00003209515,0.00034742575,0.0012612836,0.004307602,0.000012878209,0.0013577886,0.00024062394,0.00013117869],"about_ca_topic_score_codex":0.00059938413,"about_ca_topic_score_gemma":0.00067239447,"teacher_disagreement_score":0.06436891,"about_ca_system_score_codex":0.00012880501,"about_ca_system_score_gemma":0.00026400795,"threshold_uncertainty_score":0.9988888},"labels":[],"label_agreement":null},{"id":"W2029242830","doi":"10.1016/j.jclinepi.2004.02.012","title":"Statistical measures were proposed for identifying longitudinal patterns of change in quantitative health indicators","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","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":"St Mary's Hospital; University of Toronto; Montreal General Hospital; McGill University","funders":"","keywords":"Longitudinal study; Statistics; Longitudinal data; Econometrics; Environmental health; Medicine; Computer science; Mathematics; Data mining","score_opus":0.8293138452189737,"score_gpt":0.6619455432920713,"score_spread":0.16736830192690233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029242830","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":[0.21892492,0.00021622812,0.7771038,0.0028367196,0.0004788591,0.00033131836,0.00009050041,0.0000048934917,0.000012765271],"genre_scores_gemma":[0.52585316,0.00020260511,0.4733689,0.00040189316,0.00015216367,0.0000070557135,0.0000017591169,0.000011095202,0.0000013732658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98896444,0.0039490815,0.006060145,0.0002829348,0.00028645125,0.00045695738],"domain_scores_gemma":[0.92141217,0.07366984,0.0041687065,0.00017252256,0.00027673342,0.00029999256],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03385296,0.00017359474,0.0029634242,0.00024488012,0.00004121919,0.0000051817597,0.00027768247,0.00023763832,0.00005111743],"category_scores_gemma":[0.22436547,0.0001236969,0.00035547165,0.00014075951,0.00030216662,0.000084460225,0.00004897703,0.0008079684,0.0000014165236],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044875575,0.0004313056,0.35841674,0.00038847484,0.000087517714,0.000018583723,0.0003429713,0.000007447817,0.0000051001484,0.61064255,0.000104514555,0.02910604],"study_design_scores_gemma":[0.0014383876,0.0022634408,0.4545612,0.00046327573,0.000034337063,0.000015144963,0.00011794783,0.000110006724,0.000012095799,0.5408547,0.000052945863,0.00007654353],"about_ca_topic_score_codex":0.00019317058,"about_ca_topic_score_gemma":0.00018594333,"teacher_disagreement_score":0.30692825,"about_ca_system_score_codex":0.000080098616,"about_ca_system_score_gemma":0.00040382223,"threshold_uncertainty_score":0.9948517},"labels":[],"label_agreement":null},{"id":"W2029446254","doi":"10.1016/j.jclinepi.2007.12.010","title":"Assessing continuity of care in a community diabetes program: Initial questionnaire development and validation","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","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":"St. Michael's Hospital; Centre for Global Health Research; University of Toronto","funders":"","keywords":"Likert scale; Construct validity; Scale (ratio); Reliability (semiconductor); Completeness (order theory); Psychology; Medicine; Psychometrics; Clinical psychology; Mathematics; Developmental psychology","score_opus":0.44641523146510975,"score_gpt":0.6292955605418654,"score_spread":0.18288032907675567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029446254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937759,0.0009666399,0.0002278409,0.0033443244,0.00073960837,0.00027626308,0.0000018313563,0.000013465231,0.0006541218],"genre_scores_gemma":[0.98322177,0.0004344125,0.0117575675,0.004265805,0.00028195413,0.000013774968,0.000008438006,0.0000075599714,0.000008695216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9756136,0.018385276,0.005390784,0.000116998075,0.000137582,0.0003557433],"domain_scores_gemma":[0.9674439,0.02824374,0.0033701991,0.00015982614,0.0005847682,0.00019758838],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.026984734,0.00011361932,0.0019630387,0.00014105916,0.00036915732,0.0000019468146,0.00016707732,0.00044885968,0.000016826178],"category_scores_gemma":[0.04340687,0.000086993685,0.00015248607,0.00011063831,0.0003083304,0.00022747526,0.00012513562,0.0024848888,0.000002783725],"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":[0.00013129658,0.00014942614,0.89054585,0.0004340471,0.000021581223,0.0000076004517,0.0023851423,0.0000019704173,0.0000017177535,0.00019610056,0.00043198967,0.10569326],"study_design_scores_gemma":[0.0014941943,0.0006677529,0.99053675,0.00058750686,0.00001719648,0.00000805304,0.0011425826,0.000012308765,0.0000107823735,0.0012135471,0.004240995,0.000068335474],"about_ca_topic_score_codex":0.00015538925,"about_ca_topic_score_gemma":0.00045881033,"teacher_disagreement_score":0.10562492,"about_ca_system_score_codex":0.00018573797,"about_ca_system_score_gemma":0.0026929996,"threshold_uncertainty_score":0.9998164},"labels":[],"label_agreement":null},{"id":"W2029532220","doi":"10.1016/j.jclinepi.2010.09.016","title":"Ratio of means for analyzing continuous outcomes in meta-analysis performed as well as mean difference methods","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":231,"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; Sunnybrook Health Science Centre; Health Sciences Centre; Hospital for Sick Children; Public Health Ontario; SickKids Foundation; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Strictly standardized mean difference; Confidence interval; Study heterogeneity; Mean difference; Medicine; Internal medicine; Pooled variance; Publication bias; Standard deviation; Random effects model; Statistics; Mathematics","score_opus":0.9475274836160614,"score_gpt":0.7029674465665074,"score_spread":0.24456003704955398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029532220","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":[0.2509636,0.0021521149,0.7377434,0.0031891223,0.00066916837,0.00067531696,0.000012781423,0.0000025850325,0.004591926],"genre_scores_gemma":[0.7009757,0.00019407041,0.2924303,0.0016788638,0.000095793184,0.000020946694,0.0000017731167,0.000012376558,0.0045901835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7242939,0.1775508,0.093390666,0.0014279617,0.0026387458,0.0006979273],"domain_scores_gemma":[0.35422176,0.5423282,0.093428135,0.0043282686,0.0049234824,0.0007701633],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6878415,0.00044805979,0.046167932,0.0013865612,0.000067328554,0.000052686086,0.0027844638,0.00042020204,0.017445857],"category_scores_gemma":[0.74716383,0.00018279656,0.034851868,0.0015948509,0.00031980374,0.00022321826,0.00014816983,0.00077667704,0.0002329606],"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":[0.00018797435,0.00031522507,0.8977774,0.000028400416,0.08164442,0.0000087273975,0.0004642301,0.00037626893,0.000016041666,0.008891756,0.0012741814,0.009015388],"study_design_scores_gemma":[0.0012145201,0.0014719566,0.53882587,0.000017627934,0.19356313,0.000033847926,0.00094938243,0.01748622,0.00008249856,0.23915361,0.006842563,0.00035879773],"about_ca_topic_score_codex":0.00013679705,"about_ca_topic_score_gemma":0.000293603,"teacher_disagreement_score":0.45001212,"about_ca_system_score_codex":0.000024231069,"about_ca_system_score_gemma":0.0002396406,"threshold_uncertainty_score":0.9834523},"labels":[],"label_agreement":null},{"id":"W2030071566","doi":"10.1016/s0895-4356(02)00609-1","title":"A comparative review of four preference-weighted measures of health-related quality of life","year":2003,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":216,"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":"Preference; Quality of life (healthcare); Measure (data warehouse); Health Utilities Index; Medicine; EQ-5D; Quality (philosophy); Index (typography); Statistics; Health related quality of life; Gerontology; Computer science; Mathematics; Data mining; Nursing","score_opus":0.9692665499267782,"score_gpt":0.6812424669445447,"score_spread":0.2880240829822335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030071566","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":[0.00028729474,0.98668844,0.0020638593,0.0068480032,0.0015029794,0.0013281916,0.0003926842,0.0000057366447,0.0008828436],"genre_scores_gemma":[0.00036492822,0.98740804,0.006342292,0.0054764887,0.00024678986,0.000023927118,0.00003586967,0.000033820295,0.00006783523],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.75005007,0.085157804,0.16291504,0.0008624835,0.00034003428,0.0006745507],"domain_scores_gemma":[0.63952345,0.11175291,0.2457646,0.0011124844,0.0012281131,0.0006184626],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45017403,0.0005239389,0.05714562,0.0006341412,0.000052005566,0.000003308851,0.0010032918,0.001212634,0.0005392738],"category_scores_gemma":[0.36027408,0.0004549575,0.0043481207,0.0005343951,0.0006306262,0.00017038475,0.000086226,0.0018000695,0.0000965697],"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":[0.0002169581,0.0015080641,0.024003472,0.6421345,0.0070527657,0.0000016455832,0.00045066935,0.00003461599,1.776856e-8,0.1375386,0.096981175,0.09007751],"study_design_scores_gemma":[0.0015439746,0.0012900067,0.0072431155,0.11788216,0.00035416096,0.00003486773,0.00007231018,0.0000414323,3.379192e-8,0.029543437,0.8415275,0.00046696974],"about_ca_topic_score_codex":0.0004008133,"about_ca_topic_score_gemma":0.000025566509,"teacher_disagreement_score":0.74454635,"about_ca_system_score_codex":0.00030062566,"about_ca_system_score_gemma":0.004591989,"threshold_uncertainty_score":0.9997902},"labels":[],"label_agreement":null},{"id":"W2030233093","doi":"10.1016/s0895-4356(03)00132-x","title":"Responsiveness of goal attainment scaling in a randomized controlled trial of comprehensive geriatric assessment","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Frailty in Older Adults","field":"Medicine","cited_by":227,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network; Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Goal Attainment Scaling; Randomized controlled trial; Quality of life (healthcare); Medicine; Gerontology; Physical therapy; Barthel index; Psychological intervention; Statistic; Clinical trial; Activities of daily living; Rehabilitation; Nursing; Internal medicine; Statistics","score_opus":0.14604455159001808,"score_gpt":0.5035001900815551,"score_spread":0.35745563849153705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030233093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98398614,0.0012750691,0.004751856,0.0047145197,0.0021675336,0.0025406382,0.0000025776994,0.0000038705307,0.0005578249],"genre_scores_gemma":[0.9781637,0.001576713,0.018838242,0.0008640113,0.00041350312,0.00003829519,0.000001672191,0.000016295444,0.00008757768],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.94388473,0.036855217,0.017888578,0.00033467473,0.00059834204,0.00043848177],"domain_scores_gemma":[0.7754563,0.21143652,0.011222916,0.00041148489,0.001154584,0.00031816124],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075717166,0.00023271795,0.015686175,0.00044799404,0.000016631328,0.0000017552868,0.00018904803,0.00044877394,0.00010565542],"category_scores_gemma":[0.266226,0.00014955825,0.0027904715,0.0002495281,0.00060366385,0.000048737413,0.00004287273,0.0011006494,0.0000015544786],"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":[0.9728338,0.0014732088,0.01964071,0.00012170529,0.0010060967,0.00009205731,0.000051109455,0.0010590388,0.00025053698,0.0020022332,0.00021739578,0.0012520929],"study_design_scores_gemma":[0.9508164,0.0047220928,0.03817705,0.0004998663,0.0007085869,0.00012530912,0.00015163541,0.00095166994,0.00005937222,0.0032406175,0.00044938928,0.00009801549],"about_ca_topic_score_codex":0.000024006038,"about_ca_topic_score_gemma":0.0000026742307,"teacher_disagreement_score":0.19050884,"about_ca_system_score_codex":0.00010562231,"about_ca_system_score_gemma":0.0012313988,"threshold_uncertainty_score":0.998927},"labels":[],"label_agreement":null},{"id":"W2031886110","doi":"10.1016/j.jclinepi.2009.01.006","title":"The Transnational study of oral contraceptive cardiovascular safety: history and science","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reproductive Health and Contraception","field":"Medicine","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":"McGill University; Jewish General Hospital","funders":"","keywords":"German; Gestodene; Agency (philosophy); Medicine; History; Family medicine; Library science; Population; Sociology; Environmental health; Family planning; Research methodology; Social science; Archaeology","score_opus":0.20993876662936986,"score_gpt":0.4843188142055238,"score_spread":0.274380047576154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031886110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95597017,0.0077507333,0.0017816076,0.03308978,0.00075698696,0.00035057616,4.773866e-7,0.0000033632448,0.0002963125],"genre_scores_gemma":[0.99616975,0.0012851665,0.0007285418,0.0013044811,0.00046893588,0.000001244953,1.9480585e-7,0.0000028460254,0.00003884501],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947494,0.0019252367,0.0025077295,0.00023033231,0.00037591305,0.00021134429],"domain_scores_gemma":[0.99228513,0.005180033,0.0011729035,0.00024656838,0.00087664,0.00023873284],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04792854,0.000080284604,0.0015115389,0.000084039006,0.000095176736,0.0000015200704,0.00012181107,0.00009620789,0.000011115688],"category_scores_gemma":[0.032172766,0.00004522667,0.00039037378,0.00009566793,0.00094898883,0.00009513424,0.000008799924,0.00060100236,4.7740286e-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":[0.009445197,0.0015938011,0.25588495,0.00002289357,0.0007602731,0.000041481548,0.0007138185,0.00021431064,0.00031497836,0.02702652,0.0010502657,0.7029315],"study_design_scores_gemma":[0.0034221346,0.0059106085,0.9623337,0.000012775834,0.00020105802,0.00014361062,0.00029092014,0.00014815664,0.000002636354,0.0027643305,0.024734413,0.00003569728],"about_ca_topic_score_codex":0.0000103486245,"about_ca_topic_score_gemma":0.0000050042463,"teacher_disagreement_score":0.70644873,"about_ca_system_score_codex":0.00009926395,"about_ca_system_score_gemma":0.00069544255,"threshold_uncertainty_score":0.98035794},"labels":[],"label_agreement":null},{"id":"W2031994680","doi":"10.1016/s0895-4356(99)00214-0","title":"Do potential patients prefer tissue plasminogen activator (TPA) over streptokinase (SK)?","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Acute Myocardial Infarction Research","field":"Medicine","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":"St. Joseph's Hospital; McMaster University; Queen's University","funders":"","keywords":"Medicine; Streptokinase; Stroke (engine); Myocardial infarction; Tissue plasminogen activator; Fibrinolytic agent; Thrombolysis; Emergency medicine; Internal medicine; Intensive care medicine; Physical therapy","score_opus":0.15367848152677027,"score_gpt":0.49263023367392006,"score_spread":0.3389517521471498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031994680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98364383,0.00019223585,0.00022637597,0.011523477,0.0012839331,0.00028716726,0.000024126613,0.000018141025,0.0028007224],"genre_scores_gemma":[0.97328174,0.0019901274,0.0023494312,0.01630354,0.0038326671,0.0000058696264,0.000021578819,0.000042094634,0.0021729723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917845,0.0028218727,0.003829414,0.00039718545,0.0006006282,0.00056639145],"domain_scores_gemma":[0.99040025,0.0062996224,0.0013418143,0.00047403987,0.00054999255,0.00093425537],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065101213,0.00022788759,0.0023590012,0.00017470184,0.0000722337,0.000010824704,0.000291876,0.0006504448,0.009865098],"category_scores_gemma":[0.024088986,0.00016090683,0.00091137143,0.00016585014,0.0003657609,0.00018703743,0.0000858689,0.0018666217,0.00043355167],"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":[0.007121574,0.0012312074,0.53249973,0.000031073232,0.0009636664,0.00027945347,0.000030700976,0.000144354,0.00024542605,0.00008403471,0.23304164,0.22432713],"study_design_scores_gemma":[0.004504547,0.003149929,0.6511612,0.0000567278,0.00017241568,0.00018099674,0.0000099958115,0.00011284483,0.00013453106,0.0005458988,0.33985117,0.00011974105],"about_ca_topic_score_codex":0.000032611275,"about_ca_topic_score_gemma":5.533473e-7,"teacher_disagreement_score":0.22420739,"about_ca_system_score_codex":0.000095946314,"about_ca_system_score_gemma":0.0003440341,"threshold_uncertainty_score":0.99104},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2032160051","doi":"10.1016/j.jclinepi.2013.11.014","title":"Addressing continuous data measured with different instruments for participants excluded from trial analysis: a guide for systematic reviewers","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":72,"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; SickKids Foundation; University of Toronto; McMaster University; Hospital for Sick Children","funders":"","keywords":"Missing data; Imputation (statistics); Meta-analysis; Construct (python library); Systematic review; Data collection; Medicine; Data mining; Computer science; MEDLINE; Statistics; Machine learning; Mathematics","score_opus":0.9674490120549121,"score_gpt":0.6986483343359714,"score_spread":0.2688006777189407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032160051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29249546,0.0016992156,0.6977641,0.0023750472,0.0017455849,0.0037285106,0.00011412174,0.0000042060706,0.0000737222],"genre_scores_gemma":[0.92354816,0.00013326338,0.071771614,0.0021810827,0.0016303991,0.00021116568,0.000063548585,0.000027022514,0.00043376704],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.74031794,0.155377,0.097283766,0.0019881309,0.004150781,0.0008823879],"domain_scores_gemma":[0.16051736,0.6585169,0.16105175,0.0119061945,0.006605851,0.0014019764],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.678719,0.00046461791,0.036030434,0.00040026513,0.00014643079,0.00025179653,0.004264571,0.00032098248,0.0002995658],"category_scores_gemma":[0.9035589,0.0001769526,0.007792136,0.0006281731,0.00018216782,0.00029518967,0.00020995122,0.00041375475,0.000036176018],"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":[0.029081488,0.0015145391,0.6493081,0.006206699,0.06270681,0.000009509251,0.00027600816,0.00091175624,0.000020737205,0.0014762295,0.19061793,0.0578702],"study_design_scores_gemma":[0.10941946,0.009432456,0.119524024,0.018037444,0.13478446,0.000035220164,0.0011011086,0.45877057,0.0000070976166,0.05863354,0.088814266,0.0014403682],"about_ca_topic_score_codex":0.000012087753,"about_ca_topic_score_gemma":0.00012367973,"teacher_disagreement_score":0.6310527,"about_ca_system_score_codex":0.00003683462,"about_ca_system_score_gemma":0.00020913049,"threshold_uncertainty_score":0.9782807},"labels":[],"label_agreement":null},{"id":"W2032422408","doi":"10.1016/s0895-4356(03)00110-0","title":"Should meta-analysts search Embase in addition to Medline?","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":159,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"University of Ottawa","keywords":"MEDLINE; Meta-analysis; Odds ratio; Medicine; Confidence interval; Publication bias; Internal medicine","score_opus":0.9826429483987847,"score_gpt":0.7461363902858464,"score_spread":0.2365065581129383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032422408","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60721934,0.005048274,0.2658934,0.102702394,0.0033679004,0.0012300658,0.000041674186,0.0000056407484,0.014491309],"genre_scores_gemma":[0.90026623,0.00018729451,0.07752249,0.017550237,0.0005882373,0.000016630487,0.0000030215283,0.000016275231,0.0038495928],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.4390533,0.4277337,0.123555034,0.0017974698,0.006915329,0.00094520365],"domain_scores_gemma":[0.33549574,0.6006146,0.050009225,0.005897919,0.0058606747,0.0021218408],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8299071,0.00032164308,0.023309266,0.001071851,0.000053549575,0.00008402483,0.0019142475,0.00038300056,0.031485382],"category_scores_gemma":[0.8996959,0.0001329233,0.012211197,0.0018812274,0.00013238542,0.00022593547,0.00009532821,0.0012892509,0.0022620158],"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":[0.00013882382,0.0004706335,0.39060706,0.00002554653,0.004901875,0.00017266056,0.00011832009,0.011076833,0.000015039997,0.018970087,0.5464743,0.027028842],"study_design_scores_gemma":[0.0012649111,0.0009568539,0.16824427,0.000055211705,0.0053162794,0.00029699373,0.00040697682,0.0078625325,0.000020664382,0.13280721,0.68236834,0.00039974708],"about_ca_topic_score_codex":0.00001416544,"about_ca_topic_score_gemma":0.00010775954,"teacher_disagreement_score":0.2930469,"about_ca_system_score_codex":0.00004293244,"about_ca_system_score_gemma":0.00029866127,"threshold_uncertainty_score":0.99851483},"labels":[],"label_agreement":null},{"id":"W2032535815","doi":"10.1016/j.jclinepi.2013.10.009","title":"The minimal clinically important difference determined using item response theory models: an attempt to solve the issue of the association with baseline score","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":30,"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; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Minimal clinically important difference; Medicine; Rating scale; Baseline (sea); Standard error; Gold standard (test); Physical therapy; Statistics; Randomized controlled trial; Mathematics; Internal medicine","score_opus":0.7097347802422773,"score_gpt":0.5849810002776482,"score_spread":0.12475377996462911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032535815","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7817386,0.00013975853,0.1989537,0.017545179,0.0013780063,0.00017340672,0.000005074449,0.0000060036987,0.00006029815],"genre_scores_gemma":[0.9291803,0.00010413661,0.061198458,0.008354609,0.00097154337,0.0000029287153,1.7260675e-7,0.000014976697,0.00017285248],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8880819,0.09343778,0.015217063,0.000739585,0.001770639,0.0007530016],"domain_scores_gemma":[0.045878682,0.93355936,0.017075246,0.0014738543,0.0016686629,0.00034421144],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.56431454,0.00022150758,0.0021457803,0.0001593651,0.00037820684,0.00006290116,0.0027663603,0.00035332103,0.00002368962],"category_scores_gemma":[0.9517832,0.000074053205,0.00075330597,0.00093639374,0.0006442656,0.00015165513,0.00034537265,0.0012738914,0.0000030915057],"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":[0.0072581414,0.00009974975,0.89464295,0.000002320135,0.00008453936,0.0000035353114,0.00016749908,0.0030657395,0.0001249201,0.001389986,0.0010661151,0.09209449],"study_design_scores_gemma":[0.00071514264,0.002556312,0.77553684,0.000078302764,0.000086807086,0.000055018132,0.00048509927,0.102153495,0.000012066887,0.116249755,0.001956506,0.00011468511],"about_ca_topic_score_codex":0.000020004243,"about_ca_topic_score_gemma":0.000037142694,"teacher_disagreement_score":0.84220326,"about_ca_system_score_codex":0.00004779286,"about_ca_system_score_gemma":0.00044142085,"threshold_uncertainty_score":0.5534495},"labels":[],"label_agreement":null},{"id":"W2032656498","doi":"10.1016/j.jclinepi.2004.08.022","title":"Systematic reviews involving complementary and alternative medicine interventions had higher quality of reporting than conventional medicine reviews","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Alberta; GlaxoSmithKline (Canada); University of Ottawa","funders":"","keywords":"Psychological intervention; Systematic review; Quality (philosophy); Alternative medicine; Scale (ratio); Medicine; English language; MEDLINE; Intervention (counseling); Medical education; Psychology; Family medicine; Nursing; Pathology; Mathematics education","score_opus":0.9785528732201937,"score_gpt":0.7574529363653615,"score_spread":0.2210999368548322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032656498","genre_codex":"review","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15739124,0.5924202,0.121791966,0.11364957,0.006714656,0.0048645837,0.00002134349,0.0000075759185,0.0031388595],"genre_scores_gemma":[0.7584295,0.107904784,0.09874607,0.018686285,0.008635424,0.00010936378,0.000036757287,0.00004542798,0.0074063777],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.3392235,0.30963242,0.3453509,0.0012581721,0.0040453295,0.0004897079],"domain_scores_gemma":[0.1465811,0.3253449,0.52001494,0.0031665228,0.004138673,0.00075386086],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8519544,0.00036124498,0.034308553,0.0004467651,0.000097159435,0.000021308244,0.0013932973,0.00015870856,0.010387103],"category_scores_gemma":[0.8994829,0.00014291776,0.007149532,0.0005268282,0.000746448,0.0002911282,0.00021747817,0.0007282071,0.00011594917],"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":[0.000073905445,0.00030885747,0.65695995,0.020409046,0.002033781,0.000011135762,0.0005005316,0.000023807308,0.00007917289,0.036748637,0.26843563,0.01441555],"study_design_scores_gemma":[0.0032583703,0.001709038,0.5463512,0.09081212,0.0037784036,0.00036419719,0.0012406972,0.0023461508,0.000002290244,0.09559061,0.2541212,0.00042571579],"about_ca_topic_score_codex":0.0000822276,"about_ca_topic_score_gemma":0.0001499242,"teacher_disagreement_score":0.6010383,"about_ca_system_score_codex":0.00004649435,"about_ca_system_score_gemma":0.000048406855,"threshold_uncertainty_score":0.99051756},"labels":[],"label_agreement":null},{"id":"W2032918102","doi":"10.1016/j.jclinepi.2012.11.006","title":"Increased statistical power with combined independent randomization tests used with multiple-baseline design","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Public Health Ontario; University of Toronto; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"VMware; NetApp","keywords":"Randomization; Statistics; Mathematics; Statistical power; Power (physics); Multiple baseline design; Sample size determination; Subject (documents); Medicine; Computer science; Reliability engineering; Randomized controlled trial; Internal medicine; Engineering","score_opus":0.594019471434238,"score_gpt":0.5827935140556644,"score_spread":0.01122595737857357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032918102","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":[0.09453429,0.000022294196,0.90091485,0.0026649227,0.00054589304,0.0011672422,0.000024129218,0.000044297696,0.000082059625],"genre_scores_gemma":[0.36606422,0.000028373051,0.63211924,0.001317301,0.00036373173,0.000032391545,0.0000029708663,0.000047639693,0.00002414215],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9483006,0.039879035,0.009767684,0.0005874311,0.0007815495,0.0006836715],"domain_scores_gemma":[0.19559674,0.7951064,0.0062728566,0.0006037493,0.0014420839,0.0009781296],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09210947,0.0004447327,0.0059270374,0.00016342888,0.000082241226,0.0000331973,0.00052637415,0.0006724668,0.0012747705],"category_scores_gemma":[0.8592876,0.00024436117,0.00042875356,0.00025935445,0.0009569526,0.00018540157,0.00007864792,0.001831513,0.00006210337],"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":[0.11416931,0.006128764,0.7391141,0.00024534276,0.0028574625,0.00066445576,0.000103593615,0.0019315211,0.00016037429,0.08314678,0.03243806,0.019040264],"study_design_scores_gemma":[0.059073463,0.011787893,0.16346808,0.0003784696,0.00070026505,0.00021443416,0.000042893087,0.011053827,0.000059320348,0.75262547,0.0001236259,0.00047226623],"about_ca_topic_score_codex":0.000039624523,"about_ca_topic_score_gemma":0.000016625021,"teacher_disagreement_score":0.7671782,"about_ca_system_score_codex":0.00006376651,"about_ca_system_score_gemma":0.00055287563,"threshold_uncertainty_score":0.9996382},"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":"W2033425493","doi":"10.1016/j.jclinepi.2005.07.011","title":"Distribution-based and anchor-based approaches provided different interpretability estimates for the Hydrocephalus Outcome Questionnaire","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":70,"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 Toronto; SickKids Foundation","funders":"Hospital for Sick Children; Physicians' Services Incorporated Foundation; Congress of Neurological Surgeons","keywords":"Interpretability; Outcome (game theory); Hydrocephalus; Medicine; Statistics; Econometrics; Computer science; Mathematics; Surgery; Artificial intelligence","score_opus":0.6298540183781924,"score_gpt":0.5390634607944308,"score_spread":0.09079055758376164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033425493","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":[0.27968127,0.0050227176,0.5741431,0.13903858,0.0011495951,0.0006976424,0.00022214578,0.000019883826,0.000025091318],"genre_scores_gemma":[0.9842837,0.000030308207,0.00728546,0.0074232346,0.0008271734,0.00007200116,0.000043007287,0.00001645188,0.000018648208],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9825719,0.002272487,0.0142554,0.00045017243,0.00006936159,0.00038067033],"domain_scores_gemma":[0.90255564,0.08630289,0.010316429,0.00043116792,0.00016422007,0.00022961784],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09219043,0.0002236135,0.0030838356,0.000092387476,0.00019434678,0.000032147207,0.00033355964,0.0003160535,0.00003013685],"category_scores_gemma":[0.20216984,0.00016424859,0.0006797839,0.00006830934,0.00041890694,0.00015989182,0.000031933676,0.0005065592,0.000013716913],"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":[0.00016100632,0.00023707227,0.9513425,0.0002476245,0.00006687818,3.2466716e-7,0.000015811162,0.0037594037,1.3091781e-7,0.03881194,0.004668765,0.0006885409],"study_design_scores_gemma":[0.0012541703,0.00030503306,0.67209977,0.00007132483,0.000037885296,0.0000042566676,0.000020829615,0.24701169,0.0000013668204,0.07670275,0.0023650234,0.00012590745],"about_ca_topic_score_codex":0.00021833729,"about_ca_topic_score_gemma":0.00008986904,"teacher_disagreement_score":0.7046025,"about_ca_system_score_codex":0.0002401549,"about_ca_system_score_gemma":0.00021625955,"threshold_uncertainty_score":0.934781},"labels":[],"label_agreement":null},{"id":"W2033940494","doi":"10.1016/j.jclinepi.2008.08.004","title":"Traditional assessment of health outcome following total knee arthroplasty was confounded by response shift phenomenon","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","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":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Total knee arthroplasty; Arthroplasty; Medicine; Physical therapy; Surgery","score_opus":0.2814498167532293,"score_gpt":0.49100343019242443,"score_spread":0.20955361343919515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033940494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580174,0.0007329079,0.0057101105,0.032054868,0.002756285,0.00028793127,0.000036047946,0.000023881319,0.00038057426],"genre_scores_gemma":[0.97942233,0.0002119928,0.013809004,0.005520659,0.0005211915,0.000003991258,0.00001899424,0.000032704986,0.0004591264],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9814936,0.0073982393,0.009399487,0.00039372419,0.00068290066,0.00063206226],"domain_scores_gemma":[0.954119,0.03977913,0.004814976,0.00037793763,0.0001841796,0.0007247261],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032870475,0.0003135719,0.0052673006,0.00023126243,0.00017360409,0.0000038303006,0.00013370089,0.00036145517,0.00034584166],"category_scores_gemma":[0.040132526,0.00023854249,0.0018356444,0.00017332364,0.00074547814,0.0001954903,0.000063847816,0.0017677705,0.000023718741],"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":[0.0029734294,0.001119279,0.98354405,0.000057525926,0.00065741694,0.00023484153,0.00013099455,0.000105472005,0.0001160103,0.0014967503,0.007233571,0.00233066],"study_design_scores_gemma":[0.008868909,0.00897471,0.9722537,0.00013863249,0.000104153536,0.001489824,0.00009465177,0.00016251953,0.000004019298,0.0009375215,0.006805057,0.00016630719],"about_ca_topic_score_codex":0.00002469168,"about_ca_topic_score_gemma":0.000003718235,"teacher_disagreement_score":0.032380894,"about_ca_system_score_codex":0.00023587351,"about_ca_system_score_gemma":0.0019724977,"threshold_uncertainty_score":0.9958634},"labels":[],"label_agreement":null},{"id":"W2033966474","doi":"10.1016/j.jclinepi.2007.10.015","title":"Introducing a methodology for estimating duration of surgery in health services research","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare Operations and Scheduling Optimization","field":"Health Professions","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":"Health Sciences Centre; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; University of Toronto","funders":"Canadian Institutes of Health Research; National Institutes of Health; Canada Research Chairs; Institute for Clinical Evaluative Sciences","keywords":"Anesthesiology; Duration (music); Reimbursement; Medicine; Cohort; Chart; Population; Cohort study; Quality (philosophy); Missing data; Health care; Operations management; Statistics; Environmental health; Engineering; Psychiatry","score_opus":0.8619912779840018,"score_gpt":0.7221083624527647,"score_spread":0.1398829155312371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033966474","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":[0.513115,0.0004063563,0.45666397,0.027358882,0.0019687063,0.00045611683,0.000003655236,0.000006213773,0.000021135427],"genre_scores_gemma":[0.2669832,0.0012565646,0.72783256,0.002293204,0.0015575006,0.000022566164,0.000010740745,0.000012040758,0.000031645453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.92419475,0.061183546,0.013429228,0.0002969072,0.00021860165,0.00067699],"domain_scores_gemma":[0.68523884,0.3050376,0.0069199814,0.00027692012,0.002258424,0.00026826633],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2691534,0.000090412796,0.002423051,0.00048575143,0.0004741205,0.0000012593489,0.00016000723,0.00046881416,0.000035270998],"category_scores_gemma":[0.23718622,0.00007059656,0.00024343937,0.00038364585,0.00016527459,0.00014201854,0.000043558884,0.0017647536,0.0000036173856],"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":[0.0006912283,0.00016080728,0.93286806,0.0013090722,0.000035007226,0.0000051001084,0.0040545454,0.032141536,0.00002709642,0.0031179755,0.0017033574,0.023886215],"study_design_scores_gemma":[0.002870702,0.0020412789,0.5419055,0.003553923,0.000016535823,0.00009259995,0.0047393567,0.41848466,0.000011750592,0.023183094,0.0029055288,0.00019501407],"about_ca_topic_score_codex":0.000907886,"about_ca_topic_score_gemma":0.00031318874,"teacher_disagreement_score":0.3909625,"about_ca_system_score_codex":0.00011555052,"about_ca_system_score_gemma":0.0030289367,"threshold_uncertainty_score":0.7692393},"labels":[],"label_agreement":null},{"id":"W2034052666","doi":"10.1016/j.jclinepi.2012.08.006","title":"Evidence in agenda setting: new directions for the Cochrane Collaboration","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Systematic review; Alliance; Cochrane Library; Relevance (law); Cochrane collaboration; Medicine; MEDLINE; Evidence-based medicine; Health care; Set (abstract data type); Medical education; Alternative medicine; Political science; Computer science","score_opus":0.6805637887244271,"score_gpt":0.6681438692453949,"score_spread":0.012419919479032204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034052666","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":[0.040001962,0.005328109,0.03577545,0.9131608,0.0026949556,0.0012484238,0.0000020765465,0.00003120129,0.001756995],"genre_scores_gemma":[0.9052766,0.032991387,0.045394756,0.007912486,0.005155068,0.00010848883,6.5939093e-7,0.000018383233,0.0031421927],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99050725,0.0062419246,0.00244533,0.00015495361,0.00029400396,0.0003565568],"domain_scores_gemma":[0.71509886,0.2813169,0.0018589948,0.0002542137,0.0011742102,0.0002968365],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07599657,0.000066738015,0.0007065825,0.00010111065,0.00021083796,0.000033728174,0.00056404376,0.00027302356,0.0002865939],"category_scores_gemma":[0.51288426,0.000042852327,0.00026276783,0.0004293298,0.000491969,0.00033088375,0.0000409928,0.0007320937,0.000025352907],"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":[0.00014346158,0.00008601348,0.112389475,0.000013152126,0.00004203854,0.0000043121295,0.00085882196,0.00021783079,0.00004822815,0.0126936855,0.6498849,0.2236181],"study_design_scores_gemma":[0.0007568952,0.00075297145,0.30784607,0.00036386237,0.00003775505,0.000012387628,0.0027965622,0.0021590248,0.000017415721,0.16414124,0.5209775,0.00013831077],"about_ca_topic_score_codex":0.0024943254,"about_ca_topic_score_gemma":0.0022938184,"teacher_disagreement_score":0.90524834,"about_ca_system_score_codex":0.000092423164,"about_ca_system_score_gemma":0.001306571,"threshold_uncertainty_score":0.95145595},"labels":[],"label_agreement":null},{"id":"W2035386401","doi":"10.1016/j.jclinepi.2006.09.001","title":"A randomized trial of Pegaptanib sodium for age-related macular degeneration used an innovative design to explore disease-modifying effects","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Retinal Diseases and Treatments","field":"Medicine","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":"McMaster University","funders":"","keywords":"Medicine; Randomized controlled trial; Randomization; Clinical trial; Macular degeneration; Confidence interval; Disease; Pegaptanib; Blinding; Internal medicine; Physical therapy; Ophthalmology; Chemotherapy; Bevacizumab","score_opus":0.3646101121270026,"score_gpt":0.5198044841091602,"score_spread":0.15519437198215763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035386401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87243736,0.00041129225,0.12154944,0.0022889061,0.00065808085,0.0026146963,0.0000069529938,0.000011442432,0.000021810052],"genre_scores_gemma":[0.9699966,0.00008874463,0.027873846,0.0008121531,0.00096048886,0.000120151126,0.00006977004,0.00002614266,0.00005211422],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9890165,0.005587018,0.0045580394,0.00029945312,0.00024546735,0.00029355384],"domain_scores_gemma":[0.97353995,0.02239542,0.0026652876,0.00023680177,0.0006764113,0.0004861522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012986359,0.00022163,0.0037866575,0.00018708766,0.000052604395,0.0000068561853,0.00011690239,0.00024724955,0.000012758978],"category_scores_gemma":[0.06643945,0.00014235685,0.001299334,0.00021414648,0.00020554526,0.00009519128,0.0000197323,0.00030121134,0.0000030379244],"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":[0.9830951,0.0015978577,0.0077942107,0.00009308499,0.000716437,0.00024085464,0.00005707325,0.0013080003,0.00050851604,0.0017617827,0.00053535507,0.0022917266],"study_design_scores_gemma":[0.926095,0.010957701,0.032438442,0.00032103164,0.0018178831,0.00002301735,0.00001729614,0.0048927935,0.00039832384,0.022804886,0.00008826287,0.00014533324],"about_ca_topic_score_codex":0.000020556568,"about_ca_topic_score_gemma":0.0000012205427,"teacher_disagreement_score":0.09755921,"about_ca_system_score_codex":0.000050196944,"about_ca_system_score_gemma":0.00034985124,"threshold_uncertainty_score":0.9414243},"labels":[],"label_agreement":null},{"id":"W2035464977","doi":"10.1016/j.jclinepi.2014.04.006","title":"Perceptions of authors' contributions are influenced by both byline order and designation of corresponding author","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diversity and Career in Medicine","field":"Social Sciences","cited_by":73,"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; Hospital for Sick Children; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Perception; Confidence interval; Interpretation (philosophy); Prestige; Psychology; Position (finance); Social psychology; Odds ratio; Order (exchange); Medicine; Linguistics; Pathology","score_opus":0.15442002171630645,"score_gpt":0.508509995577563,"score_spread":0.3540899738612566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035464977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8790265,0.00026022556,0.09956069,0.019436294,0.0009419295,0.000098762066,0.000043181073,0.000007413179,0.0006250383],"genre_scores_gemma":[0.9948463,0.00052301644,0.0030732397,0.0009557657,0.0003213264,5.035025e-7,0.0000037465506,0.000002635646,0.0002734857],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924358,0.0050726333,0.0018771053,0.00011656338,0.0003087903,0.00018907305],"domain_scores_gemma":[0.9765934,0.019639071,0.0024663594,0.00009149951,0.0009404908,0.00026922373],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045188166,0.000065906584,0.0010470824,0.0001107972,0.00017260216,0.000004510384,0.00025580422,0.00031882277,0.00017242192],"category_scores_gemma":[0.1851052,0.000052973446,0.0001775541,0.00020816941,0.0011745193,0.00012457707,0.000039086066,0.0004467931,0.0000017140138],"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":[0.000264595,0.0001930111,0.91726315,0.000022812561,0.00008843557,0.0000017312842,0.0015997693,0.00018041677,0.0006744254,0.03849802,0.031320106,0.009893501],"study_design_scores_gemma":[0.0024113148,0.0015461454,0.91581815,0.00029611087,0.00029776432,0.000008368499,0.0138168605,0.0010015522,0.000030711963,0.024483833,0.040142655,0.00014653598],"about_ca_topic_score_codex":0.00015368567,"about_ca_topic_score_gemma":0.00006834265,"teacher_disagreement_score":0.13991703,"about_ca_system_score_codex":0.000022031776,"about_ca_system_score_gemma":0.00018244798,"threshold_uncertainty_score":0.9831797},"labels":[],"label_agreement":null},{"id":"W2035831597","doi":"10.1016/j.jclinepi.2007.05.007","title":"Pisces did not have increased heart failure: data-driven comparisons of binary proportions between levels of a categorical variable can result in incorrect statistical significance levels","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Paranormal Experiences and Beliefs","field":"Psychology","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":"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":"Categorical variable; Statistics; Statistical significance; Type I and type II errors; Continuous variable; Medicine; Mathematics; Standard error; Heart failure; Demography; Statistical hypothesis testing; Statistical inference; Econometrics; Internal medicine","score_opus":0.40735327649397424,"score_gpt":0.535544107250461,"score_spread":0.12819083075648674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035831597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8523096,0.00029562612,0.12967986,0.008277547,0.0018122139,0.0006826528,0.0058528646,0.000025696663,0.001063987],"genre_scores_gemma":[0.9506194,0.000019657502,0.04792169,0.00069510663,0.00054942153,0.000007693957,0.000096980264,0.00001817244,0.00007190542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.983252,0.0053981864,0.009520409,0.00062725315,0.00041758743,0.00078455056],"domain_scores_gemma":[0.9304837,0.06350973,0.0044563664,0.00070006284,0.00035809726,0.00049206795],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028600823,0.00027474697,0.004225788,0.00032155163,0.000066730165,0.0000053795693,0.00097626087,0.0006163242,0.00091454235],"category_scores_gemma":[0.04329407,0.00021006112,0.0003428683,0.00047267327,0.0013232831,0.00016006338,0.0002131181,0.001629397,0.000012227964],"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":[0.0018260508,0.0013565324,0.9497562,0.00004668451,0.00028233492,0.00011929167,0.00027247044,0.0003707997,0.00046139513,0.007171799,0.036252,0.002084434],"study_design_scores_gemma":[0.0015562819,0.0017901676,0.98016053,0.00010819203,0.000111709865,0.00009796539,0.0004819916,0.0007636884,0.000075774034,0.001438408,0.013206364,0.00020889861],"about_ca_topic_score_codex":0.004246288,"about_ca_topic_score_gemma":0.0010500703,"teacher_disagreement_score":0.098309815,"about_ca_system_score_codex":0.00006516261,"about_ca_system_score_gemma":0.00095823157,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W2036315588","doi":"10.1016/j.jclinepi.2006.03.003","title":"Oncology employees valued patient-oriented research over quality of work-life research: a qualitative study","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","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":"Institute for Work & Health; Sunnybrook Health Science Centre; Health Sciences Centre; McMaster University; Women's College Hospital","funders":"Canadian Institutes of Health Research","keywords":"Qualitative research; Quality of life (healthcare); Medicine; Work (physics); Quality (philosophy); Oncology; Family medicine; Medical education; Psychology; Internal medicine; Nursing; Sociology; Engineering; Social science","score_opus":0.8452746232453568,"score_gpt":0.7094529276183282,"score_spread":0.13582169562702862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036315588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891306,0.0011750457,0.00023821749,0.006361912,0.0015889538,0.00062009896,0.000011388816,0.000012349568,0.00086139713],"genre_scores_gemma":[0.9952942,0.00068079913,0.0013164273,0.0013589659,0.0010591347,0.000022811964,0.000004421113,0.000026947962,0.00023628047],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85229397,0.13263391,0.010974124,0.00067975995,0.002330623,0.0010876178],"domain_scores_gemma":[0.7745807,0.21094294,0.004522349,0.0010223108,0.0075147282,0.001416929],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19211723,0.00021429584,0.0048583313,0.00065753434,0.00018607179,0.0000029323717,0.00042058673,0.0006310225,0.00031864454],"category_scores_gemma":[0.36552384,0.00015134856,0.0010571114,0.001268802,0.002742259,0.00010187078,0.00029283945,0.004839328,0.000026977994],"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":[0.024143968,0.0061200345,0.8694081,0.00008187131,0.0008368199,0.00033455205,0.05648927,0.000009214047,0.000024587427,0.0018993525,0.036301136,0.0043511316],"study_design_scores_gemma":[0.007851185,0.041815087,0.84090155,0.00025042632,0.000095022755,0.000068119996,0.08900711,0.000007761827,0.000015427375,0.004199645,0.015626177,0.00016246524],"about_ca_topic_score_codex":0.0019877413,"about_ca_topic_score_gemma":0.0005666234,"teacher_disagreement_score":0.1734066,"about_ca_system_score_codex":0.0002770571,"about_ca_system_score_gemma":0.002564152,"threshold_uncertainty_score":0.9999717},"labels":[],"label_agreement":null},{"id":"W2036668944","doi":"10.1016/j.jclinepi.2014.02.019","title":"Validation of international algorithms to identify adults with inflammatory bowel disease in health administrative data from Ontario, Canada","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":221,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; McMaster University; Mount Sinai Hospital; University of Ottawa; University of Toronto; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; Ottawa Hospital; Canada Research Chairs","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Canadian Child Health Clinician Scientist Program; Institute for Clinical Evaluative Sciences; American College of Gastroenterology","keywords":"Medicine; Inflammatory bowel disease; Algorithm; Incidence (geometry); Ulcerative colitis; Disease; Crohn's disease; Cohort; Health care; Internal medicine; Computer science","score_opus":0.5059050188247863,"score_gpt":0.6000459891503751,"score_spread":0.09414097032558877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036668944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9420113,0.000045752582,0.015296857,0.03906675,0.002844319,0.0003584413,0.00012965192,0.0000054449447,0.0002415073],"genre_scores_gemma":[0.9765614,0.00014815267,0.007152515,0.01472038,0.0010615052,0.000009164302,0.0002602009,0.000008112279,0.00007851356],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868208,0.005202078,0.006937145,0.00023796478,0.000458053,0.000343933],"domain_scores_gemma":[0.9692108,0.022606505,0.0062097735,0.0004380502,0.00049907155,0.0010357705],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029315388,0.00011661418,0.0011615009,0.000118534335,0.000094779,0.0000022829324,0.00056367746,0.00018726698,0.00040985548],"category_scores_gemma":[0.06383207,0.00008395237,0.00006237917,0.000074867516,0.000073669275,0.00022160693,0.00012965224,0.001527322,0.000013434984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017810249,0.00006196305,0.97150666,0.00018151294,0.000036693305,0.0000066837397,0.00084235886,0.00044575921,1.6598997e-7,0.0002963423,0.021891434,0.0029494106],"study_design_scores_gemma":[0.001851408,0.00047742762,0.9574386,0.0015142056,0.000011592181,0.0000010767479,0.00036973212,0.0064120353,3.8139257e-7,0.0007977901,0.031057881,0.00006789337],"about_ca_topic_score_codex":0.5413673,"about_ca_topic_score_gemma":0.8129163,"teacher_disagreement_score":0.27154896,"about_ca_system_score_codex":0.0004055837,"about_ca_system_score_gemma":0.010627499,"threshold_uncertainty_score":0.99952406},"labels":[],"label_agreement":null},{"id":"W2036707389","doi":"10.1016/s0895-4356(99)00237-1","title":"Assessing the Saskatchewan database for outcomes research studies of depression and its treatment","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saskatchewan Health","funders":"U.S. Food and Drug Administration","keywords":"Depression (economics); Medicine; Database; Gerontology; Computer science","score_opus":0.5466981706721923,"score_gpt":0.6582872620518321,"score_spread":0.1115890913796398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036707389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97332233,0.0044789594,0.00013995016,0.021437008,0.00019194334,0.0003261298,0.0000026954792,0.0000024540059,0.00009855662],"genre_scores_gemma":[0.98851055,0.004092572,0.0058850776,0.0007632656,0.00031615896,0.000008547637,0.0000021518604,0.0000065443137,0.00041515898],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99340034,0.003931775,0.002151611,0.00016046631,0.00017005697,0.00018577541],"domain_scores_gemma":[0.8807716,0.11757963,0.0007738116,0.00022314115,0.0004958802,0.0001559816],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035347626,0.000085077736,0.00147364,0.000067461384,0.000092146714,0.0000027951226,0.00007248616,0.00012909793,0.00003171607],"category_scores_gemma":[0.08891251,0.000035000674,0.00040531656,0.000064622436,0.0004360549,0.00008522974,0.000024468001,0.00038231377,0.0000014123625],"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":[0.0009942788,0.0005572485,0.6977011,0.0005030872,0.0005630958,0.0000053326726,0.00061861525,0.000028149941,0.0008109654,0.00017292771,0.0016973389,0.29634786],"study_design_scores_gemma":[0.0029492117,0.0036075958,0.98161906,0.00050945015,0.00016108417,0.000016504653,0.0027844845,0.0005865046,0.000083308885,0.0052163852,0.002422275,0.000044128225],"about_ca_topic_score_codex":0.000017510845,"about_ca_topic_score_gemma":0.00001319417,"teacher_disagreement_score":0.29630372,"about_ca_system_score_codex":0.000027321796,"about_ca_system_score_gemma":0.00016926325,"threshold_uncertainty_score":0.9933126},"labels":[],"label_agreement":null},{"id":"W2036721060","doi":"10.1016/j.jclinepi.2012.01.017","title":"Value of information methods for planning and analyzing clinical studies optimize decision making and research planning","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; University of Toronto; St Joseph's Health Care; Hospital for Sick Children; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Clinical decision making; Value (mathematics); Value of information; Computer science; Management science; Operations research; Medicine; Mathematics; Artificial intelligence; Engineering; Intensive care medicine; Machine learning","score_opus":0.9322645172937328,"score_gpt":0.7694551497765327,"score_spread":0.1628093675172001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036721060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39278263,0.035093497,0.5636325,0.0065404465,0.0015523524,0.0002705177,0.000011481139,0.000004716052,0.000111879424],"genre_scores_gemma":[0.3177313,0.0024815286,0.6755835,0.003117528,0.0010608688,0.000008320394,0.000001512191,0.000010599704,0.0000049028204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9635687,0.010893584,0.024537701,0.0003077963,0.000101488775,0.000590719],"domain_scores_gemma":[0.5411504,0.44040206,0.017199142,0.0002959045,0.0005423447,0.00041014355],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5646046,0.00013471313,0.003943079,0.0005745215,0.0001777468,0.000019600551,0.00020584937,0.00040269524,0.00000923714],"category_scores_gemma":[0.60381573,0.00012499721,0.00033314418,0.00013570259,0.00039856826,0.00092249655,0.00016130002,0.0008414844,0.000006646821],"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":[0.00033247116,0.00004467858,0.9315442,0.000274432,0.0002783415,2.5652503e-7,0.0014593491,0.0015714081,1.775682e-7,0.032932937,0.0040967353,0.027465027],"study_design_scores_gemma":[0.002112671,0.00091014046,0.7588872,0.0009805629,0.00005005106,0.00004001685,0.0029441009,0.047141045,6.2073275e-7,0.16603655,0.020707149,0.0001899046],"about_ca_topic_score_codex":0.000010982886,"about_ca_topic_score_gemma":4.6776353e-7,"teacher_disagreement_score":0.42950848,"about_ca_system_score_codex":0.00008896237,"about_ca_system_score_gemma":0.00011869067,"threshold_uncertainty_score":0.50972384},"labels":[],"label_agreement":null},{"id":"W2037222607","doi":"10.1016/j.jclinepi.2012.01.003","title":"Hearing, mobility, and pain predict mortality: a longitudinal population-based study","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","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":"University of Ottawa; University of Alberta","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute on Aging","keywords":"Medicine; Hazard ratio; Cohort study; Proportional hazards model; Longitudinal study; Health Utilities Index; Population; Cohort; Quality of life (healthcare); Cognition; Hearing loss; Demography; Physical therapy; Gerontology; Audiology; Internal medicine; Environmental health; Health related quality of life; Disease; Psychiatry; Confidence interval","score_opus":0.6304758642443011,"score_gpt":0.6408872047278986,"score_spread":0.010411340483597487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037222607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98844934,0.00042639434,0.0031898946,0.003101919,0.0039584273,0.0007665577,0.000009946145,0.00002929006,0.00006825964],"genre_scores_gemma":[0.99204785,0.00004007817,0.0018827386,0.003932691,0.0020160717,0.000036783873,0.000005603848,0.000017105443,0.000021083844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95102954,0.040284485,0.0074142856,0.0002877494,0.0003323231,0.0006516225],"domain_scores_gemma":[0.9118822,0.0821061,0.004442107,0.00038780711,0.00037792532,0.00080384925],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11277734,0.00017998762,0.002083123,0.00015110306,0.00034171864,0.0000021098351,0.00015907246,0.0005014707,0.0002503587],"category_scores_gemma":[0.1437891,0.00013440028,0.00029241378,0.00012941862,0.00011637255,0.00020855537,0.00009725075,0.0025922074,0.00002133305],"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":[0.00021720472,0.00035561383,0.9953743,0.00015881406,0.00009799157,0.0000035939154,0.00018108705,0.00009684556,1.2137568e-7,0.00030109505,0.0014827922,0.0017305034],"study_design_scores_gemma":[0.0014350567,0.0014048432,0.99356633,0.00016437021,0.00006742465,0.000004615015,0.0004339503,0.00069439097,3.2535425e-8,0.0015394826,0.00059468974,0.000094809504],"about_ca_topic_score_codex":0.0016688483,"about_ca_topic_score_gemma":0.00036965383,"teacher_disagreement_score":0.041821618,"about_ca_system_score_codex":0.00015156978,"about_ca_system_score_gemma":0.0005131588,"threshold_uncertainty_score":0.99970883},"labels":[],"label_agreement":null},{"id":"W2037356862","doi":"10.1016/s0895-4356(99)00211-5","title":"Occurrence of chronic obstructive pulmonary disease among Canadians and sex-related risk factors","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","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 Saskatchewan; University of Ottawa","funders":"","keywords":"COPD; Medicine; Chronic bronchitis; Overweight; Odds ratio; Demography; Population; Asthma; Epidemiology; Bronchitis; Physical therapy; Internal medicine; Obesity; Environmental health","score_opus":0.07077049229518909,"score_gpt":0.40842319260649224,"score_spread":0.3376527003113031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037356862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99138296,0.0055240956,0.000024778628,0.0010859614,0.0004155526,0.00032887532,0.00040349647,0.000012129837,0.0008221377],"genre_scores_gemma":[0.9943561,0.004545237,0.000126063,0.0001491123,0.00037124852,0.0000036962617,0.00003965645,0.000017921184,0.00039096316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99189216,0.0029402012,0.0036557617,0.00050105166,0.00037493886,0.0006358992],"domain_scores_gemma":[0.98463625,0.010642839,0.0019516178,0.00045230915,0.00029152338,0.0020254462],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004942227,0.00028836992,0.0025081998,0.00023632619,0.00009231772,0.0000043345763,0.000294999,0.00037587734,0.0018153832],"category_scores_gemma":[0.019617992,0.00021762689,0.0007928111,0.00026591835,0.002145095,0.00018912068,0.00006957501,0.0019737,0.000014054835],"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":[0.00075056835,0.00033688897,0.8991154,0.0001610464,0.0003546537,0.0005361353,0.00006153296,0.0003718812,0.0000041140165,0.00008812277,0.0005070418,0.09771265],"study_design_scores_gemma":[0.001526697,0.0006317645,0.9870468,0.00019134227,0.00045307958,0.00019508535,0.00014081807,0.003983693,0.0000031420273,0.003907328,0.0017571625,0.00016310783],"about_ca_topic_score_codex":0.0015092259,"about_ca_topic_score_gemma":0.00009529327,"teacher_disagreement_score":0.09754954,"about_ca_system_score_codex":0.00028668102,"about_ca_system_score_gemma":0.0017913755,"threshold_uncertainty_score":0.9990971},"labels":[],"label_agreement":null},{"id":"W2037384472","doi":"10.1016/j.jclinepi.2006.06.018","title":"Imputing variance estimates do not alter the conclusions of a meta-analysis with continuous outcomes: a case study of changes in renal function after living kidney donation","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":93,"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; Children's Hospital of Eastern Ontario; Western University","funders":"Canadian Institutes of Health Research","keywords":"Missing data; Meta-analysis; Confidence interval; Imputation (statistics); Statistics; Renal function; Medicine; Point estimation; Random effects model; Pooled variance; Variance (accounting); Standard error; Internal medicine; Mathematics","score_opus":0.853447232804012,"score_gpt":0.6432862530755729,"score_spread":0.21016097972843917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037384472","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","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":[0.017011212,0.9299105,0.047821373,0.0019255971,0.00065112795,0.0025115546,0.00008793755,0.0000032430257,0.00007750075],"genre_scores_gemma":[0.5208372,0.44146404,0.030996842,0.0037621886,0.0011790307,0.00047587106,0.000021852527,0.0001173767,0.0011455803],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.7749928,0.147763,0.07223816,0.0013421787,0.0032040612,0.0004598006],"domain_scores_gemma":[0.4036054,0.45122927,0.13786423,0.003505066,0.0034652469,0.00033075875],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.52021134,0.0007044188,0.06355283,0.00157375,0.000105089835,0.00009586298,0.0016959753,0.00051498914,0.0013722909],"category_scores_gemma":[0.4719678,0.00022834561,0.019135099,0.0027702348,0.00028414407,0.00015822871,0.00036106212,0.0013686651,0.000012816191],"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":[0.00022891018,0.0021660482,0.38224632,0.0027636383,0.3860891,0.0010875555,0.0013229517,0.00499171,2.3354903e-7,0.000276019,0.0030586047,0.21576893],"study_design_scores_gemma":[0.00096241373,0.0023366224,0.024682287,0.002629313,0.90681076,0.0014779799,0.0013698338,0.0038611204,4.3059938e-8,0.0009765658,0.054368876,0.00052416144],"about_ca_topic_score_codex":0.0003159322,"about_ca_topic_score_gemma":0.001433203,"teacher_disagreement_score":0.5207217,"about_ca_system_score_codex":0.000044890236,"about_ca_system_score_gemma":0.00039652537,"threshold_uncertainty_score":0.99954057},"labels":[],"label_agreement":null},{"id":"W2037435926","doi":"10.1016/j.jclinepi.2012.06.018","title":"Estimating benefits and harms of screening across subgroups: the Canadian Task Force on Preventive Health Care integrates the GRADE approach and overcomes minor challenges","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Guelph; University of Toronto; Ontario Stroke Network; Simon Fraser University; University of Manitoba; Public Health Agency of Canada; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Guideline; Grading (engineering); Health care; Cancer screening; Task force; Clinical trial; Family medicine; Randomized controlled trial; Cancer","score_opus":0.24929104303977195,"score_gpt":0.4876746417735948,"score_spread":0.23838359873382287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037435926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8564513,0.09035627,0.008561957,0.0433381,0.000531113,0.00061363744,0.000013971979,0.0000060314787,0.00012766344],"genre_scores_gemma":[0.9841613,0.0051959655,0.0071625123,0.0028306986,0.00061249494,0.0000068076415,0.0000053526046,0.000010271023,0.000014589105],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99127823,0.0062861526,0.0016855911,0.00016432836,0.00017590584,0.00040977047],"domain_scores_gemma":[0.99268275,0.005187233,0.0012863353,0.00019631698,0.0001599957,0.00048734504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04547724,0.00012653753,0.0012793102,0.000053077663,0.00024403905,0.0000060297302,0.00010559781,0.00020253113,0.0000029534294],"category_scores_gemma":[0.010678355,0.00006203836,0.00038790284,0.000060329985,0.00030093238,0.000080599864,0.0000405631,0.0009503456,4.4238675e-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":[0.00009008861,0.00010956063,0.20749567,0.00046787818,0.00041495392,0.0000018011785,0.0062847426,0.00012009021,8.889526e-7,0.0022162816,0.00019216546,0.7826059],"study_design_scores_gemma":[0.0011845023,0.0009994841,0.98894334,0.00061422685,0.00011695055,0.00032248165,0.0052848873,0.00088015024,0.0000032913583,0.00040142972,0.0011892371,0.000060004],"about_ca_topic_score_codex":0.0021397145,"about_ca_topic_score_gemma":0.0024325727,"teacher_disagreement_score":0.78254586,"about_ca_system_score_codex":0.00005217865,"about_ca_system_score_gemma":0.0002073753,"threshold_uncertainty_score":0.9976551},"labels":[],"label_agreement":null},{"id":"W2037951349","doi":"10.1016/j.jclinepi.2013.09.016","title":"Letter reply to GRADE guidelines articles 14 and 15","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Family medicine; Psychology","score_opus":0.7167629669068285,"score_gpt":0.6299412962806656,"score_spread":0.08682167062616286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037951349","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":[0.011818523,0.00048305534,0.009897395,0.97403914,0.0032535207,0.00038407065,0.000008459509,0.00002502551,0.00009083452],"genre_scores_gemma":[0.0009903564,0.00072274747,0.07481006,0.86855876,0.05428501,0.000006036974,0.000029349081,0.00006551799,0.00053214456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9712208,0.006731137,0.01994063,0.0007654216,0.0006542644,0.00068773364],"domain_scores_gemma":[0.8505955,0.13447571,0.010903793,0.0009829854,0.002187027,0.00085500145],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.05954129,0.0004413188,0.0055784136,0.0003410276,0.000053932214,0.000020357735,0.0003602554,0.0015199382,0.00025264142],"category_scores_gemma":[0.61535096,0.0003094422,0.0012511777,0.00016503061,0.00037557742,0.00014395821,0.00019209116,0.006249102,0.0001608885],"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":[0.00057409855,0.00007374372,0.030621773,0.00011366981,0.0003467155,0.00053370395,0.000011391292,0.0000126579935,0.000013247682,0.00002956167,0.9434677,0.02420178],"study_design_scores_gemma":[0.0025788157,0.0026841399,0.017186526,0.0004181987,0.0009272807,0.0019143044,0.000011469491,0.00021545734,0.000004597815,0.0059211436,0.9678846,0.00025347568],"about_ca_topic_score_codex":0.00009964648,"about_ca_topic_score_gemma":0.000012756175,"teacher_disagreement_score":0.5558097,"about_ca_system_score_codex":0.000057490837,"about_ca_system_score_gemma":0.0003846138,"threshold_uncertainty_score":0.99993575},"labels":[],"label_agreement":null},{"id":"W2038544627","doi":"10.1016/j.jclinepi.2006.09.005","title":"Low-back pain definitions in occupational studies were categorized for a meta-analysis using Delphi consensus methods","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","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 Work & Health; McMaster University; University of Toronto","funders":"","keywords":"Delphi method; Delphi; Categorization; Likert scale; Meta-analysis; Outcome (game theory); Medicine; Metric (unit); Psychology; Family medicine; Physical therapy; Computer science; Artificial intelligence; Pathology; Mathematics; Operations management","score_opus":0.6847701033727571,"score_gpt":0.6188280871972902,"score_spread":0.06594201617546691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038544627","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3935774,0.007067109,0.5660477,0.03172075,0.00062077935,0.0007765971,0.000034505047,0.000013192059,0.00014196365],"genre_scores_gemma":[0.35297227,0.00018875365,0.6431266,0.0030340343,0.0005257624,0.000031100353,0.000030886826,0.000013500032,0.00007705363],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97821736,0.014625472,0.0063831126,0.00030005578,0.00017484708,0.00029917405],"domain_scores_gemma":[0.81215453,0.18355758,0.0028644488,0.00023951975,0.001009787,0.00017412254],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08040998,0.00018961207,0.0055146017,0.00046492333,0.000060373593,0.00000343879,0.000085043546,0.00033392914,0.00017941534],"category_scores_gemma":[0.18111053,0.00011912574,0.0048788013,0.00043825223,0.0004282129,0.000040006427,0.00002006232,0.0005411329,0.0000038853177],"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":[0.009290215,0.0048876186,0.5084252,0.0029240006,0.3089947,0.000079066136,0.00034572848,0.08930762,0.0013942238,0.04085457,0.026630236,0.0068668346],"study_design_scores_gemma":[0.011570851,0.0035113103,0.45123893,0.00017833064,0.13741483,0.000091518894,0.0010023462,0.100818,0.00002241179,0.29129764,0.0023547944,0.00049903727],"about_ca_topic_score_codex":0.0000769649,"about_ca_topic_score_gemma":0.00011655668,"teacher_disagreement_score":0.25044307,"about_ca_system_score_codex":0.000080751284,"about_ca_system_score_gemma":0.00033078098,"threshold_uncertainty_score":0.94691145},"labels":[],"label_agreement":null},{"id":"W2038802143","doi":"10.1016/j.jclinepi.2010.05.007","title":"A threshold regression model for recurrent exacerbations in chronic obstructive pulmonary disease","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":16,"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","keywords":"Poisson regression; COPD; Medicine; Regression analysis; Clinical trial; Intensive care medicine; Regression; Statistics; Econometrics; Internal medicine; Mathematics","score_opus":0.19049841368051587,"score_gpt":0.49322003858026797,"score_spread":0.3027216248997521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038802143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.975244,0.0035868161,0.004267302,0.01354941,0.0017086569,0.0010149541,0.00007231313,0.000018801564,0.0005377717],"genre_scores_gemma":[0.98743194,0.0009593732,0.008074458,0.0005784814,0.0022965407,0.000071421266,0.000034469394,0.000040999483,0.0005123124],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99386555,0.00088367006,0.003651557,0.0005525185,0.00038201266,0.0006647068],"domain_scores_gemma":[0.98571604,0.009722861,0.0020434628,0.0006058051,0.0006575299,0.0012543217],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008735649,0.00026958462,0.0020614865,0.00034179148,0.00008726507,0.000006271002,0.00036308274,0.00044522548,0.00016984402],"category_scores_gemma":[0.053086247,0.00019404393,0.0011145084,0.00022902705,0.00065622624,0.00021480917,0.00014085165,0.0027956471,0.00001096706],"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":[0.013846297,0.0017671549,0.84906876,0.00065258914,0.00018052178,0.00044816616,0.000060160426,0.0040163975,0.00071155705,0.011577417,0.0035119506,0.11415905],"study_design_scores_gemma":[0.0022468255,0.00040223025,0.6050875,0.0002637936,0.000115385075,0.00010178687,0.000022112712,0.33865616,0.0000047730596,0.051527772,0.0014533888,0.00011823828],"about_ca_topic_score_codex":0.000006429181,"about_ca_topic_score_gemma":0.000044087945,"teacher_disagreement_score":0.33463976,"about_ca_system_score_codex":0.00044060103,"about_ca_system_score_gemma":0.0031725408,"threshold_uncertainty_score":0.9995049},"labels":[],"label_agreement":null},{"id":"W2038965761","doi":"10.1016/j.jclinepi.2009.04.001","title":"Individual patient meta-analysis—rewards and challenges","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Carleton University; University of Ottawa; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Meta-analysis; Medicine; Patient data; Aggregate data; MEDLINE; Data science; Computer science; Internal medicine; Pathology","score_opus":0.9735268638901531,"score_gpt":0.6892591933999572,"score_spread":0.28426767049019586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038965761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33635265,0.2917837,0.041044116,0.31816724,0.0019206133,0.000754229,0.00004219946,0.000009040913,0.009926221],"genre_scores_gemma":[0.9572278,0.005291925,0.025182867,0.011430743,0.0004272288,0.0000026155903,0.0000013796648,0.0000057668644,0.0004296562],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7793016,0.1461921,0.06870848,0.0011466392,0.0042062635,0.00044490732],"domain_scores_gemma":[0.68669724,0.23937511,0.0670446,0.0033324808,0.0026043307,0.00094621594],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6627202,0.0003217917,0.031715482,0.0007194296,0.00006852879,0.000110617766,0.001675108,0.00034404997,0.0044253645],"category_scores_gemma":[0.5860067,0.00012272543,0.02272106,0.0008261346,0.00018908433,0.00020798766,0.00012704369,0.0007429367,0.00019984398],"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":[0.00009241416,0.0004935423,0.08667218,0.000019310819,0.2646462,0.000071412134,0.0005166834,0.00095095026,8.712019e-7,0.027593538,0.076973744,0.5419692],"study_design_scores_gemma":[0.00029401958,0.0013091015,0.49401543,0.000004022317,0.16372418,0.00010321645,0.00026512373,0.00086813426,4.9047134e-7,0.14468597,0.19455592,0.00017439586],"about_ca_topic_score_codex":0.0000020137716,"about_ca_topic_score_gemma":0.000010053465,"teacher_disagreement_score":0.6208752,"about_ca_system_score_codex":0.000008057748,"about_ca_system_score_gemma":0.000087442684,"threshold_uncertainty_score":0.9964847},"labels":[],"label_agreement":null},{"id":"W2039114218","doi":"10.1016/j.jclinepi.2008.09.017","title":"Uncertainty in the minimum event risk to justify treatment was evaluated","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"McMaster University","funders":"","keywords":"Event (particle physics); Medicine; Confidence interval; Intervention (counseling); Adverse effect; Computer science; Statistics; Mathematics; Internal medicine","score_opus":0.8411022187661521,"score_gpt":0.7152376648877102,"score_spread":0.12586455387844186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039114218","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.772109,0.0002930611,0.09306616,0.1283061,0.0038394344,0.0013578401,0.000046948215,0.000030864496,0.0009506175],"genre_scores_gemma":[0.4819973,0.0011847221,0.50147575,0.012760105,0.0024546066,0.000017385708,8.2476646e-7,0.000020687376,0.000088629226],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9278708,0.05740718,0.012906766,0.0005242062,0.0005689069,0.00072215527],"domain_scores_gemma":[0.40262845,0.5917767,0.004160149,0.0006776484,0.00030659873,0.00045040558],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17207013,0.00030789923,0.0044839405,0.00014436159,0.00006697319,0.000011390853,0.00082044513,0.0005685283,0.00019782741],"category_scores_gemma":[0.8801907,0.0001558471,0.0012709539,0.0003475919,0.00024435137,0.00004020228,0.000051167677,0.0016072142,0.000058498637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066260668,0.0058189286,0.03412032,0.00003906574,0.00062540197,0.00037359115,0.00069659494,0.007203818,0.00001933825,0.11928102,0.05464314,0.7705527],"study_design_scores_gemma":[0.0031560934,0.007844105,0.11754551,0.000114635186,0.00040446882,0.00004853278,0.00009656139,0.0023570985,0.0000037263333,0.8626383,0.005640952,0.00015004762],"about_ca_topic_score_codex":0.000034917528,"about_ca_topic_score_gemma":0.00003301499,"teacher_disagreement_score":0.77040267,"about_ca_system_score_codex":0.00015744797,"about_ca_system_score_gemma":0.000275167,"threshold_uncertainty_score":0.85252804},"labels":[],"label_agreement":null},{"id":"W2039159868","doi":"10.1016/j.jclinepi.2006.11.020","title":"Placebo surgery research: a blinding imperative","year":2007,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Pain Management and Placebo Effect","field":"Neuroscience","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":"Hospital for Sick Children","funders":"","keywords":"Blinding; Placebo; Medicine; Physical therapy; Surgery; Intensive care medicine; Alternative medicine; Randomized controlled trial; Pathology","score_opus":0.7925568921266225,"score_gpt":0.6089943869690206,"score_spread":0.18356250515760186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039159868","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0072956355,0.00040652216,0.010241608,0.96277833,0.010083501,0.0006454219,0.000016697575,0.000044794913,0.00848747],"genre_scores_gemma":[0.008750178,0.0026230009,0.0007576451,0.9505469,0.033260167,0.000010079128,0.000011973795,0.000074041105,0.003965999],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7476499,0.2358454,0.011187333,0.0012826083,0.0016844784,0.0023502747],"domain_scores_gemma":[0.30739796,0.68620616,0.0052442956,0.0005005193,0.00034016525,0.00031089497],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.48472747,0.00046362798,0.0052783703,0.0017855347,0.00024958304,0.00005204934,0.0013201674,0.00272821,0.00037789528],"category_scores_gemma":[0.7825522,0.00033545773,0.0023025696,0.0007170747,0.0013429313,0.00022936275,0.00029750002,0.020218223,0.00043259823],"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":[0.00084232737,0.00005762427,0.011513392,0.00010894079,0.00010716256,0.00496254,0.000019514682,0.000017603388,0.000036149297,0.00039985607,0.97571826,0.006216616],"study_design_scores_gemma":[0.0007351585,0.00054827076,0.0010857745,0.0004065203,0.00007239395,0.00027120055,0.000013184567,0.00037684897,0.00008939262,0.009697146,0.9863828,0.00032131924],"about_ca_topic_score_codex":0.000010885121,"about_ca_topic_score_gemma":0.0000027047206,"teacher_disagreement_score":0.45036075,"about_ca_system_score_codex":0.00013245473,"about_ca_system_score_gemma":0.0006314032,"threshold_uncertainty_score":0.99990976},"labels":[],"label_agreement":null},{"id":"W2039625552","doi":"10.1016/j.jclinepi.2008.05.007","title":"Using different perspectives to generate items for a new scale measuring medical outcomes of dysphagia (MOD)","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dysphagia Assessment and Management","field":"Health Professions","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":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Dysphagia; Scale (ratio); Mod; Medicine; Physical therapy; Psychology; Computer science; Surgery; Artificial intelligence; Geography; Cartography","score_opus":0.6417640190616544,"score_gpt":0.6243904796596195,"score_spread":0.0173735394020349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039625552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7776077,0.0006148521,0.20057231,0.017104635,0.0030949435,0.0005838195,0.0000050284098,0.000015420284,0.00040132928],"genre_scores_gemma":[0.92783993,0.0011977672,0.06027284,0.006262849,0.00248844,0.000020448715,0.000001984904,0.000037013142,0.0018787258],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98902774,0.0037010126,0.005813668,0.0003316162,0.00048227262,0.0006437053],"domain_scores_gemma":[0.9730204,0.022007614,0.0032377052,0.00029230243,0.00053118676,0.0009107919],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017816057,0.00022485627,0.0031340546,0.00020730514,0.00024879188,0.0000020017278,0.00046416887,0.0004403026,0.00035031806],"category_scores_gemma":[0.044418924,0.00014815305,0.0007899776,0.00012501476,0.00018605901,0.00010585681,0.0002287706,0.0010841324,0.000012882804],"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":[0.00057046994,0.00037036516,0.9705182,0.00008731825,0.00066683494,0.00001714162,0.0009485935,0.00027049985,0.000059909005,0.0037002536,0.01961147,0.003178989],"study_design_scores_gemma":[0.0054327855,0.0011611081,0.9715594,0.00034818178,0.00027326992,0.000021455808,0.0012377131,0.0043347273,0.000022839004,0.0044446005,0.010931793,0.0002321155],"about_ca_topic_score_codex":0.00012585445,"about_ca_topic_score_gemma":0.000092993156,"teacher_disagreement_score":0.15023227,"about_ca_system_score_codex":0.00013835225,"about_ca_system_score_gemma":0.0009593568,"threshold_uncertainty_score":0.9636303},"labels":[],"label_agreement":null},{"id":"W2040293219","doi":"10.1016/j.jclinepi.2014.12.013","title":"Guideline uptake is influenced by six implementability domains for creating and communicating guidelines: a realist review","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":227,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; University of Toronto; McMaster University; Western University; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Stakeholder; Computer science; Narrative; Checklist; Clinical Practice; MEDLINE; Medicine; Psychology; Management science; Knowledge management; Nursing; Engineering; Pathology; Public relations; Political science; Cognitive psychology","score_opus":0.8048802352348821,"score_gpt":0.7148164279900794,"score_spread":0.09006380724480267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040293219","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":[0.000023419765,0.9461802,0.0058083325,0.043641448,0.000609923,0.0030989957,0.0004804404,0.00002839349,0.00012883812],"genre_scores_gemma":[0.0000012424141,0.7487441,0.19562443,0.05273572,0.0018291143,0.00008491987,0.00083863194,0.00008453411,0.000057363235],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9247399,0.01088345,0.06182926,0.0010318873,0.0006982211,0.0008172853],"domain_scores_gemma":[0.65446395,0.26270244,0.06745051,0.0031003158,0.010079398,0.0022033784],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22347029,0.0008580163,0.019658532,0.00015710582,0.00018204865,0.000024560868,0.00090176717,0.0011760669,0.00022330083],"category_scores_gemma":[0.7322186,0.0005922628,0.0036847282,0.00039364732,0.00058486,0.00026714976,0.000566395,0.003172924,0.000011175038],"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":[0.00017972491,0.00015318436,0.0007443025,0.012966595,0.0005756352,0.0000060296497,0.0000113848255,5.636601e-7,2.0819122e-7,0.00004749565,0.390967,0.59434783],"study_design_scores_gemma":[0.0037073144,0.001988857,0.00005304008,0.0396839,0.008679855,0.00084548787,0.00010933389,0.00027559596,4.7974467e-8,0.0016192395,0.9426521,0.0003852477],"about_ca_topic_score_codex":0.00027890233,"about_ca_topic_score_gemma":0.000049721446,"teacher_disagreement_score":0.5939626,"about_ca_system_score_codex":0.00035476216,"about_ca_system_score_gemma":0.003428774,"threshold_uncertainty_score":0.99965286},"labels":[],"label_agreement":null},{"id":"W2040373982","doi":"10.1016/s0895-4356(00)00243-2","title":"Do patient factors alter the relationship between physician characteristics and use of long-acting benzodiazepines?","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sleep and related disorders","field":"Psychology","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; Université de Montréal; McGill University; University of Ottawa","funders":"Health Canada; Australian Government","keywords":"Medicine; Medical prescription; Benzodiazepine; Anxiety; Family medicine; Anti-Anxiety Agents; Psychiatry; Internal medicine; Nursing","score_opus":0.3265041540736123,"score_gpt":0.4812923376299157,"score_spread":0.15478818355630342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040373982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953161,0.0004385279,0.0003402365,0.0022057234,0.001028015,0.00010779985,0.00001416461,0.000006533122,0.0005429361],"genre_scores_gemma":[0.9972125,0.00031794343,0.00019816536,0.0016016277,0.0005660151,0.0000011720051,0.0000075223115,0.000016067275,0.00007895683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924038,0.0034916461,0.0034863919,0.00020948045,0.00011879343,0.0002898555],"domain_scores_gemma":[0.93350947,0.063212216,0.0027354916,0.0002718603,0.00010617374,0.00016480184],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041676606,0.0001612406,0.0013220455,0.00007738124,0.000091202586,0.00000871499,0.00018406917,0.000457077,0.0003292693],"category_scores_gemma":[0.020569326,0.0000928958,0.00043369536,0.00012261528,0.00041881402,0.000114682196,0.00002837007,0.0012860574,0.000026910824],"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":[0.00016667398,0.00013183514,0.85876757,0.000005205789,0.00036417475,0.000007492953,0.0005190439,0.00003100102,4.0742157e-7,0.00049904303,0.00085870875,0.13864885],"study_design_scores_gemma":[0.0006739043,0.000534626,0.99204355,0.00006143887,0.00023353248,0.000015520316,0.00020728557,0.000018338487,8.4240594e-7,0.002048069,0.004071822,0.000091070615],"about_ca_topic_score_codex":0.000038599075,"about_ca_topic_score_gemma":0.0000021174017,"teacher_disagreement_score":0.13855778,"about_ca_system_score_codex":0.0000093954495,"about_ca_system_score_gemma":0.00003198931,"threshold_uncertainty_score":0.98768085},"labels":[],"label_agreement":null},{"id":"W2041353478","doi":"10.1016/j.jclinepi.2005.08.007","title":"Specific comorbidity risk adjustment was a better predictor of 5-year acute myocardial infarction mortality than general methods","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":51,"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; Myocardial infarction; Logistic regression; Comorbidity; Cohort; Population; Statistic; Cohort study; Emergency medicine; Demography; Internal medicine; Statistics; Environmental health","score_opus":0.21839436224062386,"score_gpt":0.5212225482077543,"score_spread":0.3028281859671304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041353478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9485156,0.0006288306,0.032238957,0.012785749,0.0041631707,0.00040971296,0.00009612299,0.000025795714,0.0011360644],"genre_scores_gemma":[0.71194714,0.0155851105,0.2336818,0.009621264,0.028591417,0.000024481704,0.00010102968,0.00008284654,0.00036494256],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9808196,0.011533668,0.005940002,0.0004429435,0.0006995311,0.00056424824],"domain_scores_gemma":[0.9844133,0.009771658,0.0037606715,0.00067066675,0.0008534235,0.0005302579],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034703158,0.0002794658,0.003709974,0.0002808302,0.00007201908,0.000006804003,0.000295854,0.00068632246,0.0003322674],"category_scores_gemma":[0.0131685585,0.00020195359,0.0021779386,0.00027397918,0.0008330699,0.00013967887,0.00015730775,0.0023873893,0.000029541154],"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":[0.0020652635,0.0004815621,0.8670649,0.00002559071,0.0026716646,0.00004973438,0.000016263,0.00021694426,0.001136394,0.00054365915,0.11565319,0.010074846],"study_design_scores_gemma":[0.0034505918,0.0021769113,0.9267258,0.000035068457,0.000965652,0.00022764437,0.000013545648,0.00062400056,0.00032039607,0.006197931,0.059131403,0.00013104378],"about_ca_topic_score_codex":0.00056583347,"about_ca_topic_score_gemma":0.000004982319,"teacher_disagreement_score":0.23656848,"about_ca_system_score_codex":0.00016013565,"about_ca_system_score_gemma":0.00034534984,"threshold_uncertainty_score":0.99991417},"labels":[],"label_agreement":null},{"id":"W2041934727","doi":"10.1016/j.jclinepi.2004.10.020","title":"Both clinical epidemiology and population health perspectives can define the role of health care in reducing health disparities","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","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":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Work & Health; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Epidemiology; Medicine; Population health; Health care; Public health; MEDLINE; Health equity; Population; Environmental health; Gerontology; Nursing; Political science; Pathology","score_opus":0.39919083194490756,"score_gpt":0.6213820016770297,"score_spread":0.22219116973212216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041934727","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":[0.0004525934,0.8162711,0.000043978645,0.18095289,0.0013325699,0.0008020938,0.000047679012,0.000012191782,0.00008484724],"genre_scores_gemma":[0.0049219895,0.96549284,0.002781335,0.023504794,0.003181535,0.0000148744375,0.0000310861,0.00003767297,0.00003386841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8253982,0.14211132,0.029057316,0.0009277806,0.00044507772,0.0020603251],"domain_scores_gemma":[0.8473002,0.12607503,0.024698902,0.0004950397,0.00024139845,0.001189484],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22201614,0.00048677129,0.019073982,0.00035255993,0.00069930597,0.0000141212,0.0007676393,0.0012163009,0.000028237142],"category_scores_gemma":[0.15404038,0.00031525808,0.00204604,0.00037968042,0.0017551079,0.00013563903,0.0001533027,0.0040108236,0.0000015768885],"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":[0.0000384591,0.00010509527,0.21147422,0.0025541983,0.00008234036,9.907471e-7,0.0026734115,0.000013176747,2.801571e-11,0.043692354,0.001788314,0.73757744],"study_design_scores_gemma":[0.0004383214,0.0010317462,0.25570706,0.006869055,0.00006624441,0.000028695222,0.009564306,0.000010693925,1.3456379e-10,0.006082916,0.7200096,0.00019133212],"about_ca_topic_score_codex":0.10632534,"about_ca_topic_score_gemma":0.061831903,"teacher_disagreement_score":0.7373861,"about_ca_system_score_codex":0.0012402694,"about_ca_system_score_gemma":0.013303894,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W2041946515","doi":"10.1016/j.jclinepi.2011.02.003","title":"Strengthening the reporting of Genetic RIsk Prediction Studies (GRIPS): explanation and elaboration","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; Ottawa Hospital","funders":"","keywords":"Checklist; Multidisciplinary approach; Transparency (behavior); Risk assessment; Strengths and weaknesses; Medicine; Completeness (order theory); Quality (philosophy); Public health; Disease; Risk analysis (engineering); Management science; Data science; Computer science; Psychology; Pathology; Engineering","score_opus":0.9582810679607515,"score_gpt":0.6812285641825064,"score_spread":0.2770525037782451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041946515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9281908,0.0038028636,0.06589261,0.0008678015,0.00082916016,0.00013718412,0.0000030036065,0.0000010936212,0.00027547637],"genre_scores_gemma":[0.95791423,0.00251351,0.038999625,0.00016335564,0.00033595847,0.000002381718,3.732672e-7,0.0000031267039,0.000067411514],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.76591367,0.08896848,0.14238098,0.00058799994,0.0019302736,0.00021858218],"domain_scores_gemma":[0.29765826,0.24837393,0.4451737,0.0020767117,0.0064812014,0.00023619986],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6616161,0.00011728827,0.00557452,0.00015881551,0.000094006755,0.000020144456,0.0004466751,0.00012855863,0.00019582991],"category_scores_gemma":[0.8997021,0.00004253638,0.0012261652,0.000317822,0.00020797017,0.00016363245,0.000059936214,0.0004049306,0.000011229378],"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":[0.000025949152,0.000021777249,0.9236468,0.000010661913,0.00035737854,0.0000019925803,0.0007034011,0.00025963757,0.000004719615,0.0006400794,0.004932916,0.06939465],"study_design_scores_gemma":[0.00016369755,0.00031162178,0.9328212,0.00004526848,0.00041962074,0.000052191674,0.0018056731,0.008272955,0.000005387548,0.053842116,0.0022246472,0.000035622255],"about_ca_topic_score_codex":0.000008754596,"about_ca_topic_score_gemma":0.000013794543,"teacher_disagreement_score":0.4682554,"about_ca_system_score_codex":0.000008121527,"about_ca_system_score_gemma":0.000061116276,"threshold_uncertainty_score":0.38106304},"labels":[],"label_agreement":null},{"id":"W2042191939","doi":"10.1016/j.jclinepi.2005.01.012","title":"A study compared nine patient-specific indices for musculoskeletal disorders","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":124,"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. Michael's Hospital; University of Toronto; Institute for Work & Health","funders":"","keywords":"Medicine; Physical therapy","score_opus":0.16113454416215442,"score_gpt":0.48219122486212973,"score_spread":0.3210566806999753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042191939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97582686,0.0009815829,0.0016616776,0.019175537,0.0013578394,0.0006740726,0.0000061406645,0.000022906188,0.00029340107],"genre_scores_gemma":[0.9790135,0.0003360697,0.016458925,0.0022621085,0.0017359534,0.000011723626,0.0000053373883,0.00002605606,0.00015031354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992485,0.0014914089,0.0050084833,0.00031563142,0.00026405085,0.00043546443],"domain_scores_gemma":[0.9776973,0.018734131,0.0025936489,0.00030624316,0.00022775643,0.0004409031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008032665,0.00021930067,0.0029523063,0.00018703872,0.000069457164,0.000005091181,0.00019405046,0.00022060327,0.00024359768],"category_scores_gemma":[0.025292248,0.00014899546,0.0012957369,0.00012526893,0.00031042588,0.0001445991,0.000066241926,0.00082777126,0.000056384422],"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":[0.0018214638,0.0022307304,0.84332836,0.000023996778,0.00040856667,0.000023731793,0.00024862922,0.00018529229,0.000007052004,0.0001548799,0.012489527,0.13907778],"study_design_scores_gemma":[0.010399662,0.011980358,0.8216493,0.000048650487,0.00019506809,0.00014684397,0.0007407567,0.00023593586,0.000001966877,0.00039107795,0.15407833,0.00013202464],"about_ca_topic_score_codex":0.0000063248253,"about_ca_topic_score_gemma":0.00007856081,"teacher_disagreement_score":0.1415888,"about_ca_system_score_codex":0.000044042805,"about_ca_system_score_gemma":0.0001251839,"threshold_uncertainty_score":0.98291814},"labels":[],"label_agreement":null},{"id":"W2042225280","doi":"10.1016/j.jclinepi.2010.05.009","title":"Aggregating single patient (n-of-1) trials in populations where recruitment and retention was difficult: The case of palliative care","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":84,"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":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Medicine; Clinical trial; Sample size determination; Psychological intervention; Population; Intervention (counseling); Palliative care; Research design; Gold standard (test); Consolidated Standards of Reporting Trials; N of 1 trial; Statistics; Surgery; Internal medicine; Nursing; Environmental health","score_opus":0.9581004386805326,"score_gpt":0.7348378265606642,"score_spread":0.22326261211986842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042225280","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":[0.005639499,0.97988075,0.007325975,0.0005986375,0.0034043093,0.0028124978,0.0002717402,0.0000070471733,0.000059555685],"genre_scores_gemma":[0.000360025,0.6435103,0.35547838,0.00004186633,0.0005310271,0.000040531137,0.0000040549075,0.000029276696,0.000004564191],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8654653,0.094308846,0.0389001,0.0005638181,0.0003506969,0.00041127144],"domain_scores_gemma":[0.25150156,0.7030457,0.04385502,0.0005715547,0.000831669,0.0001944645],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.121984266,0.0004234903,0.018338548,0.00019712825,0.0000659501,0.000009254647,0.00038903463,0.0015926776,0.00005298512],"category_scores_gemma":[0.92858595,0.00021828963,0.0028920674,0.00032168778,0.00071765314,0.000043624954,0.00020111905,0.0030621395,8.840694e-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":[0.00012915916,0.00035009024,0.00072574115,0.005338521,0.00033035735,0.00010798729,0.00021153674,0.000003557703,5.4567e-7,0.012078591,0.00022447213,0.98049945],"study_design_scores_gemma":[0.0029116871,0.004146638,0.00079371524,0.057976294,0.006989342,0.00045687557,0.0007854972,0.000078575096,0.0000028627646,0.86288744,0.06247452,0.00049655244],"about_ca_topic_score_codex":0.00004907109,"about_ca_topic_score_gemma":0.00020667768,"teacher_disagreement_score":0.9800029,"about_ca_system_score_codex":0.00009782119,"about_ca_system_score_gemma":0.00033113998,"threshold_uncertainty_score":0.99970347},"labels":[],"label_agreement":null},{"id":"W2042442994","doi":"10.1016/s0895-4356(99)00225-5","title":"Evaluating the outcome of treatment","year":2000,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":85,"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","funders":"","keywords":"Medicine; Quality of life (healthcare); MEDLINE; Outcome (game theory); Family medicine; Intensive care medicine; Nursing","score_opus":0.966473171622216,"score_gpt":0.748530230923593,"score_spread":0.21794294069862297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042442994","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":[0.00033080427,0.983813,0.00034376563,0.010956196,0.0025898966,0.0007201156,0.0001472022,0.000006475938,0.0010925453],"genre_scores_gemma":[0.00003650947,0.986525,0.004785349,0.0051786513,0.002718931,0.00003509745,0.0000122621095,0.000043690878,0.00066452246],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8996723,0.023236996,0.0758221,0.0006070468,0.00011800447,0.00054353534],"domain_scores_gemma":[0.72662634,0.19122224,0.08061207,0.0010485438,0.00015581066,0.0003349981],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.3234946,0.00042313535,0.022893779,0.00037281986,0.00009809361,0.000011910523,0.0009589437,0.0009375364,0.0009393347],"category_scores_gemma":[0.24864052,0.00027587582,0.0046011186,0.00018929277,0.00033771,0.00012988057,0.000062221116,0.0012492207,0.0009802787],"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":[0.000054877863,0.00028001986,0.018912598,0.005319455,0.0015803203,0.0000034614002,0.0001253536,0.0003133035,9.753175e-10,0.024262693,0.009787167,0.93936074],"study_design_scores_gemma":[0.00062209426,0.0017425227,0.0009134697,0.0019887893,0.00034179166,0.0000763765,0.000023507655,0.00034636527,1.4786024e-9,0.013836103,0.97990924,0.00019974764],"about_ca_topic_score_codex":0.00018920205,"about_ca_topic_score_gemma":0.000013498951,"teacher_disagreement_score":0.97012204,"about_ca_system_score_codex":0.0006325129,"about_ca_system_score_gemma":0.0012607225,"threshold_uncertainty_score":0.99997395},"labels":[],"label_agreement":null},{"id":"W2042803707","doi":"10.1016/j.jclinepi.2007.07.016","title":"Early stopping of randomized clinical trials for overt efficacy is problematic","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":131,"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":"Medical Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Interim; Early stopping; Randomized controlled trial; Medicine; Clinical trial; Continuation; Value (mathematics); Psychology; Statistics; Surgery; Computer science; Internal medicine; Political science; Mathematics; Law","score_opus":0.963934586630097,"score_gpt":0.7795635393828945,"score_spread":0.18437104724720255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042803707","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002139534,0.6702763,0.31413242,0.0009336229,0.007410335,0.0068416013,0.00019869317,0.00003061171,0.00015505854],"genre_scores_gemma":[0.0000014111537,0.5460726,0.44883034,0.00051719893,0.0042666,0.00010844005,0.0000028952543,0.00010511843,0.00009538569],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.30308783,0.49084848,0.20126371,0.0018387692,0.0014218617,0.0015393535],"domain_scores_gemma":[0.024681605,0.8570171,0.11421407,0.0014648046,0.0016477159,0.00097470713],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.71168005,0.0012354929,0.14248423,0.0005452954,0.000098875724,0.000020797499,0.0021128294,0.0051066605,0.00033191164],"category_scores_gemma":[0.9957683,0.00071207306,0.051658355,0.00043878204,0.0028708577,0.000110454246,0.00034227813,0.0057865637,0.00003912541],"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":[0.024808617,0.0015121293,0.000046489935,0.019875143,0.010028985,0.000030924286,0.000033753073,9.856021e-7,2.9889485e-8,0.038898118,0.032505743,0.8722591],"study_design_scores_gemma":[0.08905655,0.001991956,0.00002519243,0.027665671,0.014934036,0.00015718698,0.0000031979496,0.00009459011,1.2009987e-7,0.67508525,0.19049455,0.0004917021],"about_ca_topic_score_codex":0.000004255064,"about_ca_topic_score_gemma":2.392182e-7,"teacher_disagreement_score":0.8717674,"about_ca_system_score_codex":0.00009119835,"about_ca_system_score_gemma":0.002384023,"threshold_uncertainty_score":0.99984276},"labels":[],"label_agreement":null},{"id":"W2043985436","doi":"10.1016/j.jclinepi.2006.04.007","title":"Case selection for statins was similar in two Canadian provinces: BC and Ontario","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; York University","funders":"","keywords":"Medicine; Medical prescription; Statin; Diabetes mellitus; Acute coronary syndrome; Prescription drug; Population; Demographics; Coronary heart disease; Demography; Epidemiology; Gerontology; Family medicine; Emergency medicine; Internal medicine; Environmental health; Myocardial infarction","score_opus":0.14716003098186264,"score_gpt":0.458713128138894,"score_spread":0.31155309715703133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043985436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903689,0.00043046573,0.0019251752,0.006179029,0.000312649,0.00041783374,0.00000476156,0.0000036364954,0.0003575425],"genre_scores_gemma":[0.9793846,0.00014082556,0.015959112,0.0029214835,0.0013811773,0.000008431935,0.0000050751573,0.000011370831,0.00018789523],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99616057,0.00094125123,0.0022602838,0.00019134974,0.00009818725,0.0003483315],"domain_scores_gemma":[0.99549526,0.0030642268,0.00068823696,0.0001212752,0.00019762566,0.00043339917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017375046,0.0001016219,0.001534771,0.00014472644,0.00005693443,0.000003848448,0.000039339597,0.00018682214,0.000028095561],"category_scores_gemma":[0.0088238465,0.000073234085,0.00038851448,0.00007274661,0.000082658815,0.00005591508,0.000007799966,0.00073151535,9.940234e-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":[0.0005023336,0.00010526449,0.9685917,0.000069117435,0.00010118951,0.0010580276,0.000048509803,0.00023532647,0.0000022107472,0.0008082751,0.0020712307,0.026406817],"study_design_scores_gemma":[0.008197875,0.003224381,0.8473145,0.0001397219,0.00025279747,0.016973974,0.00008936426,0.0021929212,0.000008292736,0.009909814,0.11154871,0.00014764856],"about_ca_topic_score_codex":0.8445712,"about_ca_topic_score_gemma":0.98546004,"teacher_disagreement_score":0.14088884,"about_ca_system_score_codex":0.0003520597,"about_ca_system_score_gemma":0.00265045,"threshold_uncertainty_score":0.99952525},"labels":[],"label_agreement":null},{"id":"W2044188484","doi":"10.1016/j.jclinepi.2008.08.008","title":"Non-Cochrane vs. Cochrane reviews were twice as likely to have positive conclusion statements: cross-sectional study","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Public Health; Institute of Population and Public Health; University of Ottawa; Children's Hospital of Eastern Ontario","funders":"","keywords":"Medicine; Meta-analysis; Systematic review; Concordance; MEDLINE; Cochrane collaboration; Sample size determination; Cochrane Library; Logistic regression; Publication bias; Internal medicine; Statistics","score_opus":0.7830924180596557,"score_gpt":0.7075721991229896,"score_spread":0.07552021893666605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044188484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9336935,0.0044942247,0.03585172,0.016982934,0.0035011058,0.0023511646,0.00002429974,0.000005232567,0.0030957921],"genre_scores_gemma":[0.9421046,0.0022014554,0.012206468,0.036164768,0.0018978196,0.000017002305,0.0000084064595,0.000019430494,0.0053800466],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.75314337,0.12100596,0.1151438,0.0023178074,0.0074206744,0.00096840505],"domain_scores_gemma":[0.6711508,0.21651432,0.09340171,0.0054790922,0.01105966,0.002394448],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6647097,0.0005583991,0.021491362,0.00053604605,0.00028376785,0.00029240933,0.0028223735,0.00041960663,0.00670706],"category_scores_gemma":[0.6462744,0.00026457905,0.006793352,0.0007853533,0.00020935856,0.0005514203,0.00029049677,0.0014090998,0.004778082],"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":[0.0010785799,0.0010112071,0.89762706,0.000034073135,0.00053191016,0.00011488672,0.00031092123,0.00047146122,0.000030531486,0.00042804267,0.082518265,0.015843088],"study_design_scores_gemma":[0.0017013692,0.00740416,0.933703,0.00033422877,0.00031783342,0.00018743904,0.00024613334,0.00052703964,0.000002936742,0.010958041,0.04437488,0.00024290469],"about_ca_topic_score_codex":0.00004354209,"about_ca_topic_score_gemma":0.000031924144,"teacher_disagreement_score":0.09550835,"about_ca_system_score_codex":0.00010771205,"about_ca_system_score_gemma":0.00027934488,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W2044672799","doi":"10.1016/j.jclinepi.2009.03.015","title":"The Oort structural equation modeling approach detected a response shift after a COPD self-management program not detected by the Schmitt technique","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":37,"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; Institut Universitaire de Cardiologie et de Pneumologie de Québec; McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"COPD; Structural equation modeling; Medicine; Physical therapy; Rehabilitation; Randomized controlled trial; Gerontology; Statistics; Internal medicine; Mathematics","score_opus":0.10285370946787482,"score_gpt":0.44550446130998533,"score_spread":0.3426507518421105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044672799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9385114,0.0017312805,0.03655854,0.019914484,0.0002638877,0.0027441077,0.000009412196,0.00011940304,0.00014754261],"genre_scores_gemma":[0.96957755,0.000352683,0.027582485,0.0016124735,0.0005356771,0.00021860271,0.000009446417,0.00003159796,0.000079484766],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858588,0.00820102,0.003797372,0.00053802464,0.0007579233,0.0008468485],"domain_scores_gemma":[0.98532605,0.011318221,0.0014578718,0.0007862334,0.00059559493,0.0005160079],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.026118787,0.00033639997,0.001450329,0.00018682273,0.00029240898,0.000039100792,0.0006586998,0.0004771511,0.000031026542],"category_scores_gemma":[0.025017353,0.00017552401,0.00083070854,0.0004467749,0.000515532,0.00014204012,0.00016085414,0.002589374,0.000008287029],"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":[0.19266741,0.003099962,0.08321893,0.00051355275,0.0032028446,0.00095666334,0.00050787866,0.0030357053,0.0010322427,0.0019236981,0.003159848,0.70668125],"study_design_scores_gemma":[0.003651977,0.0025805687,0.7028514,0.00014707414,0.00043485189,0.00049545796,0.0001530076,0.28002328,0.000040756244,0.007400899,0.0019867811,0.00023390791],"about_ca_topic_score_codex":0.000012457911,"about_ca_topic_score_gemma":0.000003241771,"teacher_disagreement_score":0.70644736,"about_ca_system_score_codex":0.00034374284,"about_ca_system_score_gemma":0.0005341767,"threshold_uncertainty_score":0.9997117},"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":"W2044708081","doi":"10.1016/j.jclinepi.2006.07.006","title":"Hip protectors decrease hip fracture risk in elderly nursing home residents: a Bayesian meta-analysis","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada); University of Calgary; University of Ottawa; Canadian Institutes of Health Research; St. Joseph’s Healthcare Hamilton; Hamilton Health Sciences; University of Toronto; University Health Network; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Hip fracture; Medicine; Randomized controlled trial; Meta-analysis; CRTS; Physical therapy; Odds ratio; Osteoporosis; Surgery; Internal medicine","score_opus":0.4010586066719325,"score_gpt":0.5825036185637563,"score_spread":0.18144501189182383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044708081","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":[0.00034498586,0.9879832,0.0016528082,0.007814484,0.0003923145,0.0016309366,0.0000450262,0.000017712226,0.0001185218],"genre_scores_gemma":[0.00074775825,0.98959404,0.0048889816,0.002476475,0.0017626928,0.00008033013,0.00008339319,0.00008927898,0.00027705045],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94144785,0.036579616,0.018593064,0.0010350578,0.0009711519,0.001373271],"domain_scores_gemma":[0.9147786,0.064125724,0.016278908,0.0013027418,0.00069861347,0.0028153986],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.07398018,0.0008479501,0.037303884,0.002515717,0.000117203876,0.000023558003,0.00072792487,0.003331972,0.0009598327],"category_scores_gemma":[0.1794226,0.00049616775,0.019014182,0.0019636434,0.0005278302,0.00013085565,0.00007094574,0.012383599,0.000037675032],"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":[0.001355578,0.001469588,0.035171017,0.008512871,0.074964866,0.0013832207,0.000025119742,0.00005687752,1.7769107e-8,0.000027043547,0.014197578,0.86283624],"study_design_scores_gemma":[0.0026953265,0.0031706109,0.043947686,0.0061038234,0.44709912,0.00089825824,0.000019295516,0.00007589987,5.748689e-8,0.0040926626,0.49136582,0.0005314412],"about_ca_topic_score_codex":0.0020111273,"about_ca_topic_score_gemma":0.00032348928,"teacher_disagreement_score":0.8623048,"about_ca_system_score_codex":0.00050398544,"about_ca_system_score_gemma":0.004694163,"threshold_uncertainty_score":0.99995345},"labels":[],"label_agreement":null},{"id":"W2044886327","doi":"10.1016/j.jclinepi.2006.12.009","title":"ICD-10 adaptations of the Ontario acute myocardial infarction mortality prediction rules performed as well as the original versions","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":62,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research","keywords":"Medicine; ICD-10; Myocardial infarction; Comorbidity; Logistic regression; Mortality rate; Diagnosis code; Emergency medicine; Heart failure; Internal medicine; Population","score_opus":0.4604568831459182,"score_gpt":0.5832125707553375,"score_spread":0.1227556876094193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044886327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9470698,0.000050024937,0.003164058,0.020798864,0.007390853,0.0004274471,0.000015445348,0.000015758975,0.021067718],"genre_scores_gemma":[0.97713435,0.0009911613,0.0013422153,0.014942428,0.0029216327,0.000012321195,0.00002322917,0.000010955987,0.0026217327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9880491,0.004627219,0.0061161015,0.00015483948,0.000549412,0.0005033201],"domain_scores_gemma":[0.960249,0.03216618,0.0058479174,0.00042804744,0.00082618016,0.000482653],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05084163,0.00014084874,0.0010282492,0.00010880334,0.0010019477,0.0000029245045,0.00037191852,0.0006592274,0.002545234],"category_scores_gemma":[0.04172055,0.00007273356,0.0005222595,0.00018487195,0.00044325404,0.00021003647,0.000088871115,0.00367569,0.00048117875],"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":[0.0013990854,0.00011231908,0.93298286,0.000052488376,0.00031212607,0.0000024661165,0.0019122643,0.00025119368,0.000006164523,0.008498972,0.05020069,0.004269393],"study_design_scores_gemma":[0.00087789533,0.00063515693,0.69242907,0.00012593775,0.00020111317,0.000025423195,0.0005477388,0.00047852154,0.0000013334218,0.0050195106,0.29961687,0.000041402236],"about_ca_topic_score_codex":0.004893292,"about_ca_topic_score_gemma":0.0035348732,"teacher_disagreement_score":0.24941619,"about_ca_system_score_codex":0.00030530084,"about_ca_system_score_gemma":0.0030343414,"threshold_uncertainty_score":0.9986229},"labels":[],"label_agreement":null},{"id":"W2044999353","doi":"10.1016/j.jclinepi.2006.10.007","title":"Infant and toddler disease score was useful for risk of hospitalization based on data from administrative claims","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Obesity, Physical Activity, Diet","field":"Medicine","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":"Université de Montréal","funders":"","keywords":"Toddler; Medicine; Logistic regression; Pediatrics; Population; Cohort study; Cohort; Environmental health; Internal medicine","score_opus":0.32059220347769407,"score_gpt":0.5079006841229331,"score_spread":0.18730848064523903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044999353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9763964,0.00014078991,0.018667983,0.0036222353,0.00042567932,0.0003255501,0.00034790058,0.0000069476155,0.00006652692],"genre_scores_gemma":[0.990151,0.00021230402,0.006313272,0.0019667295,0.0012001295,0.0000016570792,0.00012679756,0.00001683364,0.000011314816],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99536973,0.0011216168,0.0026240593,0.00038855887,0.0002438475,0.00025220425],"domain_scores_gemma":[0.9487944,0.046917465,0.002760908,0.0005743445,0.00034388344,0.00060899975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010926032,0.00017486756,0.0019684099,0.000084556756,0.00003804838,0.0000038552166,0.00023689034,0.00025732355,0.000037439728],"category_scores_gemma":[0.09321094,0.00011956282,0.00039540147,0.00008787371,0.00041132903,0.0001465961,0.00009357112,0.0006807883,0.0000026862215],"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":[0.0051856423,0.0036998556,0.9859957,0.00006474792,0.00021662236,0.00003103471,0.000011591055,0.000059013753,0.000011102765,0.0007410241,0.0019938555,0.001989811],"study_design_scores_gemma":[0.0032622083,0.004873715,0.95761037,0.00025424737,0.0006038299,0.000003028878,0.000018854716,0.010874551,0.00006174491,0.021605205,0.0007327613,0.00009949271],"about_ca_topic_score_codex":0.000030066014,"about_ca_topic_score_gemma":0.000035423454,"teacher_disagreement_score":0.08228491,"about_ca_system_score_codex":0.0000269373,"about_ca_system_score_gemma":0.00029115632,"threshold_uncertainty_score":0.91442734},"labels":[],"label_agreement":null},{"id":"W2045874677","doi":"10.1016/j.jclinepi.2009.06.009","title":"Proxy reports of physical activity were valid in older people with and without cognitive impairment","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Physical Activity and Health","field":"Medicine","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":"Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Proxy (statistics); Intraclass correlation; Confidence interval; Medicine; Cognition; Inter-rater reliability; Prospective cohort study; Physical activity; Gerontology; Cognitive impairment; Cohort study; Physical therapy; Cohort; Psychology; Clinical psychology; Psychometrics; Psychiatry; Rating scale; Internal medicine; Developmental psychology; Statistics","score_opus":0.15941474236760866,"score_gpt":0.515034542320052,"score_spread":0.3556197999524433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045874677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98795986,0.000048811315,0.0005869731,0.010727494,0.00006587496,0.0003394367,0.0000018099644,0.000005468133,0.00026426138],"genre_scores_gemma":[0.9975629,0.00012487941,0.00067188445,0.0011726703,0.000438203,0.000002607613,9.727903e-7,0.0000072991616,0.000018598652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99629843,0.001261642,0.0016677014,0.0002677066,0.00021494974,0.00028956844],"domain_scores_gemma":[0.9902661,0.0066987476,0.0023202768,0.00015040887,0.00020100211,0.00036350088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005792339,0.00015081992,0.003310801,0.00008162526,0.000022380787,0.0000017233291,0.00004417321,0.00018227324,0.0000085867105],"category_scores_gemma":[0.008284593,0.000091185735,0.00030165978,0.000120692624,0.00024673986,0.00013136138,0.00002307872,0.0012093147,7.64733e-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":[0.0053229434,0.007564969,0.968173,0.000117443815,0.00010369065,0.00012362386,0.0002827361,0.000010521097,0.00013251268,0.00019167562,0.000094175426,0.017882667],"study_design_scores_gemma":[0.0035475648,0.01640173,0.97241926,0.000653281,0.00014888612,0.00065845595,0.000050919054,0.00052104174,0.00018424781,0.005304451,0.000030184357,0.00007997994],"about_ca_topic_score_codex":0.00004110816,"about_ca_topic_score_gemma":0.000020700361,"teacher_disagreement_score":0.017802687,"about_ca_system_score_codex":0.000033185108,"about_ca_system_score_gemma":0.00037951345,"threshold_uncertainty_score":0.991803},"labels":[],"label_agreement":null},{"id":"W2045910459","doi":"10.1016/j.jclinepi.2009.06.007","title":"A scale for distinguishing efficacy from effectiveness was adapted and applied to stroke rehabilitation studies","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Lawson Health Research Institute; Western University","funders":"Canadian Institutes of Health Research","keywords":"Confidence interval; Physical therapy; Medicine; Kappa; Rehabilitation; Randomized controlled trial; Reliability (semiconductor); Stroke (engine); Operationalization; Internal medicine; Mathematics","score_opus":0.3121866161788805,"score_gpt":0.5622545008997024,"score_spread":0.2500678847208219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045910459","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":[0.023672245,0.9668515,0.0027873726,0.002285221,0.001957378,0.0023054006,0.00005570262,0.000022004586,0.00006317607],"genre_scores_gemma":[0.0010163952,0.9329438,0.06242023,0.0007100629,0.0027248415,0.00006926585,0.00003133184,0.000040239196,0.00004380035],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881795,0.004546929,0.0061399615,0.0005961548,0.00020755423,0.00032989206],"domain_scores_gemma":[0.639286,0.35616654,0.0033070317,0.0002813754,0.00053796184,0.00042110268],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02290842,0.0003954497,0.014195168,0.00033264715,0.00007029161,0.000008929096,0.00016598607,0.00078413665,0.000005406775],"category_scores_gemma":[0.404944,0.00022570467,0.002476292,0.00016739723,0.0002927182,0.00004312955,0.0000623586,0.0011815662,0.000005932728],"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":[0.0016320277,0.00026027704,0.0041390476,0.006906931,0.0009387534,0.0000044288945,0.000105311374,0.000011667763,0.0000013335498,0.00010397334,0.0012874516,0.98460877],"study_design_scores_gemma":[0.004880783,0.008534531,0.13321143,0.043989535,0.004011639,0.00007507231,0.00023038378,0.000012477444,4.7266965e-7,0.003128671,0.8015927,0.0003322727],"about_ca_topic_score_codex":0.0000038903945,"about_ca_topic_score_gemma":0.0000032509097,"teacher_disagreement_score":0.98427653,"about_ca_system_score_codex":0.00016944876,"about_ca_system_score_gemma":0.00035565344,"threshold_uncertainty_score":0.9703533},"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":["metaepi_broad"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2046080627","doi":"10.1016/j.jclinepi.2008.12.007","title":"Walter O. Spitzer 1937–2006","year":2009,"lang":"de","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Migration, Racism, and Human Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences","funders":"","keywords":"Converse; Gerontology; Sociology; Demography; History; Medicine; Philosophy; Epistemology","score_opus":0.2447227925305227,"score_gpt":0.5216793537152249,"score_spread":0.2769565611847022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046080627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86831003,0.018577825,0.0043076244,0.06790615,0.028247751,0.00039242744,0.000017609096,0.000044680168,0.012195901],"genre_scores_gemma":[0.8897292,0.021986894,0.002647409,0.032343496,0.04303447,8.8777574e-7,0.000005354227,0.000020958825,0.010231301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97941685,0.01055526,0.008207704,0.00045177608,0.0005230417,0.0008453459],"domain_scores_gemma":[0.9744141,0.017581536,0.006175341,0.00038236272,0.0005572354,0.0008894259],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.045086786,0.0003116667,0.0033689176,0.00018760377,0.0004214018,0.000039084975,0.00086241437,0.001092928,0.0024657983],"category_scores_gemma":[0.034859817,0.00021625089,0.0018168913,0.00020699402,0.0006926859,0.0003793197,0.000035668978,0.001859585,0.0008007639],"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":[0.0007836596,0.0015404047,0.069586545,0.000030568546,0.0005499043,0.00022664723,0.023358101,0.00014475934,0.0000053962835,0.13877012,0.7008252,0.064178675],"study_design_scores_gemma":[0.0011141234,0.0020985994,0.20362115,0.00012212491,0.00028223067,0.000020522735,0.0007305597,0.00013243404,0.0000018414248,0.3266823,0.46491498,0.00027914098],"about_ca_topic_score_codex":0.00006297033,"about_ca_topic_score_gemma":0.0014413892,"teacher_disagreement_score":0.23591025,"about_ca_system_score_codex":0.00007454697,"about_ca_system_score_gemma":0.000663474,"threshold_uncertainty_score":0.99997723},"labels":[],"label_agreement":null},{"id":"W2046099868","doi":"10.1016/j.jclinepi.2007.12.008","title":"R and S-PLUS produced different classification trees for predicting patient mortality","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","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":"University of Toronto; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Statistics; Mathematics","score_opus":0.8048081317288023,"score_gpt":0.6610888984722897,"score_spread":0.1437192332565126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046099868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97937745,0.00034325465,0.0038451753,0.012458812,0.0030406276,0.0008073597,0.000011988682,0.000021265962,0.000094038],"genre_scores_gemma":[0.9923611,0.0010711566,0.0018065935,0.0023735524,0.0022550058,0.000059804137,0.000005127353,0.000015669235,0.000051986583],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98534024,0.006405332,0.007257164,0.00033444547,0.00018028695,0.00048252242],"domain_scores_gemma":[0.9366669,0.056384172,0.0053819064,0.00030798212,0.00084547617,0.00041355708],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015443351,0.00014840616,0.0017442438,0.000072106945,0.0005268625,0.000001324585,0.0001722859,0.0005091272,0.000034928154],"category_scores_gemma":[0.14025654,0.00010011391,0.00030942087,0.0000643746,0.00032343,0.00009570978,0.00006767786,0.0014290094,0.000008213704],"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":[0.00043494315,0.00009380094,0.9798329,0.000106507905,0.000047581787,0.0000036887714,0.0009526603,0.000034329063,0.0000397547,0.0014290664,0.0024811549,0.014543652],"study_design_scores_gemma":[0.00043895666,0.0011859864,0.97325873,0.00017076098,0.000043277527,0.000018887613,0.0012285652,0.011725124,0.000028079941,0.009382486,0.0024325433,0.000086627195],"about_ca_topic_score_codex":0.00015259883,"about_ca_topic_score_gemma":0.00029215415,"teacher_disagreement_score":0.124813184,"about_ca_system_score_codex":0.00011664951,"about_ca_system_score_gemma":0.0005373804,"threshold_uncertainty_score":0.86698544},"labels":[],"label_agreement":null},{"id":"W2046121962","doi":"10.1016/j.jclinepi.2004.08.021","title":"Language of publication restrictions in systematic reviews gave different results depending on whether the intervention was conventional or complementary","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":214,"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; University of Alberta; GlaxoSmithKline (Canada); Children's Hospital of Eastern Ontario","funders":"","keywords":"Systematic review; Psychological intervention; Publication bias; Meta-analysis; Randomized controlled trial; Medicine; Intervention (counseling); MEDLINE; Random effects model; Odds; Study heterogeneity; Odds ratio; Surgery; Pathology; Internal medicine","score_opus":0.914407917999512,"score_gpt":0.6782085590900272,"score_spread":0.23619935890948485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046121962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80088866,0.00866869,0.06373297,0.11415422,0.0032142794,0.0049723163,0.000077437406,0.0000067411106,0.004284694],"genre_scores_gemma":[0.9895526,0.0008032741,0.0040997914,0.002093637,0.0005138131,0.000040541836,0.000014735442,0.000007704828,0.0028738766],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.67089444,0.22114822,0.103952385,0.0007930108,0.0028343382,0.00037761225],"domain_scores_gemma":[0.5798797,0.32212883,0.09328442,0.0029059101,0.0015681932,0.00023293278],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53423166,0.0001910687,0.0077378675,0.00047880056,0.00006114316,0.000053415875,0.0012992934,0.00013236317,0.0034214708],"category_scores_gemma":[0.6493161,0.00006471121,0.0038899146,0.00054855034,0.00010293164,0.00018235366,0.00008843708,0.0006058791,0.00030268083],"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":[0.0011939545,0.0024177788,0.31809625,0.0028756578,0.0014811998,0.0000141772725,0.0011388321,0.0011907791,0.000027978143,0.033938285,0.56465286,0.07297229],"study_design_scores_gemma":[0.0053855283,0.0019643225,0.7814066,0.011163376,0.0012503662,0.00021395537,0.0032816879,0.030210063,0.000012545772,0.017020106,0.14774324,0.0003482011],"about_ca_topic_score_codex":0.000024790634,"about_ca_topic_score_gemma":0.00042437416,"teacher_disagreement_score":0.46331036,"about_ca_system_score_codex":0.00007113938,"about_ca_system_score_gemma":0.000046957128,"threshold_uncertainty_score":0.9974895},"labels":[],"label_agreement":null},{"id":"W2046368309","doi":"10.1016/j.jclinepi.2005.08.005","title":"An unadjusted NNT was a moderately good predictor of health benefit","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Medicine; Number needed to treat; Internal medicine; Confidence interval; Relative risk","score_opus":0.8564951572878206,"score_gpt":0.6447774638103312,"score_spread":0.21171769347748937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046368309","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":[0.0005827161,0.97287655,0.007380103,0.013847814,0.0031843921,0.0009001288,0.0007998561,0.000020553745,0.0004079068],"genre_scores_gemma":[0.00031649423,0.97982806,0.0076774205,0.008647519,0.0030744288,0.000029312718,0.00014634129,0.0000898374,0.00019058536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8936282,0.018630426,0.08564943,0.0009944909,0.00018028535,0.00091717334],"domain_scores_gemma":[0.8508543,0.04890811,0.09804562,0.0010550389,0.0003398416,0.00079711195],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2851817,0.0005942563,0.03134541,0.00083647674,0.00012039814,0.000021482663,0.0011722797,0.0017257348,0.00022204679],"category_scores_gemma":[0.089705884,0.0005538267,0.0030688022,0.00029636905,0.000303609,0.00036383542,0.00008596365,0.0020360728,0.0002088261],"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":[0.00020130735,0.0027283023,0.06364768,0.059150144,0.003165906,0.000018932164,0.0002906917,0.0024091634,5.910627e-9,0.25656638,0.15320398,0.4586175],"study_design_scores_gemma":[0.0010704355,0.0016381759,0.010495431,0.005440628,0.00015840042,0.00009004584,0.000030573174,0.0018230366,4.1480512e-9,0.03723917,0.94161123,0.0004028721],"about_ca_topic_score_codex":0.0008412277,"about_ca_topic_score_gemma":0.000102950595,"teacher_disagreement_score":0.78840727,"about_ca_system_score_codex":0.0006906642,"about_ca_system_score_gemma":0.0028068996,"threshold_uncertainty_score":0.9996913},"labels":[],"label_agreement":null},{"id":"W2046810336","doi":"10.1016/s0895-4356(99)00186-9","title":"Nutrition risk factors for institutionalization in a free-living functionally dependent elderly population","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Nutrition and Health in Aging","field":"Medicine","cited_by":157,"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; Health and Social Services Centre University Institute of Geriatrics of Sherbrooke","funders":"Health Canada; Medical Research Council Canada","keywords":"Institutionalisation; Medicine; Multivariate analysis; Gerontology; Proportional hazards model; Hazard ratio; Weight loss; Cohort; Cohort study; Multivariate statistics; Activities of daily living; Population; Univariate analysis; Demography; Physical therapy; Internal medicine; Confidence interval; Environmental health; Obesity; Psychiatry","score_opus":0.26904719483360756,"score_gpt":0.5094212828321998,"score_spread":0.24037408799859222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046810336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93006337,0.00082398235,0.055759482,0.011521676,0.0012484111,0.00035805683,0.000014866859,0.000015338343,0.00019479476],"genre_scores_gemma":[0.9723298,0.0035600031,0.018819604,0.0031843141,0.0018677535,0.000013313201,0.000060389284,0.000010902744,0.00015389982],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948578,0.0013555787,0.0032130908,0.00017911888,0.00017926515,0.0002151644],"domain_scores_gemma":[0.9861679,0.011962825,0.001287542,0.00012335823,0.00025486143,0.00020352258],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0112909535,0.000098215074,0.001055595,0.00021586004,0.00007702721,0.000004131768,0.0000722217,0.00030863885,0.00037840963],"category_scores_gemma":[0.04110505,0.000082180886,0.00035307894,0.000120958655,0.0000611629,0.00014870956,0.0000070955175,0.0005960603,0.0000054037464],"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":[0.0010102222,0.0006214139,0.95041275,0.00017381718,0.000039156075,0.0000041767635,0.000023683313,0.0017697711,0.0000031161132,0.0047133733,0.0029784802,0.03825002],"study_design_scores_gemma":[0.004178254,0.0011851235,0.9202623,0.000680374,0.00006588473,0.00009750574,0.000023983603,0.0034979046,0.0000011290543,0.04409577,0.025843678,0.00006810464],"about_ca_topic_score_codex":0.000108695036,"about_ca_topic_score_gemma":0.000088230154,"teacher_disagreement_score":0.042266432,"about_ca_system_score_codex":0.00011604528,"about_ca_system_score_gemma":0.000142652,"threshold_uncertainty_score":0.9669721},"labels":[],"label_agreement":null},{"id":"W2046881946","doi":"10.1016/j.jclinepi.2003.12.012","title":"Advances in risk-benefit evaluation using probabilistic simulation methods: an application to the prophylaxis of deep vein thrombosis","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":65,"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 Hospital; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Medicine; Confidence interval; Probabilistic logic; Risk assessment; Deep vein; Monte Carlo method; Statistics; Econometrics; Computer science; Thrombosis; Surgery; Mathematics; Internal medicine","score_opus":0.2622894232459334,"score_gpt":0.5774733633348321,"score_spread":0.3151839400888987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046881946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63296336,0.00065304985,0.36345118,0.0017563028,0.00024737424,0.00087350234,8.79756e-7,0.000004029323,0.000050315673],"genre_scores_gemma":[0.8922019,0.00086633547,0.10582838,0.0007059601,0.0003568381,0.000026863807,0.0000027551218,0.000010577416,4.031365e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9926071,0.0033363355,0.003273409,0.00027324446,0.00030261424,0.00020730156],"domain_scores_gemma":[0.9885495,0.0074997125,0.0028154217,0.00036912257,0.00061578304,0.00015050962],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038800783,0.00012249958,0.0016113075,0.0001666892,0.000048951777,0.000003769166,0.00018100523,0.00017745692,0.000020967616],"category_scores_gemma":[0.055686384,0.00007603523,0.00025903442,0.00031561925,0.000113274175,0.00017156535,0.000040334042,0.00043707853,0.0000031986021],"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":[0.00014418102,0.00057616195,0.037302688,0.00004250433,0.000040091225,4.217833e-7,0.00017086751,0.6710256,0.000060672435,0.0011806269,0.0000020300017,0.2894542],"study_design_scores_gemma":[0.0013781072,0.00297499,0.6823918,0.000158945,0.00041780874,0.0000046488904,0.0001384343,0.24046205,0.000034282835,0.07155131,0.00041333365,0.0000742725],"about_ca_topic_score_codex":0.00016827439,"about_ca_topic_score_gemma":0.00025764175,"teacher_disagreement_score":0.64508915,"about_ca_system_score_codex":0.00017416649,"about_ca_system_score_gemma":0.00015416442,"threshold_uncertainty_score":0.9897569},"labels":[],"label_agreement":null},{"id":"W2047221535","doi":"10.1016/j.jclinepi.2011.10.014","title":"Search filters can find some but not all knowledge translation articles in MEDLINE: an analytic survey","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Terminology; MEDLINE; Filter (signal processing); Information retrieval; Computer science; Field (mathematics); Sensitivity (control systems); Translation (biology); Medical physics; Medicine; Mathematics; Linguistics","score_opus":0.727354163457325,"score_gpt":0.5872265397795597,"score_spread":0.1401276236777652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047221535","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":[0.026042165,0.9716551,0.0003875769,0.0007069895,0.00094316853,0.00016504795,0.000075488446,0.000005584156,0.000018925542],"genre_scores_gemma":[0.012476232,0.9823108,0.002010653,0.0005966261,0.0021988025,0.0000057373986,0.00027555783,0.000035283723,0.00009032065],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97948235,0.014071187,0.0050905817,0.0005089827,0.00017784942,0.00066903664],"domain_scores_gemma":[0.98223984,0.014673473,0.0018912392,0.00045655522,0.00016830748,0.0005705717],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038163196,0.00037699382,0.004587086,0.00024881552,0.000031057163,0.000009310278,0.0006911073,0.0019067465,0.00002917124],"category_scores_gemma":[0.027572459,0.00025934458,0.0011534085,0.00019145719,0.0005515767,0.000009639063,0.00010612306,0.0016420156,0.000015003949],"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":[0.00016044984,0.00032218974,0.008434195,0.00062152604,0.00033532653,0.00001529866,0.000036012912,0.000011237479,0.00001582249,0.000010218496,0.00073290523,0.98930484],"study_design_scores_gemma":[0.0015160491,0.0029042894,0.038235873,0.0014173175,0.00078195607,0.00021093064,0.00004030391,0.0002333784,0.0000195854,0.00021500546,0.9538222,0.000603107],"about_ca_topic_score_codex":0.00010203714,"about_ca_topic_score_gemma":0.0007515532,"teacher_disagreement_score":0.9887017,"about_ca_system_score_codex":0.000039455546,"about_ca_system_score_gemma":0.0007955847,"threshold_uncertainty_score":0.9999859},"labels":[],"label_agreement":null},{"id":"W2047388154","doi":"10.1016/j.jclinepi.2005.11.017","title":"Evaluation of comorbidity indices for inpatient mortality prediction models","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","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":"Université de Montréal","funders":"","keywords":"Comorbidity; Medicine; Statistics; Psychiatry; Mathematics","score_opus":0.6562175460901517,"score_gpt":0.5897382518768848,"score_spread":0.06647929421326693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047388154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9714114,0.0005764682,0.021823037,0.0013942266,0.0009291651,0.00052449765,0.000030038369,0.000009511242,0.0033016552],"genre_scores_gemma":[0.99655974,0.00019403001,0.0018822912,0.00029853702,0.0009862767,0.000012169094,0.000041770487,0.0000071056093,0.000018056446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99331737,0.0018591528,0.0038810484,0.00017569098,0.0005925069,0.00017423509],"domain_scores_gemma":[0.9906497,0.0044787135,0.0034135326,0.00022213499,0.0011199149,0.00011601977],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04292555,0.00009944717,0.0013324388,0.00010739843,0.000024450579,0.0000024120702,0.000102656086,0.00017927292,0.00007325539],"category_scores_gemma":[0.018819481,0.00007408882,0.00055177533,0.00007444814,0.00021787647,0.00015065674,0.00002842311,0.0002670777,9.637582e-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":[0.0012384687,0.0019379365,0.8655362,0.00042218537,0.0008473094,0.000005452638,0.00003140627,0.06784353,0.000021142077,0.018759347,0.019835947,0.023521075],"study_design_scores_gemma":[0.0037403095,0.001240495,0.7065334,0.00008192939,0.0017029354,0.000006263326,0.00003876352,0.116228044,0.00000966818,0.16985126,0.0005270971,0.000039854054],"about_ca_topic_score_codex":0.00008537439,"about_ca_topic_score_gemma":0.000026901469,"teacher_disagreement_score":0.15900283,"about_ca_system_score_codex":0.0001028272,"about_ca_system_score_gemma":0.0005793133,"threshold_uncertainty_score":0.98944545},"labels":[],"label_agreement":null},{"id":"W2047586716","doi":"10.1016/j.jclinepi.2012.01.012","title":"GRADE guidelines: 12. Preparing Summary of Findings tables—binary outcomes","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":846,"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 Work & Health; McMaster University","funders":"","keywords":"Observational study; Relative risk; Confidence interval; Absolute risk reduction; Point estimation; Randomized controlled trial; Medicine; Meta-analysis; Statistics; Baseline (sea); Mathematics; Internal medicine","score_opus":0.9676604359397987,"score_gpt":0.7295634591413548,"score_spread":0.23809697679844388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047586716","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":[0.00011021166,0.9889181,0.0033593106,0.0011079112,0.004395101,0.0006596419,0.00003704695,0.0000031737918,0.001409477],"genre_scores_gemma":[0.000040855248,0.9633791,0.027870892,0.0009574231,0.0016813487,0.00001392079,0.000014091776,0.00004325159,0.005999116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.50646573,0.21657704,0.26792088,0.0018887819,0.0059977365,0.0011498396],"domain_scores_gemma":[0.24215038,0.52908534,0.21744457,0.006274911,0.003915596,0.0011292029],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.7827396,0.0010120916,0.098145194,0.0012175429,0.00008933523,0.00008316266,0.0064931693,0.0016419151,0.0035932434],"category_scores_gemma":[0.85519624,0.00039884564,0.042301007,0.0009897376,0.00041114227,0.00040727208,0.00078052137,0.0024580942,0.00083808217],"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":[0.000012206098,0.00017264875,0.09566723,0.0030720567,0.0023226826,0.000013260062,0.000015041331,0.00002782864,2.8872773e-8,0.00068696,0.3086146,0.58939546],"study_design_scores_gemma":[0.00022510403,0.00020435416,0.0032002951,0.005442475,0.0060737533,0.00023669048,0.00002398781,0.000118170945,1.409143e-8,0.004484751,0.9797014,0.00028900418],"about_ca_topic_score_codex":0.000019771827,"about_ca_topic_score_gemma":0.000013766706,"teacher_disagreement_score":0.6710868,"about_ca_system_score_codex":0.00007121701,"about_ca_system_score_gemma":0.00078452646,"threshold_uncertainty_score":0.99993986},"labels":[],"label_agreement":null},{"id":"W2048139673","doi":"10.1016/j.jclinepi.2014.04.001","title":"Active implementation strategy of CONSORT adherence by a dental specialty journal improved randomized clinical trial reporting","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":94,"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; Ottawa Hospital","funders":"","keywords":"Consolidated Standards of Reporting Trials; Medicine; Checklist; Randomized controlled trial; Interquartile range; Clinical trial; Family medicine; Psychology; Surgery; Internal medicine","score_opus":0.9102011549577893,"score_gpt":0.7230497012117116,"score_spread":0.18715145374607767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048139673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88637805,0.0003292513,0.105036855,0.0013017985,0.004888668,0.0009960765,0.000011657662,0.0000019175604,0.0010557326],"genre_scores_gemma":[0.9811197,0.00049833953,0.013550195,0.00093676697,0.0034756798,0.000009539024,0.0000051445995,0.000013264881,0.00039137446],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.2452578,0.44607976,0.3018878,0.0014017352,0.0045890664,0.00078382116],"domain_scores_gemma":[0.06943987,0.4981855,0.4244708,0.0017884946,0.005157172,0.0009581821],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.88856584,0.0003633272,0.029509557,0.0002956018,0.00012843967,0.00015254831,0.0017792518,0.00049771933,0.0059439274],"category_scores_gemma":[0.93818766,0.00016665636,0.014929005,0.0004135123,0.00078785775,0.00038910715,0.00013680308,0.0018164888,0.00008247529],"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":[0.16063915,0.0006140706,0.24041042,0.000023994284,0.0025881517,0.000022813063,0.000092717426,0.00004628192,0.000064110245,0.0017073312,0.08711199,0.50667894],"study_design_scores_gemma":[0.69780785,0.0100772595,0.10746882,0.00018265213,0.0034115312,0.0009644674,0.0026220297,0.011915363,0.00006001455,0.13365804,0.031243524,0.0005884582],"about_ca_topic_score_codex":0.00002881574,"about_ca_topic_score_gemma":0.000053389165,"teacher_disagreement_score":0.5371687,"about_ca_system_score_codex":0.00003945335,"about_ca_system_score_gemma":0.00082982355,"threshold_uncertainty_score":0.9949648},"labels":[],"label_agreement":null},{"id":"W2048174423","doi":"10.1016/s0895-4356(03)00048-9","title":"Bias in estimates of confidence intervals for health outcome report cards","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","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 Calgary","funders":"","keywords":"Confidence interval; Statistics; Medicine; Logistic regression; Standard deviation; Standard error; Econometrics; Mathematics","score_opus":0.7130856774095898,"score_gpt":0.5921501756437927,"score_spread":0.12093550176579715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048174423","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":[0.3087948,0.010872882,0.43859395,0.22443381,0.008634063,0.0011480191,0.00012110693,0.00001858153,0.0073828106],"genre_scores_gemma":[0.9620669,0.0013468137,0.026813276,0.009433172,0.0001779536,0.00000818988,0.0000016762685,0.000011113934,0.00014091589],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9864793,0.0008299105,0.012030319,0.00025571926,0.000033238746,0.00037152081],"domain_scores_gemma":[0.97580075,0.014471441,0.00908619,0.00029681507,0.00011949759,0.00022532084],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.083649546,0.00010840427,0.0032541056,0.00024810262,0.000021209404,0.0000034045113,0.0002152014,0.00018418448,0.00004377888],"category_scores_gemma":[0.2142574,0.00009749824,0.0005827676,0.00011136777,0.000118820135,0.00007919427,0.000029538121,0.00039752354,0.000009418646],"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":[0.00003850038,0.00007512838,0.60394526,0.00011960068,0.0000426994,0.000010969233,0.000040649193,0.000112975,6.342391e-8,0.3921405,0.0018700061,0.0016036504],"study_design_scores_gemma":[0.0011144623,0.0010544376,0.33782843,0.00011727648,0.0000074810464,0.00008549296,0.00003830628,0.0005208166,0.0000035104242,0.52278715,0.13633396,0.00010864815],"about_ca_topic_score_codex":0.0010621086,"about_ca_topic_score_gemma":0.00014208071,"teacher_disagreement_score":0.6532721,"about_ca_system_score_codex":0.000072633295,"about_ca_system_score_gemma":0.00019855698,"threshold_uncertainty_score":0.9435756},"labels":[],"label_agreement":null},{"id":"W2048634900","doi":"10.1016/j.jclinepi.2006.03.004","title":"Limited search strategies were effective in finding relevant nonrandomized studies","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":55,"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 Work & Health; University of Toronto","funders":"","keywords":"Medicine; MEDLINE; Terminology; Psychological intervention; Vocabulary; Clinical study design; Cochrane Library; Standardization; Controlled vocabulary; Research design; Cohort study; Computer science; Information retrieval; Randomized controlled trial; Clinical trial; Surgery; Nursing; Statistics; Pathology","score_opus":0.9123345603419358,"score_gpt":0.7036210264626043,"score_spread":0.20871353387933156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048634900","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96328294,0.0071086474,0.017616566,0.0075585917,0.0017280596,0.0006046423,0.0000025826632,0.000002490884,0.0020954995],"genre_scores_gemma":[0.98704976,0.0010582011,0.009353892,0.000594098,0.00076399406,0.000011454041,9.388273e-7,0.000009035874,0.0011586491],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.55502385,0.35073817,0.088846445,0.0012007729,0.0034326285,0.00075813185],"domain_scores_gemma":[0.179596,0.7825111,0.03321118,0.001573614,0.0028542667,0.0002537866],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7627578,0.0002950702,0.02210819,0.0006974958,0.0000861488,0.00012013125,0.0013214602,0.00031986216,0.0006909928],"category_scores_gemma":[0.803117,0.00012049259,0.005610678,0.0008741041,0.00035725447,0.0003014156,0.00014673635,0.0012839814,0.0003743097],"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":[0.0017784762,0.0004213066,0.85059124,0.00009058091,0.001460476,0.00020052519,0.0003161426,0.011862725,0.000043837095,0.014020649,0.07968829,0.03952577],"study_design_scores_gemma":[0.007366057,0.0008708617,0.7148639,0.0003170711,0.00035994375,0.00010413042,0.0028678954,0.00857749,0.000005616643,0.24788143,0.016568037,0.00021756678],"about_ca_topic_score_codex":0.000031240637,"about_ca_topic_score_gemma":0.00013055054,"teacher_disagreement_score":0.43177298,"about_ca_system_score_codex":0.00005558398,"about_ca_system_score_gemma":0.00021531641,"threshold_uncertainty_score":0.99240965},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2048775918","doi":"10.1016/j.jclinepi.2005.11.010","title":"Single data extraction generated more errors than double data extraction in systematic reviews","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":463,"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; Capital District Health Authority","funders":"","keywords":"McNemar's test; Data extraction; Data set; Statistics; Computer science; Extraction (chemistry); Meta-analysis; Mathematics; Data mining; Medicine; MEDLINE; Chromatography","score_opus":0.9648740447910295,"score_gpt":0.7031798080107645,"score_spread":0.26169423678026493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048775918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5280022,0.0696023,0.3444012,0.030966295,0.016085846,0.0062806495,0.00020672604,0.000026282332,0.0044284915],"genre_scores_gemma":[0.8505032,0.0049984963,0.12637,0.0032179793,0.0061872546,0.000046184647,0.0009261863,0.00007170392,0.007679024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.64009064,0.20972204,0.1426196,0.002628101,0.0041706786,0.0007689343],"domain_scores_gemma":[0.39652732,0.35914743,0.21347591,0.026589954,0.0034319346,0.0008274523],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7508445,0.00039368158,0.01873177,0.0005622948,0.00009157976,0.00020260553,0.0060788486,0.00047983404,0.0012684561],"category_scores_gemma":[0.7052623,0.00017975466,0.002045781,0.0011919348,0.00015215755,0.0016176306,0.0004820714,0.0011853747,0.0009792439],"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":[0.0002516192,0.0012068744,0.22861362,0.0020112263,0.0005588168,0.00012043864,0.00004377311,0.0027693731,0.00022095127,0.00081776956,0.7426853,0.020700231],"study_design_scores_gemma":[0.002173843,0.00039725428,0.14078096,0.0033205263,0.0021607147,0.0011698835,0.0004220077,0.1979243,0.00000796975,0.010430935,0.6406427,0.0005689158],"about_ca_topic_score_codex":0.00018789801,"about_ca_topic_score_gemma":0.0007228846,"teacher_disagreement_score":0.322501,"about_ca_system_score_codex":0.000069670976,"about_ca_system_score_gemma":0.00020144919,"threshold_uncertainty_score":0.9997986},"labels":[],"label_agreement":null},{"id":"W2049539186","doi":"10.1016/j.jclinepi.2014.11.004","title":"Discordances originated by multiple meta-analyses on interventions for myocardial infarction: a systematic review","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":30,"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 General Hospital; McGill University","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Medicine; Psychological intervention; Meta-analysis; Population; Myocardial infarction; Internal medicine; MEDLINE; Psychiatry","score_opus":0.7688790135989907,"score_gpt":0.6789197326838071,"score_spread":0.08995928091518357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049539186","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":[2.9598903e-7,0.9714792,0.009700775,0.0127823595,0.0020098458,0.0037246684,0.00016380835,0.000024132023,0.00011493082],"genre_scores_gemma":[0.000004958642,0.9809242,0.0017130122,0.013365348,0.0020426533,0.000745068,0.00019993982,0.00007242353,0.00093238265],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9556861,0.023335388,0.019099198,0.0006709479,0.00064981834,0.0005585635],"domain_scores_gemma":[0.85198325,0.12615474,0.018475074,0.0011519011,0.0014623521,0.0007726892],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.06357906,0.00071227713,0.046877597,0.0005482296,0.00011040862,0.000020267069,0.0007010225,0.00090987555,0.00023571083],"category_scores_gemma":[0.35296005,0.00036242805,0.03826645,0.0005171391,0.0004289572,0.00010502554,0.00010562128,0.00302662,0.00014684115],"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":[0.00016258073,0.00028548948,0.000014263494,0.6590155,0.065326996,0.000013764704,0.0000011363558,0.0000032946687,4.7096187e-8,0.00014909574,0.2529736,0.022054255],"study_design_scores_gemma":[0.00061351416,0.0019996474,0.0000034717555,0.24964355,0.13747166,0.00036518456,0.0000026199248,0.000021858681,4.287436e-8,0.00010968203,0.6096071,0.00016164684],"about_ca_topic_score_codex":0.000019086407,"about_ca_topic_score_gemma":0.0000014256451,"teacher_disagreement_score":0.40937194,"about_ca_system_score_codex":0.00020037593,"about_ca_system_score_gemma":0.0007048137,"threshold_uncertainty_score":0.99988276},"labels":[],"label_agreement":null},{"id":"W2049895337","doi":"10.1016/j.jclinepi.2007.08.010","title":"Patients with systemic autoimmune diseases could not distinguish comorbidities from their index disease","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Systemic Sclerosis and Related Diseases","field":"Medicine","cited_by":16,"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; McGill University","funders":"Institute of Musculoskeletal Health and Arthritis; Actelion Pharmaceuticals; Canadian Institutes of Health Research; Pfizer Pharmaceuticals; University of Toronto; Arthritis Society","keywords":"Medicine; Comorbidity; Cohort; Internal medicine; Disease; Scleroderma (fungus); Systemic disease; Construct validity; Quality of life (healthcare); Severity of illness; Cohort study; Systemic scleroderma; Immunology; Psychometrics; Clinical psychology","score_opus":0.18126088549223301,"score_gpt":0.396875213895069,"score_spread":0.215614328402836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049895337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984924,0.010651457,0.00033291557,0.0015899474,0.001823495,0.00029955452,0.00024780357,0.0000463474,0.00008444425],"genre_scores_gemma":[0.99120504,0.0034998239,0.00015385041,0.0031671918,0.0017126806,0.000008414958,0.00009949788,0.00003829595,0.00011518715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9921533,0.002036095,0.00453768,0.00038355854,0.0004819328,0.0004074466],"domain_scores_gemma":[0.97728723,0.016220191,0.003920803,0.0005740037,0.00078609964,0.0012116721],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021904823,0.00032182486,0.0034354413,0.00011759203,0.00014673939,0.000007658889,0.00029738204,0.00035152998,0.00013938452],"category_scores_gemma":[0.03810241,0.00017554485,0.001016087,0.00012933624,0.0007870054,0.00010467436,0.00007203031,0.00093453407,0.000022143267],"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":[0.005304351,0.0009579289,0.9830288,0.00008854471,0.0007079678,0.0002903883,0.000058635578,0.00010572215,0.0000052420605,0.0000425262,0.00784585,0.0015640213],"study_design_scores_gemma":[0.0067605474,0.0008922525,0.9865399,0.0030759072,0.00070933887,0.00015555852,0.00010205654,0.0003755746,0.0000013539116,0.00024018824,0.0009557144,0.00019158048],"about_ca_topic_score_codex":0.0000795213,"about_ca_topic_score_gemma":0.0000012468977,"teacher_disagreement_score":0.03591193,"about_ca_system_score_codex":0.00007473984,"about_ca_system_score_gemma":0.0007071723,"threshold_uncertainty_score":0.9700001},"labels":[],"label_agreement":null},{"id":"W2050216778","doi":"10.1016/j.jclinepi.2010.07.009","title":"A decade of knowledge translation research—what has changed?","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Scopus; Knowledge translation; Mentorship; Library science; Medicine; Medical education; Computer science; MEDLINE; Political science; Knowledge management","score_opus":0.98258884766293,"score_gpt":0.8454668316518968,"score_spread":0.13712201601103313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050216778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7579424,0.00038886414,0.0033524707,0.22906168,0.006941978,0.00053922145,0.000009834162,0.00001158466,0.0017519875],"genre_scores_gemma":[0.9646992,0.0015831382,0.015206867,0.014473265,0.00382653,0.000021773287,0.0000013520628,0.00001643961,0.0001714379],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.94792575,0.03987369,0.010371312,0.00029218226,0.00050118146,0.0010358898],"domain_scores_gemma":[0.6173519,0.37326413,0.005708765,0.0004544261,0.00228179,0.000938989],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.241225,0.00010814984,0.0016877082,0.00044082935,0.0004156527,0.0000052500004,0.00058666436,0.0006811466,0.0009537524],"category_scores_gemma":[0.3619095,0.00007852405,0.00031838237,0.0005216594,0.0010486728,0.00043367245,0.000089891386,0.0050985236,0.00021637196],"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":[0.0008078863,0.00037010282,0.51650065,0.0005316541,0.00008294099,0.000009138951,0.024007747,0.000008105945,0.0023526507,0.020927152,0.1241817,0.31022027],"study_design_scores_gemma":[0.002254986,0.00095125934,0.3669965,0.0003208168,0.000018990357,0.000016816042,0.0020384497,0.00038279666,0.000043203396,0.025009379,0.6018766,0.00009019369],"about_ca_topic_score_codex":0.00009953175,"about_ca_topic_score_gemma":0.0009409188,"teacher_disagreement_score":0.47769493,"about_ca_system_score_codex":0.00005025392,"about_ca_system_score_gemma":0.003027552,"threshold_uncertainty_score":0.9999595},"labels":[],"label_agreement":null},{"id":"W2050257625","doi":"10.1016/j.jclinepi.2007.10.023","title":"Reliability studies of diagnostic tests are not using enough observers for robust estimation of interobserver agreement: a simulation study","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Kappa; Reliability (semiconductor); Statistics; Sample (material); Variance (accounting); Cohen's kappa; Sample size determination; Variation (astronomy); Inter-rater reliability; Computer science; Population; Variable (mathematics); Econometrics; Mathematics; Medicine","score_opus":0.8782298280510391,"score_gpt":0.620131203012851,"score_spread":0.25809862503818815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050257625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94049704,0.0002841422,0.055926852,0.001284826,0.001270666,0.0007174982,0.0000116297415,0.0000037520517,0.0000035779092],"genre_scores_gemma":[0.9608097,0.00018044128,0.038544606,0.0002508945,0.00018696935,0.0000063167154,8.5048504e-7,0.000006782358,0.000013448677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9774507,0.0074603464,0.012924083,0.0005308105,0.0013357827,0.00029826805],"domain_scores_gemma":[0.50787836,0.46410236,0.019915951,0.0011196557,0.006739813,0.0002438418],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10365155,0.00020713432,0.0032790226,0.00018394706,0.00012730059,0.0000067168394,0.0006826267,0.0002001976,0.000038086535],"category_scores_gemma":[0.77846193,0.00013272808,0.0009856916,0.0003570678,0.00064795476,0.0003874422,0.00016355424,0.0003870304,0.0000031269333],"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":[0.00046134985,0.0010251763,0.4723378,0.000048839516,0.00012662531,0.0000025915162,0.00030481518,0.52329993,0.000012432991,0.000021214799,0.00027410037,0.0020850939],"study_design_scores_gemma":[0.0023098788,0.0032548944,0.85579324,0.00025974284,0.00017818222,0.0000041121148,0.0011434099,0.12633163,0.000037989386,0.010508118,0.000076642114,0.000102141355],"about_ca_topic_score_codex":0.000033948214,"about_ca_topic_score_gemma":0.000035368124,"teacher_disagreement_score":0.6748104,"about_ca_system_score_codex":0.00010981267,"about_ca_system_score_gemma":0.0001797572,"threshold_uncertainty_score":0.92297935},"labels":[],"label_agreement":null},{"id":"W2050393126","doi":"10.1016/j.jclinepi.2005.02.003","title":"Risks and benefits of population-based genetic testing for Mendelian subsets of common diseases were examined using the example of colorectal cancer risk","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"BRCA gene mutations in cancer","field":"Biochemistry, Genetics and Molecular Biology","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":"Canadian Institutes of Health Research; Institute for Work & Health; Institute of Population and Public Health; University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Genetic testing; Harm; Population; Medicine; Mendelian inheritance; Genetic predisposition; Colorectal cancer; Risk assessment; Disease; Epidemiology; Cancer; Genetics; Environmental health; Biology; Pathology; Internal medicine; Computer science; Psychology; Gene","score_opus":0.26233107635368746,"score_gpt":0.46857704840394027,"score_spread":0.2062459720502528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050393126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909002,0.005204688,0.0029641814,0.00032571855,0.00019569798,0.00018074483,0.00022342798,0.0000012932597,0.000004053857],"genre_scores_gemma":[0.9599902,0.0005221793,0.038898308,0.00015850221,0.0003906416,0.000007248277,0.000017227338,0.000014081476,0.0000015901921],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99625975,0.0009328016,0.0023432705,0.00019620029,0.00010202982,0.00016595291],"domain_scores_gemma":[0.9880951,0.0075641517,0.0036110345,0.00020550546,0.0004389588,0.00008521995],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030791643,0.000119529475,0.0009234247,0.000054714284,0.0000547364,0.0000018216688,0.00019446845,0.00020593397,0.000008167077],"category_scores_gemma":[0.013559435,0.000085714615,0.0002651939,0.00008300129,0.0002873629,0.0000050116932,0.000047056335,0.00016283074,3.200278e-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":[0.00039778792,0.00008942606,0.80982417,0.000040029823,0.00013271146,1.1314295e-7,0.000012887346,0.16174373,0.00411476,0.000020301335,0.000086473534,0.023537587],"study_design_scores_gemma":[0.0012345697,0.000918776,0.9694032,0.00007297218,0.00028018438,0.000008220331,0.000019703239,0.020925641,0.006357619,0.000519186,0.00017887366,0.00008104539],"about_ca_topic_score_codex":0.0012765664,"about_ca_topic_score_gemma":0.00056979945,"teacher_disagreement_score":0.15957902,"about_ca_system_score_codex":0.000025187848,"about_ca_system_score_gemma":0.00030768735,"threshold_uncertainty_score":0.9947498},"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":"W2052157066","doi":"10.1016/j.jclinepi.2014.07.007","title":"The use of Latin squares and related block designs in implementation research","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Block (permutation group theory); Psychological intervention; Computer science; Research design; Econometrics; Clinical study design; Block design; Variable (mathematics); Statistics; Mathematics; Medicine; Clinical trial","score_opus":0.9414811609474883,"score_gpt":0.6852574035911596,"score_spread":0.25622375735632874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052157066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91960895,0.0010237868,0.001222785,0.07720436,0.0005204441,0.00023181744,0.000010153114,0.000002542571,0.00017514151],"genre_scores_gemma":[0.9899728,0.0016004655,0.005190558,0.0028294974,0.00026983966,0.000006375494,0.0000020800958,0.000010382579,0.00011804686],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9614286,0.018108793,0.019703325,0.00027225647,0.00009390375,0.00039316248],"domain_scores_gemma":[0.80081767,0.18928392,0.009251291,0.0002757979,0.00020830393,0.00016303181],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34218234,0.00007823632,0.0018135124,0.00035769236,0.000101969665,0.00001553616,0.00021196526,0.00022638479,0.00005181259],"category_scores_gemma":[0.3142519,0.000064720676,0.00017159189,0.00018971656,0.00032417415,0.0002032492,0.000050572078,0.0006925216,0.000047898073],"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":[0.00006454118,0.00004237898,0.8393147,0.00003382816,0.000045250705,4.8301024e-7,0.0002757449,0.00045630094,0.0000011755413,0.1438649,0.013373821,0.002526874],"study_design_scores_gemma":[0.0010138482,0.00054315577,0.79649496,0.000053151318,0.0000038463686,0.000008012228,0.0003350047,0.0071551413,6.5799856e-7,0.15311752,0.041215774,0.000058897178],"about_ca_topic_score_codex":0.00042843798,"about_ca_topic_score_gemma":0.00026429349,"teacher_disagreement_score":0.17117514,"about_ca_system_score_codex":0.0000819953,"about_ca_system_score_gemma":0.00014066882,"threshold_uncertainty_score":0.69152445},"labels":[],"label_agreement":null},{"id":"W2052218786","doi":"10.1016/j.jclinepi.2009.08.015","title":"The predictors of self-rated health and the relationship between self-rated health and health service needs are similar across socioeconomic groups in Canada","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Work & Health; York University; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Socioeconomic status; Health care; Environmental health; Self-rated health; Gerontology; Medicine; Ordered probit; Population","score_opus":0.21919174547115586,"score_gpt":0.4992822332678424,"score_spread":0.28009048779668655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052218786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5501536,0.004964732,0.000009264467,0.44421288,0.00037071557,0.00025146714,0.0000152072735,0.000008223018,0.00001389296],"genre_scores_gemma":[0.8614699,0.023754915,0.0001811568,0.11408302,0.00048781154,0.0000020955486,0.000004076393,0.00000767739,0.000009326775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.977732,0.015162656,0.005621372,0.00022771796,0.00025134347,0.0010049193],"domain_scores_gemma":[0.9290872,0.063416086,0.005865527,0.00020676713,0.00019179542,0.0012325795],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071415916,0.00016981122,0.0023977207,0.000059606882,0.0011586377,0.00002331687,0.00038204654,0.00026562525,0.0000031368315],"category_scores_gemma":[0.017709251,0.00010324919,0.00014863843,0.00031200532,0.00043964377,0.00014150976,0.000049171635,0.0013766093,5.689604e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011604828,0.000028240276,0.979176,0.00010714064,0.000058469683,9.119203e-7,0.0078075835,0.00003491664,7.0602363e-10,0.0062150825,0.0047152094,0.0017403825],"study_design_scores_gemma":[0.0016150388,0.00037368832,0.96339506,0.00012519973,0.000010691185,0.000003763915,0.019390084,0.00018927944,5.2964504e-9,0.0068461723,0.007979439,0.000071597206],"about_ca_topic_score_codex":0.5651306,"about_ca_topic_score_gemma":0.82938707,"teacher_disagreement_score":0.33012986,"about_ca_system_score_codex":0.0008224214,"about_ca_system_score_gemma":0.014549024,"threshold_uncertainty_score":0.99103755},"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":"W2052957337","doi":"10.1016/j.jclinepi.2012.10.004","title":"The validity of administrative data to identify hip fractures is high—a systematic review","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":false,"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; University of Saskatchewan; Arthritis Research Centre of Canada; McGill University; University of British Columbia; McGill University Health Centre; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Diagnosis code; Receiver operating characteristic; Osteoporosis; Hip fracture; Pharmacy; MEDLINE; Emergency medicine; Algorithm; Data mining; Family medicine; Internal medicine; Computer science; Population","score_opus":0.8234436957175646,"score_gpt":0.7096918995225201,"score_spread":0.1137517961950445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052957337","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":[0.000022344659,0.97191405,0.00006974707,0.022702297,0.0011954983,0.003911514,0.00012256444,0.000005188565,0.000056789973],"genre_scores_gemma":[0.000032174532,0.98408026,0.0013068775,0.012784578,0.0012719361,0.00007951443,0.00006000556,0.000037464353,0.00034721196],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.94492126,0.029758858,0.022967553,0.0006554066,0.00096010894,0.00073679996],"domain_scores_gemma":[0.5659924,0.3804126,0.04105957,0.0062705134,0.0031070064,0.003157869],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11472814,0.00046810662,0.024068376,0.0001725323,0.000104067585,0.000015807305,0.002194535,0.0010635768,0.0003541728],"category_scores_gemma":[0.49924964,0.00020273218,0.0025677322,0.00035419432,0.00046158346,0.00010081864,0.00052568765,0.00426188,0.0002752571],"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":[0.00006855885,0.000128969,0.000101652004,0.6796206,0.00075756793,0.00003499817,0.000005082315,1.4665424e-8,3.48841e-8,0.00006738931,0.21484528,0.1043698],"study_design_scores_gemma":[0.00026007733,0.0015432814,0.000894013,0.42707962,0.0041547846,0.00043418191,0.000010397089,0.0000015669023,1.2415198e-7,0.00028432126,0.56522924,0.0001083976],"about_ca_topic_score_codex":0.0000420656,"about_ca_topic_score_gemma":0.000009005033,"teacher_disagreement_score":0.3845215,"about_ca_system_score_codex":0.00009182611,"about_ca_system_score_gemma":0.0037630168,"threshold_uncertainty_score":0.9980353},"labels":[],"label_agreement":null},{"id":"W2052990536","doi":"10.1016/j.jclinepi.2009.01.014","title":"Use of both short musculoskeletal function assessment questionnaire and short form-36 among tibial-fracture patients was redundant","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone fractures and treatments","field":"Medicine","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 Toronto; Western University; St. Michael's Hospital; London Health Sciences Centre; McMaster University; Ottawa Hospital; Institute for Work & Health","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Medicine; Intramedullary rod; Fixation (population genetics); Surgery; Physical therapy","score_opus":0.09892449967662306,"score_gpt":0.4563660853887034,"score_spread":0.3574415857120803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052990536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903456,0.0002846214,0.0044484762,0.00381887,0.00071321573,0.00027381818,0.0000048063503,0.00001131827,0.00009928551],"genre_scores_gemma":[0.99155104,0.00088611036,0.004108966,0.0027610231,0.0005857091,0.0000015651062,0.00003087859,0.0000147991805,0.00005991935],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99504036,0.00086897286,0.003193488,0.00029191276,0.0003096063,0.0002956486],"domain_scores_gemma":[0.9951511,0.0021294593,0.0016506019,0.00027537678,0.00035373034,0.00043973647],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037249096,0.00023228319,0.0020955484,0.00011964983,0.00006054514,0.000007720455,0.00007536103,0.00051408354,0.00003088022],"category_scores_gemma":[0.00904497,0.00014515896,0.0006984518,0.00007620067,0.00022713044,0.00027953423,0.00002981166,0.0010413352,9.537202e-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":[0.0012040505,0.0009779496,0.8765616,0.000027206432,0.00034145857,0.000034669254,0.0000124019125,0.00006953423,0.000012011651,0.000107274114,0.002553759,0.118098095],"study_design_scores_gemma":[0.0016773492,0.008591521,0.9833949,0.00031995412,0.0006890234,0.000087747954,0.000006758096,0.00026320145,0.0000058107667,0.0019151232,0.0029436168,0.00010495458],"about_ca_topic_score_codex":0.000060289964,"about_ca_topic_score_gemma":0.000023841825,"teacher_disagreement_score":0.11799314,"about_ca_system_score_codex":0.00007339053,"about_ca_system_score_gemma":0.00015657091,"threshold_uncertainty_score":0.99930227},"labels":[],"label_agreement":null},{"id":"W2053646717","doi":"10.1016/j.jclinepi.2007.05.003","title":"A survey of abstracts of high-impact clinical journals indicated most statistical methods presented are summary statistics","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Princess Margaret Cancer Centre; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Statistics; Confidence interval; Medicine; Summary statistics; Statistical analysis; Medical statistics; p-value; Statistical hypothesis testing; Mathematics","score_opus":0.9458305348711866,"score_gpt":0.7660828170350276,"score_spread":0.17974771783615906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053646717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3314624,0.0016620072,0.6635388,0.00076057913,0.0014853983,0.00029050987,0.00061925035,0.0000018563198,0.00017918985],"genre_scores_gemma":[0.696868,0.0009362119,0.3009631,0.0005822433,0.00041213006,7.821113e-7,0.000029597744,0.00002134408,0.00018658399],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.17200457,0.54808587,0.26816323,0.00182299,0.0084594805,0.0014638777],"domain_scores_gemma":[0.057548273,0.7674449,0.15961194,0.0025539258,0.011266505,0.0015744794],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8992218,0.00048272012,0.029333476,0.00097079575,0.00006687689,0.000064410466,0.0029385379,0.00095331593,0.0048349667],"category_scores_gemma":[0.9643791,0.00022837392,0.0048675495,0.0018490067,0.0012630421,0.00022248205,0.00027431065,0.0025243112,0.00010775433],"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":[0.0007118902,0.0006458471,0.78955144,0.000046388785,0.0016100045,0.00007613647,0.00001587849,0.00045614174,0.000009538069,0.0005084731,0.12602934,0.0803389],"study_design_scores_gemma":[0.0011064719,0.0012378227,0.9652976,0.0001613341,0.00061785616,0.00008458658,0.00006920741,0.0025628158,0.000008622408,0.025700748,0.0029893704,0.00016356206],"about_ca_topic_score_codex":0.0003223342,"about_ca_topic_score_gemma":0.00021462583,"teacher_disagreement_score":0.3654056,"about_ca_system_score_codex":0.00004271438,"about_ca_system_score_gemma":0.0010104331,"threshold_uncertainty_score":0.9997769},"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":"W2054086610","doi":"10.1016/j.jclinepi.2004.11.027","title":"Procedures that assess inconsistency in meta-analyses can assess the likelihood of response bias in multiwave surveys","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"McMaster University; Hamilton Health Sciences; McMaster University Medical Centre; Health Sciences Centre","funders":"","keywords":"Non-response bias; Response bias; Statistics; Meta-analysis; Econometrics; Statistic; Inference; Causal inference; Publication bias; Psychology; Medicine; Mathematics; Computer science; Confidence interval; Artificial intelligence","score_opus":0.9291225428926071,"score_gpt":0.6781206536904303,"score_spread":0.2510018892021768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054086610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9572375,0.002127367,0.0011309269,0.03835809,0.00065410644,0.00021773257,0.000009347481,0.000007044978,0.00025791617],"genre_scores_gemma":[0.98668694,0.0011538633,0.009173709,0.0024939699,0.0003516858,0.000011118444,9.377733e-7,0.000012257332,0.00011548554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.19780898,0.79212075,0.008047205,0.0005128462,0.0006258985,0.0008843182],"domain_scores_gemma":[0.32996517,0.66424096,0.0046475916,0.00038737495,0.00049910677,0.00025981263],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7603917,0.00024296342,0.004166094,0.0004994131,0.0001337206,0.000012248643,0.0009765768,0.0007843646,0.00019655704],"category_scores_gemma":[0.8711338,0.00013905377,0.0013900185,0.0007511728,0.0015542746,0.00022501794,0.000105079685,0.0018235047,0.000004738834],"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":[0.007841827,0.0004531882,0.9831383,0.000009023184,0.0008392791,0.000063005864,0.0018281296,0.0006471385,0.00006322321,0.0003033255,0.0003307466,0.004482777],"study_design_scores_gemma":[0.0009888879,0.00030520378,0.98840857,0.00004268665,0.00042023617,0.000024269806,0.0024514967,0.000078484,0.00008604986,0.005925576,0.0011349653,0.00013356163],"about_ca_topic_score_codex":0.004635598,"about_ca_topic_score_gemma":0.10986854,"teacher_disagreement_score":0.1321562,"about_ca_system_score_codex":0.00010122653,"about_ca_system_score_gemma":0.0029786476,"threshold_uncertainty_score":0.90637404},"labels":[],"label_agreement":null},{"id":"W2054179548","doi":"10.1016/j.jclinepi.2010.03.010","title":"Item nonresponse to psychosocial questionnaires was associated with higher mortality after acute myocardial infarction","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac Health and Mental Health","field":"Medicine","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":"Toronto Rehabilitation Institute; St. Michael's Hospital; Centre for Addiction and Mental Health; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Psychosocial; Medicine; Hazard ratio; Confidence interval; Myocardial infarction; Non-response bias; Proportional hazards model; Demography; Social support; Internal medicine; Psychiatry; Psychology","score_opus":0.1400755336054575,"score_gpt":0.5304061085881607,"score_spread":0.39033057498270324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054179548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9482469,0.00005855828,0.00021377775,0.042333044,0.008298271,0.00035552113,0.000020867787,0.000024549769,0.00044851794],"genre_scores_gemma":[0.9521161,0.00019540348,0.0017922,0.040372938,0.005276363,0.000018974526,0.0000102669155,0.00002227207,0.00019548653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99206954,0.0035204184,0.0031878476,0.00030628042,0.00037486042,0.0005410788],"domain_scores_gemma":[0.9861309,0.009274025,0.0021013524,0.0003119451,0.0005315167,0.0016502766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023719642,0.00019696917,0.0023065577,0.00014899482,0.000077171586,0.0000056142744,0.000099659104,0.00066702557,0.00014814484],"category_scores_gemma":[0.05135671,0.0001342877,0.00074311474,0.00020955394,0.00023687966,0.000094260526,0.00003093675,0.0021375176,0.000037562506],"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":[0.014694211,0.00036441715,0.96571034,0.000024555775,0.00043204377,0.00013731561,0.00006052654,0.000002253069,0.00008290896,0.00011742547,0.012678381,0.005695596],"study_design_scores_gemma":[0.0031841383,0.0036120014,0.9710668,0.00018204824,0.0003961394,0.00029420326,0.000009407483,0.000008792754,0.000004086029,0.00050754484,0.020620592,0.00011424444],"about_ca_topic_score_codex":0.00013064026,"about_ca_topic_score_gemma":0.00024083903,"teacher_disagreement_score":0.027637068,"about_ca_system_score_codex":0.0001426287,"about_ca_system_score_gemma":0.0010712371,"threshold_uncertainty_score":0.9566341},"labels":[],"label_agreement":null},{"id":"W2054473715","doi":"10.1016/j.jclinepi.2012.07.014","title":"Likelihood ratios, sensitivity, and specificity values can be back-calculated when the odds ratios are known","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Toronto; University Health Network","funders":"","keywords":"False positive paradox; False positives and false negatives; Diagnostic odds ratio; False Negative Reactions; True positive rate; Sensitivity (control systems); Statistics; Odds ratio; Medicine; Meta-analysis; Likelihood ratios in diagnostic testing; Odds; Confidence interval; Mathematics; Computer science; Artificial intelligence; Logistic regression; Pathology; Internal medicine","score_opus":0.8435677692648154,"score_gpt":0.6014811249430791,"score_spread":0.2420866443217362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054473715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8441951,0.0050241034,0.04155546,0.10342535,0.0035481274,0.00056160614,0.00002166827,0.000004506406,0.0016640746],"genre_scores_gemma":[0.97624356,0.0006993508,0.008524946,0.0099236835,0.0033519412,0.0000023448724,0.000002534974,0.00001313533,0.0012385194],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7976866,0.16588856,0.032942556,0.0006790988,0.0021967487,0.00060647825],"domain_scores_gemma":[0.6675509,0.2869398,0.03930039,0.002638703,0.002562168,0.0010080338],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6166289,0.00033280448,0.010336099,0.00018305123,0.0002101803,0.00017592766,0.0009750484,0.00038187252,0.003340902],"category_scores_gemma":[0.5794972,0.00012583252,0.0033869823,0.00039823924,0.00047888997,0.0003395913,0.00024262117,0.0010734769,0.0004658656],"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":[0.000041762964,0.00014107602,0.7562901,0.0000138348,0.00048162407,0.000010822094,0.00033697643,0.00007576148,0.000024895418,0.002278273,0.22377351,0.016531399],"study_design_scores_gemma":[0.0005230086,0.00022088937,0.7676785,0.00006916683,0.0005596485,0.00035010025,0.00073437067,0.0063890396,0.000011261292,0.025567211,0.19768691,0.00020986889],"about_ca_topic_score_codex":0.000024827941,"about_ca_topic_score_gemma":0.00017073871,"teacher_disagreement_score":0.13204844,"about_ca_system_score_codex":0.000025838926,"about_ca_system_score_gemma":0.00014156908,"threshold_uncertainty_score":0.99757016},"labels":[],"label_agreement":null},{"id":"W2054563204","doi":"10.1016/j.jclinepi.2009.11.019","title":"Response times follow lognormal or gamma distribution in arthritis patients","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","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":"Alberta Children's Hospital; University of Calgary; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Canadian Arthritis Network; Canada Research Chairs","keywords":"Etanercept; Log-normal distribution; Medicine; Rheumatoid arthritis; Methotrexate; Internal medicine; Rheumatology; Distribution (mathematics); Mathematics; Statistics","score_opus":0.10935591117550945,"score_gpt":0.4584813849379157,"score_spread":0.3491254737624062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054563204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9861846,0.0008572294,0.0003081002,0.0113266,0.0010268473,0.00015658235,0.000022056345,0.000008850881,0.000109142944],"genre_scores_gemma":[0.9845195,0.012056059,0.0017047195,0.0011566108,0.00038208123,0.0000041681515,0.000024019995,0.0000113891365,0.000141456],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99224436,0.0034972639,0.0033416012,0.00019398167,0.0002641096,0.0004586615],"domain_scores_gemma":[0.97758436,0.020227846,0.0010439693,0.0002281086,0.00039408132,0.00052163313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024274603,0.00013234341,0.0017392525,0.00014076612,0.000044706514,0.000007289009,0.00016661921,0.00037297272,0.00067144085],"category_scores_gemma":[0.2244809,0.00008530983,0.00046715865,0.00014122497,0.00041691688,0.00015651307,0.000048180795,0.0018125912,0.0000390147],"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":[0.024899587,0.0005262336,0.82746494,0.000006120838,0.000059397218,0.0003113161,0.000021760407,0.0000022401666,0.00007144397,0.0004258597,0.008930403,0.1372807],"study_design_scores_gemma":[0.009455238,0.0047309515,0.9128019,0.00024891068,0.000003979308,0.00046014177,0.000018537068,0.00011287049,0.00003437456,0.0024272508,0.06962866,0.00007717254],"about_ca_topic_score_codex":0.000022256567,"about_ca_topic_score_gemma":0.00016377118,"teacher_disagreement_score":0.2002063,"about_ca_system_score_codex":0.000025490654,"about_ca_system_score_gemma":0.00048128373,"threshold_uncertainty_score":0.8413141},"labels":[],"label_agreement":null},{"id":"W2054747465","doi":"10.1016/j.jclinepi.2006.11.003","title":"Effect sizes can be calculated for studies reporting ranges for outcome variables in systematic reviews","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":251,"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":"Outcome (game theory); Maxima and minima; Systematic review; Rheumatoid arthritis; Medicine; Replication (statistics); Range (aeronautics); Human immunodeficiency virus (HIV); Statistics; MEDLINE; Econometrics; Mathematics; Internal medicine; Family medicine; Biology","score_opus":0.9583537100903815,"score_gpt":0.7429365719750513,"score_spread":0.21541713811533025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054747465","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5566768,0.060355328,0.34667423,0.017471764,0.006702206,0.011883916,0.000017865856,0.000009423654,0.00020842711],"genre_scores_gemma":[0.81044203,0.0027150922,0.17293236,0.008542245,0.002306907,0.00046521105,0.0000066897032,0.000059848644,0.0025296488],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4164447,0.22667131,0.35101587,0.0017598743,0.0028235547,0.0012846909],"domain_scores_gemma":[0.01640563,0.80150384,0.17706913,0.0017756681,0.0029097178,0.00033602302],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9532247,0.00041460982,0.04501912,0.0005182191,0.000111737325,0.000061480656,0.0013068845,0.00039806173,0.00008050724],"category_scores_gemma":[0.9921331,0.0001595129,0.010975937,0.0006924862,0.00016114471,0.00012717006,0.00008898742,0.000551787,0.000019847226],"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":[0.000517909,0.00016041164,0.9068373,0.028179226,0.002454374,0.000057922156,0.00033583704,0.0005011347,0.000036731017,0.0027657987,0.036106773,0.022046613],"study_design_scores_gemma":[0.021314913,0.012982978,0.28376317,0.048554473,0.023481827,0.0017180457,0.005833547,0.047659006,0.00012987742,0.27335104,0.27835858,0.0028525589],"about_ca_topic_score_codex":0.000009329213,"about_ca_topic_score_gemma":0.00013651453,"teacher_disagreement_score":0.6230741,"about_ca_system_score_codex":0.00007604005,"about_ca_system_score_gemma":0.0001070918,"threshold_uncertainty_score":0.9989289},"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":"W2055655128","doi":"10.1016/j.jclinepi.2011.04.009","title":"Number needed to treat is incorrect without proper time-related considerations","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":73,"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; Centre Hospitalier de l’Université de Montréal; Hôpital Notre-Dame","funders":"Canadian Institutes of Health Research","keywords":"Number needed to treat; Medicine; Observational study; Cumulative incidence; Incidence (geometry); Randomized controlled trial; Absolute risk reduction; Relative risk; Confidence interval; Mathematics; Surgery; Cohort; Internal medicine","score_opus":0.7821762632723385,"score_gpt":0.5818846094015176,"score_spread":0.20029165387082082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055655128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6838089,0.00040984963,0.004995469,0.26742318,0.0033510712,0.0007329141,0.00007773687,0.000043309254,0.039157543],"genre_scores_gemma":[0.71522284,0.00018953442,0.05175574,0.22656086,0.0013483311,0.000027587315,0.000005541731,0.000054245967,0.00483531],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9742254,0.0045316434,0.020214604,0.00048725636,0.00007473434,0.00046636665],"domain_scores_gemma":[0.96473795,0.023004346,0.010713237,0.00052204676,0.0003232427,0.00069918495],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.10090953,0.0002264862,0.004358918,0.00027027246,0.00012891596,0.000017541674,0.00030580652,0.0005126982,0.010077301],"category_scores_gemma":[0.19474787,0.00020855197,0.0006425746,0.00016116707,0.00020676463,0.00036765082,0.00006508699,0.0007359147,0.014207227],"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":[0.0001357891,0.0002528903,0.47291127,0.000034338147,0.00021704815,0.000006431906,0.0017268107,0.00007135716,0.000001785713,0.031074682,0.49329126,0.00027632457],"study_design_scores_gemma":[0.005449142,0.0021422699,0.33267125,0.00031229347,0.00013172244,0.0006114499,0.00074421056,0.005502461,0.000026857995,0.53422284,0.11720448,0.0009810252],"about_ca_topic_score_codex":0.00069790566,"about_ca_topic_score_gemma":0.000029175435,"teacher_disagreement_score":0.50314814,"about_ca_system_score_codex":0.00017932449,"about_ca_system_score_gemma":0.00040801923,"threshold_uncertainty_score":0.9908276},"labels":[],"label_agreement":null},{"id":"W2056088427","doi":"10.1016/j.jclinepi.2008.02.012","title":"Specific HRQL instruments and symptom scores were more responsive than preference-based generic instruments in patients with GERD","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Gastroesophageal reflux and treatments","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surrey Place Centre; University of Alberta; McGill University Health Centre; McMaster University","funders":"GlaxoSmithKline; AstraZeneca","keywords":"GERD; Heartburn; Medicine; Quality of life (healthcare); Confidence interval; Reflux; Internal medicine; Physical therapy; Disease; Gastroenterology","score_opus":0.19396197035902477,"score_gpt":0.3990468238672491,"score_spread":0.20508485350822434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056088427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99831194,0.00013044891,0.0000364354,0.0006574113,0.0004026707,0.00035348654,0.000010631191,0.000009063301,0.00008789753],"genre_scores_gemma":[0.99159795,0.0005400457,0.0062084263,0.0013473512,0.00017779855,0.00000659041,0.000026037866,0.000024095401,0.00007173392],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947093,0.0013015778,0.0026773585,0.00041972124,0.00041032088,0.00048168591],"domain_scores_gemma":[0.9948843,0.0022460883,0.0017210819,0.00031898022,0.00026688486,0.00056266354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019259918,0.0003014808,0.0022222898,0.00031110388,0.000071628325,0.0000052654677,0.00016967928,0.00030623554,0.000047710302],"category_scores_gemma":[0.004067159,0.00018608381,0.0002672505,0.00018317644,0.0005331703,0.00014589293,0.00006265178,0.0008698165,0.0000125615325],"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":[0.005968051,0.0009795704,0.98024327,0.00002214428,0.00023493926,0.00062111806,0.00004272384,0.000019482648,0.0000026118046,0.000018254581,0.00023099614,0.011616852],"study_design_scores_gemma":[0.016817631,0.0073381616,0.9747957,0.00025127592,0.000090527035,0.00020644575,0.00000932589,0.000056042612,0.000019583142,0.00020227853,0.00012528268,0.00008777291],"about_ca_topic_score_codex":0.000009501178,"about_ca_topic_score_gemma":0.0000023705368,"teacher_disagreement_score":0.011529079,"about_ca_system_score_codex":0.00010640058,"about_ca_system_score_gemma":0.00039668256,"threshold_uncertainty_score":0.75882775},"labels":[],"label_agreement":null},{"id":"W2056428692","doi":"10.1016/j.jclinepi.2005.08.009","title":"Author's response to: Administrative database: validity of recording vs. validity of diagnosis","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","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","funders":"","keywords":"Scopus; Medicine; Cohort; External validity; Dominance (genetics); Asthma; Cohort study; MEDLINE; Database; Library science; Family medicine; Psychology; Computer science; Pathology; Political science; Internal medicine; Social psychology","score_opus":0.44996702460455573,"score_gpt":0.5607289063305669,"score_spread":0.1107618817260112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056428692","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9316415,0.00039867207,0.0017938705,0.06454561,0.00077222893,0.0004128252,0.00021793766,0.000010070074,0.00020728458],"genre_scores_gemma":[0.9734562,0.0006774133,0.022802904,0.001153442,0.0015345004,0.000013200758,0.000011842431,0.000027076034,0.00032342342],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9779182,0.013656487,0.0065853847,0.00052598555,0.0007101438,0.0006037912],"domain_scores_gemma":[0.8979908,0.09483946,0.0038500559,0.00080426567,0.0012327726,0.0012825963],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05485108,0.00026603512,0.0038942755,0.00034995007,0.000056186003,0.0000035483376,0.00050080084,0.00041121914,0.0010057251],"category_scores_gemma":[0.33143184,0.00020968287,0.0012627194,0.00039503767,0.00082847377,0.00020690243,0.00026764788,0.0016189421,0.000029206234],"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":[0.024474448,0.001603386,0.91303396,0.00030609983,0.00033664238,0.00022169012,0.0000682332,0.000074996395,0.000645088,0.0003965114,0.036059693,0.02277923],"study_design_scores_gemma":[0.0026289558,0.0056674974,0.95210654,0.0006448019,0.0003210817,0.0002020023,0.000115841234,0.0003893922,0.0017844245,0.0013228015,0.034659393,0.00015728021],"about_ca_topic_score_codex":0.000046573357,"about_ca_topic_score_gemma":0.000018724191,"teacher_disagreement_score":0.27658075,"about_ca_system_score_codex":0.00026747008,"about_ca_system_score_gemma":0.0019035285,"threshold_uncertainty_score":0.9999075},"labels":[],"label_agreement":null},{"id":"W2056503854","doi":"10.1016/s0895-4356(99)00181-x","title":"Dealing with missing data in observational health care outcome analyses","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Petro-Canada; Provincial Laboratory of Public Health","funders":"","keywords":"Missing data; Observational study; Decile; Statistic; Statistics; Medicine; Computer science; Data mining; Mathematics","score_opus":0.9315060521257897,"score_gpt":0.7303419664088747,"score_spread":0.20116408571691502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056503854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3793349,0.0015560227,0.58894867,0.028195664,0.00038551993,0.00016650933,0.000061650026,0.000017393133,0.0013336997],"genre_scores_gemma":[0.13234003,0.00021634572,0.8626291,0.0044745672,0.00030358875,4.6230582e-7,0.0000071976738,0.000010142788,0.00001853891],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902177,0.0037806989,0.0052561625,0.0002540734,0.00020192006,0.00028946315],"domain_scores_gemma":[0.9103528,0.086603396,0.0021603496,0.0004366428,0.0001870169,0.0002597426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02382797,0.00012409953,0.00215234,0.000066814515,0.000047708865,0.000007283078,0.00043001433,0.00013859106,0.00041153276],"category_scores_gemma":[0.14282493,0.0000774591,0.00014494553,0.00012314148,0.00015245283,0.00010109588,0.000045937682,0.0007904936,0.0000040919904],"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":[0.00026809008,0.000110383,0.6896093,0.00008386424,0.00007056744,0.000037076727,0.000072660885,0.00030058745,7.7366377e-7,0.04785325,0.00071778236,0.2608757],"study_design_scores_gemma":[0.0010672333,0.00072084635,0.6697985,0.00032027747,0.00006491462,0.00007287928,0.000111769,0.0077077425,6.1017954e-7,0.31681094,0.0031863737,0.00013791067],"about_ca_topic_score_codex":0.00007991428,"about_ca_topic_score_gemma":0.0000682733,"teacher_disagreement_score":0.27368048,"about_ca_system_score_codex":0.000035366054,"about_ca_system_score_gemma":0.0003302877,"threshold_uncertainty_score":0.86439544},"labels":[],"label_agreement":null},{"id":"W2056785271","doi":"10.1016/j.jclinepi.2013.02.004","title":"The GRADE approach is reproducible in assessing the quality of evidence of quantitative evidence syntheses","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":371,"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; Population Health Research Institute; Hospital for Sick Children; University Health Network; Toronto General Hospital; University of Calgary; Canadian Agency for Drugs and Technologies in Health; Women's College Hospital; Humber River Regional Hospital; McMaster University","funders":"","keywords":"Confidence interval; Grading (engineering); Reliability (semiconductor); Inter-rater reliability; Quality of evidence; Medicine; Psychology; Physical therapy; Rating scale; Meta-analysis; Internal medicine; Developmental psychology","score_opus":0.9898598135410488,"score_gpt":0.7755362204362136,"score_spread":0.21432359310483518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056785271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8513644,0.02968916,0.043816894,0.072981276,0.0007309259,0.00073851296,0.0000016915766,0.000001163519,0.0006760273],"genre_scores_gemma":[0.96670276,0.002973372,0.029044807,0.0008401472,0.00012482466,0.000011075776,3.5862094e-8,0.000005008621,0.00029799546],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.33021885,0.5285644,0.13177516,0.0018842072,0.0068171723,0.00074018555],"domain_scores_gemma":[0.012369537,0.9064055,0.07281304,0.0042914925,0.003960582,0.00015981616],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8482775,0.00021014104,0.010491695,0.0001909053,0.00011267704,0.0001241469,0.0037207252,0.00018974306,0.0005142106],"category_scores_gemma":[0.9797841,0.000059274487,0.0038138118,0.0011461877,0.0012042887,0.0007567784,0.00023751575,0.0009167516,0.000074841846],"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":[0.00007309088,0.0001754548,0.94510984,0.00014025254,0.00031097277,8.772283e-7,0.0005945936,0.00059382396,0.00012820821,0.008614265,0.017506728,0.02675189],"study_design_scores_gemma":[0.00009066483,0.00029881793,0.896281,0.0012082531,0.00014706384,0.000017713053,0.0032390745,0.009550549,0.000031642674,0.08779961,0.0012462612,0.00008936471],"about_ca_topic_score_codex":0.00024607024,"about_ca_topic_score_gemma":0.00002302822,"teacher_disagreement_score":0.37784111,"about_ca_system_score_codex":0.000019396464,"about_ca_system_score_gemma":0.00032492285,"threshold_uncertainty_score":0.71719134},"labels":[],"label_agreement":null},{"id":"W2056818843","doi":"10.1016/j.jclinepi.2003.10.018","title":"Health-related quality of life in women with polycystic ovary syndrome, a self-administered questionnaire, was validated","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ovarian function and disorders","field":"Medicine","cited_by":152,"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 Medical Centre; McMaster University","funders":"","keywords":"Polycystic ovary; Quality of life (healthcare); Medicine; Gynecology; Ovary; Gerontology; Family medicine; Internal medicine; Nursing","score_opus":0.14946172737446808,"score_gpt":0.44593555266482926,"score_spread":0.29647382529036115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056818843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586212,0.00085572974,0.002279851,0.03716246,0.0005836191,0.00023290089,0.0000029566386,0.000032324733,0.00022895938],"genre_scores_gemma":[0.98281395,0.0003185744,0.00548536,0.011225589,0.000088628745,0.0000041442763,0.000004315626,0.000018255512,0.000041199808],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868919,0.004037955,0.008091131,0.0002815776,0.00026412297,0.00043329247],"domain_scores_gemma":[0.98845524,0.004985387,0.005048632,0.00033751153,0.0002758238,0.00089740247],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021812228,0.00019028534,0.0039388468,0.0002928844,0.00003154084,0.0000026534485,0.00013790897,0.00041293792,0.000108749206],"category_scores_gemma":[0.04495173,0.00013313701,0.0003122478,0.00044357387,0.0002886376,0.00008803906,0.00002717059,0.0011308296,0.00001703869],"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":[0.049105782,0.0036317296,0.9383678,0.0004484371,0.0010294155,0.00035937893,0.0004736215,0.0008036485,0.000013084725,0.0023351565,0.0008015868,0.0026303963],"study_design_scores_gemma":[0.016686263,0.008987414,0.965518,0.0006464201,0.000060721723,0.0011227209,0.00018551938,0.0000448937,7.622668e-7,0.0064104986,0.00022467006,0.000112132606],"about_ca_topic_score_codex":0.00037578668,"about_ca_topic_score_gemma":0.000042618012,"teacher_disagreement_score":0.032419518,"about_ca_system_score_codex":0.00019713197,"about_ca_system_score_gemma":0.0024883728,"threshold_uncertainty_score":0.96309304},"labels":[],"label_agreement":null},{"id":"W2056886934","doi":"10.1016/j.jclinepi.2006.07.002","title":"Kaplan–Meier methods yielded misleading results in competing risk scenarios","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":155,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Canada Research Chairs; Government of Canada","keywords":"Censoring (clinical trials); Kaplan–Meier estimator; Medicine; Percutaneous coronary intervention; Event (particle physics); Survival analysis; Cumulative incidence; Statistics; Proportional hazards model; Bypass grafting; Incidence (geometry); Cardiology; Surgery; Artery; Mathematics; Myocardial infarction","score_opus":0.30664181904434257,"score_gpt":0.5753369775761458,"score_spread":0.2686951585318032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056886934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8070638,0.0012529545,0.03811089,0.13361089,0.002991738,0.0004697155,0.000017392975,0.00004467264,0.016437914],"genre_scores_gemma":[0.64766884,0.0017277551,0.32811,0.01592884,0.005604479,0.0000045430716,0.000014519196,0.000042905183,0.0008981338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9770659,0.014306501,0.0073278192,0.0003693476,0.0003147074,0.0006156923],"domain_scores_gemma":[0.9036783,0.09146555,0.0035506012,0.00039970476,0.0004718224,0.0004339953],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.099251255,0.00018055792,0.0030180202,0.00038586737,0.00006697876,0.000007810247,0.00024369825,0.00058256974,0.000097466575],"category_scores_gemma":[0.25042292,0.0001309953,0.0008530758,0.00033653612,0.00033352216,0.000084655236,0.00009658721,0.0035689948,0.000047169702],"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":[0.0048488807,0.00038870002,0.8532904,0.00003300158,0.0003176455,0.000434664,0.0000688422,0.0022428937,0.00048530655,0.00038324634,0.07663829,0.060868144],"study_design_scores_gemma":[0.007806794,0.0015821129,0.81425226,0.000298886,0.00016959375,0.0008285328,0.00013524981,0.008601539,0.0001016352,0.0047606393,0.16128801,0.00017474806],"about_ca_topic_score_codex":0.0005466992,"about_ca_topic_score_gemma":0.000027538812,"teacher_disagreement_score":0.2899991,"about_ca_system_score_codex":0.0001088443,"about_ca_system_score_gemma":0.00029387994,"threshold_uncertainty_score":0.9987298},"labels":[],"label_agreement":null},{"id":"W2057411434","doi":"10.1016/j.jclinepi.2006.06.019","title":"Response to Carter et al.: a survey identified publication bias in the secondary literature","year":2006,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","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":"MEDLINE; Library science; Psychology; Medicine; Political science; Computer science; Law","score_opus":0.6876963642999342,"score_gpt":0.6721402714352223,"score_spread":0.015556092864711935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057411434","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":[0.064454414,0.00033939412,0.00027058975,0.9273695,0.006031614,0.0007856554,0.00011793031,0.000007274063,0.0006236794],"genre_scores_gemma":[0.0035888546,0.0003190028,0.00061356893,0.985645,0.0050924863,0.00008573268,0.00043442054,0.000022362961,0.004198592],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7132323,0.27232,0.011291056,0.0006857839,0.00094664446,0.001524264],"domain_scores_gemma":[0.6464993,0.34441563,0.0056107254,0.000867914,0.0021177756,0.0004886504],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.43460694,0.00025549997,0.002186688,0.00090951315,0.00027379248,0.000055773515,0.0013957272,0.00200954,0.000367378],"category_scores_gemma":[0.44498816,0.0001454077,0.0004547615,0.0011036122,0.00021866089,0.0003130189,0.000120260265,0.020938102,0.00039800498],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006200363,0.000058349808,0.12231442,0.00007854527,0.000013673105,0.000058445294,0.00078371423,0.0000024915576,7.4471853e-7,0.000020352598,0.8751694,0.0008798431],"study_design_scores_gemma":[0.00029979114,0.0002691583,0.4744734,0.00024317934,0.0000035238086,0.000013022973,0.000057914203,0.000010881833,1.1193705e-8,0.0010015523,0.52356523,0.000062341795],"about_ca_topic_score_codex":0.0011565696,"about_ca_topic_score_gemma":0.0015910319,"teacher_disagreement_score":0.35215896,"about_ca_system_score_codex":0.00022168884,"about_ca_system_score_gemma":0.0072938986,"threshold_uncertainty_score":0.99928606},"labels":[],"label_agreement":null},{"id":"W2058306321","doi":"10.1016/s0895-4356(00)00255-9","title":"Rasch analysis of the hierarchical assessment of balance and mobility (HABAM)","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Dalhousie University","keywords":"Rasch model; Balance (ability); Hierarchy; Level of measurement; Scale (ratio); Ordinal Scale; Construct (python library); Interval (graph theory); Multilevel model; Statistics; Psychology; Computer science; Medicine; Physical medicine and rehabilitation; Mathematics; Geography; Cartography","score_opus":0.17232872414700878,"score_gpt":0.5657454064307783,"score_spread":0.3934166822837695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058306321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991645,0.00033160707,0.001082788,0.0041570086,0.00053819834,0.00018178094,0.00002100561,0.0000035415374,0.0020390656],"genre_scores_gemma":[0.9921511,0.0025649003,0.0032326146,0.0015108831,0.0002784771,0.0000039225033,0.0000027998435,0.0000051496822,0.00025018398],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.979716,0.013889698,0.0056852275,0.00021472631,0.00021260371,0.00028172458],"domain_scores_gemma":[0.96731913,0.02802051,0.0038293616,0.00040157637,0.00025635102,0.00017306843],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032806113,0.00010783787,0.0026048895,0.00009033436,0.00010422816,7.583937e-7,0.0003172169,0.00042634315,0.00027009746],"category_scores_gemma":[0.012773523,0.00006163189,0.0009678033,0.00034077335,0.0005456897,0.000058273876,0.000083161416,0.0017345564,0.000002433719],"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":[0.0002119134,0.0005764833,0.98766154,0.00007440841,0.0005547411,7.543979e-7,0.000053575422,0.000049290935,0.00009155753,0.0022582624,0.00087569025,0.007591764],"study_design_scores_gemma":[0.0010962094,0.00029024857,0.980104,0.00012302442,0.0004967005,0.0000024876013,0.00004177711,0.005067751,2.6916993e-7,0.010651766,0.0020798936,0.0000458335],"about_ca_topic_score_codex":0.00006298151,"about_ca_topic_score_gemma":0.00005454608,"teacher_disagreement_score":0.020032588,"about_ca_system_score_codex":0.000028241822,"about_ca_system_score_gemma":0.00032768547,"threshold_uncertainty_score":0.99592966},"labels":[],"label_agreement":null},{"id":"W2058316829","doi":"10.1016/j.jclinepi.2007.02.002","title":"Parents were accurate proxy reporters of urgent pediatric asthma health services—a retrospective agreement analysis","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":29,"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; Health Sciences Centre; SickKids Foundation; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Proxy (statistics); Asthma; Kappa; Cohen's kappa; Family medicine; Emergency department; Pediatrics; Respondent; Retrospective cohort study; Psychiatry","score_opus":0.4450704169215611,"score_gpt":0.6040991885010063,"score_spread":0.15902877157944523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058316829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97536063,0.00085763837,0.015160353,0.0054728943,0.0025164383,0.00020320644,0.000008698655,0.000009841567,0.00041031226],"genre_scores_gemma":[0.98470914,0.0030434537,0.008441095,0.002456718,0.0012150025,0.0000013997653,0.0000043007967,0.000007029142,0.00012188089],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8615647,0.12230476,0.013409416,0.0006659724,0.00089361524,0.0011615439],"domain_scores_gemma":[0.87336224,0.10918232,0.015244069,0.0003873069,0.0008500454,0.0009740193],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52667314,0.0001661072,0.0032107234,0.00047666088,0.0002005596,0.0000049269056,0.0004888025,0.00048470235,0.00030471987],"category_scores_gemma":[0.21798542,0.0001288096,0.0012972435,0.0010453522,0.00042657854,0.00013360649,0.00007111833,0.00090612203,0.000008021085],"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":[0.003533445,0.0002630613,0.9903574,0.000022024671,0.0007415584,0.000054337426,0.0011422551,0.00008956588,0.0000011007872,0.00043517453,0.00037189605,0.0029881566],"study_design_scores_gemma":[0.0005481048,0.00087706564,0.99207836,0.00002321028,0.0002746794,0.000010007048,0.0015182979,0.000037625818,0.0000026247883,0.0021529875,0.0023808903,0.000096136544],"about_ca_topic_score_codex":0.00110282,"about_ca_topic_score_gemma":0.0021049357,"teacher_disagreement_score":0.30868772,"about_ca_system_score_codex":0.00016324135,"about_ca_system_score_gemma":0.0011718293,"threshold_uncertainty_score":0.7886018},"labels":[],"label_agreement":null},{"id":"W2059187041","doi":"10.1016/j.jclinepi.2009.08.008","title":"Correspondence analysis is a useful tool to uncover the relationships among categorical variables","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":427,"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; McGill University Health Centre; McGill University; Jewish General Hospital","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Categorical variable; Contingency table; Correspondence analysis; Multivariate statistics; Multiple correspondence analysis; Pairwise comparison; Context (archaeology); Representation (politics); Variable (mathematics); Multivariate analysis; Statistics; Computer science; Variables; Mathematics; Geography","score_opus":0.37588324888730607,"score_gpt":0.47303940398440114,"score_spread":0.09715615509709508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059187041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93091726,0.00010559807,0.037212484,0.031030435,0.00030757015,0.000089640766,0.0000128445445,0.0000096184,0.0003145638],"genre_scores_gemma":[0.9754499,0.00009095102,0.009575416,0.01362173,0.00078839296,0.0000014631635,0.0000036710783,7.188307e-7,0.00046770807],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863475,0.009410013,0.0032334444,0.00034778318,0.00030414507,0.00035710994],"domain_scores_gemma":[0.90906733,0.08874676,0.0013749091,0.00015375792,0.00030226557,0.0003549893],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032251388,0.00016535693,0.0017866446,0.00005517627,0.00023893623,0.000033492863,0.0005759427,0.00032206648,0.0011627291],"category_scores_gemma":[0.12400183,0.000048781083,0.0011867027,0.0014699767,0.00018619357,0.00011258826,0.00004621689,0.0010167024,0.000050309485],"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":[0.00030853678,0.00015669363,0.90228534,6.885975e-7,0.00037293235,0.000025117362,0.00004378054,0.0014663803,0.000106825166,0.011748715,0.013606585,0.06987844],"study_design_scores_gemma":[0.000095611824,0.0007145445,0.92349464,0.0000067672518,0.0005264649,0.000014669577,0.00005585193,0.0028196222,0.0000044286676,0.053805538,0.0183492,0.00011266948],"about_ca_topic_score_codex":0.000073499825,"about_ca_topic_score_gemma":0.00010250485,"teacher_disagreement_score":0.09175044,"about_ca_system_score_codex":0.000023214883,"about_ca_system_score_gemma":0.000030096291,"threshold_uncertainty_score":0.9997503},"labels":[],"label_agreement":null},{"id":"W2059426017","doi":"10.1016/j.jclinepi.2007.07.003","title":"The Short-Form Chronic Respiratory Disease Questionnaire was a Valid, Reliable, and Responsive Quality-of-Life Instrument in Acute Exacerbations of Chronic Obstructive Pulmonary Disease","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","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 Alberta; University of Ottawa","funders":"","keywords":"Medicine; Cronbach's alpha; Exacerbation; Quality of life (healthcare); COPD; Physical therapy; Construct validity; Cohort study; Confidence interval; Cohort; Prospective cohort study; Internal medicine; Respiratory disease; Psychometrics; Clinical psychology; Lung","score_opus":0.18138952293254035,"score_gpt":0.4677070652671745,"score_spread":0.28631754233463413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059426017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95596564,0.033600602,0.00017410406,0.00877712,0.0005022402,0.000803615,0.00008259811,0.000011989338,0.00008209026],"genre_scores_gemma":[0.98214287,0.015980754,0.00037850713,0.0005147181,0.00072579214,0.000048912912,0.000014852663,0.000037071586,0.00015651212],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9867588,0.0047634393,0.0063902573,0.0005900123,0.0008083849,0.00068909896],"domain_scores_gemma":[0.97969735,0.013929868,0.0027054418,0.0009220457,0.0010475382,0.0016977384],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.011342228,0.00034745972,0.0026424334,0.00040421047,0.00023302776,0.000005363584,0.0004425952,0.00031124565,0.000052584266],"category_scores_gemma":[0.061790906,0.00024486033,0.0008976886,0.000497426,0.0034122088,0.00029952388,0.0002986727,0.0016629174,0.0000041659364],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015658872,0.0007821093,0.95923847,0.00069562986,0.0004785855,0.000684129,0.00007231448,0.00058739044,0.00007664284,0.0035504063,0.00047921544,0.017696207],"study_design_scores_gemma":[0.0030950059,0.001096315,0.98155993,0.00080852024,0.00031294543,0.000121327445,0.00011514554,0.0024458517,0.000010098648,0.008228907,0.0020159942,0.00018993152],"about_ca_topic_score_codex":0.00007511141,"about_ca_topic_score_gemma":0.00005167233,"teacher_disagreement_score":0.05044868,"about_ca_system_score_codex":0.0010065245,"about_ca_system_score_gemma":0.009660773,"threshold_uncertainty_score":0.99929994},"labels":[],"label_agreement":null},{"id":"W2059459105","doi":"10.1016/j.jclinepi.2011.04.015","title":"Specific instructions for estimating unclearly reported blinding status in randomized trials were reliable and valid","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":179,"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 Sherbrooke; Institute for Work & Health; McMaster University","funders":"Canadian Institutes of Health Research; National Natural Science Foundation of China; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Blinding; Randomized controlled trial; Medicine; Reliability (semiconductor); Clinical trial; Randomization; MEDLINE; Research design; Statistics; Surgery; Internal medicine","score_opus":0.9688858210123364,"score_gpt":0.6955036562161118,"score_spread":0.2733821647962247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059459105","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5339977,0.0024822068,0.45109773,0.0023179029,0.0057765064,0.0015613638,0.000008281038,0.000004428156,0.0027538748],"genre_scores_gemma":[0.22922689,0.0010011983,0.7681239,0.00040103873,0.00073964184,0.000021153348,0.0000016328622,0.000013261903,0.0004712354],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5301411,0.24730743,0.21745051,0.0016521614,0.0025043369,0.0009444276],"domain_scores_gemma":[0.07435179,0.78675044,0.13361692,0.0020302352,0.002567989,0.0006826458],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8830355,0.0002358276,0.029440923,0.000657531,0.000103713384,0.00010502184,0.00066052756,0.00032852017,0.0017909062],"category_scores_gemma":[0.95199627,0.00010428446,0.0065518357,0.00054711377,0.00029942498,0.00029330511,0.00007657856,0.000702327,0.00004214969],"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":[0.020023216,0.00027640822,0.7202071,0.000077329016,0.0020371273,0.000049876195,0.0006594691,0.0008362898,0.0000129664395,0.026356192,0.05280759,0.17665644],"study_design_scores_gemma":[0.08428875,0.00077445444,0.075172536,0.00043398104,0.0017811554,0.00043127444,0.0010116813,0.058386344,0.0000050645276,0.73273283,0.04463039,0.00035155658],"about_ca_topic_score_codex":0.000038769973,"about_ca_topic_score_gemma":0.0000116256915,"teacher_disagreement_score":0.7063766,"about_ca_system_score_codex":0.000033493307,"about_ca_system_score_gemma":0.00020016063,"threshold_uncertainty_score":0.9991216},"labels":[],"label_agreement":null},{"id":"W2059624136","doi":"10.1016/j.jclinepi.2006.06.005","title":"How to do clinical practice research: a new book and a new series in the Journal of Clinical Epidemiology","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","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 Ottawa; McMaster University","funders":"","keywords":"Epidemiology; Clinical epidemiology; Series (stratigraphy); Medicine; Clinical Practice; MEDLINE; Family medicine; Pathology; Biology","score_opus":0.662527234375773,"score_gpt":0.637969245768441,"score_spread":0.024557988607331938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059624136","genre_codex":"commentary","genre_gemma":"empirical","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":[0.16278371,0.023391297,0.007887667,0.7972665,0.0030328953,0.0008675118,0.0000039319116,0.000015091569,0.004751387],"genre_scores_gemma":[0.42083955,0.11363076,0.18688147,0.19242078,0.074539624,0.000013737233,0.00001276466,0.00016172118,0.011499601],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8967377,0.07397656,0.025543015,0.00090614543,0.0012778937,0.0015586735],"domain_scores_gemma":[0.38481146,0.5899437,0.017832765,0.0017148905,0.0023467974,0.003350361],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31070587,0.00036820743,0.0067470507,0.00053425354,0.00009238225,0.00005024853,0.0010034431,0.0009370446,0.00014576846],"category_scores_gemma":[0.70389456,0.00021942459,0.0015637727,0.00055029744,0.0018429168,0.00073622755,0.0003690105,0.006429217,0.000026344078],"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":[0.0103348205,0.000923934,0.31467536,0.000064837084,0.00041281746,0.0009240318,0.000092995724,0.000073278075,0.0000010822614,0.016041402,0.6184125,0.03804291],"study_design_scores_gemma":[0.0053692157,0.008265765,0.4395429,0.00031860103,0.00044611082,0.001989673,0.0010143712,0.000037193568,2.0893674e-7,0.046743926,0.4961554,0.000116641095],"about_ca_topic_score_codex":0.00030869912,"about_ca_topic_score_gemma":0.00015780223,"teacher_disagreement_score":0.6048457,"about_ca_system_score_codex":0.000095148214,"about_ca_system_score_gemma":0.00403345,"threshold_uncertainty_score":0.995863},"labels":[],"label_agreement":null},{"id":"W2059829654","doi":"10.1016/j.jclinepi.2011.08.013","title":"Qualitative research—specialized or fragmented?","year":2012,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Ophthalmology and Visual Health Research","field":"Medicine","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 Toronto; St. Michael's Hospital","funders":"","keywords":"Qualitative research; Health care; Public relations; Nursing research; Medical education; Psychology; Sociology; Medicine; Engineering ethics; Social science; Nursing; Political science","score_opus":0.9197937217570636,"score_gpt":0.7996099999624834,"score_spread":0.12018372179458026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059829654","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":[0.012978162,0.004018035,0.00016845546,0.97247607,0.0053776777,0.0006799084,0.00002613688,0.000014838237,0.0042607235],"genre_scores_gemma":[0.0035750873,0.0065406524,0.0057949126,0.868417,0.0901047,0.000027663322,0.0000789547,0.00009905945,0.025361948],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8867309,0.098508134,0.010566344,0.0006240771,0.0014210799,0.0021494774],"domain_scores_gemma":[0.6074716,0.38100532,0.0059669507,0.0008793809,0.0031990914,0.0014776814],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.23275076,0.00041044434,0.008322872,0.00092374516,0.00018961637,0.0000071812638,0.0007013441,0.0060237776,0.005985874],"category_scores_gemma":[0.38754582,0.00023976076,0.001718559,0.0004707269,0.002468063,0.00011528389,0.0002412634,0.035193425,0.00083723397],"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":[0.010501846,0.00059050857,0.014762662,0.0008728501,0.0007755263,0.0052590203,0.00037074077,9.293804e-8,9.050417e-7,0.00042553144,0.96213764,0.004302693],"study_design_scores_gemma":[0.003572779,0.012641638,0.015970076,0.0008976987,0.00022202078,0.0033626235,0.0003229095,0.000006929132,0.0000013259381,0.010457099,0.9523596,0.0001852998],"about_ca_topic_score_codex":0.00006068551,"about_ca_topic_score_gemma":0.0000029397286,"teacher_disagreement_score":0.28249717,"about_ca_system_score_codex":0.00026760245,"about_ca_system_score_gemma":0.003725233,"threshold_uncertainty_score":0.99994075},"labels":[],"label_agreement":null},{"id":"W206017025","doi":"10.1016/s0895-4356(01)00363-8","title":"Modelling time-dependent hazard ratios in relative survival","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal General Hospital; McGill University","funders":"Canadian Institutes of Health Research; Ligue Contre le Cancer","keywords":"Proportional hazards model; Relative survival; Hazard ratio; Hazard; Survival analysis; Population; Cancer survival; Statistics; Medicine; Oncology; Econometrics; Internal medicine; Mathematics; Cancer; Cancer registry; Confidence interval; Biology; Environmental health","score_opus":0.27578473195520475,"score_gpt":0.4746208555862743,"score_spread":0.19883612363106956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W206017025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7975105,0.00048045284,0.19093241,0.006492434,0.0010175976,0.00010923918,5.7135566e-7,0.00001516256,0.003441623],"genre_scores_gemma":[0.9891877,0.00083474355,0.0068452344,0.0009798049,0.0012731757,0.0000019716153,0.000001205144,0.00001197757,0.00086417556],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941734,0.0021579883,0.0030208703,0.00020670699,0.00019696938,0.00024408444],"domain_scores_gemma":[0.9864145,0.01166999,0.0013035106,0.00014856434,0.00022683243,0.00023663598],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017414963,0.00011225386,0.0017350069,0.00015893277,0.000028044804,0.0000028761624,0.000085037056,0.000321371,0.00012625038],"category_scores_gemma":[0.023143344,0.00008389688,0.00045115143,0.00016571552,0.000092676935,0.00011402856,0.000025872221,0.0013665243,0.000045340264],"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":[0.025301663,0.00033098177,0.82550186,0.000015777612,0.00022190952,0.0004403097,0.00010278155,0.11596027,0.000046243487,0.00041948902,0.00092951173,0.030729182],"study_design_scores_gemma":[0.011532671,0.018900745,0.3346294,0.0005316423,0.00029596538,0.00229276,0.00013274899,0.5917973,0.000046731646,0.027373303,0.012128132,0.00033860005],"about_ca_topic_score_codex":0.00006696751,"about_ca_topic_score_gemma":0.00004632665,"teacher_disagreement_score":0.4908725,"about_ca_system_score_codex":0.0000888333,"about_ca_system_score_gemma":0.00020994595,"threshold_uncertainty_score":0.9850851},"labels":[],"label_agreement":null},{"id":"W2060344068","doi":"10.1016/j.jclinepi.2005.02.002","title":"Measures of adherence based on self-report exhibited poor agreement with those based on pharmacy records","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medication Adherence and Compliance","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Louis-H Lafontaine; Health and Social Services Centre University Institute of Geriatrics of Sherbrooke; Université Laval; Hôpital du Saint-Sacrement","funders":"Réseau québécois de recherche sur le vieillissement","keywords":"Pharmacy; Medicine; Kappa; Medical prescription; Cohen's kappa; Drug; Family medicine; Medical record; Internal medicine; Psychiatry; Pharmacology","score_opus":0.40262666256081153,"score_gpt":0.5240210512172849,"score_spread":0.1213943886564734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060344068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8002419,0.00046703007,0.05036531,0.12160299,0.0015409468,0.001047296,0.000009268586,0.00006936308,0.024655929],"genre_scores_gemma":[0.92201227,0.00025962482,0.035657458,0.04057564,0.0008907711,0.0000138275645,0.0000068299887,0.000014832045,0.00056873524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99274206,0.0018269303,0.004083188,0.00035180207,0.0006897401,0.00030626077],"domain_scores_gemma":[0.98401195,0.009948079,0.004241839,0.00052158185,0.0007327029,0.00054386386],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0151959015,0.00021517018,0.0019220827,0.00017827474,0.000034231703,0.0000023494058,0.00026490403,0.00017368705,0.0013329252],"category_scores_gemma":[0.026249921,0.00013194524,0.0004574266,0.00021044782,0.00021596668,0.00005363038,0.000013142605,0.0010520204,0.00012632678],"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":[0.012427325,0.004007868,0.82005346,0.00012526776,0.0003217477,0.0004072384,0.000020640206,0.0029396766,0.00021016606,0.00016333035,0.048734795,0.11058847],"study_design_scores_gemma":[0.03131593,0.034013435,0.56720024,0.0049150563,0.0009080536,0.0006571784,0.000061482984,0.13392301,0.0020099282,0.0005311789,0.22393486,0.0005296212],"about_ca_topic_score_codex":0.000026386168,"about_ca_topic_score_gemma":0.0000075451258,"teacher_disagreement_score":0.2528532,"about_ca_system_score_codex":0.000067234505,"about_ca_system_score_gemma":0.0013567802,"threshold_uncertainty_score":0.99957997},"labels":[],"label_agreement":null},{"id":"W2060515758","doi":"10.1016/j.jclinepi.2014.09.024","title":"A systematic review highlights a knowledge gap regarding the effectiveness of health-related training programs in journalology","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Academic Writing and Publishing","field":"Arts and Humanities","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":"Université de Montréal; Hôpital Notre-Dame; St. Paul's Hospital; University of Ottawa; Royal College of Physicians and Surgeons of Canada; Royal Ottawa Mental Health Centre; Ottawa Hospital","funders":"Canadian Institutes of Health Research; University of Ottawa","keywords":"PsycINFO; MEDLINE; Medical education; Cochrane Library; Peer review; Medicine; Quality (philosophy); Checklist; Alternative medicine; Psychology","score_opus":0.5509199672726365,"score_gpt":0.5119151834815855,"score_spread":0.03900478379105099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060515758","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":[0.0000220636,0.9909923,0.00009133094,0.002416722,0.0028249973,0.0015234964,0.000003727947,0.000017744207,0.0021076102],"genre_scores_gemma":[0.0008423562,0.99630237,0.00007295086,0.00058545376,0.0019129328,0.00006903932,0.000011707419,0.000052884054,0.00015032945],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.81051266,0.1586537,0.029217858,0.00048240394,0.00031605863,0.00081733824],"domain_scores_gemma":[0.7679175,0.1975739,0.03319682,0.0004940808,0.0005662264,0.00025143276],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37550324,0.00053619116,0.028784579,0.0004369896,0.00020490115,0.000042971762,0.0014451325,0.0009806199,0.000043379092],"category_scores_gemma":[0.20125265,0.00026025245,0.003920346,0.00024742127,0.0008194168,0.00019402806,0.0001329844,0.005979592,0.000017432676],"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":[0.00002621526,0.00010318294,0.000031325137,0.7960171,0.000838393,0.000016280319,0.001446711,0.0000013029392,1.4711127e-9,0.08581017,0.0014273626,0.11428195],"study_design_scores_gemma":[0.00034193025,0.00039741097,0.00000670996,0.61171484,0.0011933567,0.0006002384,0.00021363856,0.000007846628,5.604367e-10,0.004917132,0.3804592,0.0001477242],"about_ca_topic_score_codex":0.000052165717,"about_ca_topic_score_gemma":0.000039132654,"teacher_disagreement_score":0.37903184,"about_ca_system_score_codex":0.00015093315,"about_ca_system_score_gemma":0.001216039,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W2060947741","doi":"10.1016/j.jclinepi.2012.11.008","title":"Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":348,"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 Health Network; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Logistic regression; Random forest; Support vector machine; Decision tree; Artificial intelligence; Machine learning; Regression; Medicine; Computer science; Statistics; Mathematics","score_opus":0.8274950577973865,"score_gpt":0.6728096974974961,"score_spread":0.15468536029989044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060947741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95494735,0.0023152402,0.029409992,0.011401716,0.0007875375,0.0010402802,0.00008118188,0.000013642148,0.0000030664662],"genre_scores_gemma":[0.8827702,0.00026045833,0.11491887,0.0007234529,0.0012277522,0.00003752738,0.00003433033,0.000018605935,0.000008839573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97471017,0.020070402,0.004351797,0.00043966118,0.00013758506,0.00029038143],"domain_scores_gemma":[0.8856088,0.1092234,0.0035557647,0.00048752007,0.0008116825,0.00031281065],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033795744,0.00016171744,0.001191244,0.00008833367,0.0006663717,0.000017869697,0.00025405828,0.0003994786,0.000033027623],"category_scores_gemma":[0.100543626,0.00010284145,0.000097983124,0.0001558004,0.00027676704,0.00038619028,0.00018815247,0.0016001012,0.000001037988],"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":[0.00022044421,0.00006230494,0.9693587,0.000092761744,0.000071448296,0.0000075424155,0.0027928718,0.0000301782,0.00011172819,0.000113961505,0.0007768367,0.02636125],"study_design_scores_gemma":[0.00036937074,0.00057272636,0.6709871,0.00037906202,0.0001903772,0.00007210223,0.036116,0.287863,6.389181e-7,0.0018640874,0.0015121886,0.00007329763],"about_ca_topic_score_codex":0.000930467,"about_ca_topic_score_gemma":0.00042168878,"teacher_disagreement_score":0.29837152,"about_ca_system_score_codex":0.000033529337,"about_ca_system_score_gemma":0.00032204558,"threshold_uncertainty_score":0.9949106},"labels":[],"label_agreement":null},{"id":"W2061036287","doi":"10.1016/s0895-4356(99)00120-1","title":"Use of grade membership analysis to profile the practice styles of individual physicians in the management of acute low back pain","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","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":"Institute for Work & Health; Occupational Cancer Research Centre","funders":"","keywords":"Watchful waiting; Guideline; Medicine; Management styles; Intervention (counseling); Family medicine; Nursing; Management","score_opus":0.17055913977803755,"score_gpt":0.4803984197981476,"score_spread":0.3098392800201101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061036287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95466703,0.00010747382,0.0007602089,0.04327323,0.00006337652,0.0004949144,0.000013264569,0.0000017316491,0.0006187595],"genre_scores_gemma":[0.971906,0.0006683607,0.02013681,0.006988805,0.00013422403,0.0000058095957,0.00000836036,0.000006863487,0.00014476593],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9840922,0.011500952,0.0036234178,0.00016798044,0.0004210335,0.00019442836],"domain_scores_gemma":[0.9485813,0.04844343,0.0022963325,0.0003871308,0.00021657946,0.00007524239],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048150856,0.000109663815,0.0016551665,0.00016116323,0.000016351541,0.0000023931698,0.0003082773,0.0001468889,0.00018728393],"category_scores_gemma":[0.017719772,0.000053023534,0.0009573457,0.00070367276,0.00036740385,0.000088382716,0.000030335237,0.00054769136,0.000004097838],"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":[0.009324436,0.009321529,0.61507577,0.0031279763,0.036240593,0.00007053681,0.0070258887,0.015043362,0.00043577855,0.007591207,0.025651451,0.2710915],"study_design_scores_gemma":[0.00095519697,0.0023243516,0.98794395,0.0004117453,0.0026293884,0.000005804951,0.0021831295,0.00077548233,0.000021122542,0.0006813067,0.0020122018,0.00005634754],"about_ca_topic_score_codex":0.00005441343,"about_ca_topic_score_gemma":0.000016988011,"teacher_disagreement_score":0.37286815,"about_ca_system_score_codex":0.000013705868,"about_ca_system_score_gemma":0.00005096149,"threshold_uncertainty_score":0.9905544},"labels":[],"label_agreement":null},{"id":"W2061086447","doi":"10.1016/j.jclinepi.2012.05.003","title":"The quality, breadth, and timeliness of content updating vary substantially for 10 online medical texts: an analytic survey","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","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":"Hamilton Health Sciences; McMaster University","funders":"","keywords":"Quality (philosophy); Sample (material); Scale (ratio); Point (geometry); Medicine; Resource (disambiguation); Computer science; Information retrieval; Statistics; Family medicine; Mathematics; Geography","score_opus":0.7396932344573217,"score_gpt":0.7014701190923505,"score_spread":0.03822311536497125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061086447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96551585,0.0007455661,0.01973257,0.011072868,0.002190645,0.00042911086,0.00013553847,0.000009715982,0.00016813305],"genre_scores_gemma":[0.9720433,0.0011406501,0.007921689,0.016307766,0.0023309132,0.0000078402845,0.000094688985,0.000013708071,0.00013945973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94556516,0.032925338,0.02016145,0.00019532406,0.00041353784,0.00073918904],"domain_scores_gemma":[0.6975791,0.28287995,0.014803345,0.00051785365,0.0029641157,0.0012556419],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31581122,0.00014443266,0.0021168122,0.00007086572,0.00037365322,0.000004806819,0.0004550111,0.00059959275,0.0003862151],"category_scores_gemma":[0.42057818,0.00007729199,0.00028539408,0.0001349761,0.00046817446,0.000635237,0.00012855342,0.0015738151,0.000008414331],"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":[0.001507902,0.00029805198,0.9498582,0.00026335436,0.00006600721,2.540188e-7,0.00022983395,0.0000026635025,0.0000010791879,0.002665472,0.003586388,0.041520778],"study_design_scores_gemma":[0.0018140257,0.00043678543,0.97357064,0.00019183684,0.000032275566,0.000008874975,0.00065848324,0.0063819415,4.0070745e-7,0.001700758,0.01512553,0.00007841473],"about_ca_topic_score_codex":0.0002588141,"about_ca_topic_score_gemma":0.00084965816,"teacher_disagreement_score":0.2499546,"about_ca_system_score_codex":0.000037702666,"about_ca_system_score_gemma":0.0011991074,"threshold_uncertainty_score":0.7045163},"labels":[],"label_agreement":null},{"id":"W2061211489","doi":"10.1016/j.jclinepi.2014.11.023","title":"Grading the strength of a body of evidence when assessing health care interventions: an EPC update","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":281,"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; Ottawa Hospital","funders":"Agency for Healthcare Research and Quality","keywords":"Grading (engineering); Observational study; Psychological intervention; CLARITY; Systematic review; Medicine; Health care; Concordance; Randomized controlled trial; Evidence-based medicine; MEDLINE; Medical physics; Family medicine; Applied psychology; Psychology; Nursing; Alternative medicine; Surgery","score_opus":0.9698907698676973,"score_gpt":0.7549767541571039,"score_spread":0.21491401571059343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061211489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5381584,0.015867528,0.41087514,0.03277998,0.0016567406,0.0003781682,0.00000789815,0.0000023711855,0.0002737703],"genre_scores_gemma":[0.95471615,0.0006530589,0.042685483,0.0015914458,0.0002854041,0.0000016712231,8.6631144e-7,0.000005961099,0.000059954087],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6044392,0.3029099,0.08835826,0.0008345753,0.003001206,0.00045685217],"domain_scores_gemma":[0.46486843,0.3918703,0.13424453,0.004029708,0.0044280994,0.0005589596],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6779526,0.00018011422,0.010887037,0.00027580714,0.00009899276,0.00007226065,0.002465476,0.0001476787,0.00087450986],"category_scores_gemma":[0.7539817,0.000063618485,0.005970236,0.00039931026,0.0003326679,0.00044976908,0.00015061685,0.0006630664,0.000030242983],"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":[0.000060210667,0.00024406686,0.63521713,0.00044420673,0.00057602755,0.0000020910484,0.00073159405,0.00033884647,0.000012623755,0.014180174,0.029579073,0.31861398],"study_design_scores_gemma":[0.0009286243,0.0037383146,0.73584384,0.0049500954,0.0011447944,0.000088938774,0.0047598705,0.02771321,0.000012177797,0.17237869,0.04817979,0.0002616333],"about_ca_topic_score_codex":0.00003388161,"about_ca_topic_score_gemma":0.000047008118,"teacher_disagreement_score":0.41655773,"about_ca_system_score_codex":0.000023409013,"about_ca_system_score_gemma":0.0002768128,"threshold_uncertainty_score":0.957527},"labels":[],"label_agreement":null},{"id":"W2061338750","doi":"10.1016/s0895-4356(03)00211-7","title":"Delphi as a method to establish consensus for diagnostic criteria","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Peripheral Nerve Disorders","field":"Medicine","cited_by":480,"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 Western Hospital","funders":"Physicians' Services Incorporated Foundation","keywords":"Cronbach's alpha; Delphi method; Delphi; Medicine; Outlier; Statistic; Cohen's kappa; Statistics; Medical physics; Family medicine; Psychology; Psychometrics; Computer science; Clinical psychology; Mathematics","score_opus":0.32499638957750787,"score_gpt":0.59748467635958,"score_spread":0.27248828678207215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061338750","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":[0.7506858,0.0015154169,0.15002598,0.09147478,0.0029560118,0.00085092906,0.000016287873,0.00002591147,0.0024488668],"genre_scores_gemma":[0.2988205,0.00032695284,0.62069875,0.078557536,0.0011029752,0.00002789263,0.0000042948564,0.000042994045,0.00041809262],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900392,0.0047263056,0.004234813,0.00032835474,0.00016032105,0.0005109938],"domain_scores_gemma":[0.73469764,0.2586301,0.002832132,0.0006085795,0.0014815428,0.001750036],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031096442,0.00019414705,0.0028966162,0.00013978443,0.000042918407,0.000006733508,0.00017851232,0.00038678548,0.0004439458],"category_scores_gemma":[0.71819544,0.00014383406,0.0009981861,0.00017157457,0.00017101111,0.000043121556,0.000027368364,0.0007034388,0.000036817073],"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":[0.008861707,0.0015616085,0.28222796,0.00024386462,0.0010968172,0.0006899126,0.00020418344,0.00043018983,0.0012794884,0.023181913,0.5640229,0.116199456],"study_design_scores_gemma":[0.010479647,0.011599037,0.2093904,0.0003197471,0.000608197,0.0029932768,0.00030106978,0.00046446247,0.00013193217,0.078936316,0.68443465,0.00034123656],"about_ca_topic_score_codex":0.000028545064,"about_ca_topic_score_gemma":0.000010728986,"teacher_disagreement_score":0.687099,"about_ca_system_score_codex":0.000042065407,"about_ca_system_score_gemma":0.0005369066,"threshold_uncertainty_score":0.9976901},"labels":[],"label_agreement":null},{"id":"W2061912725","doi":"10.1016/j.jclinepi.2013.06.005","title":"Synthesizing evidence on complex interventions: how meta-analytical, qualitative, and mixed-method approaches can contribute","year":2013,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":294,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Psychological intervention; Relevance (law); Systematic review; Thematic analysis; Management science; Narrative; Qualitative research; Computer science; Variety (cybernetics); MEDLINE; Psychology; Data science; Sociology; Social science; Artificial intelligence; Political science; Engineering","score_opus":0.9873906499660094,"score_gpt":0.810709071503336,"score_spread":0.1766815784626734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061912725","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0009267074,0.0008286689,0.048361555,0.946659,0.0017128907,0.0010728893,0.00026191148,0.000021918644,0.00015442485],"genre_scores_gemma":[0.0035349801,0.0010326679,0.06361582,0.9243336,0.0051971646,0.00019552602,0.00002257665,0.000051912,0.0020158105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.78995645,0.19204076,0.014810437,0.0008975715,0.00081762165,0.0014771422],"domain_scores_gemma":[0.24925137,0.725204,0.022297347,0.0008482702,0.001445213,0.00095381995],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24181853,0.00059772556,0.010069384,0.0006140103,0.0005923129,0.000040131505,0.0011638602,0.0020699692,0.001399576],"category_scores_gemma":[0.68092215,0.00038406692,0.0027550412,0.00032389458,0.0011851789,0.0003574664,0.00034978928,0.011993295,0.00015537353],"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":[0.00006799906,0.000037499558,0.0018994367,0.0011791278,0.0019212482,0.000031063737,0.00090201764,0.000004823196,5.2667883e-7,0.0025117074,0.98826903,0.0031755273],"study_design_scores_gemma":[0.0013712144,0.0016043491,0.016023282,0.0026760472,0.004034566,0.000071380586,0.0034309183,0.0007849881,6.288386e-7,0.01796012,0.95153505,0.0005074544],"about_ca_topic_score_codex":0.00029339813,"about_ca_topic_score_gemma":0.000088399036,"teacher_disagreement_score":0.5407051,"about_ca_system_score_codex":0.00030226415,"about_ca_system_score_gemma":0.0015556773,"threshold_uncertainty_score":0.9998611},"labels":[],"label_agreement":null},{"id":"W2062240619","doi":"10.1016/j.jclinepi.2014.09.008","title":"Cross-linked survey analysis is an approach for separating cause and effect in survey research","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"University of Toronto; Health Sciences Centre; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Respondent; Survey data collection; Survey methodology; Selection bias; Timeline; Population; Matching (statistics); Cross-sectional study; Non-response bias; Survey research; Psychology; Statistics; Medicine; Applied psychology; Environmental health; Mathematics","score_opus":0.8948807602527982,"score_gpt":0.7361257173472777,"score_spread":0.15875504290552045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062240619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776802,0.00017917811,0.020726101,0.00060976116,0.00042282228,0.00022229807,0.000021010499,0.000006260024,0.00013235882],"genre_scores_gemma":[0.9837236,0.00024013528,0.014503471,0.00075327867,0.00057676504,0.00000888032,0.000020760632,0.000010890085,0.00016223056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.24797398,0.74632597,0.003876631,0.00060964836,0.0003621064,0.00085164537],"domain_scores_gemma":[0.34941953,0.6479564,0.0011873879,0.0002582007,0.000794499,0.00038400147],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91628176,0.00014985994,0.0028579226,0.0005033029,0.00040387324,0.000035582707,0.00053179596,0.0009326454,0.000043028613],"category_scores_gemma":[0.90390366,0.000114216564,0.0004610094,0.0011150814,0.0017103915,0.00020102895,0.00007407026,0.0015389859,0.0000023951397],"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":[0.011168567,0.00011916412,0.983793,0.000008781941,0.00027306072,0.0000026962805,0.0005816269,0.0002776069,0.0000029216349,0.00021178715,0.00031120508,0.0032495712],"study_design_scores_gemma":[0.0011851386,0.0012143692,0.9889799,0.000006732526,0.00007348283,0.000002090357,0.000080603495,0.0057764514,0.000001798157,0.0022398995,0.00033217217,0.000107387976],"about_ca_topic_score_codex":0.007943372,"about_ca_topic_score_gemma":0.020959044,"teacher_disagreement_score":0.10144555,"about_ca_system_score_codex":0.000040545052,"about_ca_system_score_gemma":0.00037818935,"threshold_uncertainty_score":0.9986628},"labels":[],"label_agreement":null},{"id":"W2063005954","doi":"10.1016/j.jclinepi.2011.04.007","title":"Sensitive Clinical Queries retrieved relevant systematic reviews as well as primary studies: an analytic survey","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":23,"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":"Canadian Institutes of Health Research","keywords":"PsycINFO; CINAHL; MEDLINE; Systematic review; Etiology; Medicine; Information retrieval; Computer science; Internal medicine; Biology","score_opus":0.9777776711586176,"score_gpt":0.7428429140863486,"score_spread":0.23493475707226896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063005954","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011667523,0.98329717,0.0022398438,0.00034546573,0.006821474,0.0044690277,0.000040513893,0.000009679996,0.0026601308],"genre_scores_gemma":[0.000022098999,0.97732896,0.0059906268,0.00441078,0.00219241,0.000060266844,0.000042240834,0.000094246934,0.009858401],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.0889493,0.66195047,0.24063201,0.0031816168,0.0042906115,0.0009960254],"domain_scores_gemma":[0.011716294,0.6870316,0.27964717,0.009862133,0.009826418,0.0019163623],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9471821,0.0021646686,0.22270735,0.0010778726,0.00023770337,0.00027275755,0.0076898476,0.0029923825,0.0039424384],"category_scores_gemma":[0.98459697,0.0008523415,0.055103116,0.002889596,0.0016910211,0.00063058344,0.00089214183,0.006067771,0.030604957],"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":[0.00048101434,0.0010765478,0.012140272,0.17787163,0.024352884,0.0007175545,0.0002450492,0.0000032296068,1.2045723e-8,0.0020341887,0.37786394,0.40321368],"study_design_scores_gemma":[0.00039638038,0.002191209,0.0022946503,0.06582157,0.016215188,0.0013045765,0.00023059528,0.000037425303,6.028099e-9,0.009422821,0.9013824,0.0007031882],"about_ca_topic_score_codex":0.000045693003,"about_ca_topic_score_gemma":0.00013415728,"teacher_disagreement_score":0.52351844,"about_ca_system_score_codex":0.0002751467,"about_ca_system_score_gemma":0.003219754,"threshold_uncertainty_score":0.99939275},"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":"W2063767105","doi":"10.1016/j.jclinepi.2005.09.007","title":"Ordinal regression model and the linear regression model were superior to the logistic regression models","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":108,"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; University of Alberta","funders":"","keywords":"Statistics; Ordinal regression; Logistic regression; Confidence interval; Ordered logit; Linear regression; Regression analysis; Segmented regression; Regression diagnostic; Ordinal data; Mathematics; Ordinal Scale; Cross-sectional regression; Odds ratio; Regression dilution; Regression; Bayesian multivariate linear regression","score_opus":0.7463516114223616,"score_gpt":0.5825618595411016,"score_spread":0.16378975188126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063767105","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":[0.28584617,0.007952945,0.3131005,0.38977072,0.0014189945,0.0007034545,0.00008088075,0.000023282217,0.0011030709],"genre_scores_gemma":[0.916102,0.002810439,0.040843226,0.036114577,0.0025740708,0.00003619103,0.000009542237,0.000048102895,0.0014618383],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97714114,0.0055940533,0.015772441,0.0006784632,0.00019842872,0.0006154978],"domain_scores_gemma":[0.9525921,0.033683773,0.01200348,0.0009563844,0.0002939326,0.0004703556],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14142798,0.00033894714,0.0041426793,0.00022413647,0.0004449928,0.000038992785,0.000793443,0.00058062834,0.000045865778],"category_scores_gemma":[0.08230765,0.0001788913,0.0006996826,0.00014465045,0.00060732645,0.0004074695,0.00024748547,0.0013424496,0.00011204567],"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":[0.0011287974,0.00014777275,0.017793797,0.000085565545,0.00006575265,0.0000045488227,0.00035182395,0.6254683,0.0000018475008,0.22741114,0.1264835,0.0010571717],"study_design_scores_gemma":[0.0016166362,0.0001614725,0.0036950426,0.0002751282,0.000023771257,0.00004151673,0.00010250618,0.6870751,3.2609844e-7,0.30219468,0.0046651307,0.00014870708],"about_ca_topic_score_codex":0.00029971715,"about_ca_topic_score_gemma":0.000074526644,"teacher_disagreement_score":0.6302558,"about_ca_system_score_codex":0.00016454252,"about_ca_system_score_gemma":0.00034512923,"threshold_uncertainty_score":0.9254225},"labels":[],"label_agreement":null},{"id":"W2064052286","doi":"10.1016/j.jclinepi.2014.11.012","title":"Copresentation of relative and absolute effects is essential to promote optimal interpretability of treatment effects","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Interpretability; Absolute (philosophy); Medicine; Computer science; Machine learning; Philosophy; Epistemology","score_opus":0.7282977570590544,"score_gpt":0.642368630379622,"score_spread":0.08592912667943242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064052286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5329978,0.0018882056,0.19825917,0.26045746,0.003258131,0.002603079,0.000046261637,0.0000026551402,0.00048727807],"genre_scores_gemma":[0.6033388,0.0008551212,0.12946263,0.25562975,0.0067474665,0.00007775018,0.000028182962,0.00008556998,0.003774722],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77991945,0.15739688,0.057992447,0.0015063813,0.0027035517,0.00048130233],"domain_scores_gemma":[0.5851954,0.34877616,0.061149605,0.0022971956,0.0022382562,0.00034334208],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28034192,0.00049581344,0.02450788,0.00049134565,0.000035805482,0.000037624577,0.0012598096,0.0010972822,0.0004928754],"category_scores_gemma":[0.5637447,0.00022399699,0.007067131,0.00035045645,0.00048052162,0.00015413464,0.00020225362,0.0013962482,0.00009666118],"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":[0.0004916642,0.00026451965,0.06356708,0.0015882599,0.0048350845,0.00006762503,0.0008463312,0.00023783508,0.000077256016,0.00019539424,0.87909836,0.048730582],"study_design_scores_gemma":[0.0056862123,0.03256254,0.2103431,0.003887907,0.012889222,0.0003353979,0.00006929319,0.02289637,0.0005908598,0.06916475,0.6405139,0.0010604755],"about_ca_topic_score_codex":0.000032051663,"about_ca_topic_score_gemma":0.0000040661707,"teacher_disagreement_score":0.28340277,"about_ca_system_score_codex":0.000061387414,"about_ca_system_score_gemma":0.00020996187,"threshold_uncertainty_score":0.9899743},"labels":[],"label_agreement":null},{"id":"W2064347247","doi":"10.1016/j.jclinepi.2012.08.001","title":"GRADE guidelines: 13. Preparing Summary of Findings tables and evidence profiles—continuous outcomes","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":761,"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","funders":"","keywords":"Measure (data warehouse); Outcome (game theory); Standard deviation; Guideline; Construct (python library); Statistics; Medicine; Computer science; Duration (music); Mathematics; Data mining; Pathology","score_opus":0.8906265183209625,"score_gpt":0.6541961937295419,"score_spread":0.23643032459142066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064347247","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":[0.0011035186,0.98483574,0.0009944695,0.009149966,0.0028412857,0.00077088486,0.00012908048,0.00001292967,0.000162122],"genre_scores_gemma":[0.00020231346,0.97737455,0.015853489,0.004016543,0.0020410938,0.000037122714,0.000013398956,0.00005979328,0.00040169875],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9332954,0.0080704475,0.05695691,0.0007771338,0.000153066,0.0007470346],"domain_scores_gemma":[0.7957245,0.14230496,0.060105707,0.00084249984,0.00038290655,0.00063941046],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28716993,0.0005482703,0.023459053,0.0006559563,0.00008921758,0.000023509927,0.0009280745,0.001337815,0.00012923693],"category_scores_gemma":[0.4575163,0.00046741765,0.0022941572,0.00019799962,0.00040647783,0.0006695562,0.0002830428,0.0015173006,0.00014563612],"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":[0.00003731826,0.00022559501,0.7837275,0.033689257,0.0013047918,0.0000041428,0.00013081034,0.000018790444,1.6734925e-8,0.01311611,0.06570972,0.102035955],"study_design_scores_gemma":[0.00048459615,0.00029041286,0.01594409,0.019255562,0.00043577395,0.00012716695,0.000054073185,0.00009986721,2.290612e-8,0.006418506,0.95646936,0.00042058917],"about_ca_topic_score_codex":0.00044953072,"about_ca_topic_score_gemma":0.000046716068,"teacher_disagreement_score":0.89075965,"about_ca_system_score_codex":0.00024478885,"about_ca_system_score_gemma":0.0007431352,"threshold_uncertainty_score":0.99995863},"labels":[],"label_agreement":null},{"id":"W2064480399","doi":"10.1016/j.jclinepi.2004.02.016","title":"Asthma severity scores for preschoolers displayed weaknesses in reliability, validity, and responsiveness","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":68,"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; Hospital for Sick Children; SickKids Foundation","funders":"","keywords":"Asthma; Medicine; Inter-rater reliability; Severity of illness; Construct validity; Psychometrics; Physical therapy; Rating scale; Pediatrics; Clinical psychology; Psychiatry; Psychology; Internal medicine; Developmental psychology","score_opus":0.27234356824774225,"score_gpt":0.5320428745383305,"score_spread":0.2596993062905883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064480399","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":[0.014440332,0.98112196,0.0005003193,0.0013701275,0.0012716685,0.0011886988,0.00007375878,0.000012551448,0.000020578027],"genre_scores_gemma":[0.0009790622,0.9944316,0.0021810564,0.00067759684,0.0015505571,0.000042894142,0.00002199695,0.000051306826,0.00006393689],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9822721,0.008312255,0.007965867,0.00067159417,0.00026308477,0.0005151338],"domain_scores_gemma":[0.9267395,0.06622029,0.0051378743,0.0005513751,0.00049851,0.0008524277],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.024652448,0.00050168973,0.011555773,0.00036840353,0.00006261634,0.000011046486,0.00034949539,0.0013802766,0.000027864562],"category_scores_gemma":[0.19967635,0.00031266085,0.002733084,0.00022506439,0.00076972827,0.00012536658,0.00017986899,0.0020135075,0.0000054483226],"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":[0.0061295168,0.0011959509,0.11652948,0.060369432,0.00039079622,0.0005692881,0.00001343376,0.000056375346,1.7091375e-7,0.00027000552,0.0022896505,0.8121859],"study_design_scores_gemma":[0.002794573,0.002849407,0.11784335,0.034639224,0.0012230104,0.00072248344,0.000012946325,0.000012693169,1.4830673e-7,0.0042840317,0.83533216,0.00028599854],"about_ca_topic_score_codex":0.000016735528,"about_ca_topic_score_gemma":0.000013191508,"teacher_disagreement_score":0.8330425,"about_ca_system_score_codex":0.00015838431,"about_ca_system_score_gemma":0.0038805583,"threshold_uncertainty_score":0.9999325},"labels":[],"label_agreement":null},{"id":"W2064507326","doi":"10.1016/s0895-4356(99)00148-1","title":"Lessons learned from enrollment in the BEST study—A multicenter, randomized trial of group psychosocial support in metastatic breast cancer","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Regional Cancer Foundation; University of Ottawa; Research Manitoba; University of Alberta; Hamilton Regional Laboratory Medicine Program; University of British Columbia; University of Manitoba; BC Cancer Agency; University of Calgary; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; McMaster University; University of Toronto","funders":"University of Toronto","keywords":"Psychosocial; Randomized controlled trial; Randomization; Medicine; Clinical trial; Generalizability theory; Breast cancer; Population; Psychological intervention; Cancer; Family medicine; Physical therapy; Internal medicine; Psychology; Psychiatry","score_opus":0.2935298684178816,"score_gpt":0.541074720412916,"score_spread":0.24754485199503445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064507326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95590746,0.0005645227,0.00004388819,0.040464163,0.0016526103,0.0010787457,0.00003978839,0.0000025798902,0.0002462553],"genre_scores_gemma":[0.9891615,0.0055553005,0.00016198431,0.003758417,0.0012125126,0.000068719186,0.0000069582575,0.000013011665,0.00006161749],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.97689587,0.015562919,0.006431422,0.00032098984,0.00043521047,0.00035361372],"domain_scores_gemma":[0.9710034,0.026514528,0.0019152369,0.00028579752,0.00011807067,0.00016295341],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037679963,0.00018706283,0.0047363434,0.00013504387,0.000021630343,0.000004695335,0.0003026077,0.00019548085,0.0012100949],"category_scores_gemma":[0.009161075,0.00010671061,0.001122911,0.00020766495,0.0003090234,0.000059322007,0.000022131057,0.0012702794,0.0000075033618],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.73333967,0.0049955067,0.18260421,0.000015767962,0.0004726381,0.00010955564,0.0017559349,0.000040635383,0.0000028675381,0.000038052105,0.00035425936,0.0762709],"study_design_scores_gemma":[0.7831529,0.0027525576,0.20758362,0.00018065836,0.0006988667,0.000023136294,0.0023198968,0.00010314546,3.8715024e-7,0.0017096194,0.0013874571,0.00008779689],"about_ca_topic_score_codex":0.0083115185,"about_ca_topic_score_gemma":0.009064921,"teacher_disagreement_score":0.07618311,"about_ca_system_score_codex":0.000071025286,"about_ca_system_score_gemma":0.00032442439,"threshold_uncertainty_score":0.99970293},"labels":[],"label_agreement":null},{"id":"W2064658902","doi":"10.1016/s0895-4356(01)00509-1","title":"Comparison of the responsiveness of lupus disease activity measures to changes in systemic lupus erythematosus activity relevant to patients and physicians","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":51,"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 Health Centre; Toronto Western Hospital; Montreal General Hospital; University Health Network; University of Toronto; McGill University","funders":"Canadian Arthritis Network","keywords":"Medicine; Systemic lupus erythematosus; Internal medicine; Confidence interval; Lupus erythematosus; Disease; Systemic disease; Connective tissue disease; Autoimmune disease; Immunology; Antibody","score_opus":0.2259744657111512,"score_gpt":0.471781620414512,"score_spread":0.2458071547033608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064658902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9860984,0.0008780661,0.00027225792,0.010426993,0.0012960362,0.0009705415,0.000022580383,0.000005495562,0.000029649887],"genre_scores_gemma":[0.99853164,0.00046908087,0.00020278776,0.0004137635,0.00020321959,0.000017554321,2.950816e-7,0.000024222702,0.00013742056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9884768,0.0069828145,0.0029529512,0.0003843161,0.00074345415,0.00045967707],"domain_scores_gemma":[0.9765788,0.018678335,0.0027951878,0.0006351662,0.0007523285,0.0005602164],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011408522,0.00023391584,0.0039950605,0.00035169136,0.000043486012,0.0000035983185,0.0003903825,0.00026114736,0.0000102545855],"category_scores_gemma":[0.08740856,0.00014495899,0.00046647235,0.00046350152,0.00033008624,0.00006778237,0.00024291221,0.0008659313,0.0000049218834],"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":[0.009073467,0.0012548299,0.9706662,0.0009657827,0.00013737599,0.000023438308,0.0010200882,0.00014528417,0.0035705573,0.00002682889,0.0016334911,0.011482646],"study_design_scores_gemma":[0.0038371496,0.002750063,0.9840366,0.0050753527,0.00015702861,0.0011226828,0.0003755415,0.00092600146,0.0011178557,0.00014900374,0.00030259494,0.00015010843],"about_ca_topic_score_codex":0.000066095075,"about_ca_topic_score_gemma":0.0001663412,"teacher_disagreement_score":0.076000035,"about_ca_system_score_codex":0.00015991808,"about_ca_system_score_gemma":0.00018661117,"threshold_uncertainty_score":0.9202786},"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":"W2066363392","doi":"10.1016/j.jclinepi.2007.09.007","title":"Health Utilities Index Mark 3 showed valid in Alzheimer Disease, arthritis, and cataracts","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute of Health Economics; University of Alberta","funders":"","keywords":"Health Utilities Index; Medicine; Gerontology; Quality of life (healthcare); Index (typography); Population; Demography; Disease; Physical therapy; Psychology; Internal medicine; Health related quality of life; Environmental health","score_opus":0.7769341593164061,"score_gpt":0.5838545738545514,"score_spread":0.19307958546185466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066363392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.723697,0.0776755,0.001306387,0.19487323,0.0016416645,0.0003129388,0.00009898875,0.000011335627,0.00038295388],"genre_scores_gemma":[0.9106719,0.031650573,0.0024471958,0.054205094,0.00088766805,0.000008973271,0.000010193258,0.000019467503,0.00009892898],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9739785,0.0056967344,0.019217813,0.0004607677,0.0000863681,0.0005597809],"domain_scores_gemma":[0.9580515,0.029936528,0.010696381,0.00035906144,0.00009358712,0.0008629349],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12062056,0.00018652347,0.0045281537,0.0003503852,0.00011845899,0.0000099269855,0.00025169726,0.00027349516,0.00016144307],"category_scores_gemma":[0.109019764,0.00020000356,0.00035967724,0.00011184499,0.00041625416,0.00039351344,0.00005924144,0.0007963982,0.00013346704],"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":[0.00013439391,0.00013216122,0.9514499,0.000052950527,0.00007275096,0.000017821265,0.00025572305,0.0000807933,7.7977e-9,0.012987562,0.03237058,0.0024453872],"study_design_scores_gemma":[0.0013392811,0.00023931706,0.91479135,0.00016620295,0.000004787574,0.00007607951,0.00012445512,0.0011430511,2.504959e-8,0.04735598,0.03461114,0.0001483409],"about_ca_topic_score_codex":0.0008659698,"about_ca_topic_score_gemma":0.0002481483,"teacher_disagreement_score":0.1869749,"about_ca_system_score_codex":0.00013049932,"about_ca_system_score_gemma":0.00076824287,"threshold_uncertainty_score":0.9055062},"labels":[],"label_agreement":null},{"id":"W2067205484","doi":"10.1016/j.jclinepi.2007.03.001","title":"The standard gamble showed better construct validity than the time trade-off","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Gastrointestinal motility and disorders","field":"Medicine","cited_by":40,"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; McMaster University","funders":"","keywords":"Medicine; Quality of life (healthcare); Time-trade-off; Construct validity; Irritable bowel syndrome; Standard deviation; Physical therapy; Psychometrics; Internal medicine; Clinical psychology; Statistics; Mathematics","score_opus":0.19408688501617885,"score_gpt":0.462910892171745,"score_spread":0.2688240071555662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067205484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81670976,0.00052417954,0.00587092,0.17389044,0.00093345245,0.00018561906,0.000004675231,0.000014129275,0.0018668163],"genre_scores_gemma":[0.9754442,0.00034963776,0.0056227646,0.01684509,0.0015126304,8.5476904e-7,0.0000018959612,0.000014753056,0.00020815698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99202114,0.003151859,0.0037217329,0.0002130122,0.0003334325,0.0005588342],"domain_scores_gemma":[0.9130911,0.08368394,0.002009777,0.00047328806,0.00026001554,0.00048188513],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055978872,0.00017179745,0.0016035562,0.000043767548,0.00018831163,0.000010686481,0.00034664213,0.00024088261,0.0001668224],"category_scores_gemma":[0.10172832,0.00007729098,0.00097219535,0.00010806479,0.0014503661,0.000057017303,0.000052874246,0.0018806063,0.000033627362],"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":[0.004123845,0.00013290957,0.9024785,0.000012892673,0.00016322293,0.00009482949,0.000030840445,0.000009204359,0.00003817601,0.0008354947,0.032243785,0.05983626],"study_design_scores_gemma":[0.0020991853,0.0028264278,0.90128994,0.00008319363,0.00018574606,0.0016990366,0.00016215569,0.00015689574,0.000019293886,0.016886026,0.07452207,0.00007000811],"about_ca_topic_score_codex":0.000007916433,"about_ca_topic_score_gemma":0.000024966763,"teacher_disagreement_score":0.15873446,"about_ca_system_score_codex":0.00003599608,"about_ca_system_score_gemma":0.0002869359,"threshold_uncertainty_score":0.9720684},"labels":[],"label_agreement":null},{"id":"W2067661817","doi":"10.1016/j.jclinepi.2013.02.003","title":"GRADE guidelines: 15. Going from evidence to recommendation—determinants of a recommendation's direction and strength","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1295,"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 Agency for Drugs and Technologies in Health; University of Ottawa; McMaster University","funders":"","keywords":"Guideline; Intervention (counseling); Resource (disambiguation); Computer science; Confidence interval; Medicine; Nursing","score_opus":0.8517406491176167,"score_gpt":0.636225481252777,"score_spread":0.2155151678648397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067661817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7383639,0.0010144382,0.015418116,0.24239098,0.0022050033,0.00035259544,0.00007858489,0.000010784209,0.00016557927],"genre_scores_gemma":[0.80709296,0.005313249,0.1361498,0.048731975,0.0024237547,0.000040463034,0.00002264584,0.00003508749,0.0001900765],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97483844,0.0036038663,0.020741928,0.0004541082,0.000061502586,0.00030018273],"domain_scores_gemma":[0.9183225,0.063544855,0.016934361,0.00031038362,0.000459536,0.0004283452],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089467496,0.00017041853,0.0031517248,0.0003154536,0.000081256716,0.000023319815,0.00026690398,0.00027749897,0.001375328],"category_scores_gemma":[0.3413036,0.00017137858,0.00029567158,0.0001467529,0.000096538795,0.00080912316,0.00008602535,0.00041563934,0.00037531523],"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":[0.00004895671,0.00009543908,0.8474821,0.00006761952,0.000089075096,3.0446046e-7,0.00018855877,0.00006155071,0.000003403705,0.0008984548,0.10078824,0.050276287],"study_design_scores_gemma":[0.0010406934,0.00067943713,0.8583187,0.0005731172,0.000025107653,0.00001731379,0.0003759384,0.01797673,0.00000624131,0.039924987,0.08081399,0.0002477572],"about_ca_topic_score_codex":0.0018089206,"about_ca_topic_score_gemma":0.0001901559,"teacher_disagreement_score":0.2518361,"about_ca_system_score_codex":0.00013706571,"about_ca_system_score_gemma":0.00015895408,"threshold_uncertainty_score":0.9995375},"labels":[],"label_agreement":null},{"id":"W2067670776","doi":"10.1016/j.jclinepi.2012.01.022","title":"The “Lost NNT” can be used to represent uncertainty surrounding number needed to treat","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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; Vancouver Coastal Health","funders":"","keywords":"Number needed to treat; Context (archaeology); Actuarial science; Scale (ratio); Confidence interval; Risk analysis (engineering); Computer science; Statistics; Mathematics; Medicine; Relative risk; Economics","score_opus":0.8217633485441703,"score_gpt":0.6239034322607311,"score_spread":0.19785991628343924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067670776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5686015,0.0004308033,0.0024596618,0.42233536,0.0036274774,0.00033003394,0.000040329753,0.000008756615,0.0021660698],"genre_scores_gemma":[0.8514066,0.0002952716,0.0044644135,0.13680442,0.0051903375,0.000025714427,0.0000047752515,0.00003640299,0.0017721159],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9736668,0.0066998415,0.01803089,0.00044956128,0.00014015692,0.0010127511],"domain_scores_gemma":[0.87834215,0.10934404,0.0096507175,0.0008407926,0.00023044038,0.0015918567],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24285154,0.00022686337,0.0036293094,0.00019543654,0.00025405613,0.000041099032,0.00064317585,0.000343644,0.0004941702],"category_scores_gemma":[0.35430866,0.00018237422,0.0006853231,0.00023955638,0.00015137075,0.00027664323,0.00013635558,0.00072604505,0.0019155547],"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":[0.00014508651,0.000105452535,0.65016365,0.000023976474,0.00010462138,0.0000013491951,0.00091106776,0.0008914953,0.000001072997,0.054049224,0.29313174,0.0004712492],"study_design_scores_gemma":[0.0013692693,0.00045139223,0.24454902,0.00008823064,0.000029136389,0.00006340667,0.0024141038,0.00056484126,0.0000030349875,0.020602914,0.7295108,0.00035386631],"about_ca_topic_score_codex":0.002313838,"about_ca_topic_score_gemma":0.0005337527,"teacher_disagreement_score":0.43637905,"about_ca_system_score_codex":0.0005001743,"about_ca_system_score_gemma":0.00025662358,"threshold_uncertainty_score":0.99886155},"labels":[],"label_agreement":null},{"id":"W2067849939","doi":"10.1016/j.jclinepi.2005.12.021","title":"Abbreviated guidelines for scoring the Cumulative Illness Rating Scale (CIRS) in family practice","year":2006,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":107,"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","funders":"","keywords":"Rating scale; Scale (ratio); Medicine; Statistics; Geography; Mathematics; Cartography","score_opus":0.5648820494649681,"score_gpt":0.6001291976060111,"score_spread":0.035247148141043017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067849939","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":[0.0055265115,0.0041868365,0.0077754227,0.9748163,0.0031101282,0.0011721982,0.000020949776,0.000025420912,0.003366235],"genre_scores_gemma":[0.0026271245,0.0020168917,0.017374082,0.9514461,0.024937078,0.00005355687,0.00013085625,0.00008778253,0.0013264982],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826511,0.005227825,0.010296857,0.0005813104,0.00051451824,0.00072834786],"domain_scores_gemma":[0.88459456,0.102740906,0.00975771,0.0006194647,0.0021396196,0.00014777166],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04037765,0.00046475607,0.004657929,0.0002835533,0.0001033963,0.000028135775,0.00055414747,0.0011207385,0.000040231993],"category_scores_gemma":[0.23364979,0.00028061113,0.0015287136,0.00027210035,0.00046114819,0.00025039187,0.00014860537,0.0048579588,0.000012882842],"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":[0.00062917033,0.00014636254,0.0066719977,0.00062728755,0.0005255956,0.00053004455,0.000026582897,0.0021339608,0.0000014209523,0.00020768789,0.9818289,0.0066709383],"study_design_scores_gemma":[0.004602197,0.0007705361,0.026708994,0.0023631852,0.0015323458,0.00014061829,0.00045369624,0.0043444666,5.851174e-7,0.0068502594,0.9519195,0.00031361912],"about_ca_topic_score_codex":0.00021729044,"about_ca_topic_score_gemma":0.00002860164,"teacher_disagreement_score":0.19327214,"about_ca_system_score_codex":0.00020572275,"about_ca_system_score_gemma":0.000979591,"threshold_uncertainty_score":0.9999646},"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":"W2069378996","doi":"10.1016/j.jclinepi.2010.03.002","title":"Guidelines for Reporting Reliability and Agreement Studies (GRRAS) were proposed","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":2097,"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; Western University","funders":"","keywords":"Reliability (semiconductor); Psychology; Medicine; Statistics; Mathematics; Physics","score_opus":0.8672390330587612,"score_gpt":0.6777059197779776,"score_spread":0.1895331132807836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069378996","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":[0.86515754,0.00081930705,0.009263499,0.11820952,0.005886674,0.00046457764,0.0000036511228,0.000008726315,0.00018651423],"genre_scores_gemma":[0.74720305,0.0011730612,0.23945084,0.007989421,0.003441096,0.000014099624,8.075982e-7,0.000012807161,0.0007148376],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95896083,0.004705852,0.03348568,0.000917647,0.0013962543,0.0005337567],"domain_scores_gemma":[0.42399958,0.44324395,0.093427196,0.003587839,0.03416727,0.001574159],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45064372,0.00021836588,0.003410418,0.00012306408,0.00019645992,0.000036675057,0.0007325085,0.0003323937,0.000116874406],"category_scores_gemma":[0.94168174,0.00011435207,0.0010388456,0.00015202149,0.00080750836,0.00022719738,0.00022781966,0.0010628202,0.000012046918],"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":[0.00041550235,0.00025348336,0.7635147,0.000054199194,0.00016140574,0.000008256494,0.00009904367,0.0002754978,0.0004237409,0.0019835006,0.0986567,0.13415396],"study_design_scores_gemma":[0.001543044,0.0017198691,0.25295988,0.00010894832,0.00010334914,0.00006973462,0.0009580551,0.0018206442,0.00009909769,0.54122025,0.19920006,0.00019706109],"about_ca_topic_score_codex":0.000008643571,"about_ca_topic_score_gemma":0.000060091228,"teacher_disagreement_score":0.5392367,"about_ca_system_score_codex":0.000028629456,"about_ca_system_score_gemma":0.00029350707,"threshold_uncertainty_score":0.5656779},"labels":[],"label_agreement":null},{"id":"W2069636027","doi":"10.1016/j.jclinepi.2006.07.003","title":"Walter O. Spitzer 1937–2006, Co-Editor, Journal of Chronic Disease 1982–1988 and Clinical Epidemiology 1988–1994","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"T-cell and Retrovirus Studies","field":"Immunology and Microbiology","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":"Élisabeth Bruyère Hospital; University of Ottawa","funders":"","keywords":"Epidemiology; Medicine; Health care; Gerontology; Clinical epidemiology; Family medicine; Pathology; Law; Political science","score_opus":0.10839532558254472,"score_gpt":0.44106074831431075,"score_spread":0.332665422731766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069636027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7962202,0.124064006,0.0031904057,0.02065904,0.054498278,0.0003863299,0.00014288718,0.000043642347,0.00079525536],"genre_scores_gemma":[0.90353477,0.047536973,0.0019183353,0.0058668037,0.038527608,0.0000057760167,0.000042231466,0.00007436188,0.0024931259],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.966448,0.016416447,0.014935111,0.0007238579,0.00015075984,0.0013257952],"domain_scores_gemma":[0.92552096,0.061830815,0.0109905265,0.00056287437,0.0005676471,0.00052719127],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04308543,0.0006162505,0.0075347726,0.0003665328,0.00029441947,0.000010177858,0.0008778331,0.0018366016,0.00049287744],"category_scores_gemma":[0.062119342,0.0003982471,0.0027823397,0.00016417104,0.004248631,0.0002310742,0.00030275545,0.004412195,0.00017774056],"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":[0.002217205,0.0009838098,0.6723526,0.000066848355,0.001209344,0.0001647448,0.000017931754,0.000083712635,0.00031222668,0.0016180326,0.30791697,0.013056559],"study_design_scores_gemma":[0.006463892,0.0048217103,0.54471374,0.00020959221,0.00074190093,0.0009602699,0.000041832605,0.000038190297,0.000037542046,0.0110775195,0.43050882,0.00038498602],"about_ca_topic_score_codex":0.00017943534,"about_ca_topic_score_gemma":0.000077319004,"teacher_disagreement_score":0.12763889,"about_ca_system_score_codex":0.00011973186,"about_ca_system_score_gemma":0.0008509814,"threshold_uncertainty_score":0.99984694},"labels":[],"label_agreement":null},{"id":"W2070193705","doi":"10.1016/j.jclinepi.2008.08.003","title":"Poor reporting of search strategy and conflict of interest in over 250 narrative and systematic reviews of two biologic agents in arthritis: A systematic review","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Society of Obstetricians and Gynaecologists of Canada","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; Agency for Healthcare Research and Quality","keywords":"Systematic review; Medicine; Critical appraisal; MEDLINE; Conflict of interest; Etanercept; Grey literature; Narrative review; Clinical trial; Publication bias; Alternative medicine; Meta-analysis; Family medicine; Rheumatoid arthritis; Internal medicine; Political science; Intensive care medicine; Pathology; Business; Finance","score_opus":0.7264917536219762,"score_gpt":0.607378617756835,"score_spread":0.11911313586514116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070193705","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":[0.023183519,0.97253215,0.000008187072,0.0001088203,0.000078028505,0.0040407,0.000012015439,0.0000018472647,0.000034715144],"genre_scores_gemma":[0.011606399,0.987829,0.00027670898,0.0001347755,0.000042825024,0.00007273322,0.0000069183343,0.000019942378,0.000010676818],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9296733,0.027965294,0.041279797,0.00040806807,0.00027276162,0.00040075605],"domain_scores_gemma":[0.93004465,0.029908918,0.038783316,0.00046046328,0.000504196,0.0002984368],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07650404,0.00040139316,0.03732871,0.00058504625,0.000017385231,0.000003638547,0.00027178702,0.0004595235,0.000038787264],"category_scores_gemma":[0.2987926,0.00022314992,0.0015134109,0.0003858433,0.00088807713,0.00008474645,0.0001254428,0.0017080896,0.0000012513955],"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":[0.00008273289,0.0002034865,0.006086544,0.9669902,0.0005672028,0.00030882566,0.00016175686,3.0892457e-7,0.0000011448645,0.00020489884,0.00007584511,0.025317058],"study_design_scores_gemma":[0.0016979955,0.0020417608,0.0010854409,0.9895112,0.0002125366,0.004243582,0.00019585212,0.000022193992,2.7587345e-7,0.00018792,0.00067602214,0.0001252073],"about_ca_topic_score_codex":0.000086481356,"about_ca_topic_score_gemma":0.00007511987,"teacher_disagreement_score":0.22228858,"about_ca_system_score_codex":0.000047542995,"about_ca_system_score_gemma":0.00062205264,"threshold_uncertainty_score":0.97696316},"labels":[],"label_agreement":null},{"id":"W2070365761","doi":"10.1016/j.jclinepi.2004.10.014","title":"A reliable coding system to define screening prostate-specific antigen tests was developed in a case–control study","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","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":"Markham Stouffville Hospital; University of British Columbia; Arthritis Research Centre of Canada; University of Ottawa; University of Toronto; Sunnybrook Health Science Centre; Health Sciences Centre; Princess Margaret Cancer Centre; Ottawa Hospital","funders":"National Cancer Institute","keywords":"Medicine; Kappa; Prostate-specific antigen; Rectal examination; Gynecology; Prostate; Context (archaeology); Urology; Internal medicine; Cancer","score_opus":0.2411116389113289,"score_gpt":0.47312109769182614,"score_spread":0.23200945878049725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070365761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.980666,0.0022139647,0.001946,0.013338348,0.00045446746,0.0012368666,0.000009844419,0.00002227365,0.0001122655],"genre_scores_gemma":[0.9628181,0.0009145717,0.03257341,0.0027284902,0.00084365456,0.000052466574,0.0000017149039,0.000027324131,0.00004027679],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9918275,0.0015366569,0.005387638,0.00044220194,0.00022562248,0.00058040867],"domain_scores_gemma":[0.9872045,0.00987879,0.0016317135,0.00031535837,0.00037865236,0.0005909715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017480154,0.0002514855,0.0033320612,0.00028374098,0.00007385855,0.000011755162,0.00014214245,0.00019761658,0.000034940214],"category_scores_gemma":[0.012767759,0.00017281175,0.00036429992,0.00032470858,0.00006085227,0.00011074335,0.00005946866,0.0008107114,0.000038379305],"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":[0.0028516173,0.0010279206,0.93878466,0.000043446486,0.00033672946,0.008331378,0.00022852076,0.0025855163,0.000019265619,0.00011286226,0.002191492,0.043486614],"study_design_scores_gemma":[0.014430989,0.007562278,0.9617843,0.0011331023,0.00019808969,0.003820825,0.00066554657,0.0010594412,0.000019780557,0.000027366847,0.009125336,0.00017295795],"about_ca_topic_score_codex":0.00011402512,"about_ca_topic_score_gemma":0.00021900993,"teacher_disagreement_score":0.043313656,"about_ca_system_score_codex":0.00034488103,"about_ca_system_score_gemma":0.0003195636,"threshold_uncertainty_score":0.9955481},"labels":[],"label_agreement":null},{"id":"W2070452757","doi":"10.1016/j.jclinepi.2009.01.013","title":"MEDLINE, EMBASE, and Cochrane index most primary studies but not abstracts included in orthopedic meta-analyses","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":60,"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":"MEDLINE; CINAHL; Medicine; Meta-analysis; Cochrane Library; Psychological intervention; Internal medicine; Psychiatry","score_opus":0.9538503139033521,"score_gpt":0.7217914150196714,"score_spread":0.2320588988836807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070452757","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":[0.895642,0.053263225,0.003964145,0.04432541,0.0008098166,0.00040110006,0.0000124713715,0.000004080999,0.0015777675],"genre_scores_gemma":[0.9530821,0.006885037,0.013748874,0.024456052,0.0005806365,0.0000047308995,0.0000026359353,0.000009622297,0.0012303059],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.74211866,0.12631471,0.12306672,0.0017964918,0.0058632093,0.00084017427],"domain_scores_gemma":[0.36501983,0.5400689,0.08501849,0.0035652868,0.005180978,0.0011464873],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6451921,0.00048143673,0.03348906,0.0008434139,0.000092551076,0.00008893896,0.0015158899,0.00043223563,0.0009775799],"category_scores_gemma":[0.8257664,0.00019382569,0.0063392194,0.001112871,0.00043489327,0.00036886372,0.00020711376,0.001404648,0.000116541916],"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":[0.00067191455,0.0009730152,0.7279213,0.00019281374,0.01892661,0.0006994009,0.00028527525,0.0062213824,0.00013434557,0.001364266,0.1197144,0.12289527],"study_design_scores_gemma":[0.0011458051,0.0005720297,0.9457924,0.00008147594,0.0051608207,0.00020383227,0.000270804,0.0014121152,0.0000062124445,0.036349118,0.008782854,0.000222562],"about_ca_topic_score_codex":0.000022910415,"about_ca_topic_score_gemma":0.00010707002,"teacher_disagreement_score":0.41375422,"about_ca_system_score_codex":0.000036825433,"about_ca_system_score_gemma":0.00030446934,"threshold_uncertainty_score":0.9999357},"labels":[],"label_agreement":null},{"id":"W2070558469","doi":"10.1016/j.jclinepi.2006.04.001","title":"EMBASE search strategies achieved high sensitivity and specificity for retrieving methodologically sound systematic reviews","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":102,"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":"MEDLINE; Systematic review; Information retrieval; Medicine; Computer science; Medical physics; Biology","score_opus":0.9633625893941528,"score_gpt":0.700253013817999,"score_spread":0.2631095755761538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070558469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35169932,0.0051774,0.63769215,0.0032226378,0.00066005375,0.0012486689,0.000009444267,0.0000031705229,0.00028715632],"genre_scores_gemma":[0.72572476,0.0010468257,0.27009323,0.0011755083,0.0012900359,0.000015246079,0.0000027074582,0.000013220717,0.00063847506],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.45906553,0.45757687,0.079007864,0.0013167055,0.0023818917,0.00065112376],"domain_scores_gemma":[0.13544156,0.8054739,0.052912895,0.002349071,0.0033351826,0.00048738043],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8914965,0.00040657827,0.02780844,0.0002949295,0.0001853607,0.0003393554,0.0010544725,0.00046486023,0.0003915527],"category_scores_gemma":[0.89142483,0.00016566664,0.0061288318,0.00058800034,0.00042431866,0.000341878,0.00016618476,0.0009822466,0.00011656835],"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":[0.0012692171,0.0009335396,0.56867623,0.017830687,0.0020829982,0.00023907034,0.0002038653,0.004047163,0.00055998797,0.27794996,0.08837863,0.03782865],"study_design_scores_gemma":[0.0011752337,0.0011738155,0.3809663,0.001569826,0.0013751449,0.0005286768,0.0007012519,0.013179371,0.00000816718,0.5857016,0.013177863,0.0004427293],"about_ca_topic_score_codex":0.000027738486,"about_ca_topic_score_gemma":0.000070637325,"teacher_disagreement_score":0.3740254,"about_ca_system_score_codex":0.0000339213,"about_ca_system_score_gemma":0.00016591785,"threshold_uncertainty_score":0.9866248},"labels":[],"label_agreement":null},{"id":"W2070877465","doi":"10.1016/j.jclinepi.2008.02.004","title":"Systematic reviews can be produced and published faster","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":104,"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 Ottawa; Children's Hospital of Eastern Ontario","funders":"U.S. Public Health Service","keywords":"Systematic review; MEDLINE; Medicine; Journal club; Grey literature; Quartile; Scopus; Interquartile range; Psychological intervention; Library science; Family medicine; Medical education; Computer science; Political science; Surgery; Confidence interval","score_opus":0.9423567029623191,"score_gpt":0.6608303438083841,"score_spread":0.281526359153935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070877465","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7470256,0.039078075,0.031656474,0.16596568,0.0071003716,0.004640968,0.000014422851,0.00000996182,0.0045084497],"genre_scores_gemma":[0.8676659,0.012842356,0.04881807,0.04424776,0.0035803071,0.00007895083,0.000004991133,0.00004727808,0.022714416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.53027856,0.31622612,0.14767632,0.0014976945,0.0037087873,0.0006125454],"domain_scores_gemma":[0.26088494,0.53964263,0.18382035,0.007966759,0.005942841,0.0017424857],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7781477,0.00033672157,0.03040363,0.0003866467,0.00011676944,0.0001309772,0.0019674567,0.0002983152,0.001985866],"category_scores_gemma":[0.9498925,0.00012333188,0.0058711483,0.00066550827,0.00033486655,0.0003598574,0.0001661213,0.0008642424,0.00040784082],"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":[0.000032287273,0.00011506455,0.37841016,0.001844737,0.0005926145,0.000048979375,0.00027926435,0.0000130166645,0.000006997964,0.0012659903,0.6116162,0.0057746912],"study_design_scores_gemma":[0.0020458836,0.0014025214,0.2686452,0.0039459188,0.0020536755,0.005449392,0.0004812929,0.004061824,0.000004846532,0.043726116,0.6674767,0.00070663],"about_ca_topic_score_codex":0.0000050447998,"about_ca_topic_score_gemma":0.000012472147,"teacher_disagreement_score":0.2693936,"about_ca_system_score_codex":0.000019308245,"about_ca_system_score_gemma":0.00020032698,"threshold_uncertainty_score":0.99892646},"labels":[],"label_agreement":null},{"id":"W2070949299","doi":"10.1016/j.jclinepi.2009.03.022","title":"Response shift and outcome assessment in orthopedic surgery: is there a difference between complete and partial treatment?","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","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":"Sunnybrook Health Science Centre; Health Sciences Centre; University of Toronto","funders":"","keywords":"Medicine; Orthopedic surgery; Physical therapy; Scopus; Surgery; MEDLINE","score_opus":0.3217168489879902,"score_gpt":0.5122535652715668,"score_spread":0.19053671628357666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070949299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9098523,0.00065806234,0.00034314912,0.08875297,0.0001927718,0.00015178577,0.000011414293,0.000009211073,0.000028306737],"genre_scores_gemma":[0.9908599,0.001136279,0.0016789702,0.00589993,0.00031584915,0.0000015875645,0.000002197126,0.000010464681,0.00009477126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9915308,0.0038251707,0.0037769063,0.00031172167,0.00017637521,0.0003790268],"domain_scores_gemma":[0.95163894,0.04630201,0.0012927802,0.00022560534,0.000049933442,0.0004907366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013209633,0.00022338178,0.003628457,0.0001856707,0.00004114926,0.000008025092,0.00006941439,0.00027446126,0.000055615412],"category_scores_gemma":[0.019253854,0.00014014337,0.000418417,0.00009608298,0.0003260631,0.000076044154,0.000040292212,0.00078240177,0.0000050533345],"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":[0.0021321033,0.00019233122,0.95346004,0.000011973428,0.000106901854,0.00025065808,0.00008025048,7.731627e-7,0.000009356461,0.00013807582,0.00013951404,0.043478016],"study_design_scores_gemma":[0.00410131,0.0044952617,0.98553765,0.00012260326,0.00014050075,0.00021361273,0.000028447454,0.00011609084,0.0000011738404,0.0013772936,0.0037578135,0.00010827206],"about_ca_topic_score_codex":0.00003486112,"about_ca_topic_score_gemma":0.00002085418,"teacher_disagreement_score":0.08285304,"about_ca_system_score_codex":0.00005499232,"about_ca_system_score_gemma":0.00026520854,"threshold_uncertainty_score":0.9890074},"labels":[],"label_agreement":null},{"id":"W2071103776","doi":"10.1016/j.jclinepi.2008.09.004","title":"Systematic reviews of low back pain prognosis had variable methods and results—guidance for future prognosis reviews","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":245,"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; Institute for Work & Health; University of Toronto; University Health Network","funders":"Microsoft","keywords":"Medicine; Systematic review; Psychosocial; Sciatica; Low back pain; MEDLINE; Physical therapy; Alternative medicine; Pathology; Psychiatry","score_opus":0.32619333469860945,"score_gpt":0.575035486564436,"score_spread":0.2488421518658266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071103776","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":[9.881564e-7,0.9591129,0.025204454,0.0032881792,0.0010448574,0.011181569,0.0000189334,0.0000088675015,0.00013929803],"genre_scores_gemma":[1.6985257e-7,0.6172811,0.3793447,0.001157342,0.0016740197,0.00031159562,0.000024978417,0.000030123269,0.0001760192],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.8379137,0.114112854,0.045905516,0.0010082948,0.00033228364,0.00072736334],"domain_scores_gemma":[0.7557487,0.19889732,0.04257406,0.0010354932,0.0010665178,0.0006779117],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41002065,0.0007055225,0.034419667,0.00029259815,0.000057602294,0.000008923267,0.00042658256,0.0017546839,0.000033859193],"category_scores_gemma":[0.6555093,0.00036029133,0.006899225,0.00051543245,0.00035069315,0.00009317931,0.000058305297,0.0018187455,0.000011924793],"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":[0.00011628461,0.00024506118,0.000102840306,0.5037795,0.00035119394,9.441815e-7,0.0000118306925,2.0681658e-7,3.8551792e-7,0.00016098242,0.017234758,0.47799605],"study_design_scores_gemma":[0.00079211564,0.0030499503,0.00016075718,0.37646213,0.0023667496,0.000058829275,0.000009436456,0.000059612703,7.8295265e-8,0.00055107207,0.6163098,0.00017945145],"about_ca_topic_score_codex":0.0000024573756,"about_ca_topic_score_gemma":9.4209776e-7,"teacher_disagreement_score":0.5990751,"about_ca_system_score_codex":0.00008583342,"about_ca_system_score_gemma":0.00053933146,"threshold_uncertainty_score":0.9998849},"labels":[],"label_agreement":null},{"id":"W2071351610","doi":"10.1016/s0895-4356(01)00407-3","title":"A taxonomy for responsiveness","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":489,"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 Work & Health; St. Michael's Hospital","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Taxonomy (biology); Meaning (existential); Psychology; Context (archaeology); Computer science; Selection (genetic algorithm); Social psychology; Cognitive psychology; Management science; Artificial intelligence; Ecology; Geography; Psychotherapist; Biology; Engineering","score_opus":0.8979589234014199,"score_gpt":0.6413604132216578,"score_spread":0.2565985101797621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071351610","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":[0.2959491,0.0047387267,0.40050903,0.2886206,0.006052613,0.00095818803,0.0000847621,0.000021874037,0.0030651167],"genre_scores_gemma":[0.52534306,0.004019641,0.22089335,0.23160525,0.014487519,0.00026640302,0.000019129298,0.00009641115,0.0032692682],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9715664,0.0044152853,0.023111355,0.0003894148,0.00004898287,0.0004685564],"domain_scores_gemma":[0.8585583,0.11968879,0.020538198,0.00044084954,0.00032548775,0.0004483615],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25492093,0.00015027449,0.0043868273,0.00028522275,0.0000925658,0.000011671631,0.0004204392,0.0003855068,0.00033818823],"category_scores_gemma":[0.40549225,0.00015313331,0.00092811364,0.00011541222,0.00016699712,0.0002878493,0.000036837526,0.0004665098,0.00043120084],"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":[0.0006984148,0.00017832509,0.6527823,0.00009039943,0.00019952738,0.000006633736,0.00006214196,0.00036761895,4.176922e-7,0.20295446,0.1396947,0.0029650673],"study_design_scores_gemma":[0.0014888108,0.00053159177,0.12798259,0.00004773771,0.000010496401,0.0000671224,0.00009445666,0.0014421392,2.450985e-7,0.1303528,0.7378542,0.00012783152],"about_ca_topic_score_codex":0.000049156017,"about_ca_topic_score_gemma":0.000017544513,"teacher_disagreement_score":0.5981595,"about_ca_system_score_codex":0.00015256318,"about_ca_system_score_gemma":0.00036409212,"threshold_uncertainty_score":0.76721567},"labels":[],"label_agreement":null},{"id":"W2071654623","doi":"10.1016/s0895-4356(02)00446-8","title":"In the dark The reporting of blinding status in randomized controlled trials","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":176,"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; McMaster University","funders":"","keywords":"Blinding; Randomized controlled trial; Medicine; MEDLINE; Randomization; Alternative medicine; Family medicine; Double blind; Clinical trial; Surgery; Internal medicine; Placebo; Pathology","score_opus":0.962672989704361,"score_gpt":0.7217179844100274,"score_spread":0.24095500529433356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071654623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8836141,0.014714527,0.012060087,0.074941486,0.002591072,0.0029874027,0.0000022523182,8.977821e-7,0.009088171],"genre_scores_gemma":[0.99062234,0.0018324035,0.0029505505,0.003618483,0.00048101,0.000023036826,1.444044e-7,0.0000042278793,0.00046778002],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.008922657,0.68802,0.2994509,0.00046485607,0.0027370742,0.0004045004],"domain_scores_gemma":[0.0026451799,0.7354071,0.25974494,0.0013215889,0.0007826697,0.000098490185],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.98579574,0.00021287105,0.07396099,0.00053261744,0.00004952447,0.00007446422,0.0018744548,0.00022981717,0.0029572286],"category_scores_gemma":[0.9969335,0.00005046146,0.019508319,0.00097251195,0.00035489723,0.00013674196,0.00006562017,0.0011492531,0.00005423681],"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":[0.026876006,0.00045122317,0.8205263,0.00003104522,0.002311708,0.00012639689,0.0018229695,0.002452042,0.000008225308,0.012599752,0.10265725,0.030137083],"study_design_scores_gemma":[0.35717362,0.00046944368,0.11262639,0.00042793652,0.0028781018,0.00029990726,0.003347334,0.06554173,0.0000013438691,0.42431334,0.032671846,0.00024902067],"about_ca_topic_score_codex":0.000024524019,"about_ca_topic_score_gemma":0.000031065654,"teacher_disagreement_score":0.7078999,"about_ca_system_score_codex":0.00001543831,"about_ca_system_score_gemma":0.00011632141,"threshold_uncertainty_score":0.9979542},"labels":[],"label_agreement":null},{"id":"W2071708073","doi":"10.1016/j.jclinepi.2013.10.006","title":"Scientific reporting is suboptimal for aspects that characterize genetic risk prediction studies: a review of published articles based on the Genetic RIsk Prediction Studies statement","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"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":"Statement (logic); Predictive modelling; Computer science; Risk assessment; Identification (biology); Transparency (behavior); Data extraction; Medicine; MEDLINE; Actuarial science; Data mining; Statistics; Machine learning; Biology; Mathematics","score_opus":0.36115718878274405,"score_gpt":0.5050026682541758,"score_spread":0.14384547947143178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071708073","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":[0.0136459395,0.96979976,0.009163829,0.0022786132,0.0030204228,0.0015676345,0.00050042913,0.000010023314,0.000013356122],"genre_scores_gemma":[0.0025573573,0.9833263,0.010290318,0.0015993798,0.001725813,0.00023623597,0.00015804403,0.000052577976,0.00005392987],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96513516,0.0134914825,0.019089906,0.0011413987,0.0004458145,0.0006962374],"domain_scores_gemma":[0.91511804,0.022822352,0.058368035,0.0013090285,0.0021319296,0.00025064105],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09856091,0.0005929158,0.007586655,0.00021864408,0.00035404201,0.000025749183,0.0006449553,0.00082609477,0.000034020974],"category_scores_gemma":[0.40185893,0.0003471912,0.00313149,0.00028116573,0.0008092627,0.0000134784605,0.00021710104,0.0010947275,0.000004561166],"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":[0.0003933791,0.00064423407,0.103718884,0.03577089,0.009940908,0.000009760949,0.000101653306,0.0012565264,0.000013624673,0.00003360027,0.18355593,0.6645606],"study_design_scores_gemma":[0.001576828,0.0066643422,0.06464162,0.025858382,0.008360336,0.000101176905,0.00014437146,0.0028806443,0.000013605015,0.002727788,0.88648593,0.00054497377],"about_ca_topic_score_codex":0.000007654805,"about_ca_topic_score_gemma":0.000008547736,"teacher_disagreement_score":0.70293,"about_ca_system_score_codex":0.00012634844,"about_ca_system_score_gemma":0.00085083605,"threshold_uncertainty_score":0.999898},"labels":[],"label_agreement":null},{"id":"W2071765390","doi":"10.1016/j.jclinepi.2009.04.010","title":"Correlation between serial tests made disease probability estimates erroneous","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"University of Ottawa; Children’s Health Research Institute; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Statistics; Correlation; Medicine; Mathematics","score_opus":0.7797870899597635,"score_gpt":0.665207925896476,"score_spread":0.1145791640632875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071765390","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":[0.38915542,0.00014540865,0.5876548,0.017838841,0.0040594665,0.00062420894,0.00005303915,0.000086314554,0.00038246613],"genre_scores_gemma":[0.27359432,0.000057563317,0.72118783,0.001221472,0.003870636,0.0000028625625,0.000002247778,0.000019335037,0.00004375336],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736201,0.013738571,0.011198758,0.00048936513,0.00040666075,0.00054653187],"domain_scores_gemma":[0.2750745,0.7151675,0.007273391,0.00071336434,0.0005515361,0.0012196649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0753423,0.00030355217,0.0046634157,0.00008424333,0.00007820352,0.0000149425505,0.0004628705,0.000705832,0.00024059386],"category_scores_gemma":[0.9380143,0.00021559426,0.001118175,0.00016058914,0.0005753135,0.00013314988,0.00008115934,0.0017296574,0.00004178761],"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":[0.0036728715,0.0014640895,0.7479676,0.00014123887,0.0002831498,0.00017713882,0.000027863989,0.00062200095,0.000015207547,0.11943402,0.010060905,0.11613391],"study_design_scores_gemma":[0.001023009,0.0010841604,0.41272235,0.00009421719,0.0002883722,0.000022186681,0.0000015100782,0.00086361077,0.0000026744167,0.5836182,0.00016280427,0.00011685211],"about_ca_topic_score_codex":0.0000024213057,"about_ca_topic_score_gemma":9.0571996e-7,"teacher_disagreement_score":0.86267203,"about_ca_system_score_codex":0.000069246824,"about_ca_system_score_gemma":0.00032272228,"threshold_uncertainty_score":0.95212966},"labels":[],"label_agreement":null},{"id":"W2071773687","doi":"10.1016/j.jclinepi.2013.12.007","title":"A new model of comorbidity and multimorbidity that disaggregates risk, responsiveness, and vulnerability","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","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":"University of Ottawa","keywords":"Comorbidity; Vulnerability (computing); Multimorbidity; Medicine; Internal medicine; Computer science; Computer security","score_opus":0.36424868403644006,"score_gpt":0.5062148222227149,"score_spread":0.1419661381862748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071773687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96897155,0.001017468,0.023378473,0.0058815083,0.00026784572,0.00016029351,0.000009992221,0.000013189083,0.0002996534],"genre_scores_gemma":[0.98060817,0.0042732093,0.014027202,0.00065942376,0.0003502046,9.856599e-7,0.0000024263115,0.000009735602,0.00006865147],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99374616,0.003346693,0.0022063984,0.0002940823,0.00018080098,0.00022586375],"domain_scores_gemma":[0.9697999,0.02650475,0.002568517,0.0003960672,0.00018735597,0.0005434441],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01997936,0.00016529909,0.0022425982,0.0000779913,0.000046615158,0.0000056528193,0.00012746363,0.00021323307,0.000039893053],"category_scores_gemma":[0.08812253,0.0001144984,0.00034036092,0.000053676733,0.0007725384,0.00012277425,0.00014346857,0.000743964,0.0000014238404],"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":[0.0022620622,0.00021454268,0.95801216,0.00023502205,0.00019842225,0.000008501374,0.000034496938,0.00067467,0.000026240634,0.0026058874,0.004277452,0.031450536],"study_design_scores_gemma":[0.0036344188,0.0009395224,0.88450927,0.00016199226,0.0004067792,0.000035392113,0.0000437096,0.053242493,0.000019936713,0.055386778,0.0015307802,0.00008895355],"about_ca_topic_score_codex":0.00017841534,"about_ca_topic_score_gemma":0.000033024295,"teacher_disagreement_score":0.07350292,"about_ca_system_score_codex":0.000022654762,"about_ca_system_score_gemma":0.00030356308,"threshold_uncertainty_score":0.9195586},"labels":[],"label_agreement":null},{"id":"W2071921759","doi":"10.1016/j.jclinepi.2009.01.024","title":"The minimal detectable change cannot reliably replace the minimal important difference","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":352,"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; University of Toronto; SickKids Foundation; Hospital for Sick Children; St. Michael's Hospital; McMaster University","funders":"","keywords":"Receiver operating characteristic; Minimal clinically important difference; Quality of life (healthcare); Medicine; Reliability (semiconductor); Index (typography); Standard error; Statistics; Mathematics; Surgery; Computer science","score_opus":0.0990319098299401,"score_gpt":0.4039044978609946,"score_spread":0.3048725880310545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071921759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786291,0.003272268,0.00021126964,0.016228685,0.0011089233,0.00021731763,0.000010386191,0.0000068786762,0.0003151486],"genre_scores_gemma":[0.9816379,0.002809119,0.00068867544,0.011195571,0.0030998492,0.000012067176,0.0000046906257,0.000017394794,0.00053472637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99259335,0.002783078,0.003421824,0.00037435774,0.0002142045,0.0006131753],"domain_scores_gemma":[0.9921302,0.0037643546,0.002709521,0.000742005,0.00030977602,0.000344113],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016536796,0.00024038176,0.0008894635,0.000028801725,0.00024462285,0.000019880721,0.0008764255,0.0004193481,0.000018245868],"category_scores_gemma":[0.043140452,0.00012337453,0.0007166431,0.000072042756,0.0004882959,0.000009059667,0.00012727658,0.0008097567,0.000009906519],"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":[0.019105162,0.00054799893,0.7906461,0.000034385543,0.00059321197,0.00084957905,0.00014575351,0.00009420441,0.0118314065,0.0034148463,0.106959745,0.06577764],"study_design_scores_gemma":[0.0010158912,0.0019480849,0.9182873,0.00002833372,0.00007496898,0.00023731339,0.00006238673,0.0002949336,0.0002555355,0.0022163794,0.075397454,0.00018143287],"about_ca_topic_score_codex":0.000015226696,"about_ca_topic_score_gemma":0.0000787387,"teacher_disagreement_score":0.12764122,"about_ca_system_score_codex":0.000019810423,"about_ca_system_score_gemma":0.00040046815,"threshold_uncertainty_score":0.96491957},"labels":[],"label_agreement":null},{"id":"W2072269232","doi":"10.1016/s0895-4356(03)00122-7","title":"Classification systems for upper-limb musculoskeletal disorders in workers:","year":2003,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Institute for Work & Health; University of Toronto; McMaster University","funders":"Medical Research Council Canada","keywords":"Medicine; Upper limb; Musculoskeletal disorder; Muscle disorder; Physical medicine and rehabilitation; Physical therapy; Computer science; Human factors and ergonomics; Poison control; Medical emergency; Internal medicine","score_opus":0.243772639733207,"score_gpt":0.5351056345878177,"score_spread":0.29133299485461067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072269232","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":[0.00033457627,0.9880393,0.002976006,0.0018408519,0.00394914,0.0021534923,0.000007412453,0.000011900736,0.00068729045],"genre_scores_gemma":[0.0002789164,0.9937342,0.0035087925,0.00021284002,0.001657937,0.00012360523,0.00006590494,0.00006141641,0.00035641037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.976587,0.010628839,0.011457905,0.00055538444,0.00025624945,0.00051462464],"domain_scores_gemma":[0.9279735,0.06384692,0.0069532422,0.0005009838,0.00030743843,0.00041791063],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04051791,0.00044607083,0.0102560455,0.0006237862,0.000039271366,0.0000076160113,0.0002703926,0.0018591011,0.000029267503],"category_scores_gemma":[0.102743484,0.00028080237,0.006619325,0.00036140435,0.0003623803,0.000085403604,0.000023097631,0.0021489528,0.0000263751],"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":[0.0002315384,0.00058830745,0.022145724,0.04793053,0.0004908498,0.000002988011,0.000008668788,0.000017121418,7.793576e-8,0.002081389,0.0044672578,0.9220356],"study_design_scores_gemma":[0.0016474453,0.0025078857,0.023750493,0.01836995,0.0009180541,0.00006287843,0.000106331485,0.00019324855,7.3581935e-10,0.0010336253,0.9511756,0.0002344902],"about_ca_topic_score_codex":0.000012473569,"about_ca_topic_score_gemma":0.000008909904,"teacher_disagreement_score":0.9467083,"about_ca_system_score_codex":0.00022035903,"about_ca_system_score_gemma":0.0009877991,"threshold_uncertainty_score":0.9999644},"labels":[],"label_agreement":null},{"id":"W2072396417","doi":"10.1016/j.jclinepi.2010.01.006","title":"Reflections on the minimal important difference: research is the ultimate goal, not the anchor","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Goal setting; Psychology; Process management; Computer science; Medicine; Engineering; Social psychology","score_opus":0.7779179441530263,"score_gpt":0.7123470799961854,"score_spread":0.06557086415684088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072396417","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":[0.41177276,0.00007125252,0.00009219184,0.57495254,0.0015528816,0.00039707083,0.0000065653276,0.000017323346,0.011137387],"genre_scores_gemma":[0.9776796,0.0023767457,0.0010777138,0.0137031935,0.0037031062,0.0000448102,2.3189817e-7,0.000015274694,0.0013992848],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9685466,0.025338113,0.003375023,0.0003468647,0.0013911758,0.001002211],"domain_scores_gemma":[0.75807136,0.2380356,0.0016060646,0.00087594916,0.0010831679,0.0003278677],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.25246158,0.00014381533,0.00084483327,0.00012547354,0.00196889,0.00008836613,0.0028686868,0.00056120765,0.00076730934],"category_scores_gemma":[0.37164924,0.0000545698,0.0006546778,0.0006155934,0.00622067,0.00007949763,0.00025681304,0.008973207,0.0000974677],"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":[0.0007920246,0.00039871308,0.059299286,0.0000056953922,0.0001609011,0.000037909627,0.0032414773,0.0000036147776,0.0012599413,0.4255735,0.4872276,0.02199935],"study_design_scores_gemma":[0.00031440682,0.0011642473,0.23942752,0.000047819485,0.000030152496,0.000050145438,0.0038226862,0.00030197707,0.00013226345,0.240684,0.51389533,0.0001294431],"about_ca_topic_score_codex":0.00081151817,"about_ca_topic_score_gemma":0.0016639435,"teacher_disagreement_score":0.5659069,"about_ca_system_score_codex":0.000060886487,"about_ca_system_score_gemma":0.0010123693,"threshold_uncertainty_score":0.9993304},"labels":[],"label_agreement":null},{"id":"W2073015584","doi":"10.1016/s0895-4356(03)00246-4","title":"Validation of diagnostic codes within medical services claims","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":443,"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":"Medical Research Council","keywords":"Medicine; Medical diagnosis; Gold standard (test); Diagnosis code; Comorbidity; Medical record; COPD; Diabetes mellitus; Disease; Emergency medicine; Intensive care medicine; Internal medicine; Pathology; Environmental health","score_opus":0.584328309000388,"score_gpt":0.639146006923215,"score_spread":0.05481769792282698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073015584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93796855,0.000251323,0.019117165,0.037409775,0.0041083912,0.00020653658,0.0000050688723,0.000018955447,0.00091421575],"genre_scores_gemma":[0.97058964,0.0019494988,0.005575176,0.019921754,0.0019073314,0.0000061232786,0.000011596841,0.000008853902,0.000030026345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9815,0.0066258097,0.010774629,0.00013697064,0.00056476804,0.0003978071],"domain_scores_gemma":[0.8289063,0.15854858,0.010504526,0.0002636459,0.0008024225,0.0009745488],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07874444,0.00011601818,0.001911865,0.00012271215,0.0001763337,0.0000012676843,0.00035914022,0.00095237483,0.00056178955],"category_scores_gemma":[0.30456498,0.00007550346,0.00027256063,0.00013398862,0.00026322991,0.00016242151,0.00006882955,0.0025442678,0.00012990742],"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":[0.00060132233,0.00031247555,0.93227243,0.0018803854,0.000110925954,0.000023759896,0.0022838598,0.0018325694,0.0000053224007,0.044570368,0.0049352525,0.011171336],"study_design_scores_gemma":[0.011085164,0.003739743,0.6839794,0.009243315,0.00020325388,0.000110435234,0.0021789647,0.0034897418,0.00006249627,0.2655158,0.020092446,0.00029927964],"about_ca_topic_score_codex":0.00015000747,"about_ca_topic_score_gemma":0.00005543696,"teacher_disagreement_score":0.24829306,"about_ca_system_score_codex":0.00006501274,"about_ca_system_score_gemma":0.0017757668,"threshold_uncertainty_score":0.99975693},"labels":[],"label_agreement":null},{"id":"W2073056556","doi":"10.1016/j.jclinepi.2005.09.005","title":"“Precision” and “Accuracy”: Two Terms That Are Neither","year":2006,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":194,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; McMaster University; University of Toronto","funders":"","keywords":"Reliability (semiconductor); Conceptualization; Inter-rater reliability; Scale (ratio); Test (biology); Computer science; Synonym (taxonomy); Validity; Criterion validity; Psychology; Process (computing); Cognitive psychology; Psychometrics; Artificial intelligence; Statistics; Mathematics; Rating scale; Construct validity; Geography","score_opus":0.9346514191644626,"score_gpt":0.7216304917470712,"score_spread":0.21302092741739143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073056556","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":[0.00020844783,0.98062146,0.009252972,0.0012397327,0.0060287,0.00022935623,0.000019652829,0.000014559291,0.0023851444],"genre_scores_gemma":[0.00003590116,0.9553931,0.039566338,0.0011648166,0.002940106,0.0000036015952,0.0000016442411,0.000033583863,0.0008609406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9344106,0.04206487,0.020427722,0.0011825953,0.0011824168,0.0007318214],"domain_scores_gemma":[0.14958537,0.8122269,0.036053997,0.0011204588,0.0004868119,0.0005264995],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24545562,0.00056667026,0.017319467,0.0011259684,0.00012160122,0.00010689382,0.002515462,0.0012604299,0.00029993005],"category_scores_gemma":[0.92399764,0.00027347775,0.0034537567,0.0011742841,0.000592939,0.00024231094,0.0005891158,0.0031848107,0.000101097576],"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":[0.000025848509,0.000050454983,0.06419694,0.00014528782,0.000105130406,0.00006961007,0.0000021085066,0.000006875588,4.0569352e-9,0.00018231837,0.046663705,0.8885517],"study_design_scores_gemma":[0.00047517786,0.00025902045,0.033420056,0.0026172763,0.00026312965,0.0008479923,0.000015749245,0.000031774827,7.143739e-9,0.08696296,0.8748732,0.00023363227],"about_ca_topic_score_codex":0.000017885854,"about_ca_topic_score_gemma":0.000006142411,"teacher_disagreement_score":0.88831806,"about_ca_system_score_codex":0.000038542534,"about_ca_system_score_gemma":0.0002926205,"threshold_uncertainty_score":0.99997175},"labels":[],"label_agreement":null},{"id":"W2073059260","doi":"10.1016/j.jclinepi.2014.01.006","title":"Applying Grading of Recommendations Assessment, Development and Evaluation (GRADE) to diagnostic tests was challenging but doable","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":164,"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":"European Commission","keywords":"Grading (engineering); Operationalization; Quality of evidence; Test (biology); Systematic review; Publication bias; Perspective (graphical); Evidence-based medicine; MEDLINE; Medicine; Medical physics; Psychology; Meta-analysis; Computer science; Alternative medicine; Artificial intelligence; Pathology","score_opus":0.9248872393294887,"score_gpt":0.7005075891732893,"score_spread":0.22437965015619943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073059260","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":[0.6105593,0.0005623284,0.36945185,0.016474811,0.0010297765,0.0006800773,0.0000014473295,0.0000020037482,0.0012384057],"genre_scores_gemma":[0.8300625,0.00022437528,0.16828065,0.0010450959,0.00023458291,0.000038910843,0.0000017225086,0.0000062117115,0.00010597235],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.87134147,0.0781678,0.046307594,0.0008604177,0.0028934504,0.00042927268],"domain_scores_gemma":[0.39076057,0.57238936,0.03252717,0.001371946,0.0023501297,0.00060084934],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5984932,0.00018060693,0.006379001,0.00043857456,0.00013578172,0.000060299517,0.0007210885,0.00014099835,0.00061535666],"category_scores_gemma":[0.76035666,0.00009435984,0.0010072144,0.00037949308,0.00006359112,0.00017722062,0.00012768795,0.00041673132,0.000070013506],"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":[0.0000063165735,0.00009812089,0.442621,0.000035855668,0.00023981572,9.768706e-7,0.00013570744,0.0020704025,0.000022208518,0.0045689144,0.012185398,0.5380153],"study_design_scores_gemma":[0.00082885195,0.00040249407,0.680961,0.00038728493,0.00049138267,0.000050910203,0.0006324674,0.075659916,0.000021018473,0.071044795,0.1693057,0.00021417993],"about_ca_topic_score_codex":0.0000047052595,"about_ca_topic_score_gemma":0.000013954848,"teacher_disagreement_score":0.5378011,"about_ca_system_score_codex":0.000043282256,"about_ca_system_score_gemma":0.00018192534,"threshold_uncertainty_score":0.6737724},"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":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2073124633","doi":"10.1016/s0895-4356(99)00221-8","title":"The standard of reporting of health-related quality of life in clinical cancer trials","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"U.S. Food and Drug Administration; Cancer Care Ontario","keywords":"Checklist; Medicine; Consolidated Standards of Reporting Trials; Quality of life (healthcare); Randomized controlled trial; Guideline; Clinical trial; MEDLINE; Gold standard (test); Physical therapy; Family medicine; Surgery; Psychology; Pathology; Nursing; Internal medicine","score_opus":0.6365808727920407,"score_gpt":0.640911842689951,"score_spread":0.004330969897910375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073124633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9565068,0.01486681,0.00009582467,0.026330365,0.0016498631,0.00022558274,0.000020929745,0.0000033303854,0.0003004838],"genre_scores_gemma":[0.97422516,0.023070693,0.00037146572,0.0017054431,0.0005345088,0.0000024315761,0.0000015977313,0.00001079,0.00007788013],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.81486744,0.052361052,0.13084199,0.00046340108,0.0008382403,0.0006278932],"domain_scores_gemma":[0.6805343,0.19486281,0.12152082,0.0009009741,0.0015455578,0.00063555007],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39648402,0.00013538063,0.011747551,0.00008244437,0.000027361617,0.0000010883654,0.00022080743,0.00048254553,0.00040637844],"category_scores_gemma":[0.539162,0.000076697055,0.002154088,0.00025248853,0.0007370988,0.000035232362,0.000031945525,0.0014357249,6.7813767e-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":[0.013454261,0.00020067273,0.8143739,0.00019141454,0.0003554338,0.0000066537796,0.00012880853,0.000080873055,0.000008833436,0.00034405242,0.0014419351,0.16941318],"study_design_scores_gemma":[0.0052585984,0.0030556465,0.98156506,0.00089725666,0.00012474904,0.000018866605,0.00027896772,0.00003751209,0.000019581445,0.003337104,0.0053443937,0.00006224826],"about_ca_topic_score_codex":0.0035155863,"about_ca_topic_score_gemma":0.0022797827,"teacher_disagreement_score":0.16935092,"about_ca_system_score_codex":0.000057792862,"about_ca_system_score_gemma":0.002661186,"threshold_uncertainty_score":0.80303913},"labels":[],"label_agreement":null},{"id":"W2073457340","doi":"10.1016/j.jclinepi.2008.09.006","title":"Conference abstracts of a new oncology drug do not always lead to full publication: Proceed with caution","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; McMaster University","funders":"","keywords":"Generalizability theory; Medicine; Publication bias; Confidence interval; Population; Odds ratio; Family medicine; Internal medicine; Oncology; Psychology; Environmental health","score_opus":0.9092971426391641,"score_gpt":0.6648259383659416,"score_spread":0.24447120427322244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073457340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5828815,0.00046935273,0.11723984,0.2849915,0.0007507496,0.00071715907,0.000005376753,0.000005285814,0.012939221],"genre_scores_gemma":[0.9283537,0.00009840229,0.05902345,0.0094777625,0.000522617,0.000003078568,0.0000014481056,0.0000050227573,0.0025145032],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.90606666,0.03067092,0.05870434,0.0010671049,0.0029734548,0.0005175463],"domain_scores_gemma":[0.71273965,0.14766622,0.11769914,0.0039183097,0.015937768,0.0020389426],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3952619,0.0002467676,0.010751304,0.00041132694,0.000050238552,0.000091055175,0.0018632029,0.00031876384,0.0019520675],"category_scores_gemma":[0.5777281,0.00010844263,0.0020044912,0.0008664517,0.00017865456,0.0003122846,0.00005808241,0.00074473885,0.0006210978],"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":[0.0010497554,0.0005201518,0.04279341,0.000029186478,0.00037464025,0.000019380672,0.00058371865,0.0012970517,0.00017480584,0.022645444,0.58866984,0.3418426],"study_design_scores_gemma":[0.00126431,0.004245013,0.5567681,0.00014802306,0.00035370336,0.0003275761,0.00036462102,0.0013281996,0.00003657256,0.055580314,0.37937352,0.00021003667],"about_ca_topic_score_codex":0.000015223132,"about_ca_topic_score_gemma":0.00005634913,"teacher_disagreement_score":0.5139747,"about_ca_system_score_codex":0.000042397587,"about_ca_system_score_gemma":0.001146237,"threshold_uncertainty_score":0.99896026},"labels":[],"label_agreement":null},{"id":"W2073644162","doi":"10.1016/j.jclinepi.2008.10.009","title":"AMSTAR is a reliable and valid measurement tool to assess the methodological quality of systematic reviews","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1770,"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 Ottawa; Institute of Population and Public Health","funders":"","keywords":"Intraclass correlation; Inter-rater reliability; Kappa; Medicine; Construct validity; Reliability (semiconductor); Systematic review; Confidence interval; Criterion validity; Cohen's kappa; Medical physics; Statistics; Psychometrics; Mathematics; MEDLINE; Clinical psychology; Rating scale; Internal medicine; Biology","score_opus":0.9935874369043814,"score_gpt":0.7700991734328491,"score_spread":0.2234882634715324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073644162","genre_codex":"methods","genre_gemma":"empirical","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":[0.2874009,0.03716433,0.5720119,0.09485326,0.0019997444,0.004710452,0.000007853098,0.000005065693,0.0018465266],"genre_scores_gemma":[0.5850248,0.0054814667,0.3541916,0.05349223,0.00074433547,0.000042772674,3.5474406e-7,0.00001292426,0.0010095596],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.21986432,0.5956446,0.17417563,0.0014995525,0.008123549,0.00069234567],"domain_scores_gemma":[0.14164108,0.6907246,0.14972372,0.007809141,0.0090922145,0.0010092378],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9430243,0.00030588513,0.028831944,0.00018144466,0.00008595777,0.000088781126,0.0023206784,0.00027887884,0.0008696379],"category_scores_gemma":[0.947829,0.000095892836,0.0062946966,0.0006941587,0.00017092701,0.00013010994,0.00013937664,0.0007083155,0.00019319837],"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":[0.00053728215,0.0007703012,0.3044684,0.0073001226,0.0019131321,0.000016524622,0.00069618627,0.00040962934,0.00031268492,0.039707817,0.583803,0.060064934],"study_design_scores_gemma":[0.0008440074,0.0023250566,0.5900339,0.004001092,0.0018107531,0.00015525521,0.00048224136,0.0013644072,0.000020574458,0.25841984,0.14016216,0.00038072857],"about_ca_topic_score_codex":0.0000068152226,"about_ca_topic_score_gemma":0.0000037991128,"teacher_disagreement_score":0.44364083,"about_ca_system_score_codex":0.000032379226,"about_ca_system_score_gemma":0.00013115851,"threshold_uncertainty_score":0.98558605},"labels":[],"label_agreement":null},{"id":"W2074062633","doi":"10.1016/j.jclinepi.2009.04.008","title":"A statistical method was used for the meta-analysis of tests for latent TB in the absence of a gold standard, combining random-effect and latent-class methods to estimate test accuracy","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":42,"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 for Advancing Health Outcomes; University of British Columbia; BC Centre for Disease Control; Vancouver Coastal Health","funders":"","keywords":"Latent tuberculosis; Concordance; Latent class model; Confidence interval; Gold standard (test); Tuberculin; Medicine; Meta-analysis; Statistics; Tuberculosis; Internal medicine; Mathematics; Pathology; Mycobacterium tuberculosis","score_opus":0.525848515645023,"score_gpt":0.6663886570271714,"score_spread":0.14054014138214843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074062633","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":[0.00011419993,0.6432593,0.33711424,0.015079255,0.00016455766,0.0038211928,0.00043311596,0.0000052311657,0.000008932452],"genre_scores_gemma":[0.0004451979,0.64461297,0.35214248,0.0021823493,0.00018200811,0.0003360687,0.000043922668,0.000036813777,0.000018220413],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9417067,0.042482246,0.013484634,0.000802217,0.0005394716,0.0009847189],"domain_scores_gemma":[0.28781238,0.7042145,0.0061516687,0.00071455346,0.0006650992,0.00044174967],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24079694,0.0006007183,0.03139677,0.00072695507,0.00006889445,0.0000133042995,0.00086948887,0.0008360554,0.000031266052],"category_scores_gemma":[0.7282056,0.0002444087,0.008598147,0.00091162336,0.00060574873,0.00005533129,0.00014603903,0.00222569,7.776053e-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":[0.006234827,0.00053356343,0.008507805,0.005910268,0.10422723,0.000051668674,0.00007922541,0.0009728153,0.0000090296035,0.0023688746,0.0051924237,0.86591226],"study_design_scores_gemma":[0.013469917,0.02862174,0.020782841,0.0029455281,0.5766587,0.0006239765,0.00003619671,0.034166887,0.0000043103273,0.008351244,0.31376904,0.00056961126],"about_ca_topic_score_codex":0.000072325216,"about_ca_topic_score_gemma":0.00006337044,"teacher_disagreement_score":0.8653427,"about_ca_system_score_codex":0.00007508104,"about_ca_system_score_gemma":0.0006635171,"threshold_uncertainty_score":0.99666977},"labels":[],"label_agreement":null},{"id":"W2074163347","doi":"10.1016/j.jclinepi.2007.05.010","title":"A review of five cardiology journals found that observer variability of measured variables was infrequently reported","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Medicine; Categorical variable; Continuous variable; Cohen's kappa; Kappa; Statistic; Statistics; Internal medicine; Mathematics","score_opus":0.8734374309110979,"score_gpt":0.6395238285885412,"score_spread":0.23391360232255676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074163347","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":[0.0001583807,0.98385376,0.007476886,0.0009777028,0.005018267,0.0011834101,0.00007293357,0.00000775968,0.0012508915],"genre_scores_gemma":[0.00012741343,0.98945516,0.0074903965,0.0015479543,0.0012205332,0.000013271163,0.000012010136,0.000033026572,0.00010020912],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7620946,0.13426879,0.09404967,0.0022393684,0.0058751763,0.0014723996],"domain_scores_gemma":[0.4292139,0.42355308,0.12744696,0.0048698573,0.013718341,0.0011978442],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.6338015,0.00087895093,0.03615671,0.0007922468,0.00009600933,0.000025922332,0.0039740126,0.0024654302,0.0010737982],"category_scores_gemma":[0.795835,0.0004940671,0.012314747,0.0015768822,0.0016660796,0.00035102598,0.0005259726,0.0040575885,0.000028896244],"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":[0.00040938315,0.00088168046,0.06380491,0.05163168,0.0056545585,0.00016554711,0.000026762338,0.00017021624,0.0000014474984,0.00092402636,0.057157546,0.81917226],"study_design_scores_gemma":[0.0006606966,0.00082563824,0.008996502,0.08758862,0.0033142057,0.0006554328,0.000020721742,0.000008341111,3.8443224e-7,0.057756606,0.8398267,0.00034616774],"about_ca_topic_score_codex":0.000054239827,"about_ca_topic_score_gemma":0.0000094327415,"teacher_disagreement_score":0.8188261,"about_ca_system_score_codex":0.00029270706,"about_ca_system_score_gemma":0.0036756834,"threshold_uncertainty_score":0.99983937},"labels":[],"label_agreement":null},{"id":"W2074418432","doi":"10.1016/j.jclinepi.2004.05.003","title":"Health-related quality of life (HRQL) scores reported from parents and their children with chronic illness differed depending on utility elicitation method","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Childhood Cancer Survivors' Quality of Life","field":"Medicine","cited_by":71,"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; SickKids Foundation","funders":"","keywords":"Medicine; Health Utilities Index; Quality of life (healthcare); Health related quality of life; Visual analogue scale; El Niño; Quality of Life Research; Pediatrics; Physical therapy; Internal medicine; Public health; Pathology","score_opus":0.27652637939021935,"score_gpt":0.5149240773271093,"score_spread":0.23839769793688997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074418432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95904714,0.002185534,0.019151561,0.018584793,0.00051998836,0.00042438123,0.000044076027,0.00002583382,0.000016717471],"genre_scores_gemma":[0.98741513,0.0007841052,0.007427259,0.0037471468,0.0005384854,0.0000033795861,0.000055520955,0.000026723426,0.000002250708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.978973,0.009856393,0.009708718,0.0005880001,0.00045949593,0.0004144496],"domain_scores_gemma":[0.95739084,0.02972836,0.011175035,0.00060371123,0.00034764738,0.0007543922],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035317883,0.0003117855,0.0054138405,0.00015526915,0.000099913734,0.0000054402453,0.00020421387,0.00044151218,0.000033831388],"category_scores_gemma":[0.08879569,0.00019944126,0.0005763082,0.00020040537,0.00048233118,0.00010561653,0.00006128118,0.0014669053,0.000001575857],"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":[0.005227575,0.00063187507,0.96461433,0.00012752587,0.0015050424,0.000007447619,0.0006883685,0.00023342745,0.000043243293,0.00034506232,0.000059490758,0.026516614],"study_design_scores_gemma":[0.010117671,0.003460387,0.9711005,0.0010653315,0.00015365964,0.00012743843,0.00022107459,0.00015327291,0.00009104285,0.01332733,0.000015212871,0.00016709522],"about_ca_topic_score_codex":0.007243656,"about_ca_topic_score_gemma":0.0012480087,"teacher_disagreement_score":0.05347781,"about_ca_system_score_codex":0.00016792426,"about_ca_system_score_gemma":0.0012323743,"threshold_uncertainty_score":0.9993672},"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":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2074652774","doi":"10.1016/j.jclinepi.2006.12.011","title":"Assisted self-report of health-services use showed excellent reliability in a longitudinal study of older adults","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Technology Use by Older Adults","field":"Social Sciences","cited_by":29,"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 and Social Services Centre University Institute of Geriatrics of Sherbrooke; Université de Sherbrooke","funders":"","keywords":"Reliability (semiconductor); Longitudinal study; Gerontology; Medicine; Psychology","score_opus":0.19751735333400097,"score_gpt":0.5066897988498186,"score_spread":0.3091724455158176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074652774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920477,0.0003341698,0.0005676795,0.0049532754,0.0013312569,0.0006547269,0.0000022311795,0.000035614423,0.00007329849],"genre_scores_gemma":[0.99218965,0.00041725184,0.0068216124,0.0003179428,0.00021743908,0.000003645126,9.999495e-7,0.0000118967,0.00001955156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9717037,0.011049337,0.015047392,0.00063291745,0.0007436514,0.0008229874],"domain_scores_gemma":[0.9528847,0.032899354,0.011821137,0.00065283256,0.0013830743,0.0003589274],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11771283,0.00020898142,0.0036504103,0.00039197493,0.00009892766,0.0000042563615,0.0007830942,0.00073914597,0.00003859613],"category_scores_gemma":[0.07505997,0.0001680995,0.0005395509,0.0006250569,0.0007810283,0.00025024547,0.00015931283,0.0012718174,0.0000017302866],"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":[0.0007483599,0.0050282753,0.97866863,0.000111210444,0.000136602,0.00017502638,0.0062702904,0.00002247466,0.0000010863706,0.00016248394,0.00020208147,0.008473473],"study_design_scores_gemma":[0.0031739757,0.0019527021,0.9844467,0.00038188955,0.000055574772,0.000044509055,0.008254918,0.000025159656,0.000003098077,0.00092264387,0.0006292934,0.000109559536],"about_ca_topic_score_codex":0.011905499,"about_ca_topic_score_gemma":0.0345309,"teacher_disagreement_score":0.042652857,"about_ca_system_score_codex":0.00017003751,"about_ca_system_score_gemma":0.0006944158,"threshold_uncertainty_score":0.9946743},"labels":[],"label_agreement":null},{"id":"W2075852660","doi":"10.1016/s0895-4356(02)00602-9","title":"The metaphor of patients as customers Implications for measuring satisfaction","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":61,"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. Michael's Hospital","funders":"","keywords":"Metaphor; Embodied cognition; Customer satisfaction; Outcome (game theory); Patient satisfaction; Possession (linguistics); Meaning (existential); Psychology; Object (grammar); Social psychology; Medicine; Marketing; Nursing; Psychotherapist; Business; Epistemology; Economics; Linguistics; Philosophy","score_opus":0.527901506446111,"score_gpt":0.6122262870522767,"score_spread":0.08432478060616566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075852660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745954,0.00049197354,0.005278943,0.009364958,0.00802694,0.0010789323,0.00004085458,0.000014318912,0.0011076318],"genre_scores_gemma":[0.9925924,0.0010839973,0.0040407144,0.0017627457,0.00031851052,0.000084261475,0.0000033928404,0.000018711817,0.000095273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98061603,0.011483559,0.0070334137,0.00020151815,0.00019213912,0.00047335337],"domain_scores_gemma":[0.874398,0.1144065,0.008591021,0.00037449237,0.0019154159,0.00031456936],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029803636,0.00012942543,0.0013563519,0.00011606974,0.0006826824,0.0000014040049,0.00020634118,0.00041674048,0.00008063278],"category_scores_gemma":[0.23886615,0.00008209713,0.00057122164,0.00016177831,0.00020540055,0.0001159206,0.000026992353,0.0012405062,0.000036273977],"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":[0.0002675447,0.00002847278,0.9476639,0.000059950256,0.00010319797,5.6018738e-8,0.00006907499,0.00005296951,0.000005453802,0.030657366,0.0043896376,0.016702376],"study_design_scores_gemma":[0.0012184347,0.00051215815,0.91848165,0.00006418366,0.00006401813,0.00000231104,0.0002445893,0.000013385249,0.0000050644835,0.030803727,0.048530564,0.000059903632],"about_ca_topic_score_codex":0.000095255375,"about_ca_topic_score_gemma":0.00010487056,"teacher_disagreement_score":0.20906252,"about_ca_system_score_codex":0.00015466961,"about_ca_system_score_gemma":0.0007761376,"threshold_uncertainty_score":0.99902135},"labels":[],"label_agreement":null},{"id":"W2075880110","doi":"10.1016/j.jclinepi.2007.11.017","title":"Cardiologists' charting varied by risk factor, and was often discordant with patient report","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","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":"Toronto Rehabilitation Institute; Institute for Clinical Evaluative Sciences; University of Ottawa; St. Michael's Hospital; Western University; University of Toronto; University Health Network; London Health Sciences Centre; York University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Risk factor; Dyslipidemia; Concordance; Body mass index; Diabetes mellitus; Medical record; Obesity; Family history; Internal medicine; Physical therapy","score_opus":0.1920818828557311,"score_gpt":0.46524021807268584,"score_spread":0.27315833521695476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075880110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92028457,0.0014422943,0.07327872,0.004114483,0.0004438083,0.00020718666,0.000006198334,0.0000137005345,0.00020902703],"genre_scores_gemma":[0.9874553,0.0048986236,0.0051628533,0.0018837926,0.00046844262,0.0000038897447,0.0000078795065,0.000012850473,0.00010637051],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9882633,0.0072680237,0.0036464236,0.00028289596,0.00024694708,0.0002923898],"domain_scores_gemma":[0.9928097,0.0030982525,0.0030623714,0.00028071966,0.00026006254,0.000488891],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025865953,0.0001395372,0.0023341875,0.000052879823,0.00010429757,0.0000019803094,0.000056053177,0.00021307387,0.00003216858],"category_scores_gemma":[0.037754294,0.00008132677,0.0006960443,0.00006692683,0.00032691206,0.0000648885,0.000035716886,0.001085914,0.000004298829],"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":[0.0003395612,0.0001761842,0.9013221,0.000045679233,0.00062044634,0.0016340767,0.00008475151,0.000018835632,0.000028935234,0.00002052651,0.0023434726,0.0933654],"study_design_scores_gemma":[0.002291935,0.003343899,0.95159537,0.00012407356,0.00023278075,0.022192769,0.000050088922,0.00008285744,0.000019418785,0.00029073015,0.01968013,0.000095959025],"about_ca_topic_score_codex":0.000039076844,"about_ca_topic_score_gemma":0.0000015076769,"teacher_disagreement_score":0.093269445,"about_ca_system_score_codex":0.00003450749,"about_ca_system_score_gemma":0.0002521481,"threshold_uncertainty_score":0.9703511},"labels":[],"label_agreement":null},{"id":"W2075888392","doi":"10.1016/j.jclinepi.2010.02.021","title":"Survival distributions impact the power of randomized placebo-phase design and parallel groups randomized clinical trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Public Health Ontario; University of Toronto; Hospital for Sick Children","funders":"","keywords":"Weibull distribution; Sample size determination; Randomized controlled trial; Placebo; Statistics; Log-normal distribution; Completely randomized design; Mathematics; Medicine; Time point; Surgery; Physics","score_opus":0.7783455377838716,"score_gpt":0.7020928746141641,"score_spread":0.07625266316970747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075888392","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09145996,0.00031491023,0.89115995,0.007345782,0.0067277183,0.0027316946,0.00010466433,0.00002264798,0.00013268943],"genre_scores_gemma":[0.2464448,0.002079305,0.74840283,0.00057786214,0.0023565593,0.000063785265,0.0000025908605,0.000042036147,0.000030228495],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.22749177,0.69920343,0.070080705,0.0009948431,0.0010665101,0.001162749],"domain_scores_gemma":[0.007885518,0.962506,0.026544811,0.0010033597,0.0010825316,0.0009777987],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.8541882,0.00053027156,0.032587986,0.00014222621,0.00014121637,0.000032123287,0.000992836,0.001547754,0.00089384307],"category_scores_gemma":[0.9950083,0.00024026394,0.010214617,0.00022404558,0.007882792,0.000117240605,0.00023051942,0.0048353546,0.000010248338],"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":[0.71879375,0.0011743247,0.0012342407,0.000025133497,0.0029804232,0.0000181041,0.000036039753,0.00001811619,0.000014381086,0.2629434,0.0049954224,0.0077666733],"study_design_scores_gemma":[0.44088918,0.00085573044,0.00072882476,0.000055407392,0.0018643613,0.000054787266,0.000017027523,0.0024462363,0.0000043080454,0.55284154,0.0001061232,0.00013643758],"about_ca_topic_score_codex":0.000013221598,"about_ca_topic_score_gemma":0.0000028213162,"teacher_disagreement_score":0.28989816,"about_ca_system_score_codex":0.000020442918,"about_ca_system_score_gemma":0.00062152796,"threshold_uncertainty_score":0.99974847},"labels":[],"label_agreement":null},{"id":"W2075949563","doi":"10.1016/j.jclinepi.2013.05.018","title":"Measuring quality of care: considering measurement frameworks and needs assessment to guide quality indicator development","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Safety and Medication Errors","field":"Health Professions","cited_by":155,"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; St. Michael's Hospital; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Stakeholder; Quality (philosophy); Conceptual framework; Process management; Quality management; Health care; Process (computing); Conceptual model; Medicine; Management science; Risk analysis (engineering); Computer science; Knowledge management; Business; Operations management; Engineering","score_opus":0.6813296236937261,"score_gpt":0.6311674996339561,"score_spread":0.05016212405976994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075949563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8621518,0.00050118833,0.10839419,0.025211599,0.0018445831,0.00065253366,0.0000029243697,0.000015516138,0.0012256817],"genre_scores_gemma":[0.9161875,0.00019616722,0.07359904,0.009620151,0.00030533475,0.000046168854,0.0000018634923,0.000011301423,0.00003243136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9740173,0.012928606,0.0115201045,0.0002707561,0.0007551002,0.0005081203],"domain_scores_gemma":[0.94628775,0.03838935,0.011432386,0.00051212683,0.0021268867,0.0012514972],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08193672,0.00017990272,0.0024188047,0.00021506644,0.00022578891,0.0000010597405,0.00028959764,0.0007762416,0.00020736273],"category_scores_gemma":[0.14555809,0.00013551791,0.00025454193,0.00014621724,0.00021707105,0.00011206223,0.00021121616,0.0025198723,0.000038008147],"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":[0.000142157,0.00012544487,0.975171,0.00035776812,0.00017398292,6.0168287e-7,0.0031518016,0.000092134775,0.000104781655,0.0025920265,0.0022321048,0.015856175],"study_design_scores_gemma":[0.001191641,0.00025305682,0.95675915,0.00064743054,0.000028752838,0.0000015298208,0.004462059,0.000012163543,0.000023850303,0.0013333425,0.03516085,0.0001261484],"about_ca_topic_score_codex":0.00017395981,"about_ca_topic_score_gemma":0.000067007204,"teacher_disagreement_score":0.06362137,"about_ca_system_score_codex":0.00035276814,"about_ca_system_score_gemma":0.0022423575,"threshold_uncertainty_score":0.99978137},"labels":[],"label_agreement":null},{"id":"W2076169192","doi":"10.1016/j.jclinepi.2009.08.012","title":"Successful high-quality knowledge translation research: three case studies","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Health Sciences Centre; University of Alberta Hospital","funders":"","keywords":"Medicine; Scopus; Psychological intervention; Audit; Randomized controlled trial; MEDLINE; Quality management; Intervention (counseling); Family medicine; Nursing; Internal medicine","score_opus":0.9949561388328916,"score_gpt":0.8944697382611576,"score_spread":0.10048640057173397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076169192","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":[0.00059253984,0.971694,0.0010612642,0.01868392,0.0053621433,0.0017033174,0.00008011732,0.000027871258,0.0007948442],"genre_scores_gemma":[0.00016219779,0.9810483,0.005159887,0.006140345,0.007154348,0.00008229517,0.000007791459,0.000038455233,0.00020639387],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.71853226,0.24316344,0.034817956,0.0008102326,0.00079457066,0.0018815539],"domain_scores_gemma":[0.22832277,0.74396574,0.021778414,0.00092351326,0.003701466,0.0013080785],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.45784464,0.00048294582,0.014952477,0.0009362806,0.0011189714,0.00000802433,0.0011253305,0.0019952578,0.00034576154],"category_scores_gemma":[0.5755604,0.0003082885,0.0017389898,0.0012449817,0.0011765343,0.00029799956,0.00024690182,0.01113635,0.00066328404],"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":[0.00005652498,0.00008372318,0.001256057,0.011317584,0.00021349694,0.00026206544,0.0007583937,6.826251e-7,7.868786e-9,0.004125948,0.037386738,0.9445388],"study_design_scores_gemma":[0.0010226781,0.00076714106,0.0011271015,0.008787142,0.00030669637,0.0005246295,0.00061930704,0.0000040904533,4.640281e-9,0.023409916,0.96321416,0.00021715515],"about_ca_topic_score_codex":0.00023636894,"about_ca_topic_score_gemma":0.0017029116,"teacher_disagreement_score":0.94432163,"about_ca_system_score_codex":0.0006642254,"about_ca_system_score_gemma":0.009296386,"threshold_uncertainty_score":0.99993694},"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":"W2078119823","doi":"10.1016/j.jclinepi.2012.02.019","title":"A survey of physicians show a one-third reduction in harmful outcomes to be a clinically important difference for statin therapy","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","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":"St. Joseph’s Healthcare Hamilton; St. Joseph's Hospital; McMaster University","funders":"Ministerul Cercetării, Inovării şi Digitalizării; McMaster University","keywords":"Medicine; Minimal clinically important difference; Statin; Physical therapy; Myocardial infarction; Internal medicine; Revascularization; Emergency medicine; Intensive care medicine; Randomized controlled trial","score_opus":0.40530651812770707,"score_gpt":0.5264035812660307,"score_spread":0.12109706313832364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078119823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97036254,0.0010285877,0.009130373,0.017679185,0.0009911599,0.000754652,0.000027894477,0.0000063606544,0.000019241159],"genre_scores_gemma":[0.96534574,0.0040434264,0.01888138,0.010583481,0.0010469633,0.000026737758,0.000009488041,0.000022271155,0.00004051619],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98724437,0.004217713,0.007411198,0.00026613154,0.0003405117,0.00052009034],"domain_scores_gemma":[0.9792216,0.015637897,0.0035691166,0.0004663168,0.0006676521,0.0004374178],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0777198,0.00018126008,0.004406083,0.00020202417,0.000024216737,0.0000023965997,0.00018155976,0.00033973408,0.000015840937],"category_scores_gemma":[0.08473557,0.000120759985,0.0013252094,0.0002727646,0.00015047399,0.00007009545,0.000034456905,0.00086747285,0.0000015514912],"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":[0.003826883,0.0013130858,0.90771663,0.000060620125,0.00043950428,0.000003512805,0.00017455236,0.000008004392,0.00016315887,0.00012695808,0.0011776299,0.084989436],"study_design_scores_gemma":[0.0042195227,0.004829928,0.9882344,0.0001596698,0.000099750905,0.0000349548,0.00008217861,0.00007251067,0.0000389751,0.0007178907,0.0014074317,0.00010278914],"about_ca_topic_score_codex":0.00052281516,"about_ca_topic_score_gemma":0.00012628095,"teacher_disagreement_score":0.08488665,"about_ca_system_score_codex":0.000041577005,"about_ca_system_score_gemma":0.00042008064,"threshold_uncertainty_score":0.9496816},"labels":[],"label_agreement":null},{"id":"W2078150295","doi":"10.1016/j.jclinepi.2006.05.004","title":"Preparing reports for publication and responding to reviewers' comments","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":38,"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; Psychology; Information retrieval; Library science; Data science; Computer science","score_opus":0.1440914190535964,"score_gpt":0.4934518736824106,"score_spread":0.3493604546288142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078150295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9548192,0.001652827,0.010505748,0.028886952,0.0009309174,0.0007228826,0.0000031158904,0.000016791455,0.0024615559],"genre_scores_gemma":[0.97139865,0.00048171086,0.013456713,0.012612265,0.0014763835,0.000016148648,0.000015866493,0.000012852385,0.0005293973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959775,0.000633815,0.0029123973,0.00019480965,0.00011009326,0.00017138773],"domain_scores_gemma":[0.9927283,0.0049752733,0.0014056,0.00023833911,0.00035950154,0.00029302266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01642164,0.000078416284,0.0012203315,0.00017945729,0.000038112044,0.0000070902856,0.000050704097,0.000098638426,0.000019020672],"category_scores_gemma":[0.07460032,0.000057222547,0.000516621,0.00011061023,0.000049527862,0.00007666726,0.000032856184,0.00018046402,0.0000021981834],"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":[0.00030805028,0.00013548511,0.8910457,0.00008388349,0.000084318046,0.0000055593705,0.0000064304827,0.000009356742,0.000042754786,0.00113919,0.086407274,0.020732],"study_design_scores_gemma":[0.0009728428,0.00066630397,0.67909163,0.00022766889,0.00020175985,0.0005491651,0.000010907042,0.00005868071,0.000017406328,0.0027000727,0.31544885,0.000054671058],"about_ca_topic_score_codex":0.0000056326403,"about_ca_topic_score_gemma":0.0000022972674,"teacher_disagreement_score":0.22904159,"about_ca_system_score_codex":0.000023762574,"about_ca_system_score_gemma":0.00008133189,"threshold_uncertainty_score":0.9331947},"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":"W2078868555","doi":"10.1016/j.jclinepi.2010.02.022","title":"Methodologies to evaluate the effectiveness of knowledge translation interventions: a primer for researchers and health care managers","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":64,"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; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Psychological intervention; Primer (cosmetics); Knowledge translation; Translation (biology); Health care; Medicine; Knowledge management; Nursing; Computer science; Political science; Biology","score_opus":0.9900522660287203,"score_gpt":0.8829022445420794,"score_spread":0.10715002148664088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078868555","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":[0.00007836986,0.918335,0.05672928,0.016803177,0.0021816553,0.0056712744,0.00007731019,0.000008187727,0.00011573486],"genre_scores_gemma":[0.00004405014,0.9263821,0.06976417,0.0027141757,0.00055084523,0.0004739404,0.000008531288,0.000026938573,0.000035206496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.77122414,0.21474907,0.012502905,0.0004483809,0.00028024486,0.0007952448],"domain_scores_gemma":[0.381354,0.60964197,0.0069183675,0.00042031976,0.0011734302,0.000491917],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.474214,0.00023781038,0.0062120208,0.0004622225,0.00037082392,0.000003943827,0.0007094617,0.0007310482,0.000029693496],"category_scores_gemma":[0.4534821,0.00013035302,0.0014723188,0.00043576164,0.0005269271,0.000085842395,0.00017460449,0.003124009,0.000012612075],"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":[0.00020976414,0.000014047815,0.00040257856,0.051513802,0.00012851394,2.0819763e-7,0.0013881811,0.0000016046711,1.2762223e-7,0.0014768379,0.0023810498,0.9424833],"study_design_scores_gemma":[0.0010365968,0.0015496522,0.00759748,0.019795662,0.0003331418,0.000006039552,0.00092548295,0.0000051293814,9.8164314e-8,0.004428023,0.9642243,0.00009842752],"about_ca_topic_score_codex":0.00009461008,"about_ca_topic_score_gemma":0.00021485309,"teacher_disagreement_score":0.9618432,"about_ca_system_score_codex":0.00024252094,"about_ca_system_score_gemma":0.0053584045,"threshold_uncertainty_score":0.99917585},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","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":"medium"}],"label_agreement":"split"},{"id":"W2079031448","doi":"10.1016/j.jclinepi.2014.06.016","title":"Side effects are incompletely reported among systematic reviews in gastroenterology","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":30,"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; Ottawa Hospital","funders":"National Health and Medical Research Council","keywords":"Medicine; Systematic review; Internal medicine; Gastroenterology; MEDLINE; Biology","score_opus":0.8932240023213982,"score_gpt":0.6439290742111524,"score_spread":0.24929492811024578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079031448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87777644,0.0027840692,0.10862026,0.004817576,0.0030141002,0.0016808608,0.000001075446,0.000004290453,0.0013013337],"genre_scores_gemma":[0.9808965,0.00037025323,0.011135995,0.0064568794,0.00065952935,0.00003710138,9.4925196e-7,0.000015168499,0.00042763512],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.3252777,0.5230307,0.1472443,0.0012611187,0.0024625787,0.0007236167],"domain_scores_gemma":[0.105146095,0.6567467,0.2291528,0.005766457,0.0022522477,0.00093573256],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.83851343,0.0004251813,0.04217677,0.0007051312,0.0000536199,0.00007157114,0.002494934,0.000424258,0.00039502847],"category_scores_gemma":[0.9646318,0.00017839987,0.008063293,0.00072358374,0.0002981189,0.00021895675,0.00019403709,0.0013093487,0.0008988059],"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":[0.00005144456,0.00010188309,0.9771029,0.0018846528,0.0002569883,0.000080582904,0.000024777195,0.00016141825,0.0000027749604,0.00045951072,0.016915338,0.0029577578],"study_design_scores_gemma":[0.00078458333,0.00067378615,0.95357007,0.0036421523,0.00044118136,0.0003626531,0.000044706434,0.0074646804,2.9957758e-7,0.023553189,0.009338187,0.0001244945],"about_ca_topic_score_codex":0.0000117032505,"about_ca_topic_score_gemma":0.00017393634,"teacher_disagreement_score":0.2201316,"about_ca_system_score_codex":0.000040966333,"about_ca_system_score_gemma":0.00006265669,"threshold_uncertainty_score":0.9998791},"labels":[],"label_agreement":null},{"id":"W2079258339","doi":"10.1016/s0895-4356(03)00176-8","title":"Measures of importance for economic analysis based on decision modeling","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":39,"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; Health Canada","funders":"","keywords":"Probabilistic logic; Computer science; Econometrics; Entropy (arrow of time); Decision analysis; Ranking (information retrieval); Range (aeronautics); Variance (accounting); Statistics; Machine learning; Data mining; Mathematics; Artificial intelligence; Economics; Engineering","score_opus":0.8505611807918025,"score_gpt":0.6227462510338455,"score_spread":0.22781492975795703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079258339","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":[0.30937088,0.0012478471,0.67722607,0.009839977,0.0012833225,0.0002455485,0.000084384155,0.0000053095696,0.0006966722],"genre_scores_gemma":[0.90813416,0.00029305537,0.08072279,0.010359377,0.00043451993,0.00001067703,0.0000053327653,0.000018976845,0.000021122536],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9718697,0.0028483584,0.024375362,0.00046710068,0.00007982248,0.00035965713],"domain_scores_gemma":[0.90962684,0.07113285,0.01819347,0.00055063353,0.00019854908,0.0002976738],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22957356,0.0001728206,0.0053745266,0.00065283413,0.00006645454,0.000008020595,0.00034773877,0.00036453194,0.0002813744],"category_scores_gemma":[0.25112626,0.0001717051,0.0017675346,0.00014366134,0.00009547376,0.00016206581,0.000011781581,0.0003690019,0.00007184014],"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":[0.00021389376,0.00010326675,0.46941268,0.000036978836,0.00037075262,3.6689232e-7,0.000018329725,0.45991498,1.3153824e-7,0.066549525,0.003021591,0.00035751617],"study_design_scores_gemma":[0.0020975515,0.0006245243,0.03568347,0.000057007335,0.00011905598,0.0000029293683,0.000056408695,0.776917,0.0000013967824,0.17494851,0.009311694,0.00018048256],"about_ca_topic_score_codex":0.00006775126,"about_ca_topic_score_gemma":0.0000841022,"teacher_disagreement_score":0.5987633,"about_ca_system_score_codex":0.00023468336,"about_ca_system_score_gemma":0.00043600058,"threshold_uncertainty_score":0.7933161},"labels":[],"label_agreement":null},{"id":"W2079345175","doi":"10.1016/s0895-4356(03)00118-5","title":"Factors associated with the onset of an episode of depressive symptoms in the general population","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":61,"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 Work & Health; University of Alberta","funders":"","keywords":"Depression (economics); Headaches; Medicine; Marital status; Population; Depressive symptoms; Psychiatry; Anxiety","score_opus":0.14240305780394394,"score_gpt":0.4664329768842329,"score_spread":0.324029919080289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079345175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99651027,0.00012050542,0.00029793172,0.0026742446,0.00013683995,0.00017915507,0.0000025038485,0.0000016635764,0.00007690727],"genre_scores_gemma":[0.998688,0.000021363638,0.00035677606,0.0008216258,0.00008231193,0.0000015554449,0.000010331012,0.0000058213664,0.000012261533],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98772216,0.0096250875,0.0022043083,0.00010572789,0.00020226231,0.00014048458],"domain_scores_gemma":[0.96828264,0.028653903,0.0025568022,0.000211749,0.00021842642,0.0000765061],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018223107,0.00008988646,0.0011925149,0.00006956845,0.000022810886,0.0000010020584,0.00012664874,0.00021322296,0.000017886816],"category_scores_gemma":[0.074912906,0.000034186472,0.00035019848,0.00014896953,0.00030556432,0.000050602295,0.0000061388796,0.0005647342,1.4252369e-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":[0.0001815417,0.00031433647,0.9962905,0.00002387149,0.00012015991,0.0000017834385,0.00016758611,0.00075653486,0.0000490882,0.00096867484,0.00012418875,0.0010017548],"study_design_scores_gemma":[0.0013313366,0.00220443,0.9925644,0.000119729244,0.00009303883,0.000008838962,0.00018084313,0.0005030097,0.000017482998,0.0029088245,0.000033862267,0.00003420684],"about_ca_topic_score_codex":0.000078008634,"about_ca_topic_score_gemma":0.0001222818,"teacher_disagreement_score":0.0566898,"about_ca_system_score_codex":0.00002041031,"about_ca_system_score_gemma":0.000079872385,"threshold_uncertainty_score":0.9328795},"labels":[],"label_agreement":null},{"id":"W2079429487","doi":"10.1016/j.jclinepi.2006.09.002","title":"Studies reporting ROC curves of diagnostic and prediction data can be incorporated into meta-analyses using corresponding odds ratios","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":30,"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; Sunnybrook Health Science Centre; University of Toronto; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Diagnostic odds ratio; Meta-analysis; Receiver operating characteristic; Odds ratio; Odds; Medicine; Statistics; MEDLINE; Mathematics; Internal medicine; Logistic regression; Chemistry","score_opus":0.9212560746961093,"score_gpt":0.6678770993554153,"score_spread":0.253378975340694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079429487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9463094,0.041298524,0.0013195084,0.010363047,0.0004605751,0.00020106621,0.000026434758,0.000008967941,0.000012507153],"genre_scores_gemma":[0.97891325,0.009229304,0.009722857,0.0015237754,0.00051532616,0.000004695243,0.000063748994,0.000013169613,0.000013874466],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9873688,0.0024388116,0.009383724,0.00035309195,0.00025963684,0.00019592674],"domain_scores_gemma":[0.8746718,0.10035212,0.022896195,0.00070343004,0.0011063414,0.0002700685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025135402,0.00019556806,0.004610985,0.0001931667,0.000075222546,0.000004848373,0.00012427369,0.00016905529,0.000025133062],"category_scores_gemma":[0.434055,0.00011616706,0.00055608805,0.00022044657,0.00032012668,0.00015096183,0.00013885603,0.00040426195,2.5304837e-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":[0.00018782212,0.0003793319,0.9839506,0.00015958407,0.0073476695,0.00021132386,0.0000318156,0.0011058571,0.000306795,0.000067380046,0.005260651,0.0009911635],"study_design_scores_gemma":[0.0022009728,0.0017826541,0.94562846,0.0011800033,0.03758382,0.0008254842,0.0003141801,0.006505759,0.0005116023,0.0029236816,0.00039512603,0.00014827163],"about_ca_topic_score_codex":0.0004424297,"about_ca_topic_score_gemma":0.00017535289,"teacher_disagreement_score":0.4089196,"about_ca_system_score_codex":0.000060318092,"about_ca_system_score_gemma":0.00026929457,"threshold_uncertainty_score":0.8711479},"labels":[],"label_agreement":null},{"id":"W2079658350","doi":"10.1016/j.jclinepi.2011.10.012","title":"Systematic reviews identify important methodological flaws in stroke rehabilitation therapy primary studies: review of reviews","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","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":"U.S. Public Health Service; Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Systematic review; Blinding; Medicine; CINAHL; PsycINFO; MEDLINE; Rehabilitation; Psychological intervention; Comparability; Physical therapy; Randomized controlled trial; Surgery; Nursing","score_opus":0.7715227156450835,"score_gpt":0.6591039561339813,"score_spread":0.11241875951110214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079658350","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":[0.000035316913,0.98671955,0.00020011853,0.0013763483,0.0032871477,0.00824688,0.000010833627,0.000009523605,0.00011429935],"genre_scores_gemma":[6.4630257e-7,0.9566981,0.037536412,0.003940486,0.0012442804,0.00036505237,0.000023365643,0.00004688793,0.00014474326],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.81426454,0.1257235,0.058067765,0.00071771734,0.00061537686,0.0006110881],"domain_scores_gemma":[0.35035166,0.56103486,0.08387396,0.0021899806,0.0016589656,0.00089060207],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.3698219,0.0008114328,0.065400384,0.0006863853,0.000028582075,0.000003446548,0.0005727987,0.0013866173,0.00023486317],"category_scores_gemma":[0.7166033,0.0003905328,0.014626662,0.0006850956,0.00065215206,0.00017058305,0.000115259645,0.0031229951,0.00006594952],"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":[0.00009828809,0.00037634684,0.0023471126,0.6241401,0.0007537127,0.000012078666,0.000034645218,4.3990394e-8,3.2283543e-7,0.000069479305,0.004495015,0.3676729],"study_design_scores_gemma":[0.00057857117,0.0014831786,0.001937349,0.47021315,0.0030093235,0.0002791692,0.000021151145,2.5775915e-7,1.8888748e-8,0.00020176459,0.5221207,0.00015537231],"about_ca_topic_score_codex":0.0000024798926,"about_ca_topic_score_gemma":0.0000012656516,"teacher_disagreement_score":0.5176257,"about_ca_system_score_codex":0.00041539955,"about_ca_system_score_gemma":0.00085880054,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W2079702467","doi":"10.1016/j.jclinepi.2005.09.003","title":"Eight predictive factors associated with response patterns during physiotherapy for soft tissue shoulder disorders were identified","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Shoulder Injury and Treatment","field":"Medicine","cited_by":22,"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; McMaster University; University of Toronto; St. Michael's Hospital; Institute for Work & Health","funders":"Canadian Institutes of Health Research; Health Canada","keywords":"Soft tissue; Medicine; Physical therapy; Physical medicine and rehabilitation; Surgery","score_opus":0.1229492272850397,"score_gpt":0.480385157075323,"score_spread":0.35743592979028327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079702467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97460896,0.00032519852,0.017870124,0.005953434,0.00061159837,0.00049207004,0.00006942225,0.00002775858,0.00004144274],"genre_scores_gemma":[0.99688786,0.00018362972,0.0006152099,0.0007149013,0.0007393042,0.000018162415,0.000047849277,0.000042402513,0.00075065135],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99454105,0.0019199508,0.002510986,0.00034964262,0.00024590042,0.00043247745],"domain_scores_gemma":[0.9750219,0.02221878,0.0020172591,0.0002495544,0.00024931112,0.00024317419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004902842,0.00026959073,0.0021689679,0.00013453685,0.000109388435,0.000007550204,0.00014077654,0.00042449872,0.00010919676],"category_scores_gemma":[0.011143957,0.00016327773,0.0006991798,0.00009749981,0.00021203813,0.00011387459,0.000019193802,0.00065537315,0.0000018900786],"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":[0.024008079,0.0013549243,0.9681785,0.000038541435,0.0014065059,0.000061115155,0.00007463702,0.00030820718,0.0005352936,0.000039050843,0.0019169737,0.0020781904],"study_design_scores_gemma":[0.0092943525,0.006385983,0.9773212,0.00020243652,0.0006225374,0.000032645446,0.000089129884,0.00009095815,0.0012547477,0.0023340115,0.0022275092,0.00014449474],"about_ca_topic_score_codex":0.00003474752,"about_ca_topic_score_gemma":0.00009164917,"teacher_disagreement_score":0.022278938,"about_ca_system_score_codex":0.0001122839,"about_ca_system_score_gemma":0.00018427944,"threshold_uncertainty_score":0.9971856},"labels":[],"label_agreement":null},{"id":"W2079787810","doi":"10.1016/j.jclinepi.2004.02.014","title":"A flexible modeling approach to estimating the component effects of smoking behavior on lung cancer","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":51,"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; Centre Hospitalier de l’Université de Montréal; Montreal General Hospital; Institut National de la Recherche Scientifique","funders":"","keywords":"Lung cancer; Medicine; Smoking cessation; Demography; Odds ratio; Multicollinearity; Etiology; Cancer; Public health; Statistics; Internal medicine; Regression analysis; Mathematics; Pathology","score_opus":0.2715119809417106,"score_gpt":0.5211395152141349,"score_spread":0.24962753427242435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079787810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8496501,0.00019050663,0.1462817,0.0022513843,0.001225476,0.0003035108,8.088829e-7,0.000010453486,0.000086067404],"genre_scores_gemma":[0.98108745,0.0000507182,0.015718432,0.0022721095,0.0008192302,0.000026705666,0.0000017754315,0.00001619022,0.000007374508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959929,0.000723195,0.002511847,0.0002029898,0.00031649543,0.0002525829],"domain_scores_gemma":[0.9931287,0.0048141098,0.0013786335,0.00024677158,0.00022652045,0.00020522205],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008834844,0.00013729527,0.001445879,0.00011668743,0.00006916202,0.000004084359,0.00018171892,0.00022320927,0.000007118744],"category_scores_gemma":[0.0124934865,0.00008062911,0.00046118826,0.00013978031,0.000088646746,0.000042202533,0.000039165294,0.0010230225,4.802879e-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":[0.00044073904,0.0008015769,0.5864388,0.00015582054,0.00013193383,0.000020272124,0.0002582554,0.39534584,0.00026769115,0.0008336252,0.00012540915,0.015180049],"study_design_scores_gemma":[0.004116632,0.0017197578,0.92290795,0.0020488957,0.0012721793,0.00017863781,0.00007192797,0.06593389,0.00056493777,0.0010209036,0.000024953,0.00013936423],"about_ca_topic_score_codex":0.00014139849,"about_ca_topic_score_gemma":9.578638e-7,"teacher_disagreement_score":0.3364691,"about_ca_system_score_codex":0.00012712507,"about_ca_system_score_gemma":0.00019793585,"threshold_uncertainty_score":0.9958247},"labels":[],"label_agreement":null},{"id":"W2079828477","doi":"10.1016/j.jclinepi.2014.06.013","title":"Priority-based initiative for updating existing evidence-based clinical practice guidelines: the results of two iterations","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Juravinski Hospital; Cancer Care Ontario; McMaster University","funders":"","keywords":"Guideline; Prioritization; Medicine; Quality of evidence; Evidence-based practice; Quality (philosophy); Evidence-based medicine; Process management; Alternative medicine; Randomized controlled trial; Pathology; Business","score_opus":0.8559546995643833,"score_gpt":0.7086200717376087,"score_spread":0.14733462782677464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079828477","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":[0.04161379,0.00030623504,0.5821695,0.371824,0.0024737176,0.0010124431,0.000039722174,0.000026037984,0.00053462066],"genre_scores_gemma":[0.2919032,0.00023849405,0.5809468,0.1208473,0.005958316,0.000016599994,0.000043644104,0.000028699633,0.000016976286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9397164,0.024104321,0.03425989,0.0006466456,0.0007495242,0.0005232462],"domain_scores_gemma":[0.10068455,0.8545816,0.029652933,0.000941534,0.013646418,0.0004929709],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29485038,0.0002792134,0.003149555,0.0001656472,0.00019036145,0.000021526761,0.00045754708,0.0004207237,0.000033357217],"category_scores_gemma":[0.9805213,0.00017713718,0.0016196895,0.00033613766,0.00064422324,0.00055855105,0.00008448171,0.002099115,0.000009862557],"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":[0.050543543,0.0032828527,0.28978714,0.0005211075,0.0014195231,0.00005096499,0.00021096217,0.015186278,0.00019433412,0.014173395,0.12760648,0.4970234],"study_design_scores_gemma":[0.057252344,0.0254499,0.10884696,0.0044856938,0.0050236885,0.00026044605,0.0014170654,0.41954926,0.00014401544,0.016442977,0.36054486,0.00058277766],"about_ca_topic_score_codex":0.00007336916,"about_ca_topic_score_gemma":0.00003607658,"teacher_disagreement_score":0.8390318,"about_ca_system_score_codex":0.00007004243,"about_ca_system_score_gemma":0.0027555942,"threshold_uncertainty_score":0.91197264},"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":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2079960868","doi":"10.1016/j.jclinepi.2004.10.006","title":"Electronic mail was not better than postal mail for surveying residents and faculty","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":128,"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":"Office of Graduate Education, Massachusetts Institute of Technology; University at Buffalo","keywords":"Medicine; Confidence interval; Postal service; Randomized controlled trial; Non-response bias; Family medicine; Internal medicine","score_opus":0.6696730583230093,"score_gpt":0.6264181919764982,"score_spread":0.0432548663465111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079960868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94397503,0.0005103812,0.004009668,0.050201815,0.00095763436,0.00013850244,0.000017015689,0.000011651217,0.00017828008],"genre_scores_gemma":[0.9616255,0.0013532151,0.023866843,0.009340467,0.0028137728,0.0000040985524,0.0000074032623,0.000012508813,0.00097615534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9021107,0.092971474,0.0032688498,0.00039727334,0.0002643297,0.0009873842],"domain_scores_gemma":[0.76822364,0.22966643,0.0014327909,0.00013753661,0.00023906572,0.00030053937],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36272752,0.00015194285,0.0015223493,0.00010580386,0.00031523593,0.000014429512,0.00038206903,0.0006445647,0.00009143669],"category_scores_gemma":[0.44214574,0.00011819428,0.00053493184,0.00010286495,0.000747569,0.00023452772,0.00006376446,0.0010542236,0.000007738272],"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":[0.012662245,0.000100328165,0.93054724,0.0000073715028,0.00019467656,0.000013642439,0.0005619701,0.000015822254,0.00005168733,0.003213004,0.008335159,0.044296853],"study_design_scores_gemma":[0.0013075927,0.00058848073,0.91095746,0.000019065576,0.000049249644,0.000037999973,0.00017723911,0.000036003185,0.000022663873,0.010646677,0.076032646,0.00012494763],"about_ca_topic_score_codex":0.00033247133,"about_ca_topic_score_gemma":0.0025310523,"teacher_disagreement_score":0.13669495,"about_ca_system_score_codex":0.000069245754,"about_ca_system_score_gemma":0.0005366314,"threshold_uncertainty_score":0.65620613},"labels":[],"label_agreement":null},{"id":"W2080122029","doi":"10.1016/j.jclinepi.2004.03.008","title":"Condition-specific Western Ontario McMaster Osteoarthritis Index was not superior to region-specific Lower Extremity Functional Scale at detecting change","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; McMaster University","funders":"","keywords":"WOMAC; Osteoarthritis; Medicine; Physical therapy; Confidence interval; Arthroplasty; Physical medicine and rehabilitation; Surgery; Internal medicine; Pathology","score_opus":0.22197810890321454,"score_gpt":0.3852598007693194,"score_spread":0.1632816918661049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080122029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808392,0.0011074072,0.0032535254,0.009238931,0.004542445,0.00061456254,0.000013559353,0.00003837485,0.00035199497],"genre_scores_gemma":[0.9802498,0.00056543027,0.003548522,0.009069201,0.004543698,0.000043002903,0.000024606357,0.000053678847,0.0019020404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9936904,0.00072397286,0.003715844,0.0006747231,0.00047304365,0.0007220698],"domain_scores_gemma":[0.9936616,0.0030776623,0.0013823283,0.00043004894,0.00045032363,0.0009980698],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038686749,0.00040161295,0.0026370052,0.00026633762,0.00021576037,0.000021545971,0.0001906712,0.00067295565,0.0016150551],"category_scores_gemma":[0.0015452472,0.00032961858,0.0011308416,0.00017417475,0.00029752927,0.00030933128,0.00013953877,0.0013805714,0.0004360864],"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":[0.008838946,0.0006539546,0.8470085,0.000021320277,0.00011290165,0.0013703665,0.0005046813,0.000031178366,0.0012208223,0.00019626322,0.0015447251,0.13849634],"study_design_scores_gemma":[0.018677281,0.010585107,0.8274073,0.0008894735,0.00012611887,0.0064754,0.00012678941,0.0000014651844,0.00060805725,0.0010930842,0.13363086,0.0003790358],"about_ca_topic_score_codex":0.00015253696,"about_ca_topic_score_gemma":0.005676541,"teacher_disagreement_score":0.1381173,"about_ca_system_score_codex":0.0006806192,"about_ca_system_score_gemma":0.00025780496,"threshold_uncertainty_score":0.9999156},"labels":[],"label_agreement":null},{"id":"W2080128477","doi":"10.1016/j.jclinepi.2005.03.003","title":"The structural equation modeling technique did not show a response shift, contrary to the results of the then test and the individualized approaches","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Structural equation modeling; Test (biology); Medicine; Applied mathematics; Mathematics; Econometrics; Statistics; Biology","score_opus":0.30956192980839353,"score_gpt":0.45283692661913383,"score_spread":0.1432749968107403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080128477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6084707,0.001307521,0.0053840918,0.3835156,0.00040920248,0.00071690674,0.000025386113,0.000007235162,0.0001633545],"genre_scores_gemma":[0.9876389,0.0003654533,0.0010768479,0.009786607,0.0010243912,0.00002639546,0.0000013917441,0.000011993636,0.00006803932],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.98680407,0.009234447,0.0031287917,0.00021522232,0.00034561832,0.0002718373],"domain_scores_gemma":[0.8882945,0.10870361,0.0019914082,0.0006437339,0.0002133339,0.00015339108],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066518225,0.00015468389,0.0011969719,0.00004378533,0.00021891897,0.00001553428,0.0005455613,0.00024143497,0.000004523597],"category_scores_gemma":[0.13545199,0.000050075603,0.00053775916,0.0001515532,0.00075487146,0.000058406178,0.00015873014,0.0012729496,7.120567e-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":[0.41746122,0.0004038724,0.15894185,0.00011959506,0.0018005007,0.000018864901,0.030765384,0.018399177,0.0005261343,0.03355487,0.008366645,0.3296419],"study_design_scores_gemma":[0.026642647,0.0037815317,0.68292826,0.0008094548,0.001252968,0.00072937604,0.0048986687,0.173226,0.0004637907,0.06419825,0.04063175,0.00043731846],"about_ca_topic_score_codex":0.00012190982,"about_ca_topic_score_gemma":0.00035869362,"teacher_disagreement_score":0.5239864,"about_ca_system_score_codex":0.000034076456,"about_ca_system_score_gemma":0.00028532752,"threshold_uncertainty_score":0.9612159},"labels":[],"label_agreement":null},{"id":"W2080701168","doi":"10.1016/j.jclinepi.2012.02.008","title":"New methods can extend the use of minimal important difference units in meta-analyses of continuous outcome measures","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"SickKids Foundation; Institute for Clinical Evaluative Sciences; McMaster University; Hospital for Sick Children","funders":"","keywords":"Meta-analysis; Random effects model; Medicine; Confidence interval; Clinical trial; Statistics; Point estimation; Mean difference; Standard error; Estimation; Treatment effect; Drug trial; Econometrics; Internal medicine; Mathematics","score_opus":0.9886393920051221,"score_gpt":0.7473320582811612,"score_spread":0.24130733372396085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080701168","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74781436,0.024154024,0.21693006,0.008821805,0.0015579157,0.00051152124,0.00003041593,0.0000016916557,0.00017819257],"genre_scores_gemma":[0.826922,0.0004130058,0.17001061,0.0013310562,0.0002477574,0.0000032910054,5.702707e-7,0.000009675778,0.0010620235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5166107,0.34302267,0.13438724,0.00086193415,0.0042964737,0.00082103576],"domain_scores_gemma":[0.20810871,0.6623456,0.120162025,0.0041081286,0.0043786876,0.0008968609],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6787355,0.00036384104,0.028347842,0.00048570713,0.00003565248,0.00003991358,0.002388371,0.00030440357,0.0019733158],"category_scores_gemma":[0.8850498,0.000116617055,0.009339368,0.0012875001,0.0004143998,0.00021076025,0.00019372697,0.0009069511,0.000012664112],"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":[0.00008461317,0.0001212091,0.953945,0.000015521926,0.004052586,0.0000046783466,0.00016513506,0.00018176812,0.00013079711,0.0019136542,0.0074196425,0.031965423],"study_design_scores_gemma":[0.00041837312,0.000305739,0.9541731,0.000028858536,0.008670588,0.00006719721,0.00028065758,0.00081787555,0.000059010963,0.011116857,0.023927523,0.00013423941],"about_ca_topic_score_codex":0.00040271628,"about_ca_topic_score_gemma":0.00020857826,"teacher_disagreement_score":0.31932294,"about_ca_system_score_codex":0.000015518068,"about_ca_system_score_gemma":0.0003509323,"threshold_uncertainty_score":0.99893904},"labels":[],"label_agreement":null},{"id":"W2081338827","doi":"10.1016/j.jclinepi.2011.01.003","title":"Challenges in guideline methodology","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"St. Michael's Hospital","funders":"National Institute for Health and Care Research","keywords":"Guideline; Medicine; Intensive care medicine; Pathology","score_opus":0.9635407775421592,"score_gpt":0.7216052792620303,"score_spread":0.24193549828012884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081338827","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":[0.56502587,0.009318252,0.09126962,0.3041817,0.008315902,0.0007500558,0.0000041460708,0.000054613272,0.021079822],"genre_scores_gemma":[0.36428988,0.011444497,0.59879726,0.023267604,0.0021186522,0.0000030971385,0.000005553761,0.000024925164,0.00004853149],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.969707,0.012075902,0.017218232,0.00037225368,0.0002112279,0.00041537802],"domain_scores_gemma":[0.88771576,0.103037864,0.0072986404,0.00053251075,0.0008927843,0.0005224272],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14249735,0.00016264421,0.0033529922,0.00026732718,0.000013592845,9.71085e-7,0.00023406246,0.00050911645,0.00086846633],"category_scores_gemma":[0.49794534,0.00011665936,0.00072263606,0.00014121516,0.00023812275,0.0001540062,0.000082832375,0.0016137811,0.00005158576],"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":[0.0036907257,0.00080631586,0.49903014,0.000026675067,0.00020517103,0.00034146663,0.00015492836,0.000011019629,0.000033330165,0.0062621064,0.010640225,0.47879788],"study_design_scores_gemma":[0.00513612,0.003990458,0.86389965,0.000071169656,0.00023624377,0.0013882708,0.0005217482,0.000278414,0.000020822437,0.062468924,0.061874285,0.00011388528],"about_ca_topic_score_codex":0.00010868414,"about_ca_topic_score_gemma":0.00016231147,"teacher_disagreement_score":0.50752765,"about_ca_system_score_codex":0.000041681895,"about_ca_system_score_gemma":0.00040751148,"threshold_uncertainty_score":0.95090973},"labels":[],"label_agreement":null},{"id":"W2081634320","doi":"10.1016/j.jclinepi.2010.04.027","title":"Observational studies in systemic reviews of comparative effectiveness: AHRQ and the Effective Health Care Program","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":75,"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; McMaster University","funders":"Agency for Healthcare Research and Quality; U.S. Food and Drug Administration","keywords":"Observational study; Randomized controlled trial; Medicine; Systematic review; Psychological intervention; Comparative effectiveness research; Observational methods in psychology; Evidence-based medicine; MEDLINE; Inclusion (mineral); Health care; Agency (philosophy); Psychology; Alternative medicine; Nursing; Surgery; Pathology; Social psychology","score_opus":0.9738164202290723,"score_gpt":0.8328909882359095,"score_spread":0.14092543199316288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081634320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690671,0.0136942845,0.0007633775,0.009220729,0.0014854268,0.0054475213,0.000012528039,0.000008587128,0.00030047548],"genre_scores_gemma":[0.97333777,0.0068482286,0.0063920002,0.012656558,0.00028947872,0.0004637519,9.993041e-7,0.0000059280264,0.0000052860655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8742973,0.11523071,0.009544759,0.00024962012,0.00020338039,0.0004741844],"domain_scores_gemma":[0.74219835,0.24736507,0.0091143865,0.00019670637,0.0009161745,0.00020931031],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15680042,0.00014423204,0.0044259173,0.00012679413,0.00020929979,8.507506e-7,0.00026319723,0.0001634716,0.000019344061],"category_scores_gemma":[0.14973898,0.00007470077,0.0002460276,0.0003094761,0.0012357831,0.00012635966,0.00010721911,0.0012412095,0.0000096033145],"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":[0.0012717749,0.000072287294,0.9094696,0.0024416207,0.00009925657,0.000001631541,0.05579839,0.000006885154,0.0000011977212,0.016441977,0.0018418499,0.012553527],"study_design_scores_gemma":[0.0043115397,0.0016461663,0.96877986,0.00203358,0.000027213948,0.0000147378505,0.011548331,0.00003346856,9.997536e-7,0.0071206717,0.0044251857,0.00005827199],"about_ca_topic_score_codex":0.0002516509,"about_ca_topic_score_gemma":0.00027199247,"teacher_disagreement_score":0.13213436,"about_ca_system_score_codex":0.00021302295,"about_ca_system_score_gemma":0.0011024473,"threshold_uncertainty_score":0.8682514},"labels":[],"label_agreement":null},{"id":"W2081705519","doi":"10.1016/j.jclinepi.2013.12.009","title":"Multicriteria decision analysis methods with 1000Minds for developing systemic sclerosis classification criteria","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Systemic Sclerosis and Related Diseases","field":"Medicine","cited_by":65,"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; University of Toronto; St Joseph's Health Care; Toronto Western Hospital; Western University; Mount Sinai Hospital","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Medicine; Confidence interval; Intraclass correlation; Physical therapy; Surgery; Physical medicine and rehabilitation; Internal medicine; Psychometrics","score_opus":0.4618244318302919,"score_gpt":0.574616521733866,"score_spread":0.11279208990357409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081705519","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":[0.4245432,0.0011526735,0.5715619,0.0016865806,0.0007976556,0.00020429087,0.0000035369521,0.00001318768,0.000036972207],"genre_scores_gemma":[0.6378453,0.0010418583,0.35912487,0.0012354221,0.0006873887,0.000013407178,0.000010236501,0.000017804894,0.000023752165],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9889913,0.004455698,0.0055648787,0.00042174655,0.00022612372,0.00034025207],"domain_scores_gemma":[0.948402,0.04547264,0.004030246,0.00048508262,0.0011542179,0.00045581567],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03416969,0.00022264356,0.003761568,0.000426505,0.0000891428,0.000016929742,0.00022694663,0.00055091386,0.00004277257],"category_scores_gemma":[0.07457767,0.00012963748,0.0013163234,0.00047129224,0.00018025441,0.00009467866,0.00003095515,0.00040560472,0.0000070205815],"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":[0.006493473,0.00039762535,0.5840039,0.00038937305,0.0051214336,0.0000070825554,0.00011134427,0.00033227023,0.011903128,0.0015100227,0.003776449,0.38595387],"study_design_scores_gemma":[0.005023186,0.0016909803,0.93893135,0.004132396,0.0054232134,0.0002743392,0.00018355102,0.041657552,0.00018172622,0.00080251443,0.0014943064,0.00020485988],"about_ca_topic_score_codex":0.000008079745,"about_ca_topic_score_gemma":0.0000019941679,"teacher_disagreement_score":0.385749,"about_ca_system_score_codex":0.00008812618,"about_ca_system_score_gemma":0.00025992226,"threshold_uncertainty_score":0.99452555},"labels":[],"label_agreement":null},{"id":"W2081713975","doi":"10.1016/s0895-4356(00)00342-5","title":"Establishing the minimal number of items for a responsive, valid, health-related quality of life instrument","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health and Wellbeing Research","field":"Health Professions","cited_by":61,"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":"Intraclass correlation; Reliability (semiconductor); Construct validity; Quality of life (healthcare); Sample (material); Construct (python library); Domain (mathematical analysis); Test (biology); Psychology; Sample size determination; Statistics; Physical therapy; Psychometrics; Medicine; Mathematics; Clinical psychology; Computer science","score_opus":0.6361322711259338,"score_gpt":0.6700087463545799,"score_spread":0.03387647522864601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081713975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88035625,0.0006577902,0.0012426912,0.11422513,0.0018438832,0.0007598844,0.000029072125,0.000007360871,0.00087791675],"genre_scores_gemma":[0.97721833,0.0022043122,0.00469783,0.014143229,0.0011817756,0.000026361253,0.000005943566,0.00002367565,0.0004985349],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.92616946,0.052095916,0.01971459,0.00031531317,0.00053827895,0.00116643],"domain_scores_gemma":[0.5927841,0.38900375,0.014995446,0.00054735615,0.0016092209,0.0010601202],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22249053,0.00016371295,0.003744329,0.00014166138,0.0003588067,0.0000026223627,0.0006055413,0.0007167565,0.00027418908],"category_scores_gemma":[0.5287941,0.00009839747,0.000802991,0.00034232787,0.0005019644,0.00012350391,0.00015231314,0.0029874756,0.000021160535],"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":[0.008170371,0.0002620201,0.93021256,0.000609762,0.00013000115,0.0000029758419,0.0008075927,0.000037989583,0.000011284654,0.007231865,0.04009151,0.012432053],"study_design_scores_gemma":[0.005738765,0.0021401916,0.891544,0.00081108307,0.00003049976,0.000023779563,0.0018812241,0.00039740163,0.000001820109,0.029520309,0.06779487,0.00011609778],"about_ca_topic_score_codex":0.0018084119,"about_ca_topic_score_gemma":0.00012319956,"teacher_disagreement_score":0.33690783,"about_ca_system_score_codex":0.000114273396,"about_ca_system_score_gemma":0.005042493,"threshold_uncertainty_score":0.9993127},"labels":[],"label_agreement":null},{"id":"W2082130583","doi":"10.1016/s0895-4356(03)00131-8","title":"Effect of nonsteroidal anti-inflammatory drugs on stage of colon cancer at diagnosis","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory mediators and NSAID effects","field":"Medicine","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":"Jewish General Hospital; McGill University","funders":"","keywords":"Medicine; Colorectal cancer; Odds ratio; Cancer; Nonsteroidal; Confidence interval; Internal medicine; Confounding; Stage (stratigraphy); Drug; Medical prescription; Cancer registry; Oncology; Pharmacology","score_opus":0.07928793744321022,"score_gpt":0.46232221077062113,"score_spread":0.3830342733274109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082130583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951773,0.0011900093,0.000030140292,0.0004661752,0.0022467684,0.00035491155,0.000013706949,0.0000069362245,0.0005140026],"genre_scores_gemma":[0.9957781,0.0021653147,0.00023565358,0.00096193247,0.000596885,0.000014868684,0.0000014004125,0.000025845284,0.00022001324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98782516,0.0067393337,0.0044249515,0.00025478256,0.00036430376,0.0003914862],"domain_scores_gemma":[0.94723076,0.04748866,0.0042559416,0.00033996598,0.00026728748,0.0004174142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029712213,0.00024985062,0.004173917,0.00019557957,0.000035827623,0.0000010567454,0.00016390107,0.0005286791,0.00042820373],"category_scores_gemma":[0.04785387,0.00016211724,0.0011158355,0.000119410666,0.00048987917,0.000050932653,0.000039835282,0.0009211691,0.000018334262],"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":[0.0041463557,0.00026281844,0.9809489,0.00079961756,0.00033417603,0.00014062987,0.000050911214,0.00017221822,0.0013536124,0.00031773484,0.0036881983,0.007784818],"study_design_scores_gemma":[0.017376946,0.029130887,0.77418905,0.0021354589,0.00088873284,0.00015784663,0.00003373759,0.00021850699,0.13566871,0.00010778065,0.039763052,0.0003293079],"about_ca_topic_score_codex":0.000015385314,"about_ca_topic_score_gemma":0.0000068404,"teacher_disagreement_score":0.20675987,"about_ca_system_score_codex":0.00008221039,"about_ca_system_score_gemma":0.00035887587,"threshold_uncertainty_score":0.99911547},"labels":[],"label_agreement":null},{"id":"W2082162737","doi":"10.1016/s0895-4356(02)00581-4","title":"Techniques for knowledge discovery in existing biomedical databases Estimation of individual aging effects in cognition in relation to dementia","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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":"Dalhousie University","funders":"","keywords":"Dementia; Cognition; Rubric; Life expectancy; Computer science; Knowledge extraction; Expectancy theory; Cognitive impairment; Data science; Database; Disease; Artificial intelligence; Machine learning; Psychology; Medicine; Neuroscience","score_opus":0.2655294605876595,"score_gpt":0.552592368535976,"score_spread":0.2870629079483165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082162737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8474791,0.00029051732,0.15059376,0.00066563615,0.0001514977,0.00058730436,0.0000052409596,0.0000036686497,0.0002232904],"genre_scores_gemma":[0.9509163,0.00010708932,0.04842501,0.00035576164,0.00010079303,0.00003545716,0.000043902946,0.000007819211,0.000007886164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937606,0.0025456736,0.0029873692,0.00020568752,0.00021142149,0.00028923823],"domain_scores_gemma":[0.97494507,0.023809753,0.0008537089,0.00009055501,0.00016027979,0.00014064285],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031096833,0.00009875201,0.0010681427,0.00078685535,0.000016194075,0.0000042259226,0.00007803317,0.0001478607,0.000011567946],"category_scores_gemma":[0.13815346,0.00008087012,0.0001480071,0.0003542367,0.00012064244,0.00022485798,0.000043967382,0.0005475813,0.0000014413071],"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":[0.00064802996,0.0010447326,0.90906495,0.00030409562,0.000056378754,0.000035344616,0.00009132177,0.00003302769,0.00040959805,0.0013193878,0.0001768599,0.08681627],"study_design_scores_gemma":[0.004172141,0.0021397031,0.9819134,0.002390527,0.00010571092,0.00002668859,0.0001094062,0.0014109146,0.0009984502,0.0063968357,0.00026609213,0.00007013028],"about_ca_topic_score_codex":0.000013985902,"about_ca_topic_score_gemma":0.000034739798,"teacher_disagreement_score":0.107056625,"about_ca_system_score_codex":0.000056745906,"about_ca_system_score_gemma":0.00026028472,"threshold_uncertainty_score":0.9976897},"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":"W2082270078","doi":"10.1016/j.jclinepi.2007.04.019","title":"Methodological quality and homogeneity influenced agreement between randomized trials and nonrandomized studies of the same intervention for back pain","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":38,"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 for Social Innovation; Toronto General Hospital; Mount Sinai Hospital; Institute for Work & Health; University of Toronto","funders":"","keywords":"Homogeneity (statistics); Randomized controlled trial; Medicine; Physical therapy; Statistics; Surgery; Mathematics","score_opus":0.9902367732542218,"score_gpt":0.7897325288760771,"score_spread":0.20050424437814462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082270078","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016817468,0.88743603,0.104127154,0.0018172421,0.0008250892,0.004047332,0.000052298314,7.999078e-7,0.000012312055],"genre_scores_gemma":[0.00009177199,0.95034933,0.04818399,0.000523814,0.0005574009,0.000091154965,0.000003796652,0.000009526115,0.0001892114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.028538974,0.8239109,0.14459877,0.0009880827,0.0016607341,0.00030252838],"domain_scores_gemma":[0.005205148,0.82056385,0.17025508,0.0014802637,0.0022423184,0.00025332207],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97282106,0.00064678455,0.1677626,0.00032887323,0.00012749688,0.000051923602,0.0017778804,0.0009018792,0.00029461164],"category_scores_gemma":[0.99262,0.00019227332,0.050710425,0.00043813174,0.001774746,0.00009340202,0.00047143747,0.0010091873,0.000010604538],"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":[0.007012764,0.00009051681,0.0038456202,0.0042593833,0.011059903,8.410473e-7,0.000049827544,0.000003090952,8.7369344e-8,0.00037650976,0.00607785,0.9672236],"study_design_scores_gemma":[0.15869987,0.001330423,0.0055264356,0.0115688825,0.029108465,0.000105183564,0.00020397529,0.00013253707,2.9269646e-7,0.17529428,0.61750776,0.00052188657],"about_ca_topic_score_codex":0.000009070644,"about_ca_topic_score_gemma":0.0000065606914,"teacher_disagreement_score":0.96670175,"about_ca_system_score_codex":0.00003240393,"about_ca_system_score_gemma":0.0002338021,"threshold_uncertainty_score":0.9587965},"labels":[],"label_agreement":null},{"id":"W2082337007","doi":"10.1016/j.jclinepi.2010.01.016","title":"The usefulness of administrative databases for identifying disease cohorts is increased with a multivariate model","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Kidney Disease and Diabetes","field":"Medicine","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":"York University; Institute for Clinical Evaluative Sciences; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Kidney disease; Logistic regression; Renal function; Multivariate statistics; Diagnosis code; Medical diagnosis; Multivariate analysis; Cohort; Disease; Internal medicine; Statistic; Statistics; Intensive care medicine; Pathology; Population; Mathematics","score_opus":0.43717151602564835,"score_gpt":0.5360121577313806,"score_spread":0.0988406417057322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082337007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750223,0.00040545844,0.016799543,0.006680823,0.00041145517,0.00040085168,0.00021924976,0.0000075979433,0.000052705258],"genre_scores_gemma":[0.98406947,0.00014592284,0.01214888,0.0029515955,0.0005565495,0.000021518079,0.000025493595,0.000017700246,0.00006288428],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99594504,0.0006377161,0.0026325157,0.00025122744,0.00021758124,0.00031592755],"domain_scores_gemma":[0.9558558,0.038922764,0.0028860127,0.00054873695,0.0007177016,0.0010689696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009067178,0.00016609658,0.0017074787,0.000055272892,0.00010257672,0.0000066537064,0.00020644393,0.00012391437,0.000047177495],"category_scores_gemma":[0.103053294,0.00008549613,0.00064501126,0.00007200458,0.00065075257,0.00012494867,0.00005025314,0.00067840086,0.0000014587562],"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":[0.020716071,0.0013488212,0.95037955,0.00042330506,0.0012694991,0.00008958023,0.00008954244,0.00011180363,0.00067890633,0.009209951,0.011777579,0.0039053804],"study_design_scores_gemma":[0.013650463,0.002117376,0.89504296,0.00085871393,0.0026423233,0.000084073916,0.00019058835,0.058251478,0.00092034665,0.020640358,0.0053327945,0.00026854902],"about_ca_topic_score_codex":0.000030509456,"about_ca_topic_score_gemma":0.000028365082,"teacher_disagreement_score":0.09398612,"about_ca_system_score_codex":0.000013904788,"about_ca_system_score_gemma":0.0023178146,"threshold_uncertainty_score":0.9045021},"labels":[],"label_agreement":null},{"id":"W2082394503","doi":"10.1016/j.jclinepi.2008.01.005","title":"Computerized adaptive test for patients with knee impairments produced valid and responsive measures of function","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","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":"McMaster University","funders":"","keywords":"Computerized adaptive testing; Medicine; Confidence interval; Physical therapy; Rehabilitation; Ceiling effect; Prospective cohort study; Cohort study; Physical medicine and rehabilitation; Psychometrics; Surgery; Internal medicine","score_opus":0.20095998377877117,"score_gpt":0.41701767651890986,"score_spread":0.2160576927401387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082394503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99122334,0.00010316427,0.005639583,0.0018214186,0.0006294823,0.00054645253,0.000012106827,0.000008735285,0.000015709444],"genre_scores_gemma":[0.9744483,0.00008860762,0.024034863,0.0010248674,0.00031373944,0.000004974414,0.0000040208897,0.000016001812,0.00006459841],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958595,0.0010068527,0.002448471,0.00023450308,0.00022532983,0.0002253381],"domain_scores_gemma":[0.9737169,0.022411508,0.0024041468,0.00018135086,0.0010343589,0.00025173475],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004115236,0.00015525763,0.0022154143,0.00012399419,0.00005209007,0.0000011591732,0.00005838323,0.00017000832,0.000008148303],"category_scores_gemma":[0.06321339,0.00009516243,0.0003298001,0.00008360581,0.00044012457,0.00009625354,0.00003491363,0.00036080743,0.0000018012548],"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":[0.029628638,0.000728599,0.96097654,0.000037008438,0.00040064193,0.000020797463,0.00006924255,0.000019472292,0.00011028376,0.000029367866,0.0015406103,0.0064387787],"study_design_scores_gemma":[0.01489854,0.038854532,0.9441388,0.00014566781,0.00021777855,0.0002801935,0.00002588096,0.00012403468,0.000041629577,0.0003144743,0.00088023185,0.00007818342],"about_ca_topic_score_codex":0.0000043700684,"about_ca_topic_score_gemma":0.0000017460334,"teacher_disagreement_score":0.059098154,"about_ca_system_score_codex":0.000025416048,"about_ca_system_score_gemma":0.0002551453,"threshold_uncertainty_score":0.9446776},"labels":[],"label_agreement":null},{"id":"W2082561471","doi":"10.1016/j.jclinepi.2010.06.004","title":"PubMed had a higher sensitivity than Ovid-MEDLINE in the search for systematic reviews","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":false,"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 Health Network; University of Toronto","funders":"","keywords":"MEDLINE; Medicine; Systematic review; Randomized controlled trial; Internal medicine","score_opus":0.36091271384842727,"score_gpt":0.5311772336064866,"score_spread":0.17026451975805934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082561471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8962707,0.005653149,0.0015508801,0.09186669,0.0014031561,0.0029900654,0.0000066616694,0.000009149452,0.0002495624],"genre_scores_gemma":[0.976563,0.011710397,0.0032726948,0.0064935656,0.0016277664,0.00013623646,0.0000039084507,0.000015923519,0.00017653719],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9805722,0.013540593,0.004722632,0.00022445782,0.00033359503,0.00060650223],"domain_scores_gemma":[0.8885995,0.10815227,0.0017587806,0.00056391483,0.00042701227,0.00049852714],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16225149,0.00015791827,0.0036548453,0.0001455705,0.000058569563,0.000012515725,0.00026270986,0.00029657618,0.00004552091],"category_scores_gemma":[0.20764646,0.00007397652,0.0009845058,0.00015393346,0.00040907584,0.00009066132,0.000038788457,0.0022198725,0.000020464973],"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":[0.004913887,0.0020966849,0.85296726,0.01163561,0.0007110798,0.0007342551,0.0005254594,0.000011258853,0.00066925964,0.015909411,0.038678322,0.07114752],"study_design_scores_gemma":[0.0071374914,0.0023207925,0.90113807,0.0051699663,0.000053510077,0.0023741059,0.00013899803,0.0010091766,0.000027268043,0.0070267674,0.073424935,0.00017890596],"about_ca_topic_score_codex":0.000038178066,"about_ca_topic_score_gemma":0.0002115827,"teacher_disagreement_score":0.094611675,"about_ca_system_score_codex":0.000019779045,"about_ca_system_score_gemma":0.00022167663,"threshold_uncertainty_score":0.9644365},"labels":[],"label_agreement":null},{"id":"W2083330818","doi":"10.1016/j.jclinepi.2012.12.008","title":"Statistical methods for the meta-analysis of diagnostic tests must take into account the use of surrogate standards","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; University of Calgary","funders":"","keywords":"Surrogate endpoint; Medicine; Statistical analysis; Meta-analysis; Medical physics; Statistics; Mathematics; Internal medicine","score_opus":0.9630290080522151,"score_gpt":0.7413155499885182,"score_spread":0.2217134580636969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083330818","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":[0.016943712,0.0055663968,0.9543235,0.02138452,0.00064535794,0.0008928888,0.00020549224,0.0000010920514,0.00003707577],"genre_scores_gemma":[0.41782296,0.0011965333,0.57517534,0.004861511,0.00029395023,0.00009469308,0.000005485882,0.00002045351,0.0005290856],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.6868108,0.22619571,0.08069773,0.0010176182,0.0046937293,0.00058440666],"domain_scores_gemma":[0.017899334,0.9210055,0.04765477,0.0033302882,0.009805115,0.0003050107],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.73715067,0.00033416753,0.025647132,0.00042156802,0.00012548783,0.00014405837,0.0029487782,0.00026877993,0.011763103],"category_scores_gemma":[0.9712421,0.00009473074,0.020608036,0.0015293101,0.0010497778,0.00026084055,0.00022047512,0.00069681724,0.0000409706],"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":[0.0001912139,0.00040179415,0.15825215,0.00010206993,0.29872572,0.000004577922,0.0003486196,0.024199167,0.000016489053,0.023397408,0.27693298,0.21742779],"study_design_scores_gemma":[0.00039559286,0.00058910425,0.31399155,0.000013507765,0.2693026,0.000013143217,0.00031122126,0.08973749,0.000003331159,0.08918999,0.23629978,0.0001526674],"about_ca_topic_score_codex":0.00019129393,"about_ca_topic_score_gemma":0.00017022359,"teacher_disagreement_score":0.6948098,"about_ca_system_score_codex":0.000025979465,"about_ca_system_score_gemma":0.0003470345,"threshold_uncertainty_score":0.98920035},"labels":[],"label_agreement":null},{"id":"W2083852280","doi":"10.1016/j.jclinepi.2014.11.002","title":"Cochrane Airways Group reviews were prioritized for updating using a pragmatic approach","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Population Health Research Institute","funders":"Asthma and Lung UK; Evidence Synthesis Programme; National Institute for Health and Care Research","keywords":"Prioritization; Scope (computer science); Guideline; Systematic review; Publication; Process (computing); Cochrane collaboration; Computer science; Medicine; Expert opinion; MEDLINE; Management science; Engineering; Intensive care medicine; Business; Pathology; Political science","score_opus":0.893276027307836,"score_gpt":0.6699511098995793,"score_spread":0.22332491740825666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083852280","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":[0.034505438,0.004693516,0.95376843,0.00258691,0.0014499585,0.0010506791,0.000004631747,0.0000034137176,0.001937027],"genre_scores_gemma":[0.080570854,0.0009381215,0.9107173,0.004703796,0.00253548,0.000025826317,0.0000065034196,0.000025356592,0.0004767253],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6103144,0.2587247,0.12550841,0.0014935897,0.0031225467,0.00083631213],"domain_scores_gemma":[0.25845712,0.5870095,0.14550774,0.004607549,0.0034363293,0.0009817422],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.84676695,0.0003805677,0.026684124,0.00030670618,0.00017091009,0.0001370869,0.002232704,0.00040038142,0.0011991338],"category_scores_gemma":[0.9191512,0.00016619808,0.01015741,0.0005388111,0.00020972198,0.00027281145,0.00013825607,0.00086345145,0.00024250988],"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":[0.00040434962,0.00087354705,0.14432871,0.0021841761,0.0013367519,0.000007854943,0.0004125319,0.002098714,0.00014946739,0.095091954,0.28605703,0.4670549],"study_design_scores_gemma":[0.0023738123,0.00079778593,0.008051078,0.0007305163,0.0012187081,0.00029137917,0.0003953256,0.3742331,5.8480794e-7,0.12636548,0.48519832,0.00034388984],"about_ca_topic_score_codex":0.000003081843,"about_ca_topic_score_gemma":0.0000028359882,"teacher_disagreement_score":0.466711,"about_ca_system_score_codex":0.00003041434,"about_ca_system_score_gemma":0.00012791956,"threshold_uncertainty_score":0.9997556},"labels":[],"label_agreement":null},{"id":"W2083946765","doi":"10.1016/j.jclinepi.2007.02.010","title":"Minimal error in self-report of having had DXA, but self-report of its results was poor","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":40,"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 Health Network; Institute for Work & Health; St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Medicine; Osteopenia; Osteoporosis; Confidence interval; Cohen's kappa; Kappa; Population; Physical therapy; Internal medicine; Bone mineral; Statistics","score_opus":0.25178891089999467,"score_gpt":0.5453664276979008,"score_spread":0.2935775167979061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083946765","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97668827,0.0011434249,0.00013683194,0.018129844,0.0010270886,0.0004367803,0.00000984794,0.00001853968,0.0024093925],"genre_scores_gemma":[0.96843314,0.0012991657,0.026727384,0.0018650977,0.0011201453,0.0000031011039,0.000012234078,0.000029750154,0.0005099572],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9757051,0.002378554,0.01939905,0.00054977747,0.0008925695,0.0010749433],"domain_scores_gemma":[0.9464363,0.03700767,0.012143849,0.0007661515,0.0021118016,0.0015342189],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.112462014,0.00025797592,0.0046714335,0.00055478,0.00004255985,0.0000022243871,0.00032682327,0.0009595186,0.00006180123],"category_scores_gemma":[0.21433835,0.00019153662,0.00094758975,0.00041995107,0.00034105094,0.00010199063,0.00013439354,0.002532713,0.00001224859],"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":[0.009539285,0.0021425434,0.9621553,0.0006163009,0.00032318124,0.012455691,0.00016288582,0.000015713285,0.00097074587,0.00009274426,0.005507549,0.0060181073],"study_design_scores_gemma":[0.0071638497,0.004702179,0.95767874,0.0006372683,0.00019509802,0.011663666,0.00018882718,0.00034240054,0.0008604603,0.00018999216,0.016232751,0.00014474495],"about_ca_topic_score_codex":0.0003927077,"about_ca_topic_score_gemma":0.00022449951,"teacher_disagreement_score":0.10187633,"about_ca_system_score_codex":0.00014667743,"about_ca_system_score_gemma":0.002488572,"threshold_uncertainty_score":0.9997685},"labels":[],"label_agreement":null},{"id":"W2084076976","doi":"10.1016/j.jclinepi.2008.06.008","title":"New study design evaluated the validity of measures to assess change after hip or knee arthroplasty","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":68,"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; Health Sciences Centre; McMaster University","funders":"","keywords":"WOMAC; Physical therapy; Medicine; Osteoarthritis; Arthroplasty; Physical medicine and rehabilitation; Hip surgery; Hip arthroplasty; Surgery","score_opus":0.7009456468046684,"score_gpt":0.5324178473772477,"score_spread":0.1685277994274207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084076976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95841604,0.0004912277,0.022654096,0.015111107,0.0020599063,0.0012127296,0.0000036653385,0.000020891861,0.000030326895],"genre_scores_gemma":[0.97689253,0.00035621872,0.014721826,0.005701524,0.0017673733,0.000023522687,4.864807e-7,0.000030820207,0.0005057102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9825887,0.010734498,0.0050458275,0.00037067663,0.0007522199,0.0005080636],"domain_scores_gemma":[0.9564778,0.039189223,0.0022339367,0.0006235036,0.0007227602,0.00075272936],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030883847,0.00029053123,0.0035358942,0.00018163443,0.00008062718,0.0000040464897,0.00025563096,0.0003098516,0.0006244828],"category_scores_gemma":[0.13226521,0.0001438202,0.0008072488,0.00033441797,0.00037753079,0.00013379552,0.00013402707,0.0011577647,0.000083659455],"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":[0.008207365,0.00086027774,0.95302695,0.000017805502,0.0005131337,0.00045600408,0.00052647566,0.0001569779,0.000020923562,0.000009066347,0.015435429,0.020769563],"study_design_scores_gemma":[0.005350611,0.01631786,0.970054,0.00012095474,0.00043936385,0.0011656908,0.00017128886,0.00011694958,0.000026545134,0.0002061905,0.0058972016,0.00013335721],"about_ca_topic_score_codex":0.00006208078,"about_ca_topic_score_gemma":0.00010027717,"teacher_disagreement_score":0.10138136,"about_ca_system_score_codex":0.000051584644,"about_ca_system_score_gemma":0.0009857579,"threshold_uncertainty_score":0.997909},"labels":[],"label_agreement":null},{"id":"W2084358124","doi":"10.1016/j.jclinepi.2006.04.003","title":"The SF-36 summary scores and their relation to mental disorders: Physical functioning may affect performance of the summary scores","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","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; Douglas Mental Health University Institute","funders":"","keywords":"Affect (linguistics); Psychology; Clinical psychology; Medicine; Psychiatry","score_opus":0.08466886319391731,"score_gpt":0.4219770942132212,"score_spread":0.3373082310193039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084358124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97894114,0.0016895484,0.0025864865,0.01504647,0.0009610291,0.00034027305,0.0000017251314,0.0000071929853,0.00042613468],"genre_scores_gemma":[0.99571484,0.0020119087,0.00022400441,0.0008063307,0.00093610457,0.0000053793306,0.0000040826935,0.0000098814735,0.00028743883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99235946,0.005349615,0.0017007298,0.00016459092,0.000207774,0.0002178134],"domain_scores_gemma":[0.9926373,0.005907818,0.000980059,0.00023279812,0.00011282306,0.00012920289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022103913,0.00011665556,0.00093770213,0.00005262237,0.00020209709,0.0000051120905,0.00011381729,0.00014873652,0.0000073053047],"category_scores_gemma":[0.0065042446,0.000055071585,0.0007656697,0.00012908962,0.00029578095,0.00009598883,0.000069232745,0.00070334814,0.000003369242],"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":[0.0006254496,0.00018335313,0.84046364,0.00008592788,0.00016993938,8.919681e-7,0.00006235583,0.00032614343,0.00013460037,0.00042936517,0.0058382023,0.15168011],"study_design_scores_gemma":[0.0011055953,0.0012079264,0.9842485,0.00044194743,0.000086118744,0.00006585392,0.000050278693,0.0016119565,0.000046002464,0.001851682,0.009234347,0.00004977394],"about_ca_topic_score_codex":0.00002785009,"about_ca_topic_score_gemma":0.000026604657,"teacher_disagreement_score":0.15163033,"about_ca_system_score_codex":0.000035064808,"about_ca_system_score_gemma":0.00012033617,"threshold_uncertainty_score":0.77866584},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2084545298","doi":"10.1016/j.jclinepi.2013.12.003","title":"Response shift recalibration and reprioritization in health-related quality of life was identified prospectively in older men with and without stroke","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":51,"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 Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Stroke (engine); Structural equation modeling; Medicine; Confidence interval; Quality of life (healthcare); Health related quality of life; Demography; Gerontology; Prospective cohort study; Cohort; Cohort study; Physical therapy; Internal medicine; Statistics; Disease","score_opus":0.12189347346644647,"score_gpt":0.4679754524006153,"score_spread":0.3460819789341688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084545298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97501934,0.00035826577,0.0023963223,0.021735849,0.00011073012,0.00030498998,0.000001466694,0.000004518507,0.000068542],"genre_scores_gemma":[0.9948828,0.00041815327,0.0037106366,0.0008416973,0.000061006842,0.0000025433246,0.0000015426389,0.000007417054,0.00007419409],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9854128,0.009448301,0.0045998883,0.00024169637,0.00015193205,0.00014540402],"domain_scores_gemma":[0.9765501,0.020092888,0.002830976,0.00014283933,0.00016312231,0.00022008267],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046540897,0.00008926187,0.0018666643,0.00023845345,0.000016871812,0.0000034067348,0.000035112564,0.00024187061,0.000008801194],"category_scores_gemma":[0.11807925,0.00006106104,0.00009831243,0.00013941425,0.00026555816,0.00012162015,0.000016306269,0.0005345421,3.3757837e-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":[0.012867213,0.00016337,0.9832996,0.00012566948,0.00003895144,0.0000013814347,0.00038623545,0.000059419108,0.00017140691,0.0013602054,0.000041897933,0.0014846186],"study_design_scores_gemma":[0.0071815387,0.0020610655,0.98546296,0.00043774158,0.000013076132,0.00002501736,0.0001930373,0.0011662228,0.000008746619,0.003352141,0.00004829109,0.00005015162],"about_ca_topic_score_codex":0.00015826368,"about_ca_topic_score_gemma":0.00009954517,"teacher_disagreement_score":0.07153836,"about_ca_system_score_codex":0.000052551502,"about_ca_system_score_gemma":0.00029622743,"threshold_uncertainty_score":0.9817868},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2085262427","doi":"10.1016/j.jclinepi.2013.09.002","title":"Perceived disagreement (mostly) not confirmed by evidence … A reply to Watine et al.: Clinical practice guidelines: myths and misconceptions","year":2013,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; Health Sciences Centre","funders":"","keywords":"Terminology; Grading (engineering); Confusion; Clinical Practice; Popularity; Medicine; Mythology; Psychology; Alternative medicine; Medical education; Family medicine; Social psychology; Pathology; History; Linguistics; Engineering; Philosophy","score_opus":0.7306126208703128,"score_gpt":0.6711147098062826,"score_spread":0.05949791106403013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085262427","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.008962517,0.0013811166,0.009402247,0.9737181,0.0042848405,0.0019292643,0.00009695551,0.000046777714,0.00017819085],"genre_scores_gemma":[0.00065663405,0.018010857,0.16005424,0.8098349,0.009611393,0.000058221627,0.0002210013,0.0001076599,0.0014451151],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9288169,0.024362657,0.041778218,0.0020271223,0.0017917402,0.0012233566],"domain_scores_gemma":[0.37262478,0.5765106,0.03262965,0.002537992,0.013090424,0.0026065332],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.12256752,0.000908855,0.008384305,0.00030433378,0.0001369707,0.00007705775,0.00081440154,0.0020504799,0.0012972251],"category_scores_gemma":[0.8962719,0.00066768104,0.0021026707,0.0002846625,0.0010699367,0.0008752136,0.0005226416,0.012631226,0.00030255422],"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":[0.0026241278,0.00050697534,0.0070276065,0.00012397599,0.0011413886,0.00044804637,0.00006974575,0.000010731174,0.00006895731,0.00003691931,0.9565072,0.03143433],"study_design_scores_gemma":[0.0051541077,0.008253419,0.024471205,0.0015102118,0.0025734273,0.0016500723,0.00044204423,0.00038909784,0.0000013308626,0.00026555065,0.95474106,0.0005484768],"about_ca_topic_score_codex":0.0004751139,"about_ca_topic_score_gemma":0.000024198205,"teacher_disagreement_score":0.77370435,"about_ca_system_score_codex":0.00021477722,"about_ca_system_score_gemma":0.0022225373,"threshold_uncertainty_score":0.9996157},"labels":[],"label_agreement":null},{"id":"W2085441932","doi":"10.1016/j.jclinepi.2003.01.002","title":"Assessing accuracy of diagnosis-type indicators for flagging complications in administrative data","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":102,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Flagging; Medical diagnosis; Medicine; Complication; Medical record; Kappa; Chart; Emergency medicine; Statistics; Surgery; Radiology; Mathematics","score_opus":0.8122389124184975,"score_gpt":0.6703794114465711,"score_spread":0.14185950097192646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085441932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9619344,0.001280637,0.0028656446,0.032954443,0.00039423615,0.00037498525,0.000020402598,0.000005286573,0.00016998487],"genre_scores_gemma":[0.95486635,0.0016760613,0.040594872,0.0025212364,0.00027263776,0.000016972064,0.00003952512,0.000010661888,0.0000016599361],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995001,0.0006475541,0.00373492,0.00027010991,0.00012527205,0.00022112376],"domain_scores_gemma":[0.92983156,0.06514534,0.0038933877,0.00056782743,0.00028805315,0.00027385275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008558291,0.00012196568,0.0018808034,0.00020383396,0.000035671655,0.0000055582864,0.00029494136,0.00020324432,0.000025666555],"category_scores_gemma":[0.13472065,0.000086429514,0.0003196607,0.00023190786,0.00021414847,0.00020394548,0.00006554465,0.00047094424,0.0000029887672],"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":[0.00020826256,0.0017437101,0.96838075,0.00003926652,0.00024617783,0.000024586752,0.000043342105,0.00010075297,0.000010279859,0.002462859,0.0012221675,0.025517873],"study_design_scores_gemma":[0.0037774737,0.001723996,0.98319554,0.0005891685,0.00024395052,0.00006500457,0.00015139462,0.00010457199,0.00014728692,0.0064196405,0.0035183022,0.000063662774],"about_ca_topic_score_codex":0.000028023587,"about_ca_topic_score_gemma":0.000022629767,"teacher_disagreement_score":0.12616235,"about_ca_system_score_codex":0.00007226134,"about_ca_system_score_gemma":0.00083983166,"threshold_uncertainty_score":0.87256795},"labels":[],"label_agreement":null},{"id":"W2085807378","doi":"10.1016/j.jclinepi.2005.09.010","title":"Health Utilities Index mark 3 demonstrated construct validity in a population-based sample with type 2 diabetes","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute of Health Economics; University of Alberta","funders":"","keywords":"Sample (material); Construct validity; Type 2 diabetes; Index (typography); Construct (python library); Population; Medicine; Statistics; Environmental health; Gerontology; Psychology; Diabetes mellitus; Mathematics; Psychometrics; Computer science; Endocrinology; Chemistry; Chromatography","score_opus":0.6142770190092874,"score_gpt":0.5385583002412262,"score_spread":0.07571871876806124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085807378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9515452,0.0012030433,0.0060267076,0.039663434,0.00093402155,0.0002629678,0.000111917325,0.000015234239,0.00023748665],"genre_scores_gemma":[0.9685484,0.00009583401,0.016443122,0.014285262,0.00053427374,0.0000058194796,0.000045025085,0.000018206094,0.000024026956],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97532845,0.0061716493,0.017462926,0.00039460516,0.000090325826,0.000552026],"domain_scores_gemma":[0.9226658,0.06267559,0.013873819,0.0003190467,0.00018453259,0.00028122417],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10594849,0.000192028,0.0041761277,0.00039180947,0.0000886101,0.000017073073,0.00023922873,0.00032544148,0.00022304132],"category_scores_gemma":[0.09725442,0.000183843,0.00027732548,0.0002716336,0.00025234823,0.00022354418,0.000017983279,0.00068490155,0.000044617795],"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":[0.00011127329,0.000117147065,0.9766442,0.000103675906,0.000036005098,0.0000012990109,0.000013843821,0.0027267486,3.5828997e-8,0.015649756,0.0043566385,0.00023937355],"study_design_scores_gemma":[0.0013258035,0.0005296088,0.90270823,0.00012964995,0.000004753526,0.0000060828443,0.000053671756,0.009701797,1.3053658e-7,0.08254872,0.0028457625,0.0001457845],"about_ca_topic_score_codex":0.006351952,"about_ca_topic_score_gemma":0.0020067478,"teacher_disagreement_score":0.07393597,"about_ca_system_score_codex":0.000337029,"about_ca_system_score_gemma":0.0009997449,"threshold_uncertainty_score":0.9602294},"labels":[],"label_agreement":null},{"id":"W2086203781","doi":"10.1016/j.jclinepi.2007.03.010","title":"Application of generalizability theory confirmed lower reliability of the standard gamble than the feeling thermometer","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"University of Toronto; McMaster University","funders":"AstraZeneca","keywords":"Generalizability theory; GERD; Inter-rater reliability; Reliability (semiconductor); Medicine; COPD; Intra-rater reliability; Reflux; Physical therapy; Disease; Internal medicine; Psychology; Rating scale; Confidence interval; Developmental psychology","score_opus":0.5161787684129466,"score_gpt":0.554718994206375,"score_spread":0.03854022579342842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086203781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83513355,0.0009552407,0.12737879,0.033906173,0.0014888541,0.00045512803,0.000051648833,0.0000046717696,0.00062593824],"genre_scores_gemma":[0.9875174,0.00019377877,0.0039067836,0.0077284668,0.00057790836,0.0000067193237,0.0000013127996,0.000014163943,0.000053437914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9652125,0.010150072,0.023613343,0.0004260809,0.0001771547,0.00042081988],"domain_scores_gemma":[0.84317935,0.12462548,0.029720536,0.0015447527,0.00069657795,0.0002333123],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41248316,0.00015213843,0.0029680096,0.00010145368,0.00009755978,0.000005061295,0.00075103604,0.00035731285,0.00014957944],"category_scores_gemma":[0.21318762,0.000095406904,0.0009838836,0.0001874402,0.00087970373,0.00012974218,0.00009187363,0.0006825305,0.000017909279],"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":[0.00048966706,0.00017011452,0.8992798,0.00011810913,0.00011407306,1.5191942e-7,0.00025544147,0.0008809523,0.000012879299,0.09554572,0.0015502454,0.0015828914],"study_design_scores_gemma":[0.00069663813,0.00030544194,0.74255085,0.000042096406,0.00002524763,0.0000055565674,0.00025648132,0.0012688274,0.000033909037,0.24210332,0.012621574,0.00009002155],"about_ca_topic_score_codex":0.00022168478,"about_ca_topic_score_gemma":0.000056031797,"teacher_disagreement_score":0.19929552,"about_ca_system_score_codex":0.00016117917,"about_ca_system_score_gemma":0.0002726353,"threshold_uncertainty_score":0.79344004},"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":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2086226100","doi":"10.1016/j.jclinepi.2008.06.001","title":"The capture–mark–recapture technique can be used as a stopping rule when searching in systematic reviews","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Joseph’s Healthcare Hamilton; Foothills Medical Centre; McMaster University; University of Toronto; University of Calgary; Toronto Public Health","funders":"","keywords":"CINAHL; Systematic review; MEDLINE; Medicine; Computer science; Statistics; Medical physics; Information retrieval; Mathematics; Psychiatry","score_opus":0.9036751309230715,"score_gpt":0.6476465017044899,"score_spread":0.2560286292185816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086226100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43413094,0.10084414,0.18895292,0.24361031,0.006448278,0.014630045,0.000018342651,0.000026779802,0.011338254],"genre_scores_gemma":[0.8654977,0.015407949,0.07326549,0.029765384,0.0018525147,0.00036477222,0.0000035788382,0.000072039344,0.013770546],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.40463987,0.47623158,0.11151337,0.0013462607,0.0052229534,0.0010459702],"domain_scores_gemma":[0.2628133,0.64783925,0.08094882,0.005354977,0.0021377797,0.00090585905],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8177751,0.0004155237,0.021845456,0.00048160713,0.0002990392,0.00013520262,0.0037332552,0.0004872992,0.0006188341],"category_scores_gemma":[0.90061176,0.0001474976,0.006850707,0.00086349825,0.00039587906,0.00020943875,0.0002251457,0.002491939,0.00031724834],"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":[0.00023707452,0.0004504379,0.5145208,0.0046758517,0.0016380021,0.0007244547,0.005819121,0.0007480437,0.0001220588,0.014903538,0.43742174,0.018738838],"study_design_scores_gemma":[0.0018309245,0.0008138489,0.059808876,0.011869259,0.0009519174,0.005670798,0.00289653,0.0074892067,0.000008442918,0.2649208,0.6428448,0.0008946108],"about_ca_topic_score_codex":0.000105020714,"about_ca_topic_score_gemma":0.00029235662,"teacher_disagreement_score":0.45471194,"about_ca_system_score_codex":0.00009040434,"about_ca_system_score_gemma":0.00049965386,"threshold_uncertainty_score":0.9998093},"labels":[],"label_agreement":null},{"id":"W2086381401","doi":"10.1016/j.jclinepi.2009.08.016","title":"Knowledge translation is the use of knowledge in health care decision making","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":398,"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 Institutes of Health Research; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Knowledge translation; Knowledge management; Knowledge base; Action (physics); Health care; Psychological intervention; Computer science; Medicine; Nursing; Political science; Artificial intelligence","score_opus":0.9721615097379114,"score_gpt":0.8344599059882917,"score_spread":0.1377016037496197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086381401","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":[0.00007122348,0.9780782,0.0059914826,0.011523629,0.0024757572,0.0015657052,0.000055600933,0.000008365389,0.0002300599],"genre_scores_gemma":[0.00013320263,0.9618709,0.017720375,0.018889086,0.0012831248,0.000017737728,0.000005559728,0.00002944333,0.00005057166],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8914476,0.07763921,0.028929297,0.0005236598,0.0003714469,0.001088762],"domain_scores_gemma":[0.584151,0.39370927,0.020372638,0.00059573667,0.000757461,0.00041385228],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10776473,0.00035755814,0.008994797,0.0005960554,0.00036907414,0.000004953745,0.0009651745,0.0012357027,0.00028762312],"category_scores_gemma":[0.14373034,0.0002115429,0.0015177061,0.00089309865,0.00031893115,0.00019502662,0.00012659428,0.0048880586,0.00016771047],"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":[0.000049934602,0.000050870647,0.0014874593,0.0069194273,0.000025407628,0.0000015559154,0.006345247,0.000007634024,1.9702522e-9,0.00020104753,0.043731373,0.94118005],"study_design_scores_gemma":[0.0007438095,0.00046399204,0.005606807,0.03795467,0.000087142274,0.000015149519,0.00039339613,0.00009039762,1.329602e-9,0.0009396519,0.9535817,0.00012331715],"about_ca_topic_score_codex":0.000109476125,"about_ca_topic_score_gemma":0.0012735757,"teacher_disagreement_score":0.9410567,"about_ca_system_score_codex":0.0005124447,"about_ca_system_score_gemma":0.011649338,"threshold_uncertainty_score":0.9974077},"labels":[],"label_agreement":null},{"id":"W2086818113","doi":"10.1016/j.jclinepi.2010.03.019","title":"Level of evidence and conflict of interest disclosure associated with higher citation rates in orthopedics","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton General Hospital; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Citation; Conflict of interest; Medicine; Orthopedic surgery; Sample (material); Accounting; Business; Library science; Surgery; Computer science; Finance","score_opus":0.9832336359911132,"score_gpt":0.7643458543079781,"score_spread":0.21888778168313516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086818113","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":[0.03142944,0.9624691,0.000036038342,0.0032716224,0.0019980902,0.0005019579,0.0001971384,0.0000058294645,0.000090780915],"genre_scores_gemma":[0.03462059,0.96324956,0.00024348055,0.0010770776,0.0005587137,0.000009617312,0.00002098475,0.000026857373,0.00019312795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9725748,0.018433264,0.008009062,0.0003622865,0.00016186858,0.0004587283],"domain_scores_gemma":[0.8744525,0.11415015,0.009939952,0.0002067424,0.0006758685,0.00057482446],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.038673725,0.00039642883,0.0071817003,0.00028344392,0.000044575587,0.000003435851,0.00047800632,0.004018865,0.0002864695],"category_scores_gemma":[0.0725321,0.00023293865,0.00067307433,0.00037514366,0.0015164476,0.00014783628,0.00011298403,0.011383745,0.0000030897952],"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":[0.0012570774,0.00086792966,0.3062502,0.007836858,0.0011918457,0.00012590611,0.000093389084,0.000015859245,0.000008060584,0.0028536485,0.0014043226,0.6780949],"study_design_scores_gemma":[0.0026366902,0.0023993694,0.078062415,0.023921195,0.0027245583,0.00014559341,0.00003192014,0.00008322046,0.000010283222,0.0014759849,0.88813275,0.00037604084],"about_ca_topic_score_codex":0.000018414325,"about_ca_topic_score_gemma":0.00012853889,"teacher_disagreement_score":0.8867284,"about_ca_system_score_codex":0.00004991352,"about_ca_system_score_gemma":0.0010442407,"threshold_uncertainty_score":0.9972741},"labels":[],"label_agreement":null},{"id":"W2087018216","doi":"10.1016/j.jclinepi.2008.11.006","title":"Diagnostic test systematic reviews: Bibliographic search filters (“Clinical Queries”) for diagnostic accuracy studies perform well","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; University of Toronto; McMaster University","funders":"U.S. National Library of Medicine","keywords":"MEDLINE; Journal club; Systematic review; Medicine; Information retrieval; Medical physics; Meta-analysis; Data extraction; Computer science; Pathology","score_opus":0.9434927357553999,"score_gpt":0.7168723149679593,"score_spread":0.2266204207874406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087018216","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46335673,0.2749239,0.110988304,0.11374247,0.017485224,0.018027438,0.00009022884,0.000042083535,0.0013436363],"genre_scores_gemma":[0.6778173,0.25441602,0.041107956,0.019716784,0.0051205503,0.00026109317,0.000008413134,0.00004942574,0.0015024649],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.63236004,0.19734247,0.16276206,0.002155243,0.004018099,0.0013620483],"domain_scores_gemma":[0.0051497906,0.92411596,0.060213454,0.00377091,0.0057113273,0.0010385588],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.7985175,0.0007372185,0.04021815,0.002357204,0.00028364436,0.0002689101,0.0041164826,0.0006165025,0.001283081],"category_scores_gemma":[0.996251,0.00031764692,0.018937925,0.0041651707,0.00077090575,0.0006146765,0.00021940682,0.0017595418,0.001704052],"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":[0.00007855461,0.00058273337,0.56912935,0.00422881,0.0011852104,0.000055194676,0.00013025133,0.00011722041,6.5928583e-7,0.0012153923,0.3896375,0.03363912],"study_design_scores_gemma":[0.0032695448,0.01113974,0.6088343,0.019629564,0.006385036,0.000640585,0.0017264126,0.009045933,0.0000014304557,0.093996294,0.2442753,0.001055846],"about_ca_topic_score_codex":0.0000030316858,"about_ca_topic_score_gemma":0.000013169725,"teacher_disagreement_score":0.7267735,"about_ca_system_score_codex":0.00004650751,"about_ca_system_score_gemma":0.00029917387,"threshold_uncertainty_score":0.9999276},"labels":[],"label_agreement":null},{"id":"W2087165266","doi":"10.1016/j.jclinepi.2012.11.009","title":"Nonrandomized studies are not always found even when selection criteria for health systems intervention reviews include them: a methodological study","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Cochrane; Ottawa Hospital","funders":"","keywords":"Medicine; Systematic review; Psychological intervention; MEDLINE; Clinical study design; Interquartile range; Alternative medicine; Research design; Randomized controlled trial; Intervention (counseling); Health care; Family medicine; Gerontology; Clinical trial; Surgery; Nursing","score_opus":0.9918090233674235,"score_gpt":0.8687232033100825,"score_spread":0.12308582005734103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087165266","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":[0.00018115886,0.89676315,0.05558911,0.014901132,0.012820258,0.019586852,0.00009848488,0.00004362742,0.000016235696],"genre_scores_gemma":[0.000025936275,0.9311029,0.042069707,0.016082954,0.006114545,0.004066402,0.0000148451445,0.00005981583,0.00046292404],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.59410584,0.36121237,0.041811567,0.00094244094,0.00051286485,0.0014149286],"domain_scores_gemma":[0.34963962,0.5601101,0.085611455,0.00080184184,0.002673115,0.0011638742],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5198302,0.000747779,0.03131123,0.00047338766,0.0009400783,0.000024231655,0.0011113583,0.0012848099,0.00038697355],"category_scores_gemma":[0.6492616,0.00042379697,0.003660071,0.00042007264,0.00029623226,0.00031811156,0.00044541172,0.0042251917,0.00027354472],"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":[0.0015182527,0.0006643116,0.0019449975,0.06624011,0.0015318075,0.0000042954352,0.0022870605,0.0000023895138,9.818799e-8,0.00031094003,0.41667584,0.5088199],"study_design_scores_gemma":[0.008297721,0.003630277,0.0005013588,0.024437316,0.0009544867,0.000068558584,0.0017735303,0.00004921576,4.242964e-9,0.002168053,0.9578418,0.000277681],"about_ca_topic_score_codex":0.00027667123,"about_ca_topic_score_gemma":0.000210644,"teacher_disagreement_score":0.54116595,"about_ca_system_score_codex":0.0011547772,"about_ca_system_score_gemma":0.0025595257,"threshold_uncertainty_score":0.99982136},"labels":[],"label_agreement":null},{"id":"W2087259067","doi":"10.1016/s0895-4356(02)00537-1","title":"Comparative responsiveness of generic and specific quality-of-life instruments","year":2003,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":568,"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; McMaster University; London Health Sciences Centre","funders":"","keywords":"Metric (unit); Medicine; Quality of life (healthcare); Statistics; Mathematics; Operations management","score_opus":0.9391656927325536,"score_gpt":0.6811658925384191,"score_spread":0.2579998001941345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087259067","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":[0.009495231,0.98375845,0.0015626091,0.0015821193,0.0023393703,0.00052461476,0.00023682145,0.0000030793744,0.0004976782],"genre_scores_gemma":[0.0006278449,0.98762876,0.0086496025,0.002331718,0.0006282479,0.000011817601,0.000014501437,0.00003009624,0.00007739474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9066305,0.030388106,0.061750516,0.0006607584,0.0001382645,0.00043186202],"domain_scores_gemma":[0.82335037,0.09093599,0.08425064,0.0006425189,0.00033167168,0.00048879365],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22325313,0.00039376688,0.027852619,0.00068027485,0.000055706747,0.000007947257,0.0005781674,0.00096004276,0.00019230669],"category_scores_gemma":[0.14222203,0.0003687499,0.0018012432,0.00028147126,0.00064533914,0.00018361797,0.000100351135,0.0011108686,0.00010884109],"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":[0.0010958669,0.0016507591,0.19910958,0.07818655,0.0070446823,0.000009031006,0.00094254327,0.00018008026,2.3678727e-7,0.42740193,0.04393659,0.24044213],"study_design_scores_gemma":[0.0010571205,0.0005002022,0.014428375,0.0025446212,0.000090769485,0.000032565684,0.0001316232,0.00002848213,4.250764e-8,0.0120026665,0.96889216,0.00029138997],"about_ca_topic_score_codex":0.000051419727,"about_ca_topic_score_gemma":0.0000050066756,"teacher_disagreement_score":0.92495555,"about_ca_system_score_codex":0.00019138462,"about_ca_system_score_gemma":0.0012066545,"threshold_uncertainty_score":0.99987644},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","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":"W2087477832","doi":"10.1016/j.jclinepi.2013.08.004","title":"Using GRADE for evaluating the quality of evidence in hyperbaric oxygen therapy clarifies evidence limitations","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Cardiovascular and Diving-Related Complications","field":"Medicine","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":"McMaster University","funders":"","keywords":"Hyperbaric oxygen; Medicine; Decompression illness; Observational study; Quality of evidence; Randomized controlled trial; Evidence-based medicine; Grading (engineering); Carbon monoxide poisoning; Intensive care medicine; Physical therapy; Decompression; Poison control; Surgery; Decompression sickness; Alternative medicine; Emergency medicine; Internal medicine; Pathology","score_opus":0.9764702345378682,"score_gpt":0.7226793925698369,"score_spread":0.25379084196803126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087477832","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":[0.0034064008,0.9815501,0.009083777,0.0038193369,0.00053558376,0.0015737101,0.000004769669,0.000006466986,0.0000198743],"genre_scores_gemma":[0.001894976,0.9759654,0.020774834,0.00059390604,0.0006137693,0.00009529496,0.000004589702,0.00002762493,0.000029650559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.973544,0.015521079,0.009792215,0.00040093806,0.00041429314,0.00032747476],"domain_scores_gemma":[0.6220952,0.36455062,0.010382686,0.0011999451,0.0015349637,0.00023658104],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0844436,0.00029535816,0.007740804,0.00025710193,0.00009623233,0.000011088229,0.0005893732,0.0008095452,0.000016950313],"category_scores_gemma":[0.42074737,0.00014911058,0.005329108,0.00049384055,0.0004014907,0.00016204607,0.00008635408,0.0021265638,0.0000060120083],"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":[0.00024093034,0.00024097164,0.005217475,0.003583049,0.001768744,0.0000025692075,0.000077298784,0.00068972324,0.000014864334,0.0009007306,0.0004691068,0.98679453],"study_design_scores_gemma":[0.008421981,0.009078561,0.20908001,0.24035893,0.025263,0.0026381891,0.0003888992,0.008715703,0.000003152219,0.04482525,0.4497596,0.0014667105],"about_ca_topic_score_codex":0.00013314995,"about_ca_topic_score_gemma":0.000006517656,"teacher_disagreement_score":0.98532784,"about_ca_system_score_codex":0.00011690365,"about_ca_system_score_gemma":0.0018555792,"threshold_uncertainty_score":0.94275796},"labels":[],"label_agreement":null},{"id":"W2087553366","doi":"10.1016/j.jclinepi.2009.08.002","title":"Outpatient urticaria diagnosis codes have limited predictive value for same-day influenza vaccine adverse event detection","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Urticaria and Related Conditions","field":"Medicine","cited_by":5,"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":"U.S. Public Health Service; Centers for Disease Control and Prevention; Hamilton Health Sciences Foundation; U.S. Department of Health and Human Services","keywords":"Medicine; Vaccination; Rash; Influenza vaccine; Medical diagnosis; Diagnosis code; Adverse effect; Medical record; Outpatient clinic; Pediatrics; Internal medicine; Immunology; Pathology","score_opus":0.11683921531199239,"score_gpt":0.44951862731929515,"score_spread":0.3326794120073028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087553366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86092937,0.00094627467,0.1053897,0.028775632,0.002573945,0.0010415155,0.000040586307,0.000054843928,0.00024814968],"genre_scores_gemma":[0.98120874,0.0011116352,0.003893818,0.012231066,0.0014201829,0.00003718821,0.000015630516,0.00001914027,0.000062599334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924205,0.0019521713,0.004644193,0.0003276209,0.0002200581,0.00043547724],"domain_scores_gemma":[0.973517,0.02248101,0.0022871154,0.00030266665,0.0007848836,0.00062731944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065617133,0.00022848921,0.0021492892,0.00023764084,0.000111039575,0.000003971557,0.00014256511,0.0007954066,0.000061922714],"category_scores_gemma":[0.09364337,0.00015795275,0.0013117864,0.00015533897,0.0001386727,0.00011691816,0.00002619875,0.0013954547,0.000014255566],"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":[0.017658155,0.0057385718,0.848253,0.00004563418,0.009440333,0.00016872627,0.00073698675,0.01383872,0.0007908263,0.0059234044,0.015818952,0.081586696],"study_design_scores_gemma":[0.008692311,0.0204803,0.9221191,0.00030994526,0.0062380712,0.00018003206,0.00014752898,0.016075315,0.0002931378,0.017635057,0.007653731,0.00017551231],"about_ca_topic_score_codex":0.0000140548855,"about_ca_topic_score_gemma":0.000007646166,"teacher_disagreement_score":0.12027939,"about_ca_system_score_codex":0.00013395643,"about_ca_system_score_gemma":0.00022801441,"threshold_uncertainty_score":0.9139913},"labels":[],"label_agreement":null},{"id":"W2087888521","doi":"10.1016/j.jclinepi.2012.03.008","title":"Application of the systematic review and bibliometric network analysis (SeBriNA) methodology contextualizes evidence. Part 2: rituximab for non-Hodgkin's lymphoma","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Lymphoma Diagnosis and Treatment","field":"Medicine","cited_by":6,"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":"Canadian Institutes of Health Research","keywords":"Data extraction; Medicine; Randomized controlled trial; Systematic review; Grading (engineering); Citation; MEDLINE; Evidence-based medicine; Rituximab; Medical physics; Alternative medicine; Lymphoma; Computer science; Library science; Pathology","score_opus":0.5681861577016148,"score_gpt":0.5815530398219163,"score_spread":0.01336688212030146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087888521","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":[0.000025981293,0.98628026,0.0075712805,0.0016618731,0.00069555844,0.0037188123,0.00002713844,0.0000055570454,0.000013563616],"genre_scores_gemma":[0.0003721808,0.9882629,0.007465198,0.002250939,0.001038101,0.00051342795,0.0000190824,0.00003157107,0.00004661726],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9700301,0.016322164,0.012276667,0.0005196635,0.0003330817,0.00051827467],"domain_scores_gemma":[0.76530284,0.21025081,0.022063281,0.0011154327,0.00083579426,0.00043186842],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07392393,0.0005099268,0.03095388,0.003307292,0.00007398873,0.000007233733,0.0005536455,0.00092200097,0.000027039778],"category_scores_gemma":[0.14681761,0.00023974171,0.0073071024,0.011406542,0.00040918402,0.000081631224,0.00016857096,0.00045308584,0.00000898735],"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":[0.00009310728,0.00056465075,0.02174552,0.4975055,0.0132238,0.0000047897984,0.000003853619,0.0000011868659,7.606876e-9,0.000509621,0.002811176,0.4635368],"study_design_scores_gemma":[0.0023378928,0.001464226,0.022991681,0.34468928,0.38085434,0.0009050165,0.0000052913056,0.000045915993,1.06968315e-7,0.00042581317,0.24603194,0.00024850963],"about_ca_topic_score_codex":0.00002525464,"about_ca_topic_score_gemma":0.0000067697642,"teacher_disagreement_score":0.4632883,"about_ca_system_score_codex":0.00015113354,"about_ca_system_score_gemma":0.0005589866,"threshold_uncertainty_score":0.98343265},"labels":[],"label_agreement":null},{"id":"W2088177587","doi":"10.1016/s0895-4356(99)00188-2","title":"Co-morbidity data in outcomes research Are clinical data derived from administrative databases a reliable alternative to chart review?","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":263,"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; St. Paul's Hospital; Centre for Advancing Health Outcomes","funders":"Health Canada; Ministry of Health, British Columbia","keywords":"Medicine; Database; Chart; Psychological intervention; Population; MEDLINE; Emergency medicine; Medical emergency; Environmental health; Statistics; Computer science; Nursing","score_opus":0.9114352751679524,"score_gpt":0.7655030945658688,"score_spread":0.14593218060208357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088177587","genre_codex":"empirical","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":[0.48286182,0.014382308,0.00071880233,0.47678187,0.006731822,0.0030272463,0.0086998,0.000056337572,0.0067400155],"genre_scores_gemma":[0.06613564,0.3582088,0.032185588,0.5283521,0.009830662,0.00008586087,0.0030701095,0.00009623222,0.002035012],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.926912,0.052882012,0.016210219,0.0016024136,0.0008907135,0.0015026315],"domain_scores_gemma":[0.56941664,0.4095598,0.0088477805,0.008204639,0.0015627113,0.0024084214],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.18470079,0.00037185324,0.0068967356,0.00023967442,0.00039740323,0.0000079516985,0.0047322516,0.000656959,0.0053711613],"category_scores_gemma":[0.38535407,0.00026214347,0.00040200487,0.00044071945,0.00060653733,0.00082939083,0.0018204938,0.008551588,0.0015162294],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008708784,0.00029971814,0.5468162,0.0001507472,0.000109292574,0.00015273428,0.00005554267,9.303515e-7,3.611346e-7,0.000046811045,0.44279534,0.008701464],"study_design_scores_gemma":[0.0016002555,0.00048086498,0.5832133,0.001763842,0.000059530452,0.000006185641,0.000247516,0.000070353024,3.0741379e-7,0.0009893457,0.41142088,0.00014759315],"about_ca_topic_score_codex":0.0040366556,"about_ca_topic_score_gemma":0.0056979274,"teacher_disagreement_score":0.41672617,"about_ca_system_score_codex":0.00027237914,"about_ca_system_score_gemma":0.006063383,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W2088393947","doi":"10.1016/s0895-4356(03)00115-x","title":"Evaluation of the minimal important difference for the feeling thermometer and the St. George's Respiratory Questionnaire in patients with chronic airflow obstruction","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":177,"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; Health Sciences Centre","funders":"Medical Research Council Canada","keywords":"Medicine; Physical therapy; Quality of life (healthcare); Feeling; COPD; Confidence interval; Internal medicine; Psychology","score_opus":0.11910374631012842,"score_gpt":0.42906054435599256,"score_spread":0.3099567980458641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088393947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98818207,0.006400766,0.00034697252,0.0034673836,0.00048299244,0.001095584,0.000006122741,0.0000020726586,0.000016068123],"genre_scores_gemma":[0.9988137,0.00023463515,0.00018540115,0.00042452855,0.00028315219,0.000035151035,9.910011e-7,0.000013205358,0.00000922063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9896656,0.006806157,0.0023387508,0.00024067602,0.00067326793,0.0002755442],"domain_scores_gemma":[0.98464024,0.011579687,0.0020511101,0.00041671254,0.0011894167,0.00012285092],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038107455,0.0001417055,0.0009689623,0.00007271122,0.00010768431,0.000004858069,0.00020249479,0.00016371768,0.000031734446],"category_scores_gemma":[0.07167183,0.000054921842,0.00033344858,0.00016559772,0.0011269322,0.00006560259,0.000044939577,0.0008217707,2.4953468e-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":[0.0029117789,0.00013944623,0.9489898,0.00006818893,0.00019711624,0.0000011721867,0.00004926647,0.0002748544,0.000013204811,0.0009499384,0.000027979113,0.046377234],"study_design_scores_gemma":[0.011003387,0.00082342734,0.9720604,0.00029570598,0.00049119955,0.000022136563,0.00006781474,0.0077308756,0.000007410795,0.007261822,0.00018115643,0.000054701806],"about_ca_topic_score_codex":0.000021147229,"about_ca_topic_score_gemma":0.00006235494,"teacher_disagreement_score":0.046322532,"about_ca_system_score_codex":0.00024190331,"about_ca_system_score_gemma":0.0012426786,"threshold_uncertainty_score":0.99047077},"labels":[],"label_agreement":null},{"id":"W2089287976","doi":"10.1016/j.jclinepi.2007.08.016","title":"Determination of the minimal clinically important difference for seven fatigue measures in rheumatoid arthritis","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":122,"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; Child and Family Research Institute; Arthritis Research Centre of Canada","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Rheumatoid arthritis; Medicine; Internal medicine; Minimal clinically important difference; Physical therapy; Randomized controlled trial","score_opus":0.22442491151977478,"score_gpt":0.4602761356826791,"score_spread":0.23585122416290433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089287976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832476,0.00521587,0.0050593973,0.005564209,0.0004756203,0.00035887084,0.000011840775,0.000004877168,0.000061710285],"genre_scores_gemma":[0.88622016,0.102132276,0.01080937,0.000613583,0.00017206703,0.000011356032,0.0000020801062,0.0000122867095,0.000026821595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9892909,0.0022570903,0.007507074,0.00021745318,0.0003615612,0.0003659406],"domain_scores_gemma":[0.97305685,0.022381324,0.0034180605,0.00029674848,0.00058182166,0.0002651747],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018751236,0.0001448032,0.0023880934,0.00012598636,0.00006534,0.00000270626,0.00031249825,0.00029640293,0.000028662556],"category_scores_gemma":[0.15365812,0.00008620224,0.00095457863,0.00012765493,0.0008186281,0.00007151997,0.000053618267,0.000864363,0.0000011084577],"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":[0.001972943,0.00036694345,0.88601476,0.000024257337,0.00006727991,0.00004648582,0.00015514441,0.000004385695,0.00017940607,0.00040701136,0.00052569853,0.11023567],"study_design_scores_gemma":[0.0061637843,0.0033617357,0.97436196,0.00091164355,0.0000053876793,0.0010397796,0.000070685586,0.0009561497,0.00012647214,0.010418846,0.0024940069,0.0000895469],"about_ca_topic_score_codex":0.000030233596,"about_ca_topic_score_gemma":0.000101124024,"teacher_disagreement_score":0.13490687,"about_ca_system_score_codex":0.0000234434,"about_ca_system_score_gemma":0.00070267566,"threshold_uncertainty_score":0.853471},"labels":[],"label_agreement":null},{"id":"W2089521868","doi":"10.1016/j.jclinepi.2004.10.005","title":"Quality-adjusted life years was a poor predictor of women's willingness to pay in acute and chronic conditions: results of a survey","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":30,"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":"Willingness to pay; Medicine; Quality-adjusted life year; EQ-5D; Quality of life (healthcare); Breast cancer; Visual analogue scale; Logistic regression; Nausea; Health economics; Demography; Cancer; Public health; Physical therapy; Health related quality of life; Cost effectiveness; Internal medicine; Economics; Nursing","score_opus":0.6159332084358381,"score_gpt":0.5643214250178599,"score_spread":0.05161178341797823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089521868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9574544,0.0011382389,0.0011075216,0.038529906,0.000627351,0.00031978812,0.00076963403,0.000005226581,0.000047920537],"genre_scores_gemma":[0.98514694,0.0013470094,0.003532975,0.00921982,0.0006277109,0.000016160084,0.00001885348,0.000016807815,0.00007371643],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9630829,0.007959667,0.027852826,0.00045761344,0.00011469897,0.000532272],"domain_scores_gemma":[0.9262751,0.055889,0.016554117,0.00039471543,0.000268699,0.0006184106],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2318287,0.00016122432,0.0050215228,0.00043518923,0.000027424243,0.000006014213,0.00034317674,0.00039463764,0.00009305159],"category_scores_gemma":[0.31477332,0.00015507347,0.0002909378,0.0002708628,0.00028034137,0.00021204456,0.00007176223,0.0005791231,0.00004650165],"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":[0.0009977414,0.00033665524,0.980986,0.00022114864,0.0003209129,0.0000021001956,0.0009739527,0.0018751838,0.0000050501644,0.006904338,0.006454544,0.0009223901],"study_design_scores_gemma":[0.00402334,0.00096623495,0.9770121,0.00018107194,0.000010911025,0.000007299376,0.00018430619,0.0014921066,0.0000015328804,0.0058280868,0.010152883,0.00014012284],"about_ca_topic_score_codex":0.00077824463,"about_ca_topic_score_gemma":0.000834992,"teacher_disagreement_score":0.082944624,"about_ca_system_score_codex":0.00043458256,"about_ca_system_score_gemma":0.0007422881,"threshold_uncertainty_score":0.790994},"labels":[],"label_agreement":null},{"id":"W2089670708","doi":"10.1016/j.jclinepi.2008.06.021","title":"Explaining pragmatic trials to pragmatic policymakers","year":2009,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Health","funders":"","keywords":"Pragmatism; Compromise; Flexibility (engineering); Politics; Value (mathematics); Quality (philosophy); Adaptation (eye); Political science; Positive economics; Epistemology; Psychology; Law and economics; Medicine; Sociology; Economics; Law; Computer science; Management; Philosophy","score_opus":0.9425925536791687,"score_gpt":0.7119308854126087,"score_spread":0.23066166826655998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089670708","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010263918,0.0012731237,0.05658835,0.9302879,0.0049257204,0.0012728072,0.000030886826,0.000005997277,0.0045887996],"genre_scores_gemma":[0.0004957287,0.00026163395,0.081534825,0.88855386,0.020538604,0.000022569247,0.000018076116,0.00004544618,0.008529235],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.09145045,0.642933,0.25317344,0.0021253647,0.008961513,0.0013561932],"domain_scores_gemma":[0.04108459,0.7210995,0.22722614,0.0059104254,0.0036080328,0.0010713004],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9321597,0.001050305,0.08621248,0.00207841,0.00013564806,0.00043019277,0.0068823183,0.0027333614,0.0097320685],"category_scores_gemma":[0.98707986,0.00044577426,0.029225456,0.001509413,0.00024559686,0.00028689008,0.0002710637,0.006939843,0.0063042967],"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":[0.000043929216,0.000050599356,0.0017922212,0.00010383982,0.0012153133,0.00021703403,0.00010564675,0.00025485258,5.10146e-7,0.00039968896,0.9462531,0.04956327],"study_design_scores_gemma":[0.0006151592,0.0008391798,0.0034926024,0.00061926834,0.0015297444,0.00039229682,0.00010570192,0.0006172238,9.159786e-8,0.07400188,0.9174388,0.0003480187],"about_ca_topic_score_codex":0.000010917262,"about_ca_topic_score_gemma":0.000005493331,"teacher_disagreement_score":0.07816649,"about_ca_system_score_codex":0.00010408149,"about_ca_system_score_gemma":0.00095624715,"threshold_uncertainty_score":0.99979943},"labels":[],"label_agreement":null},{"id":"W2089749652","doi":"10.1016/s0895-4356(00)00325-5","title":"Loss to follow-up in a longitudinal study on aging in Spain","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":85,"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":"Longitudinal study; Demography; Baseline (sea); Logistic regression; Multivariate statistics; Multivariate analysis; Gerontology; Medicine; Longitudinal data; Population; Psychology; Statistics","score_opus":0.4652982675971093,"score_gpt":0.600173543447422,"score_spread":0.13487527585031273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089749652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89492726,0.00009555742,0.00024035081,0.1017001,0.0018521548,0.00020511934,4.2104304e-7,0.000005071928,0.00097393733],"genre_scores_gemma":[0.9792702,0.00049204583,0.00036827635,0.018522883,0.001083655,0.0000041647054,1.0346537e-7,0.000006370124,0.0002522608],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9854915,0.00948311,0.0037559122,0.0002528503,0.00028172272,0.00073487125],"domain_scores_gemma":[0.9624083,0.036040477,0.00081720663,0.00014705076,0.00008657508,0.00050036097],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076571554,0.0001107199,0.0017230288,0.0002599093,0.000090207715,0.000010166185,0.0003731786,0.00022063118,0.00011301811],"category_scores_gemma":[0.1288856,0.0000868507,0.00028725015,0.00040414988,0.00013849561,0.000105195075,0.000050742437,0.0010285238,0.000032767428],"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":[0.0003665121,0.00036853473,0.98294944,0.000005338462,0.000012464092,0.00039372686,0.0015305365,0.00014557072,1.9759918e-8,0.0050015273,0.00074457814,0.008481726],"study_design_scores_gemma":[0.0015961605,0.000713911,0.9720559,0.00013025707,0.000005957861,0.0000066896505,0.0033718213,0.000016756278,1.9492122e-8,0.005001001,0.01702301,0.00007851263],"about_ca_topic_score_codex":0.0068025184,"about_ca_topic_score_gemma":0.05196344,"teacher_disagreement_score":0.08434295,"about_ca_system_score_codex":0.00017018369,"about_ca_system_score_gemma":0.00039513796,"threshold_uncertainty_score":0.9998113},"labels":[],"label_agreement":null},{"id":"W2089878277","doi":"10.1016/j.jclinepi.2013.05.013","title":"Systematic reviews of complex interventions: framing the review question","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":99,"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":"Psychological intervention; Framing (construction); Interdependence; Management science; Scope (computer science); Systematic review; Engineering ethics; Intervention (counseling); Computer science; Risk analysis (engineering); Psychology; MEDLINE; Medicine; Sociology; Political science; Engineering; Social science","score_opus":0.9638615941696256,"score_gpt":0.7300001158249738,"score_spread":0.23386147834465176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089878277","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007759795,0.565522,0.347791,0.06711187,0.0029300791,0.00621889,0.000004051429,0.0000040317705,0.0026583062],"genre_scores_gemma":[0.30758196,0.44952482,0.16660295,0.06435509,0.0026195457,0.00046249706,0.000009088805,0.000055791665,0.008788269],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.3525598,0.46832573,0.17550763,0.00060867076,0.0026693472,0.00032884095],"domain_scores_gemma":[0.050478864,0.658348,0.2766042,0.006283807,0.007792398,0.0004926595],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8379889,0.00023517392,0.026065903,0.00019294836,0.000067281384,0.00006287368,0.0026994639,0.00016552443,0.012677749],"category_scores_gemma":[0.9415157,0.00007303017,0.01516272,0.0006692868,0.00025729794,0.00024815672,0.00014004053,0.0006849768,0.0025107372],"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":[0.000007544193,0.00021037723,0.031973448,0.05725374,0.00096278504,0.0000024911114,0.000051213374,0.000039692488,0.000007810057,0.012971475,0.82860315,0.06791627],"study_design_scores_gemma":[0.0006361746,0.0010668031,0.25034183,0.21295117,0.0052270666,0.0004940989,0.00044139326,0.010605461,6.4434875e-7,0.20552404,0.31232756,0.00038375056],"about_ca_topic_score_codex":0.000012277779,"about_ca_topic_score_gemma":0.0000054243765,"teacher_disagreement_score":0.5162756,"about_ca_system_score_codex":0.00001686652,"about_ca_system_score_gemma":0.00006425607,"threshold_uncertainty_score":0.9982659},"labels":[],"label_agreement":null},{"id":"W2089908284","doi":"10.1016/j.jclinepi.2004.03.017","title":"An observational study found that authors of randomized controlled trials frequently use concealment of randomization and blinding, despite the failure to report these methods","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":213,"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; Vancouver Coastal Health Research Institute; University of British Columbia; McMaster University","funders":"","keywords":"Blinding; Randomization; Observational study; Randomized controlled trial; Medicine; Confidence interval; MEDLINE; Meta-analysis; Surgery; Internal medicine","score_opus":0.9830326412179182,"score_gpt":0.7819282752615037,"score_spread":0.20110436595641457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089908284","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039881966,0.68377423,0.29524475,0.0015535613,0.0018127846,0.013575336,0.000026243706,0.000002025265,0.000022883643],"genre_scores_gemma":[0.0033801456,0.83382547,0.16066916,0.00050411647,0.0007075637,0.00036179592,0.000019441975,0.000037920738,0.0004943722],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.03887332,0.76129675,0.1939337,0.001252729,0.0042872513,0.00035626546],"domain_scores_gemma":[0.022706173,0.71733254,0.25256342,0.0026536891,0.0042967387,0.0004474382],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9629712,0.00077515637,0.17511171,0.001030156,0.00009756659,0.00024262731,0.0024708796,0.00080033595,0.0007058472],"category_scores_gemma":[0.9753773,0.00023690185,0.035025526,0.0010214408,0.0006189125,0.0003439452,0.00017364569,0.0011287344,0.000007223682],"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":[0.14389636,0.0028821512,0.08493339,0.0044131074,0.109038286,0.00014757148,0.0022741393,0.005076572,0.0000022784627,0.02372911,0.006249412,0.6173576],"study_design_scores_gemma":[0.42090744,0.0026955479,0.004824916,0.011015176,0.11315108,0.0005988062,0.0009826078,0.0016074685,3.1150782e-7,0.06684084,0.37660947,0.00076631893],"about_ca_topic_score_codex":0.00003463492,"about_ca_topic_score_gemma":0.000019528687,"teacher_disagreement_score":0.6165913,"about_ca_system_score_codex":0.00006425453,"about_ca_system_score_gemma":0.0014392269,"threshold_uncertainty_score":0.97463846},"labels":[],"label_agreement":null},{"id":"W2089918264","doi":"10.1016/j.jclinepi.2013.06.020","title":"Cohort study of trials submitted to ethics committee identified discrepant reporting of outcomes in publications","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":32,"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":"Inselspital, Universitätsspital Bern; Compute Canada; Canadian Institutes of Health Research; University of Bern","keywords":"Medicine; Confidence interval; Odds ratio; Protocol (science); Internal medicine; Cohort; Specialty; Cohort study; Clinical trial; Randomized controlled trial; Family medicine; Alternative medicine; Pathology","score_opus":0.9760676327081949,"score_gpt":0.7560917649542921,"score_spread":0.21997586775390277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089918264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96238,0.00009467213,0.009516298,0.025291013,0.0007914243,0.001496628,0.000004054238,0.0000015331211,0.00042436752],"genre_scores_gemma":[0.98902595,0.00003979105,0.008887078,0.0009877249,0.00010861191,0.000036491507,0.000001142247,0.000007304097,0.0009058895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.14875305,0.42065698,0.42188475,0.0014132005,0.0066891685,0.0006028429],"domain_scores_gemma":[0.012739787,0.6606757,0.31295854,0.004316345,0.008811559,0.00049805734],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91446394,0.00023113581,0.03237116,0.00090889283,0.000053185708,0.00007499638,0.0022078378,0.00035874877,0.002113986],"category_scores_gemma":[0.9898561,0.00009833152,0.0053332034,0.0013984403,0.00017576403,0.00025721308,0.00025754113,0.0012228193,0.00011486183],"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":[0.000024013458,0.00066050095,0.97790223,0.00001722973,0.00072902534,0.0000026384462,0.00034837396,0.00018664583,0.00001804803,0.0010849338,0.016760517,0.002265817],"study_design_scores_gemma":[0.00056235434,0.0003712754,0.9789198,0.000051292474,0.000365421,0.00000966081,0.0013176522,0.00043277733,0.0000019431984,0.01668336,0.0012104152,0.00007403257],"about_ca_topic_score_codex":0.00054181775,"about_ca_topic_score_gemma":0.0005242367,"teacher_disagreement_score":0.24001871,"about_ca_system_score_codex":0.000020797002,"about_ca_system_score_gemma":0.00033471533,"threshold_uncertainty_score":0.9987982},"labels":[],"label_agreement":null},{"id":"W2090132603","doi":"10.1016/j.jclinepi.2011.01.012","title":"GRADE guidelines 6. Rating the quality of evidence—imprecision","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":2682,"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":"Quality of evidence; Quality (philosophy); Medicine; Meta-analysis; Internal medicine","score_opus":0.9117431739366876,"score_gpt":0.6635809712434746,"score_spread":0.24816220269321299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090132603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9256772,0.004156136,0.004702992,0.061116327,0.0014543994,0.00020507014,8.5522856e-7,0.00001125436,0.0026757722],"genre_scores_gemma":[0.9491712,0.0043732203,0.03396454,0.010370687,0.001653192,0.0000017384415,5.140671e-7,0.000012713701,0.0004521933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98330396,0.0069123805,0.008884605,0.00019403516,0.0004503445,0.00025464434],"domain_scores_gemma":[0.77958405,0.21246712,0.005786778,0.0005919309,0.001185952,0.00038415025],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.100861326,0.00013924125,0.0041151815,0.000066323424,0.000039900733,0.0000020019795,0.00028116122,0.00030301264,0.00015051854],"category_scores_gemma":[0.47061384,0.000057271856,0.0026000373,0.00012904023,0.00043139525,0.0000835716,0.000059317044,0.0008148369,0.000010829047],"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":[0.0016006265,0.00015042281,0.93155736,0.000040042036,0.00021361615,0.0000531406,0.000105974934,0.000009876557,0.00013563927,0.006454339,0.0029970806,0.05668191],"study_design_scores_gemma":[0.0010659002,0.0010424063,0.9716333,0.00032065474,0.00021022343,0.00039678422,0.00013164437,0.000063147534,0.00009595781,0.0042934585,0.020677788,0.000068696354],"about_ca_topic_score_codex":0.000085407126,"about_ca_topic_score_gemma":0.000005122383,"teacher_disagreement_score":0.3697525,"about_ca_system_score_codex":0.000013735521,"about_ca_system_score_gemma":0.00021083177,"threshold_uncertainty_score":0.9258525},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2090554279","doi":"10.1016/j.jclinepi.2014.12.015","title":"Quality of evidence is a key determinant for making a strong GRADE guidelines recommendation","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Medicine; Guideline; Logistic regression; Grading (engineering); Odds ratio; Quality of evidence; Confidence interval; Evidence-based medicine; Family medicine; Internal medicine; Meta-analysis; Alternative medicine; Pathology","score_opus":0.9958577060447447,"score_gpt":0.8140133657190499,"score_spread":0.18184434032569474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090554279","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":[0.15931793,0.0018694617,0.7675788,0.068653,0.0019685847,0.0004219061,0.000013299544,0.000001601168,0.00017546532],"genre_scores_gemma":[0.6293088,0.00043819103,0.3624273,0.0060717673,0.0010878748,0.000008205793,0.0000013813573,0.00001034238,0.00064612395],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.72281194,0.13951245,0.1329032,0.0010464545,0.0032282032,0.0004977564],"domain_scores_gemma":[0.33039024,0.51623434,0.13647318,0.0025475768,0.013776132,0.0005785474],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8019962,0.0002001188,0.012037186,0.00024322666,0.000043366752,0.000047858175,0.0015299338,0.00023930937,0.0006333338],"category_scores_gemma":[0.9490541,0.000080688915,0.005311414,0.0003613861,0.0001446223,0.00034100443,0.00012945951,0.00035892366,0.000060420534],"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":[0.00023987124,0.00008803063,0.56456614,0.000076834396,0.0002485515,0.0000014857025,0.0001509186,0.00019408847,0.000008564798,0.0019561918,0.2250137,0.20745565],"study_design_scores_gemma":[0.0018119777,0.0019394289,0.2355415,0.0008754707,0.0006451313,0.000098846416,0.0010726315,0.06591278,0.000015265772,0.22801374,0.4637558,0.00031745422],"about_ca_topic_score_codex":0.00001884454,"about_ca_topic_score_gemma":0.00003806718,"teacher_disagreement_score":0.46999088,"about_ca_system_score_codex":0.00003053046,"about_ca_system_score_gemma":0.00041014366,"threshold_uncertainty_score":0.822838},"labels":[],"label_agreement":null},{"id":"W2090732416","doi":"10.1016/j.jclinepi.2005.07.012","title":"Performance measures were necessary to obtain a complete picture of osteoarthritic patients","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":304,"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; Health Sciences Centre; Women's College Hospital; McMaster University","funders":"","keywords":"WOMAC; Physical therapy; Medicine; Regression analysis; Association (psychology); Osteoarthritis; Timed Up and Go test; Physical medicine and rehabilitation; Self-report study; Psychology; Statistics; Clinical psychology; Mathematics; Balance (ability)","score_opus":0.14462094428942673,"score_gpt":0.42678203776302637,"score_spread":0.28216109347359963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090732416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793786,0.00044437684,0.00050745765,0.018103652,0.0007967437,0.00021662274,0.000010655944,0.000011560772,0.00053032255],"genre_scores_gemma":[0.9759757,0.00029694085,0.0113364095,0.0112537695,0.0009763113,0.000001775081,0.0000035607611,0.00001892158,0.00013662624],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99326694,0.0012535681,0.004498527,0.00022632135,0.00036256094,0.00039208742],"domain_scores_gemma":[0.98721707,0.009601319,0.001787258,0.00031940197,0.0005347651,0.0005401593],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006636329,0.00019557249,0.0028116372,0.00017164099,0.000040365587,0.0000023172304,0.00022869771,0.00028045522,0.00015579959],"category_scores_gemma":[0.049268164,0.00013443714,0.0006683811,0.00013083471,0.00026944026,0.00013346683,0.000080844984,0.0009111448,0.00008754928],"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":[0.0012817194,0.00032405742,0.892408,0.00007485933,0.000111851696,0.000012292711,0.000082010454,0.00050658954,0.00006804945,0.00006827413,0.004760624,0.10030165],"study_design_scores_gemma":[0.0046782154,0.005588737,0.94262135,0.00039756062,0.00010362601,0.00015301732,0.000045619185,0.0002590768,0.000033478234,0.00013846121,0.04587035,0.00011053052],"about_ca_topic_score_codex":0.000003571026,"about_ca_topic_score_gemma":0.000021274222,"teacher_disagreement_score":0.100191124,"about_ca_system_score_codex":0.000042735155,"about_ca_system_score_gemma":0.0002220301,"threshold_uncertainty_score":0.95874023},"labels":[],"label_agreement":null},{"id":"W2091007651","doi":"10.1016/j.jclinepi.2005.12.019","title":"The Trial Protocol Tool: the PRACTIHC software tool that supported the writing of protocols for pragmatic randomized controlled trials","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Institute for Clinical Evaluative Sciences","funders":"University of Aberdeen; European Commission","keywords":"Protocol (science); Randomized controlled trial; Computer science; Calculator; Resource (disambiguation); Research design; Sample (material); Software; Medical physics; Medicine; Surgery; Alternative medicine; Operating system","score_opus":0.8871167904669771,"score_gpt":0.6961434218136551,"score_spread":0.19097336865332204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091007651","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004432694,0.0002576352,0.14916359,0.0391382,0.0010883654,0.80541223,0.00001614643,0.000005222459,0.00048592282],"genre_scores_gemma":[0.017176928,0.000048386042,0.027156625,0.0029375132,0.004819319,0.9445524,0.0000034693073,0.000036472866,0.0032688524],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.075845145,0.7155728,0.20126899,0.00092031376,0.005576748,0.00081600336],"domain_scores_gemma":[0.014645838,0.79437524,0.18480705,0.0024871437,0.003580648,0.00010408016],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9622469,0.00046615014,0.05022554,0.0001663666,0.00051913154,0.0005196292,0.0037075842,0.00040803742,0.0010779052],"category_scores_gemma":[0.98860866,0.000101554324,0.032016743,0.000476119,0.0009291525,0.00026427335,0.00014487875,0.0011003957,0.00003692737],"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":[0.7497583,0.00046277704,0.0070517273,0.00013939687,0.0041878675,0.0000036905342,0.00006577905,0.00040568516,0.000005306776,0.01419108,0.19554003,0.02818836],"study_design_scores_gemma":[0.57664055,0.0010047684,0.0014645081,0.00021601284,0.0026837597,0.000050967967,0.00026417707,0.0073233354,0.000004363881,0.19988555,0.2103119,0.00015011204],"about_ca_topic_score_codex":0.000008003934,"about_ca_topic_score_gemma":0.000012659799,"teacher_disagreement_score":0.18569446,"about_ca_system_score_codex":0.000021949574,"about_ca_system_score_gemma":0.0008754068,"threshold_uncertainty_score":0.99983525},"labels":[],"label_agreement":null},{"id":"W2091033400","doi":"10.1016/j.jclinepi.2014.04.009","title":"A summary to communicate evidence from systematic reviews to the public improved understanding and accessibility of information: a randomized controlled trial","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cochrane; University of Ottawa; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Grading (engineering); Randomized controlled trial; Interquartile range; Medicine; Quality of evidence; Systematic review; Evidence-based medicine; Plain language; MEDLINE; Intervention (counseling); Medical education; Family medicine; Alternative medicine; Nursing; Surgery; Pathology","score_opus":0.915415759837285,"score_gpt":0.6442581166617436,"score_spread":0.27115764317554136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091033400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077721424,0.009827372,0.82544446,0.070228875,0.0019823262,0.014372723,0.000004984289,0.0000028455634,0.00041500258],"genre_scores_gemma":[0.96645004,0.0023841965,0.021490308,0.008843474,0.00041813735,0.00029444008,9.221452e-7,0.000006079034,0.00011242024],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.16399449,0.67893,0.1528611,0.000750826,0.0029988908,0.0004647077],"domain_scores_gemma":[0.021587977,0.87932044,0.09174043,0.0044373926,0.0022734785,0.00064029364],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90835065,0.00029824307,0.0440545,0.000372637,0.0001328159,0.0003362643,0.0037698913,0.0002173502,0.0003445059],"category_scores_gemma":[0.98311734,0.000093229326,0.00754169,0.000734793,0.00031441875,0.000686063,0.00049444055,0.0006271662,0.00013738463],"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":[0.8714256,0.00028223702,0.017769473,0.0033752369,0.004461323,0.0000010188692,0.0018765153,0.00014509985,0.000010457815,0.018304111,0.06392575,0.01842316],"study_design_scores_gemma":[0.74811983,0.0018297445,0.0029940342,0.009059788,0.0042541013,0.000026381602,0.0011788483,0.08201188,4.6452396e-7,0.1278843,0.022255654,0.00038494493],"about_ca_topic_score_codex":0.00002145131,"about_ca_topic_score_gemma":0.0000583521,"teacher_disagreement_score":0.8887286,"about_ca_system_score_codex":0.00004691399,"about_ca_system_score_gemma":0.0001899507,"threshold_uncertainty_score":0.97013754},"labels":[],"label_agreement":null},{"id":"W2091538045","doi":"10.1016/j.jclinepi.2014.03.013","title":"Scoping reviews: time for clarity in definition, methods, and reporting","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2793,"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; St. Michael's Hospital; University of Ottawa; University of Toronto","funders":"","keywords":"CLARITY; Terminology; Confusion; Consistency (knowledge bases); Computer science; Management science; Knowledge translation; Field (mathematics); Systematic review; Data science; Process management; Knowledge management; MEDLINE; Psychology; Engineering; Political science; Artificial intelligence","score_opus":0.9759914182322607,"score_gpt":0.7661860522381492,"score_spread":0.20980536599411148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091538045","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045423813,0.010253397,0.93050736,0.010299295,0.0008872076,0.0007447786,0.0000012965035,0.000001756686,0.0018810873],"genre_scores_gemma":[0.0137324575,0.0012589943,0.97851574,0.0055111866,0.0006747692,0.00001343052,0.0000010612432,0.000007646519,0.00028471628],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3353485,0.41852352,0.24258305,0.0014401925,0.0014948644,0.00060986384],"domain_scores_gemma":[0.02907995,0.747585,0.21868217,0.0021214036,0.0020665075,0.0004649435],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9390732,0.00017559384,0.018932406,0.00025390965,0.00006356452,0.00006266397,0.0006961687,0.00027854447,0.0005585405],"category_scores_gemma":[0.98582196,0.00007885404,0.0036962926,0.00034785157,0.00013211938,0.00016267921,0.000087613844,0.0006014596,0.000122223],"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":[0.000033952063,0.000060028764,0.6485832,0.00025924185,0.00010482931,0.000003607951,0.000039341245,0.00003951752,0.000017071568,0.010206339,0.03737844,0.30327448],"study_design_scores_gemma":[0.0005460806,0.00030931784,0.20371546,0.0010551357,0.00021044588,0.00014260043,0.000025466761,0.011468651,0.0000012644432,0.6459467,0.13644849,0.0001304203],"about_ca_topic_score_codex":0.000002931079,"about_ca_topic_score_gemma":0.000009209986,"teacher_disagreement_score":0.63574034,"about_ca_system_score_codex":0.000011305501,"about_ca_system_score_gemma":0.00009413899,"threshold_uncertainty_score":0.9956326},"labels":[],"label_agreement":null},{"id":"W2091676488","doi":"10.1016/j.jclinepi.2014.05.006","title":"Considering intellectual, in addition to financial, conflicts of interest proved important in a clinical practice guideline: a descriptive study","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":77,"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; McMaster University","funders":"","keywords":"Guideline; Descriptive research; Conflict of interest; Actuarial science; Descriptive statistics; Clinical Practice; Medicine; Family medicine; Accounting; Business; Psychology; Finance; Statistics; Mathematics; Pathology","score_opus":0.8680484211535888,"score_gpt":0.703771948976174,"score_spread":0.1642764721774148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091676488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97368497,0.0003787171,0.0012105732,0.020213813,0.0031786186,0.0009172982,0.00002054364,0.000012991709,0.0003824612],"genre_scores_gemma":[0.9517074,0.00085154694,0.0053865584,0.040816657,0.0011682608,0.000026537022,0.000004179341,0.000019604882,0.000019255978],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.94898164,0.032399178,0.017061211,0.0005867317,0.0001909915,0.0007802483],"domain_scores_gemma":[0.8242286,0.16564023,0.006922944,0.00042213494,0.0013648074,0.0014212773],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.11679711,0.00030348322,0.0034261437,0.0003821052,0.00005797855,0.000006159196,0.0005009149,0.001426046,0.00044174405],"category_scores_gemma":[0.59772927,0.00025693703,0.00045369356,0.00045656203,0.00053721265,0.00022194615,0.000210923,0.007924863,0.000029727626],"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":[0.020439794,0.00878077,0.8489068,0.000112503396,0.0004025809,0.0007482013,0.0031729408,0.0010948009,0.0003202911,0.00388296,0.04665373,0.06548463],"study_design_scores_gemma":[0.0173825,0.019469785,0.21183106,0.0006704314,0.00045145076,0.00037000555,0.0042233127,0.011360359,0.0003766118,0.008460389,0.7247883,0.0006157678],"about_ca_topic_score_codex":0.00013710931,"about_ca_topic_score_gemma":0.00064809417,"teacher_disagreement_score":0.6781346,"about_ca_system_score_codex":0.0001305385,"about_ca_system_score_gemma":0.0008879756,"threshold_uncertainty_score":0.99998826},"labels":[],"label_agreement":null},{"id":"W2091686363","doi":"10.1016/s0895-4356(99)00119-5","title":"Ready, set, stop, and standing","year":2000,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Dissent; Suspect; Set (abstract data type); Rhetorical question; Measure (data warehouse); Quality (philosophy); Scopus; Reading (process); Psychology; Quality of life (healthcare); Computer science; Epistemology; MEDLINE; Linguistics; Philosophy; Political science; Law; Data mining","score_opus":0.8538401883715452,"score_gpt":0.6206322234516659,"score_spread":0.23320796491987927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091686363","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":[0.0066585415,0.010696427,0.0017851904,0.97213656,0.0039647003,0.00027526988,0.0003136991,0.00001682294,0.00415282],"genre_scores_gemma":[0.0009120321,0.010389583,0.0055204793,0.9614664,0.019480478,0.000007882778,0.00005294585,0.00006312445,0.0021071308],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95308304,0.0095248325,0.03567788,0.0008041681,0.00013224404,0.0007778438],"domain_scores_gemma":[0.87926537,0.088205785,0.031357646,0.0006199486,0.00014110803,0.00041012358],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.2064617,0.00038239177,0.009715398,0.0005611327,0.00012074846,0.00003547156,0.00058531604,0.0024400789,0.0011875982],"category_scores_gemma":[0.14795107,0.0003892316,0.00088052265,0.00009609045,0.00040025075,0.0003158434,0.000075002004,0.0048522027,0.00082592433],"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":[0.000046967725,0.000024476773,0.037617005,0.00026500036,0.0002556154,0.00004901999,0.000096003,0.000024605883,1.054665e-8,0.0067946115,0.9538812,0.0009454906],"study_design_scores_gemma":[0.00083878037,0.0003959174,0.011501557,0.00023294591,0.000036827583,0.00018645113,0.000043491535,0.00028789643,1.4865816e-8,0.08445142,0.9017273,0.00029740614],"about_ca_topic_score_codex":0.00018971358,"about_ca_topic_score_gemma":0.000010301088,"teacher_disagreement_score":0.07868095,"about_ca_system_score_codex":0.00030161274,"about_ca_system_score_gemma":0.00042856295,"threshold_uncertainty_score":0.999952},"labels":[],"label_agreement":null},{"id":"W2092146657","doi":"10.1016/j.jclinepi.2007.08.005","title":"Identifying phases of investigation helps planning, appraising, and applying the results of explanatory prognosis studies","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":137,"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 Work & Health; Health Canada; Centre for Disability Prevention and Rehabilitation; University Health Network; University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Explanatory model; Medicine; Phase (matter); Data science; Computer science; Statistics","score_opus":0.972763530646457,"score_gpt":0.7069032762591264,"score_spread":0.26586025438733063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092146657","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":[0.9729863,0.016916737,0.0068422933,0.0021200639,0.0005868747,0.0003266009,0.0000053305635,0.0000013503267,0.00021449031],"genre_scores_gemma":[0.9858547,0.0020959484,0.011123349,0.0005166502,0.00025611647,0.000010750138,7.6733807e-7,0.000004837959,0.00013691321],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.878167,0.061200954,0.057029024,0.00067827286,0.002637441,0.00028731933],"domain_scores_gemma":[0.3883052,0.49278334,0.1125869,0.0019592377,0.0040006535,0.0003646538],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43961093,0.00017654162,0.008312621,0.00030041736,0.00013306455,0.000019533956,0.0008904235,0.00014927835,0.000046447112],"category_scores_gemma":[0.7210379,0.0000695697,0.0017952587,0.00045779557,0.001084696,0.00020731482,0.00012996906,0.0004344245,0.0000064825667],"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":[0.00009433144,0.000057149293,0.92978317,0.00008212552,0.00071639754,0.000010456236,0.0015773618,0.0003430403,0.000051191204,0.00051948323,0.05708462,0.009680702],"study_design_scores_gemma":[0.0019183814,0.00087629166,0.89577895,0.0011174352,0.0009702035,0.00040151316,0.008175518,0.003052508,0.00019189663,0.05437454,0.032917824,0.00022493128],"about_ca_topic_score_codex":0.00000835256,"about_ca_topic_score_gemma":0.0000036957508,"teacher_disagreement_score":0.4898618,"about_ca_system_score_codex":0.0000074811874,"about_ca_system_score_gemma":0.000117227915,"threshold_uncertainty_score":0.57703847},"labels":[],"label_agreement":null},{"id":"W2092217399","doi":"10.1016/j.jclinepi.2008.09.008","title":"Mathematical weighting of a clinimetric index (Pediatric Ulcerative Colitis Activity Index) was superior to the judgmental approach","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"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. Michael's Hospital; Institute for Work & Health; Izaak Walton Killam Health Centre; Mount Sinai Hospital; University of Toronto; SickKids Foundation; Dalhousie University; Hospital for Sick Children","funders":"","keywords":"Weighting; Medicine; Delphi method; Cohort; Index (typography); Ulcerative colitis; Statistics; Physical therapy; Mathematics; Computer science; Internal medicine; Disease","score_opus":0.08119004234655063,"score_gpt":0.4055945678576713,"score_spread":0.32440452551112064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092217399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708504,0.00013767283,0.026320528,0.0014138278,0.00033933512,0.0003286569,0.00001674593,0.0000046927803,0.00058815524],"genre_scores_gemma":[0.9906995,0.00018777873,0.0046718544,0.0023578766,0.0020026958,0.000007727827,0.000004306001,0.00001638366,0.00005186626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99199796,0.0036053408,0.003284123,0.00037998488,0.00028729558,0.00044530386],"domain_scores_gemma":[0.9934695,0.0032683874,0.002077393,0.00043197162,0.00031884492,0.0004339276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013672795,0.00024077212,0.0014827257,0.00016356916,0.00008657687,0.000010202098,0.00055733975,0.0005137098,0.000039652423],"category_scores_gemma":[0.034911558,0.00015800934,0.0008473473,0.00027353762,0.00024263877,0.000014612707,0.00015883877,0.00080455875,0.000012903967],"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":[0.008523527,0.0017550129,0.95550543,0.00009473472,0.0004228241,0.00009439923,0.00013374368,0.0013587731,0.00065487885,0.0014220104,0.004827661,0.025207022],"study_design_scores_gemma":[0.0014520198,0.0016017831,0.9924688,0.00001962867,0.00009838895,0.000101021,0.00006985115,0.0011908249,0.00018287309,0.0020257134,0.000616002,0.00017311251],"about_ca_topic_score_codex":0.0000036895483,"about_ca_topic_score_gemma":0.0000050871827,"teacher_disagreement_score":0.036963366,"about_ca_system_score_codex":0.000030353978,"about_ca_system_score_gemma":0.00038520712,"threshold_uncertainty_score":0.9732178},"labels":[],"label_agreement":null},{"id":"W2092282228","doi":"10.1016/j.jclinepi.2013.08.003","title":"The CARE guidelines: consensus-based clinical case report guideline development","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":661,"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; Ottawa Hospital","funders":"Department of Orthopedic Surgery, Baylor College of Medicine","keywords":"Checklist; Guideline; Timeline; Medicine; Psychological intervention; Medical education; MEDLINE; Systematic review; Transparency (behavior); Informed consent; Health care; Family medicine; Alternative medicine; Nursing; Psychology; Computer science; Political science; Pathology","score_opus":0.7002852489669151,"score_gpt":0.6670484953116461,"score_spread":0.033236753655269013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092282228","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":[0.69025147,0.0021132745,0.027261838,0.2713206,0.007136241,0.0012674354,0.0000063846846,0.00006280538,0.00057997374],"genre_scores_gemma":[0.32127237,0.00089358864,0.5639157,0.104778506,0.008344156,0.00003824928,0.00007893872,0.00008374274,0.00059468485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9427356,0.00745284,0.047683854,0.0006739004,0.000713225,0.00074058573],"domain_scores_gemma":[0.60822797,0.33214617,0.033017054,0.002373405,0.02179393,0.002441467],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12618425,0.0003951751,0.0037654978,0.00014484928,0.00030182084,0.000031700885,0.0004309794,0.00075377186,0.00048066664],"category_scores_gemma":[0.7363281,0.00022721263,0.001809443,0.00023877468,0.00089073885,0.00013521875,0.00017440021,0.0025737237,0.00023648342],"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":[0.001077709,0.00033408834,0.25379845,0.000034745393,0.00046763933,0.015990524,0.00002089842,0.00016415677,0.000004488441,0.00007263566,0.390853,0.33718166],"study_design_scores_gemma":[0.007880893,0.0023966234,0.08736497,0.0001911335,0.000650795,0.08170382,0.0015094418,0.004677013,0.000013026421,0.0011127907,0.8121931,0.00030641328],"about_ca_topic_score_codex":0.00023679383,"about_ca_topic_score_gemma":0.00019988214,"teacher_disagreement_score":0.61014384,"about_ca_system_score_codex":0.00015251552,"about_ca_system_score_gemma":0.0047145863,"threshold_uncertainty_score":0.99972737},"labels":[],"label_agreement":null},{"id":"W2092322472","doi":"10.1016/j.jclinepi.2009.03.012","title":"Absolute risk reductions and numbers needed to treat can be obtained from adjusted survival models for time-to-event outcomes","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":146,"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":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Proportional hazards model; Covariate; Statistics; Hazard ratio; Population; Regression analysis; Absolute risk reduction; Medicine; Observational study; Event (particle physics); Regression; Survival analysis; Relative risk; Confidence interval; Cohort study; Cohort; Econometrics; Mathematics","score_opus":0.4477967427714711,"score_gpt":0.5484543726722505,"score_spread":0.10065762990077942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092322472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33011577,0.00002886178,0.6099085,0.058369134,0.00058473443,0.0003878789,0.00023340732,0.000019984696,0.0003517173],"genre_scores_gemma":[0.07328715,0.00011139523,0.9171406,0.008126712,0.0006617226,0.00001176704,0.0000050412946,0.000022648384,0.0006329648],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99306947,0.0026681474,0.0033826767,0.00032673863,0.00015672961,0.0003962148],"domain_scores_gemma":[0.91074175,0.086638674,0.001331735,0.00027384138,0.00030120625,0.00071276963],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010971681,0.00021892878,0.0026142492,0.00009939868,0.00008843865,0.000011272088,0.00023439716,0.0002817944,0.00012719641],"category_scores_gemma":[0.20571783,0.00015339664,0.0004871985,0.00011305297,0.00010638471,0.00005235786,0.000045821314,0.00053044845,0.0000083121895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055563394,0.0017773405,0.018661348,0.000075810276,0.0014455358,0.000040522606,0.0013591975,0.006118659,0.00026896995,0.25808185,0.25460845,0.45200595],"study_design_scores_gemma":[0.001540952,0.0017779911,0.054698113,0.000056166013,0.00036176547,0.000012123681,0.00014478352,0.012606101,0.0000071676127,0.9273843,0.0012210312,0.00018950808],"about_ca_topic_score_codex":0.00033385816,"about_ca_topic_score_gemma":0.000049036877,"teacher_disagreement_score":0.6693024,"about_ca_system_score_codex":0.00004517362,"about_ca_system_score_gemma":0.000107628155,"threshold_uncertainty_score":0.80097276},"labels":[],"label_agreement":null},{"id":"W2093043874","doi":"10.1016/j.jclinepi.2011.03.017","title":"GRADE guidelines: 7. Rating the quality of evidence—inconsistency","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2369,"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 Agency for Drugs and Technologies in Health; McMaster University","funders":"","keywords":"Spurious relationship; Econometrics; Credibility; Statistics; Quality (philosophy); Statistical hypothesis testing; Consistency (knowledge bases); Omnibus test; Point estimation; Publication bias; Meta-analysis; Confidence interval; Medicine; Subgroup analysis; Psychology; Mathematics","score_opus":0.9961731356351076,"score_gpt":0.7900796750717212,"score_spread":0.2060934605633864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093043874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69617164,0.014800352,0.19210044,0.08176416,0.005469823,0.0007318917,0.0000064845894,0.0000046775112,0.008950512],"genre_scores_gemma":[0.8785539,0.0009220158,0.112684555,0.005932226,0.000858783,0.0000033337692,1.8440599e-7,0.000007485272,0.0010374809],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.31778803,0.41913044,0.25431663,0.0012802997,0.0068286,0.00065601186],"domain_scores_gemma":[0.051743325,0.76873726,0.16398115,0.004945299,0.010121759,0.00047121767],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8883877,0.00023105933,0.014804277,0.00018608573,0.00008999002,0.000033276418,0.003512414,0.0002587075,0.0037656159],"category_scores_gemma":[0.9731324,0.00006786801,0.009116963,0.0006463248,0.00056153757,0.00025214563,0.00020041442,0.00080769975,0.00027443477],"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":[0.000066091794,0.00010090401,0.8528852,0.00003134393,0.0003977842,0.000004934329,0.00023637862,0.000048817004,0.000021447444,0.013075,0.07734961,0.055782482],"study_design_scores_gemma":[0.0003181162,0.00043039158,0.7401724,0.00022986901,0.0003841752,0.00007982375,0.0010615011,0.0012151239,0.0000111958325,0.23106661,0.02490721,0.00012360446],"about_ca_topic_score_codex":0.00005917606,"about_ca_topic_score_gemma":0.000046899517,"teacher_disagreement_score":0.3496068,"about_ca_system_score_codex":0.000011334568,"about_ca_system_score_gemma":0.00032464598,"threshold_uncertainty_score":0.99982196},"labels":[],"label_agreement":null},{"id":"W2093174411","doi":"10.1016/j.jclinepi.2009.01.005","title":"Walter O. Spitzer: measure developer, prophet, and mentor","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Palliative Care and End-of-Life Issues","field":"Medicine","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; William Osler Health System","funders":"National Cancer Institute","keywords":"Scopus; Psychology; Construct (python library); Gerontology; Quality of life (healthcare); Library science; MEDLINE; Medical education; Medicine; Family medicine; Computer science; Political science","score_opus":0.5734340837379728,"score_gpt":0.6031540992639196,"score_spread":0.02972001552594683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093174411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9418465,0.014245894,0.0026661558,0.037652344,0.00077306404,0.00015460604,0.0000020109896,0.00001033727,0.0026491156],"genre_scores_gemma":[0.90788645,0.015006743,0.058091808,0.016577601,0.0019001734,0.0000010254311,0.0000021817782,0.000012497623,0.00052153855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99563056,0.00097035104,0.00281262,0.00017371387,0.00018102926,0.0002317055],"domain_scores_gemma":[0.99291414,0.004761776,0.0013619812,0.00015556664,0.0004578426,0.0003487122],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009131873,0.00013049065,0.002174393,0.000078886944,0.000020071251,0.0000019293834,0.00010718487,0.00026240046,0.000056001616],"category_scores_gemma":[0.05067003,0.00007859804,0.00036043822,0.00007651977,0.00019238744,0.00006367483,0.000022115404,0.00060608797,0.000007857127],"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":[0.0012450995,0.00025477263,0.84865075,0.00005569219,0.00025359396,0.000111169444,0.00018774615,0.0000033509784,0.0003056461,0.00090566545,0.014591717,0.1334348],"study_design_scores_gemma":[0.0036519459,0.0050122715,0.7997061,0.0010177233,0.00023529536,0.00030457726,0.00007784409,0.00006413678,0.00028223297,0.0060084835,0.18350749,0.00013193091],"about_ca_topic_score_codex":0.0000053624826,"about_ca_topic_score_gemma":0.0000014812296,"teacher_disagreement_score":0.16891576,"about_ca_system_score_codex":0.000023190349,"about_ca_system_score_gemma":0.00021727846,"threshold_uncertainty_score":0.9573266},"labels":[],"label_agreement":null},{"id":"W2093404647","doi":"10.1016/j.jclinepi.2015.02.007","title":"Offering personalized health behavior feedback did not increase response rate: a randomized controlled trial","year":2015,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"BC Cancer Agency; University of British Columbia; Athabasca University","funders":"","keywords":"Incentive; Randomized controlled trial; Economics; Selection bias; Selection (genetic algorithm); Econometrics; Actuarial science; Public economics; Medicine; Psychology; Microeconomics; Computer science; Internal medicine","score_opus":0.6388266116732406,"score_gpt":0.6104490682305866,"score_spread":0.028377543442653974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093404647","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19506696,0.002300839,0.0007686141,0.78087395,0.01661773,0.0040352237,0.00004395838,0.00004719872,0.00024550216],"genre_scores_gemma":[0.0035884602,0.0047086296,0.0073908456,0.9338991,0.03821173,0.0003968197,0.000041097595,0.00010200703,0.011661323],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.07498732,0.90455467,0.016944736,0.00086594437,0.0011164526,0.0015308541],"domain_scores_gemma":[0.17506774,0.8020746,0.019738935,0.0005785437,0.0013605888,0.0011795858],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.9228962,0.0007166333,0.028394124,0.00064344157,0.0004819472,0.000044365803,0.0013932022,0.0051922286,0.0007801386],"category_scores_gemma":[0.9681229,0.0004900552,0.007650896,0.00030733194,0.004876432,0.00019108527,0.00015200362,0.010063686,0.000075698605],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6447787,0.00020862008,0.00020448286,0.000013728075,0.00072070496,0.0006347823,0.0004544562,0.000001279285,0.0000013148592,0.00007884009,0.3524323,0.00047073537],"study_design_scores_gemma":[0.6260412,0.0017197434,0.0018387797,0.00011591575,0.00076197006,0.00007184239,0.00011885698,0.000008912669,1.2575377e-7,0.0011672449,0.36786282,0.00029262545],"about_ca_topic_score_codex":0.001091565,"about_ca_topic_score_gemma":0.00010885071,"teacher_disagreement_score":0.19147849,"about_ca_system_score_codex":0.0004121282,"about_ca_system_score_gemma":0.014056652,"threshold_uncertainty_score":0.9997551},"labels":[],"label_agreement":null},{"id":"W2093484576","doi":"10.1016/j.jclinepi.2009.08.020","title":"The Kaiser Permanente inpatient risk adjustment methodology was valid in an external patient population","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":89,"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; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Medicine; Statistic; Confidence interval; Comorbidity; Inpatient care; Retrospective cohort study; Population; Emergency medicine; Cohort study; Cohort; Statistics; Health care; Internal medicine","score_opus":0.5545479560641987,"score_gpt":0.5787759050040904,"score_spread":0.024227948939891664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093484576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349535,0.0032081208,0.00050866796,0.010922218,0.0015036387,0.00029092073,0.0000023690357,0.0000072380085,0.00006146373],"genre_scores_gemma":[0.9716234,0.0064003253,0.01331252,0.007868799,0.0007539483,0.000009015014,0.0000084258745,0.000010590718,0.000012974193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9854464,0.009131536,0.0044639613,0.0002946693,0.000271935,0.00039152688],"domain_scores_gemma":[0.97836334,0.017788446,0.0028922725,0.00036791587,0.00021373574,0.00037432378],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0152445035,0.0001927322,0.0018741564,0.00013107076,0.00007708787,0.0000059028393,0.00016148367,0.0002783089,0.00005696041],"category_scores_gemma":[0.023091605,0.0001022396,0.00065938133,0.000092513495,0.00010489401,0.00008795404,0.00003136251,0.0009381568,0.00001055679],"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":[0.0012387987,0.0012316691,0.735048,0.000002882897,0.00008653914,0.00006467647,0.00009493569,0.00046041727,0.000008594115,0.0007865066,0.00063640386,0.26034054],"study_design_scores_gemma":[0.0027184032,0.010815656,0.9703039,0.000107324035,0.00022684621,0.00016988594,0.000073890566,0.00067607226,0.000024037387,0.012585431,0.0022177775,0.00008077916],"about_ca_topic_score_codex":0.000116206815,"about_ca_topic_score_gemma":0.00006273317,"teacher_disagreement_score":0.26025978,"about_ca_system_score_codex":0.00014798768,"about_ca_system_score_gemma":0.00008224565,"threshold_uncertainty_score":0.9851373},"labels":[],"label_agreement":null},{"id":"W2094320722","doi":"10.1016/j.jclinepi.2014.02.020","title":"Validation study in four health-care databases: upper gastrointestinal bleeding misclassification affects precision but not magnitude of drug-related upper gastrointestinal bleeding risk","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","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":"Jewish General Hospital","funders":"National Institute for Health and Care Research","keywords":"Medicine; Upper gastrointestinal bleeding; Gastrointestinal bleeding; Drug; Internal medicine; Database; Endoscopy; Pharmacology; Computer science","score_opus":0.3984434955961565,"score_gpt":0.5416387192837193,"score_spread":0.14319522368756282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094320722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9465462,0.000094855364,0.04350625,0.0066986238,0.0015351729,0.0011313802,0.000023085357,0.00004201174,0.00042242595],"genre_scores_gemma":[0.9428414,0.00024232666,0.054070964,0.0015744927,0.0011032978,0.000028169181,0.000046706893,0.000030948875,0.00006166888],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.963533,0.021938121,0.01214676,0.000534776,0.0007856879,0.0010616574],"domain_scores_gemma":[0.91209465,0.0713734,0.014013479,0.0004917822,0.001196381,0.0008303093],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09961371,0.00034140848,0.0027727925,0.0006429099,0.00051283743,0.000008782034,0.00048865,0.00027899307,0.00019520019],"category_scores_gemma":[0.22782789,0.0002651281,0.0003900704,0.00038456864,0.0001990506,0.00045112186,0.00018723414,0.0047950866,0.00007635894],"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":[0.0012157251,0.0003039817,0.97638595,0.00067689223,0.000026259788,0.0000057755647,0.0013123361,0.00064873346,0.0000612175,0.00048241284,0.0024556732,0.016425017],"study_design_scores_gemma":[0.005310472,0.003937958,0.9563824,0.0061162347,0.00009661627,0.00012666256,0.00622574,0.020603223,0.000008643894,0.0004850474,0.00052668375,0.0001803111],"about_ca_topic_score_codex":0.00042422945,"about_ca_topic_score_gemma":0.00010822346,"teacher_disagreement_score":0.12821418,"about_ca_system_score_codex":0.0003749479,"about_ca_system_score_gemma":0.0011505152,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W2094826099","doi":"10.1016/s0895-4356(00)00357-7","title":"The randomized placebo-phase design for clinical trials","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":51,"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; Hospital for Sick Children; McMaster University; SickKids Foundation; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Randomized controlled trial; Placebo; Accrual; Research design; Medicine; Clinical trial; Clinical study design; N of 1 trial; Sample size determination; Randomization; Medical physics; Physical therapy; Alternative medicine; Surgery; Statistics; Internal medicine; Mathematics","score_opus":0.9496119838420165,"score_gpt":0.7275679699574721,"score_spread":0.22204401388454442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094826099","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":[0.020125145,0.010481276,0.7069272,0.25083452,0.008751865,0.0022673192,0.000044068533,0.000017352262,0.0005513094],"genre_scores_gemma":[0.1645172,0.16877902,0.3219088,0.28397873,0.053936664,0.0009581703,0.000035599056,0.0002414975,0.0056443005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6643555,0.18637018,0.14678568,0.0010207068,0.00019246012,0.0012754382],"domain_scores_gemma":[0.057846274,0.8808268,0.059572894,0.00067034684,0.0004022507,0.00068143965],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90656567,0.000250624,0.015227775,0.0001949143,0.0002843588,0.000043199052,0.0007731183,0.00072519336,0.00025814128],"category_scores_gemma":[0.94229144,0.00017325394,0.004120329,0.000115076924,0.00075541076,0.00024833207,0.000049198534,0.0010437446,0.00040112835],"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":[0.15035132,0.0006394832,0.032636635,0.000057167315,0.0016152533,0.0000064355568,0.000105905085,0.00060327456,1.0589324e-7,0.22746736,0.56902874,0.017488329],"study_design_scores_gemma":[0.18085769,0.0011624956,0.0024013247,0.00005478096,0.000105496845,0.000047112175,0.00009988163,0.025842078,1.5184476e-7,0.33642927,0.4528085,0.00019124111],"about_ca_topic_score_codex":0.000027046046,"about_ca_topic_score_gemma":0.000009050873,"teacher_disagreement_score":0.69445664,"about_ca_system_score_codex":0.00012059468,"about_ca_system_score_gemma":0.0006128615,"threshold_uncertainty_score":0.9993922},"labels":[],"label_agreement":null},{"id":"W2094956413","doi":"10.1016/j.jclinepi.2007.11.016","title":"ROC area discrimination (ROCAD) curve: a new method of evaluating the discriminating ability of ordinal scales","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"Arthritis Research Centre of Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Receiver operating characteristic; Ordinal Scale; Ordinal data; Statistics; Mathematics; Scale (ratio); Correlation; Area under curve; Pattern recognition (psychology); Artificial intelligence; Computer science; Medicine","score_opus":0.7187415650752808,"score_gpt":0.6319747242458305,"score_spread":0.0867668408294503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094956413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95297,0.0013208976,0.02919611,0.015669262,0.0003455301,0.00023274153,0.000003633387,0.000004790026,0.00025702777],"genre_scores_gemma":[0.9189219,0.00074164633,0.07917141,0.0006673729,0.0004457818,0.000004647244,0.0000036005738,0.0000109885095,0.00003267442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9886326,0.0049502435,0.005438623,0.0002695606,0.00044871098,0.00026025338],"domain_scores_gemma":[0.92719096,0.06571219,0.0055998587,0.00041519722,0.00080042245,0.00028139216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029032461,0.00017608152,0.002659652,0.00009595433,0.00007589989,0.0000016601564,0.00021208932,0.00021587215,0.000092138645],"category_scores_gemma":[0.16150239,0.00009113712,0.0011237309,0.00016593424,0.0004751613,0.00008042037,0.00007048128,0.00065904204,0.0000015082026],"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":[0.0007437285,0.00093213865,0.8385466,0.0000912713,0.0003189207,0.000013439394,0.00032984267,0.00026151555,0.00033772975,0.0009697642,0.0011926708,0.15626241],"study_design_scores_gemma":[0.0024036935,0.0046796524,0.9763793,0.00039417527,0.00068755174,0.00043893338,0.00032359906,0.0038943735,0.00043248892,0.010212222,0.00008556754,0.000068441215],"about_ca_topic_score_codex":0.00020209856,"about_ca_topic_score_gemma":0.000025298532,"teacher_disagreement_score":0.15619397,"about_ca_system_score_codex":0.000058336573,"about_ca_system_score_gemma":0.00043978458,"threshold_uncertainty_score":0.9998154},"labels":[],"label_agreement":null},{"id":"W2095460484","doi":"10.1016/j.jclinepi.2005.11.015","title":"Administrative data accurately identified intensive care unit admissions in Ontario","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Health Sciences Centre; Western University; Institute for Clinical Evaluative Sciences; Lawson Health Research Institute; Sunnybrook Health Science Centre","funders":"Health Canada; Canada Research Chairs","keywords":"Medicine; Intensive care unit; Diagnosis code; Health care; Emergency medicine; Health information; Medical emergency; Database; Intensive care medicine; Environmental health; Computer science; Population","score_opus":0.8532998571331445,"score_gpt":0.6336099933575668,"score_spread":0.21968986377557764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095460484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782824,0.0014137507,0.000060171024,0.017461887,0.0009076206,0.00021855657,0.000019889283,0.0000067355954,0.0016289827],"genre_scores_gemma":[0.9899687,0.0003313051,0.002382074,0.0062419167,0.00047436025,0.0000040579007,0.00014939516,0.000011832194,0.0004363595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99365044,0.0014136642,0.004088682,0.00036793578,0.00017628145,0.0003029939],"domain_scores_gemma":[0.9769487,0.018566746,0.002163494,0.0006573278,0.0011432385,0.000520532],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004640156,0.00018342263,0.002341096,0.00014256708,0.000037049707,0.000007252771,0.00031649813,0.0003283659,0.0005436374],"category_scores_gemma":[0.07887966,0.000119221055,0.00042422692,0.0001200829,0.00015210001,0.00013042019,0.00012711523,0.0012831582,0.00003080696],"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":[0.0007690054,0.00052885857,0.9716758,0.000010686088,0.00020034866,0.00095888425,0.0001366948,0.000020909498,0.0000053593603,0.00047083767,0.022827286,0.0023953046],"study_design_scores_gemma":[0.0036030798,0.0016465816,0.96212876,0.00031488203,0.00028704252,0.00030315283,0.001395577,0.000032641485,0.000028162622,0.0020604902,0.028110784,0.00008882152],"about_ca_topic_score_codex":0.008966648,"about_ca_topic_score_gemma":0.081456855,"teacher_disagreement_score":0.07423951,"about_ca_system_score_codex":0.00014878511,"about_ca_system_score_gemma":0.0019970657,"threshold_uncertainty_score":0.99763274},"labels":[],"label_agreement":null},{"id":"W2096074908","doi":"10.1016/j.jclinepi.2012.03.013","title":"GRADE guidelines: 14. Going from evidence to recommendations: the significance and presentation of recommendations","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":1406,"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":"Grading (engineering); Guideline; Presentation (obstetrics); Intervention (counseling); Medicine; Medical education; Psychology; Computer science; Nursing; Engineering; Surgery; Pathology","score_opus":0.7721252335838884,"score_gpt":0.6612626555094365,"score_spread":0.11086257807445188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096074908","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":[0.27221316,0.0006802116,0.05875382,0.6663798,0.001178104,0.0007302216,0.000013447843,0.000009372547,0.00004186914],"genre_scores_gemma":[0.55341846,0.009628139,0.3822985,0.052252244,0.0021391907,0.000051893727,0.000036127145,0.000024578829,0.00015086825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98510927,0.0041676247,0.009908224,0.00030751977,0.0002809331,0.00022643835],"domain_scores_gemma":[0.7793411,0.21086137,0.0065825204,0.00049838406,0.002304303,0.00041230343],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026555363,0.00014672778,0.0013720363,0.00011946535,0.0000784307,0.00001569269,0.00025196665,0.0001739366,0.0006206092],"category_scores_gemma":[0.5166856,0.000094244555,0.00031845027,0.00024765966,0.00021068378,0.0005343401,0.00010910348,0.0008032729,0.000048537335],"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":[0.0004710452,0.00021669098,0.2619773,0.00003186116,0.00024212344,0.0000022903664,0.00018853079,0.00012853494,0.00083836564,0.00033555538,0.3613576,0.37421012],"study_design_scores_gemma":[0.0029995318,0.0023260831,0.86161155,0.0012932586,0.0006845704,0.00009561269,0.002038135,0.0066635055,0.00014260974,0.03516062,0.08678128,0.00020321838],"about_ca_topic_score_codex":0.0009013587,"about_ca_topic_score_gemma":0.00010641204,"teacher_disagreement_score":0.6141276,"about_ca_system_score_codex":0.000042777145,"about_ca_system_score_gemma":0.0003002051,"threshold_uncertainty_score":0.92036116},"labels":[],"label_agreement":null},{"id":"W2096833944","doi":"10.1016/j.jclinepi.2006.10.008","title":"Assessing equity in clinical practice guidelines","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Centre for Global Health Research; University of Ottawa","funders":"World Health Organization","keywords":"Equity (law); Psychological intervention; Harm; Clinical Practice; Medicine; Cost effectiveness; Actuarial science; Risk analysis (engineering); Business; Psychology; Family medicine; Political science; Nursing; Social psychology","score_opus":0.9567987096595311,"score_gpt":0.8261967716751191,"score_spread":0.130601937984412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096833944","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":[0.00007310266,0.9568159,0.009786412,0.021490354,0.008741058,0.0009136007,0.000007395929,0.000027752389,0.0021444364],"genre_scores_gemma":[0.0000080124755,0.74821115,0.20848511,0.03047506,0.012619798,0.0000055401206,0.00004349282,0.000082149105,0.00006967146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.79668,0.04947484,0.14866719,0.0017511132,0.0017596806,0.0016672192],"domain_scores_gemma":[0.17566541,0.7367262,0.07673701,0.0016204836,0.007446751,0.0018041063],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4793704,0.0007799487,0.024028,0.0008350421,0.000059498358,0.00004674819,0.0008826439,0.0036532567,0.00022513885],"category_scores_gemma":[0.95847076,0.0005380278,0.0071916366,0.0008577313,0.00063769805,0.001037319,0.00063245714,0.012419915,0.00017900178],"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":[0.00068338995,0.0012192711,0.005608055,0.0028226112,0.0008380222,0.0014102518,0.0000034191423,0.000004058421,1.7674347e-8,0.00024859948,0.035718933,0.9514434],"study_design_scores_gemma":[0.0033582696,0.0018994374,0.00567636,0.017656056,0.005935588,0.0050711334,0.00011540491,0.000076810225,1.0934283e-8,0.0011326044,0.9587136,0.00036475871],"about_ca_topic_score_codex":0.000081256185,"about_ca_topic_score_gemma":0.000034602723,"teacher_disagreement_score":0.9510786,"about_ca_system_score_codex":0.0004432042,"about_ca_system_score_gemma":0.008592371,"threshold_uncertainty_score":0.9997071},"labels":[],"label_agreement":null},{"id":"W2098554116","doi":"10.1016/j.jclinepi.2015.03.020","title":"Multiattribute health utility scoring for the computerized adaptive measure CAT-5D-QOL was developed and validated","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"St. Paul's Hospital; Centre for Advancing Health Outcomes; McGill University; Toronto Rehabilitation Institute; University of Toronto; University Health Network; University of British Columbia; Research Canada","funders":"","keywords":"Statistics; Quality (philosophy); Quality of life (healthcare); Measure (data warehouse); Medicine; Computerized adaptive testing; Mathematics; Computer science; Psychometrics; Data mining","score_opus":0.9354756561331118,"score_gpt":0.623718159264968,"score_spread":0.3117574968681438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098554116","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":[0.15416817,0.0063449345,0.60488963,0.2295447,0.003748773,0.0010413545,0.00017907948,0.00002165829,0.00006168166],"genre_scores_gemma":[0.7678438,0.0014895048,0.17314285,0.05487627,0.0024678744,0.00004416465,0.000016527028,0.00004034386,0.00007867652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97498935,0.0069249338,0.016913475,0.0005032127,0.000101310034,0.0005676936],"domain_scores_gemma":[0.9039235,0.07628662,0.017767243,0.00049241923,0.00066629454,0.00086391985],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30071515,0.00021082512,0.0044361264,0.00013884096,0.00021732939,0.000024946872,0.00043841338,0.00032021521,0.000019087283],"category_scores_gemma":[0.22194088,0.00017075337,0.0004216088,0.00012357203,0.00026609647,0.00026767844,0.00010348743,0.0005875214,0.00005199026],"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":[0.0017242462,0.00035203408,0.79379153,0.0003199579,0.0011343267,0.0000035032758,0.0018300738,0.0013029225,5.818453e-7,0.04449166,0.14134905,0.013700145],"study_design_scores_gemma":[0.00850382,0.0014177344,0.6858092,0.000217944,0.00004287833,0.000072293835,0.000756454,0.13326056,8.4262086e-7,0.055373985,0.114183456,0.00036085633],"about_ca_topic_score_codex":0.00045714987,"about_ca_topic_score_gemma":0.00013330093,"teacher_disagreement_score":0.6136756,"about_ca_system_score_codex":0.00029821138,"about_ca_system_score_gemma":0.0012147544,"threshold_uncertainty_score":0.7846131},"labels":[],"label_agreement":null},{"id":"W2098764582","doi":"10.1016/j.jclinepi.2009.01.002","title":"Kids versus trees: Reye's syndrome and spraying for spruce budworm in New Brunswick","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Plant and Fungal Interactions Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institutes of Health Research; McGill University","funders":"","keywords":"Spruce budworm; Reye's syndrome; Forestry; Lepidoptera genitalia; Agronomy; Biology; Environmental science; Medicine; Geography; Tortricidae; Botany; Pediatrics","score_opus":0.22995779758447138,"score_gpt":0.5091688195336902,"score_spread":0.2792110219492188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098764582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877645,0.0015318207,0.0030983672,0.006243744,0.00074522884,0.000114254755,0.0000029577438,0.0000025123384,0.0004966351],"genre_scores_gemma":[0.9879031,0.0026493429,0.006565524,0.0011566884,0.0009976432,7.651384e-7,0.000010839835,0.000008178454,0.0007079133],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997192,0.0005620787,0.0016252785,0.00023501851,0.00007411601,0.0003115061],"domain_scores_gemma":[0.99431413,0.004582335,0.0005843124,0.00015369605,0.00010217445,0.0002633719],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057786345,0.00011505005,0.00083936553,0.00010733182,0.000034426615,0.000008315384,0.00020456471,0.0003554726,0.000013288683],"category_scores_gemma":[0.026193563,0.0000917604,0.0002981089,0.00006884276,0.0000878407,0.000012014558,0.000038962156,0.00054258324,0.0000037365937],"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":[0.03513085,0.0008779981,0.5725949,0.00006428269,0.00069759,0.0003623312,0.0000643125,0.0006794918,0.03735057,0.007268616,0.06713141,0.27777764],"study_design_scores_gemma":[0.008305084,0.014463897,0.8164883,0.00015275802,0.00006384988,0.0011459466,0.00007191563,0.0010545219,0.00060073985,0.004761045,0.15257329,0.00031862612],"about_ca_topic_score_codex":0.000068825204,"about_ca_topic_score_gemma":0.00045101496,"teacher_disagreement_score":0.27745903,"about_ca_system_score_codex":0.000014994771,"about_ca_system_score_gemma":0.00045810555,"threshold_uncertainty_score":0.98200923},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2099385941","doi":"10.1016/j.jclinepi.2013.06.004","title":"Complex interventions and their implications for systematic reviews: a pragmatic approach","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":218,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; Ottawa Hospital; Institute of Population and Public Health; University of Ottawa","funders":"Canadian Institutes of Health Research; Centers for Disease Control and Prevention","keywords":"Psychological intervention; Systematic review; occam; Management science; Perspective (graphical); Intervention (counseling); Computer science; Data science; MEDLINE; Psychology; Engineering ethics; Medicine; Political science; Artificial intelligence; Nursing","score_opus":0.9506858075970587,"score_gpt":0.7932827291561718,"score_spread":0.15740307844088686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099385941","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":[0.023519004,0.0009602555,0.77275443,0.1892751,0.00084319053,0.011620421,0.000062051666,0.000028054823,0.00093751337],"genre_scores_gemma":[0.48456988,0.002538868,0.33830076,0.16417132,0.0021714745,0.0073327865,0.000024760679,0.000052124644,0.0008380286],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.96083176,0.025154006,0.013195253,0.0002259574,0.00006611321,0.0005269197],"domain_scores_gemma":[0.7128523,0.27143124,0.013455125,0.00049695274,0.0010545297,0.00070987653],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09334888,0.00014565942,0.0031135844,0.00015046177,0.00039838513,0.000007602465,0.0003915847,0.00020946868,0.00020100255],"category_scores_gemma":[0.3614395,0.000082311475,0.0006342077,0.00018140118,0.000242978,0.00021962354,0.00009251856,0.0007312919,0.00010667966],"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":[0.000048552658,0.00040097104,0.18059409,0.13805744,0.0003011592,1.4275899e-7,0.00462951,0.000011955152,0.00006618262,0.09275491,0.5693403,0.013794784],"study_design_scores_gemma":[0.0032016335,0.0011261906,0.74291074,0.013279762,0.00018407778,0.00010471074,0.004440533,0.0052611968,1.1216825e-7,0.15190758,0.07732051,0.00026293212],"about_ca_topic_score_codex":0.000027999937,"about_ca_topic_score_gemma":0.0000152449265,"teacher_disagreement_score":0.56231666,"about_ca_system_score_codex":0.00006124001,"about_ca_system_score_gemma":0.0003500112,"threshold_uncertainty_score":0.93358815},"labels":[],"label_agreement":null},{"id":"W2099933252","doi":"10.1016/j.jclinepi.2005.02.005","title":"Simplified search strategies were effective in identifying clinical trials of pharmaceuticals and physical modalities","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Toronto; University Health Network; Toronto Western Hospital; Mount Sinai Hospital; Institute for Work & Health","funders":"","keywords":"CINAHL; MEDLINE; Medicine; Clinical trial; Modalities; Cochrane Library; Intervention (counseling); Meta-analysis; Physical therapy; Medical physics; Psychological intervention; Pathology; Psychiatry","score_opus":0.9757002885872852,"score_gpt":0.7954998506522213,"score_spread":0.1802004379350639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099933252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96797806,0.00251415,0.020913754,0.0065619624,0.00064549706,0.0005646596,0.000011110639,0.0000018632259,0.0008089548],"genre_scores_gemma":[0.9905909,0.0011390366,0.0056625432,0.0008756601,0.0015371768,0.000006568883,6.7385605e-7,0.000009292579,0.00017816054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.27622902,0.5824028,0.13559231,0.0013959216,0.0036328111,0.000747113],"domain_scores_gemma":[0.17157044,0.78582436,0.03898583,0.0013443748,0.0016603583,0.0006146459],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.87059695,0.00030830217,0.027633019,0.0004822472,0.00005046662,0.00013410795,0.0013230459,0.0004212238,0.0009904003],"category_scores_gemma":[0.82222676,0.00014066315,0.0073368317,0.0004913221,0.0008480402,0.00049133727,0.00023016025,0.0017178304,0.00012510993],"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":[0.00076202466,0.0007059235,0.54072875,0.00015338967,0.0012495642,0.000022421906,0.0006175126,0.002213693,0.00010125454,0.027625939,0.007461006,0.4183585],"study_design_scores_gemma":[0.0038847772,0.0011330857,0.6372275,0.00028019954,0.00084286317,0.000073215866,0.0033149545,0.05149653,0.000053805117,0.2871838,0.014237353,0.00027194148],"about_ca_topic_score_codex":0.000012225831,"about_ca_topic_score_gemma":0.000017416725,"teacher_disagreement_score":0.41808656,"about_ca_system_score_codex":0.00002564308,"about_ca_system_score_gemma":0.00032978543,"threshold_uncertainty_score":0.9999228},"labels":[],"label_agreement":null},{"id":"W2100163003","doi":"10.1016/s0895-4356(02)00614-5","title":"Statin use and the risk of breast cancer","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer, Lipids, and Metabolism","field":"Biochemistry, Genetics and Molecular Biology","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":"Saskatchewan Health","funders":"","keywords":"Medicine; Statin; Breast cancer; Cohort; Hormone replacement therapy (female-to-male); Internal medicine; Population; Relative risk; Cancer; Medical prescription; Cohort study; Oncology; Confidence interval; Environmental health; Pharmacology","score_opus":0.09365195438080653,"score_gpt":0.4302984676981215,"score_spread":0.336646513317315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100163003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9792462,0.009535141,0.0025998773,0.002102827,0.006250069,0.00009013068,0.00006248289,0.0000011605712,0.00011209828],"genre_scores_gemma":[0.87548244,0.10606961,0.003922275,0.003591813,0.010626255,0.000004932193,0.0000023209216,0.000016905537,0.00028342468],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935259,0.0041786493,0.0018664753,0.000165952,0.000077829856,0.0001851758],"domain_scores_gemma":[0.99263877,0.0047099837,0.0020289172,0.0002194854,0.00026264117,0.00014019816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012854783,0.000105247695,0.0011035379,0.000024216883,0.00003497546,0.0000039139877,0.00014130124,0.00021052113,0.00003486153],"category_scores_gemma":[0.03568916,0.00005795161,0.0004310273,0.00004109409,0.00064714917,0.000005602306,0.00003772225,0.00037834706,5.749954e-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":[0.0026483985,0.00011182244,0.9145302,0.00001944443,0.00058765756,2.5794085e-7,0.00004781323,0.00034807212,0.0013620305,0.0059116418,0.056639925,0.01779269],"study_design_scores_gemma":[0.0038423503,0.00025890904,0.5931276,0.000020482501,0.0001943273,0.00012889218,0.000043956832,0.000037839374,0.00012900632,0.0033383507,0.39879322,0.00008505596],"about_ca_topic_score_codex":0.00017224123,"about_ca_topic_score_gemma":0.00007970226,"teacher_disagreement_score":0.3421533,"about_ca_system_score_codex":0.000003665194,"about_ca_system_score_gemma":0.00021715998,"threshold_uncertainty_score":0.9724336},"labels":[],"label_agreement":null},{"id":"W2102381912","doi":"10.1016/j.jclinepi.2010.09.013","title":"Describing reporting guidelines for health research: a systematic review","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":149,"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 College of Naturopathic Medicine; Queen's University; Children's Hospital of Eastern Ontario; Ottawa Hospital","funders":"Medical Research Council; Cancer Research UK","keywords":"Checklist; Guideline; Systematic review; Medicine; MEDLINE; Consolidated Standards of Reporting Trials; Randomized controlled trial; Medical education; Family medicine; Psychology; Political science; Pathology","score_opus":0.9912864423081622,"score_gpt":0.8159723724322036,"score_spread":0.17531406987595866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102381912","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":[5.2458586e-7,0.94639766,0.007011833,0.038327906,0.001949155,0.006216416,0.00001622125,0.000022918606,0.000057346093],"genre_scores_gemma":[2.6721077e-7,0.8652491,0.08871779,0.041504674,0.0040355874,0.00017545235,0.00006230201,0.00009791275,0.00015689041],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.7318311,0.060263276,0.20390609,0.0012563749,0.0011565655,0.0015865933],"domain_scores_gemma":[0.06924833,0.5900238,0.31604347,0.0025748436,0.019322228,0.0027872948],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6427251,0.0005669659,0.04031537,0.0005698024,0.00015409525,0.000013249623,0.0007079562,0.0010154931,0.00010566135],"category_scores_gemma":[0.989574,0.00033820583,0.008505543,0.0005776473,0.0003070043,0.00017532764,0.00023058099,0.0050521023,0.000054779048],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007297465,0.00011803089,0.000027626518,0.5325566,0.0006845524,0.000051822954,0.0000045355873,8.3115474e-8,3.8242516e-9,0.00015602076,0.11003122,0.35629654],"study_design_scores_gemma":[0.0004723774,0.001604966,0.000003929039,0.5134128,0.005461431,0.0030721824,0.000025339357,0.000012319337,3.3792549e-9,0.0005896437,0.47522733,0.000117697346],"about_ca_topic_score_codex":0.000050699542,"about_ca_topic_score_gemma":0.000012388581,"teacher_disagreement_score":0.66258276,"about_ca_system_score_codex":0.0003743185,"about_ca_system_score_gemma":0.0096666785,"threshold_uncertainty_score":0.999907},"labels":[],"label_agreement":null},{"id":"W2103185235","doi":"10.1016/j.jclinepi.2009.03.010","title":"Changing author counts in five major general medicine journals: effect of author contribution forms","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":21,"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; University of Toronto","funders":"","keywords":"Medical journal; Medicine; New england; Family medicine; Alternative medicine; Medical literature; Impact factor; MEDLINE; Law; Political science; Pathology","score_opus":0.7354483997857146,"score_gpt":0.713000899036358,"score_spread":0.02244750074935664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103185235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95541596,0.0036431744,0.015600726,0.021421261,0.0024501514,0.00016226055,0.000008302181,0.0000038208436,0.001294344],"genre_scores_gemma":[0.99583894,0.0007060465,0.00090030284,0.00087655766,0.00088766654,7.004151e-7,0.0000011153386,0.0000040959444,0.0007845797],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98114616,0.006469359,0.007938932,0.00038151903,0.003306236,0.0007577703],"domain_scores_gemma":[0.87708,0.11396171,0.0050531877,0.00034994975,0.0029345755,0.0006205788],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.38574484,0.00013105886,0.0024933077,0.02124649,0.000061669314,0.000042394167,0.0011285113,0.00037285656,0.0005383229],"category_scores_gemma":[0.70851517,0.000065530985,0.0005508125,0.024923835,0.00026392256,0.0002606908,0.00011094738,0.0010639027,0.000048508406],"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":[0.00076921843,0.00016585592,0.46842226,0.000008023374,0.000056516303,0.000090660484,0.00006142524,0.00017108936,0.00019608333,0.005075705,0.053165868,0.47181728],"study_design_scores_gemma":[0.003154751,0.005331734,0.8733127,0.00013625866,0.00003327923,0.000110102825,0.00005850595,0.011403053,0.00010639388,0.092887856,0.01335386,0.00011149601],"about_ca_topic_score_codex":0.000009815785,"about_ca_topic_score_gemma":0.0000018654554,"teacher_disagreement_score":0.4717058,"about_ca_system_score_codex":0.00007749824,"about_ca_system_score_gemma":0.00017239599,"threshold_uncertainty_score":0.99580187},"labels":[],"label_agreement":null},{"id":"W2103537640","doi":"10.1016/j.jclinepi.2011.03.011","title":"Updating comparative effectiveness reviews: Current efforts in AHRQ's Effective Health Care Program","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":40,"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; University of Ottawa","funders":"","keywords":"Guideline; Process (computing); Health care; Compromise; Key (lock); Risk analysis (engineering); Systematic review; Medicine; Computer science; Management science; Best practice; MEDLINE; Data science; Political science; Engineering","score_opus":0.8501626182042888,"score_gpt":0.6722852089143415,"score_spread":0.17787740928994733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103537640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.840072,0.12067132,0.013196549,0.009134746,0.0077384124,0.0061932337,0.00006760187,0.000048683418,0.0028775085],"genre_scores_gemma":[0.96136326,0.0044162427,0.025048666,0.007677366,0.0011546107,0.0002884766,0.000016967824,0.000029336086,0.0000050914587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94607556,0.026485182,0.025998175,0.0006653795,0.0000830153,0.00069268094],"domain_scores_gemma":[0.93707514,0.03801561,0.023822334,0.00040567113,0.0002126249,0.00046862362],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24667618,0.0002785641,0.008454364,0.00037531718,0.00010037349,0.000010293064,0.00039967056,0.00028821392,0.00008956624],"category_scores_gemma":[0.10292317,0.00026246154,0.00079138944,0.00024496813,0.00022534376,0.00035103725,0.00007451054,0.0013227544,0.00031014538],"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":[0.00024894215,0.00063473155,0.9093275,0.0013034843,0.00012250485,0.0000038123085,0.0039375606,0.00007970704,4.283065e-8,0.031145385,0.004936934,0.048259377],"study_design_scores_gemma":[0.0020228312,0.00221259,0.9109527,0.0013437981,0.000012803184,0.000018257915,0.00064683513,0.00046467516,7.16304e-7,0.019156447,0.06291287,0.00025547142],"about_ca_topic_score_codex":0.0003833315,"about_ca_topic_score_gemma":0.00016981931,"teacher_disagreement_score":0.14375299,"about_ca_system_score_codex":0.00068064197,"about_ca_system_score_gemma":0.0003940495,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null},{"id":"W2103779230","doi":"10.1016/j.jclinepi.2014.06.014","title":"The value of including observational studies in systematic reviews was unclear: a descriptive study","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"H2020 European Research Council","keywords":"Observational study; Medicine; Systematic review; MEDLINE; Pathology; Biology","score_opus":0.9855335637438157,"score_gpt":0.7365681350500062,"score_spread":0.24896542869380955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103779230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444194,0.025957463,0.016015096,0.0074780053,0.0031939833,0.0024711317,0.0000014016163,0.000001762869,0.00046177141],"genre_scores_gemma":[0.98528504,0.0022959753,0.010153937,0.0012378931,0.00044324994,0.000039045797,1.8167295e-7,0.000008506134,0.00053617754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.1858132,0.64657205,0.16142206,0.000990193,0.004662276,0.00054021145],"domain_scores_gemma":[0.03337461,0.85532355,0.10394576,0.002790385,0.004324528,0.00024115978],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8963257,0.0002729568,0.025490591,0.00029410928,0.0001446276,0.000052451964,0.0024074812,0.00014840851,0.000096546464],"category_scores_gemma":[0.97042364,0.00008974524,0.0045968015,0.00094409654,0.0003934899,0.00019518299,0.00029931753,0.00074589637,0.00016181935],"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":[0.00008770439,0.00035289934,0.925606,0.0014798954,0.0014098599,0.0000068948,0.0018223195,0.0012164928,0.0000028500262,0.036065623,0.026574004,0.0053754714],"study_design_scores_gemma":[0.0015514703,0.0021645392,0.61924887,0.006427663,0.0014576444,0.000072250936,0.015908808,0.021914044,6.3481383e-7,0.3064772,0.024511416,0.00026545583],"about_ca_topic_score_codex":0.000008959874,"about_ca_topic_score_gemma":0.00006826153,"teacher_disagreement_score":0.30635712,"about_ca_system_score_codex":0.000065064196,"about_ca_system_score_gemma":0.00013784613,"threshold_uncertainty_score":0.988977},"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":"W2104675861","doi":"10.1016/j.jclinepi.2010.04.026","title":"GRADE guidelines: 1. Introduction—GRADE evidence profiles and summary of findings tables","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":10460,"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":"Grading (engineering); Quality of evidence; Evidence-based medicine; Quality (philosophy); Evidence-based practice; Systematic review; Medicine; MEDLINE; Actuarial science; Meta-analysis; Alternative medicine; Business; Pathology","score_opus":0.9530019511900161,"score_gpt":0.6695969753049804,"score_spread":0.28340497588503566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104675861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86592317,0.026243344,0.03961048,0.06321554,0.003832677,0.00061224203,0.000012619103,0.0000048584598,0.0005451025],"genre_scores_gemma":[0.5624675,0.016935267,0.406308,0.004831863,0.005078698,0.000013731407,0.0000026880537,0.000028801946,0.0043334477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.83891255,0.071636036,0.085066415,0.0011702013,0.0027462414,0.0004685832],"domain_scores_gemma":[0.59861124,0.3092972,0.08019679,0.003800963,0.0072578075,0.0008359773],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.582577,0.0002529528,0.011260666,0.00040527436,0.000064811065,0.000037300848,0.0016671016,0.00028994822,0.0033062028],"category_scores_gemma":[0.8668239,0.00011021445,0.003149973,0.0005976285,0.0005703613,0.00045039807,0.00018920557,0.00062191434,0.00009788091],"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":[0.000085962456,0.00008892742,0.60649353,0.00005285935,0.00026860725,0.0000059948397,0.00010282954,0.000025601066,0.000054185777,0.004605653,0.37737265,0.010843165],"study_design_scores_gemma":[0.00087735604,0.0011812055,0.596654,0.0005567943,0.0008842329,0.00044410344,0.0007516981,0.0023127208,0.00012357262,0.18843284,0.20749529,0.00028617837],"about_ca_topic_score_codex":0.000030443192,"about_ca_topic_score_gemma":0.0000080914315,"teacher_disagreement_score":0.36669752,"about_ca_system_score_codex":0.000011417513,"about_ca_system_score_gemma":0.00017674679,"threshold_uncertainty_score":0.9976049},"labels":[],"label_agreement":null},{"id":"W2105206593","doi":"10.1016/j.jclinepi.2008.06.019","title":"Flexible statistical models provided new insights into the role of quantitative prognostic factors for mortality in gastric cancer","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Gastric Cancer Management and Outcomes","field":"Medicine","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":"McGill University","funders":"Ligue Contre le Cancer; McGill University; Association pour la Recherche sur le Cancer","keywords":"Cancer; Medicine; Oncology; Internal medicine; Bioinformatics; Biology","score_opus":0.37161712624831833,"score_gpt":0.5145436484582278,"score_spread":0.14292652220990942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105206593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9240159,0.0023717436,0.06946852,0.0030233015,0.0003835369,0.000604791,0.0000052285363,0.0000066110924,0.00012036224],"genre_scores_gemma":[0.9814534,0.0018555444,0.015487915,0.0007576825,0.0003006564,0.000015185691,0.0000052286714,0.000011617302,0.00011272475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99521834,0.000829088,0.0032120708,0.00021755612,0.00023547576,0.00028749884],"domain_scores_gemma":[0.97265404,0.024908615,0.0017499187,0.00018454464,0.00026837765,0.0002344741],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036349345,0.00015318408,0.002051754,0.00016891964,0.000040282503,0.0000021003548,0.00019520141,0.0001493959,0.00003359059],"category_scores_gemma":[0.036862027,0.000083759245,0.00042203124,0.00025245445,0.000301706,0.00011223068,0.00004637326,0.00056050677,8.872779e-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":[0.0011775396,0.00021709588,0.9713661,0.00006572121,0.00028132834,0.000020843496,0.0007118429,0.001437539,0.000009521843,0.016010592,0.0018318725,0.00687],"study_design_scores_gemma":[0.0023582093,0.0018645598,0.89818066,0.00009216536,0.00027557684,0.0000102984895,0.0003485915,0.007951013,0.000017910377,0.087375715,0.0014598123,0.00006550021],"about_ca_topic_score_codex":0.0012105281,"about_ca_topic_score_gemma":0.00031611562,"teacher_disagreement_score":0.07318546,"about_ca_system_score_codex":0.00006819079,"about_ca_system_score_gemma":0.0008688389,"threshold_uncertainty_score":0.9712509},"labels":[],"label_agreement":null},{"id":"W2105832903","doi":"10.1016/j.jclinepi.2009.12.016","title":"Relative risk and odds ratio data are still portrayed with inappropriate scales in the medical literature","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Odds ratio; Reciprocal; Relative risk; Confidence interval; Scale (ratio); Medicine; Odds; Statistics; Mathematics; Geography","score_opus":0.8102461535365199,"score_gpt":0.6332432112797253,"score_spread":0.17700294225679458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105832903","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":[0.907324,0.0024325633,0.051013667,0.037775725,0.00072428165,0.00031363094,0.000031616055,0.0000013903982,0.0003830891],"genre_scores_gemma":[0.97638446,0.0012626856,0.018137803,0.003318052,0.0007571411,0.000002822873,0.0000060339885,0.000006564585,0.00012446182],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7741276,0.17497908,0.04416797,0.0013962258,0.004876192,0.0004529357],"domain_scores_gemma":[0.33881095,0.57689834,0.07282088,0.0076683117,0.002813012,0.0009885307],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7140793,0.00023074461,0.0076724784,0.00020754579,0.00007463384,0.000151704,0.003307921,0.00054446765,0.00062592886],"category_scores_gemma":[0.8591365,0.00006864353,0.00095724425,0.0007140458,0.00062381267,0.00034967932,0.00023503232,0.0038358003,0.000046296966],"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":[0.00011888297,0.000107208056,0.9493374,0.0000120709665,0.00023802782,0.00016611535,0.00027555542,0.00002037519,6.1109915e-7,0.007261503,0.013363729,0.029098487],"study_design_scores_gemma":[0.00063618197,0.00026540915,0.8935682,0.0001201813,0.00021849194,0.0006419704,0.00029080187,0.011301106,6.841953e-8,0.05899831,0.033870887,0.00008835438],"about_ca_topic_score_codex":0.0000080370055,"about_ca_topic_score_gemma":0.0007091253,"teacher_disagreement_score":0.43531665,"about_ca_system_score_codex":0.000004041119,"about_ca_system_score_gemma":0.00020768544,"threshold_uncertainty_score":0.9984624},"labels":[],"label_agreement":null},{"id":"W2106311978","doi":"10.1016/j.jclinepi.2013.08.005","title":"Applying an equity lens to interventions: using PROGRESS ensures consideration of socially stratifying factors to illuminate inequities in health","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":1635,"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; Institute of Population and Public Health; Bruyère; University of Ottawa","funders":"Medical Research Council","keywords":"Psychological intervention; Health equity; Equity (law); Socioeconomic status; Disadvantage; Acronym; Public economics; Social determinants of health; Health care; Medicine; Psychology; Actuarial science; Political science; Economic growth; Environmental health; Economics; Population; Nursing","score_opus":0.7329751885356314,"score_gpt":0.65853013972719,"score_spread":0.07444504880844138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106311978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540267,0.00036026357,0.0028075355,0.04111162,0.00078304124,0.00073981617,0.0000052993896,0.000009138419,0.00015661697],"genre_scores_gemma":[0.9802972,0.00021713483,0.012627617,0.0063824104,0.00042983526,0.000017054163,0.000001094842,0.000007711262,0.00001995139],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868887,0.0067358967,0.0053094947,0.00019048153,0.00027653252,0.00059886987],"domain_scores_gemma":[0.9864688,0.00983983,0.0025931143,0.000113231545,0.00044356156,0.0005414532],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036773935,0.000115392286,0.0016966673,0.00020876424,0.00026539876,0.000037340855,0.0002582287,0.00022550719,0.00009499619],"category_scores_gemma":[0.055618085,0.00009539244,0.00034395792,0.0001786496,0.00035185204,0.00046564284,0.0000930109,0.00047350995,0.0000021896205],"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":[0.000046104917,0.00016149695,0.92620194,0.00031755088,0.000029215791,0.0000022880329,0.007257321,0.0007797607,0.000005619421,0.03329672,0.00067872327,0.031223275],"study_design_scores_gemma":[0.00036550226,0.00084826734,0.9512439,0.0009880329,0.000011699936,0.0000020248426,0.025592487,0.00029084648,0.0000038259127,0.019362569,0.0011614726,0.00012938833],"about_ca_topic_score_codex":0.016692705,"about_ca_topic_score_gemma":0.018191857,"teacher_disagreement_score":0.03472921,"about_ca_system_score_codex":0.00018959284,"about_ca_system_score_gemma":0.0015515643,"threshold_uncertainty_score":0.99972355},"labels":[],"label_agreement":null},{"id":"W2106656235","doi":"10.1016/j.jclinepi.2010.01.003","title":"AHRQ Series Commentary 1: Rating the evidence in comparative effectiveness reviews","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Systematic review; Medicine; Health care; MEDLINE; Evidence-based practice; Agency (philosophy); Evidence-based medicine; Alternative medicine; Management science; Political science; Pathology; Sociology; Engineering","score_opus":0.9680271290904991,"score_gpt":0.7378589787667509,"score_spread":0.23016815032374827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106656235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9151419,0.008195445,0.011513596,0.060003858,0.0034923586,0.00091280526,0.0000017200274,0.0000014484048,0.00073689286],"genre_scores_gemma":[0.97007704,0.0014497134,0.016360974,0.010956316,0.00094803807,0.000021706655,5.1573295e-7,0.0000057891457,0.0001799295],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.42021474,0.4916015,0.08409976,0.0010475727,0.002501569,0.0005348342],"domain_scores_gemma":[0.08194278,0.85762095,0.055333864,0.0031020422,0.0016611923,0.0003391465],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8495924,0.00025577276,0.015627613,0.00017410867,0.0001227703,0.00009717353,0.0026324838,0.00020478375,0.0013497206],"category_scores_gemma":[0.84477985,0.000086326756,0.0039424878,0.0007126,0.00051500427,0.00048668848,0.00019527292,0.0021387143,0.00041532452],"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":[0.000116195086,0.000074692834,0.8684087,0.000034191915,0.000120905795,0.000009599494,0.00021154706,0.00013693192,0.00009029292,0.0021762087,0.09703803,0.03158272],"study_design_scores_gemma":[0.00031151882,0.0003334566,0.7527455,0.0004068479,0.00012960452,0.00011762991,0.00030674247,0.0010323374,0.000013463771,0.03216756,0.21232888,0.000106447456],"about_ca_topic_score_codex":0.00001826812,"about_ca_topic_score_gemma":0.0003318031,"teacher_disagreement_score":0.36601946,"about_ca_system_score_codex":0.000018201461,"about_ca_system_score_gemma":0.00011227737,"threshold_uncertainty_score":0.99956316},"labels":[],"label_agreement":null},{"id":"W2107021177","doi":"10.1016/j.jclinepi.2012.01.006","title":"GRADE guidelines: 11. Making an overall rating of confidence in effect estimates for a single outcome and for all outcomes","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":745,"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":"Confidence interval; Outcome (game theory); Rating scale; Guideline; Rating system; Ordinal Scale; Medicine; Statistics; Mathematics","score_opus":0.9431571239167648,"score_gpt":0.7198952943374226,"score_spread":0.22326182957934215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107021177","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":[0.0024254953,0.9619191,0.024643814,0.0066818222,0.002080616,0.0019834936,0.00023941179,0.000009560222,0.0000166471],"genre_scores_gemma":[0.0036432836,0.7545324,0.22483708,0.01381468,0.0026558568,0.00027411975,0.0000677826,0.00013687293,0.000037904658],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9505931,0.0045595975,0.04351988,0.0006066789,0.0000750617,0.0006456824],"domain_scores_gemma":[0.7164995,0.23942319,0.04306113,0.00045874293,0.00024210985,0.0003153011],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26298743,0.00046124685,0.019463891,0.0005168389,0.00005755156,0.000022857319,0.0005416685,0.0009358196,0.000019904825],"category_scores_gemma":[0.47099715,0.00039366542,0.0018736438,0.00007529616,0.0001819283,0.00040436452,0.00007872067,0.0006584417,0.000008791665],"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":[0.00011673497,0.00038030374,0.8176863,0.050104782,0.0008536898,0.0000025253369,0.00017863249,0.00017498895,1.4873488e-7,0.06247474,0.0019229656,0.066104196],"study_design_scores_gemma":[0.0051235487,0.0031998195,0.021625204,0.014762019,0.0010557814,0.00017639699,0.000089384666,0.008280009,9.829644e-8,0.06908484,0.8755426,0.0010603181],"about_ca_topic_score_codex":0.00011308058,"about_ca_topic_score_gemma":0.00008076359,"teacher_disagreement_score":0.8736196,"about_ca_system_score_codex":0.00023313511,"about_ca_system_score_gemma":0.00027424478,"threshold_uncertainty_score":0.9998515},"labels":[],"label_agreement":null},{"id":"W2107169068","doi":"10.1016/j.jclinepi.2012.03.009","title":"The systematic review and bibliometric network analysis (SeBriNA) is a new method to contextualize evidence. Part 1: description","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":18,"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":"Canadian Institutes of Health Research","keywords":"Systematic review; Grading (engineering); Data science; Computer science; Data extraction; Context (archaeology); Relevance (law); Bibliometrics; Citation; Meta-analysis; Citation analysis; Quality (philosophy); Evidence-based medicine; Critical appraisal; Management science; MEDLINE; Data mining; Medicine; Library science; Alternative medicine; Political science; Geography","score_opus":0.9452749707894987,"score_gpt":0.7093100142682834,"score_spread":0.2359649565212153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107169068","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":[0.0014262947,0.50513566,0.45684034,0.034536857,0.0009967303,0.0009247465,0.0000019295185,0.0000022068734,0.00013525959],"genre_scores_gemma":[0.09284602,0.41810647,0.28588304,0.17146051,0.0066372044,0.00012718608,0.0000020645437,0.000054989523,0.024882521],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.45190683,0.42697564,0.112315655,0.0014436878,0.005970701,0.0013874867],"domain_scores_gemma":[0.10546015,0.8006432,0.08178266,0.005143384,0.004423543,0.0025470487],"candidate_categories":["metaresearch","metaepi_broad","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8677776,0.00035853725,0.026125057,0.005362854,0.00020687302,0.0003223158,0.0023080567,0.00025563478,0.0021419825],"category_scores_gemma":[0.89906996,0.00012886482,0.008284196,0.047406364,0.00013056902,0.0005598373,0.0002589611,0.00066288706,0.00077795505],"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":[0.000031376603,0.000037232556,0.2602559,0.0030472619,0.004050356,0.0000019205293,0.000065813016,0.000083049374,2.419674e-7,0.0019794377,0.7040452,0.026402246],"study_design_scores_gemma":[0.00046444754,0.0008470488,0.37511653,0.019962057,0.0669077,0.00039658407,0.00030895876,0.0033908845,3.0094313e-7,0.027775364,0.50432336,0.00050679443],"about_ca_topic_score_codex":0.000019576739,"about_ca_topic_score_gemma":0.000016467098,"teacher_disagreement_score":0.37366757,"about_ca_system_score_codex":0.000036294263,"about_ca_system_score_gemma":0.00014413471,"threshold_uncertainty_score":0.9999298},"labels":[],"label_agreement":null},{"id":"W2108239621","doi":"10.1016/s0895-4356(00)00250-x","title":"Discrepancies among megatrials","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":49,"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; Baycrest Hospital","funders":"","keywords":"Kappa; Medicine; Odds ratio; Meta-analysis; Gold standard (test); Odds; Cohen's kappa; Internal medicine; Demography; Statistics; Mathematics; Logistic regression","score_opus":0.6334858875047313,"score_gpt":0.6656139289395658,"score_spread":0.0321280414348345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108239621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84699184,0.00067957514,0.0009817525,0.07544997,0.0014992617,0.0002423713,0.0000025492193,0.000057106383,0.074095584],"genre_scores_gemma":[0.9715577,0.008122131,0.009510243,0.0016782857,0.0044314614,0.000004255486,2.9514123e-7,0.000012281507,0.0046833856],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97759604,0.016759679,0.004375899,0.00020458245,0.00050280185,0.0005609708],"domain_scores_gemma":[0.9250834,0.07179171,0.0018991568,0.00028014337,0.00036953518,0.0005760252],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13489237,0.000098217264,0.0016910393,0.00010319657,0.00018431853,0.000018779918,0.0008261505,0.00048279852,0.0035080733],"category_scores_gemma":[0.264221,0.00007074006,0.0008074232,0.00023546784,0.0019818975,0.00025842318,0.000046188263,0.0010602233,0.0001172908],"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":[0.00047069398,0.00019029524,0.55183315,0.000007200455,0.00011577999,0.000096626034,0.00047508883,0.000056158988,0.0000062068293,0.036000386,0.08227128,0.32847714],"study_design_scores_gemma":[0.00054798945,0.0004622279,0.20872515,0.00006563401,0.000029925519,0.000015872056,0.00037978418,0.00003903998,0.0000081865355,0.13866207,0.65094554,0.00011855888],"about_ca_topic_score_codex":0.001096358,"about_ca_topic_score_gemma":0.00041050153,"teacher_disagreement_score":0.56867427,"about_ca_system_score_codex":0.000050828632,"about_ca_system_score_gemma":0.00050943106,"threshold_uncertainty_score":0.99740285},"labels":[],"label_agreement":null},{"id":"W2109346853","doi":"10.1016/j.jclinepi.2011.01.011","title":"GRADE guidelines: 5. Rating the quality of evidence—publication bias","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1843,"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":"Funnel plot; Publication bias; Observational study; Reporting bias; Suspect; Medicine; Meta-analysis; Non-response bias; Evidence-based medicine; Evidence-based practice; Quality of evidence; Randomized controlled trial; Quality (philosophy); Sample size determination; MEDLINE; Psychology; Statistics; Alternative medicine","score_opus":0.9973717538333816,"score_gpt":0.7970850390389328,"score_spread":0.20028671479444882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109346853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5366886,0.006569386,0.30005485,0.14747693,0.0032520494,0.0006882512,0.000005766382,0.000004861032,0.00525926],"genre_scores_gemma":[0.89017594,0.00077894627,0.09818878,0.008674292,0.00095349574,0.000005310773,6.261733e-7,0.0000075803314,0.0012150354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2785524,0.44706315,0.26506934,0.0013175854,0.0073848027,0.0006127154],"domain_scores_gemma":[0.036997955,0.7433395,0.19761285,0.0049828403,0.016635293,0.0004315699],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90253687,0.00019160508,0.010790011,0.00022221371,0.00007969123,0.000051387753,0.0032701138,0.00023957613,0.0034323875],"category_scores_gemma":[0.98316205,0.000057304576,0.0062569934,0.0008104476,0.00038577858,0.000346006,0.00015748199,0.00066946755,0.00032178368],"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":[0.000046721758,0.00008674467,0.7622713,0.000020557067,0.0002552657,9.539636e-7,0.00019742652,0.00004469925,0.000019369329,0.016090922,0.15050848,0.07045759],"study_design_scores_gemma":[0.00024504514,0.00029635406,0.81522906,0.00012838363,0.0002362713,0.000035890578,0.0005488631,0.00248451,0.000014419319,0.1298794,0.050806522,0.00009529217],"about_ca_topic_score_codex":0.000057433437,"about_ca_topic_score_gemma":0.00002640404,"teacher_disagreement_score":0.35348728,"about_ca_system_score_codex":0.000011806823,"about_ca_system_score_gemma":0.00026626213,"threshold_uncertainty_score":0.9974786},"labels":[],"label_agreement":null},{"id":"W2111059791","doi":"10.1016/j.jclinepi.2009.07.002","title":"A first step to assess harm and benefit in clinical trials in one scale","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","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":"University of Ottawa; Institute of Population and Public Health","funders":"","keywords":"Harm; Medicine; Context (archaeology); Metric (unit); Clinical trial; Scale (ratio); Intensive care medicine; Psychology; Internal medicine; Operations management; Social psychology","score_opus":0.7033849761034902,"score_gpt":0.636543728604159,"score_spread":0.06684124749933118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111059791","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":[0.0053475886,0.98314744,0.00021430355,0.009257543,0.0006987964,0.0011735266,0.000018413732,0.0000071888303,0.0001352161],"genre_scores_gemma":[0.00017680816,0.98769593,0.008215949,0.0021321087,0.001623836,0.000025451698,0.000009856251,0.000036392255,0.00008368931],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94262546,0.025335344,0.029983437,0.00074520754,0.00045127288,0.0008592847],"domain_scores_gemma":[0.7456412,0.2431415,0.008399573,0.0006403873,0.0003369453,0.0018403915],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.23402834,0.0004323,0.030030677,0.0008768403,0.00003342053,0.000021000424,0.00044508724,0.0015820357,0.00013174307],"category_scores_gemma":[0.3875247,0.00028576923,0.0031181595,0.00041057324,0.00037653162,0.00009752761,0.00015210819,0.0050819167,0.000040483854],"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":[0.0012533652,0.00092748605,0.03919933,0.0013921646,0.0003418447,0.00033087475,0.000013093197,0.000001994731,2.8158436e-8,0.0003330481,0.001838059,0.9543687],"study_design_scores_gemma":[0.0057503367,0.0045074457,0.09288637,0.047684282,0.00013793664,0.0005618381,0.0000134474485,0.000027950728,1.9548738e-8,0.0034204354,0.84479374,0.00021620108],"about_ca_topic_score_codex":0.000060666418,"about_ca_topic_score_gemma":0.0005461512,"teacher_disagreement_score":0.9541525,"about_ca_system_score_codex":0.00010495797,"about_ca_system_score_gemma":0.0009095574,"threshold_uncertainty_score":0.99995947},"labels":[],"label_agreement":null},{"id":"W2111985824","doi":"10.1016/j.jclinepi.2008.06.007","title":"AHRQ Series Paper 4: Assessing harms when comparing medical interventions: AHRQ and the Effective Health-Care Program","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":186,"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; McMaster University","funders":"H2020 European Research Council; Health Services Research and Development; U.S. Department of Veterans Affairs","keywords":"Medicine; Psychological intervention; Observational study; Terminology; Systematic review; Randomized controlled trial; MEDLINE; Grey literature; Health care; Evidence-based medicine; Alternative medicine; Family medicine; Actuarial science; Intensive care medicine; Nursing","score_opus":0.8330361413456372,"score_gpt":0.6831585300581089,"score_spread":0.1498776112875283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111985824","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":[0.00009775814,0.926232,0.0024469225,0.06607946,0.0028188368,0.0018760252,0.000031598236,0.00002773298,0.00038970765],"genre_scores_gemma":[0.00013473959,0.97428143,0.008084383,0.014374855,0.0027390122,0.00023887173,0.00003351658,0.00005476192,0.000058448586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9200034,0.034953345,0.043233782,0.0008469521,0.0002181069,0.000744388],"domain_scores_gemma":[0.84918797,0.104023,0.04508307,0.0006561933,0.00025386887,0.00079588295],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21693483,0.0005037607,0.020319818,0.00038337978,0.00039005026,0.000087034525,0.00088968175,0.0011512374,0.0002148261],"category_scores_gemma":[0.27607474,0.00035820212,0.003675642,0.00016462003,0.0014053395,0.00062601507,0.0002856016,0.0033333532,0.00016784554],"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":[0.000093149436,0.00027129703,0.015278396,0.022232063,0.0014688062,0.0000149150355,0.000830491,0.0000067682686,6.5056516e-11,0.039100766,0.029210247,0.8914931],"study_design_scores_gemma":[0.0019162904,0.0005857412,0.0039503975,0.017616084,0.00013526712,0.0007037336,0.00037026382,0.00017723296,3.0895178e-10,0.014135291,0.9601232,0.0002865051],"about_ca_topic_score_codex":0.00021066715,"about_ca_topic_score_gemma":0.00012782613,"teacher_disagreement_score":0.930913,"about_ca_system_score_codex":0.0005240261,"about_ca_system_score_gemma":0.0014930106,"threshold_uncertainty_score":0.999887},"labels":[],"label_agreement":null},{"id":"W2112280905","doi":"10.1016/j.jclinepi.2012.01.004","title":"Informed consent documents do not encourage good-quality decision making","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":68,"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; University of Toronto; Sunnybrook Health Science Centre; Health Sciences Centre; McGill University; Ottawa Hospital","funders":"","keywords":"Conformity; Transparency (behavior); Conformity assessment; Informed consent; Quality (philosophy); Scale (ratio); Psychology; Medicine; Family medicine; Medical education; Applied psychology; Social psychology; Alternative medicine; Computer science","score_opus":0.7795655944915766,"score_gpt":0.689566658990508,"score_spread":0.08999893550106863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112280905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9373397,0.0048537278,0.0055215163,0.023753023,0.018016579,0.0009899654,0.000026919712,0.00005794491,0.009440579],"genre_scores_gemma":[0.93612605,0.0031850066,0.033309493,0.025436014,0.001750855,0.000026616328,0.00000521064,0.000022687584,0.00013805887],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9522342,0.03082262,0.014989796,0.00026096829,0.0005420474,0.001150337],"domain_scores_gemma":[0.51327163,0.46885008,0.014630109,0.0011940835,0.0010255567,0.0010285571],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049802955,0.00024646032,0.0026024696,0.00020017054,0.00051669916,0.000005550309,0.00091046875,0.0009374206,0.0007829854],"category_scores_gemma":[0.4748544,0.00017934448,0.0006702176,0.00018619323,0.00031187217,0.00052169117,0.00057213474,0.0037429922,0.00047574245],"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":[0.0009649549,0.00018072242,0.9490481,0.00023452424,0.00007626109,0.0000026246498,0.0012852895,0.000015707788,0.000002815948,0.009575673,0.01666978,0.021943534],"study_design_scores_gemma":[0.0023290338,0.0003549164,0.89569014,0.0015523465,0.0000428686,0.000025863072,0.0021794336,0.00003962611,0.0000011135302,0.014994262,0.08261319,0.00017721699],"about_ca_topic_score_codex":0.00010339217,"about_ca_topic_score_gemma":0.00014638496,"teacher_disagreement_score":0.4389626,"about_ca_system_score_codex":0.00038427574,"about_ca_system_score_gemma":0.0024535202,"threshold_uncertainty_score":0.9985554},"labels":[],"label_agreement":null},{"id":"W2112548834","doi":"10.1016/j.jclinepi.2011.01.010","title":"Testing a tool for the classification of study designs in systematic reviews of interventions and exposures showed moderate reliability and low accuracy","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":73,"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; University of Alberta","funders":"Agency for Healthcare Research and Quality","keywords":"Inter-rater reliability; Reliability (semiconductor); Context (archaeology); Test (biology); Systematic review; Research design; CLARITY; Statistics; Computer science; Medicine; Reliability engineering; Medical physics; MEDLINE; Mathematics; Engineering; Rating scale","score_opus":0.9765515537496716,"score_gpt":0.6909558342193558,"score_spread":0.2855957195303158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112548834","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8601037,0.003733988,0.13307028,0.00040487625,0.00015303171,0.0025053918,0.0000024886417,5.225355e-7,0.000025691808],"genre_scores_gemma":[0.972443,0.00038863704,0.026971977,0.00006897359,0.000030948555,0.000068970796,1.18939305e-7,0.0000034279365,0.000023990653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.68765134,0.20808385,0.10204106,0.00081694906,0.0011338285,0.0002729905],"domain_scores_gemma":[0.11063685,0.80308354,0.08072201,0.002346605,0.0030585187,0.00015247815],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.69192725,0.00014636689,0.010164782,0.00017305597,0.000047999267,0.000026308177,0.0007371911,0.00010600852,0.0000801695],"category_scores_gemma":[0.9256294,0.000053679123,0.001965854,0.00034115312,0.00021427528,0.00016601197,0.00008059506,0.00026588567,0.0000023119342],"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":[0.00013539036,0.00051314716,0.9742187,0.004843171,0.00025569176,6.6248157e-7,0.0007221852,0.00010522059,0.000037469053,0.0007708624,0.00037541657,0.018022053],"study_design_scores_gemma":[0.00050331076,0.0009242815,0.93336207,0.0020232652,0.00068913156,0.000012885293,0.0009714411,0.038957153,0.000001512467,0.022472778,0.000028164637,0.000054007087],"about_ca_topic_score_codex":0.000014243778,"about_ca_topic_score_gemma":0.000033121,"teacher_disagreement_score":0.5949997,"about_ca_system_score_codex":0.000008017778,"about_ca_system_score_gemma":0.00006381201,"threshold_uncertainty_score":0.6948442},"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":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2112598277","doi":"10.1016/j.jclinepi.2006.11.011","title":"Age–social stratification designs had a negligible impact on income–mortality associations","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","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":"Health Sciences Centre; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Demography; Socioeconomic status; Medicine; Confidence interval; Social class; Odds ratio; Household income; Cohort study; Cohort; Age adjustment; Mortality rate; Odds; Population; Epidemiology; Logistic regression; Internal medicine; Economics; Geography","score_opus":0.5658545191601155,"score_gpt":0.6441437235070592,"score_spread":0.07828920434694364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112598277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9502569,0.00009761304,0.0047477623,0.03264392,0.0020787765,0.0001902491,0.00001529252,0.000023838968,0.009945651],"genre_scores_gemma":[0.987,0.00030443052,0.0015098477,0.00776103,0.0032140159,0.0000013998059,0.0000048062184,0.00000802219,0.00019646496],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9877887,0.0065770713,0.004289253,0.00019483698,0.0004253647,0.00072479714],"domain_scores_gemma":[0.94726413,0.048301578,0.003311863,0.00015442065,0.00036162528,0.0006063774],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0840612,0.00013015645,0.001504011,0.000120297205,0.0005419119,0.000026332606,0.0003432262,0.0005873734,0.00015593479],"category_scores_gemma":[0.09770874,0.000096404816,0.00086222583,0.00026701653,0.00039179166,0.00018201268,0.000018232573,0.0009871549,0.000026728381],"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":[0.00010746185,0.00018520012,0.8862256,0.000008023643,0.00009092458,0.000016846605,0.0005579891,0.000033240663,0.0000010384191,0.09920205,0.007519556,0.0060520875],"study_design_scores_gemma":[0.00036645672,0.00028827443,0.9530507,0.000021347065,0.0000361008,0.0000013782674,0.0004191119,0.000012147936,0.0000011875771,0.03636102,0.00935811,0.000084185944],"about_ca_topic_score_codex":0.0032248416,"about_ca_topic_score_gemma":0.0043218066,"teacher_disagreement_score":0.06682511,"about_ca_system_score_codex":0.0003410461,"about_ca_system_score_gemma":0.0011160878,"threshold_uncertainty_score":0.9431518},"labels":[],"label_agreement":null},{"id":"W2114020743","doi":"10.1016/j.jclinepi.2008.05.013","title":"The quality of reporting of trial abstracts is suboptimal: Survey of major general medical journals","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":133,"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":"Blinding; Randomized controlled trial; Medicine; Consolidated Standards of Reporting Trials; MEDLINE; Family medicine; Medical journal; Alternative medicine; Population; Surgery; Environmental health; Pathology","score_opus":0.9876513373407932,"score_gpt":0.7958890913357177,"score_spread":0.19176224600507552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114020743","genre_codex":"review","genre_gemma":"review","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011101861,0.98187757,0.0016559992,0.0011772884,0.0030227972,0.00074123975,0.00006605313,9.065835e-7,0.00035629954],"genre_scores_gemma":[0.0011736412,0.9918262,0.0049361973,0.00026183276,0.0013525788,0.000005036762,0.0000057163734,0.000024381154,0.00041442263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.03745515,0.44036826,0.5075534,0.0012490808,0.0126477545,0.0007263236],"domain_scores_gemma":[0.0150696,0.48199493,0.49142924,0.003154428,0.007730048,0.0006217502],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.947161,0.0006726695,0.098400734,0.00062192563,0.00011473779,0.000049574035,0.0061493544,0.0018473325,0.002999678],"category_scores_gemma":[0.98779446,0.00023940994,0.038645003,0.0014563726,0.0013721068,0.00013727581,0.0003915914,0.0032748575,0.00005228604],"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":[0.0015779964,0.000507974,0.046735764,0.0027358676,0.005502037,0.000060515587,0.00003412412,0.000034945817,2.1328141e-7,0.00032232807,0.093992986,0.84849524],"study_design_scores_gemma":[0.005871591,0.0014248944,0.12737115,0.008985209,0.0033713493,0.0014279679,0.00003943795,0.00022103376,7.75551e-7,0.0052190255,0.845613,0.00045457188],"about_ca_topic_score_codex":0.000238398,"about_ca_topic_score_gemma":0.00009588171,"teacher_disagreement_score":0.8480407,"about_ca_system_score_codex":0.000035768437,"about_ca_system_score_gemma":0.0042638257,"threshold_uncertainty_score":0.9994485},"labels":[],"label_agreement":null},{"id":"W2114532574","doi":"10.1016/j.jclinepi.2004.12.004","title":"Simulated computerized adaptive tests for measuring functional status were efficient with good discriminant validity in patients with hip, knee, or foot/ankle impairments","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":117,"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":"Computerized adaptive testing; Discriminant validity; Physical medicine and rehabilitation; Physical therapy; Psychology; Rating scale; Item response theory; Ankle; Discriminant function analysis; Linear discriminant analysis; Psychometrics; Rehabilitation; Differential item functioning; Concurrent validity; Activities of daily living; Statistics; Medicine; Clinical psychology; Mathematics; Developmental psychology; Surgery","score_opus":0.22876425594685032,"score_gpt":0.41777185491721697,"score_spread":0.18900759897036665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114532574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824142,0.000049662,0.01420845,0.0017249872,0.00060697383,0.0009215741,0.000024122566,0.000022578119,0.00002743701],"genre_scores_gemma":[0.9641286,0.000014575755,0.03435488,0.0009302245,0.00041931248,0.000008378358,0.0000175268,0.0000366872,0.000089815316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939931,0.001117918,0.0032743004,0.00042747823,0.0004748305,0.00071236014],"domain_scores_gemma":[0.9830917,0.013366192,0.0021296318,0.00026444637,0.00058590656,0.0005620842],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049046213,0.00032399193,0.0026577662,0.00019761798,0.00007661827,0.0000072428443,0.00010901674,0.00024356694,0.00006143561],"category_scores_gemma":[0.010523087,0.0001730233,0.00040693503,0.00017438245,0.00026629053,0.00014074902,0.00007314556,0.0008519674,0.0000084486655],"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":[0.050372027,0.002521592,0.903904,0.00004882749,0.00036720154,0.000064219705,0.00006926071,0.034805,0.000004613623,0.00003981315,0.00020423553,0.007599164],"study_design_scores_gemma":[0.039254185,0.023689507,0.92043585,0.00044561794,0.00023517405,0.00011934823,0.000051606927,0.014425784,0.000006585304,0.00005577658,0.001086897,0.00019366277],"about_ca_topic_score_codex":0.00001867506,"about_ca_topic_score_gemma":0.00009447922,"teacher_disagreement_score":0.021167915,"about_ca_system_score_codex":0.0002568419,"about_ca_system_score_gemma":0.00055764185,"threshold_uncertainty_score":0.9978117},"labels":[],"label_agreement":null},{"id":"W2114686628","doi":"10.1016/j.jclinepi.2008.02.009","title":"A new 'Mechanistic-Practical” Framework for designing and interpreting randomized trials","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":93,"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; McMaster University","funders":"","keywords":"Randomized controlled trial; Interpretation (philosophy); Clinical trial; Perspective (graphical); Medicine; Management science; Research design; Computer science; Medical physics; Psychology; Artificial intelligence; Surgery; Sociology; Pathology","score_opus":0.9035995120411151,"score_gpt":0.6735499002739189,"score_spread":0.23004961176719618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114686628","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":[0.008746975,0.0029008496,0.8810756,0.10420411,0.002222837,0.00061491283,0.000014965911,0.000011298311,0.00020844015],"genre_scores_gemma":[0.06848862,0.0023986488,0.8932494,0.032603864,0.0030833455,0.000025281246,0.0000017706058,0.000026399683,0.00012269696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9350883,0.02248973,0.041267034,0.0005373573,0.00008302263,0.0005345979],"domain_scores_gemma":[0.13988695,0.8197442,0.039076988,0.0003399465,0.0002283653,0.0007235106],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5278637,0.0001934201,0.011808243,0.00023183935,0.000156823,0.000020069849,0.00022351668,0.00056439295,0.00026628256],"category_scores_gemma":[0.9461697,0.00017405805,0.0013848213,0.00007392094,0.00024893062,0.00026857835,0.000050197123,0.000851628,0.000082585306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012570977,0.00008632965,0.02681188,0.000114049486,0.00058969256,0.000007029959,0.0004821513,0.0000689051,8.0961286e-7,0.90562874,0.051946234,0.0016932194],"study_design_scores_gemma":[0.031007998,0.00049915607,0.0020772936,0.00025559988,0.00008278703,0.00017724647,0.00014338562,0.008731168,0.0000013137809,0.94406855,0.012764788,0.00019074033],"about_ca_topic_score_codex":0.000069502865,"about_ca_topic_score_gemma":0.0000024763071,"teacher_disagreement_score":0.7972545,"about_ca_system_score_codex":0.00008818786,"about_ca_system_score_gemma":0.0005298349,"threshold_uncertainty_score":0.80718786},"labels":[],"label_agreement":null},{"id":"W2115164020","doi":"10.1016/j.jclinepi.2012.09.006","title":"Call to RECORD: the need for complete reporting of research using routinely collected health data","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":40,"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; University of Ottawa","funders":"National Institute for Health and Care Research; Wellcome Trust","keywords":"Scopus; Medicine; Observational study; Family medicine; Epidemiology; Health care; MEDLINE; Strengthening the reporting of observational studies in epidemiology; Citation; Medical record; Library science; Pathology; Computer science; Political science; Internal medicine","score_opus":0.9581350051145759,"score_gpt":0.7306230364735641,"score_spread":0.22751196864101186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115164020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.864504,0.0018280315,0.04543012,0.08550743,0.0016049778,0.000807309,0.000035231144,0.000009054279,0.00027385663],"genre_scores_gemma":[0.82362133,0.00018883828,0.15926862,0.013454448,0.0033389246,0.0000031648997,0.000011929775,0.000016944912,0.000095777534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98224205,0.004394569,0.0118219685,0.0002672599,0.0004529126,0.0008212703],"domain_scores_gemma":[0.89140946,0.07946141,0.022933912,0.0015880421,0.0031459536,0.0014612064],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19942243,0.000107709406,0.0028226986,0.0001444583,0.00016466188,0.0000043943855,0.0005241996,0.00017961679,0.00002295387],"category_scores_gemma":[0.49825686,0.00006376098,0.00038119132,0.0004668549,0.00025320545,0.00011256418,0.00026844974,0.0011951004,0.0000023895755],"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":[0.0027176528,0.00011515583,0.86834013,0.000090948124,0.00016493429,0.000011507249,0.00014404468,0.00011094783,0.00019680527,0.0003294129,0.11660212,0.0111763235],"study_design_scores_gemma":[0.0022046277,0.004765031,0.8807773,0.0011078259,0.00016411589,0.0011125315,0.0007706083,0.009929687,0.000011159428,0.0012732199,0.09776815,0.00011572027],"about_ca_topic_score_codex":0.0014249823,"about_ca_topic_score_gemma":0.00013057806,"teacher_disagreement_score":0.29883444,"about_ca_system_score_codex":0.00012212477,"about_ca_system_score_gemma":0.0013200088,"threshold_uncertainty_score":0.82436305},"labels":[],"label_agreement":null},{"id":"W2115356257","doi":"10.1016/j.jclinepi.2009.08.029","title":"Quebec Back Pain Disability Scale was responsive and showed reasonable interpretability after a multidisciplinary treatment","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":47,"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":"Interpretability; Medicine; Physical therapy; Receiver operating characteristic; Cutoff; Low back pain; Confidence interval; Pain scale; Physical medicine and rehabilitation; Internal medicine; Machine learning; Alternative medicine","score_opus":0.06915206335633707,"score_gpt":0.45130502586612603,"score_spread":0.382152962509789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115356257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96863735,0.00027879726,0.00053534535,0.029154642,0.0007408113,0.00048022764,0.0000064405494,0.000011429918,0.00015497993],"genre_scores_gemma":[0.9804886,0.00013492782,0.017067907,0.0010580757,0.00068166514,0.000017884164,0.0000051123634,0.000014587615,0.00053123065],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9865746,0.009051065,0.0034080243,0.00046866658,0.00016196353,0.00033568582],"domain_scores_gemma":[0.93956095,0.05771978,0.0010881919,0.00060013373,0.00033932592,0.00069161993],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03852915,0.00023039542,0.002305484,0.000059171074,0.000051579853,0.0000061558108,0.000102434875,0.00054130936,0.0004838624],"category_scores_gemma":[0.119851306,0.0001348636,0.0010183934,0.00008785805,0.001760705,0.00012649041,0.00007958194,0.0011375705,0.000018930794],"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":[0.007314996,0.0012322812,0.9397786,0.00023674723,0.00011048648,0.000013544035,0.00029854625,0.0000024481767,0.000712131,0.0000655867,0.0003519771,0.04988265],"study_design_scores_gemma":[0.0023153843,0.00462064,0.9854045,0.00019154543,0.00009600569,0.000060026574,0.00024303418,0.0012838972,0.000015552834,0.003303053,0.002350771,0.00011561144],"about_ca_topic_score_codex":0.0004813761,"about_ca_topic_score_gemma":0.0030465918,"teacher_disagreement_score":0.08132215,"about_ca_system_score_codex":0.00012511933,"about_ca_system_score_gemma":0.00030520963,"threshold_uncertainty_score":0.99003655},"labels":[],"label_agreement":null},{"id":"W2116984366","doi":"10.1016/j.jclinepi.2015.02.008","title":"Health administrative data can be used to define a shared care typology for people with HIV","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","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":"University of Toronto; St. Michael's Hospital; Ottawa Hospital; Institute for Clinical Evaluative Sciences; Bruyère; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Typology; Human immunodeficiency virus (HIV); Public health; Medicine; Health care; Environmental health; Family medicine; Nursing; Geography; Political science","score_opus":0.6709857742037694,"score_gpt":0.6292434630923853,"score_spread":0.041742311111384045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116984366","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":[0.18537153,0.0013048426,0.03606758,0.772334,0.00045883312,0.0012835517,0.0018814201,0.000022092261,0.0012761585],"genre_scores_gemma":[0.82505083,0.00023470767,0.14844055,0.020316036,0.0019879732,0.000048891197,0.0012999522,0.00004795216,0.0025731155],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943558,0.0018800399,0.0026751012,0.00034672517,0.00022820194,0.000514145],"domain_scores_gemma":[0.9860002,0.009146318,0.0013045884,0.0006064324,0.0010712249,0.0018712765],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01211257,0.00014232736,0.0025381874,0.00015061969,0.00005580561,0.000006027953,0.00043900902,0.00018584734,0.0001352333],"category_scores_gemma":[0.1211866,0.000090446636,0.00033525517,0.00016645418,0.00019243629,0.000081054925,0.00013406368,0.000775967,0.00001726858],"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":[0.0056547513,0.00038743808,0.19515422,0.00012304285,0.00036850208,0.000051839736,0.000961895,0.000008614572,0.000005361265,0.0015392094,0.7892455,0.0064996704],"study_design_scores_gemma":[0.018876852,0.19527426,0.15151855,0.0008745588,0.00033010612,0.0014110772,0.009376385,0.0013446952,0.000010927964,0.0015289102,0.6191596,0.00029410108],"about_ca_topic_score_codex":0.00029496223,"about_ca_topic_score_gemma":0.01180871,"teacher_disagreement_score":0.752018,"about_ca_system_score_codex":0.00010940957,"about_ca_system_score_gemma":0.0034276946,"threshold_uncertainty_score":0.88621604},"labels":[],"label_agreement":null},{"id":"W2118278867","doi":"10.1016/j.jclinepi.2014.05.003","title":"The Hospital-patient One-year Mortality Risk score accurately predicted long-term death risk in hospitalized patients","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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 Ottawa","funders":"","keywords":"Medicine; Emergency medicine; Hospital admission; Statistic; Framingham Risk Score; Cohort; Intensive care unit; Population; Risk assessment; Cohort study; Pediatrics; Intensive care medicine; Disease; Internal medicine","score_opus":0.3115749063106973,"score_gpt":0.49118427008742965,"score_spread":0.17960936377673237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118278867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944275,0.0006106994,0.00016656383,0.0022358962,0.0016931377,0.0006414209,0.000031581185,0.000017215585,0.00017600268],"genre_scores_gemma":[0.98653436,0.010955609,0.00076324877,0.0010993911,0.00056148163,0.000026526788,0.000023909797,0.000026740167,0.000008729603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9875375,0.0056182705,0.00538148,0.00044424244,0.00045975138,0.000558739],"domain_scores_gemma":[0.96920913,0.023036623,0.005885581,0.00070785935,0.0005811844,0.0005796288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013009925,0.00029988433,0.0027124998,0.00010757954,0.00013233197,0.000015881571,0.000311432,0.00043872118,0.00006131736],"category_scores_gemma":[0.12578183,0.00016594763,0.0010263409,0.00016241406,0.00032158554,0.00010899825,0.000106568375,0.0014676539,0.000026539607],"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":[0.00091083936,0.0030640364,0.96244127,0.000015855992,0.0007628889,0.00003280794,0.000054581797,0.000031144617,1.0535988e-7,0.00017308285,0.0011017477,0.031411663],"study_design_scores_gemma":[0.008766872,0.009913789,0.9763132,0.00029247918,0.0007099948,0.000006957347,0.000014239211,0.00019857274,0.0000065678537,0.0032077737,0.0004268043,0.00014278592],"about_ca_topic_score_codex":0.00017164806,"about_ca_topic_score_gemma":0.0000713464,"teacher_disagreement_score":0.112771906,"about_ca_system_score_codex":0.00013070216,"about_ca_system_score_gemma":0.00016811503,"threshold_uncertainty_score":0.8815821},"labels":[],"label_agreement":null},{"id":"W2118299779","doi":"10.1016/j.jclinepi.2012.04.001","title":"Urgent readmission rates can be used to infer differences in avoidable readmission rates between hospitals","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Heart Failure Treatment and Management","field":"Medicine","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":"Institute for Clinical Evaluative Sciences; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Interquartile range; Medicine; Emergency medicine; Hospital readmission; Internal medicine","score_opus":0.35262200223835666,"score_gpt":0.5135693161233351,"score_spread":0.16094731388497846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118299779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85377324,0.0004081728,0.00015743994,0.14450784,0.00054771424,0.00040001984,0.0000026493171,0.000013953357,0.00018898021],"genre_scores_gemma":[0.98758626,0.00059248897,0.004216416,0.00535617,0.0010889773,0.00001216316,0.000013217596,0.00001849709,0.0011158201],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99376553,0.0014452848,0.0035579698,0.00027745374,0.0002865523,0.00066718337],"domain_scores_gemma":[0.98491275,0.011564442,0.001111099,0.00029337025,0.00015188627,0.001966473],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015974523,0.00025288496,0.0028527952,0.0002841852,0.000055922665,0.00000813995,0.00016238134,0.00037420253,0.0005148941],"category_scores_gemma":[0.05094217,0.00014928261,0.00042181878,0.00021259427,0.0000878788,0.00014623637,0.00010835344,0.00073240494,0.000045601155],"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":[0.00035455578,0.00045974157,0.9627214,0.00003459808,0.00016572578,0.00003816974,0.00018457041,0.0000032006326,0.0001642141,0.00020631596,0.030810883,0.004856621],"study_design_scores_gemma":[0.0018651448,0.0023110488,0.9185457,0.00039752724,0.00018068826,0.000014671131,0.00012969953,0.000014666676,0.00044934655,0.00070794293,0.07524462,0.00013893892],"about_ca_topic_score_codex":0.00014982183,"about_ca_topic_score_gemma":0.00003435084,"teacher_disagreement_score":0.13915166,"about_ca_system_score_codex":0.00010607504,"about_ca_system_score_gemma":0.0003002903,"threshold_uncertainty_score":0.9570522},"labels":[],"label_agreement":null},{"id":"W2118788859","doi":"10.1016/j.jclinepi.2012.09.013","title":"Some improvements are apparent in identifying adverse effects in systematic reviews from 1994 to 2011","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Systematic review; Medicine; Adverse effect; MEDLINE; Meta-analysis; Data extraction; Internal medicine","score_opus":0.8816318847741158,"score_gpt":0.6463443115375861,"score_spread":0.2352875732365297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118788859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.955688,0.017680919,0.014186058,0.003555733,0.004170972,0.004607444,0.0000041270996,0.0000024349515,0.00010429137],"genre_scores_gemma":[0.95346874,0.0025676773,0.026576584,0.014504734,0.0012795227,0.00039718527,0.000002835866,0.000028581415,0.0011741208],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6629929,0.21324493,0.11858575,0.0014423166,0.0029546213,0.0007794687],"domain_scores_gemma":[0.4372071,0.4362458,0.11822802,0.005608788,0.0012639005,0.001446386],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.5717565,0.00038625486,0.026305998,0.0008342227,0.00003474521,0.00009331625,0.0024491958,0.00031538893,0.0021781973],"category_scores_gemma":[0.74222434,0.00017095939,0.004664662,0.0006580887,0.000064250795,0.00054791407,0.0002831862,0.00092163944,0.009248331],"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":[0.000026931468,0.00024116872,0.9301883,0.0024187984,0.00024119392,0.00004877186,0.00016250442,0.00022715017,0.000030372532,0.0002631564,0.057135135,0.0090165],"study_design_scores_gemma":[0.0010767177,0.00025379975,0.91186804,0.008606253,0.0002640477,0.0000105379295,0.00038474955,0.0035118533,0.000001563581,0.07006818,0.0037243906,0.00022986118],"about_ca_topic_score_codex":0.00024345219,"about_ca_topic_score_gemma":0.00022478268,"teacher_disagreement_score":0.22578579,"about_ca_system_score_codex":0.0000956821,"about_ca_system_score_gemma":0.00007325897,"threshold_uncertainty_score":0.99873394},"labels":[],"label_agreement":null},{"id":"W2118803436","doi":"10.1016/j.jclinepi.2004.11.028","title":"Powering our way to the elusive side effect: A composite outcome ‘basket’ of predefined designated endpoints in each organ system should be included in all controlled trials","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Inflammatory mediators and NSAID effects","field":"Medicine","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Medicine; Sample size determination; Rofecoxib; Clinical trial; Clinical endpoint; Population; Relative risk; Intensive care medicine; Confidence interval; Internal medicine; Statistics","score_opus":0.3201792477276133,"score_gpt":0.5237674917931054,"score_spread":0.20358824406549214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118803436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97143036,0.000511315,0.000632025,0.023982614,0.001207517,0.0020494845,0.000006221857,0.000018941219,0.0001615303],"genre_scores_gemma":[0.9913447,0.00006802615,0.0014746098,0.0057534087,0.0012434149,0.000039958766,0.000004352494,0.00003461512,0.000036928195],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9590061,0.025462303,0.013997446,0.00038177177,0.00048044097,0.0006719563],"domain_scores_gemma":[0.9015419,0.091423795,0.0057303384,0.000445046,0.00032691343,0.00053199],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15669124,0.00038501946,0.012100473,0.0005600791,0.000038587004,0.0000065704394,0.0004115089,0.00068520557,0.000025428724],"category_scores_gemma":[0.26844698,0.00020391041,0.0014053868,0.00032642848,0.000085478656,0.00007930192,0.00013496859,0.0018935292,0.000018581166],"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":[0.069260985,0.0008083354,0.889439,0.000596206,0.001467092,0.0012883967,0.00096620637,0.0064568077,0.022108417,0.0003038526,0.0021097802,0.0051949234],"study_design_scores_gemma":[0.10971002,0.009886795,0.85297984,0.0034076453,0.0014979573,0.0007881179,0.0004434234,0.012840397,0.0062965113,0.000110286426,0.0015401976,0.00049882365],"about_ca_topic_score_codex":0.00008711235,"about_ca_topic_score_gemma":0.00017550946,"teacher_disagreement_score":0.11175574,"about_ca_system_score_codex":0.00029249,"about_ca_system_score_gemma":0.00025043753,"threshold_uncertainty_score":0.86836386},"labels":[],"label_agreement":null},{"id":"W2119664063","doi":"10.1016/j.jclinepi.2007.12.013","title":"Evaluation of a diabetes management program in China demonstrated association of improved continuity of care with clinical outcomes","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","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":"St. Michael's Hospital; Centre for Global Health Research; University of Toronto","funders":"Shanghai Municipal Health Bureau","keywords":"Medicine; Glycemic; Diabetes mellitus; Fructosamine; Body mass index; Diabetes management; Blood pressure; Physical therapy; Medical record; Weight management; Weight loss; Type 2 diabetes; Emergency medicine; Internal medicine; Obesity; Overweight","score_opus":0.26868990141619625,"score_gpt":0.5928842145222347,"score_spread":0.32419431310603847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119664063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99281883,0.00043711995,0.00010085777,0.0030413049,0.00083426526,0.0012253361,0.000017475986,0.000010068611,0.0015147458],"genre_scores_gemma":[0.9902173,0.0009980754,0.007203494,0.0013251338,0.00015087856,0.000033631022,0.000010927993,0.000012172842,0.000048366677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96659386,0.019971328,0.011974482,0.00025985952,0.00069136935,0.0005091054],"domain_scores_gemma":[0.9523721,0.030298017,0.014227367,0.0003032675,0.0026181496,0.0001811022],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08174265,0.00017115352,0.0042717014,0.00021384483,0.00006739355,5.494156e-7,0.00027948734,0.00072182046,0.00004609852],"category_scores_gemma":[0.053957228,0.00011352785,0.0006766791,0.0002711541,0.0003035798,0.00010487477,0.00008615501,0.0015623502,0.0000016495685],"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":[0.00054861,0.00059332064,0.94526553,0.0005103037,0.0004736836,0.0000026743032,0.00028125697,0.00002835691,0.000002578392,0.00015942853,0.0007272892,0.051406946],"study_design_scores_gemma":[0.007328428,0.0026987272,0.98682964,0.00034645892,0.00046439245,7.52755e-7,0.00036297305,0.0003822316,0.0000030652818,0.0011698116,0.00033149062,0.00008200548],"about_ca_topic_score_codex":0.00014340537,"about_ca_topic_score_gemma":0.0006506085,"teacher_disagreement_score":0.05132494,"about_ca_system_score_codex":0.0003539775,"about_ca_system_score_gemma":0.0026719507,"threshold_uncertainty_score":0.9540117},"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":"W2120720728","doi":"10.1016/j.jclinepi.2013.09.008","title":"A users' guide to understanding therapeutic substitutions","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McMaster University; University of British Columbia; Dalhousie University; University of Ottawa; Centre for Advancing Health Outcomes","funders":"Canadian Institutes of Health Research; Pfizer","keywords":"Mechanism (biology); Medicine; Therapeutic approach; MEDLINE; Drug; Computer science; Risk analysis (engineering); Bioinformatics; Pharmacology; Biology; Pathology; Disease","score_opus":0.8695492125528388,"score_gpt":0.6268938302587176,"score_spread":0.2426553822941212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120720728","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":[0.07876897,0.0016644527,0.46789375,0.44093448,0.0035801094,0.0005128261,0.00002112293,0.000022744387,0.006601558],"genre_scores_gemma":[0.81888014,0.000513261,0.03559649,0.14230478,0.0019019239,0.000026290456,0.0000025660527,0.000026571435,0.00074795604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9773684,0.0031076146,0.01861415,0.00035461495,0.00007112605,0.00048407592],"domain_scores_gemma":[0.93250793,0.053574607,0.012267428,0.00057688775,0.0002016318,0.0008714883],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.121208414,0.00015908609,0.0031799024,0.00035663223,0.00013416077,0.00002897304,0.00044297197,0.00031399966,0.0011783498],"category_scores_gemma":[0.14884706,0.00015499229,0.000588821,0.00018041176,0.00018346778,0.0004307015,0.000050876257,0.0005818509,0.003840835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001788544,0.00007124849,0.2650113,0.00002781666,0.00013389235,0.000001240173,0.00013355887,0.00043043034,7.5698966e-7,0.60116994,0.1327953,0.00020662532],"study_design_scores_gemma":[0.0009737841,0.00042429747,0.27661365,0.000091900176,0.000015260044,0.000038025693,0.00059336395,0.0021733535,2.5846734e-7,0.5087305,0.21012847,0.0002171712],"about_ca_topic_score_codex":0.00037771757,"about_ca_topic_score_gemma":0.00005577785,"teacher_disagreement_score":0.7401112,"about_ca_system_score_codex":0.0005095932,"about_ca_system_score_gemma":0.00029549366,"threshold_uncertainty_score":0.9997347},"labels":[],"label_agreement":null},{"id":"W2120836888","doi":"10.1016/j.jclinepi.2005.10.016","title":"VEINES-QOL/Sym questionnaire was a reliable and valid disease-specific quality of life measure for deep venous thrombosis","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":200,"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; McGill University; Jewish General Hospital","funders":"Sanofi","keywords":"Medicine; Quality of life (healthcare); Discriminant validity; Deep vein; Construct validity; Venous thrombosis; Gold standard (test); Physical therapy; Convergent validity; Thrombosis; Internal consistency; Psychometrics; Surgery; Internal medicine; Clinical psychology","score_opus":0.2834046305202028,"score_gpt":0.4736820063845112,"score_spread":0.19027737586430837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120836888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94444406,0.016696032,0.013257881,0.023214936,0.0013286928,0.00066798483,0.000015639713,0.000025831214,0.0003489301],"genre_scores_gemma":[0.9842706,0.005331722,0.0059806313,0.0025490383,0.0017670874,0.000018301127,0.000010367099,0.000027950882,0.00004433771],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992919,0.0011888342,0.004841838,0.0003591777,0.00030657646,0.00038457508],"domain_scores_gemma":[0.9885694,0.006808581,0.0030055363,0.0004025467,0.0006783235,0.00053564913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016751343,0.00021791524,0.0040406855,0.00012420231,0.00008740626,0.0000072054504,0.00017161164,0.00029107765,0.000046760757],"category_scores_gemma":[0.024844533,0.00015997622,0.00093669945,0.0001205921,0.00035129595,0.00008681414,0.000058758258,0.00044883986,0.0000045834245],"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":[0.0024880446,0.00445978,0.89723235,0.0010023613,0.00073221023,0.000025263182,0.00006590213,0.0007338154,0.00008388542,0.025769264,0.0606271,0.0067800484],"study_design_scores_gemma":[0.0032079592,0.0022866116,0.9575737,0.00048287393,0.00055985776,0.000013858887,0.000048597783,0.00023529357,0.00000776878,0.021676002,0.013766565,0.00014090656],"about_ca_topic_score_codex":0.00017427644,"about_ca_topic_score_gemma":0.000041533345,"teacher_disagreement_score":0.060341377,"about_ca_system_score_codex":0.00005211913,"about_ca_system_score_gemma":0.00026089977,"threshold_uncertainty_score":0.9833696},"labels":[],"label_agreement":null},{"id":"W2122091183","doi":"10.1016/j.jclinepi.2009.09.015","title":"A prospective global measure, the Punum Ladder, provides more valid assessments of quality of life than a retrospective transition measure","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Respiratory and Cough-Related Research","field":"Medicine","cited_by":70,"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":"Measure (data warehouse); Quality of life (healthcare); Medicine; Quality (philosophy); Physics; Computer science; Data mining; Nursing","score_opus":0.3164953344064468,"score_gpt":0.5573639321564281,"score_spread":0.24086859774998132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122091183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797766,0.00066844246,0.0031165618,0.013310875,0.00070918514,0.0006869037,0.000033847722,0.000011804397,0.0016857298],"genre_scores_gemma":[0.99657905,0.00016097024,0.0011052169,0.0013457278,0.0007512404,0.000011649993,0.0000020792127,0.000014336621,0.000029706154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98575187,0.007415349,0.0049900827,0.00036557298,0.0010843992,0.00039274103],"domain_scores_gemma":[0.982955,0.008613592,0.004403723,0.0005842445,0.0029622437,0.00048119246],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050267737,0.00022136372,0.0030550705,0.000087617445,0.000085101965,0.0000060606644,0.00040181875,0.00075835455,0.00007713923],"category_scores_gemma":[0.11058356,0.0001226837,0.0012628385,0.0004037256,0.0012862852,0.00015872001,0.000050382598,0.0033298407,0.0000030574736],"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":[0.009494308,0.0011768222,0.975024,0.00015170389,0.0013851174,0.000023151171,0.00020743709,0.000028587636,0.0024098747,0.005354641,0.00073319545,0.0040112026],"study_design_scores_gemma":[0.0041762954,0.003784507,0.97261083,0.00023664703,0.00028534757,0.00009258501,0.00040510806,0.00013799267,0.0002740791,0.017749758,0.00014878092,0.0000980388],"about_ca_topic_score_codex":0.00011555543,"about_ca_topic_score_gemma":0.00008464288,"teacher_disagreement_score":0.06031582,"about_ca_system_score_codex":0.0000893018,"about_ca_system_score_gemma":0.0017510143,"threshold_uncertainty_score":0.9989695},"labels":[],"label_agreement":null},{"id":"W2122274466","doi":"10.1016/j.jclinepi.2008.09.014","title":"An international survey indicated that unpublished systematic reviews exist","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":75,"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; Canadian Institutes of Health Research; University of Ottawa; Children's Hospital of Eastern Ontario; University of Toronto; Institute of Population and Public Health","funders":"","keywords":"Library science; Medicine; MEDLINE; Family medicine; Political science; Computer science","score_opus":0.9649852237098306,"score_gpt":0.720360227945394,"score_spread":0.24462499576443664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122274466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6926024,0.01434464,0.19508141,0.052305523,0.020491129,0.0045955786,0.00006204309,0.000028055718,0.020489238],"genre_scores_gemma":[0.9736452,0.001445399,0.012179514,0.010443057,0.00090988964,0.000007275662,0.000019306124,0.000010444517,0.0013398912],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.3549788,0.512891,0.12490299,0.0013954844,0.0052503003,0.0005814416],"domain_scores_gemma":[0.3103646,0.4679166,0.20539889,0.007673905,0.007011665,0.0016343347],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.881766,0.0003771261,0.025534563,0.0006686415,0.00008051588,0.00041683746,0.00612418,0.00042699475,0.003910153],"category_scores_gemma":[0.9347229,0.00015004123,0.0064182123,0.0009776131,0.00017540665,0.00094814127,0.00008223551,0.0010348102,0.0011942189],"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":[0.00007768618,0.000328527,0.82408047,0.00020422379,0.00043463547,0.00002073826,0.00005373515,0.00006472169,0.000003302958,0.002462603,0.1570124,0.015256985],"study_design_scores_gemma":[0.00044489402,0.00047916023,0.9215862,0.0006131742,0.00025799082,0.0001427208,0.00005595443,0.002375713,3.5446493e-7,0.02685877,0.047024004,0.00016107551],"about_ca_topic_score_codex":0.000010005276,"about_ca_topic_score_gemma":0.000021932858,"teacher_disagreement_score":0.28104284,"about_ca_system_score_codex":0.000044100998,"about_ca_system_score_gemma":0.00018412682,"threshold_uncertainty_score":0.9995835},"labels":[],"label_agreement":null},{"id":"W2122504861","doi":"10.1016/j.jclinepi.2012.05.010","title":"Development of a scale for assessing respondents' perceptions of health research questionnaires (the REP-HQ Scale)","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"Université Laval","funders":"Institut National Du Cancer","keywords":"Scale (ratio); Psychology; Perception; Psychometrics; Applied psychology; Environmental health; Medicine; Family medicine; Clinical psychology; Geography; Cartography","score_opus":0.8849215496635899,"score_gpt":0.7328099719886317,"score_spread":0.1521115776749582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122504861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9344832,0.00084736175,0.046574276,0.016224649,0.0015015445,0.00021023516,0.0000026393634,0.0000049890823,0.00015113222],"genre_scores_gemma":[0.80718136,0.0004111767,0.19088385,0.0005296727,0.00079267705,0.000008364142,9.909141e-7,0.000007139496,0.00018475884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.511881,0.4750208,0.010367215,0.00037703582,0.0009804158,0.0013735377],"domain_scores_gemma":[0.57110107,0.42322946,0.003786529,0.0002797919,0.0012360502,0.00036713708],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.75172484,0.00008688002,0.0014711263,0.00022857983,0.0007360713,0.0000055283317,0.0004879258,0.00039166273,0.000081044716],"category_scores_gemma":[0.58684254,0.00005821808,0.0004472728,0.00034810012,0.002214562,0.00020412984,0.00007894718,0.0008992523,0.000005407167],"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":[0.0031914338,0.0004323367,0.8978137,0.00003458621,0.000068791574,3.6194743e-7,0.012456718,0.000008488286,0.00017785431,0.0025240423,0.0032900923,0.08000163],"study_design_scores_gemma":[0.00035189028,0.00024501176,0.96814805,0.00015679568,0.00001748258,0.000007850696,0.0068486747,0.0000076059514,0.000032000247,0.005704734,0.018431302,0.000048571626],"about_ca_topic_score_codex":0.00020807532,"about_ca_topic_score_gemma":0.0005203238,"teacher_disagreement_score":0.16488232,"about_ca_system_score_codex":0.00010365368,"about_ca_system_score_gemma":0.0026879122,"threshold_uncertainty_score":0.8159646},"labels":[],"label_agreement":null},{"id":"W2123635123","doi":"10.1016/j.jclinepi.2005.11.013","title":"A user's guide to selecting a comorbidity index for clinical research","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":143,"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":"Medicine; Comorbidity; Radiation therapy; COPD; Cancer; Laryngectomy; Internal medicine; Observational study; Larynx; Diabetes mellitus; Physical therapy; Intensive care medicine; Surgery","score_opus":0.6373271331157568,"score_gpt":0.6721371763308686,"score_spread":0.03481004321511172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123635123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8462223,0.00080407417,0.055383157,0.07928363,0.0029625616,0.0014766225,0.000011250688,0.00006146146,0.013794959],"genre_scores_gemma":[0.9377967,0.0006619407,0.03531678,0.009818942,0.0130870845,0.000029914627,0.000012290307,0.0000486371,0.0032276828],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.985348,0.0050259787,0.0077722194,0.0005124579,0.0005030401,0.0008383074],"domain_scores_gemma":[0.91878366,0.07629969,0.0020827788,0.0005467223,0.0015055056,0.000781615],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.103547,0.00018825763,0.0028652204,0.00032603773,0.00011840288,0.000018752808,0.00041825158,0.00043244514,0.00013188366],"category_scores_gemma":[0.22451638,0.00014288463,0.0012599621,0.00037949308,0.000467902,0.00009851543,0.00020271318,0.0019113552,0.00004772512],"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":[0.0018150897,0.0005643655,0.4912334,0.000073813164,0.00018885528,0.00008154508,0.000003967895,0.00014832625,0.000004196657,0.0048997584,0.49267456,0.008312115],"study_design_scores_gemma":[0.0040027634,0.0029158376,0.5770241,0.00016391753,0.00014178352,0.0000700389,0.00007091826,0.0008676949,0.0000023571554,0.014309285,0.4003377,0.00009361403],"about_ca_topic_score_codex":0.00019149235,"about_ca_topic_score_gemma":0.00011371669,"teacher_disagreement_score":0.120969385,"about_ca_system_score_codex":0.00015710395,"about_ca_system_score_gemma":0.0012139663,"threshold_uncertainty_score":0.923087},"labels":[],"label_agreement":null},{"id":"W2123768626","doi":"10.1016/j.jclinepi.2007.04.021","title":"Radar plots: a useful way for presenting multivariate health care data","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":220,"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. Michael's Hospital; University of Toronto","funders":"","keywords":"Radar chart; Bar chart; Multivariate statistics; Radar; Computer science; Pie chart; Relevance (law); Data presentation; Multivariate analysis; Data science; Presentation (obstetrics); Field (mathematics); Plot (graphics); Graphical model; Data mining; Information retrieval; Statistics; Artificial intelligence; Data collection; Machine learning; Mathematics; Medicine","score_opus":0.7121486938718011,"score_gpt":0.5746039580667881,"score_spread":0.13754473580501303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123768626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92200774,0.0027793134,0.041812953,0.03072017,0.0016383089,0.0004054214,0.00044687578,0.000034013865,0.00015517614],"genre_scores_gemma":[0.63929087,0.0014253354,0.34730163,0.0069830213,0.0046953075,0.0000038810476,0.00015167324,0.0000038021096,0.00014446392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98876584,0.0062751644,0.0038802302,0.00043718447,0.00018181035,0.00045977143],"domain_scores_gemma":[0.92343724,0.07312725,0.002556576,0.00018286247,0.0003088994,0.00038717446],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019997828,0.00015527355,0.0022146115,0.000018747818,0.0002822672,0.000008510191,0.000754237,0.00022651488,0.00010241184],"category_scores_gemma":[0.113086216,0.000053827014,0.0006338718,0.00015332924,0.00022673502,0.00013250549,0.00015484085,0.00054546806,0.0000056353447],"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":[0.0011517392,0.0006218282,0.31654555,0.000072277464,0.00057398924,0.0000863747,0.0002591111,0.00008951459,0.0006138196,0.0033746024,0.04580205,0.6308091],"study_design_scores_gemma":[0.00084311713,0.0017435973,0.8085728,0.00004366863,0.00008885921,0.00010729897,0.00032053818,0.0030320152,0.000011651335,0.005932215,0.17911498,0.00018924681],"about_ca_topic_score_codex":0.00013965751,"about_ca_topic_score_gemma":0.00009685121,"teacher_disagreement_score":0.6306199,"about_ca_system_score_codex":0.00001779807,"about_ca_system_score_gemma":0.00007055491,"threshold_uncertainty_score":0.8943846},"labels":[],"label_agreement":null},{"id":"W2123961659","doi":"10.1016/j.jclinepi.2008.06.020","title":"The Dutch diagnostic model for laboratory animal allergen sensitization was generalizable in Canadian apprentices","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Occupational exposure and asthma","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hôpital du Sacré-Cœur de Montréal","funders":"Medical Research Council; Canadian Institutes of Health Research; Medical Research Council Canada","keywords":"Apprenticeship; Sensitization; Medicine; Allergen; Environmental health; Allergy; Immunology; Geography","score_opus":0.20020230511919995,"score_gpt":0.46033216210224853,"score_spread":0.2601298569830486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123961659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95581883,0.0014198015,0.006062668,0.03572104,0.0005779536,0.00021987456,0.000015620264,0.0000039350157,0.00016027795],"genre_scores_gemma":[0.98421913,0.0023383491,0.007286124,0.004678676,0.0011649267,0.0000061544424,0.000016305987,0.000012273591,0.00027802665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965261,0.00074851373,0.0021213435,0.00014308996,0.00012022929,0.00034073097],"domain_scores_gemma":[0.97674775,0.021351976,0.0008539932,0.00013926954,0.00049761636,0.00040938682],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0076550827,0.00009522106,0.0008703494,0.00009238971,0.00011663705,0.0000032155467,0.00010173015,0.0002141469,0.00001620553],"category_scores_gemma":[0.06746423,0.00006098711,0.0002458141,0.00010667919,0.00014193234,0.0000762491,0.000012240571,0.00035626808,0.0000063707575],"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":[0.0006050014,0.00010622123,0.9400112,0.00001780496,0.000092628165,0.00007214146,0.000070755894,0.020009512,0.000037331087,0.0033573653,0.034991927,0.0006280927],"study_design_scores_gemma":[0.001619142,0.000682625,0.68092185,0.000052409894,0.000054495536,0.00011476357,0.000019258949,0.29139572,0.000010822395,0.003062292,0.021982972,0.00008362015],"about_ca_topic_score_codex":0.0018037737,"about_ca_topic_score_gemma":0.018520236,"teacher_disagreement_score":0.2713862,"about_ca_system_score_codex":0.00005443796,"about_ca_system_score_gemma":0.0014883167,"threshold_uncertainty_score":0.99938923},"labels":[],"label_agreement":null},{"id":"W2125475270","doi":"10.1016/j.jclinepi.2008.10.016","title":"Choice of data extraction tools for systematic reviews depends on resources and review complexity","year":2009,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":87,"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":"Data extraction; Computer science; Systematic review; Software portability; Table (database); Data science; Software; Listing (finance); Data collection; Selection (genetic algorithm); Data mining; MEDLINE; Machine learning","score_opus":0.9881436847521281,"score_gpt":0.7700061760786993,"score_spread":0.21813750867342885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125475270","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":[0.0000035648927,0.9837904,0.008303838,0.0014435985,0.0006863608,0.0052827,0.00011255963,0.0000018983675,0.0003751091],"genre_scores_gemma":[0.0000017631587,0.97385377,0.022240976,0.00227826,0.0010277297,0.00005913633,0.00004726198,0.00002193266,0.0004691993],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.40352795,0.3804859,0.20941418,0.0023519553,0.0036534627,0.0005665526],"domain_scores_gemma":[0.05813893,0.68515235,0.24586117,0.008314542,0.002017722,0.00051531626],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8312176,0.0008469986,0.11593508,0.00056918664,0.000098691824,0.00016204937,0.006675322,0.00082902116,0.0006353009],"category_scores_gemma":[0.9588952,0.00032453125,0.017245574,0.00086649857,0.00029948514,0.00058990513,0.00034125854,0.0016632001,0.00023203739],"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":[0.000010613614,0.00007751115,0.00003924859,0.23747417,0.0005074605,0.0000022758898,0.000002273958,3.563714e-7,5.7105227e-9,0.0004740641,0.091480836,0.6699312],"study_design_scores_gemma":[0.00014590561,0.000410966,0.00012563742,0.26411524,0.0068826023,0.00019336231,0.000005128786,0.00007311473,1.9737996e-9,0.0025605552,0.7253218,0.00016567933],"about_ca_topic_score_codex":0.000003208042,"about_ca_topic_score_gemma":0.000011098595,"teacher_disagreement_score":0.6697655,"about_ca_system_score_codex":0.000046840676,"about_ca_system_score_gemma":0.00030881475,"threshold_uncertainty_score":0.99992067},"labels":[],"label_agreement":null},{"id":"W2125611358","doi":"10.1016/j.jclinepi.2008.02.002","title":"Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Manitoba Health; Institute for Clinical Evaluative Sciences; National Research Council Institute for Biodiagnostics; University of Manitoba","funders":"Canadian Institutes of Health Research; Johns Hopkins University","keywords":"Database; Osteoporosis; Medicine; Computer science; Data mining; Internal medicine","score_opus":0.7656525986732909,"score_gpt":0.6046937267204945,"score_spread":0.16095887195279646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125611358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98716587,0.0015327479,0.0013547327,0.008382282,0.0006161879,0.00039240156,0.00050384866,0.0000057588795,0.000046195262],"genre_scores_gemma":[0.95787126,0.0023522472,0.035390563,0.0030927185,0.0011407298,0.0000025328395,0.000099682904,0.000015681222,0.000034574296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9890202,0.005254726,0.004466704,0.00041216635,0.00039148427,0.00045469424],"domain_scores_gemma":[0.91737723,0.07607154,0.0037395044,0.0014308062,0.0005856812,0.00079521956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019262223,0.0001935933,0.002478007,0.000073738396,0.00019568861,0.000003316189,0.00047707694,0.00027642422,0.00013185474],"category_scores_gemma":[0.14733835,0.000106782056,0.00047067588,0.00013903478,0.00093837327,0.00015063467,0.00033047545,0.0017090273,0.0000030795907],"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":[0.0042787343,0.0010017859,0.9647171,0.00010442903,0.0003977786,0.0022717952,0.00020841864,0.000018029508,0.00077796966,0.000029050701,0.016808236,0.009386679],"study_design_scores_gemma":[0.006853617,0.00480105,0.94883245,0.00027355927,0.00057645456,0.016085718,0.0014189087,0.010110311,0.00073690165,0.0002681278,0.009846663,0.00019621784],"about_ca_topic_score_codex":0.0031637284,"about_ca_topic_score_gemma":0.0006772779,"teacher_disagreement_score":0.12807612,"about_ca_system_score_codex":0.00005260182,"about_ca_system_score_gemma":0.0016199066,"threshold_uncertainty_score":0.85984397},"labels":[],"label_agreement":null},{"id":"W2125703774","doi":"10.1016/j.jclinepi.2003.08.002","title":"Selection bias found in interpreting analyses with missing data for the prehospital index for trauma","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":51,"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; Montreal General Hospital","funders":"","keywords":"Index (typography); Missing data; Selection bias; Selection (genetic algorithm); Statistics; Medicine; Computer science; Mathematics; Artificial intelligence","score_opus":0.7710354620548242,"score_gpt":0.6536011011170065,"score_spread":0.11743436093781767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125703774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02722657,0.00010244783,0.9674597,0.0045745037,0.00030630876,0.00027929049,0.000014555406,0.0000058327946,0.000030790892],"genre_scores_gemma":[0.3255592,0.000016029593,0.67360795,0.00041782265,0.00037715904,0.000006991498,0.0000013081806,0.000010674158,0.0000028777747],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951038,0.0013495053,0.002905181,0.00025087665,0.00010700181,0.0002836412],"domain_scores_gemma":[0.77939,0.21777765,0.0021634216,0.00028044256,0.0002835471,0.00010494829],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027019687,0.00012893985,0.0013454834,0.00007125429,0.00007980418,0.000020234886,0.0004401234,0.0001819188,0.0000094524885],"category_scores_gemma":[0.37102437,0.00006681539,0.00021806697,0.0001491863,0.00021222286,0.00013420315,0.000049259444,0.00058438146,2.4354478e-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":[0.0046138484,0.00075406756,0.17094636,0.00036883928,0.0008207057,0.000015451376,0.0002751457,0.0015399923,0.000021929429,0.2141372,0.0019365528,0.6045699],"study_design_scores_gemma":[0.0018072232,0.0016898431,0.046064433,0.00040492418,0.00018743417,0.00006527273,0.00010530947,0.04812602,0.000010409525,0.9010721,0.0003723203,0.0000947302],"about_ca_topic_score_codex":0.000031661748,"about_ca_topic_score_gemma":0.00011180267,"teacher_disagreement_score":0.6869349,"about_ca_system_score_codex":0.00004005839,"about_ca_system_score_gemma":0.00022159089,"threshold_uncertainty_score":0.9364538},"labels":[],"label_agreement":null},{"id":"W2125791807","doi":"10.1016/j.jclinepi.2005.08.013","title":"New methods give better estimates of changes in diagnostic accuracy when prior information is provided","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Global Cancer Incidence and Screening","field":"Medicine","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":"Mammography; Test (biology); Medicine; Logistic regression; Receiver operating characteristic; Ultrasound; Medical physics; Breast cancer; Computer science; Radiology; Statistics; Cancer; Internal medicine","score_opus":0.3446635126790997,"score_gpt":0.5624593938272537,"score_spread":0.217795881148154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125791807","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":[0.6948167,0.002826286,0.18426022,0.11578098,0.0009534594,0.00055723824,0.0000076214446,0.00001712269,0.00078038825],"genre_scores_gemma":[0.26604477,0.00071772037,0.70861953,0.023273705,0.0012789237,0.000005471632,0.000007827127,0.000009776346,0.000042273874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941759,0.0010000682,0.004216104,0.00013063166,0.00020081189,0.00027645656],"domain_scores_gemma":[0.9230117,0.0720667,0.004086383,0.00021579817,0.0003927604,0.00022664457],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012689724,0.00013298505,0.001902617,0.00018223611,0.00001651382,0.000005364153,0.00017510424,0.0002867655,0.00017450782],"category_scores_gemma":[0.2416946,0.00009234942,0.0003210833,0.00013135768,0.00009827798,0.00034727514,0.000049935068,0.0006585033,0.00001005257],"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":[0.0006151224,0.000049679074,0.6781769,0.00007498853,0.000056762008,0.00002494405,0.00016926527,0.00008870412,0.00007345376,0.00024214099,0.029993119,0.29043493],"study_design_scores_gemma":[0.002479006,0.0015401561,0.92847955,0.00067352696,0.00017481885,0.00015097218,0.00007220008,0.00090891635,0.0006360453,0.044930335,0.019857906,0.00009655857],"about_ca_topic_score_codex":0.0008293584,"about_ca_topic_score_gemma":0.000090428075,"teacher_disagreement_score":0.52435935,"about_ca_system_score_codex":0.00005058022,"about_ca_system_score_gemma":0.0003688807,"threshold_uncertainty_score":0.76469296},"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":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2126152361","doi":"10.1016/j.jclinepi.2005.05.001","title":"Using cancer registry data for survival studies: the example of the Ontario Cancer Registry","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Head and Neck Cancer Studies","field":"Medicine","cited_by":179,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Cancer registry; Cancer; Medicine; Cancer survival; Oncology; Internal medicine","score_opus":0.7933969424367766,"score_gpt":0.6233322138512782,"score_spread":0.17006472858549837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126152361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83868605,0.03068625,0.00083634484,0.1233495,0.00555098,0.00041861017,0.000108819615,0.0000064515157,0.0003569867],"genre_scores_gemma":[0.8482635,0.059554454,0.021979237,0.037996307,0.025840873,0.000056755707,0.00001079552,0.000083398656,0.0062146983],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99446565,0.0011038303,0.0034602995,0.0003345453,0.0002580604,0.00037759304],"domain_scores_gemma":[0.9718409,0.021802284,0.0042574974,0.0012754845,0.00065694255,0.00016686512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016358467,0.00017853251,0.0027936513,0.00002521677,0.00016282084,0.0000028286977,0.0007652686,0.0002263876,0.00007259859],"category_scores_gemma":[0.044108685,0.00008167303,0.0005985239,0.000108250126,0.0008594172,0.00007948688,0.00032198348,0.0011137776,5.2943847e-7],"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":[0.0013117092,0.000165323,0.8388232,0.00017662239,0.0018264438,0.0000057379266,0.0005248038,0.00050231215,0.000056206612,0.0003188708,0.1404126,0.01587614],"study_design_scores_gemma":[0.0024035012,0.00040163618,0.3168571,0.000856045,0.00086057733,0.00007176642,0.0003745229,0.00052720774,0.000023199475,0.0006300728,0.67689157,0.0001027994],"about_ca_topic_score_codex":0.02542412,"about_ca_topic_score_gemma":0.09301617,"teacher_disagreement_score":0.536479,"about_ca_system_score_codex":0.00027637728,"about_ca_system_score_gemma":0.0022003867,"threshold_uncertainty_score":0.9810657},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2126309462","doi":"10.1016/j.jclinepi.2012.08.005","title":"When projecting required effectiveness of interventions for hospital readmission reduction, the percentage that is potentially avoidable must be considered","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Heart Failure Treatment and Management","field":"Medicine","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":"Ottawa Hospital; Carleton University; University of Ottawa","funders":"","keywords":"Psychological intervention; Medicine; Reduction (mathematics); Emergency medicine; Intensive care medicine; Nursing; Mathematics","score_opus":0.3355165877780357,"score_gpt":0.5060459066719434,"score_spread":0.17052931889390766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126309462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86437243,0.0013266368,0.022049556,0.10553656,0.003899066,0.0023458647,0.000011823454,0.000022431303,0.00043563667],"genre_scores_gemma":[0.97711563,0.0002877201,0.020091632,0.0007877838,0.00089935726,0.000029376117,0.000011146825,0.0000172013,0.0007601482],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99398345,0.0028123932,0.002471046,0.0001979801,0.0001796441,0.0003554703],"domain_scores_gemma":[0.9872188,0.009892797,0.0019974622,0.00028048217,0.00035087683,0.00025956993],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026571922,0.00015368397,0.0016060676,0.000110440415,0.00012123965,0.0000058056294,0.00012191756,0.00022087916,0.00017086037],"category_scores_gemma":[0.02458973,0.00008738449,0.00138405,0.00006430742,0.0002344929,0.0001977147,0.00007068872,0.00043106914,0.0000045141105],"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":[0.006868163,0.0057409843,0.71244,0.0027343049,0.004650122,0.000031609543,0.0023068106,0.000020446556,0.0025976251,0.0033165729,0.22744782,0.03184554],"study_design_scores_gemma":[0.01760494,0.015630977,0.81367934,0.006030622,0.0059471563,0.00085784926,0.0062226267,0.00018701826,0.003455988,0.010459125,0.11948482,0.00043955105],"about_ca_topic_score_codex":0.000046912402,"about_ca_topic_score_gemma":0.0000026529337,"teacher_disagreement_score":0.11274321,"about_ca_system_score_codex":0.000067776375,"about_ca_system_score_gemma":0.00017169926,"threshold_uncertainty_score":0.98362654},"labels":[],"label_agreement":null},{"id":"W2127084255","doi":"10.1016/s0895-4356(00)00345-0","title":"A comparison of patients' responses about their disability with and without attribution to their affected area","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","cited_by":20,"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 Work & Health; SickKids Foundation; Hospital for Sick Children","funders":"Medical Research Council; Arthritis Society","keywords":"Attribution; Affect (linguistics); Counterintuitive; Generalized estimating equation; Psychology; International Classification of Functioning, Disability and Health; Medicine; Physical therapy; Clinical psychology; Social psychology; Rehabilitation; Statistics; Mathematics","score_opus":0.22069919294959336,"score_gpt":0.4956690878103505,"score_spread":0.2749698948607572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127084255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891532,0.0002777249,0.004118302,0.00582548,0.0002708034,0.00029650377,0.0000121492385,0.0000096254635,0.0000361855],"genre_scores_gemma":[0.9967906,0.00020132924,0.0020398458,0.00072217884,0.00020604406,0.0000035084302,0.0000092793625,0.00000842742,0.000018775245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99263656,0.003875416,0.002892351,0.0002243237,0.00015765395,0.00021367082],"domain_scores_gemma":[0.96956223,0.027424864,0.0017848022,0.00024665147,0.0006236449,0.00035781585],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013589405,0.00014797878,0.0023573716,0.000080039084,0.000043641183,0.0000019444842,0.00006290879,0.00023893075,0.00003981223],"category_scores_gemma":[0.06687533,0.00007530958,0.00031310166,0.00019050777,0.00064618,0.00006835534,0.000028745804,0.00053309184,0.0000010540228],"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":[0.012870537,0.0012069469,0.90758437,0.000038921182,0.00012570643,0.0000019555862,0.00021245707,0.000020579313,0.00008325783,0.000031287615,0.00010369856,0.07772027],"study_design_scores_gemma":[0.001847501,0.008216071,0.98591197,0.00025514257,0.000103417864,0.00005573469,0.00017875286,0.00016975448,0.00009787368,0.00034348422,0.002748191,0.000072131974],"about_ca_topic_score_codex":0.000007499944,"about_ca_topic_score_gemma":0.000011018394,"teacher_disagreement_score":0.07832757,"about_ca_system_score_codex":0.00003033322,"about_ca_system_score_gemma":0.000106927175,"threshold_uncertainty_score":0.9409848},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"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":"W2128659393","doi":"10.1016/j.jclinepi.2008.12.011","title":"A pragmatic–explanatory continuum indicator summary (PRECIS): a tool to help trial designers","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":1398,"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; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; University of Toronto; Public Health Ontario","funders":"Medical Research Council; European Commission","keywords":"Clinical trial; Intervention (counseling); Research design; Medicine; Management science; Clinical study design; Outcome (game theory); Work (physics); Computer science; Nursing; Pathology; Mathematics; Engineering","score_opus":0.6123364426840952,"score_gpt":0.6530127906231212,"score_spread":0.04067634793902608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128659393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82122934,0.00093937264,0.007112515,0.16060391,0.003634984,0.0016767746,0.000013896478,0.00005270538,0.0047364696],"genre_scores_gemma":[0.7073911,0.0039271265,0.12380052,0.15008323,0.012022706,0.000036966117,0.0000137560355,0.000074828116,0.0026497806],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97685,0.008438193,0.011743811,0.00066053227,0.0013509742,0.00095649215],"domain_scores_gemma":[0.567142,0.42130205,0.0057404186,0.0013193587,0.0015930609,0.0029031117],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16869788,0.0002955026,0.004841938,0.00043035529,0.000077870565,0.000016499482,0.0008406078,0.0017845059,0.00034940377],"category_scores_gemma":[0.75775605,0.00020838933,0.001573039,0.00032851577,0.00057463907,0.00013088933,0.00014409423,0.007877238,0.000231195],"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":[0.29697308,0.004033454,0.09599841,0.00022374862,0.0010358721,0.001424806,0.00022247565,0.000021071091,0.00052907603,0.024516568,0.43668514,0.1383363],"study_design_scores_gemma":[0.13848215,0.08619488,0.2892422,0.0022631984,0.0007189625,0.0007174877,0.00022398563,0.00015639265,0.0001673205,0.36343443,0.11763955,0.0007594299],"about_ca_topic_score_codex":0.0000076808265,"about_ca_topic_score_gemma":0.00001939285,"teacher_disagreement_score":0.58905816,"about_ca_system_score_codex":0.00013851379,"about_ca_system_score_gemma":0.0028696156,"threshold_uncertainty_score":0.99951136},"labels":[],"label_agreement":null},{"id":"W2128912109","doi":"10.1016/s0895-4356(03)00148-3","title":"Cross-cultural evaluation of the Parkinson's Disease Questionnaire: tests of data quality, score reliability, response rate, and scaling assumptions in the United States, Canada, Japan, Italy, and Spain","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":61,"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":"Comparability; Reliability (semiconductor); Cross-cultural; Quality of life (healthcare); Medicine; Cross-cultural studies; Data quality; Clinical trial; Psychology; Gerontology; Social psychology; Nursing","score_opus":0.32328111919961644,"score_gpt":0.5257769818846278,"score_spread":0.2024958626850114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128912109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869323,0.0019088537,0.000073210664,0.010373527,0.00017822413,0.00037165981,0.0001532898,0.0000020758314,0.0000068865616],"genre_scores_gemma":[0.997348,0.00076600135,0.0005232139,0.0012410947,0.00004787738,0.0000059470512,0.00004975148,0.000006939669,0.000011165146],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95548135,0.040046334,0.0033658643,0.0003401024,0.00054061593,0.00022571467],"domain_scores_gemma":[0.9256507,0.06610206,0.0045817816,0.0013211457,0.0017397813,0.0006044925],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13542058,0.00014894507,0.001229492,0.00008516815,0.00008460997,0.00001038844,0.00023719136,0.0001295094,0.000013769866],"category_scores_gemma":[0.372895,0.00007482672,0.00017208775,0.00025189793,0.0006104402,0.0001522163,0.0000948145,0.00046741322,1.4386333e-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":[0.0019817986,0.00036507627,0.9940231,0.00007304198,0.000109605026,0.00001495619,0.000050880288,0.0006866235,0.000016176451,0.0004570785,0.0002707968,0.001950858],"study_design_scores_gemma":[0.0026560542,0.00023066072,0.98292565,0.0003694731,0.00056378107,0.00004687447,0.00014344808,0.004360002,0.0000043456494,0.0066750185,0.001962354,0.00006236015],"about_ca_topic_score_codex":0.014400435,"about_ca_topic_score_gemma":0.013574166,"teacher_disagreement_score":0.23747443,"about_ca_system_score_codex":0.000096237374,"about_ca_system_score_gemma":0.0015810938,"threshold_uncertainty_score":0.99216276},"labels":[],"label_agreement":null},{"id":"W2128984995","doi":"10.1016/j.jclinepi.2014.02.009","title":"After adjusting for bias in meta-analysis seasonal influenza vaccine remains effective in community-dwelling elderly","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Influenza Virus Research Studies","field":"Medicine","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":"University of Toronto","funders":"Medical Research Council; Rijksuniversiteit Groningen","keywords":"Meta-analysis; Seasonal influenza; Influenza vaccine; Medicine; Publication bias; Environmental health; Demography; Gerontology; Coronavirus disease 2019 (COVID-19); Virology; Vaccination; Internal medicine; Infectious disease (medical specialty); Sociology; Disease","score_opus":0.7696710465388428,"score_gpt":0.646111522817804,"score_spread":0.12355952372103873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128984995","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":[0.0029707619,0.9921782,0.0017030053,0.00084561756,0.00025245425,0.0019088683,0.000049726175,0.000011108625,0.000080260026],"genre_scores_gemma":[0.0011480718,0.98503697,0.007466319,0.0044568926,0.0013069179,0.00042412002,0.00002616074,0.00008127671,0.000053291275],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9271499,0.054239318,0.016252654,0.00066536595,0.0005441607,0.0011486312],"domain_scores_gemma":[0.5960809,0.39115232,0.009913149,0.0010261707,0.0012257913,0.00060167245],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.18478756,0.00083272415,0.042128436,0.0023373826,0.00011832952,0.00001460719,0.0007312486,0.0015948877,0.000102018654],"category_scores_gemma":[0.44360754,0.00050344947,0.01622693,0.0014898998,0.00032104016,0.00012440907,0.00035191062,0.010974948,0.000020995594],"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":[0.004495851,0.0010446687,0.1492363,0.030643616,0.25691858,0.00039475827,0.00020849936,0.0011474101,6.186986e-8,0.00014396224,0.00070899253,0.5550573],"study_design_scores_gemma":[0.005008238,0.0044209147,0.037147257,0.008690597,0.3193035,0.000131498,0.000058722508,0.00069031346,7.1924084e-8,0.0012134244,0.6228133,0.00052214664],"about_ca_topic_score_codex":0.00016510132,"about_ca_topic_score_gemma":0.0010411225,"teacher_disagreement_score":0.62210435,"about_ca_system_score_codex":0.00039712922,"about_ca_system_score_gemma":0.0008380073,"threshold_uncertainty_score":0.99974173},"labels":[],"label_agreement":null},{"id":"W2131441138","doi":"10.1016/j.jclinepi.2007.06.001","title":"The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Homewood Research Institute; University of Waterloo","funders":"Institute of Musculoskeletal Health and Arthritis; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"k-nearest neighbors algorithm; Rehabilitation; Machine learning; Computer science; Protocol (science); Algorithm; Artificial intelligence; Sample (material); Clinical decision support system; Health care; Data mining; Decision support system; Medicine; Physical therapy","score_opus":0.1480629574326228,"score_gpt":0.5683899836998431,"score_spread":0.4203270262672203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131441138","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00932709,0.00008157483,0.91349405,0.060301535,0.008322396,0.00829512,0.0000031227821,0.00006153255,0.00011360544],"genre_scores_gemma":[0.065921344,0.00014815654,0.91423273,0.005683956,0.012300027,0.0016157777,0.000005926055,0.000042559255,0.00004950054],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9650046,0.020813448,0.011747346,0.0007026986,0.00082709256,0.00090480247],"domain_scores_gemma":[0.88615835,0.10365403,0.0071746213,0.0010574586,0.0011773536,0.00077818084],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13255833,0.00025354853,0.0016717076,0.00014129223,0.0003049646,0.000062009974,0.0018363452,0.0004986582,0.000021084446],"category_scores_gemma":[0.09469109,0.00015039816,0.0010759378,0.0003009125,0.00060023955,0.00031770422,0.00041952624,0.004460775,0.000017132503],"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":[0.00015022619,0.000233016,0.4578557,0.00002191244,0.000041446678,0.000023739685,0.000020101848,0.00010014809,3.6163183e-7,0.0031929165,0.0032565685,0.53510386],"study_design_scores_gemma":[0.0014085606,0.0032193058,0.78592086,0.00008442691,0.000017213251,0.00007286373,0.000011479415,0.095362544,2.7188185e-7,0.014870478,0.09891462,0.00011738625],"about_ca_topic_score_codex":0.000021342436,"about_ca_topic_score_gemma":0.000018473484,"teacher_disagreement_score":0.53498644,"about_ca_system_score_codex":0.0001033123,"about_ca_system_score_gemma":0.00082401105,"threshold_uncertainty_score":0.997836},"labels":[],"label_agreement":null},{"id":"W2133980373","doi":"10.1016/j.jclinepi.2014.09.009","title":"Publishing journal's prestige does not influence critical appraisal","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Prestige; Publishing; Critical appraisal; Randomized controlled trial; Medical journal; New england; Alternative medicine; Medical research; Medicine; Evidence-based medicine; Psychology; Library science; Family medicine; Medical education; Political science; Computer science; Surgery; Law; Pathology","score_opus":0.9020800914386109,"score_gpt":0.6860893775787231,"score_spread":0.21599071385988777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133980373","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003915403,0.0011885327,0.059262864,0.9148388,0.019196924,0.00021576032,0.00002300103,0.000005469543,0.0013532699],"genre_scores_gemma":[0.011142543,0.00049218006,0.035313755,0.8969678,0.052689444,0.000006681204,0.0000070815,0.000058067573,0.0033224113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.35624894,0.44532046,0.18002354,0.0025930456,0.014010203,0.001803818],"domain_scores_gemma":[0.005506951,0.8427227,0.13265778,0.0053136204,0.012372827,0.00142611],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8433724,0.0009921348,0.040921945,0.0013061601,0.00028797702,0.0033394112,0.01258712,0.0042945165,0.0074532744],"category_scores_gemma":[0.99376833,0.00037795072,0.020001845,0.00075574213,0.0013626383,0.0021763055,0.0006063575,0.021728305,0.0018028275],"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":[0.000041864303,0.00005021393,0.059353095,0.00012001584,0.00067162554,0.00058031955,0.000030231533,0.00015914545,9.257685e-7,0.0011801397,0.9281465,0.009665925],"study_design_scores_gemma":[0.0003675244,0.0003794938,0.01746702,0.00037560664,0.00085228635,0.0021994994,0.000024846537,0.0007400899,3.144713e-7,0.080862604,0.89638114,0.00034959236],"about_ca_topic_score_codex":0.00001173907,"about_ca_topic_score_gemma":0.0000051139705,"teacher_disagreement_score":0.39740226,"about_ca_system_score_codex":0.00006559607,"about_ca_system_score_gemma":0.0010406651,"threshold_uncertainty_score":0.99986726},"labels":[],"label_agreement":null},{"id":"W2134076777","doi":"10.1016/j.jclinepi.2009.08.005","title":"A valid and reliable belief elicitation method for Bayesian priors","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":80,"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 of Toronto; Toronto General Hospital; University Health Network; Toronto Western Hospital; Hospital for Sick Children; Public Health Ontario","funders":"Canadian Institutes of Health Research","keywords":"Prior probability; Bayesian probability; Expert elicitation; Statistics; Computer science; Econometrics; Mathematics","score_opus":0.5853364478923457,"score_gpt":0.6222949697557054,"score_spread":0.036958521863359683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134076777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096276365,0.00048836274,0.822445,0.07867032,0.0012178881,0.00028592494,0.0000025088052,0.0000071477884,0.0006065065],"genre_scores_gemma":[0.22310011,0.0006096329,0.7577446,0.017189855,0.0009963679,0.000003860361,8.1645794e-7,0.0000067698916,0.00034798618],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856853,0.00556186,0.0072616693,0.00044229714,0.0007113589,0.00033753566],"domain_scores_gemma":[0.87421566,0.119271375,0.00450992,0.00042574268,0.001192671,0.00038462222],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2154536,0.00013575652,0.001906673,0.00016666942,0.00011212691,0.000034480454,0.0005043676,0.00027671867,0.00007204201],"category_scores_gemma":[0.3805293,0.00008129854,0.0006667847,0.0002097568,0.00013361144,0.00022240411,0.000033715616,0.0004813214,0.000010873747],"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":[0.0009934983,0.0004438891,0.12481695,0.00001524373,0.00008388076,0.0000052221308,0.0002200946,0.003069977,0.00024414275,0.018345347,0.061411683,0.7903501],"study_design_scores_gemma":[0.0011590153,0.0029435712,0.1722225,0.000044689863,0.000050430008,0.000024413643,0.00011814898,0.011771343,0.000027315478,0.72384447,0.087698765,0.000095334064],"about_ca_topic_score_codex":0.000006124475,"about_ca_topic_score_gemma":0.000004321033,"teacher_disagreement_score":0.7902548,"about_ca_system_score_codex":0.000024922547,"about_ca_system_score_gemma":0.00013426707,"threshold_uncertainty_score":0.8078556},"labels":[],"label_agreement":null},{"id":"W2134157683","doi":"10.1016/j.jclinepi.2005.12.020","title":"Recommendations for reporting randomized controlled trials of herbal interventions: explanation and elaboration","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Complementary and Alternative Medicine Studies","field":"Medicine","cited_by":216,"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 Work & Health; Children's Hospital of Eastern Ontario; University of Ottawa; Canadian College of Naturopathic Medicine; University of Toronto","funders":"University of Illinois at Urbana-Champaign","keywords":"Consolidated Standards of Reporting Trials; Medicine; Psychological intervention; Randomized controlled trial; Alternative medicine; Clinical trial; External validity; MEDLINE; Evidence-based medicine; Research design; Family medicine; Traditional medicine; Psychology; Nursing; Surgery; Pathology","score_opus":0.6442207726862046,"score_gpt":0.6345406036308929,"score_spread":0.00968016905531166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134157683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6112059,0.0065544834,0.31146345,0.066218294,0.0020816075,0.0020634443,0.000022794246,0.000008027997,0.000382042],"genre_scores_gemma":[0.9577528,0.0019734094,0.037385467,0.00050890615,0.0021026225,0.000051716677,0.000054599222,0.000005455071,0.00016500762],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.96863896,0.0062529016,0.024761057,0.00012576552,0.00011379239,0.00010749857],"domain_scores_gemma":[0.6949334,0.24335992,0.059975,0.00013343549,0.0014910966,0.00010714097],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16625208,0.00008844775,0.008316484,0.00015240822,0.00004299269,0.0000021951046,0.000033597134,0.000038291677,0.00007466158],"category_scores_gemma":[0.63261443,0.000049061713,0.0020144144,0.000052633884,0.00017677815,0.000064029395,0.000014319202,0.00019401086,1.3670001e-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":[0.40070406,0.0012732164,0.3951336,0.0005897549,0.007313171,0.000018128982,0.00016953505,0.00007626661,0.00030989942,0.05665203,0.032257132,0.1055032],"study_design_scores_gemma":[0.802145,0.0043677837,0.08203331,0.0018848093,0.0047631785,0.00011493498,0.0007426278,0.0024649198,0.00008040928,0.09453302,0.006759187,0.00011082933],"about_ca_topic_score_codex":0.000025045567,"about_ca_topic_score_gemma":0.000014933479,"teacher_disagreement_score":0.46636236,"about_ca_system_score_codex":0.000013668076,"about_ca_system_score_gemma":0.00006875621,"threshold_uncertainty_score":0.85851896},"labels":[],"label_agreement":null},{"id":"W2134792789","doi":"10.1016/j.jclinepi.2009.08.007","title":"A correspondence analysis revealed frailty deficits aggregate and are multidimensional","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Frailty in Older Adults","field":"Medicine","cited_by":84,"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; McGill University Health Centre; McGill University; Jewish General Hospital","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Aggregate (composite); Psychology; Gerontology; Econometrics; Medicine; Mathematics","score_opus":0.2137093045342694,"score_gpt":0.4861601679335605,"score_spread":0.2724508633992911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134792789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9563293,0.002303962,0.0039299014,0.03664471,0.00047066578,0.00013304404,0.0000070198353,0.000017058024,0.00016437593],"genre_scores_gemma":[0.94804275,0.0014321159,0.032289617,0.016654328,0.00059355114,8.57404e-7,0.000004872209,0.000010089119,0.000971844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99231553,0.0023485646,0.0042195558,0.0003925714,0.0003327118,0.00039109512],"domain_scores_gemma":[0.9711279,0.023534972,0.0036300588,0.0003853078,0.00060416234,0.0007175936],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013225029,0.00021748972,0.0037206125,0.00034965476,0.00005510928,0.000004427085,0.00016775532,0.00046310262,0.00017823666],"category_scores_gemma":[0.13520786,0.00015142957,0.0010307003,0.00044634103,0.0003243801,0.000100644866,0.000048687274,0.0013582436,0.00003317047],"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":[0.0026302293,0.00036442347,0.94655293,0.000022003624,0.00083795766,0.000636837,0.000041046795,0.00026488857,0.00017435206,0.00029059398,0.010294964,0.03788979],"study_design_scores_gemma":[0.0031623347,0.0019765547,0.9821426,0.000326792,0.0011882295,0.0010859176,0.000025245627,0.0040388275,0.000013732472,0.0022322312,0.0036799668,0.00012754342],"about_ca_topic_score_codex":0.00001253524,"about_ca_topic_score_gemma":0.00001997304,"teacher_disagreement_score":0.121982835,"about_ca_system_score_codex":0.000037332185,"about_ca_system_score_gemma":0.00019580693,"threshold_uncertainty_score":0.87207663},"labels":[],"label_agreement":null},{"id":"W2135345548","doi":"10.1016/j.jclinepi.2013.07.003","title":"A research and development agenda for systematic reviews that ask complex questions about complex interventions","year":2013,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Institute of Population and Public Health; Bruyère; University of Ottawa; Cochrane; Ottawa Hospital","funders":"National Institute for Health and Care Research","keywords":"Systematic review; Psychological intervention; Transparency (behavior); Process (computing); Management science; Lexicon; Ask price; Computer science; Psychology; Engineering ethics; Data science; MEDLINE; Political science; Artificial intelligence; Business","score_opus":0.9892156414640414,"score_gpt":0.7579128904741371,"score_spread":0.23130275098990427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135345548","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034863825,0.025186105,0.29550603,0.6655803,0.0029187542,0.009428846,0.00008288481,0.0000070703327,0.0009413703],"genre_scores_gemma":[0.0015481835,0.0071591856,0.410419,0.5242277,0.00854851,0.0016284102,0.0002200455,0.00011480838,0.046134204],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.4731297,0.3813081,0.1370767,0.0019477976,0.0053495867,0.0011881297],"domain_scores_gemma":[0.10352333,0.7525047,0.12691042,0.0052873353,0.010974662,0.00079957396],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8000267,0.00069688907,0.040965136,0.0014142283,0.00043851289,0.0005441216,0.0042597023,0.0013512282,0.007082516],"category_scores_gemma":[0.8039418,0.0003022842,0.012379764,0.0006373781,0.0008057091,0.00023188368,0.0005065252,0.0044656717,0.0028368977],"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":[0.000008928533,0.00008729568,0.0021897284,0.015275467,0.0009939224,0.000016530283,0.00005472914,0.000003162528,2.5913812e-7,0.0005878512,0.9758914,0.0048907273],"study_design_scores_gemma":[0.00034051898,0.0003875795,0.013833078,0.013185143,0.00057180435,0.00020852941,0.00011435072,0.00068439194,2.6801395e-8,0.018128438,0.9523109,0.00023519265],"about_ca_topic_score_codex":0.000013289887,"about_ca_topic_score_gemma":0.000037903465,"teacher_disagreement_score":0.37119657,"about_ca_system_score_codex":0.00011848198,"about_ca_system_score_gemma":0.00047794377,"threshold_uncertainty_score":0.9999452},"labels":[],"label_agreement":null},{"id":"W2135400982","doi":"10.1016/j.jclinepi.2010.07.015","title":"GRADE guidelines: 3. Rating the quality of evidence","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8174,"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":"Observational study; Quality (philosophy); Context (archaeology); Confidence interval; Quality of evidence; Publication bias; Medicine; Randomized controlled trial; Evidence-based medicine; Quality Score; Alternative medicine; Operations management; Internal medicine; Pathology; Engineering","score_opus":0.996826406101092,"score_gpt":0.8027858482902067,"score_spread":0.19404055781088525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135400982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6312381,0.009436347,0.29372662,0.057742234,0.0036022556,0.00047942667,0.0000037804912,0.0000029436212,0.003768268],"genre_scores_gemma":[0.88090485,0.0008572177,0.1100406,0.006457207,0.0008372251,0.000002538342,1.2817647e-7,0.0000062595004,0.00089395273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2887075,0.44574368,0.25671637,0.0012058606,0.0070127235,0.00061386847],"domain_scores_gemma":[0.052306406,0.77907735,0.15509364,0.0044245436,0.008701126,0.00039692884],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9019372,0.00019308159,0.013280261,0.00014392618,0.00007005499,0.000028592533,0.0035641438,0.00021434491,0.003132439],"category_scores_gemma":[0.97683704,0.000054970955,0.0073719304,0.000583583,0.0004533275,0.0002320742,0.00018463378,0.00073793845,0.00026425582],"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":[0.000064782645,0.00007983215,0.82674986,0.000024512086,0.0002726901,0.0000035831858,0.00021518096,0.00008501068,0.000026463436,0.01115234,0.0936516,0.06767415],"study_design_scores_gemma":[0.00025880948,0.00036173523,0.7902337,0.00021425332,0.00026323483,0.000055065775,0.000665966,0.0017574016,0.000015146009,0.17943406,0.026639557,0.00010107216],"about_ca_topic_score_codex":0.000041552885,"about_ca_topic_score_gemma":0.00002334732,"teacher_disagreement_score":0.33333367,"about_ca_system_score_codex":0.000008344811,"about_ca_system_score_gemma":0.00020565101,"threshold_uncertainty_score":0.99777883},"labels":[],"label_agreement":null},{"id":"W2135760566","doi":"10.1016/j.jclinepi.2014.12.014","title":"The number of subjects per variable required in linear regression analyses","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1043,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Statistics; Linear regression; Confidence interval; Mathematics; Regression analysis; Regression dilution; Standard error; Regression; Population; Segmented regression; Statistic; Linear model; Proper linear model; Standard deviation; Polynomial regression; Medicine","score_opus":0.6415066932237838,"score_gpt":0.6428740076196767,"score_spread":0.0013673143958928824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135760566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12801796,0.0004554573,0.8615987,0.0037557422,0.001965586,0.000117079515,0.00000561056,0.000008339763,0.0040755775],"genre_scores_gemma":[0.08733977,0.00030947715,0.9114112,0.00034015867,0.0004566621,0.0000014569107,3.3281532e-7,0.000010500979,0.00013043136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98571014,0.008753437,0.004832412,0.00016415805,0.00024383746,0.00029601227],"domain_scores_gemma":[0.837486,0.15828377,0.0031120826,0.00031914067,0.0005433549,0.00025562753],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04954595,0.00012184605,0.0020257859,0.000050776165,0.000031666084,0.0000045487286,0.0003435565,0.0002899169,0.00009483183],"category_scores_gemma":[0.49677497,0.000058739988,0.00029737534,0.00017878701,0.00036376622,0.0000682057,0.00007662733,0.00076123205,0.000011055688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013279576,0.00042259018,0.3212742,0.00006744874,0.00015619812,0.000045511377,0.00010897286,0.000029224488,0.00008212155,0.6353695,0.015238333,0.025877943],"study_design_scores_gemma":[0.00083595247,0.00032719807,0.020971462,0.00019323638,0.00006063806,0.000056877336,0.0000821918,0.0016570584,0.00002560003,0.97411805,0.001606188,0.000065522014],"about_ca_topic_score_codex":0.00003743033,"about_ca_topic_score_gemma":0.0000074051527,"teacher_disagreement_score":0.44722903,"about_ca_system_score_codex":0.000024330862,"about_ca_system_score_gemma":0.00032446484,"threshold_uncertainty_score":0.9786925},"labels":[],"label_agreement":null},{"id":"W2136008482","doi":"10.1016/j.jclinepi.2014.04.003","title":"Network meta-analyses could be improved by searching more sources and by involving a librarian","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":189,"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; University of Ottawa","funders":"","keywords":"MEDLINE; Medicine; Systematic review; Interquartile range; Electronic database; Meta-analysis; Information retrieval; Family medicine; Computer science; Surgery; Pathology","score_opus":0.9479113934976748,"score_gpt":0.6806661473237743,"score_spread":0.26724524617390055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136008482","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":[0.43920738,0.08371518,0.30362102,0.16905415,0.0017462468,0.00074849674,0.00004802587,0.000015019646,0.0018444676],"genre_scores_gemma":[0.83068687,0.0018159442,0.09057296,0.06798482,0.002701212,0.000014931383,0.000013008245,0.000051963598,0.00615831],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77041656,0.17382306,0.05100074,0.0012880492,0.0027273546,0.00074425666],"domain_scores_gemma":[0.40971333,0.5250614,0.059327308,0.0030301032,0.0014629689,0.0014048782],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.64527726,0.00041273388,0.021618994,0.00022673332,0.00021886158,0.0003916574,0.0021605846,0.0004242383,0.0020550783],"category_scores_gemma":[0.7006461,0.00016750461,0.007296635,0.0005923387,0.0004598827,0.00044324607,0.00032642393,0.0014015323,0.00005038837],"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":[0.00005249255,0.0000727928,0.14377856,0.000026204762,0.0060882573,0.0000036266256,0.00010479671,0.00063892,0.00019468089,0.0014285379,0.83218026,0.015430874],"study_design_scores_gemma":[0.0008344543,0.00076516956,0.023319906,0.000049544495,0.009278481,0.00008246087,0.00042505327,0.104724325,0.000007687469,0.099475235,0.76065075,0.0003869442],"about_ca_topic_score_codex":0.000039361777,"about_ca_topic_score_gemma":0.00001338549,"teacher_disagreement_score":0.39147946,"about_ca_system_score_codex":0.000010135776,"about_ca_system_score_gemma":0.00010525536,"threshold_uncertainty_score":0.9988572},"labels":[],"label_agreement":null},{"id":"W2136186850","doi":"10.1016/j.jclinepi.2008.01.007","title":"The Completeness of Reporting (CORE) index identifies important deficiencies in observational study conference abstracts","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; McMaster University","funders":"Canadian Institutes of Health Research; McMaster University","keywords":"Observational study; Completeness (order theory); Index (typography); Medicine; Computer science; Mathematics; Internal medicine; World Wide Web","score_opus":0.9854991479547747,"score_gpt":0.7067084340231099,"score_spread":0.27879071393166477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136186850","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":[0.9931894,0.0006897016,0.0030144146,0.0018213993,0.0007913692,0.00025782755,0.0000018494396,8.957033e-7,0.00023316435],"genre_scores_gemma":[0.99746424,0.00028772771,0.001569529,0.0003077635,0.00013972113,0.00000397652,5.3193185e-7,0.0000040119753,0.00022249666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5500926,0.08722387,0.35187107,0.0014676024,0.008484873,0.0008600091],"domain_scores_gemma":[0.15495299,0.4817864,0.35120988,0.0032937527,0.0084012505,0.00035574392],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7299914,0.00019154312,0.009950874,0.00023534198,0.00017774983,0.000060313632,0.0019627027,0.00014714264,0.0002952673],"category_scores_gemma":[0.88848484,0.000074408475,0.0024689757,0.00070445036,0.00061392365,0.00020599873,0.00016028107,0.00070393796,0.000026208929],"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":[0.000039419534,0.00021305826,0.99336815,0.0000082447,0.000112576876,0.00006795506,0.00019935127,0.001453521,0.000013564393,0.0015207084,0.0020085957,0.000994874],"study_design_scores_gemma":[0.00026704802,0.00018805277,0.9591021,0.000038831793,0.000047103054,0.00016294702,0.0015437506,0.0038362073,0.0000012178674,0.033691686,0.0010587628,0.00006227119],"about_ca_topic_score_codex":0.000084131076,"about_ca_topic_score_gemma":0.0004445872,"teacher_disagreement_score":0.39513958,"about_ca_system_score_codex":0.000017077808,"about_ca_system_score_gemma":0.0005731891,"threshold_uncertainty_score":0.68022186},"labels":[],"label_agreement":null},{"id":"W2136403658","doi":"10.1016/j.jclinepi.2010.09.011","title":"GRADE guidelines: A new series of articles in the Journal of Clinical Epidemiology","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3125,"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; McMaster University","funders":"","keywords":"Grading (engineering); Quality of evidence; Epidemiology; Systematic review; Clinical epidemiology; Evidence-based medicine; MEDLINE; Medicine; Evidence-based practice; Health care; Alternative medicine; Medical education; Family medicine; Data science; Computer science; Meta-analysis; Pathology; Political science","score_opus":0.9020459756302964,"score_gpt":0.6674652016856231,"score_spread":0.23458077394467336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136403658","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":[0.6972991,0.0034373293,0.009859738,0.28418466,0.0048139114,0.00019711141,0.000018890398,0.000003799605,0.00018544687],"genre_scores_gemma":[0.7859796,0.007769562,0.120978974,0.075151816,0.009936086,0.0000039657325,0.000002818929,0.00003620493,0.00014095865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8383479,0.038481265,0.12132715,0.0006005167,0.0002587546,0.0009844179],"domain_scores_gemma":[0.43087816,0.44986525,0.11526327,0.0014884819,0.0013330816,0.0011717409],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.60603845,0.00024599128,0.00922923,0.00046512223,0.000059923426,0.000008306235,0.0013131913,0.0009055699,0.000305578],"category_scores_gemma":[0.79764175,0.00018167117,0.0015686654,0.00027314556,0.00085406034,0.00047759668,0.000088537534,0.002917089,0.000091020614],"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":[0.00034048964,0.0003014068,0.8341724,0.000063096515,0.00016351057,0.000006857101,0.0004072048,0.00041327346,0.000002883969,0.066739194,0.09461894,0.0027706868],"study_design_scores_gemma":[0.0022400355,0.0013813484,0.6078749,0.00012476325,0.00004011501,0.0004056447,0.0007230027,0.0011739928,0.0000014677696,0.30684882,0.07903896,0.0001469946],"about_ca_topic_score_codex":0.00050531025,"about_ca_topic_score_gemma":0.0005214313,"teacher_disagreement_score":0.411384,"about_ca_system_score_codex":0.00005018488,"about_ca_system_score_gemma":0.0011807038,"threshold_uncertainty_score":0.9993832},"labels":[],"label_agreement":null},{"id":"W2136683961","doi":"10.1016/j.jclinepi.2004.10.017","title":"Cumulative Illness Rating Scale was a reliable and valid index in a family practice context","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":220,"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 Sherbrooke","funders":"Université de Sherbrooke","keywords":"Intra-rater reliability; Inter-rater reliability; Intraclass correlation; Context (archaeology); Rating scale; Physical therapy; Medicine; Reliability (semiconductor); Psychology; Psychometrics; Clinical psychology; Developmental psychology","score_opus":0.2598121052201004,"score_gpt":0.5343948304251304,"score_spread":0.27458272520502996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136683961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9387876,0.0029545454,0.0017081094,0.04337377,0.00045410224,0.0003011631,0.0000013537862,0.000014751744,0.012404604],"genre_scores_gemma":[0.97451496,0.001944485,0.006697865,0.015620755,0.000891537,0.00000450014,0.0000016587453,0.000014412411,0.00030979738],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939435,0.0016267442,0.003576279,0.00028495988,0.00022263183,0.00034586774],"domain_scores_gemma":[0.9769023,0.019998629,0.0022737987,0.00021875881,0.00028876727,0.00031772864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018644743,0.00016220335,0.0019497556,0.0001546825,0.00004281286,0.000011383115,0.00012080305,0.00023586806,0.00007214394],"category_scores_gemma":[0.052539453,0.000121697325,0.00026441293,0.00015660052,0.0003289007,0.0003958037,0.00009444193,0.0011050111,0.000014697671],"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":[0.0066946205,0.0015038219,0.8448727,0.00028407885,0.0005740145,0.00056883565,0.0009545889,0.00449355,0.000024337152,0.007894145,0.023333026,0.10880227],"study_design_scores_gemma":[0.014050846,0.0017319553,0.7997806,0.00091483427,0.00047408332,0.00042481706,0.008077536,0.022992916,0.0000061483297,0.0075923074,0.14368568,0.00026828377],"about_ca_topic_score_codex":0.00014466213,"about_ca_topic_score_gemma":0.00006234196,"teacher_disagreement_score":0.12035266,"about_ca_system_score_codex":0.00009908444,"about_ca_system_score_gemma":0.00037686678,"threshold_uncertainty_score":0.9554414},"labels":[],"label_agreement":null},{"id":"W2137250593","doi":"10.1016/j.jclinepi.2012.09.007","title":"Prioritization of systematic reviews leads prioritization of research gaps and needs","year":2012,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; University of Ottawa; Ottawa Hospital","funders":"","keywords":"Scopus; Prioritization; Systematic review; Consistency (knowledge bases); Computer science; MEDLINE; Medicine; Management science; Data science; Information retrieval; Library science; Knowledge management; Political science; Engineering; Artificial intelligence","score_opus":0.9544736106130939,"score_gpt":0.7092613274203688,"score_spread":0.24521228319272503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137250593","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019123022,0.36620015,0.09363715,0.49609646,0.010287193,0.009949248,0.00007490329,0.000008186507,0.004623653],"genre_scores_gemma":[0.12020209,0.26893267,0.124514356,0.3766259,0.058600027,0.0002778744,0.00019760427,0.00038748403,0.050261997],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.3006159,0.51755124,0.17085485,0.0011477629,0.008942928,0.0008873096],"domain_scores_gemma":[0.25323975,0.5449611,0.18263501,0.004802136,0.01389112,0.00047087335],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8382911,0.00048676223,0.041343655,0.0021485419,0.00007910261,0.000082589606,0.0026640566,0.0019475635,0.00104437],"category_scores_gemma":[0.899132,0.00022295193,0.0065798247,0.002118697,0.0008253781,0.0003279373,0.00026459183,0.0037035411,0.0002259111],"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":[0.000023671468,0.000074699376,0.073324084,0.036638815,0.00043664116,0.00000903929,0.00014231655,0.000009542233,0.0000072320177,0.0015314793,0.88500106,0.00280141],"study_design_scores_gemma":[0.0007098505,0.0010562165,0.01564335,0.029175134,0.0029239843,0.00033892755,0.00024984308,0.0007985124,0.0000039899824,0.031930447,0.91678107,0.0003886783],"about_ca_topic_score_codex":0.000007070665,"about_ca_topic_score_gemma":0.000002100382,"teacher_disagreement_score":0.119470574,"about_ca_system_score_codex":0.000050714887,"about_ca_system_score_gemma":0.00038321764,"threshold_uncertainty_score":0.9998688},"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":"W2138291707","doi":"10.1016/j.jclinepi.2007.08.006","title":"Author reply: the master-question: meta-analyses and stopped-early randomized trials—a problem?","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","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":"Institute of Nutrition, Metabolism and Diabetes; McMaster University","funders":"","keywords":"Meta-analysis; Randomized controlled trial; Medicine; Psychology; Internal medicine","score_opus":0.7028823135206211,"score_gpt":0.6068440409772692,"score_spread":0.09603827254335195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138291707","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.326956,0.022130614,0.052592244,0.58737856,0.0021270872,0.0017969027,0.0000039821925,0.00005009111,0.006964535],"genre_scores_gemma":[0.8375246,0.0046191304,0.06859322,0.06293331,0.00735965,0.00003461123,0.0000054528737,0.0000654613,0.018864553],"study_design_codex":"randomized_trial","study_design_gemma":"not_applicable","domain_scores_codex":[0.9469936,0.03865415,0.012993496,0.00037978266,0.0005054228,0.00047353315],"domain_scores_gemma":[0.44751924,0.5429012,0.0075507234,0.0005947783,0.0006089624,0.0008251035],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38542518,0.0002606712,0.017273009,0.00016018386,0.00007713934,0.000016746324,0.00017214361,0.00039542874,0.00025440654],"category_scores_gemma":[0.39521745,0.00010216334,0.00923165,0.00016002693,0.0006853856,0.00008166058,0.00004589283,0.0012581617,0.000012998692],"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":[0.40332735,0.0006771431,0.3662183,0.00014584347,0.061344106,0.002022473,0.0003132037,0.00006456413,0.000092533744,0.090254076,0.014345773,0.061194632],"study_design_scores_gemma":[0.1495783,0.0028411578,0.34503242,0.00013828238,0.08015524,0.0053183655,0.00016854121,0.00013035198,0.000032453245,0.029865682,0.38637716,0.00036204822],"about_ca_topic_score_codex":0.000055561133,"about_ca_topic_score_gemma":0.000004936214,"teacher_disagreement_score":0.52444524,"about_ca_system_score_codex":0.000026709768,"about_ca_system_score_gemma":0.00018593628,"threshold_uncertainty_score":0.9973166},"labels":[],"label_agreement":null},{"id":"W2138520847","doi":"10.1016/j.jclinepi.2012.10.015","title":"Clinical experience may affect clinician compliance with assigned treatment in randomized trials","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medication Adherence and Compliance","field":"Medicine","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":"McMaster University","funders":"","keywords":"Randomized controlled trial; Medicine; Clinical trial; Physical therapy; Protocol (science); Affect (linguistics); Surgery; Alternative medicine; Psychology; Internal medicine","score_opus":0.6653388159302364,"score_gpt":0.6244852421835998,"score_spread":0.04085357374663656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138520847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94647247,0.0013580504,0.013668088,0.031760022,0.0018013349,0.0022769955,0.0000016650114,0.000024607049,0.0026367889],"genre_scores_gemma":[0.9521816,0.004575442,0.026903432,0.012920765,0.0016050279,0.00020434603,0.000004124739,0.000020436508,0.0015848414],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95669335,0.026749456,0.015161575,0.00053747115,0.00035031023,0.0005078586],"domain_scores_gemma":[0.64638984,0.33248428,0.017272996,0.0012103479,0.00097400544,0.0016685647],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.087832,0.00030646415,0.013289592,0.00015559819,0.000040153343,0.000010616503,0.00035785942,0.0005035624,0.0019196492],"category_scores_gemma":[0.25596783,0.00015680298,0.0020765404,0.00023841635,0.0012882157,0.00015585852,0.000031597217,0.0011679782,0.0005826729],"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":[0.050129507,0.0011635509,0.85049444,0.000029499723,0.00042900976,0.00010444522,0.000063335574,0.000011872186,0.000011189183,0.00042335765,0.006119751,0.09102002],"study_design_scores_gemma":[0.20557186,0.0067651756,0.7735566,0.0010828226,0.00035247774,0.00023284266,0.00019545999,0.0015759455,0.000011630274,0.0032819472,0.0071751364,0.00019808552],"about_ca_topic_score_codex":0.00010968158,"about_ca_topic_score_gemma":0.000013379587,"teacher_disagreement_score":0.3103035,"about_ca_system_score_codex":0.000069996786,"about_ca_system_score_gemma":0.00090432,"threshold_uncertainty_score":0.99899274},"labels":[],"label_agreement":null},{"id":"W2141080664","doi":"10.1016/j.jclinepi.2009.01.011","title":"What kind of randomized trials do we need?","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":52,"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","funders":"","keywords":"Randomized controlled trial; Medicine; MEDLINE; Political science; Surgery","score_opus":0.33140266198136764,"score_gpt":0.5437044603126209,"score_spread":0.21230179833125323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141080664","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":[0.4567786,0.055298652,0.0029601632,0.47193286,0.006165451,0.0009959743,0.0000020650361,0.000022438016,0.005843821],"genre_scores_gemma":[0.81948286,0.14232089,0.009438796,0.022602148,0.004702946,0.000003115724,0.0000023492976,0.000020109293,0.0014267908],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.96367943,0.02191439,0.013457245,0.00022381931,0.00038758744,0.00033751276],"domain_scores_gemma":[0.6150181,0.3754516,0.007998408,0.00039543284,0.00050337473,0.0006330604],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.17048612,0.00019944948,0.022576455,0.00019811063,0.000018893872,0.000009144741,0.00017672368,0.00056739675,0.00033217247],"category_scores_gemma":[0.45577365,0.000105598985,0.010096198,0.00013816517,0.00043817286,0.00014018276,0.000017150995,0.00090670097,0.000016793934],"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":[0.43679994,0.0011034752,0.09656179,0.000096760414,0.0032052628,0.0007753252,0.00019448172,0.000083611696,0.00011732442,0.06144921,0.013449131,0.38616368],"study_design_scores_gemma":[0.42840672,0.0051529757,0.18856215,0.0015573684,0.00467245,0.0022487296,0.00032475078,0.0001416243,0.000079483645,0.066393256,0.30214342,0.0003170623],"about_ca_topic_score_codex":0.0000032279008,"about_ca_topic_score_gemma":1.8961772e-7,"teacher_disagreement_score":0.44933072,"about_ca_system_score_codex":0.000017133098,"about_ca_system_score_gemma":0.00022693726,"threshold_uncertainty_score":0.99981743},"labels":[],"label_agreement":null},{"id":"W2142460408","doi":"10.1016/j.jclinepi.2004.08.010","title":"Seven items were identified for inclusion when reporting a Bayesian analysis of a clinical study","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University Health Network; Institute for Work & Health; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Set (abstract data type); Variance (accounting); Statistics; Psychology; Computer science; Mathematics","score_opus":0.9635245563009668,"score_gpt":0.7652974136164435,"score_spread":0.19822714268452324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142460408","genre_codex":"review","genre_gemma":"review","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011184688,0.92583036,0.06517086,0.001068228,0.0036217747,0.0028321806,0.00007202997,0.0000046674895,0.00028139603],"genre_scores_gemma":[0.0016762872,0.9516966,0.03845693,0.000727208,0.0042000306,0.00006305094,0.000042627365,0.000061131395,0.003076183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.16121253,0.34153074,0.4862732,0.003281486,0.0068194,0.0008826284],"domain_scores_gemma":[0.073519245,0.44869864,0.46652326,0.005563801,0.0048739407,0.0008211049],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.927549,0.0010152187,0.15786757,0.0028262716,0.0002698572,0.00016383255,0.0066189943,0.001984437,0.0030179366],"category_scores_gemma":[0.95500493,0.00044555162,0.091987975,0.0033762143,0.00034059503,0.0002725652,0.0017602266,0.0029615813,0.00011612641],"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":[0.0000770156,0.0008166213,0.06429248,0.000945681,0.025481788,0.00004642482,0.00015220763,0.00011906203,9.477143e-9,0.000106628926,0.03377319,0.8741889],"study_design_scores_gemma":[0.00066433835,0.000931702,0.0064782095,0.0020329321,0.07264689,0.00008019715,0.00019785113,0.004250574,2.7701783e-9,0.005582443,0.9068063,0.00032856673],"about_ca_topic_score_codex":0.00002608394,"about_ca_topic_score_gemma":0.00019947486,"teacher_disagreement_score":0.8738603,"about_ca_system_score_codex":0.00007923062,"about_ca_system_score_gemma":0.0015908187,"threshold_uncertainty_score":0.9997996},"labels":[],"label_agreement":null},{"id":"W2142522698","doi":"10.1016/j.jclinepi.2015.11.003","title":"Modified intention-to-treat analysis did not bias trial results","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","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":"McMaster University; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Statistics; Psychology; Mathematics","score_opus":0.7040360130875892,"score_gpt":0.6124404423782148,"score_spread":0.09159557070937441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142522698","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":[0.00090390944,0.99040127,0.00064059993,0.0043445695,0.0018080677,0.00092505204,0.00015406155,0.000019399555,0.00080305326],"genre_scores_gemma":[0.00031098872,0.9938388,0.0016021985,0.000840395,0.0022311972,0.000024273188,0.00019365558,0.000042449057,0.000916069],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9684013,0.014330197,0.0152011635,0.0006480159,0.0007365992,0.00068269396],"domain_scores_gemma":[0.9350455,0.05176938,0.008610872,0.0009752483,0.0014438377,0.0021552031],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.074396044,0.00049762864,0.02136622,0.0014245935,0.000059530226,0.000023187547,0.00062112516,0.0011856391,0.00013095219],"category_scores_gemma":[0.34175828,0.00028749442,0.009005713,0.0009892966,0.00040287356,0.000086070315,0.0001680736,0.0030516814,0.00022640273],"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":[0.053129118,0.00048068623,0.00028120118,0.0006547086,0.0059422874,0.00026681332,0.000017381923,0.000013180535,2.754464e-8,0.00021989497,0.02416171,0.914833],"study_design_scores_gemma":[0.031898998,0.0066723847,0.00025932243,0.0052476116,0.0025441046,0.00033873628,0.000010090601,0.000045500034,4.2954536e-8,0.00068134686,0.9520902,0.000211681],"about_ca_topic_score_codex":0.000087700006,"about_ca_topic_score_gemma":0.000029870323,"teacher_disagreement_score":0.92792845,"about_ca_system_score_codex":0.00014275048,"about_ca_system_score_gemma":0.001786188,"threshold_uncertainty_score":0.99995774},"labels":[],"label_agreement":null},{"id":"W2142651097","doi":"10.1016/j.jclinepi.2006.01.013","title":"Patients undergoing knee surgery provided accurate ratings of preoperative quality of life and function 2 weeks after surgery","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","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":"McMaster University; Hamilton Health Sciences; Western University","funders":"","keywords":"Medicine; Quality of life (healthcare); SF-36; Surgery; Physical therapy; Randomized controlled trial; Minimal clinically important difference; Health related quality of life; Disease; Internal medicine","score_opus":0.1458339327663969,"score_gpt":0.4187143591656787,"score_spread":0.2728804263992818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142651097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948736,0.0005567181,0.0008454101,0.0025545703,0.0008877988,0.00020274123,0.000008173039,0.000008393746,0.00006261178],"genre_scores_gemma":[0.99669373,0.00017916043,0.0011697103,0.0014435936,0.00041028563,0.0000036571362,0.000007379586,0.000016114385,0.000076375516],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9878152,0.0036070098,0.0077796676,0.00024894904,0.00027595452,0.0002731937],"domain_scores_gemma":[0.8962116,0.09591633,0.0066759577,0.0002174141,0.00072758674,0.00025109277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015661122,0.00019035819,0.0038663882,0.00019349926,0.000029879699,0.0000037788905,0.00004610844,0.000304286,0.000067029105],"category_scores_gemma":[0.17373474,0.0001331305,0.000853047,0.00013669272,0.0003873501,0.00024823713,0.000057989237,0.00055196404,0.0000029392002],"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":[0.005306279,0.00041983195,0.98825073,0.00033503395,0.00023467078,0.0000066528414,0.000033259104,0.000040220726,0.000057423313,0.00014742854,0.0025264898,0.0026419994],"study_design_scores_gemma":[0.0024495348,0.0012777311,0.99460244,0.00032441624,0.00011464362,0.000015976431,0.000053251904,0.000056522116,0.000043451175,0.00080384826,0.00015768404,0.00010049502],"about_ca_topic_score_codex":0.00009704164,"about_ca_topic_score_gemma":0.00007742251,"teacher_disagreement_score":0.15807362,"about_ca_system_score_codex":0.000026673095,"about_ca_system_score_gemma":0.00071839255,"threshold_uncertainty_score":0.83322525},"labels":[],"label_agreement":null},{"id":"W2143066175","doi":"10.1016/s0895-4356(99)00122-5","title":"Ready, set, stop Reflections on assessing quality of life and the WHOQOL-100 (U.S. version)","year":2000,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Quality of life (healthcare); Gerontology; Commercialization; Quality (philosophy); Medicine; Marketing; Nursing; Business","score_opus":0.8650506703310162,"score_gpt":0.6490095600163145,"score_spread":0.21604111031470175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143066175","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":[0.02106635,0.0034125198,0.0010522931,0.9611792,0.0033703246,0.00035398323,0.00024017411,0.000012470183,0.0093126595],"genre_scores_gemma":[0.010519893,0.0068768165,0.0028108351,0.96883434,0.009936351,0.000012416168,0.00004939771,0.00004811235,0.00091185584],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93656945,0.027274976,0.03461929,0.0007406909,0.00021573062,0.0005798438],"domain_scores_gemma":[0.76459175,0.19378611,0.040143758,0.00089336914,0.00026608535,0.00031893188],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.25557753,0.00035598635,0.009339062,0.00053498417,0.00024151852,0.000039376973,0.00067389745,0.0018420183,0.0007684148],"category_scores_gemma":[0.27524075,0.00028678286,0.001276412,0.00018239893,0.0010474937,0.00031582656,0.00008078143,0.0048471084,0.0004349889],"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":[0.0003959717,0.00007988387,0.015442991,0.0003109204,0.00043249817,0.0000045073652,0.00017352113,0.00016623287,4.0344617e-8,0.023088196,0.9594152,0.00049002416],"study_design_scores_gemma":[0.0026595998,0.00039841078,0.045900792,0.00024328002,0.000050994506,0.000031095577,0.00016062843,0.00025202555,3.743928e-8,0.04983595,0.9002128,0.00025434824],"about_ca_topic_score_codex":0.00092971046,"about_ca_topic_score_gemma":0.000031663454,"teacher_disagreement_score":0.17197773,"about_ca_system_score_codex":0.00024526313,"about_ca_system_score_gemma":0.00079790753,"threshold_uncertainty_score":0.99995846},"labels":[],"label_agreement":null},{"id":"W2143517695","doi":"10.1016/j.jclinepi.2004.04.003","title":"Automated variable selection methods for logistic regression produced unstable models for predicting acute myocardial infarction mortality","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":342,"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; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Logistic regression; Stepwise regression; Feature selection; Statistics; Selection (genetic algorithm); Variables; Regression analysis; Myocardial infarction; Medicine; Model selection; Linear regression; Mathematics; Internal medicine; Computer science; Artificial intelligence","score_opus":0.5592846650599506,"score_gpt":0.6167847183683072,"score_spread":0.05750005330835661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143517695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20174326,0.0003173949,0.78729284,0.007079962,0.0022467605,0.0011378274,0.000016927028,0.00010218184,0.00006284674],"genre_scores_gemma":[0.3780546,0.0003753171,0.6182508,0.0016025532,0.0014980274,0.00012361749,0.000041528292,0.000026961792,0.000026625443],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940986,0.0014857375,0.0034305183,0.00041545805,0.00014645136,0.0004232427],"domain_scores_gemma":[0.97991365,0.01598397,0.0026484078,0.00024279121,0.000910396,0.000300793],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024010364,0.00020992075,0.0024077254,0.0001232056,0.00014306058,0.000008633955,0.00009228836,0.0004976219,0.0000096132835],"category_scores_gemma":[0.06548327,0.0001380658,0.00086110155,0.00018149476,0.000094586925,0.00018154243,0.000025087413,0.0004909463,8.1860964e-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":[0.012240951,0.0042945934,0.65938866,0.0005005756,0.010962682,0.000021914098,0.00012125712,0.22551332,0.0034701396,0.029265514,0.012143859,0.042076547],"study_design_scores_gemma":[0.02013213,0.013441055,0.21032757,0.00066648173,0.006327207,0.0005350879,0.00003610566,0.48289663,0.0020203663,0.25949782,0.0038253218,0.0002942483],"about_ca_topic_score_codex":0.000072824216,"about_ca_topic_score_gemma":0.0000029383968,"teacher_disagreement_score":0.44906107,"about_ca_system_score_codex":0.00024993924,"about_ca_system_score_gemma":0.00063734216,"threshold_uncertainty_score":0.94238853},"labels":[],"label_agreement":null},{"id":"W2143839180","doi":"10.1016/j.jclinepi.2013.09.017","title":"The GRADE recommendations. Weak recommendations are unhelpful to decision makers","year":2013,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"McMaster University","keywords":"Scopus; Intervention (counseling); Medicine; Presentation (obstetrics); MEDLINE; Prestige; Family medicine; Alternative medicine; Evidence-based medicine; Psychology; Political science; Nursing; Pathology","score_opus":0.7820573005714361,"score_gpt":0.6065778866967045,"score_spread":0.17547941387473154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143839180","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":[0.00053616223,0.00286521,0.018459883,0.9597717,0.016161473,0.00082730915,0.00031739226,0.000023670427,0.001037182],"genre_scores_gemma":[0.00013077984,0.008982041,0.04045864,0.93234533,0.014092838,0.00010010364,0.00010925356,0.000085127926,0.0036958624],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94269913,0.013459264,0.041553583,0.000989891,0.00021972778,0.0010784116],"domain_scores_gemma":[0.72789186,0.22724487,0.042311437,0.0013437589,0.00057922705,0.00062883913],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.19941986,0.0004965342,0.0068390546,0.00073336746,0.00053505576,0.00012641154,0.0016819899,0.001975052,0.0019736683],"category_scores_gemma":[0.3953673,0.00041882324,0.0016069079,0.00032110716,0.00025934077,0.0004344731,0.00022266417,0.0053351074,0.006715069],"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":[0.00003168898,0.00006221005,0.01203359,0.000059626625,0.00029316943,0.0000045214283,0.00005176824,0.000077623255,9.214342e-9,0.0059947334,0.9725928,0.008798301],"study_design_scores_gemma":[0.000693978,0.00028118462,0.01901054,0.0003444706,0.00003208396,0.00004798019,0.00023115637,0.00036274747,2.7910428e-8,0.11001021,0.8686518,0.0003338111],"about_ca_topic_score_codex":0.00020417008,"about_ca_topic_score_gemma":0.00013564693,"teacher_disagreement_score":0.21480726,"about_ca_system_score_codex":0.00071943953,"about_ca_system_score_gemma":0.0005006509,"threshold_uncertainty_score":0.9998264},"labels":[],"label_agreement":null},{"id":"W2144476291","doi":"10.1016/j.jclinepi.2012.10.005","title":"Randomized trials published in higher vs. lower impact journals differ in design, conduct, and analysis","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":84,"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 Manitoba; University of Toronto; SickKids Foundation; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Blinding; Medicine; Randomized controlled trial; Subgroup analysis; MEDLINE; Publication bias; Impact factor; Meta-analysis; Family medicine; Internal medicine","score_opus":0.9620847292114143,"score_gpt":0.7100508573792077,"score_spread":0.2520338718322066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144476291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90639687,0.0058793225,0.041670457,0.042752873,0.0015151006,0.0013464817,0.000004612343,0.0000016828185,0.00043258446],"genre_scores_gemma":[0.9808489,0.0014172035,0.01238495,0.003646415,0.00049341546,0.000027944561,0.0000012969126,0.000011478819,0.0011683926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.16788687,0.6743545,0.15261064,0.0012714003,0.003074424,0.0008021938],"domain_scores_gemma":[0.021790264,0.88199675,0.08982922,0.0023433133,0.0029916775,0.0010487549],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.92252105,0.00045551267,0.068275906,0.002757766,0.000039356477,0.0005740749,0.0017275177,0.00061229966,0.08117769],"category_scores_gemma":[0.94906455,0.00015910703,0.018092211,0.0027744002,0.00039582764,0.0009366599,0.00013724613,0.001516961,0.0002550687],"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":[0.010040761,0.00023840074,0.8828084,0.000008488475,0.0045167403,0.000036959424,0.000059312082,0.0013193411,0.000011079553,0.0002727226,0.09206929,0.008618525],"study_design_scores_gemma":[0.0391393,0.00027280438,0.8282337,0.000057063302,0.0018254521,0.000031289397,0.00003317071,0.012043536,5.224275e-7,0.116579086,0.0016221195,0.00016195733],"about_ca_topic_score_codex":0.00008571731,"about_ca_topic_score_gemma":0.00003026345,"teacher_disagreement_score":0.2076423,"about_ca_system_score_codex":0.00005219335,"about_ca_system_score_gemma":0.00021837745,"threshold_uncertainty_score":0.99174136},"labels":[],"label_agreement":null},{"id":"W2144998643","doi":"10.1016/j.jclinepi.2010.12.009","title":"The Brazilian-Portuguese versions of the McGill Pain Questionnaire were reproducible, valid, and responsive in patients with musculoskeletal pain","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":97,"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":"Intraclass correlation; McGill Pain Questionnaire; Cronbach's alpha; Medicine; Physical therapy; Portuguese; Brazilian Portuguese; Standard error; Ceiling effect; Psychometrics; Clinical psychology; Statistics; Mathematics; Visual analogue scale; Alternative medicine","score_opus":0.07295625434647027,"score_gpt":0.39925438310729977,"score_spread":0.32629812876082953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144998643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852173,0.0005310157,0.00016906792,0.013083935,0.00042858723,0.00041730894,0.000004623365,0.0000051968896,0.00014298946],"genre_scores_gemma":[0.99598616,0.00041710705,0.0015764805,0.0017801981,0.00012922904,0.0000042863066,0.0000017047485,0.000012449,0.00009240035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97996336,0.016383123,0.0028240976,0.00031064256,0.00026879302,0.00024997178],"domain_scores_gemma":[0.9646886,0.031388056,0.002331652,0.0006929823,0.00064838165,0.00025034708],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07149992,0.00014491794,0.0011041563,0.00010158108,0.0001041313,9.682079e-7,0.00018354761,0.00024883146,0.000016347356],"category_scores_gemma":[0.26866236,0.000062869236,0.0004751293,0.00021218762,0.000952108,0.00007739764,0.000062645064,0.00089513336,0.0000013551684],"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":[0.002613854,0.00038910084,0.936644,0.00013125436,0.00009829903,0.0000051794186,0.00008792069,0.00000741042,0.000011155251,0.0006450572,0.0016949616,0.057671797],"study_design_scores_gemma":[0.0020417643,0.0056341435,0.9860673,0.0006820106,0.00007061053,0.0000065630516,0.00021340516,0.00006508368,0.000002462087,0.003617999,0.0015305558,0.00006807899],"about_ca_topic_score_codex":0.000061111394,"about_ca_topic_score_gemma":0.000056123743,"teacher_disagreement_score":0.19716243,"about_ca_system_score_codex":0.00003591751,"about_ca_system_score_gemma":0.00018184652,"threshold_uncertainty_score":0.9560862},"labels":[],"label_agreement":null},{"id":"W2145110201","doi":"10.1016/j.jclinepi.2005.01.010","title":"Concordance between supervised and postal administration of the Mini Asthma Quality of Life Questionnaire (MiniAQLQ) and Asthma Control Questionnaire (ACQ) was very high","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":40,"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":"Fonden for Almen Praksis","keywords":"Asthma; Concordance; Medicine; Quality of life (healthcare); Administration (probate law); Family medicine; Physical therapy; Environmental health; Internal medicine; Nursing","score_opus":0.08247784592909578,"score_gpt":0.4272772525594999,"score_spread":0.3447994066304041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145110201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741628,0.0041031553,0.00082623377,0.020277763,0.00033615663,0.00021955602,0.000048160484,0.000007931684,0.00001821536],"genre_scores_gemma":[0.9943378,0.0004040432,0.00107651,0.002796077,0.0013464662,0.0000022771483,0.000004290937,0.000012813309,0.000019733943],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9905951,0.0039371923,0.004679094,0.00026997976,0.0002909606,0.00022765927],"domain_scores_gemma":[0.98675835,0.008038148,0.00365167,0.00030928556,0.0006829731,0.0005595587],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008711164,0.00020320422,0.0025056575,0.00007403389,0.00006925507,0.000004477296,0.0001551631,0.00040284716,0.000021523152],"category_scores_gemma":[0.05753343,0.00012700797,0.0004614832,0.0001071891,0.001281172,0.00015139773,0.000052469437,0.00062300585,0.000001221534],"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":[0.003113296,0.00027765988,0.96122044,0.00020614355,0.00016922264,0.000009597928,0.000058637914,0.0000152278035,0.0001625399,0.000634199,0.00026298178,0.033870053],"study_design_scores_gemma":[0.004946878,0.0030501303,0.989325,0.0006484116,0.0001576949,0.00009940496,0.000098390214,0.00015555997,0.0000740775,0.00049155456,0.0008487314,0.0001041908],"about_ca_topic_score_codex":0.00004718879,"about_ca_topic_score_gemma":0.000044501383,"teacher_disagreement_score":0.04882227,"about_ca_system_score_codex":0.000025937266,"about_ca_system_score_gemma":0.00095357565,"threshold_uncertainty_score":0.95040536},"labels":[],"label_agreement":null},{"id":"W2145171366","doi":"10.1016/j.jclinepi.2010.08.010","title":"Conducting quantitative synthesis when comparing medical interventions: AHRQ and the Effective Health Care Program","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":736,"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":"H2020 European Research Council; Agency for Healthcare Research and Quality","keywords":"Psychological intervention; Transparency (behavior); Consistency (knowledge bases); Agency (philosophy); Health care; Management science; Inclusion (mineral); Comparative effectiveness research; Computer science; Clinical study design; Research design; Medicine; Risk analysis (engineering); Process management; Psychology; Clinical trial; Nursing; Political science; Engineering; Mathematics","score_opus":0.9616347699983405,"score_gpt":0.8095308987224958,"score_spread":0.15210387127584468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145171366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.777316,0.0028318698,0.019284045,0.19089402,0.0038773871,0.0033317837,0.000012921068,0.00006346142,0.0023885411],"genre_scores_gemma":[0.92068964,0.0006914769,0.042047143,0.035691094,0.0006117256,0.00023731247,7.997108e-7,0.000014362969,0.000016458687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.92158675,0.068347044,0.008682768,0.00029682153,0.00036387247,0.0007227174],"domain_scores_gemma":[0.649789,0.33794525,0.01011239,0.0003043892,0.00085686444,0.000992087],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15237927,0.00014684928,0.002508577,0.00013822688,0.0006752486,0.000004677405,0.000468382,0.0002719576,0.00040474147],"category_scores_gemma":[0.49992952,0.0000823801,0.000455954,0.00015726738,0.0014460611,0.00018144985,0.00022818989,0.0024341927,0.000037120943],"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":[0.0010380931,0.00013615911,0.74387413,0.00081087725,0.0002270226,0.00000852377,0.056453396,0.0000012065286,1.2792982e-7,0.054921497,0.007248691,0.13528028],"study_design_scores_gemma":[0.011142317,0.004868296,0.8054223,0.0049555744,0.00020295945,0.00012728112,0.11518665,0.0012543707,0.0000017773573,0.03736824,0.019181171,0.0002890444],"about_ca_topic_score_codex":0.0010262135,"about_ca_topic_score_gemma":0.0007552376,"teacher_disagreement_score":0.34755024,"about_ca_system_score_codex":0.00012487193,"about_ca_system_score_gemma":0.0013972567,"threshold_uncertainty_score":0.99986726},"labels":[],"label_agreement":null},{"id":"W2145530678","doi":"10.1016/j.jclinepi.2004.12.005","title":"Psychological distress confirmed as predictor of long-term back-related functional limitations in primary care settings","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital du Saint-Sacrement; Université Laval","funders":"Fonds de recherche du Québec; Washington State University","keywords":"Term (time); Distress; Psychological distress; Primary care; Medicine; Psychology; Clinical psychology; Psychiatry; Gerontology; Family medicine; Anxiety","score_opus":0.15442473951508753,"score_gpt":0.45453766677540697,"score_spread":0.30011292726031946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145530678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781493,0.000834184,0.00044834515,0.014795382,0.0006924842,0.00027810482,0.000008339082,0.000009952687,0.004783906],"genre_scores_gemma":[0.99212503,0.0005039746,0.0036153644,0.0026858672,0.0006423654,0.0000047191934,0.00009833003,0.000011273837,0.0003130475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924866,0.00213,0.0046167057,0.00026877286,0.00025258263,0.0002453512],"domain_scores_gemma":[0.9777193,0.019472975,0.0018593416,0.0002089012,0.0004494285,0.00029004854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006352999,0.00015018429,0.0017301393,0.00016831166,0.000024373212,0.0000019219622,0.00012563738,0.0005605191,0.00048084155],"category_scores_gemma":[0.037764028,0.00010137973,0.0007865141,0.00016168355,0.0005985921,0.000088436835,0.000027858803,0.001117951,0.00004396612],"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":[0.0014977973,0.001031407,0.9380932,0.00044020574,0.00013824608,0.000020147148,0.00016083985,0.00020732125,0.00028569734,0.00044779325,0.001702172,0.055975188],"study_design_scores_gemma":[0.004877005,0.0025561347,0.9901009,0.0005157383,0.000062005434,0.000111612586,0.00009827194,0.00009989726,0.0000042229385,0.00086220383,0.0006326176,0.00007939252],"about_ca_topic_score_codex":0.0000026632054,"about_ca_topic_score_gemma":0.000009717267,"teacher_disagreement_score":0.055895794,"about_ca_system_score_codex":0.000091291535,"about_ca_system_score_gemma":0.00017053206,"threshold_uncertainty_score":0.97034127},"labels":[],"label_agreement":null},{"id":"W2147407888","doi":"10.1016/j.jclinepi.2006.11.019","title":"Combining ratings from multiple physician reviewers helped to overcome the uncertainty associated with adverse event classification","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Safety and Medication Errors","field":"Health Professions","cited_by":30,"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 Ottawa","funders":"","keywords":"Medicine; Predictive value; Adverse effect; Latent class model; Statistics; Internal medicine; Mathematics","score_opus":0.4011499321970556,"score_gpt":0.5681139536584912,"score_spread":0.16696402146143557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147407888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88355666,0.00012873205,0.058667753,0.0536657,0.0026154632,0.00070829794,0.000018900964,0.00002554013,0.00061292393],"genre_scores_gemma":[0.9486376,0.00017016349,0.0016327432,0.04855263,0.0008011164,0.000015840966,0.00004204336,0.000014174938,0.0001336859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98451793,0.00905004,0.0053307777,0.00025436166,0.00034931613,0.0004975802],"domain_scores_gemma":[0.88638943,0.10289597,0.009131692,0.0003750529,0.0007137121,0.00049416686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05354253,0.00015828252,0.0014891099,0.00007144864,0.00036628934,4.891057e-7,0.00035650225,0.00035833346,0.000066509274],"category_scores_gemma":[0.2008597,0.00008866472,0.0003552603,0.00027997486,0.0002072452,0.00009697406,0.000056854533,0.001996511,0.00007818776],"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":[0.0014087533,0.00031680847,0.97195023,0.000023408975,0.00023942311,0.000005977332,0.0023434234,0.0019204442,0.00007735963,0.0011781561,0.009852891,0.010683105],"study_design_scores_gemma":[0.0022564258,0.00048216962,0.9411219,0.0009984464,0.00009552652,7.473715e-7,0.002339057,0.0019831965,0.0000017692308,0.00093884865,0.04968252,0.00009940867],"about_ca_topic_score_codex":0.00013954722,"about_ca_topic_score_gemma":0.0003974807,"teacher_disagreement_score":0.14731717,"about_ca_system_score_codex":0.00020686856,"about_ca_system_score_gemma":0.00046037138,"threshold_uncertainty_score":0.9745771},"labels":[],"label_agreement":null},{"id":"W2147841266","doi":"10.1016/j.jclinepi.2009.03.020","title":"Case management poststroke did not induce response shift: the value of residuals","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","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":"Royal Victoria Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Psychological intervention; Medicine; Overtime; Intervention (counseling); Clinical trial; Physical therapy; Randomized controlled trial; Physical medicine and rehabilitation; Psychiatry; Internal medicine","score_opus":0.1868017317962644,"score_gpt":0.49992853664718373,"score_spread":0.31312680485091937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147841266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8847761,0.00037641564,0.00036604394,0.1126345,0.00080710807,0.00020931635,0.0000045933593,0.0000062143245,0.0008196691],"genre_scores_gemma":[0.9738646,0.0005403345,0.0075820894,0.016967673,0.0006133282,0.0000012530214,6.4553865e-7,0.000008041806,0.0004220046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9879349,0.006907955,0.004422796,0.00020410524,0.00026688387,0.00026338495],"domain_scores_gemma":[0.9462103,0.050591316,0.0022903162,0.00042496028,0.00021226202,0.00027081213],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04110684,0.000136238,0.0018575152,0.00019526356,0.000047567184,0.0000029441019,0.00019565292,0.00028967336,0.00005942154],"category_scores_gemma":[0.0858382,0.00007285661,0.0010264191,0.00014859374,0.00033567194,0.00005271463,0.00004020605,0.0009565423,0.000012984502],"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":[0.10042697,0.0033715053,0.5980493,0.00031547376,0.002421353,0.013580733,0.0011774906,0.000785568,0.0019314855,0.059637435,0.04913283,0.16916987],"study_design_scores_gemma":[0.002374808,0.0052191555,0.9746704,0.00017356998,0.00023641491,0.00402819,0.00023387464,0.000036135087,0.00008036528,0.0061484487,0.0067344233,0.0000642307],"about_ca_topic_score_codex":0.000008321359,"about_ca_topic_score_gemma":0.0000010384247,"teacher_disagreement_score":0.37662113,"about_ca_system_score_codex":0.00003982992,"about_ca_system_score_gemma":0.00018860385,"threshold_uncertainty_score":0.9873823},"labels":[],"label_agreement":null},{"id":"W2148354119","doi":"10.1016/j.jclinepi.2011.10.008","title":"The Global Rating Scale complements the AGREE II in advancing the quality of practice guidelines","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":117,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research; Canadian Partnership Against Cancer; University of Ottawa; Ottawa Hospital; BC Cancer Agency; McMaster University; Cancer Care Ontario","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Rating scale; Scale (ratio); Outcome (game theory); Quality (philosophy); Medicine; Psychology; Clinical psychology; Developmental psychology; Mathematics; Pathology","score_opus":0.8101579374006679,"score_gpt":0.706638940148075,"score_spread":0.10351899725259284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148354119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60503674,0.0012065138,0.008719504,0.38054693,0.0020789537,0.0006443238,0.000009733362,0.000008913986,0.0017483821],"genre_scores_gemma":[0.8387871,0.0025801954,0.09946477,0.05734038,0.0017593028,0.000008560859,0.0000038206827,0.000016285385,0.000039606042],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95619774,0.01843878,0.02363207,0.00034211625,0.0007875328,0.000601789],"domain_scores_gemma":[0.5070563,0.45161396,0.032917283,0.001655771,0.006302933,0.00045375267],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21601975,0.00017944587,0.0017643028,0.0000327911,0.00027564948,0.000007178025,0.00066157494,0.00018142739,0.00008367807],"category_scores_gemma":[0.7754641,0.000076057615,0.0006692494,0.0002919184,0.0006775351,0.00027422892,0.00033428732,0.0015238733,0.00000680821],"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":[0.0038760751,0.00045096586,0.86240166,0.000025901418,0.0003165316,0.000012693828,0.00033133494,0.000114776296,0.000030001807,0.004411918,0.0175747,0.11045344],"study_design_scores_gemma":[0.0037658012,0.001651336,0.9010876,0.00014927927,0.00037443615,0.00026908563,0.006378171,0.00096461957,0.00000992639,0.021546364,0.06370859,0.00009484163],"about_ca_topic_score_codex":0.0013862767,"about_ca_topic_score_gemma":0.0021287152,"teacher_disagreement_score":0.55944437,"about_ca_system_score_codex":0.00009100656,"about_ca_system_score_gemma":0.000610213,"threshold_uncertainty_score":0.8072727},"labels":[],"label_agreement":null},{"id":"W2148679943","doi":"10.1016/j.jclinepi.2006.06.004","title":"Dealing with the media","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Business Strategies and Management Research","field":"Decision Sciences","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 Ottawa; Institute of Population and Public Health; McMaster University; BC Research (Canada)","funders":"","keywords":"Medicine","score_opus":0.6612290599074706,"score_gpt":0.6102931936937248,"score_spread":0.050935866213745795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148679943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52356887,0.0011449342,0.14039631,0.29961112,0.0017032374,0.00014658543,0.0000013635968,0.000011768361,0.03341581],"genre_scores_gemma":[0.9922093,0.00022154526,0.0032320803,0.0021941152,0.0015578661,7.8491786e-7,2.9340774e-7,0.000005047209,0.0005789505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9923088,0.0028852918,0.0034880945,0.000206576,0.00081082893,0.00030042627],"domain_scores_gemma":[0.8611836,0.13433881,0.0030218272,0.00042780495,0.00089052896,0.0001374302],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09061161,0.00008532327,0.0011060284,0.00011609671,0.00009704096,0.000053190546,0.0010329982,0.00010846456,0.00031466674],"category_scores_gemma":[0.07676553,0.000031236556,0.0003412653,0.00031849204,0.0005509507,0.00015577594,0.00011579804,0.00064283144,0.000053198426],"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":[0.00044042408,0.0000925547,0.30773208,0.0000035978678,0.000065132954,0.00011070355,0.000016997747,0.006297431,0.0000042057545,0.39163476,0.18588762,0.10771448],"study_design_scores_gemma":[0.00043844848,0.00020401289,0.54142463,0.000009845261,0.000016352453,0.000047091962,0.00021515215,0.00062057195,8.551204e-7,0.26929227,0.18768567,0.000045114804],"about_ca_topic_score_codex":0.00009339628,"about_ca_topic_score_gemma":0.00022825375,"teacher_disagreement_score":0.46864045,"about_ca_system_score_codex":0.000006426572,"about_ca_system_score_gemma":0.00012115636,"threshold_uncertainty_score":0.93640673},"labels":[],"label_agreement":null},{"id":"W2150240148","doi":"10.1016/s0895-4356(03)00203-8","title":"Is the health utilities index responsive in total hip arthroplasty patients?","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"London Health Sciences Centre; Western University; Institute of Health Economics; University of Ottawa","funders":"","keywords":"Health Utilities Index; Statistic; WOMAC; Medicine; Physical therapy; Statistics; Total hip arthroplasty; Index (typography); Surgery; Osteoarthritis; Disease; Mathematics; Health related quality of life; Internal medicine; Alternative medicine; Pathology; Computer science","score_opus":0.6677718433997778,"score_gpt":0.5707640597025984,"score_spread":0.09700778369717944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150240148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7967043,0.0032119586,0.002210118,0.19330053,0.0030805022,0.00036711837,0.00006181865,0.000005925558,0.0010577372],"genre_scores_gemma":[0.8899623,0.0010537355,0.0017443066,0.10637333,0.00051251735,0.000010520407,0.0000024318886,0.000017279264,0.0003235873],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9573547,0.017179731,0.02424214,0.0004528779,0.00011502937,0.00065551576],"domain_scores_gemma":[0.89014435,0.088818766,0.019760901,0.00058789033,0.0002449759,0.00044311845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22196965,0.00017754127,0.0035785127,0.0002913186,0.00012743786,0.000013920035,0.00026908529,0.0003297976,0.00057621655],"category_scores_gemma":[0.33675557,0.00014748718,0.00054687826,0.0001762904,0.00033156134,0.00025659378,0.000041036685,0.0010983073,0.00036692352],"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":[0.0001265862,0.00014886032,0.88153845,0.000037487935,0.000056905035,0.000001057596,0.0006798125,0.00014553945,4.4929207e-9,0.064839266,0.05176953,0.00065652234],"study_design_scores_gemma":[0.0014388885,0.00064065016,0.79915637,0.00006120037,0.0000025377585,0.000015215997,0.0008346147,0.00054165866,6.0104604e-8,0.085896425,0.1113016,0.00011077808],"about_ca_topic_score_codex":0.0002852656,"about_ca_topic_score_gemma":0.000112696245,"teacher_disagreement_score":0.11478593,"about_ca_system_score_codex":0.00031525706,"about_ca_system_score_gemma":0.00079570763,"threshold_uncertainty_score":0.801146},"labels":[],"label_agreement":null},{"id":"W2151706470","doi":"10.1016/j.jclinepi.2004.12.001","title":"Conventional models overestimate the statistical significance of volume–outcome associations, compared with multilevel models","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":75,"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; University Health Network","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Multilevel model; Statistics; Regression analysis; Confidence interval; Medicine; Volume (thermodynamics); Linear regression; Outcome (game theory); Statistical model; Regression; Statistical significance; Random effects model; Meta-analysis; Mathematics; Internal medicine","score_opus":0.4286165118154147,"score_gpt":0.5443587068446052,"score_spread":0.11574219502919048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151706470","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":[0.25536215,0.0039867717,0.6973198,0.040479273,0.00035426524,0.00097219244,0.0005334323,0.000022943834,0.00096915936],"genre_scores_gemma":[0.93545634,0.00023072449,0.062256843,0.0014231576,0.00035172486,0.00001090656,0.000022362954,0.000012370584,0.00023559974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940401,0.0016018472,0.0032923033,0.00020505885,0.00051581283,0.00034487896],"domain_scores_gemma":[0.9800447,0.016627412,0.002061711,0.00023768083,0.0006496557,0.00037882235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00850721,0.00014713658,0.0019151403,0.00006171043,0.00006430404,0.00000477569,0.00019672979,0.00014589212,0.00020102257],"category_scores_gemma":[0.009839599,0.000078359444,0.0004012905,0.00007465137,0.0005430405,0.0001441099,0.000036754423,0.0008539146,0.000013719868],"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":[0.0038606739,0.0011845331,0.8418657,0.00006370292,0.00094739633,0.000095630676,0.00004222367,0.09507877,0.0000030696103,0.042411014,0.007642765,0.0068045123],"study_design_scores_gemma":[0.0046965615,0.0015505592,0.6278917,0.00007176564,0.00021171178,0.00008595229,0.000014231809,0.33740586,0.0000046653045,0.027744982,0.0002595687,0.00006244306],"about_ca_topic_score_codex":0.00010762248,"about_ca_topic_score_gemma":0.00003173451,"teacher_disagreement_score":0.6800941,"about_ca_system_score_codex":0.00014175313,"about_ca_system_score_gemma":0.00067149225,"threshold_uncertainty_score":0.99850094},"labels":[],"label_agreement":null},{"id":"W2151807121","doi":"10.1016/j.jclinepi.2012.09.004","title":"Does this child have appendicitis? A systematic review of clinical prediction rules for children with acute abdominal pain","year":2012,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Appendicitis Diagnosis and Management","field":"Medicine","cited_by":198,"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. Michael's Hospital; SickKids Foundation; Institute for Clinical Evaluative Sciences; University of Toronto; Hospital for Sick Children","funders":"","keywords":"Alvarado score; Medicine; Appendicitis; Abdominal pain; Nausea; Vomiting; Physical therapy; Pediatrics; Internal medicine; Surgery","score_opus":0.2144065683510894,"score_gpt":0.5135022776084387,"score_spread":0.2990957092573493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151807121","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":[0.000016423743,0.9819377,0.0068158396,0.0023818838,0.0015307972,0.006771249,0.00030332952,0.00002083083,0.00022193724],"genre_scores_gemma":[0.000026677448,0.9798753,0.008735659,0.0059717377,0.004431929,0.0003223121,0.00037541805,0.00009690391,0.0001640127],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.957417,0.015019382,0.025409186,0.00074961846,0.0006684014,0.00073641393],"domain_scores_gemma":[0.92207474,0.045046296,0.030525127,0.00097067386,0.0005613534,0.00082181767],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.11719322,0.00078264455,0.03280111,0.00034264565,0.0000850515,0.000008635592,0.00070098846,0.0013317923,0.00028957156],"category_scores_gemma":[0.08107113,0.00034108016,0.0076194336,0.00015511987,0.0006298324,0.00013374229,0.00015981686,0.0026235795,0.000037133763],"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":[0.00040765112,0.0008662693,0.007956287,0.65803605,0.0110944575,0.000060871767,0.0000056778617,1.0639827e-7,1.3813324e-9,0.00039334563,0.019547097,0.30163217],"study_design_scores_gemma":[0.002068622,0.004836615,0.003377681,0.66768944,0.064683035,0.0018382587,0.000010724195,0.000011371518,1.9793184e-8,0.00011444611,0.25511926,0.00025053884],"about_ca_topic_score_codex":0.000012645607,"about_ca_topic_score_gemma":0.000004517504,"teacher_disagreement_score":0.30138165,"about_ca_system_score_codex":0.00009491047,"about_ca_system_score_gemma":0.00060840417,"threshold_uncertainty_score":0.9999647},"labels":[],"label_agreement":null},{"id":"W2152229558","doi":"10.1016/j.jclinepi.2003.08.011","title":"Clinimetrics vs. psychometrics: an unnecessary distinction","year":2003,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"","keywords":"Psychometrics; Intraclass correlation; Structural equation modeling; Scale (ratio); Item response theory; Term (time); Reliability (semiconductor); Psychology; Cognition; Classical test theory; Econometrics; Clinical psychology; Statistics; Psychiatry; Mathematics","score_opus":0.8990231872981096,"score_gpt":0.6721006755354438,"score_spread":0.22692251176266576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152229558","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010021828,0.0048274994,0.232338,0.6762461,0.07001129,0.00032349362,0.00005906503,0.00006584348,0.0061068553],"genre_scores_gemma":[0.0010463411,0.004174062,0.14579612,0.8172343,0.029878069,0.00000404214,0.00002772832,0.00008435083,0.0017550025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.86392754,0.092765644,0.035384502,0.0023397375,0.003922088,0.0016604972],"domain_scores_gemma":[0.08439421,0.86641604,0.04213278,0.0025359215,0.0035827335,0.0009383437],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3998392,0.0007493227,0.010994962,0.006449618,0.00022218627,0.00017420803,0.0048679276,0.005406087,0.0011989194],"category_scores_gemma":[0.97568125,0.00047629708,0.0036406647,0.009401352,0.0008288512,0.00059465296,0.000279495,0.014611927,0.00024222898],"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":[0.00013964571,0.00013329841,0.24483357,0.000014233195,0.000109026274,0.0001937285,0.0000035672895,0.000040627994,6.5002745e-8,0.00006259901,0.5853647,0.16910492],"study_design_scores_gemma":[0.0008597703,0.0025900307,0.14827281,0.00004575847,0.00013851763,0.00043636296,0.00003628791,0.00025979595,1.9269416e-7,0.12964362,0.7173606,0.00035625367],"about_ca_topic_score_codex":0.000023155668,"about_ca_topic_score_gemma":0.0000028698314,"teacher_disagreement_score":0.7795333,"about_ca_system_score_codex":0.000117251126,"about_ca_system_score_gemma":0.00065899873,"threshold_uncertainty_score":0.99976885},"labels":[],"label_agreement":null},{"id":"W2152377741","doi":"10.1016/j.jclinepi.2014.02.006","title":"Poor agreement between family-level and neighborhood-level income measures among urban families with children","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","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 Toronto; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; St. Michael's Hospital","funders":"","keywords":"Low income; Demography; Medicine; Environmental health; Psychology; Sociology; Socioeconomics","score_opus":0.3136448462033874,"score_gpt":0.46395881382731585,"score_spread":0.15031396762392846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152377741","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":[0.09198392,0.0015189551,0.0024831644,0.8986686,0.0021628765,0.00052043365,0.00012214248,0.000028541439,0.0025113935],"genre_scores_gemma":[0.20062979,0.005735306,0.0026018156,0.75838095,0.031331968,0.00001011353,0.00003590362,0.00006061839,0.0012135616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9793419,0.011652099,0.0059793475,0.0006270592,0.0010298021,0.0013697474],"domain_scores_gemma":[0.9498378,0.04272929,0.005634,0.00040742304,0.0005091005,0.0008823751],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.031547837,0.0005385588,0.005632,0.0002875133,0.00047487006,0.000058629204,0.0010671419,0.0025896416,0.00007321249],"category_scores_gemma":[0.036660023,0.00035962692,0.0008423265,0.00017210182,0.0022212516,0.00022170886,0.00016372862,0.00547245,0.000020681966],"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":[0.00004077036,0.000017544726,0.66435415,0.00007526051,0.00034465457,0.00003620898,0.0001619988,0.0000015525119,6.585755e-9,0.00062832184,0.32872257,0.0056169676],"study_design_scores_gemma":[0.00079924753,0.00045717813,0.69647706,0.0003711375,0.0002251984,0.00001548016,0.00018031249,0.0000023563543,3.253376e-8,0.002794567,0.29838866,0.00028875598],"about_ca_topic_score_codex":0.007441106,"about_ca_topic_score_gemma":0.0016565957,"teacher_disagreement_score":0.14028764,"about_ca_system_score_codex":0.00015885998,"about_ca_system_score_gemma":0.0012614642,"threshold_uncertainty_score":0.99988556},"labels":[],"label_agreement":null},{"id":"W2152397973","doi":"10.1016/j.jclinepi.2013.11.005","title":"A charitable donation incentive did not increase physician survey response rates in a randomized trial","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":6,"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; Foothills Medical Centre; Humber River Regional Hospital; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Incentive; Donation; Randomized controlled trial; Family medicine; Medicine; Gerontology; Political science; Economics; Internal medicine","score_opus":0.6099749199841427,"score_gpt":0.5967234733033098,"score_spread":0.01325144668083289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152397973","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37997267,0.00037689038,0.001511074,0.6092016,0.0073765116,0.0011022328,0.000044258828,0.000018020315,0.00039671466],"genre_scores_gemma":[0.06040421,0.0021601596,0.0025617462,0.911681,0.021302292,0.00007532128,0.00010598626,0.0000555848,0.0016537088],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.07525456,0.9130065,0.009382394,0.0007020799,0.00065622194,0.0009982369],"domain_scores_gemma":[0.1923022,0.79684407,0.0093843,0.0003568151,0.0008509334,0.00026169163],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.88973653,0.00042593715,0.010484337,0.0007087525,0.00023576402,0.000029248511,0.0010450461,0.003962733,0.00017388671],"category_scores_gemma":[0.9645976,0.00032742068,0.0021797386,0.00051759894,0.0027088164,0.00025258545,0.00010756515,0.0071148723,0.000051630315],"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":[0.83853155,0.0001793169,0.008123679,0.000010546512,0.00026165924,0.00018925594,0.00030054824,0.0000068765416,0.000001442522,0.0001567475,0.15151222,0.00072615175],"study_design_scores_gemma":[0.5484012,0.0012891701,0.1528958,0.00024321543,0.00023052203,0.000010751531,0.000068303954,0.00009196265,0.0000024460594,0.015090254,0.28121495,0.0004614594],"about_ca_topic_score_codex":0.005829224,"about_ca_topic_score_gemma":0.0015264886,"teacher_disagreement_score":0.31956846,"about_ca_system_score_codex":0.0002029996,"about_ca_system_score_gemma":0.002766266,"threshold_uncertainty_score":0.9999178},"labels":[],"label_agreement":null},{"id":"W2152500261","doi":"10.1016/j.jclinepi.2012.01.001","title":"Ensuring relevance for Cochrane reviews: evaluating processes and methods for prioritizing topics for Cochrane reviews","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":59,"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; Ottawa Hospital; Cochrane","funders":"","keywords":"Systematic review; Transparency (behavior); Prioritization; Relevance (law); Cochrane collaboration; Medicine; Cochrane Library; Variety (cybernetics); Grey literature; MEDLINE; Computer science; Management science; Meta-analysis; Political science; Engineering","score_opus":0.945962810813024,"score_gpt":0.7673054041853945,"score_spread":0.17865740662762952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152500261","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":[0.0032064756,0.3046004,0.68303704,0.004935627,0.001613549,0.0025362936,0.000007989535,0.0000021665842,0.000060456765],"genre_scores_gemma":[0.0009921839,0.048482902,0.9428078,0.0027962516,0.0035948004,0.00026948508,0.0000029621608,0.000021136193,0.0010324954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8085968,0.10091261,0.0863565,0.0014350888,0.0015119083,0.0011871128],"domain_scores_gemma":[0.06836126,0.8520495,0.070099495,0.002114185,0.0066111637,0.0007643482],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.84162855,0.00037878184,0.020521292,0.00017899192,0.00022554421,0.00009279674,0.001089191,0.00033152007,0.00011559205],"category_scores_gemma":[0.97718954,0.00018078338,0.0051942496,0.00039059098,0.00014651043,0.00041290215,0.00009375009,0.0004647187,0.000019539142],"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":[0.00017331785,0.00008477981,0.012910059,0.0055689295,0.00023217562,2.5991173e-7,0.00020016552,0.000018943507,0.000079863734,0.0024109443,0.035047177,0.94327337],"study_design_scores_gemma":[0.0010774389,0.00083391985,0.0026518626,0.0018531684,0.0011222055,0.00008100028,0.00009663867,0.0070866547,0.000012998824,0.049027387,0.9359373,0.00021940963],"about_ca_topic_score_codex":6.0178496e-7,"about_ca_topic_score_gemma":0.000003660286,"teacher_disagreement_score":0.94305396,"about_ca_system_score_codex":0.00002860925,"about_ca_system_score_gemma":0.00017922153,"threshold_uncertainty_score":0.9940201},"labels":[],"label_agreement":null},{"id":"W2153572752","doi":"10.1016/j.jclinepi.2010.02.004","title":"Five questions predicted long-term, severe, back-related functional limitations: evidence from three large prospective studies","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":21,"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 Work & Health; Centre hospitalier universitaire de Québec; Hôpital du Saint-Sacrement","funders":"Canadian Institutes of Health Research","keywords":"Clinical prediction rule; Predictive validity; Medicine; Feeling; Back pain; Population; Physical therapy; Psychology; Alternative medicine; Clinical psychology; Social psychology","score_opus":0.23289643647499703,"score_gpt":0.48527327291829464,"score_spread":0.2523768364432976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153572752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96946645,0.0025045588,0.0063773408,0.017106978,0.0038058285,0.0004915659,0.000021209164,0.000033073724,0.00019302026],"genre_scores_gemma":[0.98038155,0.0022756716,0.013542661,0.0013885458,0.0018816049,0.000018838029,0.00003832589,0.00001816343,0.00045462453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9929935,0.002212985,0.0038036737,0.00038402286,0.0003075692,0.00029828734],"domain_scores_gemma":[0.91333365,0.08191928,0.0021265093,0.00035164933,0.0018952598,0.00037363573],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012271099,0.00020629591,0.0018563736,0.00015896895,0.000120453115,0.0000058666287,0.00014976494,0.00057857286,0.0005728411],"category_scores_gemma":[0.33204415,0.00013609655,0.0008303414,0.00022998212,0.0007403659,0.00028726558,0.000063809464,0.0022801948,0.00011244208],"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":[0.0008509456,0.0005406897,0.98807853,0.00009136663,0.0010433905,0.00001514628,0.00020496563,0.00006747809,0.00026395672,0.0016592488,0.0044254367,0.0027588224],"study_design_scores_gemma":[0.0027249476,0.0019219468,0.9600856,0.0009789156,0.0003357389,0.00007866549,0.00011240637,0.00067853375,0.000002561212,0.032810193,0.00015415563,0.000116381976],"about_ca_topic_score_codex":0.000016110638,"about_ca_topic_score_gemma":0.000340511,"teacher_disagreement_score":0.31977308,"about_ca_system_score_codex":0.0000690559,"about_ca_system_score_gemma":0.00042246951,"threshold_uncertainty_score":0.99064386},"labels":[],"label_agreement":null},{"id":"W2154025898","doi":"10.1016/j.jclinepi.2012.06.019","title":"Some but not all dyadic measures in shared decision making research have satisfactory psychometric properties","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":32,"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; Centre hospitalier universitaire de Québec; Ottawa Hospital; Université Laval; Western University; Hôpital Saint-François d'Assise","funders":"Canadian Institutes of Health Research","keywords":"Cronbach's alpha; Reliability (semiconductor); Observational study; Psychology; Psychometrics; Measure (data warehouse); Factorial; Clinical psychology; Statistics; Mathematics; Computer science; Data mining","score_opus":0.9126749589172267,"score_gpt":0.6794263107698045,"score_spread":0.2332486481474222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154025898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91337484,0.05897207,0.00041796052,0.01937596,0.006348978,0.0010721039,0.000014730015,0.000032759628,0.00039058615],"genre_scores_gemma":[0.9722504,0.005837706,0.009376066,0.009777319,0.0025433742,0.00008218693,0.0000029797886,0.000042596286,0.0000873617],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9244972,0.061223038,0.011107508,0.00041774183,0.0010282439,0.0017262837],"domain_scores_gemma":[0.7892213,0.20107082,0.0055384687,0.0013228263,0.0018871375,0.0009594597],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.092611104,0.0002493414,0.002510132,0.0015650089,0.00047002523,0.000008029258,0.0012557885,0.0011882377,0.000208373],"category_scores_gemma":[0.42679355,0.00017719028,0.00043740045,0.00060763716,0.00047181165,0.00068580627,0.00055499445,0.008474304,0.0002765798],"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":[0.0012718731,0.00024066046,0.9528029,0.00015599909,0.00005321342,0.000004144804,0.0023652834,0.00002790164,0.00004110971,0.00089638034,0.010957879,0.031182665],"study_design_scores_gemma":[0.0017084061,0.0006179904,0.96560645,0.0016864061,0.00001739078,0.000014367301,0.0022251485,0.00018693402,0.000003330276,0.012536801,0.0152383875,0.00015839416],"about_ca_topic_score_codex":0.0004505906,"about_ca_topic_score_gemma":0.0002941417,"teacher_disagreement_score":0.33418244,"about_ca_system_score_codex":0.0006722284,"about_ca_system_score_gemma":0.0011837897,"threshold_uncertainty_score":0.99381316},"labels":[],"label_agreement":null},{"id":"W2155301421","doi":"10.1016/j.jclinepi.2008.08.014","title":"A pragmatic resolution","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"Institute for Clinical Evaluative Sciences; University of Toronto; Sunnybrook Hospital; University of Victoria; Canadian College of Naturopathic Medicine","funders":"","keywords":"Scopus; Resolution (logic); Psychology; Medicine; MEDLINE; Computer science; Political science; Artificial intelligence; Law","score_opus":0.21719798640587784,"score_gpt":0.5402549566568264,"score_spread":0.3230569702509486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155301421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81910753,0.0022328775,0.014689482,0.15298225,0.0020428377,0.00021950965,0.0000017240044,0.000037484268,0.008686283],"genre_scores_gemma":[0.9315495,0.0014882986,0.03556929,0.028730422,0.00234743,6.6959564e-7,0.0000035401572,0.000007342145,0.00030349471],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9926478,0.0019016468,0.0047968985,0.00017566522,0.00019583598,0.0002821446],"domain_scores_gemma":[0.70872647,0.28571123,0.0037237054,0.00042032366,0.0004909548,0.0009273435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026034504,0.00010801378,0.0023508172,0.00008317752,0.000025524942,0.0000027847802,0.000120481156,0.00036212508,0.00012494987],"category_scores_gemma":[0.8499952,0.00006904891,0.00089091586,0.00011507489,0.00016482749,0.000044472017,0.00001465242,0.0010824421,0.000071996285],"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":[0.0028117963,0.0022739933,0.45916063,0.000025809692,0.00023781417,0.0005019253,0.00003976533,0.00017620802,0.00003564822,0.015177219,0.13054244,0.38901678],"study_design_scores_gemma":[0.0030874684,0.0063786777,0.9247086,0.0012066986,0.00022327229,0.0009394012,0.000011230057,0.0010370774,0.00000292042,0.04927791,0.013053897,0.00007282287],"about_ca_topic_score_codex":0.0000036275273,"about_ca_topic_score_gemma":5.4405416e-7,"teacher_disagreement_score":0.8239607,"about_ca_system_score_codex":0.000026319185,"about_ca_system_score_gemma":0.0002903794,"threshold_uncertainty_score":0.9023092},"labels":[],"label_agreement":null},{"id":"W2155947418","doi":"10.1016/j.jclinepi.2008.08.005","title":"Inadequate statistical power to detect clinically significant differences in adverse event rates in randomized controlled trials","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":138,"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; Centre for Advancing Health Outcomes; Vancouver General Hospital","funders":"","keywords":"Statistical power; Adverse effect; Event (particle physics); Medicine; Randomized controlled trial; Statistics; Internal medicine; Mathematics; Physics","score_opus":0.8062677585673081,"score_gpt":0.6897538581019267,"score_spread":0.11651390046538146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155947418","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003793331,0.6987228,0.27696708,0.001680989,0.008816035,0.012867499,0.00025730152,0.000041849595,0.00026709962],"genre_scores_gemma":[0.00018178535,0.6542075,0.34331667,0.0006945436,0.0010763681,0.000389313,0.0000027684193,0.00008361112,0.000047438487],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.24804275,0.5712223,0.17501742,0.0021088375,0.0015665402,0.0020421618],"domain_scores_gemma":[0.027682789,0.91806865,0.051050726,0.0010404495,0.00065191375,0.0015054987],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.62694836,0.0015685541,0.18188745,0.001477038,0.000057027024,0.000026959304,0.0019453161,0.003636825,0.0008834405],"category_scores_gemma":[0.9954665,0.000827178,0.02024016,0.0008314476,0.0018441174,0.00008989358,0.000399279,0.007993931,0.00011897867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26258272,0.0017740374,0.0010228761,0.0024952416,0.0044528195,0.0016194489,0.000054888947,0.000014950257,6.684055e-8,0.026953338,0.0033039015,0.69572574],"study_design_scores_gemma":[0.23246686,0.003054395,0.0005666367,0.018361604,0.00416348,0.00009260014,0.000021497372,0.00012934332,5.59017e-8,0.72655904,0.013733676,0.0008508079],"about_ca_topic_score_codex":0.00003061116,"about_ca_topic_score_gemma":0.000017732207,"teacher_disagreement_score":0.6996057,"about_ca_system_score_codex":0.0003021071,"about_ca_system_score_gemma":0.0030463901,"threshold_uncertainty_score":0.99970627},"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":"W2158711148","doi":"10.1016/j.jclinepi.2004.03.004","title":"Disease adaptation may have decreased quality-of-life responsiveness in patients with chronic progressive neurological disorders","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","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 Health Network; University of Toronto; Institute for Clinical Evaluative Sciences; Mount Sinai Hospital","funders":"","keywords":"Adaptation (eye); Disease; Quality of life (healthcare); Medicine; Physical medicine and rehabilitation; Gerontology; Physical therapy; Psychology; Internal medicine; Neuroscience","score_opus":0.4514809432464702,"score_gpt":0.5695894177815413,"score_spread":0.11810847453507106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158711148","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":[0.030273225,0.9645166,0.0003237132,0.002345922,0.00031555005,0.0021501624,0.000052726915,0.000010394253,0.00001175236],"genre_scores_gemma":[0.024900597,0.9725864,0.0014807644,0.00038261904,0.00042540123,0.0000851857,0.000082705104,0.000047433692,0.0000088848565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96840346,0.020324526,0.00917839,0.0006485515,0.0008028956,0.00064220495],"domain_scores_gemma":[0.91601586,0.07021771,0.010870172,0.00062613713,0.0010089296,0.0012611876],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017580496,0.0005186235,0.011487747,0.00051052315,0.000051432173,0.0000050530707,0.00043570044,0.00072764774,0.000057488483],"category_scores_gemma":[0.36614844,0.0002891733,0.0019591907,0.00034623427,0.0013164604,0.00008998436,0.00017042625,0.0028299931,0.0000062586614],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015645364,0.0015273616,0.56673574,0.009942338,0.0006324121,0.00008715205,0.0000133249405,0.00022193613,8.186622e-9,0.000072693554,0.000047713955,0.4050739],"study_design_scores_gemma":[0.009441676,0.0067814733,0.929876,0.021339813,0.00070801855,0.000006165804,0.000011181303,0.000066702516,5.570371e-9,0.00025830997,0.031280294,0.00023034212],"about_ca_topic_score_codex":0.00004658049,"about_ca_topic_score_gemma":0.00006259693,"teacher_disagreement_score":0.40484357,"about_ca_system_score_codex":0.00026766097,"about_ca_system_score_gemma":0.006384598,"threshold_uncertainty_score":0.999956},"labels":[],"label_agreement":null},{"id":"W2160071246","doi":"10.1016/j.jclinepi.2011.02.011","title":"Inclusion of methodological filters in searches for diagnostic test accuracy studies misses relevant studies","year":2011,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; St. Michael's Hospital","funders":"","keywords":"Test (biology); Inclusion (mineral); Medicine; Medical physics; Psychology; Biology; Social psychology","score_opus":0.9895161647790756,"score_gpt":0.7665582103548054,"score_spread":0.22295795442427013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160071246","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018921176,0.089753,0.011467766,0.87388504,0.0041704252,0.0015760704,0.00007326923,0.0000038126536,0.00014946552],"genre_scores_gemma":[0.010482996,0.1401681,0.33046922,0.50607514,0.0088979155,0.00012232977,0.000019306324,0.000077281475,0.0036877152],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5100772,0.35248333,0.12935898,0.0022159072,0.0047417185,0.0011228509],"domain_scores_gemma":[0.0033097775,0.9109593,0.077142455,0.0021898816,0.00618217,0.00021638944],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.7764628,0.0007017485,0.045884468,0.0009956948,0.00014093456,0.00003255863,0.004167687,0.0015216741,0.0005908738],"category_scores_gemma":[0.997904,0.00027634387,0.010721131,0.0006965431,0.0013822648,0.00019048146,0.0018757795,0.0037712094,0.000106493724],"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":[0.0001158288,0.00015803752,0.060896695,0.0007539639,0.0019195547,0.000178172,0.0004893923,0.00004363184,0.0000028854934,0.00010672751,0.916606,0.018729124],"study_design_scores_gemma":[0.0007202876,0.0022376275,0.019395338,0.0016890458,0.001366072,0.00009404021,0.00078505994,0.00016979182,0.0000057510715,0.32081696,0.65241694,0.00030304553],"about_ca_topic_score_codex":0.000008511528,"about_ca_topic_score_gemma":0.000020917925,"teacher_disagreement_score":0.558476,"about_ca_system_score_codex":0.00008168891,"about_ca_system_score_gemma":0.00037393364,"threshold_uncertainty_score":0.9999689},"labels":[],"label_agreement":null},{"id":"W2160274999","doi":"10.1016/j.jclinepi.2015.03.013","title":"The ethics of cluster-randomized trials requires further evaluation: a refinement of the Ottawa Statement","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":16,"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":"CRTS; Informed consent; Statement (logic); Research ethics; Psychological intervention; Multidisciplinary approach; Family medicine; Randomization; Medicine; Randomized controlled trial; Cluster randomised controlled trial; Cluster (spacecraft); Consolidated Standards of Reporting Trials; Medical education; Psychology; Alternative medicine; Nursing; Computer science; Psychiatry; Law; Political science; Pathology","score_opus":0.9336370630359181,"score_gpt":0.7561020404829479,"score_spread":0.17753502255297016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160274999","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12548086,0.0053970595,0.004805037,0.8546483,0.0043941154,0.0021907967,0.0000091607335,0.0000053534764,0.0030692972],"genre_scores_gemma":[0.9533954,0.014104828,0.016139017,0.013042647,0.0021136326,0.000049311657,0.000002378705,0.000030543022,0.0011222248],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.47707593,0.43405652,0.07642632,0.0009389156,0.010228338,0.001273981],"domain_scores_gemma":[0.01429415,0.9552079,0.019497711,0.0012373189,0.00927191,0.0004910062],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86507374,0.00017205502,0.0060643232,0.000084722,0.00007774889,0.00000606505,0.00082516397,0.0009774195,0.00017491248],"category_scores_gemma":[0.9825711,0.00006750419,0.0024335328,0.00020672914,0.003281666,0.00004411906,0.00032226538,0.0056503434,0.0000060721964],"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":[0.52122307,0.0027960106,0.08847319,0.00090601295,0.008077087,0.000023667424,0.0026919404,0.0024457346,0.00014958771,0.17053026,0.13154529,0.07113814],"study_design_scores_gemma":[0.18420357,0.004986788,0.012603319,0.0013531734,0.0017247356,0.000036701418,0.00082550815,0.002694099,0.00012404866,0.75903094,0.032305896,0.00011122082],"about_ca_topic_score_codex":0.00007868908,"about_ca_topic_score_gemma":0.00016995987,"teacher_disagreement_score":0.84160566,"about_ca_system_score_codex":0.0001153756,"about_ca_system_score_gemma":0.0060460195,"threshold_uncertainty_score":0.9995888},"labels":[],"label_agreement":null},{"id":"W2162006280","doi":"10.1016/j.jclinepi.2010.07.001","title":"AGREE II: Advancing guideline development, reporting and evaluation in health care","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":560,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Quality (philosophy); Medicine; Health care; Clinical Practice; MEDLINE; Family medicine; Nursing; Political science; Pathology","score_opus":0.6305448945421918,"score_gpt":0.6839559095183986,"score_spread":0.053411014976206816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162006280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93608886,0.00074840465,0.003543175,0.05763823,0.0014635902,0.00035530076,7.084517e-7,0.000008921025,0.00015278676],"genre_scores_gemma":[0.7062292,0.00030710376,0.2787108,0.013509138,0.0011886156,0.0000033296437,0.000022592394,0.000013425668,0.00001579976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9600214,0.003258464,0.03531869,0.0004287982,0.00049966463,0.00047301047],"domain_scores_gemma":[0.9062754,0.044534337,0.044771817,0.00054203765,0.0029491344,0.0009272844],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19796537,0.00014531362,0.0021904141,0.00019726036,0.00009085651,0.0000041803187,0.000095082076,0.0002825654,0.00014499525],"category_scores_gemma":[0.72292495,0.000112821945,0.00023521649,0.00014804897,0.00011158654,0.00019652265,0.00010152381,0.0019644953,0.000003150615],"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":[0.00028341167,0.000094818985,0.54876417,0.00004692581,0.000034408367,0.000023634484,0.00018855889,0.00007283533,0.000113031405,0.00004805693,0.0027901249,0.44754004],"study_design_scores_gemma":[0.0053833006,0.0014219768,0.8878225,0.0002570981,0.000104609644,0.0008388205,0.0008643181,0.0036151868,0.000018462051,0.0016928224,0.097860634,0.00012023714],"about_ca_topic_score_codex":0.00013067521,"about_ca_topic_score_gemma":0.0013536435,"teacher_disagreement_score":0.52495956,"about_ca_system_score_codex":0.0001320788,"about_ca_system_score_gemma":0.0028087585,"threshold_uncertainty_score":0.8534864},"labels":[],"label_agreement":null},{"id":"W2162382129","doi":"10.1016/j.jclinepi.2011.05.010","title":"Rasch analysis supports the use of the Depression, Anxiety, and Stress Scales to measure mood in groups but not in individuals with chronic low back pain","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":77,"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":"National Health and Medical Research Council","keywords":"Rasch model; Mood; Anxiety; Depression (economics); Clinical psychology; Depressed mood; Psychometrics; Physical therapy; Chronic pain; Medicine; Measure (data warehouse); Rating scale; Psychology; Psychiatry; Developmental psychology","score_opus":0.12127179383185757,"score_gpt":0.3924024960107222,"score_spread":0.2711307021788646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162382129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99123985,0.00026984344,0.0012285202,0.006727629,0.00009327433,0.00040919686,0.000007032579,0.0000018812985,0.00002276889],"genre_scores_gemma":[0.9948825,0.00032386428,0.0028471898,0.0017895205,0.00012070385,0.0000065577865,0.0000025429915,0.000009034989,0.00001807554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98812526,0.00818819,0.002893856,0.00025636508,0.00028197916,0.00025434972],"domain_scores_gemma":[0.981459,0.016357893,0.0013785163,0.00040096883,0.00019822681,0.000205352],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031084336,0.00014510068,0.001687825,0.0002159613,0.00002722613,0.0000035589305,0.00020559627,0.00028959764,0.000059998474],"category_scores_gemma":[0.042213533,0.00006090791,0.00046289124,0.00050292583,0.0004567937,0.00008634733,0.000080665974,0.0008603555,9.620865e-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":[0.0005004305,0.00030401445,0.98941004,0.00015634947,0.0003001749,0.0000032852186,0.0002815107,0.00086651207,0.00006386779,0.000030623665,0.00024783195,0.00783537],"study_design_scores_gemma":[0.0016223509,0.00088821416,0.99523306,0.00072805677,0.00019457954,0.000014633578,0.00014328657,0.0006890324,0.0000362331,0.00032370523,0.00005995263,0.000066905],"about_ca_topic_score_codex":0.0002159775,"about_ca_topic_score_gemma":0.0026249944,"teacher_disagreement_score":0.011129195,"about_ca_system_score_codex":0.000033246717,"about_ca_system_score_gemma":0.000152324,"threshold_uncertainty_score":0.9977026},"labels":[],"label_agreement":null},{"id":"W2162998437","doi":"10.1016/s0895-4356(02)00542-5","title":"Feinstein and study design","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Historical and modern epidemiology studies","field":"Social Sciences","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":"McGill University","funders":"","keywords":"Sophistication; Scope (computer science); Set (abstract data type); Meaning (existential); Clinical epidemiology; Epidemiology; Public health; Epistemology; Medicine; Reflexive pronoun; Research design; Psychology; Sociology; Computer science; Social science; Nursing; Philosophy; Pathology","score_opus":0.6914265088898165,"score_gpt":0.5622297241662177,"score_spread":0.12919678472359875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162998437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76094276,0.01939337,0.05299246,0.1314092,0.006940752,0.0007753022,0.0000015931946,0.00007425598,0.027470293],"genre_scores_gemma":[0.9745865,0.008331499,0.00950905,0.004096114,0.0016594768,0.0000020712657,3.897091e-8,0.0000073196443,0.0018079538],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.976784,0.019315584,0.0030793522,0.00024351047,0.00017547375,0.00040206636],"domain_scores_gemma":[0.94094354,0.056780234,0.0015691314,0.00012837784,0.00018498379,0.00039370783],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056522284,0.000116521755,0.0020214953,0.00007161245,0.0003319044,0.0000040917816,0.00026989906,0.0002865878,0.00013631719],"category_scores_gemma":[0.18245405,0.000079704594,0.00029453228,0.00010468988,0.0010472113,0.00010248239,0.00005874511,0.00069676194,0.000036794518],"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":[0.00012922147,0.00078211137,0.8098066,0.000003953504,0.00025002615,0.00007497779,0.0049724486,0.000050540875,7.8734945e-7,0.009793737,0.07513039,0.09900522],"study_design_scores_gemma":[0.002183182,0.0045503187,0.26026118,0.000028921824,0.00019860492,0.000035131972,0.0032295953,0.0006172925,2.0266285e-7,0.052835125,0.6757934,0.000267035],"about_ca_topic_score_codex":0.00017522121,"about_ca_topic_score_gemma":0.00012280516,"teacher_disagreement_score":0.600663,"about_ca_system_score_codex":0.0000415988,"about_ca_system_score_gemma":0.00005688131,"threshold_uncertainty_score":0.97150886},"labels":[],"label_agreement":null},{"id":"W2163296606","doi":"10.1016/s0895-4356(00)00295-x","title":"Glottic cancer in Ontario, Canada and the SEER areas of the United States","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Head and Neck Cancer Studies","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cancer Care Ontario; Princess Margaret Cancer Centre; University of Toronto; Queen's University","funders":"National Cancer Institute; Cancer Care Ontario","keywords":"Medicine; Laryngectomy; Relative survival; Epidemiology; Cancer registry; Cancer; Radiation therapy; Larynx; Surveillance, Epidemiology, and End Results; Stage (stratigraphy); Surgery; Disease; Internal medicine","score_opus":0.1765309387959699,"score_gpt":0.45985374404219914,"score_spread":0.2833228052462292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163296606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9122201,0.0018295769,0.000008834856,0.0849974,0.0005787403,0.00008496548,0.0000019520917,8.345019e-7,0.00027759452],"genre_scores_gemma":[0.9743139,0.007334053,0.00004637373,0.017714798,0.00017545724,0.0000022797958,4.742225e-7,0.000004346353,0.00040829487],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996331,0.0013185986,0.0019322286,0.000092159185,0.00013518122,0.00019086056],"domain_scores_gemma":[0.9841928,0.01444297,0.00092255016,0.00014332213,0.0001822777,0.00011608416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006597293,0.00008203706,0.0015709031,0.000035336456,0.00003126858,8.464346e-7,0.00011081612,0.00008523908,0.00010759744],"category_scores_gemma":[0.015240211,0.00003344779,0.00017085958,0.00013699621,0.0004653004,0.000014506779,0.000044234188,0.0008324867,1.5294144e-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":[0.0011733148,0.000034716923,0.9884158,0.000011994192,0.00014817118,0.000026362366,0.00017896044,0.00023166598,7.6019774e-7,0.00016151286,0.00788248,0.0017342769],"study_design_scores_gemma":[0.0031998171,0.00020987912,0.9451292,0.00021698495,0.00009803262,0.00009618269,0.000119272954,0.00029886633,0.0000012762997,0.0014458623,0.04915401,0.000030585412],"about_ca_topic_score_codex":0.9459586,"about_ca_topic_score_gemma":0.99075407,"teacher_disagreement_score":0.0672826,"about_ca_system_score_codex":0.00012618951,"about_ca_system_score_gemma":0.0014714444,"threshold_uncertainty_score":0.99305487},"labels":[],"label_agreement":null},{"id":"W2163445888","doi":"10.1016/j.jclinepi.2005.12.007","title":"Peering at peer review revealed high degree of chance associated with funding of grant applications","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":70,"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 Children's Hospital; Royal Victoria Hospital; McGill University; Concordia University; Royal Victoria Regional Health Centre; McGill University Health Centre","funders":"","keywords":"Ranking (information retrieval); Peering; Consistency (knowledge bases); Peer review; Competition (biology); Computer science; Medicine; Psychology; Family medicine; Operations research; Political science; Information retrieval; Mathematics; World Wide Web; The Internet","score_opus":0.8991065089653524,"score_gpt":0.6875258783341166,"score_spread":0.21158063063123578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163445888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8961865,0.021371806,0.055125788,0.02331009,0.0007360134,0.00053904334,0.000067346205,0.000009069628,0.0026543906],"genre_scores_gemma":[0.98288137,0.006512315,0.0077826725,0.0004331908,0.0002404054,0.000006149685,0.0000048693646,0.000009536093,0.0021295191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9815195,0.003334501,0.00883089,0.00044795155,0.005344554,0.00052256125],"domain_scores_gemma":[0.7198996,0.23538652,0.019854719,0.0011254871,0.023085015,0.00064867234],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26742163,0.00013390939,0.0029517398,0.006507877,0.000083447565,0.000023204962,0.0016154458,0.00023022896,0.00018442751],"category_scores_gemma":[0.58142024,0.00007536149,0.0006608711,0.031324867,0.00048003666,0.00016993897,0.00029149288,0.00064255996,0.000015104227],"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":[0.00012085138,0.00032378887,0.92883897,0.00008223888,0.00008592678,0.000010628125,0.000005668323,0.0002567013,0.00016025179,0.002419074,0.03625795,0.03143796],"study_design_scores_gemma":[0.00081415515,0.00066462666,0.96765757,0.0004663775,0.000053187214,0.00003089973,0.000011290316,0.00040178845,0.000047575206,0.013108667,0.016648795,0.0000950822],"about_ca_topic_score_codex":0.00007457647,"about_ca_topic_score_gemma":0.000041909774,"teacher_disagreement_score":0.31399864,"about_ca_system_score_codex":0.00008322885,"about_ca_system_score_gemma":0.00023212084,"threshold_uncertainty_score":0.9892648},"labels":[],"label_agreement":null},{"id":"W2164288288","doi":"10.1016/j.jclinepi.2006.09.004","title":"A method is presented to plan the required sample size when estimating regression-based reference limits","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","cited_by":55,"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","keywords":"Sample size determination; Statistics; Limit (mathematics); Regression; Sample (material); Regression analysis; Confidence interval; Mathematics; Sampling (signal processing); Computer science; Linear regression; Population; Variable (mathematics); Medicine","score_opus":0.5645266792041199,"score_gpt":0.6160912501656063,"score_spread":0.05156457096148637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164288288","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":[0.11776923,0.0003864901,0.48263228,0.39669865,0.0014289021,0.0005444875,0.00003441149,0.000035054894,0.0004704908],"genre_scores_gemma":[0.12195069,0.000042931846,0.74142104,0.13405076,0.0023585577,0.00000397677,0.0000032768294,0.000021845533,0.00014694684],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9820907,0.008736517,0.0076244473,0.00045451854,0.0004982534,0.0005955597],"domain_scores_gemma":[0.14753073,0.8406392,0.007879162,0.0010557855,0.0014241588,0.0014709929],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10909892,0.00023246204,0.002859812,0.000066447,0.00013088125,0.0000152560115,0.00046292657,0.00053848553,0.00038995445],"category_scores_gemma":[0.74636304,0.000120782526,0.00071816647,0.00024501156,0.00020918305,0.000110829875,0.0000811731,0.0022575145,0.000033517917],"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":[0.036458317,0.0015410194,0.436863,0.00018008068,0.0010348193,0.00036542176,0.0005039901,0.0005564995,0.0006670017,0.00323896,0.09563916,0.42295173],"study_design_scores_gemma":[0.011045423,0.008558504,0.34594482,0.0014703657,0.0010620556,0.00022439314,0.00038241502,0.03446265,0.00016157019,0.029284822,0.5669743,0.00042871005],"about_ca_topic_score_codex":0.00014649142,"about_ca_topic_score_gemma":0.000054284956,"teacher_disagreement_score":0.83456,"about_ca_system_score_codex":0.00004305546,"about_ca_system_score_gemma":0.0005005921,"threshold_uncertainty_score":0.98079026},"labels":[],"label_agreement":null},{"id":"W2164957370","doi":"10.1016/j.jclinepi.2013.10.019","title":"The statistical significance of randomized controlled trial results is frequently fragile: a case for a Fragility Index","year":2014,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":736,"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; Western University; Ottawa Hospital; Health Sciences Centre; Canada Research Chairs; University of Manitoba; University of Ottawa; Manitoba Health; Hamilton Health Sciences; London Health Sciences Centre; McMaster University; Population Health Research Institute","funders":"Heart and Stroke Foundation of Canada","keywords":"Fragility; Randomized controlled trial; Statistical significance; Medicine; Index (typography); Sample size determination; Internal medicine; Statistics; Mathematics","score_opus":0.8635471367377616,"score_gpt":0.6857694704772885,"score_spread":0.1777776662604731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164957370","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031764983,0.7457857,0.23593825,0.002109077,0.0039799865,0.011468364,0.00032962396,0.0000017059623,0.0003555396],"genre_scores_gemma":[0.0005276387,0.9830716,0.010590128,0.0009355883,0.0026258107,0.00077894947,0.000011156835,0.00003254186,0.0014265368],"study_design_codex":"randomized_trial","study_design_gemma":"not_applicable","domain_scores_codex":[0.13084395,0.59177715,0.27043128,0.0018264885,0.004355904,0.0007652483],"domain_scores_gemma":[0.018673992,0.7549772,0.21704896,0.0037714464,0.004965544,0.00056282186],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.93262446,0.00091498904,0.18451042,0.00044945435,0.00021949495,0.00018687827,0.0041552302,0.0015261627,0.0010482573],"category_scores_gemma":[0.9878337,0.00027967192,0.07006512,0.00064563367,0.0017571584,0.00008919548,0.00017863944,0.0024943657,0.00011976687],"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":[0.4595084,0.00019056347,0.000019097943,0.001306135,0.00637812,0.000058580783,0.00002002948,0.00000954426,1.8467271e-9,0.005460846,0.108805224,0.41824347],"study_design_scores_gemma":[0.33995846,0.00059076125,0.0000024367775,0.000777382,0.0077136992,0.0002110091,0.000013502478,0.0025400005,2.3076205e-9,0.049343538,0.5987028,0.00014645224],"about_ca_topic_score_codex":0.000025918165,"about_ca_topic_score_gemma":0.000019495099,"teacher_disagreement_score":0.48989755,"about_ca_system_score_codex":0.000055847573,"about_ca_system_score_gemma":0.0018880948,"threshold_uncertainty_score":0.99996555},"labels":[],"label_agreement":null},{"id":"W2165037395","doi":"10.1016/j.jclinepi.2004.03.012","title":"New ICD-10 version of the Charlson comorbidity index predicted in-hospital mortality","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":2484,"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":"Generalizability theory; ICD-10; Medicine; Comorbidity; Charlson comorbidity index; Coding (social sciences); Diagnosis code; Population; Statistics; Internal medicine; Psychiatry","score_opus":0.48288660302700526,"score_gpt":0.5947186039689906,"score_spread":0.11183200094198531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165037395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94768906,0.00008648602,0.004944015,0.04049573,0.0052183243,0.000315393,0.000010379819,0.000011136707,0.0012294934],"genre_scores_gemma":[0.99208814,0.0005265938,0.00083836424,0.0051196003,0.001293906,0.0000022787256,0.000004703384,0.0000062671934,0.00012016792],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98749495,0.0046759625,0.0068920464,0.00013892564,0.0003763135,0.00042182187],"domain_scores_gemma":[0.9793194,0.013397728,0.0060838484,0.00033278653,0.00036250087,0.0005037694],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03103334,0.000113648726,0.0015084605,0.00008887474,0.0001568419,8.996577e-7,0.00040457654,0.00076542364,0.00061926333],"category_scores_gemma":[0.09109595,0.00006683288,0.00035418314,0.00020810215,0.00020075572,0.00013860251,0.00012459756,0.0031475446,0.000048866423],"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":[0.00033539714,0.00014785487,0.9593135,0.00014808345,0.000024428346,0.0000026159755,0.0003922533,0.00026585392,9.2431753e-7,0.0015140419,0.03519277,0.002662275],"study_design_scores_gemma":[0.0034285926,0.00074000575,0.9658185,0.00067162246,0.000023851491,0.0000026732298,0.00013848611,0.0004404386,0.0000018877362,0.011322005,0.017359678,0.000052262487],"about_ca_topic_score_codex":0.0007799472,"about_ca_topic_score_gemma":0.00014584507,"teacher_disagreement_score":0.060062606,"about_ca_system_score_codex":0.00016010656,"about_ca_system_score_gemma":0.002145845,"threshold_uncertainty_score":0.99915224},"labels":[],"label_agreement":null},{"id":"W2166539157","doi":"10.1016/j.jclinepi.2011.11.008","title":"Discrete choice experiment produced estimates of acceptable risks of therapeutic options in cancer patients with febrile neutropenia","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Neutropenia and Cancer Infections","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; SickKids Foundation; University of New Brunswick; University Health Network; Hospital for Sick Children; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Febrile neutropenia; Neutropenia; Confidence interval; Outpatient visits; Outpatient clinic; Intensive care unit; Inpatient care; Emergency medicine; Pediatrics; Intensive care medicine; Internal medicine; Health care; Chemotherapy","score_opus":0.3404288998742627,"score_gpt":0.5537253859879839,"score_spread":0.2132964861137212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166539157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995315,0.0019476175,0.00022967935,0.0013401605,0.0006564104,0.00031561134,0.000008329952,0.0000043253217,0.00018282187],"genre_scores_gemma":[0.9962275,0.00072214974,0.0021184331,0.0004341268,0.00042111598,0.000026207086,0.0000032115597,0.000016391547,0.00003085618],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961225,0.00072984496,0.002501069,0.0001638893,0.00016828487,0.00031442475],"domain_scores_gemma":[0.993967,0.0031166382,0.0021037832,0.00024547637,0.00034437372,0.00022276097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029833224,0.0001400565,0.0018405718,0.00011686393,0.000027743929,0.0000017985097,0.00013209955,0.00013279798,0.00028741005],"category_scores_gemma":[0.0029981155,0.00008493853,0.00028119938,0.00019244787,0.00024415995,0.00018569846,0.000039458355,0.00053903967,0.000002315287],"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":[0.0010615373,0.0011513953,0.99166167,0.000050364295,0.00024119763,7.783084e-7,0.000075022166,0.00049075787,0.0013083983,0.00020750829,0.00029915583,0.0034522114],"study_design_scores_gemma":[0.0032571577,0.002225166,0.99010456,0.00022489828,0.00029015195,0.000012268056,0.00003622345,0.00003564714,0.0021890234,0.000112193564,0.0014369979,0.00007574391],"about_ca_topic_score_codex":0.0005235475,"about_ca_topic_score_gemma":0.000045945853,"teacher_disagreement_score":0.0033764676,"about_ca_system_score_codex":0.0000635482,"about_ca_system_score_gemma":0.00024093015,"threshold_uncertainty_score":0.3589241},"labels":[],"label_agreement":null},{"id":"W2168090621","doi":"10.1016/j.jclinepi.2015.05.003","title":"A longitudinal model for disease progression was developed and applied to multiple sclerosis","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":27,"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 Hospital","funders":"Health Technology Assessment Programme; Canadian Institutes of Health Research; EMD Serono; European Committee for Treatment and Research in Multiple Sclerosis; Multiple Sclerosis Trust; Multiple Sclerosis Society; Multiple Sclerosis Society of Canada; IC Design Education Center; Teva Pharmaceutical Industries; National Institute for Health and Care Research; U.S. Department of Veterans Affairs; National Multiple Sclerosis Society; Michael Smith Health Research BC; Medical Research Council; Biogen","keywords":"Expanded Disability Status Scale; Medicine; Cohort; Observational study; Confidence interval; Cohort study; Multiple sclerosis; Autocorrelation; Physical therapy; Statistics; Demography; Internal medicine; Psychiatry; Mathematics","score_opus":0.7008445152096974,"score_gpt":0.5604157997515393,"score_spread":0.14042871545815805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168090621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85395116,0.0008784868,0.1121384,0.031362843,0.00034252112,0.0011867356,0.000019350508,0.000021599024,0.0000988917],"genre_scores_gemma":[0.82944405,0.00062886666,0.16694972,0.0021390037,0.0006666241,0.00007278174,0.0000041538906,0.000019901327,0.000074922114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99541736,0.00061391224,0.002703623,0.000391176,0.0003689723,0.0005049888],"domain_scores_gemma":[0.9804941,0.0147510795,0.0010384507,0.00027379623,0.0010047598,0.0024378179],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0173198,0.00019611295,0.0022650787,0.0001568604,0.0000840718,0.000008606153,0.00017566979,0.00019169679,0.0000047534686],"category_scores_gemma":[0.20309024,0.00012478295,0.00036185706,0.00012246735,0.00031949222,0.000071610506,0.00023281606,0.00055223895,0.000008477522],"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":[0.018748814,0.00050893694,0.8557734,0.00014058177,0.00026068877,0.000012630495,0.00016093918,0.0012656479,0.00022940898,0.00020071852,0.02575266,0.096945606],"study_design_scores_gemma":[0.0086758975,0.0016040285,0.89735985,0.00037891982,0.0001482461,0.000016371067,0.00005969221,0.08724746,0.000023902041,0.0016670343,0.0026745112,0.0001440942],"about_ca_topic_score_codex":0.0000035909434,"about_ca_topic_score_gemma":0.000010952307,"teacher_disagreement_score":0.18577044,"about_ca_system_score_codex":0.000070063346,"about_ca_system_score_gemma":0.00065685913,"threshold_uncertainty_score":0.8036225},"labels":[],"label_agreement":null},{"id":"W2168764238","doi":"10.1016/j.jclinepi.2007.10.017","title":"Few systematic reviews exist documenting the extent of bias: a systematic review","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":82,"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 of Population and Public Health; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research; Health Canada; University of Ottawa","keywords":"Systematic review; Systematic error; Medicine; MEDLINE; Political science; Statistics; Mathematics","score_opus":0.9687098018047212,"score_gpt":0.72325904031448,"score_spread":0.24545076149024125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168764238","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010362075,0.981248,0.0025643231,0.00096862926,0.0022119367,0.012161349,0.000012195694,0.0000035096841,0.0008289974],"genre_scores_gemma":[0.0000027085127,0.9899827,0.0030105938,0.00262914,0.0007859011,0.00042932213,0.000005083595,0.000052608968,0.0031019],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.07177786,0.60346735,0.31587246,0.0015694591,0.006559293,0.00075357757],"domain_scores_gemma":[0.03807944,0.54157525,0.40611014,0.009856437,0.003789875,0.0005888295],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8996747,0.0015758609,0.24057883,0.0008788915,0.00021953539,0.00018677521,0.011728721,0.00096525106,0.0013238182],"category_scores_gemma":[0.97153974,0.00045581162,0.08575497,0.0028886746,0.0006345577,0.00026953078,0.0006239556,0.0029612503,0.0034525702],"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":[0.0000023374985,0.00009138801,0.000046968547,0.8810595,0.0026063216,0.00002942243,0.00002534814,0.0000013394731,2.133606e-9,0.00075417943,0.08293914,0.032444008],"study_design_scores_gemma":[0.00008029199,0.000111494504,0.000004334756,0.55520463,0.017704193,0.0016774959,0.000030162972,0.000022630864,1.4182971e-9,0.00096287765,0.4240045,0.00019737497],"about_ca_topic_score_codex":0.000005136746,"about_ca_topic_score_gemma":0.0000036156164,"teacher_disagreement_score":0.34106535,"about_ca_system_score_codex":0.00012525625,"about_ca_system_score_gemma":0.00094520266,"threshold_uncertainty_score":0.99978936},"labels":[],"label_agreement":null},{"id":"W2170538328","doi":"10.1016/j.jclinepi.2010.07.012","title":"Minimal change is sensitive, less specific to recovery: a diagnostic testing approach to interpretability","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sports injuries and prevention","field":"Medicine","cited_by":59,"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 Work & Health; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Interpretability; Medicine; Statistics; Computer science; Mathematics; Machine learning","score_opus":0.3751571079880765,"score_gpt":0.49018043183914783,"score_spread":0.11502332385107134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170538328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9698079,0.00007367769,0.009343267,0.015226797,0.0029011695,0.00046326857,0.000012123305,0.000013887823,0.0021578784],"genre_scores_gemma":[0.8880516,0.00008292601,0.09108386,0.016662529,0.003992192,0.000011285196,0.0000035231596,0.000018203275,0.00009382595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946821,0.0010255972,0.0033195494,0.00041385996,0.00018465745,0.00037427287],"domain_scores_gemma":[0.9657168,0.031252217,0.001340816,0.00041935526,0.0005150173,0.0007558093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020708231,0.00017948603,0.0021188802,0.00015116407,0.00004355268,0.000007645142,0.00017229984,0.00036365347,0.0001647392],"category_scores_gemma":[0.18596946,0.00013238227,0.00062397483,0.00022701191,0.0001616374,0.00008895542,0.00011356099,0.0014641439,0.00004332418],"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":[0.0019161851,0.0006541464,0.7554196,0.00005466569,0.00009910311,0.00006540339,0.00031726708,0.000009058662,0.00019946828,0.00024260658,0.014264683,0.22675782],"study_design_scores_gemma":[0.00065172074,0.0028750864,0.9543945,0.00024294373,0.00009297487,0.0005301864,0.000120599325,0.00018503187,0.000036189445,0.0010080506,0.03973293,0.00012975502],"about_ca_topic_score_codex":0.000045009943,"about_ca_topic_score_gemma":0.000011657265,"teacher_disagreement_score":0.22662808,"about_ca_system_score_codex":0.000033337947,"about_ca_system_score_gemma":0.00011792779,"threshold_uncertainty_score":0.82088745},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2171762906","doi":"10.1016/j.jclinepi.2010.02.006","title":"The COSMIN study reached international consensus on taxonomy, terminology, and definitions of measurement properties for health-related patient-reported outcomes","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":4442,"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":"Terminology; Taxonomy (biology); Delphi method; Confusion; Delphi; Consistency (knowledge bases); Management science; Medicine; Psychology; Applied psychology; Computer science; Artificial intelligence; Engineering; Linguistics; Ecology","score_opus":0.8170932433584581,"score_gpt":0.5349041107663476,"score_spread":0.28218913259211054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171762906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9132114,0.00016675061,0.0002725753,0.081946425,0.0033409519,0.00089696195,0.000008605174,0.0000051671286,0.00015116922],"genre_scores_gemma":[0.995866,0.000117223084,0.002555033,0.001294475,0.0000896816,0.000046118457,5.359728e-7,0.0000051414136,0.000025807873],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98165023,0.005626863,0.010877745,0.00040365473,0.0011377146,0.00030376832],"domain_scores_gemma":[0.9297979,0.0577233,0.009249949,0.0006048247,0.0024000504,0.00022400494],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11914837,0.00015795481,0.0016898619,0.00015018943,0.00022250338,0.000025479645,0.000605055,0.0001784293,0.000022042272],"category_scores_gemma":[0.40713936,0.00007446431,0.0004844949,0.000091933776,0.000882184,0.000051908795,0.00010140854,0.00081549096,0.000003880514],"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":[0.0012842019,0.0016583,0.8948935,0.0000067261776,0.0005431209,0.0000048633447,0.00022945566,0.00007202853,0.00010976105,0.0029336,0.010192911,0.088071495],"study_design_scores_gemma":[0.0035620073,0.0060702427,0.8864807,0.000069725815,0.0000838946,0.00006129876,0.001801442,0.00033894306,0.000030487563,0.079168476,0.022213036,0.00011974064],"about_ca_topic_score_codex":0.000035300724,"about_ca_topic_score_gemma":0.00021169493,"teacher_disagreement_score":0.287991,"about_ca_system_score_codex":0.00004022543,"about_ca_system_score_gemma":0.0003749423,"threshold_uncertainty_score":0.9070221},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2174135902","doi":"10.1016/j.jclinepi.2015.08.027","title":"Sensitivity subgroup analysis based on single-center vs. multi-center trial status when interpreting meta-analyses pooled estimates: the logical way forward","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Health Network; University of Toronto; McMaster University","funders":"","keywords":"Meta-analysis; Confidence interval; Odds ratio; Medicine; Random effects model; Randomized controlled trial; Single Center; Subgroup analysis; Pooled variance; Strictly standardized mean difference; Clinical trial; Center (category theory); Statistics; Meta-regression; Mean difference; Coverage probability; Internal medicine; Mathematics","score_opus":0.9608484217637977,"score_gpt":0.6965283431786208,"score_spread":0.2643200785851769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174135902","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":[0.00014843667,0.72616714,0.26241633,0.0047117304,0.0032262134,0.0025089153,0.000278468,0.000013511111,0.00052924146],"genre_scores_gemma":[0.009666718,0.82836336,0.12650932,0.028131088,0.0047994666,0.00027874514,0.00035360866,0.00026728143,0.0016303807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.54264635,0.3543841,0.09308664,0.002576117,0.0060928417,0.0012139708],"domain_scores_gemma":[0.24005666,0.60223657,0.14299971,0.0076303007,0.005312398,0.0017643702],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.7243409,0.0018425006,0.11223622,0.0020299088,0.0002253508,0.0006765653,0.0046128174,0.0016611874,0.005513564],"category_scores_gemma":[0.83150166,0.0005900529,0.110412836,0.0025174401,0.0007612288,0.00028634127,0.00065410323,0.00421068,0.0009524629],"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":[0.006360332,0.005565469,0.01625099,0.0010379669,0.22580813,0.00035352242,0.000110555986,0.0036759165,9.284779e-8,0.00011226915,0.11802216,0.6227026],"study_design_scores_gemma":[0.006005485,0.0013863444,0.00020126058,0.0007945669,0.19129266,0.00009595823,0.000039114446,0.040297862,2.4232941e-8,0.00080746325,0.75861126,0.00046798986],"about_ca_topic_score_codex":0.000025093294,"about_ca_topic_score_gemma":0.00009307968,"teacher_disagreement_score":0.6405891,"about_ca_system_score_codex":0.0002943156,"about_ca_system_score_gemma":0.00076417695,"threshold_uncertainty_score":0.9998254},"labels":[],"label_agreement":null},{"id":"W2177453088","doi":"10.1016/j.jclinepi.2015.10.019","title":"Deficiencies in reporting of statistical methodology in recent randomized trials of nonpharmacologic pain treatments: ACTTION systematic review","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University","funders":"U.S. Food and Drug Administration","keywords":"Medicine; Physical therapy; Randomized controlled trial; Missing data; Clinical trial; Systematic review; Massage; MEDLINE; Interpretability; Alternative medicine; Surgery; Internal medicine; Statistics","score_opus":0.9913673775642305,"score_gpt":0.8053903285175825,"score_spread":0.18597704904664802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177453088","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028352075,0.92998946,0.062795766,0.0005562094,0.0009615505,0.0055174436,0.000030059993,0.0000011850366,0.000120005476],"genre_scores_gemma":[0.000026573267,0.9509587,0.04814344,0.0004632348,0.0001159228,0.0001842966,0.000014979183,0.000016165524,0.000076628814],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.0055403393,0.6752822,0.3156575,0.0008363673,0.0023071386,0.00037643514],"domain_scores_gemma":[0.0020646022,0.61116636,0.382346,0.0015071072,0.0026781007,0.0002378349],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9927634,0.0007635633,0.2854307,0.0017164708,0.000020071955,0.000021925798,0.0024039687,0.0010352279,0.0016479528],"category_scores_gemma":[0.9983926,0.00028124836,0.025045652,0.0022850272,0.0005952787,0.00012173399,0.00020005528,0.0016059434,0.000046278186],"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":[0.0013277777,0.00054731435,0.00074003637,0.41894427,0.0030421917,0.00010804275,0.000052427153,0.000049094288,1.527627e-7,0.0010948201,0.00629776,0.5677961],"study_design_scores_gemma":[0.026879692,0.0015582428,0.00014996034,0.7374532,0.07259333,0.0007180694,0.00034182094,0.0016661949,1.5006401e-7,0.060190182,0.09779821,0.00065089506],"about_ca_topic_score_codex":0.00002150609,"about_ca_topic_score_gemma":0.000011273538,"teacher_disagreement_score":0.5671452,"about_ca_system_score_codex":0.00022907148,"about_ca_system_score_gemma":0.0019044008,"threshold_uncertainty_score":0.99996394},"labels":[],"label_agreement":null},{"id":"W2177595123","doi":"10.1016/j.jclinepi.2015.07.009","title":"Patient-centered rapid reviews will drive local decision making: commentary on Hartling et al.","year":2015,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Bruyère; University of Ottawa","funders":"","keywords":"Popularity; Summit; Scopus; Health technology; Stakeholder; Medicine; MEDLINE; Political science; Public relations; Management science; Psychology; Health care; Economics; Geography; Social psychology","score_opus":0.7328901589764846,"score_gpt":0.587424419724486,"score_spread":0.14546573925199857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177595123","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":[0.0010742352,0.013506545,0.031877287,0.94102895,0.01081932,0.00078126765,0.00028653993,0.000017554648,0.00060831115],"genre_scores_gemma":[0.00092628377,0.011555586,0.017006448,0.962465,0.007722623,0.000023821165,0.00014759148,0.000087507564,0.00006515478],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9283691,0.023034915,0.046198837,0.0011605411,0.00030269966,0.00093389966],"domain_scores_gemma":[0.83204985,0.10989069,0.055800464,0.0012712214,0.0004014771,0.00058629736],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.25129917,0.0006226035,0.012005267,0.00069437,0.00012275687,0.000040385454,0.0009736373,0.0017764913,0.00066834106],"category_scores_gemma":[0.24210341,0.00058423914,0.0021213104,0.00014104092,0.00036279074,0.00047345008,0.0002181919,0.00649694,0.0017355088],"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":[0.00022806879,0.00017961753,0.0091622565,0.00015576463,0.00025563542,0.000052675547,0.000111683104,0.00028776322,8.528515e-9,0.00055162946,0.9765494,0.01246553],"study_design_scores_gemma":[0.0016586174,0.0017648247,0.0010477349,0.0022082066,0.000039622002,0.00006653784,0.000054447977,0.0014340915,2.6217538e-8,0.029484905,0.9618072,0.00043378674],"about_ca_topic_score_codex":0.000056177305,"about_ca_topic_score_gemma":0.000015049076,"teacher_disagreement_score":0.09631926,"about_ca_system_score_codex":0.00096731406,"about_ca_system_score_gemma":0.00043424967,"threshold_uncertainty_score":0.9996609},"labels":[],"label_agreement":null},{"id":"W2180071050","doi":"10.1016/j.jclinepi.2015.08.026","title":"A standardized approach to estimating survival statistics for population-based cystic fibrosis registry cohorts","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cystic Fibrosis Research Advances","field":"Medicine","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":"University of British Columbia; Hospital for Sick Children; University of Toronto; St. Michael's Hospital","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Canadian Institutes of Health Research","keywords":"Medicine; Statistics; Population; Cystic fibrosis; Cohort; Internal medicine; Mathematics; Environmental health","score_opus":0.2570000937225419,"score_gpt":0.5294371686405824,"score_spread":0.27243707491804053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180071050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047265805,0.00020402104,0.9476119,0.0027381487,0.0012349389,0.0005904919,0.0002036531,0.000019820134,0.00013116852],"genre_scores_gemma":[0.14073418,0.0000074049008,0.8568748,0.0008796109,0.0012772138,0.000021026952,0.0000999497,0.000028165816,0.00007760691],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99211574,0.0020913084,0.004255003,0.00036083508,0.0006546922,0.0005224317],"domain_scores_gemma":[0.9311996,0.063169695,0.002267406,0.00040047764,0.001582967,0.0013798664],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03081842,0.00020039332,0.0031571947,0.00016314036,0.00006470549,0.000015539075,0.00022931086,0.00024775622,0.000021101507],"category_scores_gemma":[0.5521142,0.00014783042,0.00046381156,0.00018742608,0.00019169778,0.00007313332,0.00005008393,0.00069866923,0.000007440318],"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":[0.028413562,0.00084897777,0.7761088,0.000903562,0.0004418789,0.00007493487,0.000049658465,0.07885235,0.00007219401,0.0040288772,0.085679956,0.024525262],"study_design_scores_gemma":[0.01958292,0.01325628,0.49484035,0.0010476705,0.0006725014,0.00034424648,0.00016810889,0.40260267,0.000018451265,0.042383518,0.024601074,0.00048218883],"about_ca_topic_score_codex":0.000056698806,"about_ca_topic_score_gemma":0.000007703275,"teacher_disagreement_score":0.5212957,"about_ca_system_score_codex":0.00018202171,"about_ca_system_score_gemma":0.0015221662,"threshold_uncertainty_score":0.99797636},"labels":[],"label_agreement":null},{"id":"W2192085918","doi":"10.1016/j.jclinepi.2015.11.015","title":"Reporting of consent rates in critical care studies: room for improvement","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Children's Hospital of Eastern Ontario; Wilfrid Laurier University; University of Ottawa","funders":"","keywords":"Generalizability theory; Medicine; Interquartile range; Informed consent; Observational study; Confidence interval; Randomized controlled trial; Consolidated Standards of Reporting Trials; Intensive care unit; Population; Family medicine; External validity; Intensive care medicine; Alternative medicine; Internal medicine; Psychology; Environmental health","score_opus":0.9759288119078092,"score_gpt":0.8372022330359987,"score_spread":0.1387265788718105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2192085918","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":[0.000222175,0.988334,0.00026660773,0.007284046,0.0024920984,0.0011785307,0.000026333764,0.0000054462257,0.00019078534],"genre_scores_gemma":[0.00029790134,0.980068,0.016118553,0.0011172253,0.002135944,0.000055925833,0.000013141314,0.000050717437,0.00014254925],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9253094,0.0085937455,0.063280106,0.00087445875,0.0010516323,0.00089063565],"domain_scores_gemma":[0.034656156,0.91071147,0.041686364,0.0010335314,0.010860425,0.0010520665],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3252852,0.0004163543,0.025924074,0.00037161197,0.000033765613,0.0000044752524,0.0005419647,0.0026677768,0.000023462697],"category_scores_gemma":[0.9822411,0.00025380094,0.0043729013,0.00024655298,0.0014642237,0.00003961948,0.00038979764,0.00898625,0.0000057009574],"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":[0.00092897227,0.00071526977,0.011237257,0.1711685,0.0015232654,0.0005535045,0.00011954574,0.0000036850543,3.0957077e-7,0.004750555,0.005111585,0.80388755],"study_design_scores_gemma":[0.0038746458,0.016746443,0.00035180937,0.123368174,0.0034013991,0.00049637706,0.001456237,0.000023778628,0.0000013676158,0.09556475,0.7543715,0.00034349138],"about_ca_topic_score_codex":0.000017738106,"about_ca_topic_score_gemma":0.00006640797,"teacher_disagreement_score":0.9021177,"about_ca_system_score_codex":0.0004434277,"about_ca_system_score_gemma":0.012827544,"threshold_uncertainty_score":0.9999914},"labels":[],"label_agreement":null},{"id":"W2195700003","doi":"10.1016/j.jclinepi.2015.11.002","title":"Systematic reviews experience major limitations in reporting absolute effects","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":66,"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","funders":"","keywords":"Absolute (philosophy); Medicine; MEDLINE; Philosophy; Epistemology; Political science","score_opus":0.9842462796651894,"score_gpt":0.7535935175624867,"score_spread":0.2306527621027027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2195700003","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040553965,0.9866152,0.004308511,0.00035546336,0.0037671225,0.0033656473,0.0000026390671,0.0000028823995,0.0015419831],"genre_scores_gemma":[0.00001990741,0.97946227,0.015700452,0.00058568886,0.0009106213,0.0002575905,0.0000035000335,0.000032332275,0.0030276678],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.114589304,0.49032784,0.3882818,0.0017890711,0.004259295,0.00075269333],"domain_scores_gemma":[0.021933524,0.5408783,0.42913413,0.004711994,0.0025683476,0.0007737274],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.91947705,0.00092380436,0.14492366,0.0010449452,0.00007702979,0.00019380938,0.00484994,0.0011353941,0.00038560288],"category_scores_gemma":[0.9929822,0.00035668132,0.030433485,0.0023595653,0.00025375132,0.00034252138,0.0003297361,0.0026141957,0.0029974577],"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":[0.000005521222,0.00012435322,0.0015842731,0.12339189,0.0007464683,0.00023320754,0.00017050123,0.000010929418,7.995716e-9,0.00057104474,0.054236528,0.81892526],"study_design_scores_gemma":[0.00018282978,0.00016813779,0.0003604741,0.10058214,0.0025206127,0.00072499306,0.00008530351,0.00029586593,1.4359203e-9,0.0056760493,0.88914406,0.00025950844],"about_ca_topic_score_codex":0.000004677865,"about_ca_topic_score_gemma":0.000023267783,"teacher_disagreement_score":0.8349076,"about_ca_system_score_codex":0.00016547897,"about_ca_system_score_gemma":0.0010911614,"threshold_uncertainty_score":0.99988854},"labels":[],"label_agreement":null},{"id":"W2202742746","doi":"10.1016/j.jclinepi.2015.10.020","title":"Text mining describes the use of statistical and epidemiological methods in published medical research","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Toronto General Hospital; North York General Hospital; University of Toronto","funders":"Medical Research Council","keywords":"Epidemiology; Biostatistics; Medicine; Statistical hypothesis testing; Statistics; Descriptive statistics; Epidemiological method; Sample size determination; Medical statistics; Sample (material); Delphi method; MEDLINE; Data science; Computer science; Pathology; Mathematics","score_opus":0.9898631697246477,"score_gpt":0.792012596539463,"score_spread":0.19785057318518473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2202742746","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32746947,0.0036256937,0.5866049,0.07973143,0.0012353817,0.00041347847,0.0000076751385,0.000002064487,0.0009099288],"genre_scores_gemma":[0.29999098,0.00076785317,0.6935791,0.004652806,0.00060647697,0.0000089069645,0.0000014566039,0.000011351017,0.00038112252],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.09778567,0.8103329,0.082931794,0.0012867813,0.006753445,0.0009094331],"domain_scores_gemma":[0.015138672,0.95767033,0.019405236,0.0020425287,0.0043932446,0.0013500098],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.948664,0.00024954046,0.015514707,0.00060565077,0.000071511626,0.00015069738,0.0027324492,0.0006966515,0.0028137807],"category_scores_gemma":[0.9950779,0.00008398783,0.0019081179,0.0013116658,0.0023566154,0.00044446072,0.0006492807,0.002679728,0.000060113587],"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":[0.00014265746,0.00011744732,0.6060624,0.000010975542,0.00012994591,0.000039553353,0.00013055382,0.00013430446,0.0000011040532,0.023427116,0.2261581,0.14364585],"study_design_scores_gemma":[0.00075550465,0.0008470935,0.4799538,0.00010913126,0.00009918258,0.00026748242,0.00088097714,0.053306777,4.413564e-7,0.29182774,0.17184392,0.000107957836],"about_ca_topic_score_codex":0.00006873447,"about_ca_topic_score_gemma":0.000060841154,"teacher_disagreement_score":0.2684006,"about_ca_system_score_codex":0.000032028547,"about_ca_system_score_gemma":0.00073427166,"threshold_uncertainty_score":0.99962115},"labels":[],"label_agreement":null},{"id":"W2224430732","doi":"10.1016/j.jclinepi.2015.10.022","title":"A Rasch analysis of the Brief Pain Inventory Interference subscale reveals three dimensions and an age bias","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pain Management and Opioid Use","field":"Medicine","cited_by":20,"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; Western University","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Brief Pain Inventory; Differential item functioning; Population; Psychology; Clinical psychology; Observational study; Item response theory; Psychometrics; Statistics; Medicine; Chronic pain; Psychiatry; Developmental psychology; Mathematics","score_opus":0.3084529204911649,"score_gpt":0.4722531696435159,"score_spread":0.16380024915235097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2224430732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797312,0.00042138586,0.008686726,0.010623077,0.00026357203,0.00011606294,0.0000027308868,0.000005796468,0.00014947016],"genre_scores_gemma":[0.9912075,0.0010472004,0.0013453679,0.00578404,0.0002682097,0.0000012775298,0.0000010815958,0.0000072737166,0.0003380501],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9907092,0.0058955722,0.0027861656,0.0002212005,0.00016596346,0.00022192382],"domain_scores_gemma":[0.972358,0.024489675,0.002131969,0.0005192935,0.00018846973,0.00031260957],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039416928,0.00011931316,0.00204234,0.00021872882,0.000035571265,0.0000027195208,0.00026928447,0.0001935601,0.00009191334],"category_scores_gemma":[0.0945437,0.00005336385,0.00077574555,0.0002964567,0.00057801575,0.00007172176,0.00013147712,0.00042393443,0.0000015841038],"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":[0.0002927107,0.00015189723,0.984209,0.000019999188,0.0008943217,0.000021891803,0.00003685979,0.000005133511,0.00033546533,0.0016634252,0.0035167416,0.008852575],"study_design_scores_gemma":[0.0010893128,0.00086041546,0.9816867,0.00028062926,0.0013054468,0.000004215493,0.00002687628,0.0011717532,0.000005868098,0.01176178,0.0017484177,0.000058602138],"about_ca_topic_score_codex":0.000029261115,"about_ca_topic_score_gemma":0.0001809133,"teacher_disagreement_score":0.055126775,"about_ca_system_score_codex":0.000018461633,"about_ca_system_score_gemma":0.00007094653,"threshold_uncertainty_score":0.9891224},"labels":[],"label_agreement":null},{"id":"W2224995371","doi":"10.1016/j.jclinepi.2015.11.017","title":"A guide for health professionals to interpret and use recommendations in guidelines developed with the GRADE approach","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":174,"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":"Grading (engineering); Trustworthiness; Certainty; Medicine; Evidence-based medicine; Equity (law); Preference; MEDLINE; Actuarial science; Psychology; Alternative medicine; Business; Social psychology; Economics","score_opus":0.8669620622800094,"score_gpt":0.740337490174598,"score_spread":0.12662457210541134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2224995371","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":[0.000032528595,0.49393457,0.07175183,0.43042472,0.00086521165,0.0028910856,0.00007515955,0.000008768011,0.000016140068],"genre_scores_gemma":[0.0000020094074,0.70773834,0.23151298,0.0588599,0.0012243253,0.00013746967,0.00006115374,0.00003926364,0.0004245792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9700315,0.009430327,0.019214874,0.0005788189,0.00025978676,0.00048468343],"domain_scores_gemma":[0.7379862,0.24909155,0.010157943,0.00054396054,0.0015956841,0.0006246602],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.081591554,0.00038130587,0.0074327383,0.00033311348,0.000081784354,0.0000143100515,0.00035527567,0.00048717277,0.000023894785],"category_scores_gemma":[0.5391973,0.00016098362,0.00082573656,0.00029719988,0.00018045573,0.00019060254,0.00018564849,0.0015951322,0.0000058806663],"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":[0.00039333856,0.00015820246,0.0005736334,0.0008878189,0.00025373523,0.0000031468908,0.000028698501,9.0733516e-7,1.609467e-8,0.00015620564,0.33249587,0.6650484],"study_design_scores_gemma":[0.0020487746,0.0016419068,0.00074044854,0.020365883,0.00051520916,0.00046019553,0.000099472076,0.00003260544,9.473268e-9,0.00033624988,0.9735993,0.00015990653],"about_ca_topic_score_codex":0.000052661475,"about_ca_topic_score_gemma":0.00017826026,"teacher_disagreement_score":0.6648885,"about_ca_system_score_codex":0.00016566322,"about_ca_system_score_gemma":0.0038690274,"threshold_uncertainty_score":0.94569474},"labels":[],"label_agreement":null},{"id":"W2230178933","doi":"10.1016/j.jclinepi.2015.11.016","title":"Reporting quality of N-of-1 trials published between 1985 and 2013: a systematic review","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Medicine; Consolidated Standards of Reporting Trials; Clinical trial; Confidence interval; Family medicine; MEDLINE; Systematic review; Internal medicine","score_opus":0.9878246598447115,"score_gpt":0.7945127383159708,"score_spread":0.19331192152874066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2230178933","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028368924,0.98767346,0.0060969726,0.0021600642,0.0010904333,0.0025929632,0.00006501169,0.0000016418287,0.00029111002],"genre_scores_gemma":[0.000033118256,0.9931115,0.0049206107,0.0003419047,0.00087293173,0.00002920456,0.0000056070085,0.00002284032,0.00066226436],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.020911556,0.5154667,0.4581798,0.0011870803,0.0038642683,0.00039060073],"domain_scores_gemma":[0.0024915086,0.4955183,0.49408045,0.0037457529,0.0037371104,0.00042687115],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97966,0.0008044986,0.29152423,0.00088157423,0.000047445625,0.00008709629,0.004130367,0.0012368334,0.0020821714],"category_scores_gemma":[0.9964891,0.0002566618,0.051544085,0.0011998141,0.0004981492,0.0003169257,0.00043218254,0.0015008777,0.0001636244],"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":[0.000007996712,0.000044823348,0.0069671017,0.6929696,0.0041287364,0.000006129105,0.0000060234715,8.113509e-8,2.0116442e-8,0.0006973073,0.036482174,0.25868997],"study_design_scores_gemma":[0.00027044996,0.00020935008,0.00075114367,0.60551834,0.019172264,0.00016855409,0.000009871961,0.0000022000477,1.2850679e-8,0.01201466,0.36165747,0.00022567871],"about_ca_topic_score_codex":0.0000146330185,"about_ca_topic_score_gemma":0.0000028864051,"teacher_disagreement_score":0.3251753,"about_ca_system_score_codex":0.00003708602,"about_ca_system_score_gemma":0.0011060477,"threshold_uncertainty_score":0.99998856},"labels":[],"label_agreement":null},{"id":"W2230898161","doi":"10.1016/j.jclinepi.2015.05.010","title":"The new paradigm: from ‘bench to bedside’ to the translational research ‘valleys of death’","year":2015,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Biomedical Ethics and Regulation","field":"Medicine","cited_by":4,"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":"University of Ottawa","keywords":"Translational science; Translational research; Translational medicine; Population; Systematic review; Guideline; MEDLINE; Medicine; Scopus; Clinical trial; Cochrane Library; Clinical Practice; Population health; Alternative medicine; Library science; Family medicine; Political science; Environmental health; Pathology; Computer science","score_opus":0.5238057286169494,"score_gpt":0.6185851350042957,"score_spread":0.09477940638734628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2230898161","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006416719,0.0043372246,0.0057769837,0.586698,0.4017169,0.00045205178,0.000044907327,0.0000047219933,0.00032758297],"genre_scores_gemma":[0.004839858,0.0036458934,0.006449435,0.0035162356,0.97998995,0.0000075996018,0.00008669069,0.000039607283,0.0014247346],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98124534,0.008048272,0.0067261066,0.00046485112,0.0029226681,0.0005927376],"domain_scores_gemma":[0.6345235,0.35345393,0.003783746,0.0011941753,0.0044900845,0.002554546],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.114602655,0.00024650127,0.0029853908,0.0002172569,0.00016263712,0.000015255312,0.0010180731,0.0029182744,0.00010516758],"category_scores_gemma":[0.27500713,0.00010943551,0.00096958585,0.00038186365,0.0012768939,0.000033121763,0.00016407152,0.0076393955,0.000056424855],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00218491,0.0000994969,0.00046604048,0.000022035694,0.0003963695,0.000013405167,0.00018658067,0.000116523275,0.000005379719,0.004528398,0.96215963,0.029821213],"study_design_scores_gemma":[0.0012507258,0.0020450847,0.009820269,0.0003611397,0.00017719083,0.000010432082,0.000027414728,0.00012506045,0.0000012729176,0.18751165,0.798589,0.00008079205],"about_ca_topic_score_codex":0.0006239332,"about_ca_topic_score_gemma":0.0003315383,"teacher_disagreement_score":0.58318174,"about_ca_system_score_codex":0.00009524088,"about_ca_system_score_gemma":0.007401109,"threshold_uncertainty_score":0.99837613},"labels":[],"label_agreement":null},{"id":"W2231074671","doi":"10.1016/j.jclinepi.2015.11.018","title":"Rating the quality of evidence is by necessity a matter of judgment","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Blinding; Scopus; Pollock; Quality (philosophy); Medicine; Transparency (behavior); Psychology; MEDLINE; Computer science; Philosophy; Epistemology; Law; Surgery; History; Political science; Randomized controlled trial","score_opus":0.9760354535682091,"score_gpt":0.7359087542159788,"score_spread":0.2401266993522303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2231074671","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0100354375,0.0039932644,0.028764643,0.95471513,0.0014562366,0.0003303349,0.000054877808,6.233336e-7,0.00064944784],"genre_scores_gemma":[0.016538277,0.0012999473,0.005985173,0.96178895,0.004140897,0.0000073482743,0.0000022611262,0.000019113411,0.010218014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.29295594,0.48083985,0.2125378,0.001900262,0.01088657,0.00087957544],"domain_scores_gemma":[0.17345628,0.61929804,0.19890615,0.0044470634,0.0037052757,0.00018721548],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7993873,0.00043569482,0.028195938,0.00022176217,0.00006710019,0.000052703934,0.0054595345,0.0011335971,0.013295132],"category_scores_gemma":[0.77755547,0.00012210937,0.012894843,0.0003930154,0.0008341844,0.00020794453,0.00038682992,0.002835349,0.00058199716],"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":[0.000031752126,0.000024571955,0.19886197,0.00016305714,0.00052223477,0.0000034033628,0.000035587964,0.0000021508527,0.000015990621,0.000032481094,0.79046905,0.009837755],"study_design_scores_gemma":[0.0002863674,0.00026392905,0.058285754,0.0010954153,0.00063079264,0.000027275464,0.000043724347,0.000061922095,0.000014730155,0.023154952,0.91596276,0.0001724086],"about_ca_topic_score_codex":0.000036699883,"about_ca_topic_score_gemma":0.0000037371028,"teacher_disagreement_score":0.14057623,"about_ca_system_score_codex":0.000030484644,"about_ca_system_score_gemma":0.00031468557,"threshold_uncertainty_score":0.9999214},"labels":[],"label_agreement":null},{"id":"W2237679042","doi":"10.1016/j.jclinepi.2015.12.008","title":"Improving GRADE evidence tables part 2: a systematic survey of explanatory notes shows more guidance is needed","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; University of Toronto; McMaster University","funders":"McMaster University; American Thoracic Society","keywords":"Grading (engineering); Observational study; Systematic review; Quality of evidence; Psychology; Evidence-based medicine; MEDLINE; Quality (philosophy); Baseline (sea); Medicine; Meta-analysis; Actuarial science; Alternative medicine; Pathology","score_opus":0.9350509966107277,"score_gpt":0.6535339054625325,"score_spread":0.2815170911481951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237679042","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69737357,0.030314796,0.24555357,0.021852149,0.0035375329,0.0011745025,0.00009782872,0.0000065830786,0.000089489724],"genre_scores_gemma":[0.9844295,0.0010057661,0.009602527,0.0035584879,0.00041545107,0.00001635528,6.0945894e-7,0.000016755668,0.00095453934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.60986775,0.25987774,0.12251863,0.0015364818,0.005373293,0.00082612596],"domain_scores_gemma":[0.19208024,0.7063223,0.09254214,0.003673079,0.004809062,0.000573142],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.758035,0.00038392638,0.021573298,0.00039088438,0.00007268296,0.000070113085,0.0033092343,0.0003912898,0.0024899961],"category_scores_gemma":[0.9631948,0.00013817701,0.005196876,0.00075258675,0.0004809681,0.00054147653,0.00021859267,0.00048242463,0.00030646654],"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":[0.00012372975,0.00009425761,0.90711653,0.0015760529,0.0006061414,0.000013581517,0.0001017722,0.000032629356,0.00019790868,0.00039316594,0.08373824,0.006005988],"study_design_scores_gemma":[0.0024946744,0.0013336434,0.9309826,0.0271531,0.0019178304,0.00031636868,0.0008955619,0.009569868,0.00028288967,0.019945556,0.0043251407,0.0007827603],"about_ca_topic_score_codex":0.00018080507,"about_ca_topic_score_gemma":0.00011578249,"teacher_disagreement_score":0.4464446,"about_ca_system_score_codex":0.00003935964,"about_ca_system_score_gemma":0.00040158106,"threshold_uncertainty_score":0.99842185},"labels":[],"label_agreement":null},{"id":"W2239631772","doi":"10.1016/j.jclinepi.2015.12.007","title":"Improving GRADE evidence tables part 1: a randomized trial shows improved understanding of content in summary of findings tables with a new format","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":123,"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; St. Joseph’s Healthcare Hamilton; Bruyère; Cochrane; Institute for Work & Health; University of Toronto; McMaster University","funders":"","keywords":"Randomized controlled trial; Confidence interval; Preference; Computer science; Quality (philosophy); Medicine; Information retrieval; Statistics; Surgery; Mathematics","score_opus":0.9109934911096078,"score_gpt":0.5904354545764129,"score_spread":0.3205580365331949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2239631772","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":[0.56571543,0.0041741156,0.41947487,0.007626693,0.001158417,0.0017131086,0.000013425709,0.0000020321402,0.00012188954],"genre_scores_gemma":[0.9773089,0.0022837394,0.018125048,0.0005815297,0.00040844362,0.00001979239,6.5476206e-7,0.000014321315,0.0012575451],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.80533624,0.08427833,0.10480892,0.001166922,0.0035323058,0.00087727536],"domain_scores_gemma":[0.28202838,0.63155276,0.082371175,0.0018787776,0.0015837863,0.00058510737],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5915941,0.00031876666,0.022066206,0.00054674863,0.00004207075,0.00004822193,0.0015043673,0.00030303415,0.0011746062],"category_scores_gemma":[0.791363,0.00010817907,0.00515426,0.000552057,0.00063715695,0.00060241343,0.00015375091,0.00047055897,0.00000695591],"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":[0.659113,0.00039820597,0.27006772,0.00027073995,0.0018987355,0.000017687942,0.00030923623,0.00012483346,0.0012381481,0.009083995,0.035705622,0.02177208],"study_design_scores_gemma":[0.8506284,0.0043158713,0.003375274,0.0056278235,0.0018369639,0.00010132271,0.0017842553,0.008523767,0.00014330045,0.12032592,0.0028938428,0.0004433067],"about_ca_topic_score_codex":0.00027484543,"about_ca_topic_score_gemma":0.0003559276,"teacher_disagreement_score":0.5472744,"about_ca_system_score_codex":0.000082534345,"about_ca_system_score_gemma":0.00067853235,"threshold_uncertainty_score":0.99973845},"labels":[],"label_agreement":null},{"id":"W22498429","doi":"10.1016/j.jclinepi.2011.12.012","title":"The National Environmental Policy Act of 1969—The Brave New World of Environmental Legislation","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Environmental law and policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"National Environmental Policy Act; Environmental law; Statute; Legislation; Political science; Law; Public administration; Environmental impact statement; Environmental policy; Subject (documents); Legislative history; Environmental impact assessment; Library science; Environmental planning; Geography","score_opus":0.1852386159975961,"score_gpt":0.49009576067146676,"score_spread":0.30485714467387065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W22498429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7548432,0.0013013262,0.0006645593,0.20816417,0.0014801039,0.00041228282,0.00012625835,0.000008099794,0.03300004],"genre_scores_gemma":[0.9864698,0.0036519212,0.00034467687,0.0017049415,0.0026069134,9.5155906e-7,0.000001060019,0.000008133863,0.0052116173],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99330145,0.0032477144,0.002485429,0.00014048665,0.0005203986,0.00030451693],"domain_scores_gemma":[0.9721686,0.02452186,0.0029238614,0.0001550747,0.000013534463,0.00021707488],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.013812115,0.00011370976,0.0006777418,0.00007175239,0.00021223762,0.0000046919263,0.000543349,0.00017417228,0.00053020276],"category_scores_gemma":[0.0121594425,0.00005461686,0.00054952054,0.00008330434,0.0031520564,0.00017164787,0.00008590153,0.00032637655,0.000036553745],"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":[0.00041467856,0.00030781512,0.51370937,0.000002812562,0.00023386825,0.0000013134812,0.000737623,0.00005294918,0.0019559762,0.24241714,0.011906863,0.2282596],"study_design_scores_gemma":[0.00070237403,0.00031484014,0.557078,0.000022838321,0.000027838512,0.000007167134,0.0001476024,0.000005271818,0.000108674336,0.050819676,0.3906966,0.00006909734],"about_ca_topic_score_codex":0.0003597575,"about_ca_topic_score_gemma":0.00034236597,"teacher_disagreement_score":0.37878972,"about_ca_system_score_codex":0.00017262346,"about_ca_system_score_gemma":0.00036821383,"threshold_uncertainty_score":0.9995608},"labels":[],"label_agreement":null},{"id":"W2253376458","doi":"10.1016/j.jclinepi.2015.11.020","title":"GRADE guidelines system is reproducible when instructions are clearly operationalized even among the guidelines panel members with limited experience with GRADE","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Health Sciences Centre","funders":"","keywords":"Operationalization; Medicine; Psychology; Medical physics","score_opus":0.7081487604053213,"score_gpt":0.5806997629428426,"score_spread":0.12744899746247862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253376458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64959747,0.00026486258,0.013385568,0.33508906,0.0009793312,0.00055818714,0.000015981706,0.000051723313,0.000057827656],"genre_scores_gemma":[0.84103554,0.0012234605,0.1222193,0.029938485,0.0045295865,0.00006249516,0.000013049185,0.00007618122,0.00090188097],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9829564,0.0034044117,0.011407022,0.00084668916,0.00087543874,0.0005100429],"domain_scores_gemma":[0.95487046,0.028490445,0.0091293715,0.0013643174,0.0055514206,0.000593955],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026862375,0.00038197255,0.0025366866,0.00018183797,0.00024248191,0.000031784326,0.0005229068,0.00036129012,0.0002577775],"category_scores_gemma":[0.23220612,0.00016121437,0.0005844371,0.000391926,0.0010474436,0.00071707746,0.00010872235,0.001009207,0.000020532165],"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":[0.003726207,0.00025831023,0.8974899,0.000057134668,0.0008496071,0.000112435024,0.00028668036,0.00059360766,0.00020665982,0.00083688274,0.08659656,0.008986014],"study_design_scores_gemma":[0.019306289,0.0052807285,0.8123073,0.0034593896,0.0018858183,0.0068571595,0.007513114,0.0045175995,0.00022192555,0.0018702891,0.13610987,0.0006705236],"about_ca_topic_score_codex":0.0005984567,"about_ca_topic_score_gemma":0.0002895866,"teacher_disagreement_score":0.30515057,"about_ca_system_score_codex":0.0001360793,"about_ca_system_score_gemma":0.00093194086,"threshold_uncertainty_score":0.93100166},"labels":[],"label_agreement":null},{"id":"W2254929923","doi":"10.1016/j.jclinepi.2015.12.006","title":"Improving GRADE evidence tables part 3: detailed guidance for explanatory footnotes supports creating and understanding GRADE certainty in the evidence judgments","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":174,"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; University of Toronto; McMaster University; Cochrane","funders":"","keywords":"Grading (engineering); Certainty; Systematic review; Evidence-based medicine; Transparency (behavior); Evidence-based practice; Scientific evidence; MEDLINE; Medicine; Computer science; Psychology; Alternative medicine; Statistics; Mathematics","score_opus":0.9401004975708547,"score_gpt":0.6422796381907058,"score_spread":0.2978208593801489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2254929923","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":[0.5454633,0.015444901,0.3975317,0.038928837,0.0013877257,0.0011550525,0.000010008003,0.000004059602,0.00007441818],"genre_scores_gemma":[0.98358816,0.0020496615,0.0115149375,0.0021349585,0.00046638842,0.000034420675,3.0493993e-7,0.000010215997,0.00020098072],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.86415875,0.0861196,0.044721354,0.0014016264,0.0027348502,0.00086381723],"domain_scores_gemma":[0.24118954,0.72366166,0.032326747,0.0017199842,0.00074104534,0.0003610086],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6180132,0.00030430531,0.0067595188,0.00027044237,0.00020663042,0.00016498567,0.0018368188,0.00023813249,0.0003261332],"category_scores_gemma":[0.87080103,0.00010719393,0.0021569303,0.00040183906,0.00036919882,0.0008079302,0.00014867811,0.00047095917,0.000015995254],"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":[0.000115649804,0.000044493245,0.9678374,0.00007993983,0.00012140523,0.000018636249,0.00016273846,0.000043370626,0.00008759474,0.0039061746,0.014054381,0.013528196],"study_design_scores_gemma":[0.003004981,0.0015742397,0.5497545,0.0072319284,0.00091043295,0.0003488293,0.003884269,0.011418013,0.000038618775,0.40645075,0.014780709,0.00060273334],"about_ca_topic_score_codex":0.000023373674,"about_ca_topic_score_gemma":0.00014219728,"teacher_disagreement_score":0.63754207,"about_ca_system_score_codex":0.000096460986,"about_ca_system_score_gemma":0.00022595133,"threshold_uncertainty_score":0.4620672},"labels":[],"label_agreement":null},{"id":"W2258105780","doi":"10.1016/j.jclinepi.2015.10.018","title":"Critical EPICOT items were absent in Cochrane human immunodeficiency virus systematic reviews: a bibliometric analysis","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Bruyère; University of Ottawa; Institute of Population and Public Health; McMaster University","funders":"","keywords":"Systematic review; Medicine; Psychological intervention; Population; Meta-analysis; Human immunodeficiency virus (HIV); Family medicine; Research design; MEDLINE; Clinical study design; Demography; Gerontology; Clinical trial; Environmental health; Psychiatry; Social science; Internal medicine","score_opus":0.9543698016403744,"score_gpt":0.7476668559472635,"score_spread":0.20670294569311098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258105780","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010064945,0.9857558,0.0076347333,0.00043888862,0.0025554097,0.0024743713,0.000039290455,0.0000048217876,0.0009960437],"genre_scores_gemma":[0.00031228215,0.9943531,0.0026907783,0.00051398075,0.0008672018,0.000121346275,0.000020093883,0.000047898986,0.0010732862],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.29584697,0.4462157,0.24591133,0.0024527174,0.0083732605,0.0012000462],"domain_scores_gemma":[0.044115376,0.7083286,0.22625323,0.010942141,0.008490901,0.0018697324],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","research_integrity","insufficient_payload"],"category_scores_codex":[0.905135,0.0015587881,0.20020589,0.11340282,0.00015596674,0.0005698522,0.009174505,0.002037005,0.005063908],"category_scores_gemma":[0.9572466,0.00064376666,0.062978745,0.17591365,0.0006691071,0.00046250786,0.0005916884,0.0043553915,0.0048001013],"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":[0.000031109023,0.0017003287,0.012077889,0.22814697,0.011176308,0.0004279114,0.00007787523,0.00011176425,1.2558269e-7,0.0046225577,0.07545925,0.6661679],"study_design_scores_gemma":[0.00040051815,0.00055986975,0.002160654,0.059238933,0.032844823,0.0004582942,0.00006387056,0.0006064728,3.3035967e-9,0.0070650466,0.89597076,0.0006307642],"about_ca_topic_score_codex":0.000051912415,"about_ca_topic_score_gemma":0.000052094016,"teacher_disagreement_score":0.8205115,"about_ca_system_score_codex":0.00032924628,"about_ca_system_score_gemma":0.0010436514,"threshold_uncertainty_score":0.99971604},"labels":[],"label_agreement":null},{"id":"W2261735716","doi":"10.1016/j.jclinepi.2015.12.010","title":"Automatically quantifying the scientific quality and sensationalism of news records mentioning pandemics: validating a maximum entropy machine-learning model","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":32,"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; Norges Forskningsråd; Pierre Elliott Trudeau Foundation","keywords":"Sensationalism; Computer science; Social media; Data science; Information retrieval; Advertising; World Wide Web; Business","score_opus":0.49872240571375576,"score_gpt":0.5500606175580137,"score_spread":0.051338211844257964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261735716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8441395,0.00012437331,0.12545724,0.028114406,0.0007091775,0.000108093496,0.000005160635,0.000017161541,0.0013248904],"genre_scores_gemma":[0.9731014,0.00066775753,0.02419086,0.0013243848,0.00029635793,4.7658673e-7,0.0000014080415,0.000005741763,0.0004116586],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98700243,0.007762946,0.0042601107,0.0001645178,0.0004841612,0.00032583682],"domain_scores_gemma":[0.96085066,0.033426553,0.0048049185,0.00015600813,0.00050077366,0.00026108677],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089110136,0.00009760158,0.0008600698,0.000101011225,0.00052365067,0.00005409011,0.00026588797,0.00019262702,0.0000815911],"category_scores_gemma":[0.21706724,0.000051511965,0.00030044693,0.00014854512,0.00091385684,0.0004442856,0.000069129106,0.0004711692,0.000004785835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002083241,0.00009419406,0.5143962,0.000056749068,0.00018600782,0.0000013706633,0.011865562,0.0017591385,0.00070690055,0.31745246,0.0020980937,0.15117499],"study_design_scores_gemma":[0.0039739124,0.0005084272,0.20986153,0.000863669,0.00020321661,0.00005223428,0.009686974,0.24917823,0.000047632508,0.501585,0.023582755,0.00045640432],"about_ca_topic_score_codex":0.00015229781,"about_ca_topic_score_gemma":0.0001234351,"teacher_disagreement_score":0.30453467,"about_ca_system_score_codex":0.00004293385,"about_ca_system_score_gemma":0.00045877317,"threshold_uncertainty_score":0.9379528},"labels":[],"label_agreement":null},{"id":"W2262449114","doi":"10.1016/j.jclinepi.2015.12.011","title":"Knowledge synthesis methods for integrating qualitative and quantitative data: a scoping review reveals poor operationalization of the methodological steps","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Operationalization; Narrative; Process (computing); Computer science; Qualitative research; MEDLINE; Systematic review; Management science; Data science; Knowledge management; Psychology; Sociology; Epistemology; Engineering","score_opus":0.9923664630974257,"score_gpt":0.8454584875581033,"score_spread":0.14690797553932244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262449114","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.0026774e-7,0.5480325,0.44806817,0.0016476715,0.00055619364,0.0015350014,0.00009042478,7.3580725e-7,0.000068503796],"genre_scores_gemma":[5.2035824e-7,0.5812182,0.41780877,0.00048653336,0.00022885436,0.00006797686,0.000006493995,0.00001280441,0.00016988265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.17875735,0.72831964,0.08978314,0.0015112187,0.001292782,0.00033587415],"domain_scores_gemma":[0.0054313447,0.87255394,0.11389959,0.0028937263,0.0049881,0.0002332943],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.89828277,0.0005981523,0.054675058,0.0003509654,0.0001566352,0.00007737718,0.0044953157,0.00068027613,0.00064262963],"category_scores_gemma":[0.98957866,0.00018120493,0.009984686,0.0010236347,0.0006941481,0.00034289787,0.0007883413,0.00091031793,0.000034582703],"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":[0.000016644784,0.000046946938,0.000080620055,0.029488733,0.0012183877,3.3709608e-7,0.00010258211,7.6422026e-7,2.4760806e-7,0.024095422,0.014234343,0.93071496],"study_design_scores_gemma":[0.00017974051,0.000281965,0.00003621492,0.39774024,0.005683336,0.0000737487,0.0003533424,0.0006010109,1.675925e-7,0.042435724,0.5523627,0.00025182375],"about_ca_topic_score_codex":0.000002009207,"about_ca_topic_score_gemma":0.000009724682,"teacher_disagreement_score":0.93046314,"about_ca_system_score_codex":0.000043287575,"about_ca_system_score_gemma":0.0012741898,"threshold_uncertainty_score":0.9999301},"labels":[],"label_agreement":null},{"id":"W2265528961","doi":"10.1016/j.jclinepi.2015.11.021","title":"Knowledge synthesis methods for generating or refining theory: a scoping review reveals that little guidance is available","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Refining (metallurgy); Management science; Computer science; Data science; Psychology; Engineering; Chemistry","score_opus":0.9681132455293067,"score_gpt":0.8445442824602661,"score_spread":0.12356896306904053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2265528961","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":[2.9425428e-7,0.91510564,0.06674147,0.010302737,0.0037743798,0.0024518883,0.000121367244,0.000027823404,0.0014743869],"genre_scores_gemma":[1.7538392e-8,0.6835722,0.25811437,0.04747755,0.0033971057,0.00083783997,0.0000021406224,0.000071244634,0.0065275445],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7751115,0.19074492,0.030727446,0.0011072652,0.00033288202,0.0019759855],"domain_scores_gemma":[0.14903092,0.80715597,0.04017669,0.0011765192,0.0014206034,0.0010393248],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.4809722,0.0006466539,0.01839499,0.00036622593,0.000851344,0.000011822409,0.0015531931,0.0014731495,0.0066317804],"category_scores_gemma":[0.8391067,0.000344273,0.0025198476,0.00058517064,0.00036721918,0.00028661822,0.00042650034,0.0028203987,0.0012277155],"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":[0.000037268474,0.000014059354,0.00011573003,0.12862799,0.00011970318,0.0000016975472,0.00007061444,2.3238593e-8,1.06953976e-7,0.0005981245,0.19172066,0.678694],"study_design_scores_gemma":[0.00027815686,0.00016439577,0.0000030615759,0.42671672,0.0004033502,0.000030401407,0.000011898887,0.000006473222,1.2256662e-7,0.00066395925,0.57153296,0.00018852307],"about_ca_topic_score_codex":0.000009115947,"about_ca_topic_score_gemma":0.000012400061,"teacher_disagreement_score":0.6785055,"about_ca_system_score_codex":0.0004446081,"about_ca_system_score_gemma":0.01467155,"threshold_uncertainty_score":0.99990094},"labels":[],"label_agreement":null},{"id":"W2267831916","doi":"10.1016/j.jclinepi.2016.01.020","title":"A new classification of spin in systematic reviews and meta-analyses was developed and ranked according to the severity","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"National Institute for Health and Care Research; Cancer Research UK","keywords":"Meta-analysis; Systematic review; MEDLINE; Medicine; Statistics; Mathematics; Internal medicine; Biology","score_opus":0.9729143064742207,"score_gpt":0.714524897594347,"score_spread":0.2583894088798737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2267831916","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":[0.45479706,0.0292492,0.41687015,0.09546369,0.0006335238,0.002733263,0.0000058185074,0.0000020085279,0.00024529788],"genre_scores_gemma":[0.9453543,0.0026134695,0.048525296,0.002429445,0.00017260491,0.000027398968,1.583179e-7,0.0000074468803,0.0008699204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6748112,0.23052578,0.091140874,0.001053637,0.0020793667,0.00038916274],"domain_scores_gemma":[0.36953783,0.5354215,0.08825467,0.0038109715,0.0021714915,0.0008035376],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6427077,0.0002441199,0.022635283,0.00034844538,0.00004452098,0.000056309498,0.0011911748,0.00017193753,0.00046523765],"category_scores_gemma":[0.84239167,0.00006456844,0.0032347906,0.00076445384,0.00012997164,0.00020995674,0.00015440078,0.00029369496,0.00010223391],"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":[0.0002793985,0.00013385358,0.6893053,0.003073641,0.01070807,0.00001169193,0.0006044027,0.000047364447,0.00034486756,0.0076147662,0.07046409,0.21741255],"study_design_scores_gemma":[0.0012829916,0.00039469742,0.89359,0.0019150706,0.017572422,0.00025161964,0.0007954538,0.0017787534,0.000011628724,0.04292661,0.039166063,0.00031472842],"about_ca_topic_score_codex":0.000021401906,"about_ca_topic_score_gemma":0.00009874852,"teacher_disagreement_score":0.49055722,"about_ca_system_score_codex":0.000019025092,"about_ca_system_score_gemma":0.00014450106,"threshold_uncertainty_score":0.9918747},"labels":[],"label_agreement":null},{"id":"W2273555097","doi":"10.1016/j.jclinepi.2015.05.033","title":"Disclosure of data and statistical commands should accompany completely reported studies","year":2015,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; University of Ottawa","funders":"","keywords":"Computer science; Medicine; Statistics; Mathematics","score_opus":0.9898007502915757,"score_gpt":0.7575522436430417,"score_spread":0.23224850664853391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273555097","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004685717,0.019496817,0.049348976,0.92026925,0.0037523538,0.000546991,0.0010679428,0.0000031661962,0.00082875637],"genre_scores_gemma":[0.026560979,0.0059197345,0.15702917,0.7865348,0.017621653,0.000009804541,0.0006647834,0.0001029646,0.00555615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.55779386,0.25897777,0.17068906,0.0026709158,0.009034749,0.00083361863],"domain_scores_gemma":[0.14356379,0.6801287,0.15716712,0.010029084,0.008446841,0.0006644712],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.72610015,0.00060692424,0.046519823,0.0004667683,0.00007261175,0.0000985037,0.005776412,0.0013250638,0.001192403],"category_scores_gemma":[0.88851786,0.00024891962,0.003450956,0.0004446433,0.0015944084,0.0002765971,0.0015330678,0.004751421,0.00009421069],"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":[0.000052005907,0.000051859322,0.12279717,0.0001611289,0.0029715353,0.000284846,0.000033785556,0.0000065746585,1.5705574e-7,0.00023369525,0.86667305,0.006734196],"study_design_scores_gemma":[0.0005048659,0.00046436218,0.042596262,0.00021066351,0.0022728997,0.0005090154,0.0001408574,0.0014998381,2.5677203e-8,0.067647144,0.8839578,0.00019623365],"about_ca_topic_score_codex":0.000010884431,"about_ca_topic_score_gemma":0.000018870676,"teacher_disagreement_score":0.4211509,"about_ca_system_score_codex":0.000025487747,"about_ca_system_score_gemma":0.0004935971,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W2274503997","doi":"10.1016/j.jclinepi.2016.02.015","title":"David Sackett's legacy includes evidence-based mentorship","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mentoring and Academic Development","field":"Psychology","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; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Mentorship; Generosity; Enthusiasm; Flourishing; Psychology; Medicine; Medical education; Political science; Social psychology; Law","score_opus":0.55149547673523,"score_gpt":0.5613321711397101,"score_spread":0.009836694404480095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274503997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82193434,0.0043523987,0.017846046,0.12101274,0.031187478,0.00020273113,0.000004088259,0.000057061072,0.00340311],"genre_scores_gemma":[0.97452533,0.0010829641,0.0059143463,0.010281826,0.004453383,0.000012407625,7.1445254e-7,0.000026403173,0.0037026093],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9840364,0.008397525,0.0059433384,0.00046445293,0.00035316014,0.00080511725],"domain_scores_gemma":[0.9075838,0.087387115,0.0036725798,0.00045031574,0.00023396018,0.00067226443],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06414001,0.00024735602,0.0020361803,0.00018858843,0.00006891415,0.000010603668,0.00081754336,0.00063699624,0.002316092],"category_scores_gemma":[0.12824836,0.00013639094,0.0006827098,0.00013817314,0.00037266282,0.00031827533,0.00010318961,0.0010545969,0.00055625796],"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":[0.0012923101,0.00032628383,0.6375447,0.000023414037,0.00035400162,0.00009772607,0.00015070257,0.000006203312,0.00031010935,0.00810288,0.14323531,0.20855638],"study_design_scores_gemma":[0.0032788215,0.0014152084,0.5171657,0.0013361354,0.00010243707,0.00008623315,0.00006869357,0.0000062489416,0.00020151485,0.011975899,0.46407446,0.0002886003],"about_ca_topic_score_codex":0.000019097912,"about_ca_topic_score_gemma":0.0000013401996,"teacher_disagreement_score":0.32083917,"about_ca_system_score_codex":0.00012681917,"about_ca_system_score_gemma":0.0003769819,"threshold_uncertainty_score":0.99859595},"labels":[],"label_agreement":null},{"id":"W2275535763","doi":"10.1016/j.jclinepi.2015.11.022","title":"Conceptual recommendations for selecting the most appropriate knowledge synthesis method to answer research questions related to complex evidence","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":104,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; St. Michael's Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Multidisciplinary approach; Computer science; Field (mathematics); Knowledge base; Data science; Process (computing); Knowledge management; Management science; Artificial intelligence; Mathematics; Sociology","score_opus":0.9799221084820834,"score_gpt":0.8602829431530016,"score_spread":0.11963916532908181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275535763","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013945985,0.36766678,0.18382408,0.43092823,0.00688363,0.009097755,0.00053245656,0.00005732796,0.0009958075],"genre_scores_gemma":[0.00001186699,0.7944705,0.16856498,0.02948428,0.003343259,0.0020596941,0.000006820634,0.00007413989,0.0019844954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7771178,0.20122948,0.018382803,0.00089971226,0.00051592744,0.0018542944],"domain_scores_gemma":[0.19585195,0.78809756,0.008622305,0.00087725115,0.00497414,0.0015768185],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39347303,0.00041714034,0.006512459,0.0009291535,0.0021621988,0.000018451374,0.0021301736,0.0011781538,0.0009053685],"category_scores_gemma":[0.8321979,0.00022562065,0.0010530946,0.0022700694,0.0005936993,0.00021804417,0.0006470152,0.0056234966,0.0011184614],"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":[0.00004926536,0.000043408723,0.00014034941,0.00089140557,0.00009441057,4.3440184e-7,0.0009584374,0.0000018661892,4.838572e-7,0.012671589,0.27480108,0.7103473],"study_design_scores_gemma":[0.00026559908,0.00061992183,0.00023139591,0.031681456,0.00020453165,0.00002988464,0.00081175595,0.00002122008,6.785766e-8,0.004701492,0.96122664,0.00020604406],"about_ca_topic_score_codex":0.00014522577,"about_ca_topic_score_gemma":0.00014382589,"teacher_disagreement_score":0.71014124,"about_ca_system_score_codex":0.0008883313,"about_ca_system_score_gemma":0.015895676,"threshold_uncertainty_score":0.9996593},"labels":[],"label_agreement":null},{"id":"W2275912072","doi":"10.1016/j.jclinepi.2015.08.030","title":"A scoping review identifies multiple emerging knowledge synthesis methods, but few studies operationalize the method","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":152,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Royal College of Physicians and Surgeons of Canada; Bruyère; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"CINAHL; PsycINFO; Operationalization; MEDLINE; Cochrane Library; Knowledge translation; Health care; Computer science; Knowledge management; Medical education; Medicine; Data science; Political science","score_opus":0.9053944439792669,"score_gpt":0.8165690834043406,"score_spread":0.0888253605749263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275912072","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":[0.0000010691015,0.9420597,0.018212752,0.027168393,0.009930811,0.0023586298,0.000014809239,0.000014236631,0.00023958899],"genre_scores_gemma":[1.7603057e-7,0.94498736,0.041055813,0.0056376243,0.0062280213,0.00073980325,0.0000032905698,0.000034074645,0.0013138388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.77444386,0.2064419,0.016941119,0.0006209237,0.00042544803,0.0011267591],"domain_scores_gemma":[0.07888333,0.90041834,0.016254378,0.0009427948,0.0026067721,0.0008944128],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3925895,0.0004456308,0.012470692,0.00033298656,0.0012773145,0.000012532649,0.0014968078,0.00081757363,0.0008144569],"category_scores_gemma":[0.8211739,0.0001886928,0.0022305432,0.00060952036,0.00066262734,0.00026346327,0.0005154937,0.0040266374,0.00056502136],"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":[0.000008722841,0.000039002283,0.00020912928,0.12836581,0.00035642297,0.0000017789465,0.00014794282,4.517574e-7,3.7345902e-8,0.00021791804,0.10022373,0.7704291],"study_design_scores_gemma":[0.0001059823,0.000055679204,0.00006386116,0.40539342,0.00035127957,0.000021949434,0.0002398401,0.000013040341,3.6225906e-8,0.00090301316,0.59273887,0.00011300573],"about_ca_topic_score_codex":0.000052208652,"about_ca_topic_score_gemma":0.00009765619,"teacher_disagreement_score":0.77031606,"about_ca_system_score_codex":0.00033207654,"about_ca_system_score_gemma":0.012980719,"threshold_uncertainty_score":0.9982711},"labels":[],"label_agreement":null},{"id":"W2279214036","doi":"10.1016/j.jclinepi.2015.02.019","title":"Knowledge synthesis research: a bibliometric analysis","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Canada Research Chairs; University of Toronto; St. Michael's Hospital; Institute for Work & Health","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Subject (documents); Bibliometrics; Computer science; Publishing; Medical research; Medical literature; Data science; Management science; Medicine; Library science; Pathology; Political science","score_opus":0.9890212536511169,"score_gpt":0.8813268878723645,"score_spread":0.10769436577875247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279214036","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":[0.000036068162,0.9801172,0.0023247278,0.008906812,0.003534103,0.0008625598,0.00013950428,0.00002036928,0.0040586432],"genre_scores_gemma":[0.000029882607,0.98654175,0.0020998502,0.0034864452,0.006038951,0.00017187741,0.0000025837087,0.000048336387,0.0015803032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.68945545,0.27410543,0.032320958,0.0008135345,0.0010103136,0.0022943136],"domain_scores_gemma":[0.09786092,0.86868733,0.026566995,0.0012045599,0.003573403,0.0021067814],"candidate_categories":["metaresearch","metaepi_broad","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","research_integrity","insufficient_payload"],"category_scores_codex":[0.533461,0.00044040458,0.019864859,0.18011564,0.00067991053,0.000010171904,0.0023554543,0.0023388388,0.004321504],"category_scores_gemma":[0.880622,0.00023600127,0.0050405697,0.20398402,0.0010023466,0.00022054269,0.00064148277,0.008160124,0.0058176126],"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":[0.000020172469,0.000057309557,0.0077348156,0.0045417976,0.0010691135,0.000012133542,0.000066395936,7.7596646e-8,3.3555434e-9,0.0009074614,0.12030975,0.865281],"study_design_scores_gemma":[0.00033513026,0.0002795728,0.008851078,0.011234243,0.0017795566,0.000016787977,0.00004936541,0.0000036933884,3.6735868e-9,0.001570615,0.97569734,0.00018263546],"about_ca_topic_score_codex":0.00007774356,"about_ca_topic_score_gemma":0.000070512135,"teacher_disagreement_score":0.86509836,"about_ca_system_score_codex":0.0007257044,"about_ca_system_score_gemma":0.014751791,"threshold_uncertainty_score":0.9989563},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2279306162","doi":"10.1016/j.jclinepi.2016.01.031","title":"Introduction: Engaging researchers on developing, using, and improving knowledge synthesis methods: a series of articles describing the results of a scoping review on emerging knowledge synthesis methods","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":26,"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. Michael's Hospital; University of Toronto; Canada Research Chairs","funders":"","keywords":"Knowledge translation; Systematic review; Scopus; Psychological intervention; Health care; Alternative medicine; MEDLINE; Medical education; Psychology; Medicine; Knowledge management; Computer science; Nursing; Political science","score_opus":0.8946043024001076,"score_gpt":0.7403907176283919,"score_spread":0.15421358477171565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279306162","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":[0.00014420401,0.96909416,0.00963394,0.016902383,0.0024847877,0.0014646648,0.000011010608,0.000011200148,0.00025362518],"genre_scores_gemma":[0.000016521175,0.86298704,0.13378903,0.00029886837,0.0026741205,0.00011729363,6.780748e-7,0.000036727128,0.00007970553],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.82477117,0.16089804,0.012135391,0.0007228874,0.0003864046,0.0010860955],"domain_scores_gemma":[0.1900333,0.7842561,0.02081623,0.0013907906,0.0025035169,0.0010000463],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38903263,0.0004297049,0.0077429665,0.0008147133,0.00083728746,0.000010609495,0.00093620067,0.0006907067,0.00010339149],"category_scores_gemma":[0.7935452,0.00022127008,0.00093430316,0.0010985906,0.0011601273,0.0002529609,0.00043263103,0.003857828,0.000017006894],"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":[0.00018578736,0.0000695077,0.00008406892,0.09145229,0.00015961382,0.0000010923435,0.0005604133,0.0000011082464,0.0000032256996,0.0004663049,0.0025558555,0.9044607],"study_design_scores_gemma":[0.00023502047,0.0004808884,0.0001120424,0.67453396,0.00040041335,0.000034826066,0.00094411435,0.00013844788,0.000027606326,0.00053261896,0.32234588,0.00021420332],"about_ca_topic_score_codex":0.00010804866,"about_ca_topic_score_gemma":0.000039532108,"teacher_disagreement_score":0.9042465,"about_ca_system_score_codex":0.0004857511,"about_ca_system_score_gemma":0.011025247,"threshold_uncertainty_score":0.9984403},"labels":[],"label_agreement":null},{"id":"W2279867742","doi":"10.1016/j.jclinepi.2016.02.001","title":"Diverse criteria and methods are used to compare treatment effect estimates: a scoping review","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Sinai Health System; Mount Sinai Hospital; Institute for Clinical Evaluative Sciences; Institute for Work & Health; Hospital for Sick Children; Centre for Social Innovation; University Health Network; SickKids Foundation; University of Toronto; Toronto Public Health","funders":"","keywords":"Observational study; Research design; Medicine; Clinical study design; Treatment effect; Statistics; Sample size determination; MEDLINE; Clinical trial; Mathematics","score_opus":0.973788508128348,"score_gpt":0.8051623039781306,"score_spread":0.16862620415021745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279867742","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":[0.000017503231,0.9660952,0.027610825,0.0017887326,0.0017066377,0.0026500288,0.00003449264,0.0000034375557,0.00009310737],"genre_scores_gemma":[0.000001643995,0.9333646,0.06406712,0.0014893173,0.0006944742,0.00007474284,0.0000033470344,0.000026392994,0.00027835427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5196942,0.3869278,0.08925468,0.0017680964,0.0017632851,0.00059192505],"domain_scores_gemma":[0.14926767,0.7345275,0.10908287,0.0041426877,0.0015477722,0.001431447],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.6981391,0.0010501848,0.11329028,0.00062351394,0.00011119999,0.00015629755,0.0024341575,0.00045030648,0.004579139],"category_scores_gemma":[0.85584134,0.00032944375,0.020548115,0.00075007876,0.00023761591,0.00015836906,0.00042002337,0.0007361151,0.0015373512],"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":[0.000013992269,0.000040269726,0.0031829723,0.02750048,0.0011542615,0.000041803363,0.000009789506,5.6554507e-7,1.7778424e-8,0.000028197463,0.030359449,0.9376682],"study_design_scores_gemma":[0.00027065506,0.00057075545,0.00023981847,0.3350289,0.0050692027,0.00023959388,0.0000063587872,0.000021286149,1.7763133e-8,0.00053632556,0.6578097,0.00020743291],"about_ca_topic_score_codex":0.0000037760278,"about_ca_topic_score_gemma":0.000013081852,"teacher_disagreement_score":0.9374608,"about_ca_system_score_codex":0.00010761332,"about_ca_system_score_gemma":0.00046609892,"threshold_uncertainty_score":0.9999158},"labels":[],"label_agreement":null},{"id":"W2281906779","doi":"10.1016/j.jclinepi.2016.01.032","title":"GRADE Guidelines: 16. GRADE evidence to decision frameworks for tests in clinical practice and public health","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":340,"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; Cochrane","funders":"","keywords":"Grading (engineering); Test (biology); Guideline; Transparency (behavior); Computer science; Evidence-based medicine; Knowledge management; Management science; Process management; Medicine; Alternative medicine; Engineering","score_opus":0.9553377312321006,"score_gpt":0.8351776599634307,"score_spread":0.1201600712686699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281906779","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.12016101,0.00042017634,0.2726222,0.6030565,0.0027288483,0.000970369,0.000012686746,0.000012890755,0.000015306661],"genre_scores_gemma":[0.12818311,0.008857382,0.34391102,0.5158879,0.0029999192,0.00008006372,5.331097e-7,0.000023510036,0.00005654151],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9024746,0.056020986,0.037044432,0.0011095352,0.000888145,0.0024623189],"domain_scores_gemma":[0.1691889,0.8124668,0.012304497,0.00064859324,0.0024897612,0.00290142],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36081,0.00023732611,0.0030266375,0.0004373601,0.00034284647,0.00001132535,0.00077521167,0.0011487926,0.00010072822],"category_scores_gemma":[0.9644418,0.00014190584,0.00038504673,0.00058107596,0.0004037931,0.0008563279,0.00030308776,0.00321342,0.00008913029],"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":[0.00057989906,0.000121086945,0.5300604,0.00005802402,0.000016688844,0.0000045331053,0.00032185495,0.0000038937283,0.0000018803008,0.0028092063,0.20926937,0.25675315],"study_design_scores_gemma":[0.0038988714,0.0022937409,0.4849937,0.0017439538,0.000012220246,0.000041055155,0.0006638827,0.00009900561,1.0643192e-7,0.025636002,0.4804895,0.00012798388],"about_ca_topic_score_codex":0.00022898788,"about_ca_topic_score_gemma":0.00074140116,"teacher_disagreement_score":0.7564458,"about_ca_system_score_codex":0.00042589268,"about_ca_system_score_gemma":0.005468612,"threshold_uncertainty_score":0.9990862},"labels":[],"label_agreement":null},{"id":"W2287314186","doi":"10.1016/j.jclinepi.2016.02.017","title":"Low- and middle-income countries face many common barriers to implementation of maternal health evidence products","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":213,"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; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; World Health Organization","keywords":"Medicine; Low and middle income countries; Thematic analysis; Evidence-based practice; Implementation research; Qualitative research; Knowledge translation; Developing country; Global health; Health care; Environmental health; Public health; Nursing; Family medicine; Psychological intervention; Alternative medicine; Economic growth; Knowledge management; Pathology","score_opus":0.7259788535093454,"score_gpt":0.7308522688779862,"score_spread":0.004873415368640721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287314186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70391446,0.00011560406,0.0035333203,0.29064643,0.0011628555,0.00055609335,0.000053212083,0.00000822338,0.000009778818],"genre_scores_gemma":[0.928972,0.0018932596,0.005388414,0.06299525,0.00061349524,0.000019573039,3.55672e-7,0.000013111878,0.00010455092],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97416604,0.014164528,0.009944674,0.00036799218,0.00045234466,0.0009044334],"domain_scores_gemma":[0.9287276,0.060806174,0.007929675,0.00033554534,0.00076413725,0.0014368454],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076247245,0.00016596263,0.0019654923,0.00022704329,0.00031685366,0.000004286323,0.00043238976,0.00018357676,0.00052644045],"category_scores_gemma":[0.13176541,0.00010279024,0.00011900102,0.00023118613,0.00040888635,0.00041971618,0.00018614589,0.0005931405,0.00006987872],"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":[0.00030291599,0.0000077033565,0.9833307,0.0007075059,0.00002283116,0.0000023469158,0.0017752048,0.0000023095033,0.00005408814,0.0018586426,0.0057140044,0.006221714],"study_design_scores_gemma":[0.0014980207,0.0015816238,0.9786295,0.003017945,0.000013240274,0.000020720017,0.0013550519,0.0000059265917,0.00014262073,0.0014277844,0.012213601,0.00009395155],"about_ca_topic_score_codex":0.000547465,"about_ca_topic_score_gemma":0.0003826845,"teacher_disagreement_score":0.22765118,"about_ca_system_score_codex":0.00023250734,"about_ca_system_score_gemma":0.00368162,"threshold_uncertainty_score":0.95119786},"labels":[],"label_agreement":null},{"id":"W2287646667","doi":"10.1016/j.jclinepi.2015.08.033","title":"Opening-up the definition of systematic literature review: the plurality of worldviews, methodologies and methods for reviews and syntheses","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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","funders":"Canadian Institutes of Health Research","keywords":"Systematic review; Management science; Field (mathematics); Engineering ethics; Computer science; Psychology; MEDLINE; Medicine; Engineering; Political science","score_opus":0.962211849845657,"score_gpt":0.7322610675367124,"score_spread":0.2299507823089446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287646667","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008085597,0.68970007,0.27305654,0.033953015,0.0005540997,0.0017897973,0.000013412891,8.218473e-7,0.00012366475],"genre_scores_gemma":[0.005664677,0.5922401,0.3974284,0.004101453,0.00016452176,0.00007779314,4.1224786e-7,0.0000074707596,0.0003152079],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.34601808,0.57851535,0.07312587,0.0007878763,0.0012162995,0.00033654924],"domain_scores_gemma":[0.040179357,0.885417,0.06938199,0.0024553395,0.0024203851,0.00014592877],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8613147,0.00025876236,0.019446367,0.00013137433,0.00008774758,0.000051243012,0.0016848784,0.00019509859,0.00014360879],"category_scores_gemma":[0.9672341,0.00005797478,0.0041772504,0.00048439548,0.0007770464,0.0001932542,0.00020540065,0.00037869607,0.0000064500196],"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":[0.00028340318,0.00007190618,0.02036691,0.08374048,0.001736253,0.0000017745948,0.0005486871,0.0000018590056,0.0001342666,0.068009,0.14736973,0.67773575],"study_design_scores_gemma":[0.00064410496,0.0008065629,0.017462397,0.15495402,0.0053838827,0.0004670198,0.0004297561,0.00025663534,0.000027713024,0.5959558,0.22335497,0.00025715638],"about_ca_topic_score_codex":0.0000015472151,"about_ca_topic_score_gemma":0.0000031126497,"teacher_disagreement_score":0.67747855,"about_ca_system_score_codex":0.0000069851812,"about_ca_system_score_gemma":0.000052672232,"threshold_uncertainty_score":0.995111},"labels":[],"label_agreement":null},{"id":"W2288516595","doi":"10.1016/j.jclinepi.2016.02.022","title":"Three challenges described for identifying participants with missing data in trials reports, and potential solutions suggested to systematic reviewers","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"SickKids Foundation; Hospital for Sick Children; University of New Brunswick; University of Toronto; McMaster University","funders":"","keywords":"Missing data; Systematic review; Categorization; Randomized controlled trial; Data science; Process (computing); Computer science; Medicine; MEDLINE; Information retrieval; Psychology; Data mining; Management science; Artificial intelligence; Pathology; Machine learning","score_opus":0.9832173119860679,"score_gpt":0.7088153943360388,"score_spread":0.2744019176500291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288516595","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06569289,0.030073943,0.8595863,0.041050952,0.0013900071,0.002155324,0.000018358709,0.0000031001355,0.000029139776],"genre_scores_gemma":[0.8819604,0.0042269025,0.112007685,0.0008672912,0.00069286214,0.00006696317,0.0000024704589,0.000023172308,0.00015226244],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.5993281,0.22141539,0.17053065,0.002928725,0.004337987,0.001459172],"domain_scores_gemma":[0.13619412,0.72681785,0.122244954,0.009128527,0.004087044,0.0015274896],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8578492,0.00027098713,0.020774087,0.0004128538,0.00010312956,0.00013054565,0.0014800658,0.00021436847,0.00017847393],"category_scores_gemma":[0.946066,0.00009318811,0.0019023169,0.00038376637,0.00016751351,0.00043859484,0.00027826434,0.00026270808,0.000034290257],"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":[0.0019450866,0.0008891682,0.4282875,0.01722298,0.007475934,0.0009548064,0.00069249666,0.00042157195,0.00037382953,0.009155465,0.10133061,0.43125054],"study_design_scores_gemma":[0.008057994,0.0029725325,0.54414785,0.07562477,0.013057991,0.004791169,0.0021777465,0.018166417,0.000006097079,0.30886936,0.020841476,0.0012866026],"about_ca_topic_score_codex":0.0000066173825,"about_ca_topic_score_gemma":0.00017619906,"teacher_disagreement_score":0.8162675,"about_ca_system_score_codex":0.000029960363,"about_ca_system_score_gemma":0.00024718704,"threshold_uncertainty_score":0.99376357},"labels":[],"label_agreement":null},{"id":"W2289189593","doi":"10.1016/j.jclinepi.2016.02.016","title":"The rank-heat plot is a novel way to present the results from a network meta-analysis including multiple outcomes","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":228,"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; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Plot (graphics); Rank (graph theory); Meta-analysis; Statistics; Forest plot; Mathematics; Medicine; Combinatorics; Internal medicine","score_opus":0.95740010273662,"score_gpt":0.669342945671616,"score_spread":0.288057157065004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289189593","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06671948,0.0052641085,0.330687,0.59373254,0.0021478722,0.00082301284,0.00016251736,0.0000052648356,0.0004582249],"genre_scores_gemma":[0.9349288,0.0006789663,0.02788231,0.026238406,0.00235736,0.000039924664,0.000001647798,0.00002268394,0.007849942],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.702734,0.18285653,0.10419218,0.0022021919,0.006764406,0.0012506949],"domain_scores_gemma":[0.08775965,0.86969477,0.033292018,0.0062334845,0.0023050292,0.0007150697],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.70292646,0.00046390464,0.024967005,0.0002700604,0.00047612257,0.00025006887,0.005521808,0.00031386543,0.0023797664],"category_scores_gemma":[0.8719454,0.00010196745,0.03225449,0.0016445433,0.00036632174,0.00018848396,0.0007340885,0.0007924315,0.000903766],"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":[0.00051801925,0.0001277624,0.3254817,0.000001930082,0.17713755,0.0000059687086,0.00027802706,0.008254882,0.000009041832,0.0010829628,0.47385383,0.013248313],"study_design_scores_gemma":[0.0012284394,0.00017850139,0.35196847,0.000016578868,0.07277593,0.000008254709,0.00014151762,0.01126863,0.0000017301901,0.030151602,0.5320674,0.00019294227],"about_ca_topic_score_codex":0.0001588144,"about_ca_topic_score_gemma":0.00051288644,"teacher_disagreement_score":0.8682093,"about_ca_system_score_codex":0.000040808463,"about_ca_system_score_gemma":0.00011106944,"threshold_uncertainty_score":0.9998742},"labels":[],"label_agreement":null},{"id":"W2294602088","doi":"10.1016/j.jclinepi.2016.03.004","title":"Complementary approaches to searching MEDLINE may be sufficient for updating systematic reviews","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"National Research Council Canada; Canadian Patient Safety Institute; Children's Hospital of Eastern Ontario","funders":"Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"MEDLINE; Precision and recall; Ranking (information retrieval); Recall; Computer science; Support vector machine; Systematic review; Medicine; Information retrieval; Machine learning; Data mining; Psychology","score_opus":0.9829686983659722,"score_gpt":0.7045193499622208,"score_spread":0.27844934840375146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294602088","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057329796,0.0020537965,0.81575155,0.11967759,0.0015286204,0.0031109601,0.00003124567,0.0000032932633,0.0005131418],"genre_scores_gemma":[0.49207118,0.00055467145,0.48068994,0.020959321,0.0024198473,0.00016463251,0.000007014392,0.000036913945,0.003096469],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5571618,0.28953886,0.1462968,0.0016666986,0.0043107066,0.0010251041],"domain_scores_gemma":[0.17257285,0.7444598,0.076170556,0.003762218,0.0018866253,0.0011479278],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8567015,0.00033935215,0.02210263,0.00043120055,0.00013953731,0.00009265075,0.002753133,0.00015952022,0.0017950512],"category_scores_gemma":[0.89720917,0.00011026473,0.0073893038,0.00051866565,0.00014669517,0.00018864217,0.00028422292,0.00041317858,0.000594911],"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":[0.00022733163,0.00048602323,0.19175954,0.006449413,0.0015607331,0.000012948038,0.0005722911,0.000604764,0.000056199617,0.05625773,0.62418514,0.11782786],"study_design_scores_gemma":[0.0028949543,0.0027534491,0.020405864,0.011289792,0.0020089746,0.0002916293,0.0026542163,0.026676686,0.0000135405735,0.067219704,0.863032,0.00075923343],"about_ca_topic_score_codex":0.0000030170647,"about_ca_topic_score_gemma":0.0000152234525,"teacher_disagreement_score":0.45492098,"about_ca_system_score_codex":0.000056521552,"about_ca_system_score_gemma":0.0001299055,"threshold_uncertainty_score":0.99911743},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2298566148","doi":"10.1016/j.jclinepi.2010.12.007","title":"Outcomes assessment in the SPRINT multicenter tibial fracture trial: Adjudication committee size has trivial effect on trial results","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone fractures and treatments","field":"Medicine","cited_by":10,"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 Arthritis and Musculoskeletal and Skin Diseases; Canadian Institutes of Health Research; Health Canada; U.S. Public Health Service; National Institutes of Health","keywords":"Adjudication; Medicine; Sprint; Clinical trial; Dominance (genetics); Physical therapy; Law; Internal medicine; Political science","score_opus":0.30809860631982977,"score_gpt":0.5236427233620363,"score_spread":0.21554411704220655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298566148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94024813,0.000050936087,0.00024932632,0.053274147,0.0034166402,0.001633059,0.0000063651805,0.000010876869,0.0011105397],"genre_scores_gemma":[0.98072416,0.000098085424,0.0020913298,0.01478092,0.002202653,0.000024060544,0.000009682809,0.00001726226,0.000051832772],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.9848428,0.00894277,0.0050763623,0.00035086283,0.0004231167,0.00036413237],"domain_scores_gemma":[0.922447,0.071780786,0.004733281,0.0006423453,0.00012641466,0.00027014682],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029233174,0.00027894913,0.002986525,0.00010791023,0.000068415815,0.00001044977,0.00032082765,0.000599776,0.00012356146],"category_scores_gemma":[0.1038884,0.00012844182,0.001300619,0.00008833254,0.00021560326,0.00006477702,0.00004114144,0.0025743144,0.000028152268],"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":[0.67298305,0.004241767,0.2990667,0.000009593833,0.00045104005,0.00020193931,0.00013963047,0.000009209669,0.000001509664,0.00012728586,0.0062790914,0.016489182],"study_design_scores_gemma":[0.33471385,0.021540238,0.6345326,0.00007114419,0.00029716155,0.000021252376,0.000013786177,0.000027863678,0.000006572368,0.00071168086,0.0079991715,0.00006468909],"about_ca_topic_score_codex":0.00022624272,"about_ca_topic_score_gemma":0.000050871604,"teacher_disagreement_score":0.3382692,"about_ca_system_score_codex":0.000089190384,"about_ca_system_score_gemma":0.000295007,"threshold_uncertainty_score":0.9997268},"labels":[],"label_agreement":null},{"id":"W2299177375","doi":"10.1016/j.jclinepi.2016.01.021","title":"PRESS Peer Review of Electronic Search Strategies: 2015 Guideline Statement","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":5631,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Checklist; Guideline; MEDLINE; Evidence-based medicine; Computer science; Information retrieval; Peer review; Systematic review; World Wide Web; Medicine; Psychology; Political science","score_opus":0.9459189151653383,"score_gpt":0.7496451704072284,"score_spread":0.19627374475810988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299177375","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":[0.013216032,0.12719265,0.51073927,0.3394406,0.0017469194,0.00096329534,0.00004172373,0.0000036089384,0.006655926],"genre_scores_gemma":[0.2849455,0.49410853,0.09713859,0.03774351,0.0045681335,0.000036118803,0.000016507687,0.00007894589,0.08136416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.4746425,0.27750817,0.23190095,0.0016648275,0.012911725,0.0013718538],"domain_scores_gemma":[0.4278694,0.39286914,0.13247631,0.0068045696,0.03881461,0.0011659511],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86241543,0.00025340277,0.015201586,0.00019024496,0.00003016068,0.00003847743,0.0026224575,0.00020554963,0.014519178],"category_scores_gemma":[0.7956264,0.00008312746,0.0054575503,0.00038574447,0.00026083816,0.00030744929,0.00017659971,0.0006179166,0.00055687124],"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":[0.000048451537,0.00009544157,0.009862359,0.0002658667,0.00045470928,0.00000394541,0.000011367626,0.00008510403,0.000010700057,0.009284843,0.9342421,0.045635108],"study_design_scores_gemma":[0.00048563138,0.0006982718,0.0040863305,0.0011283745,0.00026308783,0.000036542075,0.00007115835,0.00038878058,0.0000036169845,0.044005074,0.94874144,0.00009167968],"about_ca_topic_score_codex":0.000012088504,"about_ca_topic_score_gemma":0.000008599408,"teacher_disagreement_score":0.41360065,"about_ca_system_score_codex":0.000048804875,"about_ca_system_score_gemma":0.0010281642,"threshold_uncertainty_score":0.9994188},"labels":[],"label_agreement":null},{"id":"W2313855642","doi":"10.1016/j.jclinepi.2015.09.020","title":"N of 1 randomized trials: a commentary","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Randomized controlled trial; Scopus; Alternative medicine; Medicine; MEDLINE; Psychotherapist; Psychology; Internal medicine; Pathology","score_opus":0.96670361408558,"score_gpt":0.7341851358766442,"score_spread":0.23251847820893579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313855642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18211351,0.0047298777,0.47968742,0.3267037,0.0042259265,0.0007957285,0.000018429795,0.0000017077134,0.001723698],"genre_scores_gemma":[0.9170404,0.0024201311,0.057341356,0.019512026,0.0019062513,0.000009289822,6.005383e-7,0.000011281747,0.0017586851],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.06481004,0.72737753,0.20405625,0.00057176885,0.0028854727,0.00029891374],"domain_scores_gemma":[0.009761043,0.8490897,0.13703221,0.0017344351,0.0020667347,0.00031589033],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9645859,0.00019720363,0.062067132,0.00033685923,0.000025159794,0.00001981602,0.0019395633,0.00024180485,0.012533538],"category_scores_gemma":[0.98808336,0.000051941395,0.026722841,0.00030418328,0.0005724194,0.00014779052,0.00011408911,0.0003420448,0.0003487905],"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":[0.010102252,0.00014416562,0.108907305,0.000012117281,0.0021506846,0.000006402453,0.000035657642,0.0000103037455,0.000021468133,0.010512021,0.7400364,0.1280612],"study_design_scores_gemma":[0.085169025,0.00054294977,0.02136548,0.00020973729,0.002047942,0.00006775498,0.00012073777,0.0006605731,0.00001153611,0.539289,0.3503765,0.00013874484],"about_ca_topic_score_codex":0.0000058878836,"about_ca_topic_score_gemma":0.0000022848342,"teacher_disagreement_score":0.7349269,"about_ca_system_score_codex":0.000011879125,"about_ca_system_score_gemma":0.00011413208,"threshold_uncertainty_score":0.98836917},"labels":[],"label_agreement":null},{"id":"W2313883229","doi":"10.1016/j.jclinepi.2016.03.021","title":"To meta-analyze or not to meta-analyze? A combined meta-analysis of N-of-1 trial data with RCT data on amphetamines and methylphenidate for pediatric ADHD","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Attention Deficit Hyperactivity Disorder","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Methylphenidate; Meta-analysis; Impulsivity; Medicine; Attention deficit hyperactivity disorder; Confidence interval; N of 1 trial; Publication bias; Clinical psychology; Psychology; Internal medicine","score_opus":0.8767111707385405,"score_gpt":0.647943573220267,"score_spread":0.22876759751827358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313883229","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":[0.0008756264,0.9304576,0.03017862,0.022221342,0.0006419864,0.0049518594,0.010635407,0.000018360903,0.000019210547],"genre_scores_gemma":[0.0006858398,0.9353481,0.0550313,0.003807362,0.0017004292,0.00021540246,0.0012851118,0.00018630088,0.0017401791],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9605314,0.014933725,0.020053567,0.0024018574,0.0013353883,0.000744077],"domain_scores_gemma":[0.7755745,0.1881482,0.026085908,0.00708748,0.0019013264,0.0012025799],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.08606025,0.0013013568,0.08195608,0.0026521375,0.000067338464,0.000023574388,0.0030760283,0.0010192384,0.0020110745],"category_scores_gemma":[0.2886977,0.0005425704,0.023199845,0.0024666074,0.00035147104,0.00036632383,0.0012946367,0.0014992283,0.000027049278],"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":[0.03649517,0.0011941943,0.00011463911,0.0019735538,0.9252842,0.00003943436,0.000009006992,0.000056313776,4.5328116e-7,0.00009179558,0.008407932,0.026333308],"study_design_scores_gemma":[0.0077160276,0.0059889876,0.00009944923,0.0001089308,0.7525219,0.000056059678,0.00001736602,0.00007995948,1.7237342e-7,0.000042731186,0.23300105,0.00036739948],"about_ca_topic_score_codex":0.00006397941,"about_ca_topic_score_gemma":0.00015481607,"teacher_disagreement_score":0.22459312,"about_ca_system_score_codex":0.00004581596,"about_ca_system_score_gemma":0.0013956757,"threshold_uncertainty_score":0.9999738},"labels":[],"label_agreement":null},{"id":"W2316616299","doi":"10.1016/j.jclinepi.2016.03.015","title":"Psychometric properties of the Neck OutcOme Score, Neck Disability Index, and Short Form–36 were evaluated in patients with neck pain","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Toronto; University Health Network","funders":"Syddansk Universitet","keywords":"Medicine; Neck pain; Physical therapy; Internal medicine; Physical medicine and rehabilitation; Alternative medicine; Pathology","score_opus":0.15247730267184953,"score_gpt":0.4342067087893107,"score_spread":0.2817294061174612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316616299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988601,0.00020346603,0.00017809718,0.009968178,0.00036402376,0.0006347129,0.0000028661311,0.0000052827218,0.000042314303],"genre_scores_gemma":[0.9979143,0.00010193658,0.00057431235,0.0012126382,0.000141275,0.000006003859,0.0000012259777,0.000013737077,0.00003458101],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912413,0.0035259023,0.0042325812,0.00029046964,0.00041209214,0.0002976799],"domain_scores_gemma":[0.98852533,0.008790629,0.0015199461,0.0004515856,0.0004554734,0.0002570591],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024205785,0.00018629768,0.002026474,0.00015450083,0.00003244142,0.0000024905617,0.00019034451,0.00033365106,0.000049981118],"category_scores_gemma":[0.13060859,0.00006777653,0.00046865531,0.00038210122,0.0010980774,0.00013187772,0.00006088243,0.0006932412,0.0000013748235],"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":[0.0032816816,0.0007530022,0.93685186,0.00032107517,0.000084879066,3.336938e-7,0.000026744947,0.00001053041,0.000021105367,0.000029535513,0.00015926892,0.05845997],"study_design_scores_gemma":[0.0056520915,0.004534434,0.9868378,0.0011097717,0.00006214487,0.0000037651962,0.000026697617,0.00022736232,0.000002907708,0.0012873904,0.00016557323,0.00009006454],"about_ca_topic_score_codex":0.00003027633,"about_ca_topic_score_gemma":0.000041835247,"teacher_disagreement_score":0.1064028,"about_ca_system_score_codex":0.00008307194,"about_ca_system_score_gemma":0.00014649866,"threshold_uncertainty_score":0.87671465},"labels":[],"label_agreement":null},{"id":"W2322140854","doi":"10.1016/j.jclinepi.2016.03.018","title":"Interpreting GRADE's levels of certainty or quality of the evidence: GRADE for statisticians, considering review information size or less emphasis on imprecision?","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":73,"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; Health Sciences Centre","funders":"","keywords":"Certainty; Grading (engineering); Systematic review; Guideline; Psychology; Quality (philosophy); Actuarial science; Management science; MEDLINE; Medicine; Epistemology; Economics","score_opus":0.9591089740372083,"score_gpt":0.7215801648802531,"score_spread":0.23752880915695518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322140854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24220383,0.0051504653,0.6721424,0.07494522,0.0029153307,0.0022049812,0.00030817758,0.0000039521206,0.00012565707],"genre_scores_gemma":[0.9387789,0.005623503,0.04754533,0.007508301,0.00018439734,0.000017352828,3.9144527e-7,0.000009476757,0.0003323648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.76470417,0.13405883,0.0963514,0.0006938799,0.003714233,0.00047747634],"domain_scores_gemma":[0.10531992,0.8136297,0.075331256,0.0020040872,0.0034893607,0.00022568423],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5788688,0.00026421103,0.012184108,0.00015469448,0.00007910374,0.00003274429,0.0020194538,0.00023053898,0.00197236],"category_scores_gemma":[0.9765955,0.00007471815,0.0046728915,0.0005220926,0.00038833573,0.0004531388,0.00018386649,0.0003946295,0.000026880434],"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":[0.0014212029,0.00016679021,0.110136636,0.0020734323,0.00074644183,0.0000022932554,0.0002599317,0.000118085554,0.00009271824,0.007280022,0.07479164,0.8029108],"study_design_scores_gemma":[0.0044302363,0.004281042,0.6273815,0.057429723,0.0021216965,0.00017342027,0.0018669913,0.002928906,0.00022420337,0.21103962,0.087448426,0.00067425263],"about_ca_topic_score_codex":0.000015871134,"about_ca_topic_score_gemma":0.00003720784,"teacher_disagreement_score":0.80223656,"about_ca_system_score_codex":0.000045219072,"about_ca_system_score_gemma":0.00049992086,"threshold_uncertainty_score":0.99894},"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":"low"}],"label_agreement":"agree"},{"id":"W2329913395","doi":"10.1016/j.jclinepi.2015.08.032","title":"Systematic reviews are not enough: policymakers need a greater variety of synthesized evidence","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Climate Change and Health Impacts","field":"Environmental Science","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 Toronto; Public Health Ontario","funders":"","keywords":"Variety (cybernetics); Systematic review; Medicine; Evidence-based medicine; Evidence-based policy; MEDLINE; Economics; Public economics; Political science; Alternative medicine; Computer science","score_opus":0.6367893331315863,"score_gpt":0.5295989180746242,"score_spread":0.10719041505696203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329913395","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":[0.003260313,0.0024600364,0.00031090216,0.99074924,0.001773354,0.0011156104,0.000043567987,0.000011776395,0.0002752241],"genre_scores_gemma":[0.0030296284,0.032443766,0.0018573318,0.9536427,0.00806277,0.000036393278,0.0000029413284,0.000058351856,0.00086611963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96761554,0.017703177,0.012430953,0.0005733025,0.00061885186,0.00105818],"domain_scores_gemma":[0.8704243,0.10440004,0.023576949,0.0009514377,0.000115412644,0.0005318941],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.0615224,0.00053650356,0.011117391,0.00015156536,0.00007101982,0.000010041309,0.0011492054,0.0019808405,0.0020065904],"category_scores_gemma":[0.2703142,0.00028567755,0.0018919403,0.00018456024,0.0008045106,0.00020095537,0.00028400918,0.0029242665,0.0006990585],"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":[0.00030328915,0.00004090267,0.019248225,0.013612298,0.00012919371,0.00017340477,0.00010305029,0.000002832022,0.00003435907,0.000006376729,0.965001,0.0013450534],"study_design_scores_gemma":[0.002151535,0.0028534844,0.04516567,0.19098938,0.0017292651,0.0010158588,0.000053435877,0.000062043146,0.000025033869,0.0029683653,0.751982,0.0010039692],"about_ca_topic_score_codex":0.00012796266,"about_ca_topic_score_gemma":0.000021774562,"teacher_disagreement_score":0.21301906,"about_ca_system_score_codex":0.00029448722,"about_ca_system_score_gemma":0.00012697517,"threshold_uncertainty_score":0.9999595},"labels":[],"label_agreement":null},{"id":"W2332511819","doi":"10.1016/j.jclinepi.2016.03.025","title":"A third of systematic reviews changed or did not specify the primary outcome: a PROSPERO register study","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Canadian Agency for Drugs and Technologies in Health; Canada Research Chairs; University of Ottawa; University of Toronto; St. Michael's Hospital","funders":"National Institute for Health and Care Research; Canadian Institutes of Health Research; University of Ottawa","keywords":"Register (sociolinguistics); Outcome (game theory); Medicine; Family medicine; Linguistics; Mathematics; Philosophy","score_opus":0.973059586795305,"score_gpt":0.7017350610403976,"score_spread":0.2713245257549074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2332511819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6607638,0.02269896,0.085503444,0.18998541,0.011888866,0.024647303,0.00004520236,0.000015444251,0.0044515613],"genre_scores_gemma":[0.92579305,0.0039873566,0.013071754,0.01792451,0.002385559,0.00021117058,4.3457655e-7,0.000039492206,0.036586657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.36173517,0.41012102,0.21928465,0.0015963922,0.0064931195,0.0007696474],"domain_scores_gemma":[0.24820343,0.55665314,0.18293864,0.008427211,0.003244152,0.00053344853],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.83257693,0.00043666648,0.041071776,0.00029976983,0.000091395144,0.00007756902,0.0044674375,0.0002855428,0.0023403973],"category_scores_gemma":[0.908933,0.00009707595,0.01089545,0.0007690291,0.00042844616,0.00023656478,0.00034653806,0.0007659407,0.0012175393],"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":[0.0005755729,0.00074020936,0.80445004,0.0036884523,0.0013416947,0.000047723985,0.00047284696,0.0000027723536,0.000022760589,0.0012581903,0.17224659,0.015153172],"study_design_scores_gemma":[0.0037533364,0.00439577,0.81431526,0.008494236,0.0036926465,0.0005016407,0.000981987,0.00015760295,0.0000029123798,0.010053804,0.15318087,0.00046996397],"about_ca_topic_score_codex":0.000004040135,"about_ca_topic_score_gemma":0.000042513737,"teacher_disagreement_score":0.26502925,"about_ca_system_score_codex":0.00004986512,"about_ca_system_score_gemma":0.00015475738,"threshold_uncertainty_score":0.9995601},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2335578498","doi":"10.1016/j.jclinepi.2016.03.019","title":"Conclusiveness resolves the conflict between quality of evidence and imprecision in GRADE","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Lunds Universitet; University of Leeds; McMaster University; Carnegie Mellon University","keywords":"Grading (engineering); Quality (philosophy); Confusion; Context (archaeology); Computer science; Probabilistic logic; Meaning (existential); Management science; Risk analysis (engineering); Psychology; Epistemology; Medicine; Artificial intelligence; Engineering","score_opus":0.9862394516335407,"score_gpt":0.7652168744777704,"score_spread":0.22102257715577023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335578498","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93351305,0.004296015,0.025911989,0.0356029,0.00038860764,0.00020186898,0.0000061749633,5.294331e-7,0.00007886281],"genre_scores_gemma":[0.9939807,0.002487169,0.0021636493,0.00081195554,0.000288566,0.0000017000774,8.765488e-8,0.000003585189,0.00026259676],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4374651,0.43389115,0.12212446,0.0012982709,0.0046512634,0.0005697521],"domain_scores_gemma":[0.081222184,0.8696195,0.045336645,0.0019758304,0.0015786543,0.00026722695],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7890723,0.00016912258,0.011652875,0.0002010116,0.000046882833,0.000027919792,0.0019282306,0.0002485211,0.00048676386],"category_scores_gemma":[0.90425426,0.00004323985,0.0025055192,0.0004014348,0.00073553965,0.0002363556,0.00028187828,0.00044972703,0.000044376204],"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":[0.000071268594,0.000025375337,0.9120274,0.000013421028,0.00009000432,0.0000019002039,0.00006789864,0.0000070967194,0.00007755908,0.0020284883,0.0027289004,0.08286065],"study_design_scores_gemma":[0.0004397959,0.00022511285,0.90976816,0.00027350333,0.00007355614,0.000011270711,0.00008835431,0.00007415856,0.000011492585,0.070021674,0.018959695,0.00005323835],"about_ca_topic_score_codex":0.00003294015,"about_ca_topic_score_gemma":0.000027723032,"teacher_disagreement_score":0.4357283,"about_ca_system_score_codex":0.000014952479,"about_ca_system_score_gemma":0.0001396173,"threshold_uncertainty_score":0.7965672},"labels":[],"label_agreement":null},{"id":"W2337029825","doi":"10.1016/j.jclinepi.2016.03.026","title":"N-of-1 trials can be aggregated to generate group mean treatment effects: a systematic review and meta-analysis","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Attention Deficit Hyperactivity Disorder","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Medicine; Systematic review; MEDLINE; Internal medicine; Biology","score_opus":0.6861744411904618,"score_gpt":0.6116342597211579,"score_spread":0.07454018146930386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337029825","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":[0.000052268486,0.9826887,0.0011817511,0.011574438,0.00020965077,0.004151303,0.00011840402,0.0000101458345,0.000013319073],"genre_scores_gemma":[0.000073878226,0.99226713,0.0015937084,0.004928824,0.00025077202,0.00023117625,0.000034185374,0.000052304156,0.00056799507],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9226422,0.054928653,0.021015937,0.0006503402,0.00037196538,0.00039096037],"domain_scores_gemma":[0.835396,0.1325099,0.02957025,0.0010720465,0.0006307093,0.0008210805],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.07480909,0.0007723412,0.10561789,0.00073916756,0.0000364413,0.000007645387,0.00029637743,0.00082626415,0.0003362958],"category_scores_gemma":[0.27124992,0.00032333075,0.024216361,0.0007187487,0.00017837647,0.00005340686,0.00007998569,0.0008135164,0.000023039374],"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":[0.00008295522,0.0004000622,0.00005680683,0.45924714,0.51151824,0.000101932856,0.000008000075,0.00000110359,3.3341374e-7,0.00011433391,0.00043212375,0.028036999],"study_design_scores_gemma":[0.0010844494,0.0020032004,0.000015472127,0.06791237,0.88334215,0.00044820574,0.0000055816827,0.0000020470031,8.5947015e-8,0.000031404834,0.04494233,0.00021270012],"about_ca_topic_score_codex":0.00003441159,"about_ca_topic_score_gemma":0.000033065382,"teacher_disagreement_score":0.39133477,"about_ca_system_score_codex":0.0001597193,"about_ca_system_score_gemma":0.00047292278,"threshold_uncertainty_score":0.99992186},"labels":[],"label_agreement":null},{"id":"W2342819438","doi":"10.1016/j.jclinepi.2016.03.028","title":"N-of-1 trials to enhance patient outcomes: identifying effective therapies and reducing harms, one patient at a time","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Alberta Health; University of Alberta","funders":"","keywords":"Medicine; Randomized controlled trial; N of 1 trial; Clinical trial; Alternative medicine; Intensive care medicine; MEDLINE; Physical therapy; Internal medicine; Pathology","score_opus":0.7547227347869369,"score_gpt":0.6748657510380461,"score_spread":0.07985698374889072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342819438","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8163019,0.00038678222,0.16749662,0.012529275,0.0021650873,0.00096636394,0.000057763213,0.00001868912,0.00007751933],"genre_scores_gemma":[0.26113677,0.0005276893,0.7356792,0.0019759277,0.00050233887,0.00003330369,1.8392242e-7,0.000038964492,0.00010562609],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9426396,0.039581828,0.016153932,0.0005966279,0.0005062312,0.00052176893],"domain_scores_gemma":[0.24153024,0.7462538,0.010702818,0.00048672853,0.0005169382,0.00050951145],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12065779,0.00031173322,0.008462949,0.00016636297,0.00006767567,0.000009009351,0.0003383354,0.00046143786,0.00036299185],"category_scores_gemma":[0.9296913,0.00016414069,0.0012246827,0.00013490052,0.0005267187,0.00010197476,0.00035330304,0.00060841354,0.000043652315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050211013,0.0009310865,0.033406608,0.00019042147,0.001876649,0.000029662073,0.0006806223,0.000005680319,0.00736078,0.0079126535,0.008323668,0.9342611],"study_design_scores_gemma":[0.0030817676,0.006806772,0.044175558,0.0019412879,0.00051461667,0.000032143074,0.000050750452,0.000017437103,0.0049581425,0.93640757,0.0016868198,0.00032711786],"about_ca_topic_score_codex":0.000006669831,"about_ca_topic_score_gemma":0.0000011378363,"teacher_disagreement_score":0.933934,"about_ca_system_score_codex":0.00010392034,"about_ca_system_score_gemma":0.00008644677,"threshold_uncertainty_score":0.90546787},"labels":[],"label_agreement":null},{"id":"W2343793418","doi":"10.1016/j.jclinepi.2016.03.027","title":"Baseline risk has greater influence over behavioral attrition on the real-world clinical effectiveness of cardiac rehabilitation","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac Health and Mental Health","field":"Medicine","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":"Institute for Clinical Evaluative Sciences; Toronto Rehabilitation Institute; University of Toronto; University of British Columbia; University Health Network","funders":"","keywords":"Attrition; Medicine; Logistic regression; Rehabilitation; Number needed to treat; Physical therapy; Demography; Relative risk; Confidence interval; Internal medicine","score_opus":0.2716291870263497,"score_gpt":0.5572525349626186,"score_spread":0.2856233479362689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343793418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816332,0.00011418107,0.00023667187,0.015354068,0.0018488796,0.0006305196,0.000056356104,0.000009638037,0.00011652345],"genre_scores_gemma":[0.9919818,0.0028070838,0.0010534044,0.0027317887,0.001353359,0.000015685635,0.000005391173,0.00001712542,0.00003434852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96641904,0.026773226,0.005752984,0.00034256733,0.00033217328,0.000379988],"domain_scores_gemma":[0.83249265,0.16306734,0.0029027003,0.00045153577,0.0005255188,0.000560276],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1111246,0.00017983097,0.0029987495,0.000155429,0.00007814216,0.0000022066167,0.00012403981,0.00038395094,0.00006288604],"category_scores_gemma":[0.10397624,0.000085436404,0.0015984531,0.00017359192,0.0008397048,0.00009251947,0.000037484333,0.001165633,0.000025614003],"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":[0.009352545,0.00051814876,0.95460457,0.00016618143,0.0000685876,0.000007913906,0.000016602115,0.00000538387,0.000085567895,0.00040380753,0.0023891863,0.03238153],"study_design_scores_gemma":[0.0034169261,0.01017987,0.9785083,0.0013512826,0.00027963307,0.000017427692,0.000016596763,0.0000118232265,0.000067007546,0.0016223696,0.004453148,0.00007560802],"about_ca_topic_score_codex":0.00046097752,"about_ca_topic_score_gemma":0.000027833818,"teacher_disagreement_score":0.13629413,"about_ca_system_score_codex":0.0001842865,"about_ca_system_score_gemma":0.00061125,"threshold_uncertainty_score":0.9152843},"labels":[],"label_agreement":null},{"id":"W2345125329","doi":"10.1016/j.jclinepi.2016.04.006","title":"The Single-Case Reporting Guideline In BEhavioural Interventions (SCRIBE) 2016 Statement","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":144,"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; University of British Columbia; Ottawa Hospital; Children's Hospital of Eastern Ontario; University of Alberta","funders":"Centre of Excellence in Cognition and its Disorders, Australian Research Council","keywords":"Consolidated Standards of Reporting Trials; Checklist; Guideline; CLARITY; Psychological intervention; Research design; Transparency (behavior); Medicine; Medical education; Alternative medicine; Psychology; Computer science; Nursing","score_opus":0.9053171845554374,"score_gpt":0.6314632220215689,"score_spread":0.2738539625338685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345125329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9102437,0.0033554717,0.0067694522,0.071758494,0.006599248,0.00019063122,0.000011573301,0.000019123996,0.001052328],"genre_scores_gemma":[0.9914864,0.000775739,0.0027506736,0.0017621062,0.0007705286,0.000018681983,0.0000011483618,0.000014756121,0.0024199698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97133356,0.00541899,0.022109875,0.00036185025,0.00014993911,0.00062578125],"domain_scores_gemma":[0.96443766,0.019895399,0.014679364,0.00039335462,0.0003440974,0.00025010397],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067023806,0.00019767255,0.0017229818,0.000082496226,0.00014465736,0.000009246929,0.00037307906,0.00030949694,0.0009649569],"category_scores_gemma":[0.06642975,0.00008067908,0.0012679122,0.0001269688,0.00058598124,0.00008931049,0.00013948597,0.00083963486,0.00009600765],"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":[0.0004050945,0.0007672092,0.510781,0.0000026371686,0.000106923195,0.002289821,0.000052739597,9.4604985e-7,0.00001907355,0.0014187237,0.08483971,0.3993161],"study_design_scores_gemma":[0.0029523175,0.003053285,0.8411155,0.00033938154,0.00012843538,0.004009496,0.0006367069,0.0000021390586,0.0000027564133,0.01774779,0.12980424,0.00020799586],"about_ca_topic_score_codex":0.0001676581,"about_ca_topic_score_gemma":0.00032936857,"teacher_disagreement_score":0.3991081,"about_ca_system_score_codex":0.00006600953,"about_ca_system_score_gemma":0.000037931695,"threshold_uncertainty_score":0.9999483},"labels":[],"label_agreement":null},{"id":"W2386513494","doi":"10.1016/j.jclinepi.2016.03.023","title":"N-of-1 trials are a tapestry of heterogeneity","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Children's Hospital of Eastern Ontario; Ottawa Hospital; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Blinding; Meta-analysis; Clinical trial; Medicine; Research design; Clinical study design; Psychological intervention; MEDLINE; Randomization; Family medicine; Internal medicine; Statistics; Nursing","score_opus":0.9859669899307759,"score_gpt":0.7796351677747236,"score_spread":0.20633182215605228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2386513494","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021606711,0.9852253,0.010013202,0.0008398897,0.0026456267,0.00051314547,0.00010290573,8.127325e-7,0.00044304857],"genre_scores_gemma":[0.00014330297,0.9911585,0.00641669,0.00025096277,0.0014183163,0.000007175871,0.0000018030782,0.00001896721,0.00058430544],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.12955086,0.56627494,0.29841122,0.001258993,0.0040258886,0.00047810897],"domain_scores_gemma":[0.037934452,0.58329797,0.37192148,0.003587227,0.002806497,0.00045236922],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8938226,0.0006159151,0.15264896,0.00076795253,0.000029755669,0.000029378169,0.004950728,0.0015335039,0.007552747],"category_scores_gemma":[0.9661694,0.00019921543,0.06857475,0.00077013794,0.0005211157,0.00011454932,0.00030552997,0.0012882716,0.0005769396],"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":[0.00003186218,0.00011173735,0.009061826,0.0030204176,0.0028804187,0.000013201684,0.0000028644558,0.0000023689097,9.370046e-8,0.00073491887,0.048028853,0.93611145],"study_design_scores_gemma":[0.0003107066,0.00030356902,0.0011826846,0.009682348,0.003919325,0.00015097692,0.0000074500713,0.00000740582,2.0312814e-7,0.008662683,0.97562593,0.00014671043],"about_ca_topic_score_codex":0.0000017678834,"about_ca_topic_score_gemma":0.0000028817308,"teacher_disagreement_score":0.9359647,"about_ca_system_score_codex":0.000025174764,"about_ca_system_score_gemma":0.0009813352,"threshold_uncertainty_score":0.9997627},"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":"W2407348336","doi":"10.1016/j.jclinepi.2016.03.033","title":"Pharmacosurveillance without borders: electronic health records in different countries can be used to address important methodological issues in estimating the risk of adverse events","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","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":"Ottawa Hospital; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Hazard ratio; Confidence interval; Comorbidity; Medical prescription; Pharmacoepidemiology; Proportional hazards model; Health records; Type 2 diabetes; Diabetes mellitus; Electronic health record; Adverse effect; Obesity; Emergency medicine; Environmental health; Internal medicine; Health care; Pharmacology","score_opus":0.4881862941247638,"score_gpt":0.6341412808256246,"score_spread":0.14595498670086082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407348336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91103786,0.00088269723,0.0014598004,0.084022485,0.0019915013,0.00046122647,0.0001099114,0.000014375323,0.000020115558],"genre_scores_gemma":[0.9693474,0.01839947,0.0015276927,0.009921969,0.0006990931,0.000030978037,0.0000032814926,0.000018684064,0.000051404604],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96943337,0.023634704,0.0053231856,0.00041150604,0.00024131306,0.00095593027],"domain_scores_gemma":[0.942237,0.05246289,0.0044646477,0.00024861307,0.00016830936,0.00041851043],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049650393,0.00031767754,0.0028747984,0.00022777908,0.00011277816,0.0000015152681,0.00059695326,0.0003703449,0.000251204],"category_scores_gemma":[0.03054735,0.00016496364,0.00049788697,0.00027902194,0.00040921985,0.00012823992,0.00008871092,0.0025594893,0.0000061775604],"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":[0.0024605233,0.00045685383,0.98306996,0.000034367353,0.0003058317,0.00003018158,0.00036993012,0.004785805,0.00056558364,0.00021115121,0.0020750903,0.005634727],"study_design_scores_gemma":[0.011890637,0.001957685,0.8607239,0.00045755165,0.00024151066,0.00011679223,0.000368459,0.0065861773,0.0010545173,0.008103296,0.10804537,0.0004540943],"about_ca_topic_score_codex":0.00042590944,"about_ca_topic_score_gemma":0.0018590156,"teacher_disagreement_score":0.12234604,"about_ca_system_score_codex":0.00025637873,"about_ca_system_score_gemma":0.0007334494,"threshold_uncertainty_score":0.9997417},"labels":[],"label_agreement":null},{"id":"W2408781124","doi":"10.1016/j.jclinepi.2016.05.006","title":"The need for ethics as well as evidence in evidence-based medicine","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Scopus; Evidence-based medicine; Alternative medicine; MEDLINE; Clinical Practice; Medicine; Psychological intervention; Empirical evidence; Evidence-based practice; Publication bias; Engineering ethics; Medical education; Psychology; Family medicine; Political science; Epistemology; Psychiatry; Pathology; Law; Philosophy; Engineering","score_opus":0.8911447138856542,"score_gpt":0.7168175374562369,"score_spread":0.1743271764294173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408781124","genre_codex":"commentary","genre_gemma":"empirical","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":[0.10694247,0.0029723356,0.024076112,0.8629456,0.0023070828,0.0005973266,0.0000011826867,0.000011686218,0.00014617179],"genre_scores_gemma":[0.76735497,0.034771115,0.010448559,0.18106394,0.0053742337,0.00002906237,0.0000019577146,0.000036944835,0.000919246],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9725141,0.011729137,0.013966097,0.00046219706,0.0007242137,0.000604279],"domain_scores_gemma":[0.11101208,0.8788976,0.0069820443,0.000625892,0.0019217976,0.0005605523],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21582226,0.00021417227,0.002373477,0.00016180956,0.00010693477,0.0000067335145,0.0004908254,0.00064873946,0.0006030382],"category_scores_gemma":[0.96392304,0.00009486265,0.0007568028,0.00023526578,0.0010484757,0.0003816755,0.00007043269,0.002188335,0.00020070044],"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":[0.042340335,0.0004065198,0.59223044,0.00018785796,0.00026958814,0.0001452946,0.000078353805,0.000078506644,0.000829771,0.0074202335,0.13637207,0.21964101],"study_design_scores_gemma":[0.026296241,0.027696038,0.30494526,0.013119052,0.00092422834,0.00051443407,0.0005529557,0.0015219094,0.00013997982,0.14336818,0.480615,0.00030674168],"about_ca_topic_score_codex":0.00024543097,"about_ca_topic_score_gemma":0.00016252037,"teacher_disagreement_score":0.8671685,"about_ca_system_score_codex":0.00014982624,"about_ca_system_score_gemma":0.0026073505,"threshold_uncertainty_score":0.9507348},"labels":[],"label_agreement":null},{"id":"W2409498199","doi":"10.1016/j.jclinepi.2016.06.003","title":"A systematic review reveals that the credibility of subgroup claims in low back pain trials was low","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":49,"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":"Subgroup analysis; Credibility; Medicine; Publication bias; Randomized controlled trial; Clinical trial; Actuarial science; Meta-analysis; Internal medicine; Law; Economics; Political science","score_opus":0.9483505888185008,"score_gpt":0.7043297522389601,"score_spread":0.24402083657954066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409498199","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017763346,0.9795859,0.007525721,0.004229451,0.0018476911,0.0065502906,0.00005957696,0.0000018089106,0.00018183673],"genre_scores_gemma":[0.00004647125,0.99293494,0.0013457861,0.0033459915,0.0009291672,0.00013037023,0.0000053540557,0.000036663678,0.0012252617],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.021795874,0.72333086,0.2480222,0.0015990552,0.0045494414,0.0007025678],"domain_scores_gemma":[0.012361396,0.70314574,0.27362865,0.008024305,0.0023166495,0.00052325777],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9797639,0.0011681127,0.20962931,0.00077564816,0.000068483816,0.0001097996,0.009487819,0.0016153126,0.007067078],"category_scores_gemma":[0.98077786,0.00032903452,0.061804995,0.0019308673,0.0007453293,0.00024706317,0.00043878087,0.002718537,0.002167951],"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":[0.000026849011,0.00017731126,0.0015576434,0.709625,0.0021800844,0.00001899506,0.000012845166,0.0000016781584,1.6630375e-8,0.00046633446,0.08462331,0.20130992],"study_design_scores_gemma":[0.00037822238,0.0002616521,0.00023375466,0.7650661,0.0062208073,0.00016137077,0.000025142654,0.00006301449,9.805703e-9,0.02280856,0.2045014,0.00027998118],"about_ca_topic_score_codex":0.0000048975985,"about_ca_topic_score_gemma":0.000012133724,"teacher_disagreement_score":0.20102994,"about_ca_system_score_codex":0.00014723504,"about_ca_system_score_gemma":0.0011224479,"threshold_uncertainty_score":0.9999162},"labels":[],"label_agreement":null},{"id":"W2411524460","doi":"10.1016/j.jclinepi.2016.05.008","title":"Bias was reduced in an open-label trial through the removal of subjective elements from the outcome definition","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; London Health Sciences Centre","funders":"National Institute for Health and Care Research","keywords":"Odds ratio; Outcome (game theory); Medicine; Confidence interval; Odds; Clinical trial; Randomized controlled trial; Internal medicine; Surgery; Physical therapy; Logistic regression; Mathematics","score_opus":0.9746865729568887,"score_gpt":0.711309841829019,"score_spread":0.26337673112786963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2411524460","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96063775,0.0004500773,0.0058991755,0.028969811,0.001852939,0.00072583713,0.00002380632,8.115076e-7,0.0014397838],"genre_scores_gemma":[0.96970564,0.00037964544,0.0229478,0.0054140985,0.0010524708,0.000014405726,0.000002140491,0.0000106236985,0.00047320378],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6163676,0.2957958,0.08320218,0.0010661397,0.0030769,0.00049137976],"domain_scores_gemma":[0.23969524,0.6749151,0.078641586,0.0043220157,0.0021702733,0.00025582092],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6124609,0.00022508444,0.009675876,0.00010304551,0.00009347096,0.00009088376,0.0045996737,0.00026471502,0.0017329545],"category_scores_gemma":[0.7982705,0.000058220285,0.002004703,0.0005351811,0.00039629298,0.00047304196,0.00032519945,0.00065343553,0.00020752469],"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":[0.012476913,0.0012415377,0.812756,0.0000058348105,0.0010119854,0.000038175247,0.0006257231,0.000020038713,0.00015970982,0.03267111,0.03208675,0.10690624],"study_design_scores_gemma":[0.021317428,0.0019842628,0.3317909,0.000121955934,0.0003665852,0.00004644967,0.0006206896,0.00025743173,0.000006333012,0.61833155,0.025030982,0.00012541657],"about_ca_topic_score_codex":0.000114453156,"about_ca_topic_score_gemma":0.00021703963,"teacher_disagreement_score":0.58566046,"about_ca_system_score_codex":0.000035774476,"about_ca_system_score_gemma":0.00023851737,"threshold_uncertainty_score":0.9991796},"labels":[],"label_agreement":null},{"id":"W2414843533","doi":"10.1016/j.jclinepi.2016.05.010","title":"Administrative data measured surgical site infection probability within 30 days of surgery in elderly patients","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Surgical site infection prevention","field":"Medicine","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":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Ottawa; University of Toronto; University Health Network; Ottawa Hospital","funders":"","keywords":"Medicine; Statistic; Surgical site infection; Multivariate statistics; Multivariate analysis; Medical prescription; Diagnosis code; Population; Emergency medicine; Surgery; Internal medicine; Statistics; Environmental health","score_opus":0.48939970368610936,"score_gpt":0.5142769599371421,"score_spread":0.02487725625103271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414843533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943292,0.00007091818,0.0017126217,0.0022569057,0.0011108904,0.00027939474,0.000020871998,0.000013526252,0.00020565746],"genre_scores_gemma":[0.99807566,0.00034380384,0.00091612764,0.00016421247,0.0004308618,0.0000036943586,0.000023742665,0.000011311389,0.0000305831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9832442,0.008311866,0.0073310146,0.0004359586,0.00038829277,0.00028871652],"domain_scores_gemma":[0.94113415,0.051488396,0.005390556,0.0006440234,0.00092960213,0.00041326974],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049903695,0.00017863221,0.002768372,0.00020673162,0.000022632346,0.0000026700952,0.00015727221,0.0005295499,0.0007724496],"category_scores_gemma":[0.1766701,0.00010352615,0.00069824094,0.00027301878,0.0004137747,0.0003199471,0.000097437776,0.00082236744,0.000024189694],"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":[0.0027586282,0.0015528997,0.9434874,0.000052826716,0.00013334783,0.00004300119,0.000012385109,0.0000072888797,0.000057315334,0.00013363069,0.00036146687,0.05139978],"study_design_scores_gemma":[0.004354136,0.002222314,0.9842237,0.00052470394,0.00010028146,0.00014839452,0.0000028520988,0.000048052203,0.00008167476,0.004944704,0.0032512052,0.000097973905],"about_ca_topic_score_codex":0.000065838896,"about_ca_topic_score_gemma":0.00007343305,"teacher_disagreement_score":0.12676641,"about_ca_system_score_codex":0.00011092439,"about_ca_system_score_gemma":0.00049451995,"threshold_uncertainty_score":0.97832406},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2417098700","doi":"10.1016/j.jclinepi.2016.05.007","title":"Geographic and temporal validity of prediction models: different approaches were useful to examine model performance","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","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; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Computer science; Predictive modelling; Statistics; Machine learning; Mathematics","score_opus":0.49036536976274725,"score_gpt":0.4388877148245395,"score_spread":0.05147765493820777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417098700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5573383,0.00010173318,0.43539897,0.0067289467,0.0003174555,0.00007359946,0.0000040912164,0.000013864393,0.00002302208],"genre_scores_gemma":[0.95166737,0.0009503048,0.04657098,0.0004887159,0.00028241886,0.0000040245263,6.2627436e-7,0.000008418104,0.000027118067],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9928764,0.0028742477,0.0032528448,0.00039890877,0.00026728716,0.0003303043],"domain_scores_gemma":[0.98763794,0.009184521,0.0020558585,0.0004789553,0.00022236696,0.00042033853],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015546937,0.0001723114,0.0014992193,0.00020109989,0.000056284603,0.0000066593384,0.00068257103,0.00027547625,0.000003947632],"category_scores_gemma":[0.009597832,0.0000968014,0.00027651608,0.00011449726,0.00020327356,0.0003850588,0.000295277,0.00067725865,0.0000012476763],"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":[0.00009799171,0.000088723194,0.936217,0.000058219288,0.000026792935,0.0000013800827,0.000053923657,0.010803397,0.000007720588,0.004081495,0.00017035485,0.048392974],"study_design_scores_gemma":[0.00038234174,0.0011705651,0.49620882,0.000102587415,0.000009614141,0.000030672098,0.0000023199739,0.48833394,0.0000049563273,0.013619423,0.00007662374,0.000058134276],"about_ca_topic_score_codex":0.000012670482,"about_ca_topic_score_gemma":0.000007481575,"teacher_disagreement_score":0.47753054,"about_ca_system_score_codex":0.00002492213,"about_ca_system_score_gemma":0.00011165604,"threshold_uncertainty_score":0.9987447},"labels":[],"label_agreement":null},{"id":"W2418187183","doi":"10.1016/j.jclinepi.2016.05.009","title":"Administrative database code accuracy did not vary notably with changes in disease prevalence","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","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; University of Ottawa; Ottawa Hospital; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Medicine; Disease; Diagnosis code; Prevalence; Diagnostic test; Diagnostic accuracy; Predictive value of tests; Predictive value; Epidemiology; Internal medicine; Pediatrics; Environmental health; Population","score_opus":0.780034786690256,"score_gpt":0.6598077968546048,"score_spread":0.12022698983565128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418187183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6639759,0.00041380807,0.021415679,0.30976963,0.0023609619,0.0007933268,0.00026341793,0.00003445893,0.00097283],"genre_scores_gemma":[0.9496271,0.006864637,0.00373293,0.03751625,0.0017127504,0.000041780608,0.000008626349,0.000013657137,0.0004822577],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9853108,0.008374738,0.0051064882,0.0002573856,0.00031542944,0.0006351634],"domain_scores_gemma":[0.8700226,0.12291394,0.0051225293,0.00037545915,0.00039292412,0.0011725372],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03715637,0.00016396397,0.001508211,0.00013253586,0.00016835828,0.0000018262587,0.00034915083,0.00032498606,0.00068492943],"category_scores_gemma":[0.24491018,0.00008030669,0.0001280939,0.00012143098,0.00032622012,0.00035169267,0.000092924674,0.0018536819,0.00012619434],"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":[0.0065858327,0.00019107632,0.95448005,0.00092462124,0.00003100126,0.00009226858,0.0004980137,0.000006050096,0.000010606296,0.0035315345,0.0103486655,0.02330025],"study_design_scores_gemma":[0.0037709144,0.0015569858,0.9376025,0.004466909,0.000048689915,0.000014803772,0.00015094833,0.0003412911,0.0000031349748,0.001692435,0.050208338,0.00014302369],"about_ca_topic_score_codex":0.000021027969,"about_ca_topic_score_gemma":0.00021304114,"teacher_disagreement_score":0.2856512,"about_ca_system_score_codex":0.00009327335,"about_ca_system_score_gemma":0.0020228222,"threshold_uncertainty_score":0.99145013},"labels":[],"label_agreement":null},{"id":"W2425813687","doi":"10.1016/j.jclinepi.2016.02.008","title":"Dave Sackett and the ethos of the EBM community","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ethos; Evangelism; Evidence-based medicine; Philosophy; Epistemology; MEDLINE; Political science; Theology; Law","score_opus":0.7490702896193341,"score_gpt":0.6578305694203364,"score_spread":0.09123972019899773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2425813687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70699227,0.00021674525,0.003490986,0.2881294,0.00073147914,0.00018324741,0.0000039222355,0.0000027699118,0.0002491633],"genre_scores_gemma":[0.96030056,0.0015202109,0.0033142893,0.034053925,0.0007030736,0.0000014235201,4.5064832e-7,0.000008286161,0.00009777678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96960014,0.022851935,0.007015427,0.00011394415,0.00023108578,0.00018747279],"domain_scores_gemma":[0.514012,0.4764126,0.007838251,0.0007946071,0.00071247347,0.0002300807],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10732069,0.000099658086,0.0017376429,0.00003189657,0.000084122104,0.0000020050588,0.000324273,0.00019230701,0.00011532848],"category_scores_gemma":[0.6425221,0.00003337782,0.00065838394,0.000081358085,0.00177402,0.00008356197,0.00020797296,0.0016843344,0.000005712891],"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":[0.004775149,0.00026213666,0.8244013,0.00003301985,0.00033095857,0.000004265276,0.0001632448,0.000002452147,0.00018755681,0.004680989,0.017619405,0.14753953],"study_design_scores_gemma":[0.01087966,0.0010597848,0.9154373,0.00021968392,0.0004516028,0.00031420004,0.00037390296,0.00007789384,0.00004239697,0.051765665,0.01933026,0.000047686946],"about_ca_topic_score_codex":0.00012148624,"about_ca_topic_score_gemma":0.00003870252,"teacher_disagreement_score":0.53520143,"about_ca_system_score_codex":0.000020163867,"about_ca_system_score_gemma":0.0002543408,"threshold_uncertainty_score":0.9192012},"labels":[],"label_agreement":null},{"id":"W2463793135","doi":"10.1016/j.jclinepi.2016.03.032","title":"A measurement framework for adherence in patient decision aid trials applied in a systematic review subanalysis","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":20,"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; Université Laval; Centre for Advancing Health Outcomes; Ottawa Hospital; University of British Columbia; Vancouver Coastal Health; Vancouver Coastal Health Research Institute; St. Paul's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Systematic review; MEDLINE; Medical physics","score_opus":0.8819457795077978,"score_gpt":0.691930526216788,"score_spread":0.19001525329100988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463793135","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":[0.000003258467,0.97118866,0.009896957,0.0025689686,0.002339194,0.013912559,0.000041664527,0.000011782367,0.00003695504],"genre_scores_gemma":[0.00007552497,0.96340173,0.025979659,0.0046997056,0.0005094279,0.005254748,0.000011724822,0.00006130854,0.000006148658],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.7373674,0.17992908,0.07963039,0.0009075912,0.0010140279,0.001151522],"domain_scores_gemma":[0.21651542,0.68890846,0.08875237,0.002900826,0.002193162,0.0007297883],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24922954,0.0006612264,0.042379126,0.00090362586,0.00015372982,0.0000044116346,0.0018725916,0.0026046273,0.00013607804],"category_scores_gemma":[0.834774,0.00036170386,0.0046497155,0.0008571933,0.00013167055,0.00008790726,0.00036397376,0.0058418647,0.00014591489],"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":[0.00034640802,0.00018017826,0.0007215438,0.64975125,0.0003590816,0.000005732088,0.00010297312,0.0000013928335,3.4751013e-9,0.0016285972,0.0013724767,0.34553036],"study_design_scores_gemma":[0.0014879416,0.00047081095,0.000034000892,0.82842547,0.001770233,0.000007078422,0.00011968077,0.000008225189,2.6911329e-9,0.02447008,0.14296263,0.00024386271],"about_ca_topic_score_codex":0.00003897436,"about_ca_topic_score_gemma":0.00016590903,"teacher_disagreement_score":0.58554447,"about_ca_system_score_codex":0.0016450767,"about_ca_system_score_gemma":0.004642101,"threshold_uncertainty_score":0.9998835},"labels":[],"label_agreement":null},{"id":"W2466770844","doi":"10.1016/j.jclinepi.2016.07.001","title":"The skills and experience of GRADE methodologists can be assessed with a simple tool","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":144,"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":"World Health Organization","keywords":"Grading (engineering); Guideline; Attendance; Curriculum; Set (abstract data type); Medical education; Computer science; Medical physics; Psychology; Medicine; Pedagogy","score_opus":0.8968567579189125,"score_gpt":0.7908808313834047,"score_spread":0.1059759265355078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466770844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83021075,0.000032105487,0.021902395,0.14701194,0.00050787814,0.00024152656,0.000016498561,0.0000060625753,0.00007083953],"genre_scores_gemma":[0.93096673,0.0008967701,0.028116759,0.0393981,0.00040790538,0.000026403957,2.1198167e-7,0.000009221303,0.00017789347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9669894,0.025887197,0.0059328,0.00023533443,0.00028541943,0.00066984375],"domain_scores_gemma":[0.63438934,0.35946035,0.005108426,0.00028597104,0.00042161564,0.00033429475],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08300156,0.00011765326,0.0014483564,0.00006792318,0.00034468816,0.000002570202,0.0004330823,0.00022290007,0.00009049738],"category_scores_gemma":[0.39842844,0.00004671992,0.00012832269,0.00017700983,0.001335494,0.00013621761,0.00011158207,0.00070590444,0.000003402992],"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":[0.00018686097,0.000039845643,0.9646174,0.000031375326,0.00003123879,0.000005267349,0.0016416352,0.0000016016659,0.0001671599,0.008635302,0.0073542176,0.017288107],"study_design_scores_gemma":[0.0020430172,0.0010060185,0.88299394,0.00012586266,0.00001806076,0.00003335808,0.0014153483,0.000012641114,0.00006785278,0.015864745,0.096336834,0.0000823412],"about_ca_topic_score_codex":0.00017845376,"about_ca_topic_score_gemma":0.00039818083,"teacher_disagreement_score":0.33357316,"about_ca_system_score_codex":0.000053481017,"about_ca_system_score_gemma":0.0013469559,"threshold_uncertainty_score":0.94424284},"labels":[],"label_agreement":null},{"id":"W2468996569","doi":"10.1016/j.jclinepi.2009.06.005","title":"Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":19882,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Johns Hopkins Bloomberg School of Public Health; Cancer Research UK; McMaster University; Ottawa Hospital Research Institute; Johns Hopkins University; University of Ioannina; GlaxoSmithKline; University of Bern; Medical Research Council; University of Ottawa; Care and Public Health Research Institute, Universiteit Maastricht; Health Services Research and Development","keywords":"Systematic review; CLARITY; Medicine; Health care; Alternative medicine; MEDLINE; Meta-analysis; Family medicine; Political science; Pathology","score_opus":0.9867670625485562,"score_gpt":0.7651237160921635,"score_spread":0.22164334645639272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468996569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0388626,0.089291066,0.7260275,0.13022491,0.0020450985,0.011991552,0.000014191216,0.000008204149,0.0015349226],"genre_scores_gemma":[0.69868886,0.0064946287,0.23045722,0.04606387,0.0024300434,0.00045972303,0.0000062478057,0.000045816138,0.015353568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.32582134,0.31640533,0.35132182,0.0015902478,0.004115575,0.0007456723],"domain_scores_gemma":[0.09476012,0.4773483,0.41917452,0.0046222964,0.0035174424,0.0005773191],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9076974,0.00039947734,0.04084205,0.0002343638,0.00016530025,0.00022157507,0.0018643582,0.00021915308,0.00061383244],"category_scores_gemma":[0.95621395,0.000110640976,0.016594294,0.00050190743,0.0001418792,0.00023197923,0.000086859945,0.00061570585,0.00009113615],"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":[0.0002254185,0.00052586704,0.031478845,0.006828606,0.03662882,0.000046370067,0.00077866664,0.0011943178,0.00004363509,0.011254932,0.85680985,0.05418467],"study_design_scores_gemma":[0.0012811397,0.0023215327,0.04015534,0.0012337109,0.087575465,0.0007123157,0.0009783368,0.024301503,0.000005060738,0.34634045,0.49455544,0.0005396993],"about_ca_topic_score_codex":0.0000026380774,"about_ca_topic_score_gemma":0.0000049273704,"teacher_disagreement_score":0.6598263,"about_ca_system_score_codex":0.000022318955,"about_ca_system_score_gemma":0.000114658884,"threshold_uncertainty_score":0.99325424},"labels":[],"label_agreement":null},{"id":"W2469738428","doi":"10.1016/j.jclinepi.2016.05.016","title":"Randomized trials are frequently fragmented in multiple secondary publications","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Research Chairs; University of Toronto; University Health Network; SickKids Foundation; Population Health Research Institute; McMaster University","funders":"","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.9530091335880546,"score_gpt":0.6889612953668207,"score_spread":0.2640478382212339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469738428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4357196,0.0043441793,0.35177147,0.19813563,0.003957671,0.0016815368,0.000053621778,0.0000069076514,0.004329378],"genre_scores_gemma":[0.96141213,0.0013383661,0.024727471,0.00633548,0.0010352692,0.000048355658,0.0000024067651,0.000013665153,0.005086877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.15564759,0.65822977,0.18149963,0.0011677005,0.0028821765,0.00057312066],"domain_scores_gemma":[0.012756172,0.87321806,0.108631164,0.0023048532,0.0025924544,0.0004972945],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.91763604,0.00025728752,0.03777996,0.0007946436,0.000054358137,0.0000817779,0.002087575,0.0003878727,0.018238625],"category_scores_gemma":[0.9902243,0.000081569284,0.013102052,0.000729391,0.00041181044,0.00037762485,0.00010946748,0.0007057095,0.0011115578],"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":[0.0049175704,0.00022366618,0.6885422,0.000010470519,0.00088651746,0.000009937124,0.000029628945,0.000031486663,0.000019761635,0.007292037,0.22127442,0.076762326],"study_design_scores_gemma":[0.12271451,0.00014119873,0.34468308,0.00021114234,0.0004593741,0.00004959324,0.00012518588,0.0016115928,0.0000037042782,0.28953058,0.24028462,0.00018542256],"about_ca_topic_score_codex":0.0000093611525,"about_ca_topic_score_gemma":0.000058049853,"teacher_disagreement_score":0.5256925,"about_ca_system_score_codex":0.000038363247,"about_ca_system_score_gemma":0.00032096307,"threshold_uncertainty_score":0.9996662},"labels":[],"label_agreement":null},{"id":"W2472007695","doi":"10.1016/j.jclinepi.2016.05.012","title":"Online obituaries are a reliable and valid source of mortality data","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Hepatitis C virus research","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University Health Network; Toronto Western Hospital; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Scopus; Medicine; Socioeconomic status; MEDLINE; Demography; Population; Political science","score_opus":0.6527590254187426,"score_gpt":0.5949971678664926,"score_spread":0.05776185755225005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472007695","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":[0.042286158,0.0029064158,0.0012490563,0.9512569,0.0010703162,0.0002845583,0.0005585797,0.0000135267655,0.00037449237],"genre_scores_gemma":[0.0054280646,0.032108832,0.011550704,0.91274345,0.033084717,0.0000036121482,0.00043415788,0.00011928179,0.004527204],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.985318,0.0045657507,0.007980751,0.0006802543,0.00075703743,0.0006982291],"domain_scores_gemma":[0.93556446,0.05138426,0.008977574,0.002341815,0.001148362,0.00058353593],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.034371156,0.0003320234,0.007169902,0.00025833666,0.000040242387,0.0000069212592,0.00097223907,0.0022873653,0.00031902816],"category_scores_gemma":[0.22974253,0.0002003377,0.00068868673,0.00011369397,0.0016559958,0.00014131427,0.00073487393,0.006926974,0.000022385395],"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":[0.0002256498,0.00010075195,0.40732798,0.00040963845,0.00055794517,0.00058338384,0.0000046874998,6.5099465e-7,0.0000024901005,0.000008278164,0.58361566,0.0071628704],"study_design_scores_gemma":[0.0016643862,0.0011469929,0.13233876,0.0014761841,0.00047700354,0.0002875716,0.000008487515,0.00014642705,0.000002097013,0.001665072,0.8606444,0.0001426421],"about_ca_topic_score_codex":0.00029003804,"about_ca_topic_score_gemma":0.000053875163,"teacher_disagreement_score":0.2770287,"about_ca_system_score_codex":0.00005262928,"about_ca_system_score_gemma":0.0011654061,"threshold_uncertainty_score":0.9990079},"labels":[],"label_agreement":null},{"id":"W2473003074","doi":"10.1016/j.jclinepi.2016.05.014","title":"Simple and multiple linear regression: sample size considerations","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":94,"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":"Simple (philosophy); Simple linear regression; Statistics; Linear regression; Sample size determination; Sample (material); Regression; Regression analysis; Mathematics; Chromatography; Chemistry","score_opus":0.6119008963524903,"score_gpt":0.6225419188717629,"score_spread":0.01064102251927257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473003074","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":[0.044422723,0.00010401707,0.94369185,0.011177386,0.00039195095,0.000080811136,0.000041607964,0.00001272045,0.00007695084],"genre_scores_gemma":[0.23555815,0.00042056935,0.76198685,0.0014357162,0.0005170352,0.0000011133832,1.4433887e-7,0.000011184067,0.000069207854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99308157,0.0031297104,0.003202697,0.00021613062,0.00011076313,0.0002591475],"domain_scores_gemma":[0.41120356,0.5865048,0.0015394916,0.00019833332,0.00024212945,0.00031166206],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012679624,0.00013214936,0.0017020215,0.000030289793,0.00007988832,0.0000032178632,0.000091399874,0.00022990827,0.0002980232],"category_scores_gemma":[0.8484251,0.00006484401,0.0002610081,0.000030655174,0.00037588642,0.00009925227,0.0000676117,0.00039871797,0.00000405252],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059122016,0.00035715144,0.113523096,0.00006274042,0.00020219732,0.000086516295,0.00006452286,0.00003963897,0.0005193286,0.74542975,0.028331617,0.110792205],"study_design_scores_gemma":[0.0013438755,0.0004018021,0.0067365817,0.00008283525,0.000041831518,0.000086647226,0.000011221841,0.0009189997,0.00003676127,0.98513216,0.0051204,0.00008688952],"about_ca_topic_score_codex":0.00000398559,"about_ca_topic_score_gemma":0.000007980625,"teacher_disagreement_score":0.83574545,"about_ca_system_score_codex":0.000012084242,"about_ca_system_score_gemma":0.000086351814,"threshold_uncertainty_score":0.439453},"labels":[],"label_agreement":null},{"id":"W2473330465","doi":"10.1016/j.jclinepi.2016.05.013","title":"Which estimates comprise optimal reporting in Systematic Reviews?","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Absolute risk reduction; Absolute (philosophy); Scopus; Baseline (sea); Presentation (obstetrics); Medicine; Systematic review; MEDLINE; Psychology; Actuarial science; Epistemology; Political science; Philosophy; Law; Economics; Surgery; Internal medicine; Confidence interval","score_opus":0.9451121699820456,"score_gpt":0.6962585584743191,"score_spread":0.24885361150772656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473330465","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002348255,0.017911881,0.04704584,0.9211988,0.006484966,0.0024490578,0.000011648875,0.0000058197593,0.0025437225],"genre_scores_gemma":[0.0032147584,0.0068343678,0.12988137,0.82152313,0.02458966,0.00014310452,0.000019628564,0.0001252896,0.013668687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.13928868,0.41897404,0.43215445,0.00230786,0.006049573,0.0012253958],"domain_scores_gemma":[0.012414749,0.5454166,0.43235844,0.005238265,0.0041890563,0.00038287646],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.92618227,0.0009371125,0.09709935,0.0012076121,0.00007819468,0.00023000856,0.005565793,0.0023594154,0.004326796],"category_scores_gemma":[0.98871475,0.00033260783,0.01927653,0.0011745167,0.00028102065,0.00031555493,0.00037221776,0.0062775705,0.0040201736],"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":[0.000013769228,0.00003088879,0.07981918,0.005900357,0.00047996338,0.0004344928,0.000020367517,0.000073150564,3.4340667e-7,0.00006712204,0.9106301,0.0025302444],"study_design_scores_gemma":[0.00050865364,0.00029167897,0.00901143,0.02685539,0.0014227547,0.0014382799,0.00003254615,0.0037046282,1.4851038e-7,0.019705234,0.9365641,0.00046515046],"about_ca_topic_score_codex":0.0000061351348,"about_ca_topic_score_gemma":0.000011259047,"teacher_disagreement_score":0.12687393,"about_ca_system_score_codex":0.00010430604,"about_ca_system_score_gemma":0.000490344,"threshold_uncertainty_score":0.9999126},"labels":[],"label_agreement":null},{"id":"W2474497176","doi":"10.1016/j.jclinepi.2016.06.005","title":"The reporting of studies using routinely collected health data was often insufficient","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":80,"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; Institute for Clinical Evaluative Sciences; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"National Institute for Health and Care Research; Wellcome Trust; Ottawa Hospital Research Institute; Universität Basel","keywords":"Observational study; Medicine; Guideline; Strengthening the reporting of observational studies in epidemiology; Operationalization; MEDLINE; Epidemiology; Population; Family medicine; Environmental health; Pathology","score_opus":0.9904099567038512,"score_gpt":0.7809794283535745,"score_spread":0.20943052835027676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474497176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7418177,0.024773533,0.114631616,0.11425296,0.0036978214,0.0005055309,0.000020921982,0.0000031517943,0.00029675732],"genre_scores_gemma":[0.9340989,0.004803316,0.054694537,0.0038949542,0.0008983436,0.000001749518,8.522289e-7,0.000013659183,0.0015937134],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.30923676,0.27337185,0.40808088,0.0019437778,0.006262653,0.001104082],"domain_scores_gemma":[0.01959578,0.55485135,0.41263974,0.006086974,0.006405267,0.00042086217],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8699685,0.00019877375,0.01706461,0.00019707694,0.00023156854,0.000040365518,0.0032012425,0.00013621984,0.00016469658],"category_scores_gemma":[0.97890395,0.00005410007,0.0029140906,0.00082021375,0.00054139714,0.00015987824,0.00066123385,0.0004125696,0.0000371469],"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":[0.00013404089,0.00017519247,0.5812718,0.000054974425,0.0017190105,0.000016644097,0.00019188617,0.00027657987,0.000037072787,0.0022326054,0.2799645,0.13392565],"study_design_scores_gemma":[0.001708622,0.0016902713,0.58249456,0.0013967121,0.0008389505,0.00066978397,0.0025345534,0.02826766,0.0000056033373,0.07302502,0.30706096,0.000307291],"about_ca_topic_score_codex":0.000016031427,"about_ca_topic_score_gemma":0.000037292266,"teacher_disagreement_score":0.28964096,"about_ca_system_score_codex":0.00005196564,"about_ca_system_score_gemma":0.00085202407,"threshold_uncertainty_score":0.9975281},"labels":[],"label_agreement":null},{"id":"W2474734324","doi":"10.1016/j.jclinepi.2016.06.010","title":"Limited responsiveness related to the minimal important difference of patient-reported outcomes in rare diseases","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Lysosomal Storage Disorders Research","field":"Medicine","cited_by":25,"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 Research Chairs; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; McMaster University","funders":"","keywords":"Observational study; Medicine; Randomized controlled trial; MEDLINE; Quality of life (healthcare); Physical therapy; Clinical study design; Research design; Clinical trial; Internal medicine","score_opus":0.24845648930818326,"score_gpt":0.5284670889178232,"score_spread":0.28001059960964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474734324","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":[0.078227185,0.9127163,0.00001847833,0.0067965738,0.0008843472,0.0012367901,0.000073375486,0.000009552272,0.000037360172],"genre_scores_gemma":[0.007107311,0.991345,0.00016462414,0.0007957138,0.00018292174,0.00003959646,0.000021413232,0.00005205002,0.00029137716],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9693329,0.0126445675,0.01612027,0.0005747498,0.0006804188,0.00064709963],"domain_scores_gemma":[0.892388,0.09322416,0.0115804,0.001059319,0.0009436523,0.0008044606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014762747,0.00048343214,0.013230868,0.0006899453,0.000039271396,0.0000047536028,0.00078638,0.0010234872,0.00017042946],"category_scores_gemma":[0.4233082,0.00020826023,0.0031538184,0.0007024101,0.00053604366,0.000048774862,0.00032412313,0.0022861275,0.000023635079],"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":[0.0027466195,0.00068515236,0.45424145,0.0016002773,0.0011659726,0.0015018978,0.00003661391,0.0000015435498,5.6481457e-7,0.00006951279,0.0007908199,0.53715956],"study_design_scores_gemma":[0.0033494413,0.0046873847,0.5752458,0.027484506,0.001587544,0.0009933246,0.00007050394,0.000009499299,2.730528e-7,0.00093883637,0.38529506,0.00033782294],"about_ca_topic_score_codex":0.000026269592,"about_ca_topic_score_gemma":0.000012263088,"teacher_disagreement_score":0.5368217,"about_ca_system_score_codex":0.00015763834,"about_ca_system_score_gemma":0.002428183,"threshold_uncertainty_score":0.99322134},"labels":[],"label_agreement":null},{"id":"W2478798886","doi":"10.1016/j.jclinepi.2016.07.007","title":"Guideline conflict of interest management and methodology heavily impacts on the strength of recommendations: comparison between two iterations of the American College of Chest Physicians Antithrombotic Guidelines","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":21,"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":"Guideline; Antithrombotic; Medicine; Internal medicine; Pathology","score_opus":0.8324756941659894,"score_gpt":0.6604707503001966,"score_spread":0.1720049438657928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2478798886","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":[0.101768434,0.00029744633,0.01100141,0.8843772,0.0009287944,0.0007662342,0.000789198,0.0000048129905,0.000066469074],"genre_scores_gemma":[0.33672607,0.0072834655,0.18399455,0.46466678,0.0068416223,0.000013324355,0.00024297356,0.00009493358,0.00013627687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9660646,0.012480439,0.020257646,0.000402473,0.00043896603,0.00035593176],"domain_scores_gemma":[0.80995303,0.15506782,0.03163778,0.00091726944,0.0023094018,0.00011470157],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03437834,0.0003772701,0.0065050833,0.00034139902,0.000053342214,0.0000029234884,0.0006505853,0.00042048632,0.000106201645],"category_scores_gemma":[0.1617579,0.00019740142,0.0011665964,0.0003780253,0.0019637744,0.00008917271,0.00026701196,0.0022504025,0.0000014313096],"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":[0.0008571506,0.000399499,0.094984174,0.00037759662,0.0024922183,0.000009387469,0.00005210534,0.000040155053,0.00023347347,0.001205025,0.8566697,0.042679466],"study_design_scores_gemma":[0.00939945,0.013031372,0.3520613,0.007736346,0.007816326,0.00012824812,0.0013505898,0.0008723364,0.0009009533,0.0089933025,0.5972395,0.00047030897],"about_ca_topic_score_codex":0.0002483824,"about_ca_topic_score_gemma":0.000095083196,"teacher_disagreement_score":0.41971043,"about_ca_system_score_codex":0.000058833466,"about_ca_system_score_gemma":0.00039066368,"threshold_uncertainty_score":0.9943107},"labels":[],"label_agreement":null},{"id":"W2490630410","doi":"10.1016/j.jclinepi.2016.07.012","title":"Meta-analysis on continuous outcomes in minimal important difference units: an application with appropriate variance calculations","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":10,"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; McMaster University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Variance (accounting); Statistics; Meta-analysis; Analysis of variance; Mathematics; Medicine; Econometrics; Internal medicine; Economics","score_opus":0.9158541395341797,"score_gpt":0.6598582198604789,"score_spread":0.25599591967370083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490630410","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":[0.00039165167,0.85575473,0.14042547,0.0015401385,0.0002869244,0.0013113748,0.00011905691,0.000004293565,0.0001663236],"genre_scores_gemma":[0.0024358523,0.9786919,0.014390086,0.0010990833,0.00044484634,0.00017456789,0.000036908277,0.000047036014,0.0026797734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7484962,0.15272716,0.09306468,0.0020081575,0.0031561812,0.00054765586],"domain_scores_gemma":[0.5079752,0.29364023,0.1855886,0.007945166,0.003922258,0.0009285442],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.50188506,0.00096577755,0.097901426,0.001732862,0.00008475915,0.00014156179,0.0039235894,0.0009547985,0.0012117373],"category_scores_gemma":[0.39232934,0.0003006179,0.026585186,0.0035988865,0.00032454674,0.00021537438,0.000131994,0.0016494883,0.00032734897],"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":[0.00010342413,0.000744833,0.0975764,0.0005328153,0.24089807,0.000075715754,0.00004714649,0.00030678953,5.4806566e-8,0.014568923,0.00048338313,0.64466244],"study_design_scores_gemma":[0.0006410104,0.0009916003,0.03229726,0.0006933812,0.45152012,0.000097908625,0.000037755806,0.001630659,1.0161674e-8,0.014974707,0.49643645,0.00067915523],"about_ca_topic_score_codex":0.000029844265,"about_ca_topic_score_gemma":0.00018364727,"teacher_disagreement_score":0.6439833,"about_ca_system_score_codex":0.000071597955,"about_ca_system_score_gemma":0.0007497624,"threshold_uncertainty_score":0.99994457},"labels":[],"label_agreement":null},{"id":"W2493763979","doi":"10.1016/j.jclinepi.2016.07.016","title":"A systematic review of discontinued trials suggested that most reasons for recruitment failure were preventable","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"McMaster University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Medicine; MEDLINE; Systematic review; Intensive care medicine; Biology","score_opus":0.9168235833639129,"score_gpt":0.7435214878758624,"score_spread":0.17330209548805053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493763979","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":[9.663348e-7,0.95945954,0.0013592959,0.023355888,0.0015019495,0.013810785,0.00031023668,0.000013100875,0.00018825106],"genre_scores_gemma":[0.0000011553393,0.98220617,0.008193743,0.0022718466,0.0019765624,0.00084789906,0.00007576343,0.000106658415,0.004320221],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8474353,0.084296905,0.063752614,0.0012925875,0.0019187841,0.0013037877],"domain_scores_gemma":[0.15464243,0.78630185,0.053153016,0.0020497998,0.0027219555,0.0011309695],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.48650387,0.0007507053,0.06515634,0.00034862943,0.000061367384,0.00001157682,0.0014860063,0.0036433118,0.00042239352],"category_scores_gemma":[0.9511475,0.0003506468,0.014839432,0.0003501511,0.00078626507,0.000103157,0.00033123983,0.006616374,0.000048588627],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041683356,0.00043250862,0.000077603836,0.87494236,0.00461225,0.00003879843,0.0000031554443,2.8445735e-8,1.238156e-7,0.00215857,0.035560627,0.08175711],"study_design_scores_gemma":[0.0017191103,0.0019636112,0.0000073605415,0.58840644,0.011799877,0.00029448143,0.000008703559,6.308908e-7,2.270118e-7,0.004980129,0.39066148,0.00015791297],"about_ca_topic_score_codex":0.0000051618504,"about_ca_topic_score_gemma":0.000014147342,"teacher_disagreement_score":0.7020049,"about_ca_system_score_codex":0.00028406273,"about_ca_system_score_gemma":0.0063491683,"threshold_uncertainty_score":0.99989456},"labels":[],"label_agreement":null},{"id":"W2501234266","doi":"10.1016/j.jclinepi.2016.07.008","title":"A primary care Web-based Intervention Modeling Experiment replicated behavior changes seen in earlier paper-based experiment","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Antibiotic Use and Resistance","field":"Immunology and Microbiology","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":"North York General Hospital; University of Toronto","funders":"Medical Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; University of Aberdeen; Scottish Government","keywords":"Intervention (counseling); Primary care; Computer science; Medicine; Psychology; Family medicine; Nursing","score_opus":0.1414147870448781,"score_gpt":0.43167491854729284,"score_spread":0.29026013150241475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501234266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97619605,0.012020868,0.005809574,0.0041792053,0.0012852959,0.00029144005,0.0000127834455,0.000028576422,0.00017620792],"genre_scores_gemma":[0.99595046,0.00055865647,0.0012918093,0.0017470783,0.0001535503,0.000026484673,0.000021901222,0.000022801438,0.00022726324],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9925586,0.0032484266,0.0031947852,0.00045058882,0.000070544986,0.00047703835],"domain_scores_gemma":[0.9945426,0.003132618,0.001599264,0.00042084145,0.00021070593,0.0000939608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005455477,0.00024231826,0.0017223946,0.00015500751,0.0000620575,0.0000037313143,0.0003518209,0.00072345074,0.0005294434],"category_scores_gemma":[0.0022708583,0.00014628044,0.0006643206,0.00008469145,0.00033593338,0.000074266856,0.00007056613,0.0006254251,0.000052504947],"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":[0.008459308,0.00396893,0.34454688,0.00024361769,0.00048368127,0.00017465005,0.00030602925,0.00054083497,0.5597008,0.00027879194,0.0033475177,0.07794895],"study_design_scores_gemma":[0.11125155,0.02293414,0.53433526,0.013094436,0.0010859029,0.00028964595,0.0028254916,0.0020292557,0.23415181,0.00088223914,0.074430875,0.0026893762],"about_ca_topic_score_codex":0.00005106404,"about_ca_topic_score_gemma":0.000051384824,"teacher_disagreement_score":0.325549,"about_ca_system_score_codex":0.00017805382,"about_ca_system_score_gemma":0.0002736941,"threshold_uncertainty_score":0.5965143},"labels":[],"label_agreement":null},{"id":"W2505867792","doi":"10.1016/j.jclinepi.2016.07.006","title":"Guideline panels should seldom make good practice statements: guidance from the GRADE Working Group","year":2016,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":235,"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":"Guideline; Grading (engineering); Scopus; Quality of evidence; Medicine; Family medicine; Clinical Practice; MEDLINE; Psychology; Meta-analysis; Political science; Engineering; Law; Pathology","score_opus":0.9357709778064598,"score_gpt":0.6948438741876686,"score_spread":0.24092710361879122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505867792","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010295469,0.007043803,0.20016485,0.7832193,0.0072408277,0.0004951363,0.00009086379,0.0000047559406,0.0016375188],"genre_scores_gemma":[0.00038454164,0.0036229964,0.07529757,0.8765923,0.037963264,0.000016840475,0.000036782498,0.000053968648,0.0060317796],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.31630898,0.48180777,0.18590453,0.003045797,0.011370965,0.0015619664],"domain_scores_gemma":[0.15210512,0.6753193,0.16183057,0.0062766806,0.0040543834,0.0004139604],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8049809,0.0009669411,0.027258718,0.00032547148,0.00022038212,0.00043496073,0.009392411,0.0022628882,0.007898532],"category_scores_gemma":[0.896535,0.00032204296,0.01282375,0.00072479976,0.0005387655,0.0005192818,0.00065039756,0.0077641113,0.0021678358],"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":[0.00006458202,0.00005874584,0.021472469,0.00001422097,0.0022569634,0.00027224817,0.00003437255,0.000028883725,0.0000010601159,0.0004544094,0.91380346,0.061538577],"study_design_scores_gemma":[0.0006582945,0.00023684971,0.0036852271,0.00050691544,0.0016667211,0.00016253671,0.000103804814,0.0002902392,1.2080696e-7,0.07389594,0.91849035,0.00030300106],"about_ca_topic_score_codex":0.000073449446,"about_ca_topic_score_gemma":0.000028688926,"teacher_disagreement_score":0.19351153,"about_ca_system_score_codex":0.00010559522,"about_ca_system_score_gemma":0.00041047373,"threshold_uncertainty_score":0.99992317},"labels":[],"label_agreement":null},{"id":"W2509379050","doi":"10.1016/j.jclinepi.2016.08.003","title":"Registry-based randomized controlled trials- what are the advantages, challenges, and areas for future research?","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":250,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Alberta; University of Calgary; St. Joseph’s Healthcare Hamilton; McMaster University","funders":"University of Calgary","keywords":"Randomized controlled trial; Generalizability theory; Medicine; Randomization; Research design; Clinical trial; Comparative effectiveness research; Population; MEDLINE; Alternative medicine; Medical physics; Family medicine; Psychology; Environmental health; Surgery; Pathology","score_opus":0.9092719835007731,"score_gpt":0.68772078347547,"score_spread":0.22155120002530304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509379050","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":[0.000004016291,0.75510323,0.0018808191,0.23259635,0.005267586,0.0047954028,0.00021301396,0.000008750886,0.00013083176],"genre_scores_gemma":[0.000008075859,0.97345275,0.0019402517,0.008461022,0.0148713505,0.00083115813,0.000022689057,0.0000729654,0.0003397202],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6772596,0.21857533,0.10106229,0.0014860652,0.00032871345,0.0012879834],"domain_scores_gemma":[0.1843124,0.7111858,0.10220391,0.0010706612,0.00066402496,0.00056319404],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.85161436,0.0006314348,0.07720638,0.00077376014,0.00026869608,0.000102349426,0.0011811254,0.002020561,0.00013122532],"category_scores_gemma":[0.8819366,0.00032412264,0.010346613,0.000116306175,0.0011525138,0.00038066017,0.00010570672,0.0025226711,0.00014101963],"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":[0.03300881,0.00022197384,0.000102480575,0.01574873,0.0053471373,0.000010074009,0.00012779316,0.0000035516402,7.8811185e-10,0.22764736,0.06560088,0.6521812],"study_design_scores_gemma":[0.09110595,0.00026874483,0.000042453255,0.013566873,0.00049966475,0.00004060389,0.00035617058,0.00008145835,7.634592e-10,0.08045552,0.8133351,0.0002474467],"about_ca_topic_score_codex":0.0000135321425,"about_ca_topic_score_gemma":0.000021487389,"teacher_disagreement_score":0.74773425,"about_ca_system_score_codex":0.00033790452,"about_ca_system_score_gemma":0.0016362538,"threshold_uncertainty_score":0.9999211},"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":"W2511023921","doi":"10.1016/j.jclinepi.2016.08.011","title":"Premature trial discontinuation often not accurately reflected in registries: comparison of registry records with publications","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Medicine; Discontinuation; Randomized controlled trial; Clinical trial; MEDLINE; Family medicine; Pediatrics; Internal medicine","score_opus":0.9435893784512495,"score_gpt":0.703435284715438,"score_spread":0.24015409373581142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511023921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84360254,0.00043403584,0.06921479,0.08253109,0.0012129373,0.00074652844,0.000025428923,0.0000041543785,0.0022285257],"genre_scores_gemma":[0.97684366,0.00017286169,0.01723532,0.0005149478,0.0005280576,0.000014882249,0.000004717933,0.00000921185,0.004676374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.797063,0.10444223,0.09308976,0.0012756259,0.0036068866,0.0005224948],"domain_scores_gemma":[0.43623662,0.38778985,0.16290565,0.0054132077,0.0071076197,0.00054707646],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38520944,0.00022981984,0.011818488,0.00044861526,0.00004211253,0.000068668814,0.0019289501,0.00044335212,0.0009217],"category_scores_gemma":[0.8427331,0.00008005434,0.0021533926,0.0012250752,0.00037352022,0.000444821,0.000076676755,0.0007106605,0.000064248525],"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":[0.00986414,0.00048491714,0.7421956,0.000022890445,0.0003456808,0.0000032645132,0.00010262957,0.00005533051,0.000040980813,0.004502267,0.19172388,0.050658435],"study_design_scores_gemma":[0.017092498,0.0031426584,0.7951724,0.0006300606,0.00039337584,0.000050162642,0.00042059005,0.00090189435,0.000027325897,0.023116894,0.15880655,0.0002456149],"about_ca_topic_score_codex":0.000012724722,"about_ca_topic_score_gemma":0.00020329094,"teacher_disagreement_score":0.4575236,"about_ca_system_score_codex":0.00004079866,"about_ca_system_score_gemma":0.00051278714,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W2511636839","doi":"10.1016/j.jclinepi.2016.07.017","title":"A very low number of national adaptations of the World Health Organization guidelines for HIV and tuberculosis reported their processes","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Tuberculosis; Human immunodeficiency virus (HIV); Medicine; Family medicine; Epidemiology; Public health; Environmental health; Intensive care medicine; Pathology","score_opus":0.7307822234208444,"score_gpt":0.6676410732455542,"score_spread":0.0631411501752902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511636839","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":[0.0005757296,0.8678566,0.017760944,0.10981709,0.0015361041,0.0019467545,0.00042599833,0.000013975764,0.00006675549],"genre_scores_gemma":[0.00027137474,0.96964234,0.023889916,0.0043734047,0.0014708308,0.000016658361,0.0001180087,0.00004406666,0.0001733833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9763716,0.002874502,0.019798191,0.0003355565,0.0004012785,0.0002188945],"domain_scores_gemma":[0.7064011,0.22618282,0.04915392,0.00057921384,0.01733225,0.00035066748],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031722877,0.00027432517,0.005780211,0.00021277062,0.00006328026,0.000003938325,0.00023817863,0.00039743056,0.00011475412],"category_scores_gemma":[0.7186647,0.00013698734,0.0011388536,0.0006847873,0.00034299167,0.00014569894,0.000093655304,0.00066329347,0.000002551851],"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":[0.0003112063,0.00050358084,0.027892262,0.0138634555,0.0018437192,0.0000016287382,0.00003119006,0.000013671225,0.0000010816641,0.0008530619,0.08927664,0.8654085],"study_design_scores_gemma":[0.0025856527,0.0005662349,0.007430538,0.028176859,0.0020996819,0.0007708878,0.00006399046,0.00009926371,0.0000021979847,0.004949092,0.9530744,0.00018117836],"about_ca_topic_score_codex":0.000015720938,"about_ca_topic_score_gemma":0.00004786957,"teacher_disagreement_score":0.86522734,"about_ca_system_score_codex":0.00010393569,"about_ca_system_score_gemma":0.007412323,"threshold_uncertainty_score":0.9982147},"labels":[],"label_agreement":null},{"id":"W2513984232","doi":"10.1016/j.jclinepi.2016.08.010","title":"Developing WHO rapid advice guidelines in the setting of a public health emergency","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Viral Infections and Outbreaks Research","field":"Medicine","cited_by":56,"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; Ottawa Hospital","funders":"Ottawa Hospital Research Institute; World Health Organization; Bill and Melinda Gates Foundation","keywords":"Advice (programming); Medicine; Public health; Medical emergency; MEDLINE; Nursing; Computer science; Political science","score_opus":0.6217099416443127,"score_gpt":0.6214907613482138,"score_spread":0.00021918029609890866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513984232","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":[0.337417,0.0020615992,0.028712891,0.63046753,0.0005921475,0.00016091848,0.0000020481311,0.0000066964976,0.0005791637],"genre_scores_gemma":[0.9286297,0.03060625,0.019560399,0.018807204,0.0020397955,0.0000059474078,0.0000011774807,0.000016469532,0.00033305524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98630315,0.006292363,0.006531307,0.00016824996,0.00025358034,0.00045135673],"domain_scores_gemma":[0.9786562,0.016685551,0.002938725,0.00026661367,0.0011696524,0.00028327142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08898259,0.0000991948,0.0016742694,0.0002372287,0.000050781186,0.0000020734358,0.0002349781,0.00017225627,0.0001807588],"category_scores_gemma":[0.1634269,0.000042571355,0.0004658457,0.00038657594,0.00014149626,0.00010423391,0.00006140308,0.0006865595,0.000009098971],"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":[0.00008568653,0.0000920546,0.60676914,0.000052750358,0.00006546461,0.000008841379,0.0000623969,0.000002658384,0.00003515265,0.0019285303,0.018212048,0.37268528],"study_design_scores_gemma":[0.001610704,0.001568944,0.9019967,0.0005203793,0.000014898247,0.00032357482,0.0001855381,0.00027979971,0.0000060138354,0.0033786013,0.09005479,0.000060089154],"about_ca_topic_score_codex":0.00015689264,"about_ca_topic_score_gemma":0.00011742757,"teacher_disagreement_score":0.6116603,"about_ca_system_score_codex":0.00006136062,"about_ca_system_score_gemma":0.001009832,"threshold_uncertainty_score":0.9380841},"labels":[],"label_agreement":null},{"id":"W2514398656","doi":"10.1016/j.jclinepi.2016.08.005","title":"Improvement evident but still necessary in clinical practice guideline quality: a systematic review","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Western University","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Guideline; Medicine; Quality (philosophy); Family medicine; Systematic review; Pathology; Political science","score_opus":0.7402259658388076,"score_gpt":0.7211650726115131,"score_spread":0.01906089322729454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514398656","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":[0.000008373388,0.92573607,0.003847362,0.06026942,0.004551073,0.0053308345,0.000056358433,0.000029746612,0.00017079452],"genre_scores_gemma":[0.000002961736,0.8781757,0.019726451,0.09613061,0.0053841122,0.00013392037,0.00008746268,0.00011738563,0.00024145072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.70437324,0.100907,0.18925992,0.001936611,0.002132684,0.0013905398],"domain_scores_gemma":[0.18960513,0.6663315,0.13409857,0.0031546112,0.0048734806,0.0019367],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.46169528,0.0011248621,0.046937,0.0005830938,0.000044369368,0.000022899783,0.0012911621,0.0022311748,0.0004369269],"category_scores_gemma":[0.9414658,0.00063346117,0.009977346,0.0006295747,0.00048286928,0.00064622227,0.0005853165,0.0072829938,0.00046716453],"study_design_candidate":"systematic_review","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":[0.00052793353,0.0010905486,0.00033276924,0.41537893,0.0019637814,0.00051647116,0.0000030336937,2.7166809e-7,4.5733298e-8,0.00013819497,0.039287563,0.54076046],"study_design_scores_gemma":[0.002479867,0.0022900107,0.0000905059,0.43839556,0.014321463,0.0015321893,0.00004293284,0.000007800178,8.832245e-9,0.0003396407,0.54018146,0.0003185939],"about_ca_topic_score_codex":0.00012984806,"about_ca_topic_score_gemma":0.000027837988,"teacher_disagreement_score":0.5654245,"about_ca_system_score_codex":0.0006935298,"about_ca_system_score_gemma":0.0059875394,"threshold_uncertainty_score":0.9999375},"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":"W2517520435","doi":"10.1016/j.jclinepi.2016.08.004","title":"Authors seldom report the most patient-important outcomes and absolute effect measures in systematic review abstracts","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Canada Research Chairs; McMaster University; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Systematic review; MEDLINE; Relative risk; Absolute risk reduction; Meta-analysis; Cochrane Library; Absolute (philosophy); Family medicine; Confidence interval; Internal medicine","score_opus":0.8594837081704251,"score_gpt":0.6711357165434036,"score_spread":0.18834799162702143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517520435","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008418584,0.9897471,0.0002773271,0.003723789,0.0023096458,0.0035506545,0.000015747792,0.0000029137705,0.0002886298],"genre_scores_gemma":[0.00006323781,0.99598104,0.0004965483,0.0020280655,0.00030383212,0.00010296703,0.0000033602337,0.00003348077,0.0009874982],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.23125994,0.44488,0.31407174,0.0022131787,0.006609123,0.0009659906],"domain_scores_gemma":[0.07456141,0.6215427,0.29459366,0.006563746,0.0019211846,0.0008172746],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8765847,0.0010582649,0.103007615,0.0006231151,0.0001072462,0.00018720694,0.0036097015,0.0010261828,0.0005062131],"category_scores_gemma":[0.95510125,0.0002764657,0.01943781,0.0010228935,0.0003739518,0.00020072924,0.00033198015,0.0024679166,0.00052147196],"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":[0.000014708602,0.00009731453,0.018798037,0.35743248,0.0039269105,0.0009961437,0.000023911778,0.0000022085867,5.8976526e-9,0.00024813664,0.061577268,0.55688286],"study_design_scores_gemma":[0.00018462908,0.00022623217,0.0025269594,0.35247478,0.0074305898,0.0030581842,0.0000096524145,0.000010325673,2.483323e-9,0.002055592,0.6317643,0.00025875532],"about_ca_topic_score_codex":0.000010622675,"about_ca_topic_score_gemma":0.000024541858,"teacher_disagreement_score":0.57018703,"about_ca_system_score_codex":0.00007911472,"about_ca_system_score_gemma":0.0007167121,"threshold_uncertainty_score":0.99996877},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","scholarly_communication"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2519326811","doi":"10.1016/j.jclinepi.2016.09.001","title":"Latent growth models matched to research questions to answer questions about dynamics of change in multiple processes","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":42,"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","keywords":"Operationalization; Covariate; Variance (accounting); Latent growth modeling; Econometrics; Computer science; Dynamics (music); Cognition; Longitudinal data; Cognitive psychology; Psychology; Mathematics; Machine learning; Data mining","score_opus":0.9338809644119007,"score_gpt":0.6854216619163461,"score_spread":0.2484593024955546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519326811","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":[0.6063259,0.000586224,0.3278804,0.06296217,0.0014706946,0.000370239,0.000036732778,0.00001274377,0.00035485128],"genre_scores_gemma":[0.8463116,0.0010471373,0.15049574,0.0015229974,0.00042318803,0.000026932277,4.1407642e-7,0.000010820849,0.00016112509],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97968656,0.011417116,0.006782605,0.00056234753,0.00091928465,0.000632117],"domain_scores_gemma":[0.45117024,0.53930604,0.0026137275,0.00069599244,0.0054175677,0.00079645065],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1484984,0.00014956051,0.0021133884,0.0017677245,0.0000770111,0.000018314695,0.0013365793,0.00033883817,0.00006801199],"category_scores_gemma":[0.9169235,0.000079971236,0.00030615248,0.0032929282,0.0003293036,0.00033080133,0.0003444925,0.00075793476,0.000039613984],"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":[0.00030314375,0.00030771468,0.83189154,0.000015896601,0.000017588693,0.000008743482,0.00014326883,0.00087022205,0.000027970058,0.013439004,0.0023323733,0.15064254],"study_design_scores_gemma":[0.00044975837,0.0008617224,0.6066653,0.00046053334,0.000006358957,0.000019365332,0.00011476952,0.0028234664,0.000005597844,0.3874862,0.0010179669,0.00008894875],"about_ca_topic_score_codex":0.00064256805,"about_ca_topic_score_gemma":0.0009957063,"teacher_disagreement_score":0.7684251,"about_ca_system_score_codex":0.00010311298,"about_ca_system_score_gemma":0.0005348201,"threshold_uncertainty_score":0.87680006},"labels":[{"model":"gemma","categories":[],"domain":null,"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":"agree"},{"id":"W2521644229","doi":"10.1016/j.jclinepi.2016.09.003","title":"Primary Outcomes Reporting in Trials (PORTal): a systematic review of inadequate reporting in pediatric randomized controlled trials","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Randomized controlled trial; Consolidated Standards of Reporting Trials; MEDLINE; Systematic review; Family medicine; Internal medicine","score_opus":0.9442311381437036,"score_gpt":0.7261371338140613,"score_spread":0.21809400432964232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521644229","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000077432334,0.9740616,0.0023930736,0.0015142148,0.0027660206,0.018396305,0.000013108556,0.0000034977688,0.0007747589],"genre_scores_gemma":[0.000057219804,0.9929469,0.0032739444,0.0010015173,0.0010355614,0.00072436966,0.0000075852818,0.000047762835,0.0009051398],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.0024619438,0.5035386,0.48840272,0.001194304,0.0038757916,0.0005266494],"domain_scores_gemma":[0.00028605608,0.49817514,0.49616376,0.0028512105,0.0022215005,0.00030234383],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.99662656,0.001564956,0.65110165,0.004030243,0.000045881243,0.0001147021,0.0039318586,0.0017215997,0.0016538593],"category_scores_gemma":[0.99974245,0.00046291566,0.18893516,0.0026772546,0.00029238395,0.00030542535,0.00035287498,0.0028100794,0.00015783132],"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":[0.0028289622,0.0002318209,0.012156542,0.8748256,0.00851073,0.0005655105,0.000018779318,0.0000039316424,1.3804138e-8,0.0004068194,0.003807957,0.096643336],"study_design_scores_gemma":[0.06312099,0.00013984338,0.00035552523,0.8524181,0.0642722,0.00062112825,0.000021077234,0.0000391801,5.3696363e-9,0.009370826,0.00915579,0.00048533437],"about_ca_topic_score_codex":0.000011030607,"about_ca_topic_score_gemma":0.000008484841,"teacher_disagreement_score":0.46216646,"about_ca_system_score_codex":0.00017742638,"about_ca_system_score_gemma":0.0037964564,"threshold_uncertainty_score":0.99978226},"labels":[],"label_agreement":null},{"id":"W2527435919","doi":"10.1016/j.jclinepi.2016.09.008","title":"Equity issues were not fully addressed in Cochrane human immunodeficiency virus systematic reviews","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Bruyère; University of Ottawa; Institute of Population and Public Health; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Systematic review; Medicine; Residence; Sexual orientation; Socioeconomic status; Quartile; Ethnic group; Family medicine; MEDLINE; Environmental health; Demography; Psychology; Sociology; Population; Political science; Social psychology; Internal medicine","score_opus":0.960866809416928,"score_gpt":0.7528223804601616,"score_spread":0.20804442895676645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527435919","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042275307,0.9885387,0.002329471,0.001190925,0.0029506446,0.0032674135,0.00004372892,0.0000048315574,0.0016320394],"genre_scores_gemma":[0.00007333515,0.99085873,0.0017471218,0.0009603316,0.0013456786,0.00011739402,0.0000075178764,0.000050762144,0.004839136],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.22604038,0.49462897,0.26951626,0.002376494,0.0062033064,0.0012345843],"domain_scores_gemma":[0.1139704,0.5519529,0.3190155,0.01073842,0.0033428622,0.000979897],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8921951,0.0014902566,0.17091748,0.0016673921,0.00017320746,0.0003024425,0.011281822,0.0019018347,0.009941222],"category_scores_gemma":[0.915315,0.000522086,0.041171666,0.0016288302,0.00057807897,0.00038592867,0.0009512052,0.0033890165,0.010399928],"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":[0.000032896067,0.00040288092,0.0004747702,0.17462987,0.0012886215,0.00013274085,0.00004422453,0.0000033468202,0.0000013161831,0.005072614,0.06493068,0.752986],"study_design_scores_gemma":[0.00038012658,0.00034797422,0.00022393712,0.18537177,0.0024416356,0.00026879692,0.000021388278,0.000023611066,3.9184183e-8,0.0074583977,0.8030481,0.000414243],"about_ca_topic_score_codex":0.00002360278,"about_ca_topic_score_gemma":0.000046522066,"teacher_disagreement_score":0.7525718,"about_ca_system_score_codex":0.00021903808,"about_ca_system_score_gemma":0.00086467736,"threshold_uncertainty_score":0.99978465},"labels":[],"label_agreement":null},{"id":"W2528915441","doi":"10.1016/j.jclinepi.2016.09.009","title":"GRADE Evidence to Decision (EtD) frameworks for adoption, adaptation, and de novo development of trustworthy recommendations: GRADE-ADOLOPMENT","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":654,"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; McMaster University","funders":"Ministry of Health – Kingdom of Saudi Arabia; McMaster University","keywords":"Trustworthiness; Adaptation (eye); Evidence-based medicine; MEDLINE; Evidence-based practice; Medicine; Computer science; Knowledge management; Psychology; Political science; Alternative medicine; Internet privacy; Pathology","score_opus":0.7121950992587792,"score_gpt":0.6287703723840937,"score_spread":0.0834247268746855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528915441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3134963,0.00031708088,0.59071785,0.09442657,0.00061672257,0.0004127797,0.0000036900335,0.0000062654963,0.0000027593683],"genre_scores_gemma":[0.36390877,0.002684704,0.6250932,0.0077736857,0.000474957,0.000024725095,0.000004425476,0.000013293927,0.000022245524],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98796546,0.0015168192,0.009532667,0.0003502727,0.00030500308,0.00032977256],"domain_scores_gemma":[0.8197288,0.17329556,0.0046385843,0.00029021496,0.0014553198,0.0005915068],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044539243,0.00017104216,0.0015588449,0.00021483852,0.000079177764,0.000005792828,0.00017918365,0.00045793972,0.000107740176],"category_scores_gemma":[0.4739626,0.00011053941,0.00034259734,0.00017563942,0.00015026524,0.00027105588,0.00008197017,0.00062779506,0.000007659051],"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":[0.003955623,0.0003265062,0.17484313,0.000049144182,0.00016612213,0.000003963052,0.00024539744,0.00012689347,0.00016330165,0.0006392731,0.009636904,0.8098437],"study_design_scores_gemma":[0.011677965,0.0047050714,0.8169553,0.0038525746,0.0004924565,0.0003223415,0.0006777852,0.0009618281,0.00016308024,0.03968136,0.12022604,0.00028415033],"about_ca_topic_score_codex":0.000006575663,"about_ca_topic_score_gemma":0.00004621577,"teacher_disagreement_score":0.8095596,"about_ca_system_score_codex":0.00015215717,"about_ca_system_score_gemma":0.0009851666,"threshold_uncertainty_score":0.9838479},"labels":[],"label_agreement":null},{"id":"W2533485695","doi":"10.1016/j.jclinepi.2016.08.007","title":"Odds ratios deconstructed: A new way to understand and explain odds ratios as conditional risk ratios","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"McMaster University","funders":"","keywords":"Odds; Odds ratio; Diagnostic odds ratio; Medicine; Statistics; Mathematics; Confidence interval; Logistic regression","score_opus":0.7361257878273237,"score_gpt":0.6429549873686936,"score_spread":0.09317080045863013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533485695","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":[0.1219192,0.00009651453,0.85139626,0.023617767,0.0018559616,0.00048676942,0.0001220238,0.00003089048,0.00047463417],"genre_scores_gemma":[0.1660327,0.00085071794,0.8223008,0.0067414287,0.0034861015,0.000010322718,0.0000018488884,0.000049274448,0.0005268473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9707547,0.017088497,0.010304572,0.0006841618,0.00053204765,0.00063606055],"domain_scores_gemma":[0.41521403,0.57711643,0.005193816,0.0005188624,0.00052392005,0.0014329503],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053489726,0.0003969704,0.004165511,0.00020597062,0.00016073108,0.00003413835,0.0004857285,0.0008364478,0.0023345768],"category_scores_gemma":[0.8640758,0.00024474453,0.0007387592,0.0001961602,0.0009778223,0.00025548445,0.00016708956,0.0012287749,0.00013729322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022444755,0.000265241,0.032543007,0.000044613542,0.0006910085,0.00007784712,0.00014124493,0.000018214127,0.00017760387,0.7853825,0.08115572,0.097258516],"study_design_scores_gemma":[0.005682642,0.0022111053,0.0177256,0.00023202352,0.00029098394,0.0002773562,0.000134333,0.00012842556,0.00010303943,0.9704912,0.0024244173,0.0002989202],"about_ca_topic_score_codex":0.000013086306,"about_ca_topic_score_gemma":0.00004043934,"teacher_disagreement_score":0.81058604,"about_ca_system_score_codex":0.00010592785,"about_ca_system_score_gemma":0.00070427585,"threshold_uncertainty_score":0.9985774},"labels":[],"label_agreement":null},{"id":"W2533817521","doi":"10.1016/j.jclinepi.2016.04.016","title":"Latin American Clinical Epidemiology Network Series – Paper 3: Cochrane develops widely in Latin America and strengthens ties with LatinCLEN","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Scopus; Library science; Latin Americans; Medicine; Public health; Epidemiology; MEDLINE; Family medicine; Medical education; Political science; Law; Pathology; Computer science","score_opus":0.4419937811170367,"score_gpt":0.6194290348164748,"score_spread":0.17743525369943813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533817521","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":[0.0011475019,0.95172894,0.0007651939,0.040361516,0.0033609425,0.0011733132,0.00009124882,0.00006163958,0.001309709],"genre_scores_gemma":[0.000041162482,0.91464645,0.032735202,0.045431335,0.0057111206,0.000081130376,0.000042263484,0.00012425861,0.0011870612],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88566333,0.0814287,0.029202184,0.0011497136,0.0003358469,0.002220201],"domain_scores_gemma":[0.58036774,0.39287308,0.024244705,0.000836906,0.00055566797,0.001121882],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07245584,0.0010820096,0.031928714,0.00039460594,0.000413125,0.000005761627,0.0009438135,0.0027719536,0.0005690263],"category_scores_gemma":[0.1676417,0.0005952845,0.0018075263,0.0006302915,0.003115052,0.00025732015,0.00051132974,0.010222513,0.00018214433],"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":[0.00067361974,0.00006429968,0.36314538,0.0025296253,0.00043074862,0.000071886425,0.000079259255,0.0000054854063,2.4513795e-9,0.001759178,0.026550984,0.60468954],"study_design_scores_gemma":[0.0014193092,0.0021109146,0.20787996,0.013681891,0.00041199115,0.0000576827,0.0001294923,0.0000064141304,4.79668e-10,0.0053957556,0.76843184,0.00047474305],"about_ca_topic_score_codex":0.00041001494,"about_ca_topic_score_gemma":0.0018043992,"teacher_disagreement_score":0.74188083,"about_ca_system_score_codex":0.00037895096,"about_ca_system_score_gemma":0.007838218,"threshold_uncertainty_score":0.9996499},"labels":[],"label_agreement":null},{"id":"W2550035039","doi":"10.1016/j.jclinepi.2016.10.004","title":"Four hundred or more participants needed for stable contingency table estimates of clinical prediction rule performance","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"Contingency table; Table (database); Statistics; Medicine; Mathematics; Computer science; Data mining","score_opus":0.4199366815559962,"score_gpt":0.5455118565174738,"score_spread":0.12557517496147758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550035039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97421724,0.00035161688,0.01277639,0.009366013,0.0026453424,0.000394328,0.00006385687,0.0000297139,0.0001554836],"genre_scores_gemma":[0.9567777,0.0035263242,0.034375705,0.0021300756,0.0023676949,0.000021200272,0.000009084582,0.000034505036,0.0007577038],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98698825,0.0010947069,0.010429631,0.00042813402,0.00031585217,0.00074345234],"domain_scores_gemma":[0.5920532,0.3979705,0.00687865,0.0005667768,0.001429207,0.0011016917],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036951676,0.0002281294,0.0046632676,0.00010094136,0.000068520436,0.000004969862,0.00026696234,0.0007014792,0.0002364472],"category_scores_gemma":[0.8405612,0.00012455744,0.0011125408,0.00016118148,0.0006639695,0.00016968796,0.000072675306,0.000691189,0.000019826966],"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":[0.010235404,0.0008837653,0.8720736,0.000091232156,0.0003968881,0.00002206398,0.000015593261,0.000047697962,0.00008709266,0.000100237405,0.014223888,0.10182254],"study_design_scores_gemma":[0.014534998,0.011975579,0.95547503,0.0037450532,0.0008877161,0.0001484055,0.00007886036,0.0065412233,0.00033524472,0.0027362,0.00338135,0.00016031678],"about_ca_topic_score_codex":0.000029818237,"about_ca_topic_score_gemma":0.000004745141,"teacher_disagreement_score":0.80360955,"about_ca_system_score_codex":0.000032437492,"about_ca_system_score_gemma":0.0010003769,"threshold_uncertainty_score":0.9916609},"labels":[],"label_agreement":null},{"id":"W2552485236","doi":"10.1016/j.jclinepi.2016.10.006","title":"Randomized trials addressing a similar question are commonly published after a trial stopped early for benefit","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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":"Clinical trial; Medicine; Early stopping; Randomized controlled trial; Sample size determination; Skepticism; Relative risk; Population; Confidence interval; Surgery; Internal medicine; Statistics; Computer science","score_opus":0.9672786583599671,"score_gpt":0.7370097620535553,"score_spread":0.23026889630641179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552485236","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001397188,0.9139842,0.064978,0.0061868867,0.007757835,0.0066285087,0.00017404163,0.0000055996074,0.00014522359],"genre_scores_gemma":[0.00005780222,0.9724587,0.014139965,0.0013563086,0.00882314,0.00061674044,0.000017220027,0.00006236349,0.0024677655],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.10033234,0.65203357,0.2405896,0.002068868,0.004111136,0.00086445484],"domain_scores_gemma":[0.01788181,0.70409507,0.26907012,0.0034306138,0.0047622654,0.000760146],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.95242196,0.001181811,0.20671743,0.0014432019,0.00014642157,0.0007966421,0.004418675,0.0025372775,0.005057947],"category_scores_gemma":[0.98795545,0.0003932702,0.10377352,0.0007822531,0.00054220454,0.0006176473,0.00027169523,0.0021363352,0.00047799113],"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":[0.14228307,0.00014973387,0.00015652116,0.0013123356,0.0040687867,0.000018061788,0.000012489017,0.0000019942502,4.8195683e-9,0.0011863877,0.057154804,0.7936558],"study_design_scores_gemma":[0.17141242,0.00048276776,0.00005675314,0.012041479,0.0102964975,0.00004969976,0.0000053988742,0.00007260919,3.1660126e-9,0.06715822,0.7381336,0.00029055984],"about_ca_topic_score_codex":0.000004222258,"about_ca_topic_score_gemma":0.000010458446,"teacher_disagreement_score":0.79336524,"about_ca_system_score_codex":0.000103855615,"about_ca_system_score_gemma":0.0011239748,"threshold_uncertainty_score":0.99985194},"labels":[],"label_agreement":null},{"id":"W2554191990","doi":"10.1016/j.jclinepi.2016.11.002","title":"Bibliographic study showed improving statistical methodology of network meta-analyses published between 1999 and 2015","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":149,"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":"Medicine; Interquartile range; Meta-analysis; MEDLINE; Study heterogeneity; Randomized controlled trial; Statistics; Mathematics; Internal medicine","score_opus":0.987852768179021,"score_gpt":0.7773647472893516,"score_spread":0.21048802088966945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554191990","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000608756,0.834318,0.16209298,0.00088370993,0.001367944,0.0010536554,0.00012019369,0.000003047765,0.00009959363],"genre_scores_gemma":[0.00028316746,0.89233273,0.10496749,0.00027782808,0.0017433148,0.000032261676,0.000011209044,0.000044500437,0.00030749926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.119360045,0.69021136,0.1811514,0.0029527815,0.0051904856,0.0011339408],"domain_scores_gemma":[0.10551256,0.7236478,0.16130342,0.0046511698,0.003775174,0.0011099081],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.88730985,0.0012559423,0.1564226,0.006397675,0.00012501873,0.0002790812,0.0054672346,0.0016159858,0.007184055],"category_scores_gemma":[0.8978718,0.00042358856,0.037017234,0.006771774,0.0011116739,0.00043534246,0.00095707044,0.0028335254,0.00014895652],"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":[0.000036840454,0.00017947577,0.06470481,0.001132347,0.05859277,0.000035810775,0.000011058486,0.000007686901,2.4622354e-8,0.0009723517,0.11391745,0.76040936],"study_design_scores_gemma":[0.00057046325,0.0015688448,0.014874924,0.0007267655,0.15259004,0.00013544734,0.000048562735,0.00004937596,7.255065e-9,0.052134756,0.77688324,0.00041759713],"about_ca_topic_score_codex":0.000048332284,"about_ca_topic_score_gemma":0.000025379095,"teacher_disagreement_score":0.75999177,"about_ca_system_score_codex":0.000025418156,"about_ca_system_score_gemma":0.0008042249,"threshold_uncertainty_score":0.9999137},"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":"W2560742554","doi":"10.1016/j.jclinepi.2016.11.014","title":"Breaking the matching in nested case–control data offered several advantages for risk estimation","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Radiation Dose and Imaging","field":"Medicine","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":"McGill University","funders":"","keywords":"Nested case-control study; Logistic regression; Medicine; Proportional hazards model; Lung cancer; Statistics; Regression analysis; Regression; Hazard ratio; Conditional logistic regression; Case-control study; Oncology; Internal medicine; Mathematics; Confidence interval","score_opus":0.2586068238974716,"score_gpt":0.5362379754577249,"score_spread":0.2776311515602533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560742554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.568396,0.00027749903,0.38615662,0.04436095,0.000521722,0.00022814304,0.000031796117,0.0000073943793,0.000019907433],"genre_scores_gemma":[0.97894573,0.0003740396,0.015265916,0.0043488294,0.0010125258,0.0000030153767,0.000005202072,0.000011696979,0.000033027423],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99414337,0.0024692446,0.0028472252,0.00020134605,0.00009927999,0.0002395617],"domain_scores_gemma":[0.93220913,0.06476323,0.0023861912,0.00040201683,0.00011084177,0.0001285653],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026325615,0.000102775,0.0012109625,0.00009767654,0.000064950036,0.0000066874595,0.00023508613,0.00014016656,0.000026013076],"category_scores_gemma":[0.12055405,0.000047778965,0.00024137787,0.00006385996,0.000099535886,0.00034629367,0.000041465428,0.00051696884,0.000004559245],"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":[0.0008761515,0.00007093926,0.55304486,0.000018832281,0.00017858217,0.0001962818,0.00006733023,0.0012456807,0.00004710475,0.00025519042,0.001828606,0.44217044],"study_design_scores_gemma":[0.008014593,0.00035667492,0.81087023,0.00029066333,0.0003169289,0.0046477946,0.00008575575,0.16298239,0.000004197521,0.0097618885,0.0025875352,0.00008131708],"about_ca_topic_score_codex":0.000055292832,"about_ca_topic_score_gemma":0.000025768146,"teacher_disagreement_score":0.4420891,"about_ca_system_score_codex":0.00003573894,"about_ca_system_score_gemma":0.00015285471,"threshold_uncertainty_score":0.9123985},"labels":[],"label_agreement":null},{"id":"W2564797893","doi":"10.1016/j.jclinepi.2016.12.002","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series–Paper 7: modern perspectives of measurement validation emphasize justification of inferences based on patient reported outcome scores","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; McGill University; University of Ottawa; University of Calgary; Children's Hospital of Eastern Ontario; University of British Columbia; Providence Health Care; McMaster University; Trinity Western University; Centre for Interdisciplinary Research in Rehabilitation; Centre for Advancing Health Outcomes; Western University","funders":"Canada Research Chairs; Research Manitoba","keywords":"Outcome (game theory); Series (stratigraphy); Patient-reported outcome; Medicine; Psychology; Quality of life (healthcare); Economics; Nursing; Mathematical economics","score_opus":0.3433529020196863,"score_gpt":0.45669760242144763,"score_spread":0.11334470040176131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564797893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98848253,0.00011647247,0.002559574,0.0070513263,0.0011661975,0.00039938456,0.000021844604,0.000017588382,0.00018508126],"genre_scores_gemma":[0.997932,0.00023136006,0.0006278128,0.0009753727,0.00014548512,0.000015183077,0.000008079574,0.000020189882,0.00004451469],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98971474,0.0018918299,0.0067472165,0.00043965015,0.00093939214,0.00026718288],"domain_scores_gemma":[0.9796241,0.0084511945,0.008521317,0.000685806,0.0024534904,0.0002640707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007100159,0.00027146103,0.002467404,0.0002642763,0.00004051478,0.0000058459586,0.00014851017,0.00032822206,0.00009742044],"category_scores_gemma":[0.08592282,0.00015134766,0.0008599965,0.00015275792,0.00032617067,0.00023256766,0.000031802785,0.0004277987,0.0000018183151],"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":[0.008714598,0.001144006,0.93649083,0.000061362145,0.00042814892,0.000026953508,0.00047571512,0.00030385694,0.000892815,0.00022510982,0.0001859988,0.051050622],"study_design_scores_gemma":[0.0033476565,0.0065410626,0.98568004,0.00058499153,0.00042664667,0.000023972774,0.0005517578,0.00013985769,0.0009511963,0.0014004407,0.00020479165,0.0001475849],"about_ca_topic_score_codex":0.00048086347,"about_ca_topic_score_gemma":0.00024803192,"teacher_disagreement_score":0.078822665,"about_ca_system_score_codex":0.00019708718,"about_ca_system_score_gemma":0.00054956914,"threshold_uncertainty_score":0.92177683},"labels":[],"label_agreement":null},{"id":"W2567215800","doi":"10.1016/j.jclinepi.2016.12.006","title":"Diffusion of Innovations model helps interpret the comparative uptake of two methodological innovations: co-authorship network analysis and recommendations for the integration of novel methods in practice","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":16,"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","funders":"Canadian Institutes of Health Research; University of Toronto; Ontario Ministry of Research and Innovation; McGill University","keywords":"Diffusion of innovations; Computer science; Opinion leadership; Diffusion; Early adopter; Knowledge translation; Confounding; Data science; Medicine; Knowledge management; Sociology; Political science; Public relations; Social science; Pathology","score_opus":0.9632085998666559,"score_gpt":0.8302669423984486,"score_spread":0.1329416574682073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567215800","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":[0.07784146,0.000039337097,0.792041,0.12900147,0.00030976042,0.0006087639,0.00008617183,0.0000026588157,0.000069383015],"genre_scores_gemma":[0.40307137,0.00030878905,0.5884424,0.00796039,0.0001300745,0.00006010252,0.000005125778,0.0000044215467,0.000017371014],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.94570917,0.03965598,0.013625747,0.0002942776,0.00027821216,0.00043659954],"domain_scores_gemma":[0.46096632,0.5258008,0.010306537,0.0003372841,0.002493412,0.000095630174],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20743114,0.00013301297,0.0019533692,0.0004512689,0.0002620333,0.0000025533607,0.00043258644,0.00026689813,0.00005208565],"category_scores_gemma":[0.43920663,0.00006029364,0.0002704814,0.0020691813,0.00075311604,0.00026158153,0.00012554025,0.0010675458,3.8960482e-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":[0.0020538892,0.0005478424,0.25085542,0.00009647122,0.0010433253,1.3711077e-7,0.015725613,0.007361052,0.005427607,0.63396424,0.009129429,0.07379497],"study_design_scores_gemma":[0.00601584,0.0014879251,0.57832927,0.00072134053,0.00095203554,0.000008511716,0.012593111,0.22320315,0.00020671434,0.1657439,0.010533893,0.00020427511],"about_ca_topic_score_codex":0.00015813668,"about_ca_topic_score_gemma":0.00036756144,"teacher_disagreement_score":0.48614484,"about_ca_system_score_codex":0.000066706096,"about_ca_system_score_gemma":0.00075704965,"threshold_uncertainty_score":0.81611645},"labels":[],"label_agreement":null},{"id":"W2569798057","doi":"10.1016/j.jclinepi.2016.12.005","title":"Response to the letter by Guogen Shan and Hua Zhang (response to letter commenting: J Clin Epidemiol. 2015;68:733-739)","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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; SickKids Foundation; Institute for Clinical Evaluative Sciences; Women's College Hospital; Hospital for Sick Children","funders":"Canadian Institutes of Health Research","keywords":"Gee; Sample size determination; Categorical variable; Type I and type II errors; Statistic; Statistics; Generalized estimating equation; Contingency table; Binary number; Zhàng; Mathematics; Binary data; Inference; Subject (documents); Econometrics; Computer science; Artificial intelligence; Library science; Geography; Arithmetic","score_opus":0.7665830285238733,"score_gpt":0.6658356382063745,"score_spread":0.1007473903174988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569798057","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0063095586,0.00048565015,0.07456879,0.90716326,0.009346103,0.0014876737,0.00048219904,0.000049020073,0.00010775306],"genre_scores_gemma":[0.00012703033,0.00021599344,0.29124382,0.6784945,0.026321264,0.00006875959,0.000007992018,0.00018553373,0.0033351192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7222983,0.23933454,0.030314313,0.0028256169,0.0019006785,0.00332651],"domain_scores_gemma":[0.28282437,0.6988999,0.0131819965,0.0030258044,0.00074504997,0.0013228512],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.42149356,0.0013705969,0.013327373,0.0005173137,0.0005361172,0.00016854398,0.004418581,0.0048629143,0.0006856498],"category_scores_gemma":[0.9514895,0.0008743574,0.002982742,0.00024884247,0.0016801676,0.00018042319,0.0018209417,0.013991841,0.00060688896],"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":[0.015116631,0.00017810505,0.0020160635,0.000121805264,0.0008445584,0.00075400225,0.0000764619,0.0000049632913,0.00008404291,0.0001415322,0.9726828,0.00797908],"study_design_scores_gemma":[0.0023859518,0.0024776557,0.0035375904,0.0008297027,0.000737862,0.00020907234,0.000010047774,0.000041776308,0.000014747991,0.11250394,0.8764513,0.0008003724],"about_ca_topic_score_codex":0.000038828486,"about_ca_topic_score_gemma":0.000007569696,"teacher_disagreement_score":0.5299959,"about_ca_system_score_codex":0.00020993182,"about_ca_system_score_gemma":0.00043697451,"threshold_uncertainty_score":0.99990445},"labels":[],"label_agreement":null},{"id":"W2570662818","doi":"10.1016/j.jclinepi.2016.12.009","title":"Systematic survey of randomized trials evaluating the impact of alternative diagnostic strategies on patient-important outcomes","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Canada Research Chairs; Health Sciences North; University of Toronto; Hamilton Health Sciences; Impact; McMaster University; NOSM University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Medicine; Blinding; Randomized controlled trial; MEDLINE; Sample size determination; Quality of life (healthcare); Intensive care medicine; Physical therapy; Internal medicine","score_opus":0.9815601476478134,"score_gpt":0.7905533106495016,"score_spread":0.19100683699831178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570662818","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002256224,0.9869408,0.0018434012,0.0001499718,0.0029793493,0.0053843204,0.00017862604,0.0000010155627,0.0002662823],"genre_scores_gemma":[0.009520482,0.98906505,0.0006777517,0.000065357046,0.00030900943,0.00009775296,0.000009929404,0.000028026485,0.0002266569],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.034418724,0.7173961,0.24201548,0.0008461163,0.004925878,0.00039772774],"domain_scores_gemma":[0.0026771151,0.61881185,0.37003952,0.0036559156,0.0046006925,0.00021489273],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9660572,0.0009994443,0.24141245,0.00080228853,0.0001003955,0.00023256731,0.006170782,0.00072740566,0.00087090785],"category_scores_gemma":[0.99815565,0.0002537948,0.085633785,0.00054162316,0.0009829829,0.00020209698,0.0002655827,0.0016500374,0.00010224413],"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":[0.008462773,0.001078342,0.04621919,0.067966305,0.12566882,0.000060449383,0.0005191117,0.0026886065,4.5551324e-8,0.0037473373,0.014531359,0.72905767],"study_design_scores_gemma":[0.06821004,0.01677505,0.0543696,0.49675077,0.16269538,0.0004554363,0.0007360976,0.0147824865,9.040084e-8,0.17497616,0.008304872,0.0019440209],"about_ca_topic_score_codex":0.0003193131,"about_ca_topic_score_gemma":0.00002673256,"teacher_disagreement_score":0.72711366,"about_ca_system_score_codex":0.00008597542,"about_ca_system_score_gemma":0.0031709466,"threshold_uncertainty_score":0.9999914},"labels":[],"label_agreement":null},{"id":"W2571651961","doi":"10.1016/j.jclinepi.2016.11.020","title":"Moving from outcomes to values to deliver high-quality health care—A new checklist for valuation studies","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Vancouver Coastal Health; St. Paul's Hospital; University of British Columbia; Vancouver Coastal Health Research Institute; Centre for Advancing Health Outcomes","funders":"","keywords":"Medicine; Health care; Quality-adjusted life year; Population; Excellence; Health economics; Economic evaluation; Health technology; Public health; Population health; Checklist; Life expectancy; Actuarial science; Environmental health; Cost effectiveness; Nursing; Business; Psychology; Political science; Risk analysis (engineering)","score_opus":0.9505816910981905,"score_gpt":0.7413902944046743,"score_spread":0.20919139669351616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2571651961","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":[0.00056218234,0.86715984,0.029381325,0.09163639,0.008244143,0.0020375994,0.0009119036,0.000018611488,0.000048013986],"genre_scores_gemma":[0.00004977398,0.8554707,0.08753494,0.04949946,0.0065326924,0.000110657966,0.00009350304,0.00007549864,0.0006327306],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93202823,0.013145666,0.052330125,0.0013643908,0.00021993372,0.00091166806],"domain_scores_gemma":[0.7268311,0.18666111,0.08179956,0.001898119,0.00097114523,0.001838965],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26533762,0.00063604314,0.029473519,0.0006507344,0.00038415563,0.00006595466,0.0013952722,0.00094991986,0.000069788315],"category_scores_gemma":[0.6141392,0.0005763436,0.0032026225,0.00012490462,0.00014788621,0.00034194556,0.0002897516,0.0010596825,0.00077560154],"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":[0.00009887208,0.00011645707,0.0121038165,0.008470201,0.0025433425,0.0000014977545,0.001603253,0.00019582547,3.0253253e-9,0.01993783,0.2387659,0.716163],"study_design_scores_gemma":[0.0009551917,0.00071149884,0.029752783,0.0043661827,0.00022260041,0.000003145659,0.00030143833,0.00001813614,7.3987456e-9,0.052390765,0.9108179,0.00046035525],"about_ca_topic_score_codex":0.0033572929,"about_ca_topic_score_gemma":0.0006361318,"teacher_disagreement_score":0.71570265,"about_ca_system_score_codex":0.0018520672,"about_ca_system_score_gemma":0.0023321472,"threshold_uncertainty_score":0.9996688},"labels":[],"label_agreement":null},{"id":"W2571766406","doi":"10.1016/j.jclinepi.2010.02.005","title":"CONSORT 2010 Statement: Updated guidelines for reporting parallel group randomised trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":998,"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; Ottawa Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; Institut National de la Santé et de la Recherche Médicale; University of Oxford; National Institute for Health and Care Research; Cancer Research UK; Janssen Scientific Affairs; Johns Hopkins University; McMaster University; Ottawa Hospital Research Institute; University of California, Irvine; University of Ottawa; Johns Hopkins Bloomberg School of Public Health; University of Pennsylvania","keywords":"Consolidated Standards of Reporting Trials; Rigour; Medicine; Psychological intervention; Randomized controlled trial; Neglect; Clinical trial; Gold standard (test); Statement (logic); Alternative medicine; Medical physics; Physical therapy; Family medicine; Nursing; Surgery; Mathematics","score_opus":0.9755207433903736,"score_gpt":0.7526271829763337,"score_spread":0.22289356041403996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2571766406","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22810687,0.001025605,0.7040406,0.049512673,0.013993448,0.002304096,0.000029113207,0.00000746566,0.0009801312],"genre_scores_gemma":[0.10260675,0.0007438999,0.863751,0.016864493,0.006839664,0.000091609174,0.000034831828,0.000040865856,0.00902688],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.21163076,0.23115754,0.54989886,0.0019060468,0.0043954584,0.0010113337],"domain_scores_gemma":[0.016811667,0.57735145,0.39039892,0.0029476392,0.011729724,0.000760617],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.96118945,0.0003696145,0.0346669,0.0003567996,0.00013581417,0.0001551848,0.0019965188,0.0005481489,0.008207042],"category_scores_gemma":[0.99386805,0.00014701541,0.015844561,0.00038126143,0.00027110818,0.00025093736,0.00010788105,0.0011580468,0.00025027466],"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":[0.0017265786,0.000110235065,0.10514773,0.000017755527,0.0011038791,0.000016380107,0.000016248894,0.00019047385,0.00014904566,0.0044588535,0.8528444,0.034218386],"study_design_scores_gemma":[0.013258871,0.000384139,0.023299143,0.000041203235,0.0010203994,0.00016104868,0.00009925351,0.009647842,0.0000049425043,0.15381165,0.7980694,0.0002020888],"about_ca_topic_score_codex":0.000008878604,"about_ca_topic_score_gemma":0.00003225266,"teacher_disagreement_score":0.34619388,"about_ca_system_score_codex":0.0000101100295,"about_ca_system_score_gemma":0.00035490343,"threshold_uncertainty_score":0.9940115},"labels":[],"label_agreement":null},{"id":"W2572228105","doi":"10.1016/j.jclinepi.2011.02.004","title":"Strengthening the reporting of Genetic RIsk Prediction Studies: the GRIPS Statement","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"University of Ottawa","funders":"National Center for Research Resources","keywords":"Statement (logic); Medicine; MEDLINE; Political science; Law","score_opus":0.9013708969838969,"score_gpt":0.6247914142749789,"score_spread":0.2765794827089181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572228105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9364816,0.009093338,0.02199145,0.028053574,0.0033702576,0.00035372132,0.000045240064,0.000008747939,0.0006020585],"genre_scores_gemma":[0.96354157,0.007753107,0.021083629,0.0060737855,0.001452277,0.000016056983,0.000001069906,0.000016120242,0.000062376566],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9181816,0.007851165,0.07318801,0.00032017153,0.00010713314,0.0003519427],"domain_scores_gemma":[0.718487,0.08399569,0.19600388,0.00084149244,0.00046358994,0.00020831512],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41469586,0.00013131229,0.0029789982,0.000105194646,0.00018298169,0.000005379521,0.00042960639,0.0001661702,0.0001221357],"category_scores_gemma":[0.5279653,0.00008034762,0.00058473856,0.0001009343,0.00037610778,0.00013941916,0.0000794321,0.0007802846,0.000044683526],"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":[0.000049695056,0.00007483941,0.9672655,0.0000613595,0.00054198725,0.0000014329122,0.0027084732,0.0010529849,1.2441406e-7,0.009147486,0.017128307,0.0019678012],"study_design_scores_gemma":[0.0005588887,0.000594354,0.8592792,0.000106775646,0.00006508309,0.0000320473,0.0039571547,0.0038883302,9.685415e-7,0.112957835,0.018476706,0.00008261832],"about_ca_topic_score_codex":0.00030931534,"about_ca_topic_score_gemma":0.00004450416,"teacher_disagreement_score":0.19969456,"about_ca_system_score_codex":0.00011097206,"about_ca_system_score_gemma":0.00017902534,"threshold_uncertainty_score":0.6026938},"labels":[],"label_agreement":null},{"id":"W2576440140","doi":"10.1016/j.jclinepi.2009.06.006","title":"The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate health care interventions: explanation and elaboration","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":10603,"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; Ottawa Hospital","funders":"Cancer Research UK","keywords":"Systematic review; Checklist; Psychological intervention; Guideline; MEDLINE; Health care; Medicine; Psychology; Management science; Nursing; Pathology; Political science","score_opus":0.9912535830674697,"score_gpt":0.8098059262584527,"score_spread":0.18144765680901698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576440140","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","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":[0.029609947,0.7641575,0.15779439,0.04443696,0.0005577355,0.0034111987,0.000007307548,0.000001669498,0.000023332415],"genre_scores_gemma":[0.8120376,0.09257832,0.09065574,0.0037287313,0.000255703,0.00018191771,0.0000059297577,0.000011205837,0.0005448578],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.48001438,0.26643413,0.24872181,0.0011051043,0.0032705606,0.0004540009],"domain_scores_gemma":[0.2969419,0.28176484,0.41180953,0.001868572,0.0073485207,0.00026661088],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.81028134,0.00020370875,0.018722786,0.00019814353,0.00019179963,0.00009018752,0.0004215377,0.000077654935,0.000025853156],"category_scores_gemma":[0.87151885,0.0000651851,0.0049211695,0.00026540417,0.000119439086,0.00021342128,0.00004740238,0.0002027236,0.0000027127596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048449627,0.00053268444,0.060286794,0.09057959,0.07803452,0.0000119296765,0.009605078,0.0014812504,0.000030839547,0.024833607,0.24681826,0.48730093],"study_design_scores_gemma":[0.0040074913,0.01312965,0.121059716,0.015819909,0.16894637,0.000349133,0.066696025,0.022093868,0.000039089347,0.5288629,0.05808547,0.0009104147],"about_ca_topic_score_codex":0.0000026071502,"about_ca_topic_score_gemma":0.000030952615,"teacher_disagreement_score":0.78242767,"about_ca_system_score_codex":0.00003317383,"about_ca_system_score_gemma":0.00010204014,"threshold_uncertainty_score":0.9958453},"labels":[],"label_agreement":null},{"id":"W2576679537","doi":"10.1016/j.jclinepi.2016.11.017","title":"The number of primary events per variable affects estimation of the subdistribution hazard competing risks model","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","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":"Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Statistics; Medicine; Estimation; Proportional hazards model; Mathematics","score_opus":0.48026792701204124,"score_gpt":0.5825631537549266,"score_spread":0.10229522674288538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576679537","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":[0.33454466,0.000028709723,0.6620065,0.0014192064,0.00057558564,0.00009928863,0.000017601156,0.0000022669526,0.001306185],"genre_scores_gemma":[0.64639986,0.000073105264,0.3532853,0.000104064035,0.00010165614,0.0000013431747,5.665618e-7,0.0000055055148,0.000028552016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992353,0.0041359835,0.002924192,0.00012528196,0.00024366584,0.00021785738],"domain_scores_gemma":[0.9083608,0.0835138,0.007130333,0.0005195227,0.00039044692,0.0000850969],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0353119,0.000106752195,0.0013686407,0.000011300934,0.0002372747,0.000007810152,0.00061557506,0.00022034555,0.000029363628],"category_scores_gemma":[0.37986612,0.00005285173,0.00038558312,0.00003092948,0.0005317597,0.00007640775,0.00017577855,0.00068066065,0.000002205038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029093935,0.00022328783,0.30284068,0.00016699493,0.0001353078,7.287338e-7,0.000028072078,0.0022316484,0.00008769047,0.6689082,0.0012759956,0.023810467],"study_design_scores_gemma":[0.00036689045,0.0000805882,0.28419325,0.00017619503,0.00008480434,0.000012336971,0.0000059644576,0.10008942,0.0000337663,0.61488205,0.00003730295,0.000037449117],"about_ca_topic_score_codex":0.000017862265,"about_ca_topic_score_gemma":0.000002652701,"teacher_disagreement_score":0.34455422,"about_ca_system_score_codex":0.0000301726,"about_ca_system_score_gemma":0.00022325086,"threshold_uncertainty_score":0.99334943},"labels":[],"label_agreement":null},{"id":"W2576687171","doi":"10.1016/j.jclinepi.2017.01.003","title":"Requesting a unique personal identifier or providing a souvenir incentive did not affect overall consent to health record linkage: evidence from an RCT nested within a cohort","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Electronic Health Records Systems","field":"Health Professions","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":"University of Ottawa","funders":"","keywords":"Incentive; Informed consent; Medicine; Family medicine; Cohort; Odds ratio; Cohort study; Confidence interval; Randomized controlled trial; Linkage (software); Record linkage; Environmental health; Population; Alternative medicine; Surgery; Internal medicine","score_opus":0.631461194203404,"score_gpt":0.6562300093536877,"score_spread":0.02476881515028373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576687171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9119513,0.0005051223,0.008247043,0.06756771,0.008856192,0.002701967,0.00003241635,0.00007162076,0.000066614215],"genre_scores_gemma":[0.9358152,0.0016676778,0.018779285,0.035346508,0.0069623534,0.00016945592,0.000008916247,0.00009055921,0.0011600412],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9204544,0.06259266,0.013181138,0.0011996782,0.00064550084,0.0019266631],"domain_scores_gemma":[0.8143528,0.15565902,0.024810491,0.0013576511,0.00132496,0.002495092],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14648108,0.0005092176,0.005620282,0.00024731964,0.0018171597,0.00005117566,0.0013767341,0.0011678125,0.00016948949],"category_scores_gemma":[0.45016596,0.000366331,0.0006571422,0.00016999987,0.00039100955,0.0008463928,0.00045700767,0.006992653,0.000103761166],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046322383,0.00017423202,0.9727884,0.00061803334,0.00024597716,0.00017949754,0.0031710623,0.000022159978,0.00014946492,0.00021134177,0.009764848,0.008042734],"study_design_scores_gemma":[0.002747173,0.0066954973,0.9611541,0.01722827,0.00012247924,0.000126488,0.00070813444,0.004978009,0.000008958709,0.0017668467,0.004028693,0.00043536452],"about_ca_topic_score_codex":0.020215027,"about_ca_topic_score_gemma":0.021900825,"teacher_disagreement_score":0.30368486,"about_ca_system_score_codex":0.0015615504,"about_ca_system_score_gemma":0.017134128,"threshold_uncertainty_score":0.9998789},"labels":[],"label_agreement":null},{"id":"W2577869045","doi":"10.1016/j.jclinepi.2016.11.012","title":"A systematic review found that deviations from intention-to-treat are common in randomized trials and systematic reviews","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"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; Clinical trial; Placebo; Randomized controlled trial; Meta-analysis; Systematic review; Intention-to-treat analysis; MEDLINE; Internal medicine; Alternative medicine; Pathology","score_opus":0.9790808798786288,"score_gpt":0.7506744461246216,"score_spread":0.22840643375400715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577869045","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005421073,0.96237373,0.008251407,0.0020449925,0.001938925,0.025155853,0.000055603246,0.000003220057,0.0001708515],"genre_scores_gemma":[0.000016602373,0.99152344,0.0028919308,0.0023268661,0.0004271573,0.0014709017,0.000020006712,0.000041333926,0.0012817333],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.05784326,0.68284833,0.2543343,0.001576668,0.0028983797,0.00049905333],"domain_scores_gemma":[0.008574825,0.6396406,0.34309757,0.0063211434,0.0016543003,0.0007115261],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.9487271,0.0014391636,0.41133308,0.0015952018,0.00018878894,0.0006315077,0.006080417,0.0011746552,0.0010038436],"category_scores_gemma":[0.99292797,0.0005066882,0.0627593,0.000995958,0.00037718954,0.00039423286,0.000485122,0.0021043029,0.0022474234],"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":[0.00015842865,0.00007991227,0.00041700248,0.95042783,0.0031844338,0.000033784476,0.000025046067,4.5485268e-7,1.4776239e-9,0.00032746617,0.017277518,0.028068103],"study_design_scores_gemma":[0.004370083,0.00006038509,0.000057942132,0.8059731,0.05436045,0.00020292372,0.000034982233,0.000059403807,5.0690085e-10,0.008254586,0.12631223,0.0003139146],"about_ca_topic_score_codex":0.000043783264,"about_ca_topic_score_gemma":0.00014599577,"teacher_disagreement_score":0.34857377,"about_ca_system_score_codex":0.00015841093,"about_ca_system_score_gemma":0.0004386871,"threshold_uncertainty_score":0.9999094},"labels":[],"label_agreement":null},{"id":"W2579129885","doi":"10.1016/j.jclinepi.2016.12.017","title":"Response to letter to the editor by A. Huitfeldt Re: Odds ratios deconstructed: a new way to understand and explain odds ratios as conditional risk ratios","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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 Toronto; McMaster University","funders":"","keywords":"Odds ratio; Odds; Counterexample; Section (typography); Paragraph; Statement (logic); Relative risk; Mathematics; Statistics; Medicine; Combinatorics; Confidence interval; Computer science; Linguistics; Philosophy; Logistic regression","score_opus":0.591890600401322,"score_gpt":0.6058424513978082,"score_spread":0.013951850996486215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579129885","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0020586564,0.00006513921,0.38373673,0.6003158,0.0116371475,0.001254668,0.0008048752,0.00002334509,0.00010364571],"genre_scores_gemma":[0.00030455686,0.00010772433,0.32691634,0.5838891,0.08658219,0.000052009265,0.000021069884,0.000101296966,0.002025672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9263931,0.0553963,0.013908567,0.001563114,0.0014414529,0.001297462],"domain_scores_gemma":[0.41420597,0.57420754,0.007761821,0.001584327,0.0007472254,0.0014931011],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10869166,0.0009424642,0.0072254976,0.0003905779,0.0005549876,0.00023197771,0.0020488657,0.0035410703,0.0014257807],"category_scores_gemma":[0.91684437,0.00063376164,0.0012945725,0.00023716279,0.0011047248,0.00022408969,0.0005538991,0.008717129,0.00035120497],"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":[0.0049585057,0.00008407827,0.00037796565,0.000054585336,0.0006812314,0.00025463893,0.00020429271,0.000021174634,0.00003212153,0.0029914354,0.9861342,0.0042057945],"study_design_scores_gemma":[0.0022094646,0.002818743,0.00063461275,0.0003257743,0.00045189692,0.00015509315,0.00006024193,0.000026176345,0.000015835783,0.3946908,0.5981147,0.0004966294],"about_ca_topic_score_codex":0.000043168326,"about_ca_topic_score_gemma":0.00007384035,"teacher_disagreement_score":0.8081527,"about_ca_system_score_codex":0.00024808702,"about_ca_system_score_gemma":0.0013009302,"threshold_uncertainty_score":0.9996114},"labels":[],"label_agreement":null},{"id":"W2579744316","doi":"10.1016/j.jclinepi.2016.12.012","title":"Questionnaires used to assess barriers of clinical guideline use among physicians are not comprehensive, reliable, or valid: a scoping review","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Health Network","funders":"","keywords":"Checklist; Guideline; Medicine; Psychological intervention; MEDLINE; Family medicine; Construct validity; Psychometrics; Clinical psychology; Nursing; Psychology; Pathology","score_opus":0.9156172915366634,"score_gpt":0.7341161392490839,"score_spread":0.18150115228757946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579744316","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":[0.00063514814,0.96570206,0.004813899,0.016771821,0.007429124,0.0044236714,0.00014388213,0.000047640326,0.000032757303],"genre_scores_gemma":[0.000047480473,0.9231108,0.038434662,0.032537967,0.0053640814,0.000050526403,0.000121875775,0.00014621617,0.00018639588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.90688056,0.02335582,0.0663284,0.0013772423,0.0011662544,0.0008917342],"domain_scores_gemma":[0.5810852,0.30145273,0.10520307,0.0031200675,0.0067856503,0.0023532752],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.106840536,0.0010288078,0.037774693,0.00047821857,0.000174501,0.000042388714,0.0014209958,0.0020220315,0.00025111006],"category_scores_gemma":[0.88304645,0.00068722566,0.008042687,0.0005127424,0.0011450225,0.0006750422,0.0005597039,0.005605443,0.00006311968],"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":[0.0014650241,0.000601255,0.054242466,0.06867062,0.002056703,0.0004775934,0.00000794105,0.000042253687,1.5899752e-7,0.000027501523,0.13327198,0.7391365],"study_design_scores_gemma":[0.002007424,0.0017399109,0.011543345,0.4382078,0.0071078874,0.0002676015,0.00001990047,0.000045828037,1.0955248e-7,0.000039123006,0.5386663,0.00035473955],"about_ca_topic_score_codex":0.00025028602,"about_ca_topic_score_gemma":0.00024130536,"teacher_disagreement_score":0.7762059,"about_ca_system_score_codex":0.00016864706,"about_ca_system_score_gemma":0.007818825,"threshold_uncertainty_score":0.9995579},"labels":[],"label_agreement":null},{"id":"W2584470920","doi":"10.1016/j.jclinepi.2017.01.007","title":"Bootstrap imputation with a disease probability model minimized bias from misclassification due to administrative database codes","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"University of Ottawa; Institute for Clinical Evaluative Sciences; Ottawa Hospital","funders":"","keywords":"Covariate; Statistics; Medicine; Imputation (statistics); Missing data; Mathematics","score_opus":0.7710431800016502,"score_gpt":0.5886414940248089,"score_spread":0.18240168597684125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584470920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9213405,0.0001452138,0.0229555,0.054622374,0.00018731295,0.00049663713,0.00013066718,0.000009726741,0.00011204057],"genre_scores_gemma":[0.9140192,0.00016736986,0.0827191,0.0025738038,0.0003724905,0.000036217527,0.000069730835,0.000012515348,0.00002952442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952068,0.0012983627,0.0025833107,0.0004412091,0.00023976709,0.00023056465],"domain_scores_gemma":[0.98126,0.013053762,0.0033725712,0.00082186994,0.00049144006,0.0010003836],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006065361,0.00019796604,0.0020012246,0.00005897536,0.00013678799,0.000022723949,0.00022045395,0.00016160277,0.000050574665],"category_scores_gemma":[0.08031652,0.00011773612,0.00044618448,0.00003558153,0.00036347762,0.00017004035,0.00004209256,0.00041409882,0.000013716009],"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":[0.013268028,0.0022319483,0.9701728,0.00003575056,0.0005336951,0.00028898916,0.000077111414,0.00076812675,0.000038567898,0.00090832694,0.0027169809,0.008959681],"study_design_scores_gemma":[0.0050269444,0.0020313745,0.96679616,0.00031933203,0.0006908133,0.000034736182,0.00003568264,0.012755041,0.00006334822,0.011930374,0.00020783572,0.00010833604],"about_ca_topic_score_codex":0.00007499214,"about_ca_topic_score_gemma":0.00007618108,"teacher_disagreement_score":0.07425116,"about_ca_system_score_codex":0.00006861779,"about_ca_system_score_gemma":0.00085086183,"threshold_uncertainty_score":0.9274304},"labels":[],"label_agreement":null},{"id":"W2587436624","doi":"10.1016/j.jclinepi.2017.01.010","title":"Rating of Included Trials on the Efficacy–Effectiveness Spectrum: development of a new tool for systematic reviews","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Centre for Family Medicine; Western University; Ottawa Hospital; University of Ottawa","funders":"National Center for Complementary and Integrative Health; National Institutes of Health; Cancer Research UK","keywords":"Systematic review; Clinical trial; Randomized controlled trial; Medicine; Inter-rater reliability; Psychological intervention; Rating scale; Likert scale; Medical physics; Delphi method; MEDLINE; Physical therapy; Psychology; Computer science; Nursing; Artificial intelligence; Surgery; Pathology","score_opus":0.967371186608289,"score_gpt":0.8187199135281661,"score_spread":0.14865127308012294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587436624","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":[0.8566866,0.00017459261,0.075708784,0.05410392,0.0028811973,0.01022294,0.000014139628,0.0000063047783,0.00020152061],"genre_scores_gemma":[0.9341154,0.0002786295,0.04866127,0.014454394,0.0020219663,0.00030816966,9.247127e-7,0.0000209166,0.000138293],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.88265455,0.08843737,0.027683398,0.00025859397,0.00039545473,0.00057065574],"domain_scores_gemma":[0.2209722,0.72453237,0.05286608,0.0007752978,0.0005621681,0.00029191005],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50596464,0.00015698743,0.006489693,0.000104450526,0.000695994,0.0000044511953,0.0009255759,0.0002516373,0.00009303195],"category_scores_gemma":[0.9204775,0.000075503325,0.00073312194,0.00009013952,0.00020706674,0.00009426617,0.00014523136,0.00081964565,0.000025083786],"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":[0.011809428,0.0010616359,0.4893375,0.17557383,0.001836238,0.0000063768343,0.027060857,0.00023439356,0.0018764074,0.09195159,0.12734956,0.07190217],"study_design_scores_gemma":[0.013192921,0.0027126155,0.8690382,0.061234176,0.00029062037,0.00000872693,0.00074131205,0.0002486402,0.00055690686,0.023178412,0.028526897,0.00027051987],"about_ca_topic_score_codex":0.00003183617,"about_ca_topic_score_gemma":0.000035380268,"teacher_disagreement_score":0.6616823,"about_ca_system_score_codex":0.00010438403,"about_ca_system_score_gemma":0.0030733594,"threshold_uncertainty_score":0.54520077},"labels":[],"label_agreement":null},{"id":"W2588152191","doi":"10.1016/j.jclinepi.2017.01.001","title":"RE: Which estimates comprise optimal reporting in systematic reviews?","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Scopus; Absolute risk reduction; Randomized controlled trial; Medicine; Guideline; Citation; Systematic review; MEDLINE; Psychology; Computer science; Library science; Population; Internal medicine; Pathology; Political science","score_opus":0.9547905860235976,"score_gpt":0.7087478933233959,"score_spread":0.24604269270020163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588152191","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032933229,0.029310312,0.018712068,0.93228126,0.008962172,0.003115323,0.000011247687,0.000006498491,0.0043078084],"genre_scores_gemma":[0.00840003,0.0081430515,0.19279525,0.74751025,0.024926236,0.00018024724,0.000044467815,0.00016294756,0.017837517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.1577935,0.40070406,0.4309136,0.002624292,0.0067228246,0.001241717],"domain_scores_gemma":[0.012161248,0.4673464,0.5074093,0.008448941,0.0042406083,0.0003935376],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.92966396,0.0009880151,0.10330768,0.0010473421,0.00017788065,0.000540108,0.008507506,0.0026563813,0.0027221958],"category_scores_gemma":[0.99331516,0.00041130887,0.019975187,0.00073495746,0.0003710566,0.00040174165,0.000501068,0.008983362,0.0024237074],"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":[0.00001374664,0.000043676293,0.084223434,0.007364258,0.00050653075,0.0011295155,0.000032120806,0.00018104544,1.00229855e-7,0.000028816055,0.90518075,0.0012959947],"study_design_scores_gemma":[0.0005378816,0.0003377928,0.015050056,0.027248682,0.0021881706,0.0013918874,0.00007730627,0.01120386,1.07829514e-7,0.015410528,0.92598706,0.0005666436],"about_ca_topic_score_codex":0.000016712567,"about_ca_topic_score_gemma":0.00003258169,"teacher_disagreement_score":0.184771,"about_ca_system_score_codex":0.000093083756,"about_ca_system_score_gemma":0.0005754415,"threshold_uncertainty_score":0.9998339},"labels":[],"label_agreement":null},{"id":"W2592510943","doi":"10.1016/j.jclinepi.2016.10.010","title":"PRECIS-2 helps researchers design more applicable RCTs while CONSORT Extension for Pragmatic Trials helps knowledge users decide whether to apply them","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Scopus; Randomized controlled trial; Medicine; Relevance (law); Citation; Pragmatism; MEDLINE; Library science; Computer science; Epistemology; Philosophy; Internal medicine; Political science","score_opus":0.9779108054682883,"score_gpt":0.7205405430057328,"score_spread":0.25737026246255557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592510943","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008291641,0.0030187862,0.44598848,0.5379375,0.0034033002,0.0066836355,0.00009513177,0.000009440338,0.0020345226],"genre_scores_gemma":[0.0015077991,0.0016842575,0.42091992,0.4742126,0.022571571,0.0011571014,0.00006198734,0.00027845736,0.077606305],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.33314103,0.5093698,0.1410626,0.004732469,0.009041414,0.0026526714],"domain_scores_gemma":[0.05106371,0.8224536,0.106636725,0.009343689,0.009008907,0.0014933788],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.88970464,0.0011650514,0.050257877,0.0010498868,0.00043604022,0.00066019496,0.0091561545,0.0032572409,0.0044728345],"category_scores_gemma":[0.9484776,0.0005282777,0.017667675,0.00069202064,0.0008006255,0.00035522608,0.00061018835,0.005097988,0.004147611],"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":[0.00043525393,0.00013552782,0.0017047005,0.00025149752,0.0016364265,0.0000757667,0.000106468935,0.0003895122,0.000011058941,0.00013053522,0.9666525,0.028470743],"study_design_scores_gemma":[0.0013354924,0.00077224476,0.0010239815,0.0008333913,0.0014604629,0.00018146425,0.0001452852,0.0024720368,0.0000054116513,0.052655946,0.9386553,0.00045897564],"about_ca_topic_score_codex":0.000015839374,"about_ca_topic_score_gemma":0.000013032673,"teacher_disagreement_score":0.31308377,"about_ca_system_score_codex":0.00016161261,"about_ca_system_score_gemma":0.0017336655,"threshold_uncertainty_score":0.9997169},"labels":[],"label_agreement":null},{"id":"W2593926725","doi":"10.1016/j.jclinepi.2017.02.010","title":"Simple randomization did not protect against bias in smaller trials","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"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; Population Health Research Institute","funders":"Canadian Institutes of Health Research; All-India Institute of Medical Sciences","keywords":"Randomization; Simple (philosophy); Clinical trial; Medicine; Statistics; Mathematics; Computer science; Internal medicine","score_opus":0.9542001172518783,"score_gpt":0.7341474733553284,"score_spread":0.22005264389654988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593926725","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":[0.38708428,0.00014217167,0.5753973,0.02467541,0.008021634,0.0022106837,0.000048531503,0.00004303792,0.002376946],"genre_scores_gemma":[0.34645608,0.0011991643,0.64442647,0.0033125766,0.004394879,0.000034655044,0.0000011967411,0.000051244107,0.00012375432],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85358506,0.109767064,0.03439738,0.00074922276,0.0006406838,0.00086059206],"domain_scores_gemma":[0.12841472,0.8441493,0.02535212,0.0011138031,0.00051110226,0.00045893804],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45908257,0.00030407787,0.011223513,0.00017615416,0.00015221132,0.00004442075,0.0011168298,0.0009898753,0.00028506826],"category_scores_gemma":[0.99394923,0.0001943993,0.0020646644,0.000089986905,0.0006816835,0.00017785317,0.00023214844,0.0020504885,0.000029915078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042326048,0.0020666139,0.33377033,0.0003571268,0.0013187067,0.00040728858,0.00007429855,0.0004707063,0.00015488768,0.14271136,0.022856357,0.45348626],"study_design_scores_gemma":[0.020182298,0.0006670496,0.06867382,0.0002570155,0.00017173999,0.0000140338225,0.000007916007,0.0012158295,0.000077988145,0.9058105,0.002727029,0.00019479368],"about_ca_topic_score_codex":0.000018497763,"about_ca_topic_score_gemma":0.000027747023,"teacher_disagreement_score":0.76309913,"about_ca_system_score_codex":0.000058724094,"about_ca_system_score_gemma":0.0002801973,"threshold_uncertainty_score":0.8908466},"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":"W2601083651","doi":"10.1016/j.jclinepi.2017.02.014","title":"Quasi-experimental study designs series—paper 10: synthesizing evidence for effects collected from quasi-experimental studies presents surmountable challenges","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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","funders":"National Science Foundation","keywords":"Series (stratigraphy); Interrupted time series; Computer science; Medicine; Geology","score_opus":0.9658187184474093,"score_gpt":0.7191176316812874,"score_spread":0.2467010867661219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601083651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9050757,0.07970465,0.003306369,0.0054955333,0.0037734602,0.0022781459,0.000013108579,0.000008714488,0.00034426537],"genre_scores_gemma":[0.981865,0.0018277946,0.012257976,0.00048601849,0.0012474658,0.00015843476,0.0000010703768,0.000032531065,0.0021237151],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85291016,0.10691947,0.034273457,0.0018544035,0.0032398712,0.0008026662],"domain_scores_gemma":[0.5716041,0.38654336,0.035152756,0.0038777257,0.002294133,0.0005279576],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3864426,0.00063406304,0.018942857,0.00026532824,0.0008934057,0.00042673651,0.0043199044,0.00038917174,0.0016299246],"category_scores_gemma":[0.8347414,0.0003204361,0.0047664708,0.00020901086,0.0006047192,0.0014185756,0.00064608443,0.0006277203,0.000308727],"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":[0.007108391,0.032736916,0.7462096,0.00037043667,0.017940843,0.0002838344,0.006797611,0.0001262584,0.001733252,0.0020459187,0.16984256,0.01480439],"study_design_scores_gemma":[0.012409154,0.09631047,0.744498,0.0027940099,0.0047254935,0.00018837987,0.04784303,0.00547941,0.002681882,0.03503049,0.046140734,0.0018989185],"about_ca_topic_score_codex":0.00009045534,"about_ca_topic_score_gemma":0.0001512357,"teacher_disagreement_score":0.44829878,"about_ca_system_score_codex":0.00013414602,"about_ca_system_score_gemma":0.0002734737,"threshold_uncertainty_score":0.9999248},"labels":[],"label_agreement":null},{"id":"W2601450050","doi":"10.1016/j.jclinepi.2017.03.007","title":"Embedding researchers in health service organizations improves research translation and health service performance: the Australian Hunter New England Population Health example","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":135,"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":"Health services; Service (business); Population health; Population; Medicine; Business; Public relations; Environmental health; Marketing; Political science","score_opus":0.9791630640109178,"score_gpt":0.8293029264388001,"score_spread":0.1498601375721177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601450050","genre_codex":"commentary","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":[0.0016257546,0.376923,0.00039783743,0.6157118,0.0012953198,0.0039323485,0.00005638085,0.00002238349,0.000035180816],"genre_scores_gemma":[0.00083662727,0.9421835,0.0043649087,0.049509652,0.0025462336,0.000057187917,0.000092214046,0.000065354165,0.00034433848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8742334,0.101759,0.019303266,0.0009178084,0.0010926831,0.0026938221],"domain_scores_gemma":[0.8678511,0.10534307,0.02132796,0.001242845,0.0017258313,0.0025092002],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32460967,0.00040910492,0.005904848,0.00094840804,0.0028784513,0.00005332602,0.0013327327,0.0008868472,0.00015224509],"category_scores_gemma":[0.057366114,0.00027132558,0.00024374525,0.0019205915,0.00025978984,0.0005950126,0.00028149734,0.0085959155,0.000062755396],"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":[0.000052844818,0.000034278382,0.020965897,0.02134974,0.000042675107,9.717204e-7,0.008975982,0.00003181146,1.6308842e-8,0.00016881328,0.013870824,0.9345061],"study_design_scores_gemma":[0.0016419889,0.00073095947,0.09066706,0.012506926,0.000017469407,0.00003096364,0.0012386024,0.0006251532,2.2001116e-9,0.00047617097,0.89191,0.00015468616],"about_ca_topic_score_codex":0.05619373,"about_ca_topic_score_gemma":0.03481902,"teacher_disagreement_score":0.93435144,"about_ca_system_score_codex":0.0013995556,"about_ca_system_score_gemma":0.030864492,"threshold_uncertainty_score":0.9999739},"labels":[],"label_agreement":null},{"id":"W2601919868","doi":"10.1016/j.jclinepi.2017.02.019","title":"Stakeholders apply the GRADE evidence-to-decision framework to facilitate coverage decisions","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":22,"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; Hamilton Health Sciences","funders":"","keywords":"MEDLINE; Management science; Medicine; Political science; Engineering","score_opus":0.9480956848583231,"score_gpt":0.6464009882179325,"score_spread":0.3016946966403906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601919868","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":[0.27791813,0.0012326548,0.36108992,0.3543883,0.004277708,0.0005873945,0.00007465608,0.000009144244,0.00042211238],"genre_scores_gemma":[0.77255213,0.0028628798,0.078407176,0.1430621,0.0025897531,0.000042790336,0.0000013956502,0.000035278772,0.0004464645],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9721671,0.004619934,0.021555876,0.00072610675,0.00022396314,0.00070705597],"domain_scores_gemma":[0.6735756,0.30405402,0.0185087,0.0022702063,0.00031863272,0.0012728787],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26598957,0.0002550937,0.0041521,0.00031259167,0.00067939394,0.00012672854,0.0021855817,0.00048955035,0.000338732],"category_scores_gemma":[0.8335158,0.0001999798,0.0009873378,0.00014457725,0.00032409801,0.00058634207,0.00032032508,0.001389152,0.0034756374],"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":[0.0006712389,0.00018916768,0.47603473,0.00004036908,0.00023966715,0.000013412972,0.001253015,0.008475292,6.2768004e-7,0.092800416,0.39225185,0.028030206],"study_design_scores_gemma":[0.00067837554,0.00050868193,0.45426404,0.00045218607,0.000011842384,0.000014396145,0.0001987185,0.00055766496,1.442901e-7,0.32928997,0.2138529,0.0001710539],"about_ca_topic_score_codex":0.00032429968,"about_ca_topic_score_gemma":0.00011442257,"teacher_disagreement_score":0.5675262,"about_ca_system_score_codex":0.00023846958,"about_ca_system_score_gemma":0.00032396836,"threshold_uncertainty_score":0.99730027},"labels":[],"label_agreement":null},{"id":"W2603068019","doi":"10.1016/j.jclinepi.2017.03.014","title":"Quasi-experimental study designs series—paper 11: supporting the production and use of health systems research syntheses that draw on quasi-experimental study designs","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University; Impact","funders":"","keywords":"Inclusion (mineral); Production (economics); Computer science; Management science; Mechanism (biology); Risk analysis (engineering); Data science; Process management; Medicine; Engineering; Psychology","score_opus":0.9776408366131476,"score_gpt":0.8116175695403337,"score_spread":0.1660232670728139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603068019","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":[0.15595318,0.7648561,0.00035963336,0.025209717,0.015463888,0.037781205,0.00016682682,0.000079849684,0.00012958761],"genre_scores_gemma":[0.4214567,0.57132065,0.0005575898,0.0022021695,0.0028780599,0.0009856058,0.0000051713073,0.00012875933,0.00046531335],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.6857589,0.2840364,0.024321074,0.00151108,0.0020710938,0.002301456],"domain_scores_gemma":[0.7432121,0.22410132,0.02906616,0.0017355955,0.00096775807,0.00091703556],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3466311,0.0007187721,0.011086841,0.00073361763,0.0035067669,0.00008263536,0.00163047,0.0007800973,0.00014197297],"category_scores_gemma":[0.3617656,0.00041801995,0.00077634177,0.00045525646,0.0016278101,0.0008545689,0.000711382,0.00558839,0.0000474299],"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":[0.0031562315,0.08354913,0.5432473,0.027543008,0.0032697816,0.00024823373,0.08763593,0.000041854637,0.0000086586915,0.0037703505,0.07997197,0.16755757],"study_design_scores_gemma":[0.0018742684,0.10897313,0.011138485,0.025529565,0.0004752213,0.0003227942,0.15909836,0.000019931496,0.0000023093748,0.00007824444,0.6917973,0.0006903641],"about_ca_topic_score_codex":0.0031885586,"about_ca_topic_score_gemma":0.00054070336,"teacher_disagreement_score":0.61182535,"about_ca_system_score_codex":0.0009090214,"about_ca_system_score_gemma":0.0076800175,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"W2603202658","doi":"10.1016/j.jclinepi.2016.03.034","title":"Quasi-experimental study designs series–paper 12: strengthening global capacity for evidence synthesis of quasi-experimental health systems research","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 Ottawa; Bruyère","funders":"","keywords":"Inclusion (mineral); Systematic review; Process (computing); Management science; Computer science; Field (mathematics); Global health; Work (physics); Risk analysis (engineering); Process management; MEDLINE; Medicine; Political science; Business; Public health; Sociology; Engineering; Social science; Nursing; Mathematics","score_opus":0.898241040089532,"score_gpt":0.670109136903679,"score_spread":0.22813190318585297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603202658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94026464,0.00936637,0.008809562,0.035109673,0.0039031233,0.0019318693,0.00026816924,0.000017099706,0.00032950434],"genre_scores_gemma":[0.98167354,0.0004553617,0.014480092,0.0015395774,0.0016093659,0.00014293702,0.0000018316535,0.00003352299,0.000063757776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9512064,0.020378528,0.025967032,0.000973869,0.00036833703,0.0011058435],"domain_scores_gemma":[0.8991119,0.07292992,0.02552859,0.0012486579,0.0004757055,0.00070521486],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.352067,0.0003216541,0.006812307,0.00026386467,0.00085854577,0.00009399348,0.0014669889,0.0004492853,0.00011593874],"category_scores_gemma":[0.35647088,0.0003233643,0.0008589606,0.000096998265,0.0008898361,0.0012007143,0.0002311306,0.000875587,0.000076082244],"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":[0.0014920577,0.011454963,0.86894697,0.00069879135,0.0007915283,0.0000068883473,0.0020038239,0.00036242258,0.00001391285,0.096696734,0.016978942,0.00055294385],"study_design_scores_gemma":[0.015592367,0.16785707,0.6541378,0.00525913,0.00019276346,0.00037596107,0.061620932,0.017412372,0.0002291207,0.0463491,0.028685788,0.002287625],"about_ca_topic_score_codex":0.004577526,"about_ca_topic_score_gemma":0.00028601533,"teacher_disagreement_score":0.21480921,"about_ca_system_score_codex":0.0011782895,"about_ca_system_score_gemma":0.0010094424,"threshold_uncertainty_score":0.99992186},"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":"W2605623339","doi":"10.1016/j.jclinepi.2017.04.002","title":"Authors of clinical trials reported individual and financial conflicts of interest more frequently than institutional and nonfinancial ones: a methodological survey","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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":"McMaster University; Impact","funders":"","keywords":"Conflict of interest; Clinical trial; Actuarial science; Business; Medicine; Accounting; Finance; Pathology","score_opus":0.9869188855550043,"score_gpt":0.7909886512434098,"score_spread":0.1959302343115945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605623339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832733,0.0011369246,0.0006766128,0.00852662,0.005393417,0.00037870003,0.0004178374,0.000009083655,0.00018748546],"genre_scores_gemma":[0.98810005,0.0033930195,0.0028763248,0.0035080092,0.0020424386,0.0000058087157,0.000021700667,0.000012516527,0.000040114963],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91597986,0.06584477,0.016534902,0.00067149516,0.0003024342,0.0006665417],"domain_scores_gemma":[0.79870856,0.17325363,0.024231218,0.0006118378,0.0012372495,0.0019574957],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.30420595,0.00034689467,0.00675994,0.00016770243,0.0003590787,0.000014358605,0.00077302946,0.0035768957,0.00021110022],"category_scores_gemma":[0.67785037,0.00025209723,0.00095983536,0.00010300467,0.0061823423,0.00019540383,0.00042913895,0.006609054,0.0000021437497],"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":[0.00938879,0.00074117933,0.91280043,0.00014027822,0.0007134398,0.0002095314,0.00014668256,0.000016206175,0.0001594878,0.0111060785,0.0016117605,0.06296613],"study_design_scores_gemma":[0.006008737,0.0019068856,0.9652574,0.00017266763,0.00062735454,0.0003253023,0.00003959207,0.00031586416,0.00022723389,0.008597589,0.016320113,0.00020127978],"about_ca_topic_score_codex":0.00019717055,"about_ca_topic_score_gemma":0.00015362182,"teacher_disagreement_score":0.3736444,"about_ca_system_score_codex":0.000018715327,"about_ca_system_score_gemma":0.0012960673,"threshold_uncertainty_score":0.99999315},"labels":[],"label_agreement":null},{"id":"W2605959951","doi":"10.1016/j.jclinepi.2017.04.015","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 6: creating national initiatives to support development and use—the PROMIS example","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Centre for Interdisciplinary Research in Rehabilitation; McGill University Health Centre","funders":"","keywords":"Leverage (statistics); Dissemination; Work (physics); Data sharing; Public relations; Business; Information Dissemination; Knowledge management; Computer science; Medicine; Data science; Political science; Alternative medicine; Engineering; World Wide Web; Telecommunications","score_opus":0.3646097229375362,"score_gpt":0.48973961115249,"score_spread":0.1251298882149538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605959951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852453,0.0000275428,0.000081613696,0.0124959415,0.0007659446,0.00025071178,0.000009444224,0.000009107328,0.0011144219],"genre_scores_gemma":[0.9823804,0.000117003125,0.003747938,0.012792387,0.00040665266,0.000018698549,0.000007657787,0.000015373545,0.0005139045],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99567586,0.00073900056,0.0026968846,0.0002767974,0.00034647697,0.00026495755],"domain_scores_gemma":[0.98131126,0.014665315,0.002689936,0.00034116014,0.0006386801,0.0003536406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064944075,0.00018058986,0.0014132106,0.000073959345,0.00028451777,0.000051635765,0.00015983665,0.00018269912,0.000076885706],"category_scores_gemma":[0.11327908,0.00010242076,0.00026835085,0.000036081994,0.00024531406,0.00048163335,0.00012303777,0.00057277025,0.0000049781793],"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":[0.0015526626,0.00011864692,0.9581365,0.000013892319,0.00030465113,0.0000752965,0.0009857295,0.0000059092,0.0000068212394,0.0005433268,0.0016528339,0.03660376],"study_design_scores_gemma":[0.001232662,0.0015890716,0.9582845,0.000109003224,0.00007034823,0.0001507476,0.00029809223,0.0000054433253,0.000026500386,0.00063233473,0.037500452,0.00010086207],"about_ca_topic_score_codex":0.00067300315,"about_ca_topic_score_gemma":0.0018009524,"teacher_disagreement_score":0.10678467,"about_ca_system_score_codex":0.000055900764,"about_ca_system_score_gemma":0.0005274203,"threshold_uncertainty_score":0.89419013},"labels":[],"label_agreement":null},{"id":"W2606079957","doi":"10.1016/j.jclinepi.2017.04.009","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Commentary","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"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":"Series (stratigraphy); Medicine; MEDLINE; Gerontology; Political science","score_opus":0.9140191703621261,"score_gpt":0.664741986946404,"score_spread":0.24927718341572214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606079957","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":[0.0008070579,0.92204,0.00016679638,0.06507449,0.009565263,0.0010752496,0.00054298865,0.00002544485,0.00070272497],"genre_scores_gemma":[0.000053850075,0.94913644,0.0026605127,0.045160852,0.002189099,0.000046418005,0.00008186557,0.000078877674,0.0005920829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9345592,0.010465916,0.053229492,0.0008836357,0.00015128951,0.00071044755],"domain_scores_gemma":[0.79718727,0.09691396,0.10328763,0.0017089599,0.00021421687,0.00068798044],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13288262,0.0006853767,0.025942944,0.00061562617,0.0002642713,0.000084672676,0.0011872251,0.0014693218,0.00022634339],"category_scores_gemma":[0.37471017,0.0005778409,0.004160612,0.00008653996,0.00040185868,0.00084620976,0.00021844383,0.00238977,0.00076810346],"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":[0.00019166368,0.00059325626,0.22131807,0.0035851218,0.0030018731,0.00009374648,0.000079740734,0.000018621233,3.6157574e-10,0.009263126,0.35997397,0.4018808],"study_design_scores_gemma":[0.0008945098,0.0009155975,0.031278532,0.0030921567,0.0002412562,0.00014280729,0.000026848187,0.000016921449,1.8073149e-9,0.01036667,0.95260346,0.00042126898],"about_ca_topic_score_codex":0.00084918755,"about_ca_topic_score_gemma":0.00014701817,"teacher_disagreement_score":0.5926295,"about_ca_system_score_codex":0.00049255986,"about_ca_system_score_gemma":0.00067570806,"threshold_uncertainty_score":0.9999118},"labels":[],"label_agreement":null},{"id":"W2606102449","doi":"10.1016/j.jclinepi.2017.04.018","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 5: patient-reported outcomes can be linked to epidemiologic measures to monitor populations and inform public health decisions","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Manitoba; Children's Hospital of Eastern Ontario; McGill University","funders":"","keywords":"Public health; Medicine; Series (stratigraphy); MEDLINE; Epidemiology; Gerontology; Family medicine; Environmental health; Nursing; Political science; Pathology","score_opus":0.5464374347129733,"score_gpt":0.5314241598748555,"score_spread":0.015013274838117874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606102449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75975364,0.000093983435,0.00027592128,0.23654221,0.001772314,0.001083784,0.000047628946,0.000058458125,0.00037204902],"genre_scores_gemma":[0.94364905,0.00050935446,0.0078064525,0.04718732,0.00031912318,0.000055552013,0.000044150023,0.0000412052,0.0003877684],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.987148,0.0014853637,0.008871455,0.000741896,0.00073577143,0.0010175152],"domain_scores_gemma":[0.97096497,0.0153248515,0.008350568,0.0017994758,0.0009857873,0.0025743623],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010700351,0.0005569928,0.00470259,0.0005382918,0.00061087386,0.0001346694,0.00049898337,0.00043999543,0.000060159848],"category_scores_gemma":[0.40824506,0.0003595591,0.000994362,0.00019004008,0.00042953462,0.0007716847,0.00048527354,0.0010639104,0.0000110723095],"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":[0.0012012282,0.0005280693,0.8777996,0.000021333099,0.00082981354,0.0001774004,0.00017476214,0.0002466152,0.0000018624434,0.0018173635,0.010504681,0.10669732],"study_design_scores_gemma":[0.0028224522,0.004566569,0.96793044,0.00021377366,0.0002836561,0.00010032799,0.0004783829,0.000043607848,4.4054258e-7,0.005199931,0.018076625,0.00028378752],"about_ca_topic_score_codex":0.002122301,"about_ca_topic_score_gemma":0.002556753,"teacher_disagreement_score":0.3975447,"about_ca_system_score_codex":0.00027068172,"about_ca_system_score_gemma":0.0006686381,"threshold_uncertainty_score":0.9998856},"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":"W2606251436","doi":"10.1016/j.jclinepi.2017.04.016","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 9: anonymization and ethics considerations for capturing and sharing patient reported outcomes","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; McGill University; Children's Hospital of Eastern Ontario","funders":"","keywords":"Data sharing; Data anonymization; Context (archaeology); Informed consent; Computer science; Baseline (sea); Data collection; Health care; Medicine; Data mining; Information privacy; Data science; Internet privacy; Alternative medicine; Political science; Statistics","score_opus":0.7713119564753157,"score_gpt":0.6349014787973756,"score_spread":0.13641047767794012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606251436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9050267,0.00010935768,0.00047182004,0.092568144,0.0009911486,0.00060787157,0.000012402178,0.000020032789,0.0001925692],"genre_scores_gemma":[0.9691155,0.0021758482,0.016109206,0.011907804,0.00025188326,0.000020240333,0.000006728743,0.000034455643,0.00037835317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99074143,0.0011836303,0.006426671,0.0006258598,0.0005888996,0.00043352277],"domain_scores_gemma":[0.5732044,0.4086465,0.011560932,0.0018020038,0.0036497207,0.0011364365],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02783466,0.000269661,0.0026328189,0.00014600685,0.00060524454,0.00011456881,0.00016567818,0.0012367464,0.00002663033],"category_scores_gemma":[0.8630985,0.00018137885,0.00050617696,0.000034852936,0.0010210873,0.000509645,0.0003150375,0.004029142,9.241029e-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":[0.0014400198,0.0002437383,0.9852663,0.00010384968,0.00056892267,0.00022302667,0.0003034463,0.000057343586,0.00002297406,0.006645897,0.00030304876,0.004821396],"study_design_scores_gemma":[0.0032904241,0.0023845911,0.8833566,0.0003218807,0.00026296952,0.00029149608,0.00012310682,0.00034566034,0.000020864927,0.108943194,0.0005156678,0.00014359914],"about_ca_topic_score_codex":0.00024514826,"about_ca_topic_score_gemma":0.0008710615,"teacher_disagreement_score":0.83526385,"about_ca_system_score_codex":0.00004751381,"about_ca_system_score_gemma":0.00058708433,"threshold_uncertainty_score":0.9982686},"labels":[],"label_agreement":null},{"id":"W2606721258","doi":"10.1016/j.jclinepi.2017.04.014","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 4: patient-reported outcomes can inform clinical decision making in chronic care","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Centre for Interdisciplinary Research in Rehabilitation; Praxis Spinal Cord Institute","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Series (stratigraphy); Medicine; Clinical decision making; MEDLINE; Intensive care medicine","score_opus":0.18365784714555913,"score_gpt":0.49341584971346375,"score_spread":0.30975800256790464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606721258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9847938,0.00040812657,0.00005247424,0.0063524176,0.007107016,0.00054094667,0.000022967075,0.000034870387,0.0006873933],"genre_scores_gemma":[0.98759323,0.0009913457,0.0009989841,0.009443202,0.000765139,0.000017776862,0.00001926874,0.00005200098,0.000119076314],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9842092,0.0014296838,0.012048638,0.0007100411,0.00079335336,0.00080912013],"domain_scores_gemma":[0.96612346,0.019554628,0.01088917,0.0017358373,0.0010079452,0.0006889648],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007952355,0.0005325455,0.005482699,0.00030981272,0.00022965849,0.00006226263,0.00053048274,0.0010714702,0.00011716959],"category_scores_gemma":[0.16138124,0.0003485189,0.002170594,0.00012869664,0.0005698766,0.0006289329,0.00032953208,0.0026256929,0.000011674268],"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":[0.004475279,0.00023252054,0.68818414,0.00003491589,0.0004034328,0.0010091761,0.0003175321,0.000053149404,9.98134e-7,0.00004972305,0.0007402682,0.30449885],"study_design_scores_gemma":[0.006858345,0.005540045,0.97260773,0.00082815683,0.00033368386,0.00027213173,0.00067363755,0.000042210006,0.0000043609666,0.0010144949,0.011514928,0.00031028478],"about_ca_topic_score_codex":0.0025025522,"about_ca_topic_score_gemma":0.028213888,"teacher_disagreement_score":0.30418858,"about_ca_system_score_codex":0.00048412528,"about_ca_system_score_gemma":0.0012697518,"threshold_uncertainty_score":0.9998967},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2606752218","doi":"10.1016/j.jclinepi.2017.04.017","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 3: patient-reported outcomes can facilitate shared decision-making and guide self-management","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":121,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre de réadaptation Lethbridge-Layton-Mackay; Trinity Western University; Providence Health Care; University of Toronto; University of Calgary; McGill University; University of British Columbia; Centre for Interdisciplinary Research in Rehabilitation; Centre for Advancing Health Outcomes; Western University; Praxis Spinal Cord Institute","funders":"","keywords":"Health literacy; Medicine; Health care; Patient participation; Medical decision making; Decision aids; MEDLINE; Nursing; Family medicine; Medical education; Psychology; Alternative medicine","score_opus":0.43431844398956904,"score_gpt":0.5436440716470965,"score_spread":0.10932562765752746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606752218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95959145,0.00046388607,0.00015933506,0.031062601,0.0053305523,0.0017987957,0.00011132893,0.000121489684,0.001360558],"genre_scores_gemma":[0.94862646,0.0016440284,0.032702982,0.016175356,0.00017698527,0.0001507242,0.00002237181,0.00006771968,0.00043334736],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97416073,0.008228722,0.014804681,0.0008897826,0.00077735283,0.001138752],"domain_scores_gemma":[0.9040211,0.06893781,0.021049228,0.0034055463,0.0016918401,0.0008944655],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008402425,0.000613598,0.0040111733,0.00035285155,0.0019993568,0.0000641573,0.0012279297,0.0008510993,0.00014155565],"category_scores_gemma":[0.21942636,0.0004314281,0.0008510069,0.0001244911,0.0004667609,0.001069519,0.0014067863,0.002730698,0.0000366405],"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":[0.0015012593,0.00031208727,0.9047599,0.00011768326,0.0008419165,0.00021545243,0.0022898298,0.00006918997,6.071402e-7,0.00047384886,0.008097902,0.08132033],"study_design_scores_gemma":[0.0036668614,0.001171822,0.94370496,0.00093892147,0.00022231576,0.000041973966,0.002318721,0.00014666948,3.3055812e-7,0.009801659,0.03763822,0.00034752718],"about_ca_topic_score_codex":0.0016574021,"about_ca_topic_score_gemma":0.0017954368,"teacher_disagreement_score":0.21102394,"about_ca_system_score_codex":0.00032769592,"about_ca_system_score_gemma":0.0005729639,"threshold_uncertainty_score":0.99981374},"labels":[],"label_agreement":null},{"id":"W2607170871","doi":"10.1016/j.jclinepi.2017.04.013","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 2: terminology proposed to measure what matters in health","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation; McGill University","funders":"","keywords":"Terminology; Quality of life (healthcare); Data science; Medicine; MEDLINE; Quality (philosophy); Computer science; Management science; Actuarial science; Nursing; Business; Political science; Epistemology; Engineering","score_opus":0.7221473047655171,"score_gpt":0.5700288974121962,"score_spread":0.15211840735332094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607170871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5270955,0.00031549993,0.00025945305,0.46869025,0.0030055607,0.0005099196,0.000023102817,0.000010002318,0.00009070138],"genre_scores_gemma":[0.6978882,0.0012849381,0.0062373397,0.29363418,0.0005639633,0.000027117025,0.000005547372,0.00004021203,0.0003185077],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9703158,0.004956346,0.023179809,0.0006793203,0.00012673861,0.0007419965],"domain_scores_gemma":[0.9521236,0.018003952,0.02789227,0.0011608216,0.0001830067,0.0006363654],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.091965385,0.00029299455,0.0058151027,0.00044814716,0.00023409723,0.00012265953,0.00068490196,0.00048364117,0.000119870776],"category_scores_gemma":[0.2508716,0.0002657696,0.0005761663,0.000065057924,0.0002666445,0.0019294675,0.00012725347,0.00094110944,0.00030293595],"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":[0.00053349184,0.00025770545,0.9625887,0.00007261964,0.00015811267,0.000029695912,0.0004018577,0.00022534897,4.2148056e-7,0.0055073397,0.01938873,0.01083594],"study_design_scores_gemma":[0.0019190008,0.0014318025,0.94228935,0.00032031076,0.0000067999817,0.000051350577,0.0003195056,0.00009485906,4.3004587e-7,0.016252303,0.037099496,0.00021480679],"about_ca_topic_score_codex":0.0023855516,"about_ca_topic_score_gemma":0.0018423416,"teacher_disagreement_score":0.17505607,"about_ca_system_score_codex":0.0003720987,"about_ca_system_score_gemma":0.00046094536,"threshold_uncertainty_score":0.99997944},"labels":[],"label_agreement":null},{"id":"W2607456113","doi":"10.1016/j.jclinepi.2017.01.014","title":"GRADE equity guidelines 1: considering health equity in GRADE guideline development: introduction and rationale","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":130,"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; Health Sciences Centre; University of Ottawa; Bruyère","funders":"Horizon Pharmaceuticals; Genentech; Celgene; Medical Research Council; Sanofi; Eli Lilly and Company; National Health and Medical Research Council; Amgen; U.S. Department of Veterans Affairs","keywords":"Guideline; Equity (law); Medicine; Actuarial science; Business; Political science","score_opus":0.8451606300005055,"score_gpt":0.7028288785593817,"score_spread":0.14233175144112375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607456113","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":[0.34445947,0.0010503724,0.015322619,0.63639593,0.002234502,0.0004131304,0.000004034971,0.000016052494,0.00010389526],"genre_scores_gemma":[0.54238963,0.0049143513,0.39739475,0.046661466,0.008452827,0.00000822739,0.00004985983,0.000032540167,0.00009637624],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9787002,0.0023411447,0.017397264,0.00052990497,0.0004941979,0.0005372585],"domain_scores_gemma":[0.9674241,0.017641613,0.012343706,0.0006573087,0.0012638656,0.000669405],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10040504,0.00023388353,0.002706309,0.00020848235,0.00027448367,0.000035369347,0.00031553756,0.00030460284,0.000110578214],"category_scores_gemma":[0.5073186,0.00018855472,0.00031257875,0.000082351165,0.00045536063,0.00053267006,0.0005697439,0.0013756227,0.000009832104],"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":[0.00088693254,0.0005186571,0.44693017,0.00013499682,0.00018583091,0.00006062295,0.00007874939,0.00019245943,0.00012338198,0.002373102,0.088973165,0.45954192],"study_design_scores_gemma":[0.0073995544,0.0010389588,0.7600811,0.0002867747,0.00011202408,0.00091762765,0.00017994472,0.0028271377,0.00004228197,0.0470911,0.17981367,0.00020979832],"about_ca_topic_score_codex":0.00027578152,"about_ca_topic_score_gemma":0.0006789877,"teacher_disagreement_score":0.58973444,"about_ca_system_score_codex":0.00022441617,"about_ca_system_score_gemma":0.0019980492,"threshold_uncertainty_score":0.92632234},"labels":[],"label_agreement":null},{"id":"W2607470951","doi":"10.1016/j.jclinepi.2017.01.016","title":"A methodological survey identified eight proposed frameworks for the adaptation of health related guidelines","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Cochrane","funders":"","keywords":"Adaptation (eye); Guideline; Context (archaeology); MEDLINE; Systematic review; Medicine; Process (computing); Medical education; Computer science; Psychology; Political science; Pathology","score_opus":0.9821930737397976,"score_gpt":0.7868079273923291,"score_spread":0.1953851463474685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607470951","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":[0.000028877166,0.7584202,0.20701732,0.027887011,0.0043213447,0.0022281595,0.000078270365,0.000010406969,0.000008394476],"genre_scores_gemma":[0.000068705485,0.8676966,0.12684028,0.0029746727,0.0018807183,0.000027244741,0.00028742422,0.000056856632,0.00016753271],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.85864246,0.07705024,0.061937068,0.00089054054,0.00075146445,0.000728201],"domain_scores_gemma":[0.27515078,0.6339128,0.08445609,0.0013781902,0.0046716817,0.00043047697],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.44778502,0.000511788,0.019067543,0.00026023874,0.00021954681,0.000019415402,0.0010060018,0.0029962717,0.00011331062],"category_scores_gemma":[0.9391607,0.00025647835,0.0053033745,0.00026534768,0.00076557905,0.00015597722,0.00017830137,0.0057271128,0.000012539366],"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":[0.0012087323,0.00026697345,0.0012724752,0.0031673652,0.0018206903,0.000011945833,0.000015611107,0.000043535067,4.0248715e-8,0.0003097176,0.022740953,0.96914196],"study_design_scores_gemma":[0.0030695838,0.003687917,0.012186459,0.011045947,0.005168934,0.0005233914,0.00006422979,0.0016971838,4.816584e-8,0.0069382475,0.95538753,0.00023055001],"about_ca_topic_score_codex":0.00040000718,"about_ca_topic_score_gemma":0.00010733752,"teacher_disagreement_score":0.9689114,"about_ca_system_score_codex":0.00012009173,"about_ca_system_score_gemma":0.004751948,"threshold_uncertainty_score":0.99998873},"labels":[],"label_agreement":null},{"id":"W2607487749","doi":"10.1016/j.jclinepi.2017.04.012","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 1: introduction","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Centre for Interdisciplinary Research in Rehabilitation; McGill University Health Centre","funders":"","keywords":"Health care; Medicine; Affect (linguistics); MEDLINE; Public relations; Psychology; Political science","score_opus":0.6609891308603165,"score_gpt":0.604172882056964,"score_spread":0.056816248803352565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607487749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93614435,0.000056121688,0.0000768553,0.04399711,0.017843464,0.0005469315,0.000015989985,0.000019203073,0.0012999799],"genre_scores_gemma":[0.94874305,0.0012311967,0.0025793612,0.038675975,0.005840622,0.00003745578,0.00003819261,0.000031153973,0.0028229777],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98484856,0.00601392,0.007784722,0.00036065019,0.00031836383,0.00067380554],"domain_scores_gemma":[0.96911037,0.016595647,0.01229463,0.00090606324,0.00047863933,0.00061467645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016710443,0.00023183718,0.0021955299,0.00009846284,0.001058773,0.000010886863,0.00036542557,0.0005410141,0.0004439753],"category_scores_gemma":[0.07214797,0.0001464443,0.0005204774,0.00003438066,0.00025610815,0.0006340889,0.00016100548,0.0020240694,0.00015776991],"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":[0.0028391099,0.00033161888,0.9276112,0.00008670529,0.0001181772,0.00002853108,0.00014416658,0.000013286351,0.0000033439262,0.0019175818,0.03900013,0.02790617],"study_design_scores_gemma":[0.002046621,0.0028983692,0.85475075,0.00021661552,0.000049683025,0.000012078204,0.00020085233,0.000015781556,0.000002878519,0.0063882023,0.13331036,0.00010781971],"about_ca_topic_score_codex":0.0007391037,"about_ca_topic_score_gemma":0.00047744284,"teacher_disagreement_score":0.094310224,"about_ca_system_score_codex":0.00011560865,"about_ca_system_score_gemma":0.0003553638,"threshold_uncertainty_score":0.9356677},"labels":[],"label_agreement":null},{"id":"W2607492635","doi":"10.1016/j.jclinepi.2017.04.011","title":"Montreal Accord on Patient-Reported Outcomes (PROs) use series – Paper 8: patient-reported outcomes in electronic health records can inform clinical and policy decisions","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut de Readaptation Gingras Lindsay de Montreal; University of Ottawa; Children's Hospital of Eastern Ontario; McGill University; Centre for Interdisciplinary Research in Rehabilitation","funders":"","keywords":"Health records; Electronic health record; Series (stratigraphy); Medicine; MEDLINE; Family medicine; Health care; Political science","score_opus":0.32892347809631844,"score_gpt":0.5854439650669367,"score_spread":0.2565204869706183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607492635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.897646,0.0003208727,0.000055663804,0.093744725,0.005762718,0.0017759347,0.000038684466,0.00005586942,0.0005995393],"genre_scores_gemma":[0.94540644,0.010436393,0.0012124437,0.040666647,0.0012077767,0.00010851354,0.000016773116,0.000092980146,0.00085206353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9511512,0.016198497,0.027869755,0.0010157864,0.00077395886,0.0029907841],"domain_scores_gemma":[0.87490636,0.08795201,0.031696696,0.002279621,0.0010325452,0.0021327788],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.051426865,0.00073422946,0.008522514,0.0007019115,0.0013703916,0.00004477337,0.0008972459,0.0018048423,0.0000707427],"category_scores_gemma":[0.44449872,0.00050000567,0.0012138876,0.0002779748,0.0007507791,0.00095040584,0.0005114835,0.008234049,0.000032539654],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020114325,0.00050237,0.82017314,0.00005331342,0.00039558407,0.0000947021,0.00036718132,0.000007729961,2.745728e-7,0.0018630862,0.005327524,0.16920367],"study_design_scores_gemma":[0.006401252,0.0078073656,0.9303244,0.0006320627,0.000064391614,0.00015489884,0.00042060827,0.000053247226,2.0234825e-7,0.011151181,0.042645697,0.00034469127],"about_ca_topic_score_codex":0.029568845,"about_ca_topic_score_gemma":0.077298,"teacher_disagreement_score":0.39307186,"about_ca_system_score_codex":0.0010436693,"about_ca_system_score_gemma":0.012234723,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W2608914567","doi":"10.1016/j.jclinepi.2017.04.021","title":"Gaps exist in the current guidance on the use of randomized controlled trial study protocols in systematic reviews","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Saskatchewan","funders":"","keywords":"Randomized controlled trial; Systematic review; Medicine; Protocol (science); MEDLINE; Medical physics; Alternative medicine; Surgery; Pathology","score_opus":0.9719788579544267,"score_gpt":0.7386877841190116,"score_spread":0.23329107383541514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608914567","genre_codex":"protocol","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42828825,0.0097552035,0.003580474,0.035406925,0.004540411,0.5168429,0.000004463155,0.0000017138062,0.0015796421],"genre_scores_gemma":[0.9452122,0.0023205825,0.0016929283,0.0037888235,0.0012469067,0.045028422,2.7892457e-7,0.000017302544,0.000692577],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.050849643,0.79436475,0.15014997,0.0006890265,0.0036004507,0.00034614015],"domain_scores_gemma":[0.050320286,0.7678444,0.17447203,0.0060180086,0.0012212357,0.00012405618],"candidate_categories":["metaresearch","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9490037,0.00034592507,0.06321099,0.0003062261,0.00013013628,0.00030781026,0.0056764963,0.00014880931,0.0002289382],"category_scores_gemma":[0.9879538,0.00008207835,0.013257778,0.00034402453,0.000472426,0.00020301045,0.00014397247,0.0013240675,0.00012565393],"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":[0.76587605,0.0049057235,0.13713449,0.0022219727,0.0016182846,0.000041097635,0.0008938424,0.0003659685,3.608175e-7,0.017084695,0.061450876,0.008406664],"study_design_scores_gemma":[0.90170795,0.0017583634,0.02997331,0.010208127,0.0012443783,0.000012348734,0.00021810355,0.004067677,5.2606136e-8,0.027725743,0.02291974,0.00016423198],"about_ca_topic_score_codex":0.000013740489,"about_ca_topic_score_gemma":0.00007694196,"teacher_disagreement_score":0.5169239,"about_ca_system_score_codex":0.000022910022,"about_ca_system_score_gemma":0.00017992772,"threshold_uncertainty_score":0.9997033},"labels":[],"label_agreement":null},{"id":"W2610194621","doi":"10.1016/j.jclinepi.2017.04.019","title":"Forty-two systematic reviews generated 23 items for assessing the risk of bias in values and preferences' studies","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"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; St. Joseph's Hospital; McMaster University; Impact","funders":"","keywords":"PsycINFO; Systematic review; MEDLINE; Data extraction; Preference; Medicine; Descriptive statistics; Presentation (obstetrics); Family medicine; Psychology; Statistics; Surgery; Mathematics","score_opus":0.9888906363101236,"score_gpt":0.7804465564282336,"score_spread":0.20844407988189007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610194621","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054353365,0.9887072,0.0046032723,0.00024902204,0.0019106065,0.0038718572,0.00002194584,0.0000010615805,0.00009153441],"genre_scores_gemma":[0.00015603709,0.98944616,0.008555066,0.00015873981,0.0007822395,0.00017392093,0.0000035299959,0.000020387093,0.0007038915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.33068046,0.50345933,0.16173278,0.0013584193,0.0022250803,0.000543935],"domain_scores_gemma":[0.05452106,0.663022,0.27528638,0.003896137,0.0030322974,0.00024213697],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.891492,0.00076973106,0.10308131,0.0006472924,0.00023987748,0.0003059084,0.0041054473,0.0006521404,0.00005621132],"category_scores_gemma":[0.96762997,0.00022214891,0.016995626,0.0006142795,0.00068941945,0.00029638468,0.0003318436,0.0015935757,0.000054716726],"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":[0.00001032389,0.00008067892,0.028047772,0.13282382,0.00461828,0.000005918578,0.0001302684,0.000034762066,1.5029803e-8,0.0002837558,0.02357062,0.8103938],"study_design_scores_gemma":[0.00053207506,0.00035324768,0.001993207,0.16273631,0.016886229,0.0001577434,0.00035102118,0.0018714466,1.3928432e-8,0.051385447,0.7633935,0.00033971932],"about_ca_topic_score_codex":0.000010055586,"about_ca_topic_score_gemma":0.000045069453,"teacher_disagreement_score":0.81005406,"about_ca_system_score_codex":0.000044348293,"about_ca_system_score_gemma":0.0005477388,"threshold_uncertainty_score":0.99284893},"labels":[],"label_agreement":null},{"id":"W2613538222","doi":"10.1016/j.jclinepi.2017.01.017","title":"GRADE equity guidelines 2: considering health equity in GRADE guideline development: equity extension of the guideline development checklist","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":75,"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; Ottawa Hospital; Impact; University of Calgary; Hamilton Health Sciences; Institute of Population and Public Health; Bruyère; University of Ottawa","funders":"Medical Research Council","keywords":"Guideline; Checklist; Equity (law); Psychological intervention; Actuarial science; Business; Medicine; Accounting; Political science; Psychology; Nursing","score_opus":0.8163526071992833,"score_gpt":0.6896025170535282,"score_spread":0.1267500901457551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613538222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5130409,0.0020859435,0.033223134,0.44371724,0.005757053,0.0014379997,0.00002174789,0.000046889898,0.0006690866],"genre_scores_gemma":[0.5885644,0.0015637868,0.36311698,0.04471272,0.0018041332,0.000009851379,0.000042857995,0.000056452736,0.0001288231],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94649565,0.004512654,0.04492127,0.0010061369,0.0017005353,0.0013637509],"domain_scores_gemma":[0.9344978,0.0216183,0.03601968,0.00237879,0.0042728256,0.0012126607],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1764051,0.00056926894,0.0054716608,0.00029524323,0.00056845846,0.000040909923,0.0017237598,0.00066088984,0.00016978089],"category_scores_gemma":[0.5445948,0.00038310123,0.001117577,0.00026865856,0.0009958206,0.00047482084,0.0039827074,0.0026073903,0.00001627615],"study_design_candidate":"observational","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":[0.0015716273,0.0016842413,0.3582235,0.0003807709,0.00045660898,0.000116202944,0.00020250327,0.0005907649,0.0007235638,0.0009305735,0.09990448,0.53521514],"study_design_scores_gemma":[0.009578957,0.0008810624,0.76670426,0.001809974,0.00023862053,0.0005561853,0.00025295684,0.0029252905,0.0007391275,0.01323754,0.20264219,0.0004338499],"about_ca_topic_score_codex":0.00091178424,"about_ca_topic_score_gemma":0.0022216735,"teacher_disagreement_score":0.53478134,"about_ca_system_score_codex":0.0007254063,"about_ca_system_score_gemma":0.008415841,"threshold_uncertainty_score":0.9998621},"labels":[],"label_agreement":null},{"id":"W2613961347","doi":"10.1016/j.jclinepi.2017.04.024","title":"Improving core outcome set development: qualitative interviews with developers provided pointers to inform guidance","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":64,"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; Medical Research Council; University of Bristol; National Institute for Health and Care Research","keywords":"Delphi method; Context (archaeology); Delphi; Set (abstract data type); Work (physics); Process management; Outcome (game theory); Medical education; Qualitative research; Process (computing); Knowledge management; Psychology; Quality (philosophy); Computer science; Engineering ethics; Medicine; Business; Sociology; Engineering","score_opus":0.8243109564887562,"score_gpt":0.7027180452146126,"score_spread":0.12159291127414362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613961347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7405272,0.00013867464,0.082760796,0.15285085,0.0023743794,0.0014693757,0.000010079439,0.00008795942,0.019780682],"genre_scores_gemma":[0.77419204,0.000060867274,0.218731,0.005293883,0.00038232934,0.000028817552,9.93444e-7,0.000021242548,0.001288845],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98895895,0.0040762285,0.0052456195,0.00034746705,0.0006228708,0.00074888737],"domain_scores_gemma":[0.972585,0.01896902,0.005937044,0.0005376192,0.0012299877,0.0007413129],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11934781,0.00020832983,0.0018925103,0.00020495214,0.0007308577,0.00008612223,0.0022823417,0.00033524024,0.00007618691],"category_scores_gemma":[0.36602584,0.00013998472,0.00033226228,0.00018111487,0.0011887046,0.0006054278,0.00044822769,0.0012566447,0.00007018766],"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":[0.001589664,0.00012675818,0.6279643,0.0001174317,0.0003039986,0.0001565199,0.06099526,0.000013994242,0.000022899882,0.016516473,0.018958624,0.27323407],"study_design_scores_gemma":[0.0030455221,0.0032308334,0.36979175,0.0013963076,0.00006143412,0.00010470932,0.049545716,0.0001293114,0.000090300746,0.012514601,0.559133,0.0009565313],"about_ca_topic_score_codex":0.000778472,"about_ca_topic_score_gemma":0.0027758793,"teacher_disagreement_score":0.54017437,"about_ca_system_score_codex":0.0002983362,"about_ca_system_score_gemma":0.001832356,"threshold_uncertainty_score":0.9068168},"labels":[],"label_agreement":null},{"id":"W2614694672","doi":"10.1016/j.jclinepi.2017.04.026","title":"CARE guidelines for case reports: explanation and elaboration document","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2086,"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; University of Ottawa","funders":"Cancer Research UK","keywords":"Elaboration; Medicine; Psychology; Philosophy; Humanities","score_opus":0.7642319293024351,"score_gpt":0.704256605380289,"score_spread":0.059975323922146107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614694672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7750644,0.0011440145,0.043751474,0.17601497,0.0032132128,0.0006516587,0.00001184658,0.000012137437,0.00013626902],"genre_scores_gemma":[0.83384794,0.0014688144,0.15111205,0.009779697,0.0036679152,0.000011661666,0.00003318691,0.00001561529,0.000063119136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98942226,0.0008182878,0.009123875,0.0002736418,0.0001800192,0.00018193475],"domain_scores_gemma":[0.9596344,0.023257894,0.012079948,0.00050260185,0.004216146,0.00030895913],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03681144,0.00012585874,0.0014379438,0.00007818378,0.00020160041,0.000027771575,0.00007108092,0.00026365614,0.000032211778],"category_scores_gemma":[0.67002434,0.00009115888,0.00035483923,0.000024770558,0.00016280894,0.00044312523,0.00005495387,0.00042171226,0.0000017416791],"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":[0.0023449543,0.00014681778,0.5027281,0.00018956677,0.00034590406,0.0037930834,0.00012586104,0.00007597989,0.00006314905,0.0014500715,0.06715992,0.4215766],"study_design_scores_gemma":[0.018754628,0.010062594,0.459551,0.00057175703,0.0025398857,0.085054375,0.004402598,0.003946984,0.000102726925,0.047962196,0.36659643,0.00045483312],"about_ca_topic_score_codex":0.00011936765,"about_ca_topic_score_gemma":0.0001411413,"teacher_disagreement_score":0.63321286,"about_ca_system_score_codex":0.00004950994,"about_ca_system_score_gemma":0.00036265366,"threshold_uncertainty_score":0.9918053},"labels":[],"label_agreement":null},{"id":"W2615863432","doi":"10.1016/j.jclinepi.2017.02.004","title":"EBM has not only called out the problems but offered solutions","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","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":"McMaster University","funders":"","keywords":"Reading (process); Evidence-based medicine; MEDLINE; Point (geometry); Medicine; Epistemology; Alternative medicine; Philosophy; Mathematics; Law; Linguistics; Pathology; Political science","score_opus":0.8698806800131382,"score_gpt":0.6750940167607591,"score_spread":0.19478666325237914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615863432","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":[0.0032579913,0.00059092394,0.0012870602,0.9671564,0.023975205,0.0010561645,0.00005763388,0.000018404677,0.0026001816],"genre_scores_gemma":[0.0046847556,0.0030413775,0.0011652403,0.8945846,0.06524822,0.000091313756,0.000047577396,0.00004213285,0.031094806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9445306,0.040771253,0.010750567,0.00060854224,0.0008881525,0.00245091],"domain_scores_gemma":[0.7960944,0.18310547,0.016170092,0.001603612,0.0019130448,0.0011133746],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13062903,0.00036337072,0.0039821183,0.0002614626,0.0034300308,0.000038787028,0.002786735,0.003641548,0.00086717604],"category_scores_gemma":[0.35987878,0.00019143985,0.001220555,0.00010970659,0.0022423929,0.00021028765,0.0004018598,0.026113402,0.001289434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001370943,0.00007330755,0.019595884,0.00028278487,0.00011621016,0.000048396538,0.00038413654,0.0000069767025,0.0000010577571,0.00016795295,0.9761751,0.0030110402],"study_design_scores_gemma":[0.0008690047,0.0006402941,0.076273724,0.0006018457,0.00006740533,0.00005590414,0.00013635491,0.00023182524,4.3657586e-8,0.00819669,0.91276866,0.00015827095],"about_ca_topic_score_codex":0.0012640792,"about_ca_topic_score_gemma":0.0009695431,"teacher_disagreement_score":0.22924975,"about_ca_system_score_codex":0.0003056844,"about_ca_system_score_gemma":0.021642748,"threshold_uncertainty_score":0.9994882},"labels":[],"label_agreement":null},{"id":"W2615921597","doi":"10.1016/j.jclinepi.2017.05.005","title":"GRADE guidelines 17: assessing the risk of bias associated with missing participant outcome data in a body of evidence","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":160,"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 Work & Health; Impact; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; McMaster University","funders":"","keywords":"Missing data; Pooling; Meta-analysis; Systematic review; Outcome (game theory); Statistics; Medicine; Publication bias; Econometrics; Psychology; MEDLINE; Computer science; Mathematics; Artificial intelligence","score_opus":0.9951610928989906,"score_gpt":0.7925636937244923,"score_spread":0.20259739917449826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615921597","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9386331,0.0027550007,0.022665022,0.035111744,0.0005254207,0.00021836357,0.00001462149,9.2647406e-7,0.00007582818],"genre_scores_gemma":[0.97806484,0.00062652153,0.020245196,0.0007167636,0.00019885396,0.0000011888438,6.895813e-7,0.000007060022,0.00013890446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7122668,0.1855676,0.09647409,0.0010063736,0.004140101,0.0005450495],"domain_scores_gemma":[0.11599859,0.65410626,0.21552846,0.009533235,0.0045026694,0.00033077048],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8327324,0.00023191799,0.01398227,0.00020430032,0.00017031812,0.00017564728,0.0062316693,0.00022443925,0.00024634163],"category_scores_gemma":[0.9854707,0.00007038301,0.002311264,0.00038903128,0.00077209563,0.0007059889,0.0005342018,0.00091036153,0.000010875895],"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":[0.000031301486,0.00009957,0.9824694,0.000017372648,0.000452991,0.000012083245,0.00004165079,0.0005992598,0.000010000931,0.00005510536,0.008430254,0.007781044],"study_design_scores_gemma":[0.00038697285,0.00017896913,0.9379427,0.001033814,0.000999937,0.000015410369,0.0001779391,0.049965873,0.0000022458712,0.007872001,0.0013508223,0.00007335106],"about_ca_topic_score_codex":0.00011867917,"about_ca_topic_score_gemma":0.00018790168,"teacher_disagreement_score":0.5962682,"about_ca_system_score_codex":0.000014299201,"about_ca_system_score_gemma":0.00037369734,"threshold_uncertainty_score":0.9991451},"labels":[],"label_agreement":null},{"id":"W2616023578","doi":"10.1016/j.jclinepi.2017.05.013","title":"Variance inflation is not the same as variance overestimation","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","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; Jewish General Hospital; McGill University","funders":"","keywords":"Overfitting; Statistics; Econometrics; Variance (accounting); Inference; Propensity score matching; Odds; Standard error; Mathematics; Logistic regression; Computer science; Economics; Artificial intelligence","score_opus":0.2556855071813623,"score_gpt":0.5168565518023022,"score_spread":0.2611710446209399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616023578","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":[0.0085929325,0.0003974295,0.011279957,0.9712704,0.006893439,0.00022616668,0.000011693802,0.000015436211,0.0013125859],"genre_scores_gemma":[0.017984709,0.0020907426,0.005949371,0.91704386,0.050158724,0.000006251786,0.000025419731,0.000046732177,0.0066941865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913745,0.0031008066,0.0042955293,0.0003757665,0.00044868764,0.00040473545],"domain_scores_gemma":[0.95889443,0.030326951,0.008947907,0.0011067989,0.00053601636,0.00018792349],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.01914084,0.00029689004,0.003080674,0.00009613859,0.00015721789,0.000024574241,0.00059691997,0.0021058063,0.00018204219],"category_scores_gemma":[0.08579651,0.00017554016,0.0010052628,0.000052182335,0.00039048668,0.0001305587,0.00004993431,0.006903526,0.00012690906],"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":[0.00077460194,0.00006294866,0.020283313,0.00012675613,0.0006620181,0.0005150527,0.00005875491,0.0000809028,0.000010261742,0.0007471523,0.9395895,0.03708874],"study_design_scores_gemma":[0.0014070099,0.0007851663,0.12674949,0.00075513584,0.00029326597,0.0008749033,0.0000014467761,0.0025872553,0.0000043045397,0.02658313,0.83980894,0.00014994979],"about_ca_topic_score_codex":0.00011258326,"about_ca_topic_score_gemma":0.000001122058,"teacher_disagreement_score":0.10646617,"about_ca_system_score_codex":0.00009221604,"about_ca_system_score_gemma":0.0007597444,"threshold_uncertainty_score":0.9991897},"labels":[],"label_agreement":null},{"id":"W2616456691","doi":"10.1016/j.jclinepi.2017.05.006","title":"The GRADE Working Group clarifies the construct of certainty of evidence","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":797,"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; McMaster University; Impact","funders":"Medical Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Statens beredning för medicinsk och social utvärdering; University of Aberdeen; Parker Institute for Cancer Immunotherapy; Scottish Government; Oak Foundation","keywords":"Certainty; Grading (engineering); Brainstorming; Systematic review; Construct (python library); Guideline; Management science; Computer science; Psychology; Medicine; MEDLINE; Mathematics; Artificial intelligence; Engineering","score_opus":0.9727773223646747,"score_gpt":0.811914680918852,"score_spread":0.16086264144582274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616456691","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":[0.48583785,0.0004310318,0.0024509951,0.5053867,0.0047985446,0.00043982564,0.0000071219806,0.0000048450897,0.0006430596],"genre_scores_gemma":[0.96892875,0.0028139306,0.0027431692,0.024457805,0.0009627001,0.00000757519,1.0271853e-7,0.0000063057046,0.00007966344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95806134,0.030036034,0.010547723,0.00020897025,0.00045304195,0.00069289067],"domain_scores_gemma":[0.5941338,0.38529235,0.018935714,0.00082290225,0.00058723055,0.00022796573],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.16941763,0.000109267,0.001576645,0.00005488759,0.0015452134,0.0000075186476,0.001782995,0.00039762576,0.00007755162],"category_scores_gemma":[0.56369543,0.000045486293,0.00040233566,0.00009968404,0.0031999093,0.00015335767,0.00030395403,0.0028235402,0.000009900847],"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":[0.0002060786,0.000012778474,0.919225,0.000062732324,0.000042788382,0.0000014977114,0.00070687634,0.000009156526,0.000029161343,0.042028323,0.015418164,0.022257453],"study_design_scores_gemma":[0.00071711815,0.00034209178,0.8845659,0.0006494702,0.00003297331,0.000013589808,0.0015181522,0.00013238225,0.000006846393,0.039557427,0.07241614,0.000047931262],"about_ca_topic_score_codex":0.0004258962,"about_ca_topic_score_gemma":0.00035943757,"teacher_disagreement_score":0.4830909,"about_ca_system_score_codex":0.000039653005,"about_ca_system_score_gemma":0.0011431917,"threshold_uncertainty_score":0.99975467},"labels":[],"label_agreement":null},{"id":"W2616743646","doi":"10.1016/j.jclinepi.2017.05.014","title":"Patient-important outcomes in decision-making: a point of no return","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University","funders":"","keywords":"Scopus; Psychological intervention; Medicine; Patient-centered outcomes; MEDLINE; Journal club; Outcomes research; Alternative medicine; Family medicine; Health care; Medical education; Nursing; Pathology","score_opus":0.6194349861416084,"score_gpt":0.5829828642948257,"score_spread":0.036452121846782704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616743646","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":[0.050504107,0.0032993276,0.0012996717,0.9316758,0.01063042,0.0005519374,0.000326773,0.000008629678,0.0017033656],"genre_scores_gemma":[0.031739656,0.0018104588,0.02428032,0.93486464,0.006815491,0.000018202314,0.000022742504,0.00008348997,0.0003650184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92539936,0.0065106456,0.06619037,0.0008512596,0.00023626286,0.00081209146],"domain_scores_gemma":[0.7110726,0.16892746,0.11750123,0.0016877335,0.0005065541,0.00030440692],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.20710184,0.0004493398,0.014851767,0.00093115825,0.00007876399,0.000025223126,0.0012951196,0.0025743665,0.0006794457],"category_scores_gemma":[0.6772064,0.0004144284,0.0021963287,0.000087257074,0.00041681615,0.00035584494,0.00020103558,0.0046405275,0.00044900528],"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":[0.000084163694,0.000101182435,0.44957858,0.00018434913,0.000197405,0.00010311356,0.00007134425,0.000018031931,1.3068651e-8,0.0009334689,0.5482211,0.0005072507],"study_design_scores_gemma":[0.0013878152,0.0009097017,0.17142875,0.0014762202,0.000031477248,0.00008746982,0.000040991014,0.0007252571,3.8480305e-8,0.17746876,0.6460494,0.0003941451],"about_ca_topic_score_codex":0.000245953,"about_ca_topic_score_gemma":0.000066073175,"teacher_disagreement_score":0.47010458,"about_ca_system_score_codex":0.000385939,"about_ca_system_score_gemma":0.0008110119,"threshold_uncertainty_score":0.9998308},"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":"W2620826610","doi":"10.1016/j.jclinepi.2017.05.017","title":"A systematic survey on reporting and methods for handling missing participant data for continuous outcomes in randomized controlled trials","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","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; McMaster University; Impact","funders":"","keywords":"Missing data; Randomized controlled trial; Medicine; Interquartile range; Imputation (statistics); MEDLINE; Clinical trial; Statistics; Surgery; Internal medicine; Mathematics","score_opus":0.9405744797648787,"score_gpt":0.763690149918479,"score_spread":0.17688432984639968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620826610","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":[0.0000015292214,0.44952187,0.54398,0.00020552464,0.0011005386,0.0050657145,0.00011518927,0.0000043871464,0.000005250249],"genre_scores_gemma":[0.000002246514,0.43329653,0.5659041,0.000079750214,0.00033859655,0.00031039058,0.000012741934,0.00003284423,0.000022850434],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.46564835,0.39720544,0.13436544,0.0013235132,0.000351273,0.0011059837],"domain_scores_gemma":[0.011204932,0.85019875,0.1366738,0.0011192143,0.00051808613,0.00028520206],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86807144,0.00062488305,0.16247077,0.00029287147,0.0001458978,0.00009884395,0.0009307473,0.001006642,0.000005432174],"category_scores_gemma":[0.9985148,0.00028588445,0.007154574,0.000052126663,0.00037467643,0.0000754366,0.00017252662,0.0012128756,3.2064696e-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":[0.03110057,0.00021225584,0.00015985538,0.10872371,0.0077517163,0.000024382658,0.000018355664,2.0059683e-7,2.9758652e-8,0.01993326,0.00022439503,0.83185124],"study_design_scores_gemma":[0.13236086,0.00061097124,0.000047515285,0.1921717,0.03230661,0.00008581176,0.000011390047,0.0063408352,3.142833e-8,0.63240886,0.003264421,0.0003909823],"about_ca_topic_score_codex":0.00002098454,"about_ca_topic_score_gemma":0.000012663776,"teacher_disagreement_score":0.8314603,"about_ca_system_score_codex":0.000030813353,"about_ca_system_score_gemma":0.0007908432,"threshold_uncertainty_score":0.99995935},"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","metaepi_broad"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"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":"W2621399066","doi":"10.1016/j.jclinepi.2017.05.018","title":"Incorporating patients' views in guideline development: a systematic review of guidance documents","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":75,"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":"Instituto de Salud Carlos III; Academy of Nutrition and Dietetics","keywords":"Guideline; Medicine; MEDLINE; Systematic review; Medical physics; Family medicine; Pathology; Political science","score_opus":0.7637346207314432,"score_gpt":0.6881316636374664,"score_spread":0.0756029570939768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621399066","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":[0.000015027797,0.99344915,0.00050277024,0.0012348498,0.0014717352,0.0031055836,0.000018154278,0.0000060939683,0.00019660531],"genre_scores_gemma":[0.000008267891,0.95922375,0.034182627,0.0055503203,0.0005411736,0.0000902162,0.0002541133,0.000056822766,0.00009272902],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.8930945,0.020685516,0.084161825,0.00062439655,0.0009553823,0.0004784203],"domain_scores_gemma":[0.7418621,0.083786204,0.16923237,0.0019494977,0.0025667984,0.0006030032],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19025393,0.0005846332,0.029740848,0.00045877483,0.00007556545,0.000007947371,0.0011166439,0.0006759827,0.00037421478],"category_scores_gemma":[0.6947721,0.00038452246,0.0031578117,0.00033356572,0.00022196866,0.00027634852,0.00045166656,0.003031623,0.000040183993],"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":[0.00007528597,0.000498414,0.0055110175,0.6530734,0.0005701564,0.00005413787,0.0000064749343,6.740304e-7,8.81846e-9,0.000031265135,0.008966129,0.33121303],"study_design_scores_gemma":[0.0013085774,0.000557773,0.0002634526,0.48489642,0.0029095917,0.00013734099,0.0000053912695,0.000005415774,1.3212621e-8,0.00011774351,0.5096435,0.00015479389],"about_ca_topic_score_codex":0.000026450392,"about_ca_topic_score_gemma":0.000021003409,"teacher_disagreement_score":0.50451815,"about_ca_system_score_codex":0.0003932793,"about_ca_system_score_gemma":0.0039317063,"threshold_uncertainty_score":0.99986064},"labels":[],"label_agreement":null},{"id":"W2621775824","doi":"10.1016/j.jclinepi.2017.06.004","title":"Deficiencies in addressing effect modification in network meta-analyses: a meta-epidemiological survey","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Joseph’s Healthcare Hamilton; University of Waterloo; McMaster University; Health Sciences Centre; McMaster University Medical Centre","funders":"","keywords":"Medicine; Meta-analysis; Randomized controlled trial; MEDLINE; Epidemiology; Univariate; Statistics; Surgery; Multivariate statistics; Internal medicine","score_opus":0.9972931111755386,"score_gpt":0.8100744055105886,"score_spread":0.18721870566495002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621775824","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017300743,0.9858115,0.010030112,0.0006816167,0.0013917222,0.0013554363,0.000035757366,0.0000032077892,0.0005176783],"genre_scores_gemma":[0.0013311688,0.9875667,0.008904834,0.00066936517,0.00080248807,0.00015627858,0.0000307748,0.00003871238,0.00049967313],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.05533226,0.7621793,0.17420363,0.0029772692,0.003994751,0.0013127653],"domain_scores_gemma":[0.057016216,0.7348409,0.19861794,0.0070604566,0.001825434,0.00063902704],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.9570328,0.0017396696,0.22486193,0.0019400198,0.00020608318,0.0004139816,0.0097320005,0.0025463612,0.0026866877],"category_scores_gemma":[0.9711579,0.0005789339,0.08769281,0.0027168228,0.0008288476,0.0004619529,0.0006258986,0.0052784863,0.00067600334],"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":[0.000108082124,0.0003401286,0.09497079,0.0021002917,0.049986523,0.00016863906,0.000020311201,0.008528689,2.0263487e-8,0.0008063849,0.03345644,0.8095137],"study_design_scores_gemma":[0.0004285034,0.00047022605,0.053987198,0.0020817195,0.11502979,0.00018925486,0.000010366374,0.0030056667,7.014758e-9,0.01540328,0.8087772,0.0006167879],"about_ca_topic_score_codex":0.00018208643,"about_ca_topic_score_gemma":0.0005781058,"teacher_disagreement_score":0.8088969,"about_ca_system_score_codex":0.00016106736,"about_ca_system_score_gemma":0.0009869689,"threshold_uncertainty_score":0.9996662},"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":"W2626495592","doi":"10.1016/j.jclinepi.2017.06.005","title":"Testing the effectiveness of simplified search strategies for updating systematic reviews","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":19,"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; Health Sciences Centre; Impact","funders":"","keywords":"Systematic review; SSS*; Sensitivity (control systems); Meta-analysis; Computer science; Medicine; Data mining; Medical physics; Information retrieval; Statistics; MEDLINE; Mathematics; Artificial intelligence; Pathology; Engineering","score_opus":0.9656116065191289,"score_gpt":0.7232061649074447,"score_spread":0.2424054416116842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626495592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.487075,0.0064662825,0.48681223,0.004056092,0.0029601264,0.0059687444,0.00001174106,0.000003289963,0.0066464995],"genre_scores_gemma":[0.9758307,0.00010909367,0.023126133,0.00030611744,0.0004779664,0.000039429782,3.8032718e-7,0.000008923255,0.0001012954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.38372692,0.50735474,0.10451759,0.00096054,0.0028404654,0.00059974607],"domain_scores_gemma":[0.044783928,0.84691334,0.09972077,0.0041390415,0.004246174,0.00019673783],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.926142,0.000240688,0.021338724,0.00013760294,0.00036928337,0.00031648175,0.004491146,0.00020008405,0.00012472687],"category_scores_gemma":[0.97920215,0.00007801127,0.0061583193,0.00024354718,0.00043012173,0.0003241749,0.00022295778,0.000608714,0.00008855702],"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":[0.0004402987,0.00023369092,0.7511759,0.04305638,0.0020841663,0.00001089221,0.0002336929,0.0026284407,0.00042754717,0.13525902,0.014538633,0.04991136],"study_design_scores_gemma":[0.001074668,0.0010203794,0.605895,0.01070734,0.0013221623,0.00012152911,0.0014169882,0.02265418,0.000012327749,0.35146803,0.004084486,0.00022289566],"about_ca_topic_score_codex":0.000012071764,"about_ca_topic_score_gemma":0.000004949069,"teacher_disagreement_score":0.48875567,"about_ca_system_score_codex":0.000014611538,"about_ca_system_score_gemma":0.00028960963,"threshold_uncertainty_score":0.9931905},"labels":[],"label_agreement":null},{"id":"W2641327920","doi":"10.1016/j.jclinepi.2017.06.010","title":"Decisional conflict screening for a diversity of primary care decisions. Are we SURE yet?","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"Hôpital Saint-François d'Assise","funders":"","keywords":"Scopus; Checklist; Test (biology); Conflict of interest; Diversity (politics); Psychology; Primary care; Medicine; Family medicine; MEDLINE; Political science; Law","score_opus":0.8532536502138206,"score_gpt":0.6219951120256649,"score_spread":0.23125853818815567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2641327920","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":[0.003940007,0.030851059,0.0078442395,0.94000566,0.012792579,0.0021969688,0.0016506616,0.000035654222,0.0006831472],"genre_scores_gemma":[0.011298906,0.01790001,0.10693138,0.84624916,0.015258636,0.000114362985,0.0008890561,0.00016568873,0.0011927921],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9609187,0.02270718,0.013560377,0.0007468607,0.0009863417,0.0010805195],"domain_scores_gemma":[0.65296215,0.30865023,0.030840466,0.002022616,0.0050695506,0.00045501042],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.021553667,0.0005366882,0.0079890685,0.0004932084,0.0019615078,0.000007216343,0.0039456557,0.0056214947,0.00014936973],"category_scores_gemma":[0.30126148,0.00041970302,0.002722269,0.000118728145,0.00088655483,0.00023068557,0.0027740586,0.014821922,0.000028802722],"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":[0.0010995966,0.00004599063,0.3150966,0.0011559883,0.0002574295,0.00005383154,0.00056851166,0.000020677102,1.2639212e-7,0.0000644015,0.66989905,0.011737815],"study_design_scores_gemma":[0.0034012746,0.00074797176,0.17181218,0.008833785,0.0002817698,0.000026693151,0.00097610964,0.00005836001,1.1565269e-7,0.006621324,0.80695695,0.00028349954],"about_ca_topic_score_codex":0.00021609965,"about_ca_topic_score_gemma":0.0000808523,"teacher_disagreement_score":0.30795658,"about_ca_system_score_codex":0.00042366202,"about_ca_system_score_gemma":0.0036288493,"threshold_uncertainty_score":0.9998255},"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":"W2734751589","doi":"10.1016/j.jclinepi.2017.06.011","title":"AHRQ series on complex intervention systematic reviews—paper 1: an introduction to a series of articles that provide guidance and tools for reviews of complex interventions","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; University of Ottawa","funders":"Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Psychological intervention; Intervention (counseling); Systematic review; Mental health; Medicine; Health care; MEDLINE; Psychology; Nursing; Psychiatry; Political science","score_opus":0.9793103644375879,"score_gpt":0.8076726265970002,"score_spread":0.17163773784058767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734751589","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":[0.00038548352,0.91721284,0.01352928,0.04548476,0.003536847,0.019411976,0.00035102086,0.000020127203,0.00006768567],"genre_scores_gemma":[0.00013040357,0.9662135,0.027721602,0.0030722548,0.001524625,0.0009734989,0.00003441202,0.00003127327,0.0002984171],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9230372,0.048809588,0.026807696,0.0005265235,0.00027817592,0.00054082583],"domain_scores_gemma":[0.8824053,0.059111252,0.05541889,0.0013056566,0.0012017003,0.00055719644],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13955408,0.0003949324,0.014108657,0.00038401384,0.00035421003,0.000023394896,0.00085059163,0.00043245513,0.00025134184],"category_scores_gemma":[0.47709712,0.00025107028,0.0022795014,0.00021228658,0.0005491185,0.001148666,0.00021858957,0.0009984346,0.000030003659],"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":[0.00021763322,0.00013692085,0.00027871662,0.5496605,0.00013289333,5.177287e-7,0.00037962451,9.228377e-7,0.0000032137552,0.0046516317,0.030401707,0.41413572],"study_design_scores_gemma":[0.0004894474,0.0026982632,0.0018373235,0.16339421,0.00053048914,0.00004032923,0.0003088775,0.0000054109446,2.7077607e-7,0.0012959092,0.82926023,0.00013924636],"about_ca_topic_score_codex":0.00003286537,"about_ca_topic_score_gemma":0.0002905636,"teacher_disagreement_score":0.7988585,"about_ca_system_score_codex":0.00014782476,"about_ca_system_score_gemma":0.0005177604,"threshold_uncertainty_score":0.99999416},"labels":[],"label_agreement":null},{"id":"W2735111168","doi":"10.1016/j.jclinepi.2017.06.016","title":"AHRQ series on complex intervention systematic reviews—paper 6: PRISMA-CI extension statement and checklist","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Bruyère; University of Ottawa","funders":"Agency for Healthcare Research and Quality","keywords":"Psychological intervention; Systematic review; Checklist; Management science; Medicine; MEDLINE; Transparency (behavior); Health care; Psychology; Computer science; Nursing; Engineering; Political science","score_opus":0.9471681176843162,"score_gpt":0.7034028608121287,"score_spread":0.24376525687218753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735111168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7444213,0.0279744,0.08603823,0.11546118,0.010827581,0.006222308,0.000031754964,0.000013180906,0.009010054],"genre_scores_gemma":[0.95210356,0.006924237,0.024176609,0.0065952516,0.001000714,0.000035363402,0.000004306179,0.00002303279,0.009136902],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.7661886,0.14339411,0.086492464,0.0010435717,0.0024762906,0.00040496208],"domain_scores_gemma":[0.69750524,0.12117466,0.17111468,0.006702262,0.002771982,0.0007311966],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6945842,0.00033140418,0.018502118,0.00021030617,0.00030850255,0.00036755326,0.001911455,0.00022467358,0.0023698993],"category_scores_gemma":[0.8221366,0.00013181918,0.005095926,0.00011123753,0.0003771817,0.00052169926,0.00028471832,0.0006226558,0.0009929301],"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":[0.0005502285,0.00079934177,0.15993321,0.011443291,0.0017621364,0.00010393314,0.0002990126,0.00008587851,0.0000774466,0.02093606,0.6806316,0.12337788],"study_design_scores_gemma":[0.0011802056,0.0015813247,0.587704,0.0071474076,0.0008697232,0.00027587236,0.00036597316,0.0028092577,0.0000017805845,0.053777136,0.3440267,0.00026060527],"about_ca_topic_score_codex":0.00000977396,"about_ca_topic_score_gemma":0.000023590166,"teacher_disagreement_score":0.4277708,"about_ca_system_score_codex":0.000030299401,"about_ca_system_score_gemma":0.000042847605,"threshold_uncertainty_score":0.9997849},"labels":[],"label_agreement":null},{"id":"W2735183640","doi":"10.1016/j.jclinepi.2017.06.017","title":"AHRQ series on complex intervention systematic reviews—paper 7: PRISMA-CI elaboration and explanation","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; University of Ottawa","funders":"Agency for Healthcare Research and Quality","keywords":"Systematic review; Psychological intervention; Workgroup; Operationalization; Checklist; Construct (python library); Management science; MEDLINE; Psychology; Medicine; Applied psychology; Nursing; Computer science; Political science","score_opus":0.9563494319380608,"score_gpt":0.7100396889102945,"score_spread":0.24630974302776631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735183640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60453767,0.016600048,0.23636381,0.1160942,0.0103937425,0.005412664,0.000031940657,0.000014004914,0.010551911],"genre_scores_gemma":[0.9755316,0.0027965961,0.014904834,0.0031978793,0.0009513795,0.000027311136,0.000006263222,0.000012341186,0.0025718252],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.8126949,0.12605149,0.05848938,0.0006810836,0.0018434398,0.00023969584],"domain_scores_gemma":[0.7038288,0.12774572,0.16018517,0.0045746374,0.0032042894,0.00046135252],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6219113,0.00024142624,0.012507661,0.00024183816,0.00026068577,0.00037535894,0.0014140713,0.00024098474,0.001391532],"category_scores_gemma":[0.8472214,0.00010229651,0.002977985,0.00014179411,0.00021341228,0.0008256346,0.00011303402,0.00047836953,0.0007649832],"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":[0.00047604452,0.0005738265,0.32701668,0.008447524,0.0015509754,0.000042297055,0.00047396313,0.0001608234,0.000072204544,0.08659868,0.4077101,0.16687685],"study_design_scores_gemma":[0.001192325,0.0013946005,0.7032677,0.004806594,0.0008422053,0.00021812825,0.00050991325,0.005861223,0.0000023092337,0.099336706,0.18229984,0.00026845266],"about_ca_topic_score_codex":0.000005211201,"about_ca_topic_score_gemma":0.000027707829,"teacher_disagreement_score":0.376251,"about_ca_system_score_codex":0.000023648854,"about_ca_system_score_gemma":0.000040977182,"threshold_uncertainty_score":0.9995213},"labels":[],"label_agreement":null},{"id":"W2735599256","doi":"10.1016/j.jclinepi.2017.06.013","title":"AHRQ series on complex intervention systematic reviews—paper 3: adapting frameworks to develop protocols","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":51,"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":"Agency for Healthcare Research and Quality","keywords":"Systematic review; Psychological intervention; Scope (computer science); Protocol (science); Computer science; Management science; Intervention (counseling); Risk analysis (engineering); Data science; Medicine; MEDLINE; Alternative medicine; Engineering; Pathology","score_opus":0.9587330241719988,"score_gpt":0.8243697439714349,"score_spread":0.13436328020056387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735599256","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":[0.08298866,0.00013123662,0.13434918,0.6920691,0.010234313,0.07405626,0.00003222656,0.00008514731,0.006053857],"genre_scores_gemma":[0.26515928,0.0004215682,0.20013975,0.51263297,0.0067733703,0.012579171,0.000003685979,0.000071776194,0.0022184679],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.94223374,0.03986691,0.01638724,0.00033849676,0.0003738482,0.0007997933],"domain_scores_gemma":[0.8477454,0.12024416,0.028018096,0.0011978378,0.0017740341,0.001020434],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18918437,0.00020783902,0.0037935043,0.0001546282,0.0011480113,0.000024459414,0.0011444729,0.0006351658,0.0006837853],"category_scores_gemma":[0.8157477,0.00013457182,0.0004155888,0.00017355978,0.0002284009,0.00047110496,0.00030857566,0.0030997167,0.0009354956],"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":[0.0022258111,0.0003451028,0.41100594,0.045531385,0.0002296195,0.0000386711,0.0050529004,0.00008226498,0.00005026583,0.048040483,0.4383576,0.049039982],"study_design_scores_gemma":[0.0020406942,0.002131106,0.52392995,0.047602817,0.00004067918,0.00003270695,0.00078349694,0.00013050628,0.0000012784278,0.007911576,0.4151764,0.00021878253],"about_ca_topic_score_codex":0.000052399548,"about_ca_topic_score_gemma":0.00015209474,"teacher_disagreement_score":0.62656325,"about_ca_system_score_codex":0.00017163172,"about_ca_system_score_gemma":0.00075871573,"threshold_uncertainty_score":0.9998424},"labels":[],"label_agreement":null},{"id":"W2736912844","doi":"10.1016/j.jclinepi.2017.02.016","title":"Quasi-experimental study designs series—paper 5: a checklist for classifying studies evaluating the effects on health interventions—a taxonomy without labels","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":200,"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":"National Institute for Health and Care Research","keywords":"Checklist; Psychological intervention; Taxonomy (biology); Series (stratigraphy); Computer science; Psychology; Medicine; Nursing; Cognitive psychology; Biology","score_opus":0.9647059482022167,"score_gpt":0.8240026333355556,"score_spread":0.1407033148666611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736912844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77221787,0.00064488716,0.0062396294,0.2071075,0.007428913,0.006132796,0.000017839235,0.000025975218,0.00018460918],"genre_scores_gemma":[0.9090596,0.00026308824,0.016983442,0.06914073,0.0026941935,0.0012528823,0.000001032395,0.000029896772,0.00057517586],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94780475,0.04099644,0.009264269,0.00047279283,0.00044113726,0.0010206196],"domain_scores_gemma":[0.8086596,0.17365927,0.015549435,0.0008162887,0.00080982345,0.0005055847],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18193264,0.00025483177,0.0029134902,0.00012167472,0.004277626,0.000026156169,0.0009690052,0.00019889536,0.00006934164],"category_scores_gemma":[0.45294532,0.00015038294,0.0006389239,0.00008917667,0.00054261065,0.0004557738,0.00031859305,0.0017884191,0.000038729493],"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":[0.002580192,0.0023594778,0.8585583,0.0014973227,0.0007589199,0.000007625782,0.011641858,0.000022577355,0.000061269224,0.0047095483,0.07808621,0.03971673],"study_design_scores_gemma":[0.022779197,0.17960483,0.6492829,0.005089773,0.00030017408,0.000035390796,0.05952183,0.00057729555,0.000025840947,0.008889338,0.073384,0.0005094673],"about_ca_topic_score_codex":0.00014705754,"about_ca_topic_score_gemma":0.00046260908,"teacher_disagreement_score":0.27101266,"about_ca_system_score_codex":0.0004123595,"about_ca_system_score_gemma":0.0017930934,"threshold_uncertainty_score":0.9970187},"labels":[],"label_agreement":null},{"id":"W2743439262","doi":"10.1016/j.jclinepi.2017.07.011","title":"Congruence between patient characteristics and interventions may partly explain medication adherence intervention effectiveness: an analysis of 190 randomized controlled trials from a Cochrane systematic review","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Medication Adherence and Compliance","field":"Medicine","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":"McMaster University; Hamilton General Hospital","funders":"Universität Basel","keywords":"Randomized controlled trial; Medicine; Psychological intervention; Systematic review; Physical therapy; Meta-analysis; Intervention (counseling); Alternative medicine; Congruence (geometry); MEDLINE; Psychology; Internal medicine; Nursing; Pathology; Social psychology","score_opus":0.5755104334938317,"score_gpt":0.6324675335733968,"score_spread":0.056957100079565115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743439262","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":[0.00084834546,0.9791235,0.012949371,0.00036940118,0.00081903226,0.005716268,0.00014861158,0.000008195873,0.000017291468],"genre_scores_gemma":[0.010659593,0.987048,0.0004968619,0.00026448313,0.00038129755,0.0005442896,0.0005501042,0.00001751025,0.000037891372],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8715277,0.09201403,0.035104893,0.0005465864,0.0005719588,0.00023485227],"domain_scores_gemma":[0.49752966,0.35775056,0.14007886,0.0017993905,0.0019500841,0.0008914569],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.20425315,0.00047586352,0.088713236,0.00051032874,0.000059862236,0.000018327746,0.0005657199,0.00067655416,0.0003984518],"category_scores_gemma":[0.6460742,0.00025705912,0.01401711,0.0002338289,0.00073804625,0.000136312,0.000076451775,0.001134261,0.000019170184],"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":[0.010115104,0.0005515193,0.002069194,0.7051928,0.037468623,0.000022493763,0.00002658022,2.2913407e-7,1.8332382e-7,0.00022040642,0.00013207615,0.24420078],"study_design_scores_gemma":[0.035679273,0.0011311074,0.0021755511,0.751309,0.20837103,0.000027693959,0.000026798156,0.00014774209,9.340355e-8,0.00027795217,0.0007038532,0.00014992374],"about_ca_topic_score_codex":0.00006341968,"about_ca_topic_score_gemma":0.0000054518487,"teacher_disagreement_score":0.44182104,"about_ca_system_score_codex":0.00006622517,"about_ca_system_score_gemma":0.0005791394,"threshold_uncertainty_score":0.99998814},"labels":[],"label_agreement":null},{"id":"W2750029871","doi":"10.1016/j.jclinepi.2017.06.001","title":"The PRECIS-2 tool has good interrater reliability and modest discriminant validity","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"North York General Hospital; Centre for Family Medicine; Western University","funders":"Medical Research Council; Chief Scientist Office; University of Aberdeen; Scottish Government; University of Dundee","keywords":"Inter-rater reliability; Discriminant validity; External validity; Intraclass correlation; Reliability (semiconductor); Face validity; Medicine; Linear discriminant analysis; Applied psychology; Validity; Clinical psychology; Psychology; Computer science; Psychometrics; Artificial intelligence; Social psychology; Developmental psychology; Rating scale","score_opus":0.9632173445817618,"score_gpt":0.6924030426664284,"score_spread":0.2708143019153334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750029871","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":[0.88056576,0.0006110346,0.04148401,0.07116447,0.003472031,0.00030177843,0.00000599161,0.0000013681146,0.0023935498],"genre_scores_gemma":[0.98915493,0.0005456184,0.006109705,0.0008309113,0.000627193,0.000004309934,2.357515e-7,0.0000058846963,0.0027212068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.77562684,0.15694404,0.06307024,0.0012455194,0.0025340319,0.0005793487],"domain_scores_gemma":[0.333975,0.5556789,0.0946098,0.011576163,0.0033941746,0.0007659879],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7460754,0.00023617,0.009188504,0.0000627697,0.00071709964,0.000790519,0.0036609713,0.00026096308,0.00054583064],"category_scores_gemma":[0.9041359,0.00007303007,0.003994357,0.00006801746,0.0013248603,0.00040160478,0.0005366948,0.0009100093,0.000222253],"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":[0.00011662593,0.000082874525,0.84270215,0.000013840513,0.00016465299,0.00000790437,0.00006926218,0.000040304036,0.0000022881236,0.004093522,0.07826993,0.07443667],"study_design_scores_gemma":[0.00023809771,0.00026698824,0.64580274,0.000033391407,0.00017276406,0.000057408208,0.00005882819,0.0065500606,0.0000011736028,0.18234277,0.16440442,0.00007135155],"about_ca_topic_score_codex":0.000018454779,"about_ca_topic_score_gemma":0.00006826854,"teacher_disagreement_score":0.44165185,"about_ca_system_score_codex":0.000016396249,"about_ca_system_score_gemma":0.00015004505,"threshold_uncertainty_score":0.7622993},"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":["metaresearch"],"domain":"methods","study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2753875979","doi":"10.1016/j.jclinepi.2017.08.018","title":"Controversy and debate on clinical genomics sequencing—paper 1: genomics is not exceptional: rigorous evaluations are necessary for clinical applications of genomic sequencing","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","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":"Centre hospitalier universitaire de Québec; University of Toronto; Université Laval; University of Ottawa","funders":"","keywords":"Genomics; Personalized medicine; Exome sequencing; Precision medicine; Exome; Health care; Genomic sequencing; Data science; Medical genetics; Medicine; Computer science; Genome; Bioinformatics; Biology; Genetics; Pathology; Mutation","score_opus":0.4942399648296587,"score_gpt":0.5707425731898546,"score_spread":0.07650260836019585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753875979","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":[0.021136327,0.9665345,0.005307537,0.0009932544,0.0021729586,0.0019605358,0.0017710691,0.000008702071,0.00011510518],"genre_scores_gemma":[0.002264089,0.9785741,0.008458895,0.00422715,0.005833921,0.000092838425,0.00027794758,0.00010768493,0.00016339513],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98257804,0.0038813583,0.011553021,0.001200048,0.00022422,0.0005632861],"domain_scores_gemma":[0.96150744,0.018630782,0.016903445,0.0013380192,0.00095686835,0.00066347467],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.025463281,0.0006495346,0.0075152437,0.00018596492,0.00028091084,0.00003520062,0.0012241672,0.0022227098,0.000029420886],"category_scores_gemma":[0.03419486,0.0005214326,0.0048467373,0.00005088265,0.0011505997,0.000018292058,0.0003730385,0.0014583473,0.000019563107],"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":[0.0013776609,0.00061128306,0.004875334,0.002337186,0.0045666294,0.000030431063,0.000022633712,0.00024319103,0.000104484876,0.0006295274,0.015169061,0.9700326],"study_design_scores_gemma":[0.0023078392,0.0019495992,0.0037537003,0.0008018599,0.0027133008,0.0002600517,0.000039937902,0.00013543434,0.0000025118165,0.0030278456,0.98449117,0.0005167333],"about_ca_topic_score_codex":0.000012466326,"about_ca_topic_score_gemma":0.00001859169,"teacher_disagreement_score":0.96951586,"about_ca_system_score_codex":0.00020277241,"about_ca_system_score_gemma":0.0048127067,"threshold_uncertainty_score":0.99972373},"labels":[],"label_agreement":null},{"id":"W2754128910","doi":"10.1016/j.jclinepi.2017.08.009","title":"Living systematic reviews: 4. Living guideline recommendations","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":339,"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":"Medical Research Council; National Centre for the Replacement, Refinement and Reduction of Animals in Research","keywords":"Guideline; Systematic review; Process (computing); Medicine; MEDLINE; Management science; Computer science; Engineering; Political science; Pathology","score_opus":0.9153166999272386,"score_gpt":0.7418525059053147,"score_spread":0.17346419402192392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754128910","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":[0.0000010773421,0.973806,0.00892593,0.008232746,0.0061379727,0.0024664497,0.000015213948,0.000025451154,0.00038914906],"genre_scores_gemma":[0.0000032072458,0.9369362,0.048386317,0.0059557487,0.0076976568,0.00006660863,0.00005360381,0.000091749396,0.00080888777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87528235,0.04798395,0.07471996,0.0007896067,0.0005255222,0.0006986442],"domain_scores_gemma":[0.1746466,0.6923616,0.1267345,0.0027535094,0.0022540127,0.0012497847],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.31100675,0.0007278518,0.033177473,0.0005032721,0.00020437744,0.000044574863,0.0010937973,0.0014559388,0.0009756089],"category_scores_gemma":[0.9443098,0.00045293226,0.00820613,0.00021919188,0.00028140252,0.00041165558,0.0004413897,0.004810068,0.0005114665],"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":[0.000019378072,0.00028796308,0.0004694079,0.11032586,0.0010457757,0.000039398124,0.000011304286,5.5965734e-7,1.0538318e-8,0.00007599203,0.10200472,0.78571963],"study_design_scores_gemma":[0.00027948414,0.00057879835,0.00009587791,0.33523256,0.008833523,0.0016670945,0.000026193482,0.000057284506,7.5521933e-10,0.00014864234,0.6528767,0.00020386465],"about_ca_topic_score_codex":0.000027999306,"about_ca_topic_score_gemma":0.000019245128,"teacher_disagreement_score":0.7855158,"about_ca_system_score_codex":0.00026712613,"about_ca_system_score_gemma":0.0023960366,"threshold_uncertainty_score":0.99993765},"labels":[],"label_agreement":null},{"id":"W2754163561","doi":"10.1016/j.jclinepi.2017.09.007","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 3: a systematic review shows limitations in most tools designed to assess quality and develop recommendations","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":21,"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; Health Sciences Centre; University of British Columbia; Impact; McMaster University","funders":"Agency for Healthcare Research and Quality","keywords":"Operationalization; Terminology; Systematic review; Computer science; Quality (philosophy); Test (biology); Health care; Confusion; Critical appraisal; Resource (disambiguation); Management science; Data science; MEDLINE; Process management; Medicine; Psychology; Alternative medicine; Engineering","score_opus":0.7257361177039493,"score_gpt":0.6401018406470225,"score_spread":0.08563427705692683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754163561","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":[0.00013032209,0.9814024,0.0011213747,0.013639689,0.00074267946,0.002745101,0.000057415924,0.000016930191,0.0001440747],"genre_scores_gemma":[0.0010196896,0.9738806,0.016100807,0.008461672,0.00022514892,0.00017101002,0.00005294708,0.00004653893,0.000041574036],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96840006,0.011536148,0.018406408,0.0007572129,0.00035145442,0.0005487083],"domain_scores_gemma":[0.055290073,0.9300543,0.011602054,0.0009099213,0.0010798336,0.0010637837],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065556265,0.00055939803,0.016479507,0.0003395069,0.00016378665,0.00008925401,0.00043197648,0.0012041082,0.00003442971],"category_scores_gemma":[0.9878362,0.00036967997,0.0008426717,0.00048298773,0.00030256665,0.00024624105,0.00020255285,0.0025699218,0.000024019912],"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":[0.00004195133,0.00032342423,0.01130621,0.1410634,0.00027065162,0.00015352631,0.000022103655,0.0000015483719,2.052555e-8,0.00070928776,0.0015508549,0.844557],"study_design_scores_gemma":[0.0009545157,0.00096266106,0.088439845,0.8871738,0.002699325,0.0009239122,0.000031093103,0.0000101193045,1.6680759e-9,0.0026889367,0.015809165,0.00030663834],"about_ca_topic_score_codex":0.000034231874,"about_ca_topic_score_gemma":0.0002475685,"teacher_disagreement_score":0.92227995,"about_ca_system_score_codex":0.00017006842,"about_ca_system_score_gemma":0.0028755108,"threshold_uncertainty_score":0.9998755},"labels":[],"label_agreement":null},{"id":"W2754475330","doi":"10.1016/j.jclinepi.2017.08.020","title":"Controversy and debate on clinical genomics sequencing—paper 2: clinical genome-wide sequencing: don't throw out the baby with the bathwater!","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","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":"Exome sequencing; Mendelian inheritance; Personal genomics; Genomics; Whole genome sequencing; Exome; Genome; DNA sequencing; Cancer genome sequencing; Genetic counseling; Disease; Genetics; Computational biology; Genetic testing; Biology; Medicine; Gene; Mutation; Internal medicine","score_opus":0.3437453694255116,"score_gpt":0.49147768262779545,"score_spread":0.14773231320228386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754475330","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":[0.021584047,0.967367,0.00044347008,0.0057343496,0.0031834142,0.0009918826,0.00013981681,0.000009134814,0.0005468909],"genre_scores_gemma":[0.0045318683,0.9746573,0.0006059797,0.012555118,0.0069258064,0.00001989492,0.00006169448,0.00010920814,0.00053314975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9774553,0.011723373,0.008464466,0.0012201401,0.00029058996,0.0008460985],"domain_scores_gemma":[0.9557167,0.03006834,0.010976489,0.002028937,0.00045015797,0.0007593185],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04184787,0.0008734899,0.0075468095,0.00007490436,0.0004622496,0.00010154128,0.0022093179,0.0020387203,0.000030184532],"category_scores_gemma":[0.0507754,0.00038152686,0.004143472,0.000048560298,0.0028594234,0.000016962707,0.0006198974,0.0035613272,0.0000350986],"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":[0.0052537424,0.0008371928,0.029202731,0.0018218387,0.017307423,0.001700157,0.00015179643,0.00030496437,0.000025639702,0.00079130207,0.06429183,0.8783114],"study_design_scores_gemma":[0.0015743892,0.0037470553,0.0023860536,0.000746581,0.0020395855,0.000908688,0.00006700533,0.000013402711,6.256661e-7,0.00052660186,0.987505,0.00048501286],"about_ca_topic_score_codex":0.000018002556,"about_ca_topic_score_gemma":0.00010144884,"teacher_disagreement_score":0.9232132,"about_ca_system_score_codex":0.00010544577,"about_ca_system_score_gemma":0.0036322817,"threshold_uncertainty_score":0.9998637},"labels":[],"label_agreement":null},{"id":"W2754736027","doi":"10.1016/j.jclinepi.2017.08.010","title":"Living systematic review: 1. Introduction—the why, what, when, and how","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":671,"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":"National Health and Medical Research Council; Medical Research Council; National Centre for the Replacement, Refinement and Reduction of Animals in Research","keywords":"Systematic review; Currency; Resource (disambiguation); Risk analysis (engineering); Computer science; Data science; Medicine; Management science; MEDLINE; Economics; Political science; Macroeconomics","score_opus":0.8855397792812411,"score_gpt":0.6523637085831975,"score_spread":0.23317607069804358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754736027","genre_codex":"commentary","genre_gemma":"review","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":[0.005879878,0.18284377,0.028059626,0.7756385,0.0062196194,0.00097005663,0.0000012836464,0.0000023928299,0.0003848666],"genre_scores_gemma":[0.32154605,0.42051372,0.037982617,0.15318193,0.02316451,0.00008866171,0.000001479414,0.000074075426,0.04344694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7068331,0.23051575,0.05779253,0.0011034274,0.003289712,0.00046543495],"domain_scores_gemma":[0.14992388,0.61126363,0.21797803,0.014151633,0.005823047,0.0008597998],"candidate_categories":["metaresearch","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8110153,0.00026080853,0.019029286,0.00013832189,0.0004187918,0.001212782,0.0039183446,0.0002008362,0.0014493567],"category_scores_gemma":[0.96055335,0.00008704329,0.004591198,0.00013888231,0.0005492684,0.001102286,0.00037144494,0.0008851174,0.00031854925],"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":[0.000006662429,0.000035009696,0.04512022,0.007912996,0.00059056433,0.000008145451,0.00006633378,0.0000047040116,6.1682215e-7,0.0026814614,0.9343443,0.009228971],"study_design_scores_gemma":[0.0004774469,0.0005975078,0.11306809,0.064507596,0.005700349,0.0019394445,0.001299974,0.0034671377,3.1499596e-7,0.102026515,0.7064838,0.0004318243],"about_ca_topic_score_codex":0.000002668049,"about_ca_topic_score_gemma":0.00001330837,"teacher_disagreement_score":0.62245655,"about_ca_system_score_codex":0.000013772576,"about_ca_system_score_gemma":0.000080905826,"threshold_uncertainty_score":0.99982405},"labels":[],"label_agreement":null},{"id":"W2754922575","doi":"10.1016/j.jclinepi.2017.09.003","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 2: a review of methodological and practical challenges","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"Western University; McMaster University; Victoria Hospital; Impact","funders":"","keywords":"Health care; Test (biology); MEDLINE; Computer science; Management science; Diagnostic test; Clinical study design; Research design; Data science; Clinical trial; Medicine; Pathology; Engineering","score_opus":0.7493340506059935,"score_gpt":0.6877203522985208,"score_spread":0.06161369830747265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754922575","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":[0.000086446096,0.97999215,0.00019735645,0.017644295,0.0009690397,0.00074331905,0.000017726175,0.000014115651,0.0003355377],"genre_scores_gemma":[0.00035470704,0.9678396,0.027300846,0.003521465,0.0008990824,0.000016589456,0.000008904387,0.0000455213,0.000013292832],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.971346,0.012860612,0.013890654,0.0008682092,0.0004609125,0.00057356735],"domain_scores_gemma":[0.0748137,0.90707564,0.0154538695,0.00087682955,0.0007157782,0.0010641946],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.08215181,0.0006092048,0.020716202,0.00018282072,0.00008669477,0.00001862852,0.0003053229,0.002411277,0.00010428269],"category_scores_gemma":[0.9875231,0.00034773143,0.0021125819,0.00012382741,0.0014519747,0.00014048353,0.00031910403,0.0046141525,0.000011740266],"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":[0.00014861833,0.00045055765,0.0041987165,0.03470726,0.0004197893,0.00084502314,0.0000065533472,8.645178e-8,1.035454e-8,0.0019156141,0.0014895011,0.9558183],"study_design_scores_gemma":[0.0011219946,0.0040338677,0.0543979,0.64446604,0.0040654326,0.009467812,0.000009854522,0.000005430207,2.8763647e-9,0.010921806,0.27127486,0.00023501896],"about_ca_topic_score_codex":0.000010301964,"about_ca_topic_score_gemma":0.000005163399,"teacher_disagreement_score":0.9555833,"about_ca_system_score_codex":0.000045296358,"about_ca_system_score_gemma":0.0018725827,"threshold_uncertainty_score":0.9998975},"labels":[],"label_agreement":null},{"id":"W2755511073","doi":"10.1016/j.jclinepi.2017.09.004","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 4: International guidelines show variability in their approaches","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Western University; McMaster University; University of British Columbia; Impact","funders":"","keywords":"Test (biology); Diagnostic test; Health care; Clinical decision making; Medicine; Medical physics; Computer science; Family medicine; Political science; Pediatrics; Biology","score_opus":0.9480298142571701,"score_gpt":0.7941344370178446,"score_spread":0.15389537723932556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755511073","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":[0.00058495975,0.9331382,0.0028956234,0.05029667,0.009437226,0.0022989374,0.00023382275,0.00003095972,0.0010835937],"genre_scores_gemma":[0.004039228,0.9732636,0.009625549,0.01052637,0.0023473187,0.00010140897,0.000014959627,0.0000415994,0.000039959523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9323691,0.038430125,0.026659494,0.00091679813,0.0004951915,0.0011292796],"domain_scores_gemma":[0.2101857,0.7629434,0.023923092,0.0009779171,0.0011955394,0.00077435287],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.21163028,0.0005269588,0.008098819,0.00050300354,0.00046650015,0.00003656771,0.001557131,0.0019485072,0.00028460877],"category_scores_gemma":[0.879385,0.00033462027,0.00077795703,0.00028085514,0.0006982915,0.0005638076,0.0005693557,0.0058084694,0.000050197727],"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":[0.000026289405,0.000066223045,0.12866108,0.0023554561,0.00005696446,0.000018128003,0.00018234823,0.0000068715517,6.6847523e-9,0.0017296697,0.00329207,0.8636049],"study_design_scores_gemma":[0.0009077326,0.00023305017,0.13058215,0.031006632,0.000094087096,0.000111042194,0.0001849119,0.00028015085,7.506274e-10,0.030823587,0.80553323,0.00024342122],"about_ca_topic_score_codex":0.000164783,"about_ca_topic_score_gemma":0.0005736631,"teacher_disagreement_score":0.8633615,"about_ca_system_score_codex":0.0004429454,"about_ca_system_score_gemma":0.0075573334,"threshold_uncertainty_score":0.9999106},"labels":[],"label_agreement":null},{"id":"W2756052618","doi":"10.1016/j.jclinepi.2017.09.005","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 5: a qualitative study with experts suggests that test accuracy data alone is rarely sufficient for decision making","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"McMaster University; Health Sciences Centre; Impact","funders":"","keywords":"Test (biology); Health care; Process (computing); Qualitative research; Preference; Developing country; Medicine; Psychology; Management science; Applied psychology; Computer science","score_opus":0.8959780327898161,"score_gpt":0.7278816273887818,"score_spread":0.16809640540103432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756052618","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":[0.006233358,0.9465888,0.039319098,0.0011369212,0.0035690626,0.0026503776,0.00039952467,0.000037146772,0.00006567855],"genre_scores_gemma":[0.06797622,0.8363155,0.09382274,0.00091497076,0.00076835346,0.0000621522,0.000017286118,0.00009849384,0.000024253555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9485786,0.023066461,0.021203432,0.0032571286,0.0024468615,0.0014475492],"domain_scores_gemma":[0.013697932,0.941627,0.03770015,0.004120278,0.0020957065,0.00075890525],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24743752,0.0012155955,0.016150882,0.0014885842,0.000875219,0.00073041336,0.006574778,0.0015561017,0.00009938938],"category_scores_gemma":[0.98712784,0.0006514023,0.0015000093,0.0015288682,0.0010503961,0.0014168203,0.002159369,0.0031028192,0.00001923974],"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":[0.00046669864,0.00081403926,0.056226045,0.00040600233,0.0003064335,0.0002797356,0.0009587038,0.000016871827,1.5445389e-8,0.000055671353,0.0074702823,0.9329995],"study_design_scores_gemma":[0.0070965555,0.023841538,0.21660204,0.13930866,0.0026993924,0.0035856327,0.018468065,0.0013219186,1.86742e-8,0.0821955,0.502501,0.002379661],"about_ca_topic_score_codex":0.00005735136,"about_ca_topic_score_gemma":0.00016004851,"teacher_disagreement_score":0.9348806,"about_ca_system_score_codex":0.00015805774,"about_ca_system_score_gemma":0.0020191579,"threshold_uncertainty_score":0.99974006},"labels":[],"label_agreement":null},{"id":"W2756480864","doi":"10.1016/j.jclinepi.2017.09.006","title":"Decision making about healthcare-related tests and diagnostic test strategies. Paper 1: a new series on testing to improve people's health","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"","keywords":"Grading (engineering); Medicine; Health care; Family medicine; Evidence-based medicine; Population; Test (biology); Alternative medicine; Medical physics; Pathology; Political science","score_opus":0.8190052404684721,"score_gpt":0.6652346716335993,"score_spread":0.15377056883487283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756480864","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":[0.7508947,0.0063508884,0.026321547,0.20765613,0.0054940414,0.0014353604,0.000023663792,0.000013605899,0.0018100655],"genre_scores_gemma":[0.9303344,0.0008589619,0.056462623,0.0110410275,0.0008652482,0.000005724972,4.7966097e-7,0.000019470228,0.0004120922],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9259614,0.02687272,0.042961866,0.0012966509,0.0021696247,0.00073778944],"domain_scores_gemma":[0.084187716,0.8365409,0.07018272,0.0046205474,0.0024586348,0.0020095336],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40196455,0.0004151976,0.012428254,0.00032607434,0.0005845884,0.00073178654,0.002229154,0.00037680604,0.00046748208],"category_scores_gemma":[0.9727323,0.00019983675,0.0018267098,0.0004435215,0.00022481482,0.0006854632,0.0003625757,0.0012605712,0.00036204586],"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":[0.00006061878,0.000056581783,0.55791086,0.000029890223,0.00007041683,0.000022144528,0.00010540221,0.00020256607,0.0000030493916,0.002366203,0.01865432,0.42051798],"study_design_scores_gemma":[0.0004964163,0.0025581773,0.87415653,0.0010111183,0.00007376179,0.0001940568,0.00015642935,0.0008896559,1.193871e-7,0.112717874,0.0075940765,0.00015180135],"about_ca_topic_score_codex":0.0002015503,"about_ca_topic_score_gemma":0.0008599947,"teacher_disagreement_score":0.8417736,"about_ca_system_score_codex":0.000055311357,"about_ca_system_score_gemma":0.0010542223,"threshold_uncertainty_score":0.8495706},"labels":[],"label_agreement":null},{"id":"W2757836714","doi":"10.1016/j.jclinepi.2017.09.019","title":"Controversy and debate on clinical genomics sequencing—paper 4: clinical genome-wide sequencing: response to Wilson, Miller, and Rousseau","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","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":"Miller; DNA sequencing; Genome; Genomics; Assertion; Personal genomics; Genetic testing; Locus (genetics); Whole genome sequencing; Computational biology; Biology; Genetics; Gene; Computer science","score_opus":0.16319915513679997,"score_gpt":0.4407617484456325,"score_spread":0.2775625933088325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757836714","genre_codex":"empirical","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":[0.74162185,0.0040150583,0.00027968214,0.25007156,0.0032221393,0.00044779707,0.00016051291,0.000009206637,0.00017223136],"genre_scores_gemma":[0.09129703,0.033994753,0.0046570078,0.8470456,0.021187311,0.0000122142965,0.000111513014,0.00016361212,0.0015309858],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97831064,0.010235735,0.008406787,0.0016945591,0.00031415836,0.0010381171],"domain_scores_gemma":[0.96210504,0.028018504,0.0063572736,0.0015364718,0.0006160475,0.0013666548],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.037969425,0.00080859364,0.005264016,0.0002087201,0.00026620532,0.00008354651,0.0011725486,0.0042304005,0.000024088897],"category_scores_gemma":[0.16830674,0.0006341731,0.0020532496,0.00004492518,0.0014897424,0.000018805964,0.00068041193,0.0045778076,0.00002971488],"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":[0.015153297,0.00018543286,0.074913524,0.000100548976,0.0020759706,0.00338834,0.000038952017,0.0001224584,0.0009817532,0.000024088169,0.8967667,0.0062489286],"study_design_scores_gemma":[0.0033773598,0.008037187,0.081622995,0.0001473415,0.00043694902,0.0008524957,0.000031920266,0.000035350058,0.000008855674,0.0010398153,0.9037516,0.00065815006],"about_ca_topic_score_codex":0.000031752206,"about_ca_topic_score_gemma":0.000023373961,"teacher_disagreement_score":0.6503248,"about_ca_system_score_codex":0.00013927039,"about_ca_system_score_gemma":0.0025123728,"threshold_uncertainty_score":0.99961096},"labels":[],"label_agreement":null},{"id":"W2764211928","doi":"10.1016/j.jclinepi.2017.09.023","title":"Decision-making frameworks and considerations for informing coverage decisions for healthcare interventions: a critical interpretive synthesis","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":52,"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; Queen's University; Impact","funders":"Health Technology Assessment Programme","keywords":"Psychological intervention; Health care; Management science; Medicine; Psychology; Nursing; Political science; Engineering","score_opus":0.7475858978140362,"score_gpt":0.659736352993749,"score_spread":0.08784954482028717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2764211928","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":[0.019835347,0.0023013577,0.78844637,0.18546131,0.002788116,0.0005805014,0.0004621104,0.00000781249,0.00011704775],"genre_scores_gemma":[0.7256936,0.0007238849,0.25404155,0.018613838,0.00078926224,0.000107222135,0.0000010094868,0.00001782125,0.000011816987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9827718,0.0013770803,0.014933633,0.0004351887,0.000062169536,0.00042014106],"domain_scores_gemma":[0.13641852,0.84503126,0.016588675,0.000718234,0.00076272665,0.00048058684],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11315562,0.00017847563,0.0035299987,0.00028795327,0.0008448188,0.00013395114,0.00038985314,0.0007251026,0.00013862655],"category_scores_gemma":[0.96929175,0.00018092112,0.0011685033,0.000028470056,0.0004249764,0.00072858034,0.0001323313,0.0008432036,0.000022995187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044951553,0.00016260051,0.083816335,0.00046749055,0.00029418262,0.0000034312695,0.00045890617,0.00014363012,7.389682e-8,0.85811406,0.027909482,0.02818031],"study_design_scores_gemma":[0.0005758986,0.0006105206,0.051133078,0.004805607,0.00004687678,0.000058475038,0.00034005995,0.0105093345,1.3058155e-7,0.9254801,0.00626268,0.00017719551],"about_ca_topic_score_codex":0.000029902707,"about_ca_topic_score_gemma":0.00012464287,"teacher_disagreement_score":0.85613614,"about_ca_system_score_codex":0.00016674693,"about_ca_system_score_gemma":0.0003338872,"threshold_uncertainty_score":0.9131929},"labels":[],"label_agreement":null},{"id":"W2765551854","doi":"10.1016/j.jclinepi.2017.10.006","title":"Kaplan–Meier survival analysis overestimates cumulative incidence of health-related events in competing risk settings: a meta-analysis","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","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":"Alberta Health Services; Foothills Medical Centre; Alberta Children's Hospital; Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Medicine; Cumulative incidence; Confidence interval; Incidence (geometry); Relative risk; Survival analysis; Internal medicine; Publication bias; MEDLINE; Random effects model; Proportional hazards model; Cohort; Mathematics","score_opus":0.8194549083751729,"score_gpt":0.67834042055074,"score_spread":0.14111448782443292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765551854","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":[0.00043412484,0.89533603,0.10249974,0.00038829632,0.00041239648,0.00044107507,0.0003552412,0.0000101485475,0.00012297966],"genre_scores_gemma":[0.0011682033,0.7636888,0.2348508,0.00009192062,0.000099425386,0.000010482915,0.000024262865,0.000032486256,0.00003363615],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.89236134,0.07699984,0.02850849,0.0007958045,0.0006328351,0.00070170866],"domain_scores_gemma":[0.5849954,0.35249904,0.060655043,0.00093671284,0.000576239,0.00033755007],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.20207687,0.00068699894,0.05275785,0.001272344,0.00013402976,0.0000123961945,0.0013191015,0.0010995858,0.0004898691],"category_scores_gemma":[0.63408476,0.00042383725,0.015491027,0.0014750159,0.000527097,0.000109065375,0.0003330224,0.003622506,0.000008779365],"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":[0.000114600334,0.000600056,0.118895486,0.005370964,0.57261133,0.00006875336,0.00014934313,0.0010391894,5.892717e-9,0.013392235,0.00014162448,0.2876164],"study_design_scores_gemma":[0.0005757484,0.00053449126,0.03296591,0.00314109,0.6752843,0.000030949388,0.000035528516,0.007817498,1.46182355e-8,0.27449152,0.0046329824,0.0004899141],"about_ca_topic_score_codex":0.0006840825,"about_ca_topic_score_gemma":0.00019304341,"teacher_disagreement_score":0.4320079,"about_ca_system_score_codex":0.00011604584,"about_ca_system_score_gemma":0.00072431646,"threshold_uncertainty_score":0.99982136},"labels":[],"label_agreement":null},{"id":"W2765897150","doi":"10.1016/j.jclinepi.2017.10.004","title":"Evidence reversal—when new evidence contradicts current claims: a systematic overview review of definitions and terms","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Terminology; Phenomenon; Systematic review; Grey literature; Meta-analysis; Evidence-based medicine; MEDLINE; Psychology; Medicine; Epistemology; Data science; Computer science; Alternative medicine; Linguistics; Political science; Pathology; Law","score_opus":0.992710229982419,"score_gpt":0.7621177131460084,"score_spread":0.23059251683641058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765897150","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":[0.0000019644544,0.9867254,0.0038390623,0.0039747087,0.0024581219,0.0028008332,0.000033247445,0.000003044831,0.00016362297],"genre_scores_gemma":[0.000007644743,0.99133474,0.0053243223,0.0017420916,0.0009430685,0.00005404446,0.000003831559,0.00003122336,0.00055901],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.406871,0.3672107,0.21531752,0.0026505904,0.0070106015,0.0009396189],"domain_scores_gemma":[0.05254166,0.6438616,0.28885105,0.009188517,0.0040682163,0.0014889799],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.72598016,0.0010976344,0.10946458,0.00072098215,0.00018069509,0.00025215605,0.0077355406,0.0008783948,0.0020690637],"category_scores_gemma":[0.9520133,0.00046155407,0.022509646,0.0007856822,0.00080310385,0.0008389015,0.00061531,0.0025934284,0.0007565405],"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":[0.000006396467,0.000043211738,0.0004339619,0.43865612,0.00087013294,0.000017905948,0.000011526424,1.6961303e-7,3.6573098e-9,0.0018270117,0.1088127,0.44932088],"study_design_scores_gemma":[0.00010625294,0.00019315,0.00016289958,0.52925825,0.010750043,0.00050273095,0.0000045511506,0.000014297783,1.5851581e-9,0.0140623255,0.44475588,0.00018964706],"about_ca_topic_score_codex":0.000013350351,"about_ca_topic_score_gemma":0.000008868066,"teacher_disagreement_score":0.44913122,"about_ca_system_score_codex":0.00009843456,"about_ca_system_score_gemma":0.0029373947,"threshold_uncertainty_score":0.99978364},"labels":[],"label_agreement":null},{"id":"W2766154230","doi":"10.1016/j.jclinepi.2017.10.003","title":"A Bayesian model that jointly considers comparative effectiveness research and patients’ preferences may help inform GRADE recommendations: an application to rheumatoid arthritis treatment recommendations","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","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":"Mount Sinai Hospital; University Health Network; University of Toronto; Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Arthritis Society","keywords":"Medicine; Rheumatoid arthritis; Grading (engineering); Comparative effectiveness research; Harm; Bayesian probability; Adverse effect; Dosing; Population; Intensive care medicine; Physical therapy; Alternative medicine; Psychology; Internal medicine; Computer science; Artificial intelligence; Social psychology","score_opus":0.49584054533980476,"score_gpt":0.5638280450298422,"score_spread":0.06798749969003742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766154230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94618094,0.00096412486,0.013492642,0.037303112,0.00027283136,0.0012668817,0.000056437144,0.000016914724,0.00044610683],"genre_scores_gemma":[0.91768056,0.07066921,0.010921127,0.00039726828,0.000095342904,0.00013352593,0.000065512155,0.000013816288,0.000023646988],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9932804,0.0033853548,0.0021303494,0.0003974635,0.0003361873,0.0004702227],"domain_scores_gemma":[0.98283094,0.013378524,0.0014065052,0.0005599075,0.0009770712,0.00084705924],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013503942,0.00021069427,0.0019432106,0.00032590347,0.00070719415,0.00008843037,0.00028187243,0.00021804,0.000049054997],"category_scores_gemma":[0.015252689,0.00015336087,0.00021873756,0.0000883726,0.00088690495,0.00060763315,0.000113395385,0.000810128,0.000016755936],"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":[0.0016736299,0.0011648425,0.57852095,0.000021520751,0.00030920724,0.000004750655,0.00073589315,0.000059895898,0.000021097654,0.0037687991,0.002737603,0.41098183],"study_design_scores_gemma":[0.012447322,0.019568034,0.8297529,0.0016628236,0.000016678528,0.00016981072,0.0017102951,0.008711447,0.00026568567,0.104383096,0.020995924,0.00031594824],"about_ca_topic_score_codex":0.0003121678,"about_ca_topic_score_gemma":0.0007464424,"teacher_disagreement_score":0.41066587,"about_ca_system_score_codex":0.0001207855,"about_ca_system_score_gemma":0.0004307524,"threshold_uncertainty_score":0.99304223},"labels":[],"label_agreement":null},{"id":"W2766211624","doi":"10.1016/j.jclinepi.2017.10.005","title":"Advances in the GRADE approach to rate the certainty in estimates from a network meta-analysis","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":733,"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; University of Toronto; McMaster University; Impact","funders":"","keywords":"Pairwise comparison; Certainty; Grading (engineering); Quality of evidence; Meta-analysis; Computer science; Econometrics; Management science; Mathematics; Medicine; Artificial intelligence; Economics; Engineering","score_opus":0.9561725517383401,"score_gpt":0.6977475494769513,"score_spread":0.25842500226138887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766211624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2251687,0.056419637,0.37120426,0.32885557,0.0026999654,0.002341064,0.000035258487,0.0000043429263,0.013271204],"genre_scores_gemma":[0.952601,0.00085844175,0.03516518,0.0104982,0.00063267286,0.00003876701,0.000001873177,0.00000680992,0.00019706863],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6576855,0.2762834,0.060735945,0.0014665549,0.0030306438,0.0007979233],"domain_scores_gemma":[0.37615392,0.5636846,0.05174101,0.007313307,0.0007749785,0.00033221242],"candidate_categories":["metaresearch","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.75476635,0.0003154299,0.02212654,0.00030763168,0.00024887902,0.00038892456,0.0078015416,0.00021681024,0.0008634268],"category_scores_gemma":[0.7331273,0.00008713619,0.013842267,0.0012736247,0.0003592452,0.00033172296,0.00026683533,0.0011894315,0.00015037041],"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":[0.00007745654,0.00017567202,0.80381554,0.000004934005,0.016176831,0.000019085861,0.0002849289,0.1452618,1.609169e-7,0.006166206,0.020131482,0.00788589],"study_design_scores_gemma":[0.00022296388,0.00007084177,0.647064,0.0000072848106,0.022983447,0.000008168204,0.00030908082,0.04270917,5.7573256e-8,0.25140157,0.03512523,0.00009818023],"about_ca_topic_score_codex":0.00018728092,"about_ca_topic_score_gemma":0.0011353737,"teacher_disagreement_score":0.72743225,"about_ca_system_score_codex":0.000014601636,"about_ca_system_score_gemma":0.00007553743,"threshold_uncertainty_score":0.9975667},"labels":[],"label_agreement":null},{"id":"W2766233621","doi":"10.1016/j.jclinepi.2017.08.001","title":"GRADE equity guidelines 4: considering health equity in GRADE guideline development: evidence to decision process","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Health Sciences Centre; McMaster University; Ottawa Hospital; McMaster University Medical Centre; St. Joseph’s Healthcare Hamilton; Impact; University of Calgary; Bruyère; University of Ottawa","funders":"Medical Research Council; World Health Organization","keywords":"Guideline; Equity (law); Disadvantaged; Grading (engineering); Psychological intervention; Evidence-based medicine; Health equity; Actuarial science; Medicine; MEDLINE; Business; Political science; Economics; Public health; Economic growth; Nursing; Engineering","score_opus":0.9766606636402441,"score_gpt":0.8567094246782578,"score_spread":0.11995123896198623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766233621","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":[0.4193253,0.00033850732,0.059298906,0.5159742,0.0038404148,0.0009590947,0.000009939183,0.000026381253,0.00022726122],"genre_scores_gemma":[0.4932382,0.0011924184,0.2515956,0.2519992,0.0018348396,0.000044369852,0.0000013010151,0.000025266381,0.00006882629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95016176,0.013505445,0.031892486,0.000873166,0.0012434912,0.0023236254],"domain_scores_gemma":[0.84386486,0.12780297,0.021633746,0.0013039646,0.0027876326,0.0026068222],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28155458,0.00030678188,0.0034549972,0.00043452234,0.0015415908,0.000028751343,0.0022715733,0.0004636179,0.00021657137],"category_scores_gemma":[0.77510315,0.00023416601,0.00027005989,0.00032477052,0.00037812974,0.0007885956,0.0017773117,0.0024331168,0.00016574204],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033435042,0.000102922,0.7057824,0.00033001634,0.00002125494,0.000028974902,0.0019895493,0.00041435557,0.0000157677,0.0009815729,0.1136411,0.1763577],"study_design_scores_gemma":[0.0025866902,0.0006152419,0.78948444,0.004101072,0.000010813083,0.00004146524,0.0006316277,0.00077680754,0.0000125061615,0.043464754,0.157999,0.0002755556],"about_ca_topic_score_codex":0.00086557836,"about_ca_topic_score_gemma":0.0042735534,"teacher_disagreement_score":0.4935486,"about_ca_system_score_codex":0.00072834536,"about_ca_system_score_gemma":0.0128476815,"threshold_uncertainty_score":0.99986833},"labels":[],"label_agreement":null},{"id":"W2766439930","doi":"10.1016/j.jclinepi.2017.10.017","title":"Reproducible research practices are underused in systematic reviews of biomedical interventions","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":117,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; St. Michael's Hospital; Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Generalitat Valenciana; University of Bristol; National Institute for Health and Care Research; Cancer Research UK; Medical Research Council; University of Ottawa","keywords":"Systematic review; Psychological intervention; Medicine; MEDLINE; Data science; Management science; Computer science; Engineering; Nursing; Political science","score_opus":0.9980100150901896,"score_gpt":0.8607453153991359,"score_spread":0.1372646996910537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766439930","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001803792,0.98914874,0.0017741176,0.0027296785,0.0024157339,0.0030910755,0.000013475073,0.0000012929331,0.0008078396],"genre_scores_gemma":[0.000055370718,0.9908073,0.0048539615,0.000098891614,0.0010128635,0.000104809566,0.0000047234935,0.000025856156,0.0030362497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.046616938,0.7044956,0.2398105,0.0022181373,0.006146574,0.0007122673],"domain_scores_gemma":[0.009397817,0.55107135,0.4242682,0.010524654,0.004193222,0.0005447786],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9690113,0.0006559545,0.12627746,0.003295662,0.00014985832,0.00024362981,0.0104745515,0.0014567184,0.0026606617],"category_scores_gemma":[0.9951845,0.00025412784,0.040104948,0.0023640909,0.0011121033,0.00040540317,0.0007870395,0.005074459,0.0019468613],"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":[0.000022367707,0.0008326807,0.0042780554,0.42579618,0.0018475356,0.000102717444,0.000041284824,0.0000013977354,1.8222641e-8,0.0015480962,0.13265951,0.43287015],"study_design_scores_gemma":[0.00017981477,0.0003083769,0.00044056826,0.22625741,0.0021967716,0.00019436778,0.00010205127,0.000039989238,3.3290373e-9,0.007610306,0.7625381,0.000132253],"about_ca_topic_score_codex":0.000025212921,"about_ca_topic_score_gemma":0.00008299774,"teacher_disagreement_score":0.6298786,"about_ca_system_score_codex":0.00012358229,"about_ca_system_score_gemma":0.001523596,"threshold_uncertainty_score":0.9999911},"labels":[],"label_agreement":null},{"id":"W2766875239","doi":"10.1016/j.jclinepi.2017.10.009","title":"Explaining odds ratios as conditional risk ratios","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"University of Toronto; McMaster University","funders":"","keywords":"Odds ratio; Odds; Interpretation (philosophy); Conditional independence; Recall; Independence (probability theory); Statistics; Medicine; Mathematics; Psychology; Philosophy; Logistic regression; Cognitive psychology; Linguistics","score_opus":0.7778813850800665,"score_gpt":0.6090544562743831,"score_spread":0.1688269288056834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766875239","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":[0.0042744665,0.002626759,0.023470782,0.95366365,0.009465344,0.00048847473,0.0007364111,0.000023992963,0.0052501024],"genre_scores_gemma":[0.007859787,0.0022199566,0.007926269,0.9312781,0.047215138,0.000044207824,0.00032319158,0.00008843661,0.0030448937],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94183266,0.015207069,0.040768173,0.0010287582,0.00025685597,0.0009064574],"domain_scores_gemma":[0.7737825,0.13043869,0.09351426,0.0012724511,0.00048603656,0.0005060965],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.2493064,0.0005383692,0.0106323,0.0006253094,0.00051050406,0.0000984091,0.0014559688,0.003129374,0.0026562416],"category_scores_gemma":[0.5668716,0.0005677759,0.0021289145,0.00006927328,0.0006604663,0.0007687814,0.00013394872,0.0073288055,0.004969794],"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":[0.00005104505,0.000054530323,0.07304237,0.00014922975,0.00057408476,0.00008988509,0.00009967709,0.0001873049,2.6782157e-8,0.022901764,0.9026351,0.0002150053],"study_design_scores_gemma":[0.001408471,0.0005187972,0.024828324,0.00021416089,0.00006663481,0.00021706604,0.00005343119,0.0009773092,1.01318804e-7,0.19375135,0.77755797,0.00040637198],"about_ca_topic_score_codex":0.00027886903,"about_ca_topic_score_gemma":0.000025080217,"teacher_disagreement_score":0.31756517,"about_ca_system_score_codex":0.0004061829,"about_ca_system_score_gemma":0.0015233227,"threshold_uncertainty_score":0.99967736},"labels":[],"label_agreement":null},{"id":"W2767713238","doi":"10.1016/s0895-4356(00)00208-0","title":"Measuring quality of sedation in adult mechanically ventilated critically ill patients","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","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":"Vancouver General Hospital; University of British Columbia","funders":"Ministerul Cercetării, Inovării şi Digitalizării","keywords":"Calmness; Sedation; Minimal clinically important difference; Medicine; Inter-rater reliability; Construct validity; Intensive care unit; Physical therapy; Rating scale; Psychometrics; Randomized controlled trial; Intensive care medicine; Anesthesia; Statistics; Surgery; Clinical psychology; Psychiatry; Mathematics","score_opus":0.2295255178568416,"score_gpt":0.4824167709495176,"score_spread":0.252891253092676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767713238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98559797,0.000049103808,0.0010630642,0.011064835,0.00042399546,0.00018994183,0.0000070322117,0.0000068625927,0.0015972144],"genre_scores_gemma":[0.93205196,0.00028751997,0.002620057,0.064837955,0.00013618122,0.0000014655802,0.000014331253,0.000014295484,0.00003622127],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98885524,0.0038903293,0.006372851,0.00023723005,0.0003343225,0.0003100166],"domain_scores_gemma":[0.8533459,0.037136003,0.004867733,0.0005826069,0.103337824,0.00072997325],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013201421,0.00014672548,0.0023557274,0.00017716961,0.000016754386,0.0000016015484,0.00014918577,0.00039434602,0.00046209164],"category_scores_gemma":[0.70549446,0.00011784683,0.00071671687,0.00018211009,0.00025389247,0.00009025143,0.000024441353,0.0010767974,0.00002539886],"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":[0.008399444,0.0016391999,0.91945624,0.00014090737,0.0002770235,0.00005717469,0.00007728645,0.000040178882,0.0006082951,0.0017707039,0.0014338236,0.06609973],"study_design_scores_gemma":[0.005049886,0.00213769,0.98642784,0.0005928661,0.0001127035,0.0000231501,0.00020741129,0.00026801982,0.00019379712,0.004602587,0.0002748318,0.00010920811],"about_ca_topic_score_codex":0.00004333662,"about_ca_topic_score_gemma":0.00002622316,"teacher_disagreement_score":0.69229305,"about_ca_system_score_codex":0.000056952646,"about_ca_system_score_gemma":0.00020492385,"threshold_uncertainty_score":0.50595796},"labels":[],"label_agreement":null},{"id":"W2768527379","doi":"10.1016/j.jclinepi.2017.01.015","title":"GRADE equity guidelines 3: considering health equity in GRADE guideline development: rating the certainty of synthesized evidence","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":89,"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; McMaster University; Health Sciences Centre; University of Calgary; Impact; Bruyère; University of Ottawa","funders":"National Health and Medical Research Council; U.S. Department of Veterans Affairs; Regeneron Pharmaceuticals; Allergan; Parker Institute for Cancer Immunotherapy; World Health Organization; Medical Research Council; University of Ottawa","keywords":"Guideline; Equity (law); Grading (engineering); Health equity; Actuarial science; Disadvantaged; Evidence-based medicine; Medicine; Psychology; MEDLINE; Public health; Business; Political science; Nursing; Economics; Economic growth","score_opus":0.9503496834351777,"score_gpt":0.7147137828651461,"score_spread":0.2356359005700316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768527379","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":[0.22908361,0.010076885,0.024950849,0.73243403,0.0023644199,0.0005921726,0.000022740438,0.000013380142,0.000461889],"genre_scores_gemma":[0.8280665,0.003217899,0.107078865,0.060309406,0.0012437241,0.000015086419,0.0000023740338,0.000025212947,0.000040896673],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9246636,0.009758681,0.06347736,0.00076193194,0.00029498915,0.0010434453],"domain_scores_gemma":[0.79122186,0.1268683,0.07900248,0.0016013883,0.0007062573,0.0005997084],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5041509,0.00026264662,0.005926284,0.0002465366,0.00046014364,0.000047431968,0.0016126801,0.00043589598,0.00009160902],"category_scores_gemma":[0.7470472,0.00021710759,0.0006126759,0.00009833254,0.0005796601,0.000482397,0.0006467287,0.0013276358,0.00004471146],"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":[0.00021405431,0.0002822086,0.82498217,0.00073069124,0.0002848008,0.000010118205,0.00095326296,0.0029023145,0.000008916023,0.07946045,0.054104503,0.03606651],"study_design_scores_gemma":[0.00310384,0.0004596725,0.6683611,0.0031226159,0.000025369516,0.00008250494,0.0007086226,0.018238375,0.00002422161,0.26329133,0.042094465,0.00048783387],"about_ca_topic_score_codex":0.0017438096,"about_ca_topic_score_gemma":0.0011401782,"teacher_disagreement_score":0.6721246,"about_ca_system_score_codex":0.000483765,"about_ca_system_score_gemma":0.0018434358,"threshold_uncertainty_score":0.885339},"labels":[],"label_agreement":null},{"id":"W2769346107","doi":"10.1016/j.jclinepi.2017.08.019","title":"Controversy and debate on clinical genomics sequencing—paper 3: response to “clinical genome-wide sequencing: do not throw out the baby with the bathwater”","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","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; University of Toronto; Université Laval; University of Ottawa","funders":"","keywords":"Genomics; Health care; DNA sequencing; Genomic sequencing; Medicine; Genome; Data science; Family medicine; Computer science; Biology; Genetics; Political science; Law","score_opus":0.16413281796727824,"score_gpt":0.423300961165183,"score_spread":0.25916814319790477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769346107","genre_codex":"empirical","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":[0.5027274,0.0009652333,0.00041449995,0.49273425,0.0023600415,0.00050177873,0.00013211441,0.0000062894314,0.00015840924],"genre_scores_gemma":[0.20945962,0.004552621,0.0011388516,0.7645441,0.018669652,0.00001866766,0.000050774655,0.00012129477,0.0014443721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.976675,0.014442435,0.00607235,0.0013758038,0.0004199795,0.0010144463],"domain_scores_gemma":[0.94824654,0.042031433,0.0061391275,0.0022521643,0.00063675555,0.00069395895],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04905082,0.00078164693,0.0038312552,0.0000983069,0.0004624231,0.0001361797,0.002272478,0.0026816851,0.00003279611],"category_scores_gemma":[0.08934656,0.00038120965,0.002117371,0.00004296322,0.002373181,0.000015781914,0.00066289474,0.005542984,0.000050604493],"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":[0.022849984,0.00014790584,0.026742782,0.000047384732,0.0029281816,0.0024499327,0.0001405555,0.0004864789,0.00095135125,0.000037330818,0.94079506,0.0024230678],"study_design_scores_gemma":[0.0025028184,0.0074929376,0.038171567,0.00011030483,0.0005755062,0.00072764157,0.00008974594,0.000020450834,0.000026569538,0.0005852372,0.9491596,0.00053759885],"about_ca_topic_score_codex":0.000023848459,"about_ca_topic_score_gemma":0.000058722435,"teacher_disagreement_score":0.29326776,"about_ca_system_score_codex":0.00012081183,"about_ca_system_score_gemma":0.0025785805,"threshold_uncertainty_score":0.999864},"labels":[],"label_agreement":null},{"id":"W2769378808","doi":"10.1016/j.jclinepi.2017.10.014","title":"Same family, different species: methodological conduct and quality varies according to purpose for five types of knowledge synthesis","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Ottawa Hospital; University of Toronto; University of Alberta; St. Michael's Hospital","funders":"National Health and Medical Research Council; Medical Research Council; Canadian Institutes of Health Research; University of Ottawa","keywords":"Systematic review; Medicine; Protocol (science); Citation; Missing data; MEDLINE; Medical physics; Statistics; Alternative medicine; Computer science; Mathematics; Pathology; Library science","score_opus":0.9944644201276043,"score_gpt":0.7932841591772162,"score_spread":0.2011802609503881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769378808","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":[0.00088795717,0.9360163,0.057754178,0.0011107625,0.002202947,0.0012349755,0.00013523473,0.0000019947977,0.00065565086],"genre_scores_gemma":[0.00026932042,0.936711,0.058992453,0.00032511505,0.0011394008,0.00005603066,0.0000029122766,0.00002095898,0.00248282],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.56424093,0.34397092,0.087403744,0.0018896664,0.0018384213,0.0006563144],"domain_scores_gemma":[0.045667466,0.85280406,0.094747335,0.0033223336,0.0027621263,0.0006966966],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7123786,0.00073568313,0.09167862,0.0006064063,0.00017959325,0.00017626332,0.0040843864,0.001111367,0.0006405377],"category_scores_gemma":[0.9657862,0.00027633336,0.01804075,0.00032155644,0.0007635977,0.00014246618,0.00071250764,0.0011440748,0.00011316413],"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":[0.00010262367,0.00011589016,0.0028787702,0.004096586,0.0018590945,0.000003180125,0.0000473515,0.000002119314,5.162671e-7,0.0073761814,0.014894789,0.9686229],"study_design_scores_gemma":[0.00017847466,0.0005622373,0.0069206995,0.0033762795,0.0038342401,0.000036838777,0.00021662316,0.000040805,2.6253596e-7,0.022077227,0.96249723,0.00025908064],"about_ca_topic_score_codex":0.000008558354,"about_ca_topic_score_gemma":0.000017856923,"teacher_disagreement_score":0.9683638,"about_ca_system_score_codex":0.000048381757,"about_ca_system_score_gemma":0.0004640268,"threshold_uncertainty_score":0.9999689},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2769927907","doi":"10.1016/j.jclinepi.2017.11.017","title":"The efficiency of database searches for creating systematic reviews was improved by search filters","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Impact; McMaster University","funders":"","keywords":"Medicine; MEDLINE; Meta-analysis; Systematic review; Randomized controlled trial; Cochrane Library; Internal medicine; Chemistry","score_opus":0.9517427660572876,"score_gpt":0.712245632400876,"score_spread":0.23949713365641156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769927907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23721598,0.051841877,0.65782076,0.036625884,0.0046894643,0.009034674,0.00015135371,0.0000047761278,0.0026152069],"genre_scores_gemma":[0.8493359,0.014854309,0.11607631,0.0027121052,0.0020326779,0.00020949403,0.00001088503,0.000057602694,0.014710688],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.65361965,0.22535743,0.11482153,0.0012754134,0.0039503383,0.00097562745],"domain_scores_gemma":[0.1338851,0.7420811,0.11223577,0.0074901152,0.0037517645,0.0005561403],"candidate_categories":["metaresearch","metaepi_broad","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8641153,0.00027139403,0.01740815,0.00014298769,0.00066191086,0.00030191318,0.0062217726,0.00019538171,0.00024190363],"category_scores_gemma":[0.96710426,0.0000900132,0.0070641963,0.00020671837,0.00075994246,0.0002762968,0.00035968714,0.0007202768,0.000113629096],"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":[0.0006531887,0.00071770273,0.18935823,0.022134332,0.0029736208,0.000012447037,0.00064714276,0.00012882038,0.0013192528,0.011009757,0.6477146,0.123330906],"study_design_scores_gemma":[0.0070908074,0.007175922,0.04119161,0.023004254,0.0055922903,0.00033374195,0.0050857826,0.4606284,0.00041823584,0.05503415,0.3930454,0.001399405],"about_ca_topic_score_codex":0.00002125654,"about_ca_topic_score_gemma":0.000012524918,"teacher_disagreement_score":0.61212,"about_ca_system_score_codex":0.000021864646,"about_ca_system_score_gemma":0.00023530454,"threshold_uncertainty_score":0.99915504},"labels":[],"label_agreement":null},{"id":"W2770433878","doi":"10.1016/j.jclinepi.2017.11.012","title":"Multiple overlapping systematic reviews facilitate the origin of disputes: the case of thrombolytic therapy for pulmonary embolism","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":39,"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":"Ministero della Salute; World Health Organization","keywords":"Medicine; Interquartile range; Pulmonary embolism; Thrombolysis; Number needed to harm; Relative risk; Systematic review; MEDLINE; Cochrane Library; Hazard ratio; Internal medicine; Absolute risk reduction; Meta-analysis; Confidence interval; Intensive care medicine; Emergency medicine; Number needed to treat; Myocardial infarction","score_opus":0.43601794102028546,"score_gpt":0.5114631968586596,"score_spread":0.07544525583837414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770433878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93343663,0.02342817,0.00611109,0.028883833,0.0024290755,0.0052023847,0.000026945341,0.000008214474,0.00047367433],"genre_scores_gemma":[0.9643657,0.031017762,0.0013149524,0.0024654858,0.00063125236,0.00007961615,0.0000014105431,0.000017227136,0.00010658085],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98994404,0.0031602879,0.0061761444,0.0002286229,0.00017418423,0.0003167054],"domain_scores_gemma":[0.93938506,0.049338765,0.009480727,0.0012601317,0.00038480453,0.00015052845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042676352,0.00021600956,0.0057686106,0.000061899635,0.00023919332,0.000010065361,0.00070103095,0.00017717274,0.000023597624],"category_scores_gemma":[0.11344045,0.00008820636,0.0017467454,0.000055938002,0.0007482076,0.00010211138,0.00011750426,0.0005138216,0.0000046276514],"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":[0.005936545,0.011966305,0.3333775,0.12823784,0.017424738,0.0017559498,0.007116482,0.0009264124,0.0015903094,0.09430766,0.09131612,0.30604413],"study_design_scores_gemma":[0.011393403,0.0077981628,0.81837004,0.026721422,0.004979748,0.0033592172,0.0029571585,0.015498375,0.00006896078,0.028797505,0.07953602,0.00051998365],"about_ca_topic_score_codex":0.00022157378,"about_ca_topic_score_gemma":0.000032999153,"teacher_disagreement_score":0.48499253,"about_ca_system_score_codex":0.000023252387,"about_ca_system_score_gemma":0.00012936894,"threshold_uncertainty_score":0.9857662},"labels":[],"label_agreement":null},{"id":"W2770925026","doi":"10.1016/j.jclinepi.2017.11.016","title":"Comparative evidence on harms in pediatric randomized clinical trials from less developed versus more developed countries is limited","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Hospital for Sick Children; Institute for Clinical Evaluative Sciences; SickKids Foundation; University of Toronto","funders":"U.S. Food and Drug Administration","keywords":"Medicine; Meta-analysis; Randomized controlled trial; Odds ratio; Number needed to harm; Systematic review; Confidence interval; Harm; Adverse effect; Publication bias; Relative risk; MEDLINE; Internal medicine; Pediatrics; Number needed to treat","score_opus":0.9805427155996695,"score_gpt":0.8014832159182368,"score_spread":0.17905949968143275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770925026","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":[0.0020218145,0.9607783,0.0005574269,0.02214868,0.010347571,0.0035533544,0.000108446744,0.000028129707,0.00045630996],"genre_scores_gemma":[0.0003602011,0.9743481,0.008642118,0.0058567827,0.009863675,0.00011816949,0.00006892543,0.000106779524,0.0006352176],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.66288656,0.24001749,0.08869456,0.003009501,0.003478458,0.0019134141],"domain_scores_gemma":[0.0092602745,0.9344792,0.048102785,0.0023131177,0.0040498013,0.0017948415],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.6585132,0.0013403392,0.08262437,0.001130794,0.00021269696,0.00009059224,0.0033823624,0.009108697,0.00041461934],"category_scores_gemma":[0.98271215,0.00078701065,0.0124441255,0.0006603244,0.0047263578,0.00028404008,0.0008472317,0.032119535,0.00053262315],"study_design_candidate":"randomized_trial","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":[0.44695538,0.0013553031,0.02276754,0.007487675,0.0076449215,0.0012542605,0.00020728081,0.0000035004566,1.1763405e-8,0.001112931,0.019002702,0.49220848],"study_design_scores_gemma":[0.23799153,0.0043116705,0.0151646165,0.09117506,0.014353079,0.00008349159,0.000078076475,0.000118935866,3.3534656e-7,0.0092023155,0.62641054,0.0011103428],"about_ca_topic_score_codex":0.00012028821,"about_ca_topic_score_gemma":0.00018158661,"teacher_disagreement_score":0.6944617,"about_ca_system_score_codex":0.0004936396,"about_ca_system_score_gemma":0.02688985,"threshold_uncertainty_score":0.9999348},"labels":[],"label_agreement":null},{"id":"W2771053950","doi":"10.1016/j.jclinepi.2017.11.019","title":"Controversy and debate on dengue vaccine series—paper 1: review of a licensed dengue vaccine: inappropriate subgroup analyses and selective reporting may cause harm in mass vaccination programs","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mosquito-borne diseases and control","field":"Medicine","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","funders":"","keywords":"Dengue fever; Dengue vaccine; Medicine; Vaccination; Dengue virus; Subgroup analysis; Meta-analysis; Relative risk; Confidence interval; Harm; Environmental health; Pediatrics; Immunology; Internal medicine","score_opus":0.3924179613507765,"score_gpt":0.5741992053214702,"score_spread":0.18178124397069367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771053950","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":[0.003720279,0.9904889,0.00008147706,0.0031683426,0.00038981126,0.002043078,0.000014959845,0.000013123049,0.00008004678],"genre_scores_gemma":[0.006996749,0.98931134,0.0007587887,0.0017537816,0.0009035894,0.000075808275,0.000051781302,0.00006166537,0.00008647071],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9783648,0.0052961675,0.014554772,0.0008528687,0.0003466028,0.00058478734],"domain_scores_gemma":[0.95339656,0.010894423,0.03317557,0.0007969247,0.0011188847,0.0006176188],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0272764,0.00068765576,0.016078014,0.000400969,0.00008508678,0.000024390916,0.00031382206,0.0009227185,0.000055298107],"category_scores_gemma":[0.18701121,0.0004398671,0.0019239965,0.00030342423,0.00008577832,0.00024093073,0.000115455725,0.002305479,0.0000019757404],"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":[0.001961888,0.00048022173,0.056709655,0.050660327,0.002776895,0.0010079788,0.000020288731,0.0000015051087,0.000003987118,0.0001707219,0.00086419645,0.88534236],"study_design_scores_gemma":[0.018514648,0.00805559,0.3150289,0.26125515,0.030556332,0.0049649063,0.000079448175,0.0002545972,0.0000025405081,0.0009616198,0.35922995,0.0010963164],"about_ca_topic_score_codex":0.00010552718,"about_ca_topic_score_gemma":0.00008576967,"teacher_disagreement_score":0.884246,"about_ca_system_score_codex":0.00014043802,"about_ca_system_score_gemma":0.00084630493,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W2771830828","doi":"10.1016/j.jclinepi.2017.11.026","title":"Some Cochrane risk-of-bias items are not important in osteoarthritis trials: a meta-epidemiological study based on Cochrane reviews","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Communications Research Centre Canada; Bruyère; University of Ottawa; Cochrane; Ottawa Hospital","funders":"Parker Institute for Cancer Immunotherapy; Ottawa Hospital Research Institute; Oak Foundation","keywords":"Epidemiology; Medicine; Meta-analysis; Osteoarthritis; Systematic review; Cochrane collaboration; Physical therapy; MEDLINE; Alternative medicine; Internal medicine; Cochrane Library; Pathology; Biology","score_opus":0.9793018242398892,"score_gpt":0.7401075223698631,"score_spread":0.2391943018700261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771830828","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025181472,0.9867452,0.00084770063,0.0018857517,0.0039708363,0.0058537708,0.00030011174,0.0000049451605,0.0001398991],"genre_scores_gemma":[0.00037873583,0.9902535,0.004007472,0.0017827479,0.0027278687,0.00030191592,0.000020439384,0.0000614791,0.00046581923],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.064912505,0.66094106,0.26460856,0.0029237121,0.0056212093,0.0009929726],"domain_scores_gemma":[0.02918458,0.58979386,0.36961097,0.00852107,0.0019981842,0.00089130044],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.969958,0.002407187,0.33484215,0.0022186488,0.00022699419,0.0002289399,0.009609321,0.0026988573,0.0044428036],"category_scores_gemma":[0.99269754,0.000852115,0.11489294,0.0013538443,0.00091745466,0.0003257485,0.0004692422,0.007066532,0.0008954429],"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":[0.00050499546,0.0021076282,0.055058055,0.0053009368,0.009376582,0.00064078445,0.00002406109,0.00014621798,2.4393078e-8,0.00034521005,0.032908846,0.89358664],"study_design_scores_gemma":[0.002543923,0.0044283383,0.008812919,0.021338988,0.040555563,0.00016052474,0.00004736568,0.00047260878,1.9140275e-8,0.005693354,0.9152827,0.00066367],"about_ca_topic_score_codex":0.000051615043,"about_ca_topic_score_gemma":0.00015585823,"teacher_disagreement_score":0.892923,"about_ca_system_score_codex":0.00011665832,"about_ca_system_score_gemma":0.0011993203,"threshold_uncertainty_score":0.99988246},"labels":[],"label_agreement":null},{"id":"W2772564313","doi":"10.1016/j.jclinepi.2017.11.022","title":"Flaws in the application and interpretation of statistical analyses in systematic reviews of therapeutic interventions were common: a cross-sectional analysis","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; St. Michael's Hospital; Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Generalitat Valenciana; University of Bristol; National Institute for Health and Care Research; Canada Research Chairs; Cancer Research UK; Medical Research Council; University of Ottawa","keywords":"Meta-analysis; Funnel plot; Interquartile range; Medicine; Random effects model; Sample size determination; Statistics; Publication bias; Subgroup analysis; Confounding; Psychological intervention; Study heterogeneity; MEDLINE; Mathematics; Internal medicine","score_opus":0.9443845471738417,"score_gpt":0.7567789989945132,"score_spread":0.1876055481793285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772564313","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":[0.46753833,0.0059765466,0.52414846,0.0010084221,0.0002050745,0.0008474623,0.000013586773,4.60939e-7,0.0002616517],"genre_scores_gemma":[0.99539346,0.00070937333,0.0036073832,0.00018276925,0.000045375124,0.000026696916,0.0000030760193,0.0000029051816,0.000028995439],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7754369,0.1462049,0.07578049,0.0006241291,0.001734559,0.0002190429],"domain_scores_gemma":[0.6667369,0.24091008,0.08787781,0.0030514281,0.0012952295,0.00012854293],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5300859,0.00016638404,0.014145268,0.0006695689,0.00006750179,0.000111574176,0.0018131323,0.00017365236,0.0003442761],"category_scores_gemma":[0.5043805,0.00006769574,0.005122395,0.00064872904,0.000498697,0.00021413177,0.00009111772,0.00048749044,0.000016011958],"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":[0.0000527737,0.00015612961,0.9849139,0.0010458664,0.0006627754,0.0000015247126,0.00011926774,0.00086209545,0.000004365626,0.0059081167,0.00009256916,0.006180624],"study_design_scores_gemma":[0.0002425098,0.00014338148,0.8928452,0.0005356895,0.0009087538,0.000014771749,0.00015205894,0.07045032,2.5218563e-7,0.03457281,0.00009083082,0.000043415235],"about_ca_topic_score_codex":0.00006916752,"about_ca_topic_score_gemma":0.00065481605,"teacher_disagreement_score":0.5278551,"about_ca_system_score_codex":0.00001861304,"about_ca_system_score_gemma":0.000051990934,"threshold_uncertainty_score":0.96694225},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"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":"W2772705208","doi":"10.1016/j.jclinepi.2017.12.001","title":"A retrospective comparison of systematic reviews with same-topic rapid reviews","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":52,"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; Canada Research Chairs; Queen's University","funders":"","keywords":"Systematic review; Medicine; Retrospective cohort study; Grey literature; MEDLINE; Population; Family medicine; Surgery; Environmental health","score_opus":0.9798943669780353,"score_gpt":0.7536716625399138,"score_spread":0.22622270443812154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772705208","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005525504,0.98293406,0.006865527,0.00039336947,0.0022780916,0.005599429,0.000016904949,0.0000023201014,0.0019047916],"genre_scores_gemma":[0.000023807668,0.9799715,0.014766323,0.0003707808,0.0012934766,0.00013340094,0.0000055811106,0.000042322503,0.0033927523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.22131877,0.49160683,0.27917546,0.002167358,0.004960366,0.00077120477],"domain_scores_gemma":[0.08562593,0.29728907,0.5970624,0.014290489,0.0048107966,0.0009213078],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.841518,0.0014003502,0.25912696,0.0010046265,0.000175953,0.0002195428,0.009742876,0.0013733559,0.0026681442],"category_scores_gemma":[0.9375941,0.00046497592,0.048535936,0.0011574749,0.00080406835,0.00030581097,0.00037545018,0.0035207039,0.0023629826],"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":[0.00002035624,0.00018997393,0.007871321,0.17945752,0.0021365094,0.000017045795,0.000057406804,0.0000013766947,6.1543886e-9,0.0008508413,0.093623064,0.7157746],"study_design_scores_gemma":[0.00024329073,0.00085261866,0.0004939982,0.17898512,0.009766237,0.0002607373,0.000027664728,0.00004530355,5.037407e-9,0.0018651112,0.8071619,0.00029798874],"about_ca_topic_score_codex":0.0000057496186,"about_ca_topic_score_gemma":0.000021255573,"teacher_disagreement_score":0.71547663,"about_ca_system_score_codex":0.00014042947,"about_ca_system_score_gemma":0.00087735115,"threshold_uncertainty_score":0.99992305},"labels":[],"label_agreement":null},{"id":"W2773013777","doi":"10.1016/j.jclinepi.2017.12.004","title":"Recommendations for assessing the risk of bias in systematic reviews of health-care interventions","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":218,"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":"Transparency (behavior); Workgroup; Psychological intervention; Systematic review; Risk assessment; Health care; Risk analysis (engineering); Context (archaeology); Actuarial science; Information bias; Reporting bias; Medicine; Applied psychology; Selection bias; Psychology; MEDLINE; Computer science; Business; Nursing; Political science","score_opus":0.983329733355029,"score_gpt":0.7788333389815846,"score_spread":0.20449639437344447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773013777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10003333,0.0670583,0.70560503,0.11540512,0.005257852,0.0054796776,0.00007430909,0.0000016484086,0.0010847505],"genre_scores_gemma":[0.906226,0.0070532723,0.085135676,0.0009756965,0.00024850504,0.00005553977,0.0000026515836,0.000009508797,0.00029318704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.35315892,0.46468458,0.1795929,0.0006397571,0.001547931,0.0003758975],"domain_scores_gemma":[0.20047112,0.49205333,0.30039373,0.0040861787,0.0028408617,0.00015477577],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8481968,0.00015834703,0.019593831,0.00028522804,0.00023056209,0.000089480316,0.0026430348,0.00014116566,0.00040590367],"category_scores_gemma":[0.95512253,0.00005631268,0.011417181,0.0002459007,0.00024873987,0.00024375573,0.00013304294,0.0005186342,0.00002708797],"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":[0.00001653995,0.00020968253,0.8125257,0.010756029,0.00061199645,4.633937e-7,0.00047254507,0.00012730587,4.89692e-7,0.0043150247,0.057347015,0.11361721],"study_design_scores_gemma":[0.0012430403,0.00081068854,0.8003206,0.028130347,0.0017802261,0.00002856181,0.004650198,0.0052156234,8.6704813e-7,0.08348646,0.07416812,0.00016524228],"about_ca_topic_score_codex":0.000033940723,"about_ca_topic_score_gemma":0.00012870367,"teacher_disagreement_score":0.80619264,"about_ca_system_score_codex":0.00002552349,"about_ca_system_score_gemma":0.00020210141,"threshold_uncertainty_score":0.99848324},"labels":[],"label_agreement":null},{"id":"W2776980134","doi":"10.1016/j.jclinepi.2017.12.018","title":"Systematic review on costs and resource use of randomized clinical trials shows a lack of transparent and comprehensive data","year":2017,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":143,"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":"Randomized controlled trial; Medicine; Resource use; MEDLINE; Cost database; Systematic review; Resource (disambiguation); Clinical trial; Environmental resource management; Surgery; Computer science; Economics","score_opus":0.9833570133991045,"score_gpt":0.7977718868549234,"score_spread":0.18558512654418113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776980134","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":[0.00003573462,0.98701817,0.0002755089,0.0053589507,0.0006710189,0.0062731197,0.0002817724,0.0000053144695,0.00008041534],"genre_scores_gemma":[0.000022947681,0.9921632,0.0027884622,0.0038410437,0.00083176524,0.000034377663,0.00006475507,0.000058514473,0.00019495956],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.4518189,0.41366616,0.12874468,0.002223024,0.0026087933,0.00093841774],"domain_scores_gemma":[0.018601388,0.91127706,0.063064985,0.0038451997,0.00204522,0.0011661442],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.67595565,0.0006898788,0.112679005,0.0003366431,0.0000593735,0.000018917783,0.0018214537,0.0033344878,0.00004449249],"category_scores_gemma":[0.9830165,0.00035509455,0.008271978,0.00013456107,0.0056051975,0.00010998738,0.0008072721,0.010991868,0.0000062151566],"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":[0.02361393,0.00053658127,0.00023674064,0.8055622,0.0072881076,0.00010572669,0.0000063901566,2.4337606e-7,2.8463521e-8,0.0010463208,0.0038421068,0.15776162],"study_design_scores_gemma":[0.035758827,0.002521193,0.00008875388,0.80390173,0.033406768,0.00036659866,0.000006783614,0.000070091075,2.267412e-8,0.0011598609,0.12252405,0.00019534075],"about_ca_topic_score_codex":0.000020580746,"about_ca_topic_score_gemma":0.000012610649,"teacher_disagreement_score":0.4976109,"about_ca_system_score_codex":0.000049220023,"about_ca_system_score_gemma":0.0021578835,"threshold_uncertainty_score":0.9998901},"labels":[],"label_agreement":null},{"id":"W2777471495","doi":"10.1016/j.jclinepi.2017.12.022","title":"Retrospective assessment of resource use and costs in two investigator-initiated randomized trials exemplified a comprehensive cost item list","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":22,"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":"Randomized controlled trial; Resource (disambiguation); Medicine; Resource use; Cost database; Operations management; Clinical trial; Cost estimate; Cost–benefit analysis; Actuarial science; Business; Computer science; Environmental resource management; Economics; Surgery; Database","score_opus":0.8819054437567955,"score_gpt":0.6608736704096155,"score_spread":0.22103177334717994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777471495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94127584,0.001158436,0.002353182,0.051635195,0.0011515606,0.0012913388,0.00017027429,0.000007766704,0.0009564408],"genre_scores_gemma":[0.973497,0.0017543224,0.008476659,0.015542698,0.0006264739,0.000032578828,0.000010057413,0.000023519053,0.000036714016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9171289,0.04266762,0.038906667,0.00065642485,0.00014531378,0.0004950245],"domain_scores_gemma":[0.50419843,0.41199118,0.08116073,0.0010729065,0.00069348956,0.00088325574],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39620268,0.00025291764,0.014841939,0.00042124427,0.00016443877,0.00007082297,0.0005000668,0.000383311,0.00007239462],"category_scores_gemma":[0.85097903,0.00023607201,0.0009152011,0.000085076645,0.0012558923,0.0005624971,0.00014610324,0.0010683856,0.000012750131],"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":[0.0036766657,0.00012074329,0.9042109,0.000065098786,0.00034832204,0.000007650791,0.00013155879,0.00007967045,0.0000018957658,0.085744575,0.0054228706,0.00019001137],"study_design_scores_gemma":[0.07008556,0.00025098512,0.8721287,0.00041310358,0.000052006664,0.00001916368,0.00013579943,0.0061335424,9.15572e-7,0.04697612,0.003620406,0.00018366698],"about_ca_topic_score_codex":0.0018873422,"about_ca_topic_score_gemma":0.00024469724,"teacher_disagreement_score":0.45477638,"about_ca_system_score_codex":0.00039317852,"about_ca_system_score_gemma":0.00053356873,"threshold_uncertainty_score":0.99978375},"labels":[],"label_agreement":null},{"id":"W2777686840","doi":"10.1016/j.jclinepi.2017.12.015","title":"Technology-assisted risk of bias assessment in systematic reviews: a prospective cross-sectional evaluation of the RobotReviewer machine learning tool","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":54,"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":"Canadian Institutes of Health Research","keywords":"Blinding; Medicine; Reliability (semiconductor); Meta-analysis; Confidence interval; Publication bias; Clinical trial; Internal medicine","score_opus":0.9262384616759126,"score_gpt":0.7051979300689227,"score_spread":0.2210405316069899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777686840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674967,0.01582091,0.009108661,0.00197506,0.0016186115,0.0031591046,0.0000088883835,0.0000018366877,0.0008102597],"genre_scores_gemma":[0.9891302,0.0020435667,0.008196339,0.00008284419,0.00012083994,0.000065034576,5.4023525e-7,0.0000073661745,0.00035325307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.45331588,0.41370437,0.12395452,0.0012480229,0.007318279,0.00045893906],"domain_scores_gemma":[0.47006416,0.18490645,0.3258062,0.0065316036,0.012519978,0.00017159949],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8577546,0.0002744105,0.01744223,0.00045251095,0.00021930097,0.00009047363,0.0030111028,0.00038307978,0.0007911669],"category_scores_gemma":[0.96359086,0.000099766214,0.006392312,0.00075255625,0.0005927242,0.00025493582,0.00030824292,0.0016692762,0.000052441625],"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":[0.000022717595,0.00014937176,0.98601776,0.00086382555,0.00042300476,7.9491883e-7,0.00001904215,0.0019018321,0.0000062471377,0.00113551,0.00024251161,0.009217351],"study_design_scores_gemma":[0.00077183236,0.00020717186,0.9360713,0.0024766107,0.0008786808,0.00004232639,0.00003415117,0.030601174,0.0000014538487,0.028214566,0.0006268749,0.00007387143],"about_ca_topic_score_codex":0.00002063405,"about_ca_topic_score_gemma":0.000066969624,"teacher_disagreement_score":0.22879791,"about_ca_system_score_codex":0.00011208632,"about_ca_system_score_gemma":0.0004636589,"threshold_uncertainty_score":0.9971449},"labels":[],"label_agreement":null},{"id":"W2780553270","doi":"10.1016/j.jclinepi.2017.12.012","title":"Bootstrap imputation minimized misclassification bias when measuring Colles' fracture prevalence and its associations using health administrative data","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone fractures and treatments","field":"Medicine","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":"Institute for Clinical Evaluative Sciences; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Imputation (statistics); Statistics; Colles' fracture; Medicine; Health data; Demography; Econometrics; Missing data; Mathematics; Health care; Surgery; Economics","score_opus":0.8020476617953068,"score_gpt":0.6035020946666066,"score_spread":0.1985455671287002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780553270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90479267,0.0035758824,0.006627831,0.08345106,0.000715292,0.0005735635,0.0001369901,0.000011990822,0.00011474095],"genre_scores_gemma":[0.9792192,0.0019259058,0.016029125,0.0020868534,0.0005713004,0.0000016185257,0.00004236979,0.000012081784,0.000111548776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994725,0.0018132803,0.0026572566,0.00033629092,0.00022706178,0.00024111559],"domain_scores_gemma":[0.9807718,0.009627995,0.008280929,0.00055335305,0.0003605617,0.0004053706],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01159982,0.00015500303,0.0016652942,0.00006321059,0.00034263913,0.000029493209,0.00027146447,0.0003192117,0.000025934765],"category_scores_gemma":[0.09210326,0.00010982582,0.00021089481,0.00002699389,0.00014280916,0.00032086164,0.00007473087,0.00071256934,0.0000021218484],"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":[0.00072113844,0.00036735038,0.983992,0.00008467981,0.00059486233,0.00003226067,0.00016217778,0.000030356381,0.000017428189,0.00010834456,0.0027008953,0.011188515],"study_design_scores_gemma":[0.003316284,0.0007219741,0.98735017,0.00037028384,0.0003639381,0.0001540845,0.00003895497,0.0048786174,0.000012460444,0.0017033792,0.0010151338,0.00007474198],"about_ca_topic_score_codex":0.00007144664,"about_ca_topic_score_gemma":0.00003260164,"teacher_disagreement_score":0.08136421,"about_ca_system_score_codex":0.00009479119,"about_ca_system_score_gemma":0.000914409,"threshold_uncertainty_score":0.91554433},"labels":[],"label_agreement":null},{"id":"W2781903047","doi":"10.1016/j.jclinepi.2017.12.026","title":"Why the ethical justification of randomized clinical trials is a scientific question","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":21,"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 Allison University; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Randomized controlled trial; Clinical trial; Medicine; Medical physics; MEDLINE; Psychology; Pathology; Law; Political science","score_opus":0.8880902378548651,"score_gpt":0.6925524311940827,"score_spread":0.19553780666078235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781903047","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1197626,0.0027586017,0.17745496,0.6849454,0.013380659,0.0009884841,0.000061566,0.000014329867,0.0006334202],"genre_scores_gemma":[0.7192162,0.002546697,0.024591194,0.24104321,0.012013652,0.00004199293,0.00001393239,0.000036974183,0.0004961336],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66431147,0.21073489,0.12269426,0.0011465907,0.00037860137,0.00073421124],"domain_scores_gemma":[0.11043392,0.773996,0.111100405,0.0016095954,0.002154257,0.00070585066],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90007704,0.00018973582,0.011070754,0.00033583894,0.00022398103,0.00004105449,0.0007456189,0.0011906122,0.00072400895],"category_scores_gemma":[0.9091743,0.00013350155,0.0026664725,0.00026569015,0.0035722854,0.00022582419,0.0000734261,0.0017898657,0.0005751304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077778692,0.00030406634,0.053660158,0.000106070394,0.00060071,5.803227e-7,0.00058604317,0.000036541802,0.0000020788602,0.3882804,0.5454342,0.0032113062],"study_design_scores_gemma":[0.040692475,0.00095296866,0.050734363,0.00029979064,0.00026715608,0.00003033259,0.00024651768,0.02477539,0.0000064910187,0.5535549,0.3281679,0.00027171132],"about_ca_topic_score_codex":0.00015973754,"about_ca_topic_score_gemma":0.000033434873,"teacher_disagreement_score":0.5994536,"about_ca_system_score_codex":0.00009015505,"about_ca_system_score_gemma":0.00060480804,"threshold_uncertainty_score":0.9991394},"labels":[],"label_agreement":null},{"id":"W2782296496","doi":"10.1016/j.jclinepi.2017.12.027","title":"Many randomized clinical trials may not be justified: a cross-sectional analysis of the ethics and science of randomized clinical trials","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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 Ottawa; Mount Allison University; Ottawa Hospital","funders":"","keywords":"Randomized controlled trial; Clinical equipoise; Protocol (science); MEDLINE; Medicine; Meta-analysis; Publication bias; Scientific evidence; Evidence-based medicine; Alternative medicine; Clinical trial; Psychology; Epistemology; Surgery; Pathology; Law; Political science","score_opus":0.9132034100728446,"score_gpt":0.7724823342003715,"score_spread":0.14072107587247307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782296496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85856026,0.0009761752,0.016886942,0.10955492,0.010443474,0.0026701975,0.00009008177,0.000017654143,0.00080030813],"genre_scores_gemma":[0.94755214,0.020084104,0.013736568,0.012414695,0.0055239126,0.000022375652,0.0000050981753,0.00003274252,0.000628376],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.1368635,0.71148276,0.14104643,0.0023785925,0.006703492,0.0015252153],"domain_scores_gemma":[0.0014150888,0.93900865,0.044744674,0.001750535,0.011601482,0.0014795848],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.979521,0.00047447425,0.046284396,0.0010749277,0.0003920305,0.000049272174,0.001952717,0.00491069,0.00071566016],"category_scores_gemma":[0.9982187,0.00023510902,0.024653958,0.0018775556,0.07550612,0.00018243094,0.0009778726,0.019192753,0.000009351672],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.62415874,0.0008660854,0.31703588,0.00013954834,0.010022511,0.000009956679,0.000082023726,0.000040199335,0.00008548255,0.044392332,0.00043426375,0.0027330008],"study_design_scores_gemma":[0.56353813,0.002320547,0.34734437,0.00046794946,0.015585022,0.00005761134,0.00005673026,0.011247164,0.000104882034,0.058484375,0.00059292646,0.0002002747],"about_ca_topic_score_codex":0.00010857586,"about_ca_topic_score_gemma":0.000054335578,"teacher_disagreement_score":0.22752587,"about_ca_system_score_codex":0.00007243939,"about_ca_system_score_gemma":0.00871107,"threshold_uncertainty_score":0.9969086},"labels":[],"label_agreement":null},{"id":"W2790026935","doi":"10.1016/j.jclinepi.2018.02.001","title":"The win ratio approach did not alter study conclusions and may mitigate concerns regarding unequal composite end points in kidney transplant trials","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"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; Centre Hospitalier de l’Université de Montréal; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Hazard ratio; Medicine; Confidence interval; Ramipril; Placebo; Kidney transplantation; Creatinine; Internal medicine; Randomized controlled trial; Relative risk; Urology; Statistical significance; Clinical trial; Transplantation; Surgery; Blood pressure; Pathology","score_opus":0.8016224349326246,"score_gpt":0.6587889254959833,"score_spread":0.1428335094366413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790026935","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":[0.749063,0.0001827412,0.21309972,0.028658675,0.0057102214,0.002043008,0.0002123128,0.000034577504,0.0009957532],"genre_scores_gemma":[0.71764183,0.00046532208,0.2745848,0.0042604883,0.002936215,0.0000182032,0.0000016086178,0.0000328439,0.000058671027],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88445234,0.09523673,0.018250007,0.0007184007,0.00057700975,0.00076550525],"domain_scores_gemma":[0.1980927,0.793338,0.006693359,0.0006167432,0.00041984924,0.00083935546],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2532452,0.00034941992,0.006837874,0.000116045776,0.00028224764,0.00004039225,0.000674943,0.00054026995,0.00009501003],"category_scores_gemma":[0.80239046,0.00019247792,0.0008268315,0.00017430465,0.0019846526,0.00010446851,0.00023753793,0.0019631332,0.000009460446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030635437,0.005134763,0.50146323,0.00028852446,0.004210117,0.00050335395,0.004082727,0.000050311308,0.0012530818,0.37646657,0.024444817,0.05146708],"study_design_scores_gemma":[0.022092963,0.006333483,0.065309346,0.0008167152,0.0012128684,0.0001528086,0.0006382684,0.0041003413,0.0003180442,0.89660984,0.0018886686,0.00052665634],"about_ca_topic_score_codex":0.000023658666,"about_ca_topic_score_gemma":0.000022360584,"teacher_disagreement_score":0.6981013,"about_ca_system_score_codex":0.00004804446,"about_ca_system_score_gemma":0.00027631645,"threshold_uncertainty_score":0.85289466},"labels":[],"label_agreement":null},{"id":"W2790302041","doi":"10.1016/j.jclinepi.2018.03.001","title":"Response to Dr. Livia Puljak's letter about our published article","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scopus; Publication bias; Systematic review; MEDLINE; Attrition; Reporting bias; Psychology; Medicine; Medical education; Meta-analysis; Political science; Law","score_opus":0.5651543854416219,"score_gpt":0.5667698303157579,"score_spread":0.0016154448741360072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790302041","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":[0.057310626,0.00017470715,0.0053914944,0.92278945,0.013509725,0.00033610195,0.000017240429,0.000017085047,0.00045358934],"genre_scores_gemma":[0.008699056,0.00005855863,0.0054755267,0.94070995,0.036091104,0.000010096596,0.0000030341087,0.000035531943,0.008917165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8956357,0.07087606,0.02502044,0.0019316934,0.004821534,0.0017145263],"domain_scores_gemma":[0.7611112,0.21388386,0.015233917,0.0034138665,0.005092835,0.0012643253],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.4055864,0.0005424379,0.0058505526,0.00076299603,0.00016516523,0.00030688941,0.004298797,0.0024845968,0.0018825618],"category_scores_gemma":[0.7543132,0.0003216221,0.0027462922,0.00070168317,0.0004871057,0.0005234345,0.00057050056,0.007048631,0.0039053052],"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":[0.0017809962,0.00015840096,0.031173492,0.0000106849075,0.00015868033,0.00025893236,0.000048156737,0.000050008133,0.00006447705,0.00001528636,0.9610845,0.0051963865],"study_design_scores_gemma":[0.0007348835,0.0019396062,0.107109584,0.00015810053,0.00007220665,0.00005824642,0.000030206364,0.00005424402,0.000009533005,0.03189531,0.8576499,0.0002881406],"about_ca_topic_score_codex":0.00001501973,"about_ca_topic_score_gemma":0.0000110581905,"teacher_disagreement_score":0.34872678,"about_ca_system_score_codex":0.00015953301,"about_ca_system_score_gemma":0.00071974314,"threshold_uncertainty_score":0.9999236},"labels":[],"label_agreement":null},{"id":"W2790403673","doi":"10.1016/j.jclinepi.2018.01.013","title":"GRADE Guidelines: 19. Assessing the certainty of evidence in the importance of outcomes or values and preferences—Risk of bias and indirectness","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":284,"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; University of Calgary; McMaster University; McMaster University Medical Centre; Impact","funders":"Canadian Institutes of Health Research; Arthritis Society; McMaster University","keywords":"Certainty; Grading (engineering); Actuarial science; Confounding; Psychology; Selection bias; Population; Publication bias; Medicine; Meta-analysis; Pathology; Environmental health; Economics","score_opus":0.9807710205973338,"score_gpt":0.7443066146558855,"score_spread":0.23646440594144824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790403673","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":[0.98003316,0.0041023334,0.0034435638,0.011853051,0.00026623026,0.00022942851,0.000004515703,4.5547932e-7,0.000067284614],"genre_scores_gemma":[0.98435843,0.0032956328,0.01046386,0.0016557684,0.00014288687,0.0000023313873,1.1731019e-7,0.0000034179454,0.00007755288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.78419644,0.15384397,0.058258973,0.0006844972,0.002706594,0.000309541],"domain_scores_gemma":[0.23301657,0.6873825,0.07400291,0.0020741934,0.0033536856,0.00017015253],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.65638995,0.00018996828,0.008686238,0.00021011509,0.00006645281,0.000041760748,0.0017104029,0.00022421243,0.00023568355],"category_scores_gemma":[0.90278566,0.000048137685,0.0013498479,0.00068314513,0.0013434235,0.00019754756,0.0001587761,0.00059971417,0.000002076365],"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":[0.0000451158,0.000038946073,0.9817919,0.00005154793,0.00017647725,0.0000015495056,0.00039951535,0.000036121954,0.0000032967641,0.0002877466,0.004505868,0.012661929],"study_design_scores_gemma":[0.00023949334,0.00035524557,0.9258279,0.00032037546,0.00030479563,0.00003567521,0.001703661,0.0022349146,0.0000044541252,0.06815526,0.00076851516,0.000049717273],"about_ca_topic_score_codex":0.00009661711,"about_ca_topic_score_gemma":0.0002088226,"teacher_disagreement_score":0.5511799,"about_ca_system_score_codex":0.000005711623,"about_ca_system_score_gemma":0.00024697583,"threshold_uncertainty_score":0.59377384},"labels":[],"label_agreement":null},{"id":"W2791081953","doi":"10.1016/j.jclinepi.2018.02.009","title":"Is providing uncertainty intervals in treatment ranking helpful in a network meta-analysis?","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":87,"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; Canada Research Chairs; St. Michael's Hospital","funders":"","keywords":"Scopus; Meta-analysis; Ranking (information retrieval); Confidence interval; Rank (graph theory); Statistics; Medicine; MEDLINE; Computer science; Mathematics; Information retrieval; Internal medicine; Combinatorics","score_opus":0.967078491098483,"score_gpt":0.7103394275835999,"score_spread":0.25673906351488307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791081953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8240702,0.0136740655,0.10505297,0.05065067,0.0023067966,0.0012935583,0.000011777582,0.0000050339568,0.0029349118],"genre_scores_gemma":[0.9755193,0.00027423495,0.01570995,0.006427078,0.000963438,0.00001736327,0.0000010136188,0.000009344441,0.0010783072],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6468782,0.24495432,0.10264432,0.0017415347,0.0028140072,0.0009676349],"domain_scores_gemma":[0.50873977,0.4050071,0.078067675,0.0046196543,0.0028742745,0.0006915212],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7186421,0.0004078314,0.03736205,0.0011436978,0.000065087785,0.00011885623,0.0019352942,0.0003662659,0.0102530075],"category_scores_gemma":[0.49858013,0.00016276869,0.024722382,0.0032339643,0.00026014345,0.00023342717,0.00016235367,0.0007221358,0.00042887413],"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":[0.00017341763,0.0002336986,0.9028394,0.000009134117,0.051971752,0.000047473633,0.00047846112,0.012626529,8.337422e-7,0.001016672,0.012865398,0.017737223],"study_design_scores_gemma":[0.0025899466,0.0025805715,0.3827754,0.0001073779,0.121928334,0.000078485304,0.00057151425,0.16322346,0.0000036914305,0.1850292,0.14059232,0.0005197135],"about_ca_topic_score_codex":0.00013550385,"about_ca_topic_score_gemma":0.0018119012,"teacher_disagreement_score":0.520064,"about_ca_system_score_codex":0.000116304676,"about_ca_system_score_gemma":0.00021565668,"threshold_uncertainty_score":0.9906517},"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":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2792121777","doi":"10.1016/j.jclinepi.2018.02.008","title":"Using decision thresholds for ranking treatments in network meta-analysis results in more informative rankings","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Mount Sinai Hospital; Centre for Social Innovation; Institute for Work & Health; Hospital for Sick Children; Institute for Clinical Evaluative Sciences; Impact; University Health Network; SickKids Foundation; University of Toronto; McMaster University","funders":"","keywords":"Meta-analysis; Ranking (information retrieval); Statistics; MEDLINE; Medicine; Randomized controlled trial; Systematic review; Rank (graph theory); Treatment effect; Best practice; Econometrics; Mathematics; Computer science; Machine learning; Internal medicine; Traditional medicine","score_opus":0.9779948542579632,"score_gpt":0.7480640352904983,"score_spread":0.22993081896746492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792121777","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":[0.00030067706,0.91927445,0.076799825,0.00037515105,0.0011137105,0.001830015,0.00007862742,0.0000017341749,0.00022581205],"genre_scores_gemma":[0.00020135155,0.87053245,0.12695813,0.0008855211,0.0010083334,0.000064253094,0.000036152647,0.000035594625,0.0002782312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5490554,0.19375166,0.24764189,0.00281031,0.005295405,0.0014452983],"domain_scores_gemma":[0.22386388,0.58487993,0.18316033,0.004633065,0.0029512546,0.0005115142],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.80325377,0.0011286292,0.12558778,0.003703698,0.00013153543,0.00021323856,0.0042357943,0.0016673214,0.00084175],"category_scores_gemma":[0.7032443,0.00045308465,0.07971361,0.006573139,0.0003266971,0.00053706,0.0003810363,0.0018658381,0.00013434104],"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":[0.0007378474,0.00030803474,0.016975414,0.0010538918,0.26564583,0.000077682394,0.00033066873,0.020229418,2.0232656e-9,0.0005648782,0.024522841,0.66955346],"study_design_scores_gemma":[0.0015450313,0.00032089502,0.001392304,0.002082768,0.31189087,0.00007512572,0.000048271406,0.013425136,3.1706784e-9,0.025066156,0.6437727,0.00038069356],"about_ca_topic_score_codex":0.000027218877,"about_ca_topic_score_gemma":0.00019428166,"teacher_disagreement_score":0.66917276,"about_ca_system_score_codex":0.00023345702,"about_ca_system_score_gemma":0.0007025126,"threshold_uncertainty_score":0.9997921},"labels":[],"label_agreement":null},{"id":"W2792220848","doi":"10.1016/j.jclinepi.2018.02.016","title":"Systematic reviews do not adequately report or address missing outcome data in their analyses: a methodological survey","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"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; Systematic review; Meta-analysis; Outcome (game theory); Medicine; MEDLINE; Statistics; Data mining; Computer science; Pathology; Mathematics","score_opus":0.997638105851686,"score_gpt":0.8241178067989564,"score_spread":0.1735202990527296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792220848","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021194794,0.9438777,0.048627567,0.000605551,0.003325094,0.0031826098,0.00013579715,0.0000046306727,0.00021987355],"genre_scores_gemma":[0.000019401296,0.93999124,0.055437874,0.0013508118,0.0015844031,0.00006012566,0.00009380634,0.000054116466,0.001408232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.038220465,0.6856675,0.26779103,0.003406751,0.004024709,0.0008895487],"domain_scores_gemma":[0.0048510325,0.7000727,0.27492464,0.016332962,0.0028849181,0.00093372416],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9781747,0.0017457337,0.20916502,0.0018316946,0.00013939533,0.00052428583,0.019203527,0.0025016805,0.0041717957],"category_scores_gemma":[0.9954337,0.0005357375,0.031158593,0.0039469954,0.0006984985,0.00051713095,0.0020206354,0.004491683,0.0019007844],"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":[0.00022648943,0.00047708367,0.024045205,0.14559203,0.007023639,0.0018464781,0.000051695053,0.000008932448,3.2795207e-8,0.00010250766,0.11188464,0.70874125],"study_design_scores_gemma":[0.0002955623,0.00032243226,0.002743826,0.07922256,0.0071337344,0.003917459,0.000044415327,0.00055476854,5.9499072e-9,0.0016843063,0.9035223,0.0005586317],"about_ca_topic_score_codex":0.00004066441,"about_ca_topic_score_gemma":0.00016932283,"teacher_disagreement_score":0.79163766,"about_ca_system_score_codex":0.00014817822,"about_ca_system_score_gemma":0.0016964037,"threshold_uncertainty_score":0.9997094},"labels":[],"label_agreement":null},{"id":"W2792308249","doi":"10.1016/j.jclinepi.2018.01.012","title":"GRADE guidelines: 18. How ROBINS-I and other tools to assess risk of bias in nonrandomized studies should be used to rate the certainty of a body of evidence","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":875,"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":"Medical Research Council; National Institute for Health and Care Research","keywords":"Randomized controlled trial; Confounding; Medicine; Guideline; Psychological intervention; Systematic review; Metric (unit); Evidence-based practice; MEDLINE; Physical therapy; Psychology; Alternative medicine; Operations management; Surgery; Psychiatry","score_opus":0.9922080303196605,"score_gpt":0.7562047525184826,"score_spread":0.2360032778011779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792308249","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9013082,0.00185814,0.02810057,0.0673906,0.0005133757,0.0007821497,0.000017492217,7.8541535e-7,0.000028733872],"genre_scores_gemma":[0.9679206,0.0013364551,0.022752032,0.007484027,0.0002923115,0.0000132576,1.0159047e-7,0.000009404044,0.00019182383],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6803086,0.24255793,0.07231442,0.0010897651,0.0032022186,0.0005270815],"domain_scores_gemma":[0.17800356,0.7578502,0.053440012,0.0026589853,0.007662172,0.00038501312],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72227246,0.00027687725,0.017599363,0.00043184534,0.000045312416,0.000042191503,0.0017938453,0.0002629801,0.00032442555],"category_scores_gemma":[0.9588136,0.00009257078,0.0030800614,0.0010269361,0.00065802113,0.00015816654,0.00028914458,0.00056823983,0.000012889176],"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":[0.0027883344,0.00021490859,0.8667255,0.00011727402,0.0019642923,0.0000044257636,0.0011537059,0.0021498702,0.0007863179,0.00073441246,0.11630549,0.0070554665],"study_design_scores_gemma":[0.016564766,0.008267613,0.80783963,0.00479277,0.004060465,0.000053234697,0.00845709,0.020163478,0.0005453454,0.05625051,0.072314195,0.0006908709],"about_ca_topic_score_codex":0.00008354595,"about_ca_topic_score_gemma":0.00032211602,"teacher_disagreement_score":0.51529235,"about_ca_system_score_codex":0.000016230437,"about_ca_system_score_gemma":0.00018175406,"threshold_uncertainty_score":0.9969854},"labels":[],"label_agreement":null},{"id":"W2792627271","doi":"10.1016/j.jclinepi.2018.03.005","title":"Network meta-analysis of diagnostic test accuracy studies identifies and ranks the optimal diagnostic tests and thresholds for health care policy and decision-making","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":51,"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 for Health and Care Research","keywords":"Bivariate analysis; Context (archaeology); Ranking (information retrieval); Statistics; Markov chain Monte Carlo; Meta-analysis; Test (biology); Computer science; Bayesian probability; Medicine; Econometrics; Mathematics; Machine learning; Internal medicine","score_opus":0.5708368832688051,"score_gpt":0.671402132839384,"score_spread":0.10056524957057889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792627271","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":[0.74025905,0.2178305,0.0038610995,0.035980947,0.0010160971,0.0009019215,0.000091193375,0.000007584542,0.000051620256],"genre_scores_gemma":[0.95871466,0.022291115,0.008916248,0.008379259,0.0016146132,0.000043863034,0.0000020356802,0.000016841826,0.000021348556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.990465,0.0038571972,0.00433519,0.00044163453,0.00024572734,0.00065524515],"domain_scores_gemma":[0.2507527,0.7448311,0.0030479464,0.0004119719,0.00060698896,0.0003493135],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029610408,0.00022711173,0.0042229486,0.0002728876,0.0003613744,0.00002117584,0.00033411742,0.00025095817,0.00006262111],"category_scores_gemma":[0.6590737,0.00012823075,0.0006626312,0.00040268194,0.0018709366,0.00010225848,0.00032288863,0.00068979355,0.0000016034584],"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":[0.001050397,0.00021950029,0.7552022,0.00033366898,0.03544754,0.00003216385,0.0030605055,0.00027899354,2.762766e-7,0.0061757574,0.02102809,0.17717095],"study_design_scores_gemma":[0.0012789995,0.00462908,0.93433976,0.00016771069,0.015708953,0.000119891105,0.0013301456,0.00032519063,2.6571635e-7,0.03911278,0.0028464503,0.00014076111],"about_ca_topic_score_codex":0.00011392394,"about_ca_topic_score_gemma":0.0006278179,"teacher_disagreement_score":0.7409739,"about_ca_system_score_codex":0.000046220222,"about_ca_system_score_gemma":0.0002379227,"threshold_uncertainty_score":0.9992203},"labels":[],"label_agreement":null},{"id":"W2792887609","doi":"10.1016/j.jclinepi.2018.03.009","title":"Reply to: Letter to the Editor by M. Olsen, M. K. Sharp, and P. M. Bossuyt","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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 Allison University; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Operationalization; Clinical equipoise; Set (abstract data type); Randomized controlled trial; Clinical trial; Medicine; Epistemology; Psychology; Philosophy; Computer science; Surgery; Pathology","score_opus":0.5863551998843677,"score_gpt":0.6404147472707429,"score_spread":0.054059547386375195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792887609","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.00078865327,0.0010067045,0.0009697994,0.97353387,0.021955386,0.00068998075,0.00006148565,0.000018953247,0.0009751741],"genre_scores_gemma":[0.00004883293,0.0020345724,0.005252123,0.6744792,0.30495092,0.000015509358,0.0000152072835,0.00007138306,0.013132294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9739468,0.009962393,0.011235542,0.0013918204,0.0020248203,0.0014386246],"domain_scores_gemma":[0.38848084,0.5971511,0.00544303,0.0028395888,0.0037354166,0.002350019],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.14305325,0.0005337694,0.00588903,0.00028031558,0.00015230305,0.00004501467,0.0016964689,0.0058406834,0.0006207766],"category_scores_gemma":[0.76393706,0.00029717863,0.0014894016,0.0002839019,0.001729271,0.00006970355,0.0009124656,0.0381927,0.00085981836],"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":[0.0009426603,0.00009372288,0.006435889,0.00019005394,0.0004432382,0.00044850504,0.000030859403,7.0920305e-7,0.000006572823,0.0000486034,0.98867655,0.002682665],"study_design_scores_gemma":[0.0010685223,0.0061263945,0.004709199,0.0010037965,0.00026429404,0.00031225936,0.000006189518,0.000010722796,0.000004328633,0.008654024,0.9775784,0.00026185444],"about_ca_topic_score_codex":0.000076451804,"about_ca_topic_score_gemma":0.00002146547,"teacher_disagreement_score":0.6208838,"about_ca_system_score_codex":0.00012311387,"about_ca_system_score_gemma":0.0011057658,"threshold_uncertainty_score":0.999948},"labels":[],"label_agreement":null},{"id":"W2792906968","doi":"10.1016/j.jclinepi.2018.02.005","title":"Methods for analyzing matched designs with double controls: excess risk is easily estimated and misinterpreted when evaluating traffic deaths","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Traffic and Road Safety","field":"Engineering","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":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Poisson regression; Confidence interval; Statistics; Relative risk; Count data; Absolute risk reduction; Poisson distribution; Demography; Medicine; Regression analysis; Mathematics; Environmental health; Population","score_opus":0.337688090335005,"score_gpt":0.5397037009594515,"score_spread":0.2020156106244465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792906968","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":[0.42264464,0.0012754536,0.5748671,0.0004145436,0.00051904237,0.00017781813,0.0000052780174,0.00005522788,0.000040898754],"genre_scores_gemma":[0.5527554,0.00020443808,0.44636542,0.00024703884,0.00038202447,0.000003781943,0.0000012191903,0.00002847189,0.000012173187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99363184,0.0023481264,0.0031349491,0.00030459077,0.000108095155,0.0004724131],"domain_scores_gemma":[0.96951264,0.028041927,0.0014737837,0.0002244925,0.00041610314,0.00033102842],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027069768,0.00026456304,0.0023580645,0.00011766449,0.00012452835,0.00001869131,0.00025933646,0.00039951358,0.000047340935],"category_scores_gemma":[0.012595462,0.00017693524,0.00039685832,0.000114543865,0.0003211513,0.00014541854,0.000025843226,0.00075720873,0.0000033581464],"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":[0.011409545,0.00015997887,0.12602824,0.00020760037,0.0032761176,0.000015225341,0.0017702328,0.21930541,0.0006595394,0.00019917826,0.0036280812,0.63334084],"study_design_scores_gemma":[0.0067907707,0.0025060477,0.039635368,0.00025881067,0.00069569226,0.00012063313,0.00007726437,0.94666994,0.00007409557,0.0023908636,0.0005346255,0.0002459114],"about_ca_topic_score_codex":0.000011857564,"about_ca_topic_score_gemma":0.00000998038,"teacher_disagreement_score":0.7273645,"about_ca_system_score_codex":0.00003658675,"about_ca_system_score_gemma":0.00010774963,"threshold_uncertainty_score":0.9957219},"labels":[],"label_agreement":null},{"id":"W2794004352","doi":"10.1016/j.jclinepi.2018.01.010","title":"A scoping review and survey provides the rationale, perceptions, and preferences for the integration of randomized and nonrandomized studies in evidence syntheses and GRADE assessments","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":31,"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; Impact","funders":"McMaster University","keywords":"Grading (engineering); Randomized controlled trial; Certainty; Systematic review; Medicine; Intervention (counseling); Evidence-based medicine; Psychology; MEDLINE; Applied psychology; Family medicine; Alternative medicine; Medical education; Nursing; Pathology","score_opus":0.9751420023304412,"score_gpt":0.7545576842830853,"score_spread":0.2205843180473559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794004352","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":[0.00067686,0.98461926,0.005963786,0.0022154297,0.00023593247,0.0062698782,0.000013932295,5.4651764e-7,0.000004374474],"genre_scores_gemma":[0.0007543748,0.9932038,0.005092854,0.0003575386,0.00013520692,0.00037532471,0.0000016186779,0.000006711419,0.000072580915],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.56793845,0.37361214,0.055693828,0.0011053832,0.0013775582,0.00027263907],"domain_scores_gemma":[0.033709645,0.9247251,0.03873275,0.0007777697,0.0019479959,0.00010675108],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.757845,0.00038095188,0.03479362,0.00023444225,0.00015755113,0.00014541033,0.0007487055,0.0002297227,0.000056701752],"category_scores_gemma":[0.9457026,0.00010723612,0.0024172938,0.00028995215,0.0019357927,0.00027554363,0.00020156677,0.00053281884,0.0000012626327],"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":[0.0036370193,0.000086303015,0.012222531,0.07097495,0.004701975,8.4314604e-7,0.00044915642,0.0000014466125,7.480586e-8,0.0006423469,0.005444929,0.9018384],"study_design_scores_gemma":[0.021928353,0.0009772792,0.012478811,0.88042766,0.031760093,0.00030090983,0.0013181262,0.0016875552,2.8778418e-8,0.033441287,0.015176225,0.0005036727],"about_ca_topic_score_codex":0.000018692692,"about_ca_topic_score_gemma":0.0003209963,"teacher_disagreement_score":0.90133476,"about_ca_system_score_codex":0.000012234684,"about_ca_system_score_gemma":0.00034763655,"threshold_uncertainty_score":0.9795359},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2794136313","doi":"10.1016/j.jclinepi.2018.02.026","title":"Do clinicians want recommendations? A multicenter study comparing evidence summaries with and without GRADE recommendations","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University","funders":"","keywords":"Certainty; Context (archaeology); Medicine; Randomized controlled trial; MEDLINE; Evidence-based medicine; Evidence-based practice; Presentation (obstetrics); Medical education; Action (physics); Family medicine; Alternative medicine","score_opus":0.7620692003378781,"score_gpt":0.6610417971729302,"score_spread":0.10102740316494785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794136313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8307964,0.00019384088,0.010556093,0.15638475,0.0013381793,0.0006332416,0.0000053500435,0.000022085793,0.00007004753],"genre_scores_gemma":[0.9156833,0.0017819476,0.07100588,0.009809239,0.0016286758,0.00000975106,0.0000106495745,0.000024259018,0.00004625564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9842311,0.0057930932,0.008802311,0.0004921323,0.00030271735,0.00037861176],"domain_scores_gemma":[0.9140308,0.07706557,0.0063265837,0.0005492714,0.0014743466,0.00055341126],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040609993,0.00023595171,0.0024522732,0.00018944668,0.00019924546,0.00003331121,0.00021446304,0.00019243547,0.00024191085],"category_scores_gemma":[0.20475413,0.00015855106,0.0002814777,0.00021344527,0.0007092395,0.0005442645,0.00015649814,0.0014624256,0.00002671255],"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":[0.0039534084,0.0011631049,0.94220215,0.000020519035,0.00046153588,0.000013952156,0.0003965962,0.0000050771764,0.000005618757,0.00009405499,0.009749347,0.04193461],"study_design_scores_gemma":[0.009348532,0.0125527065,0.945066,0.0008747453,0.0011553235,0.000275485,0.0040864213,0.0021236655,0.000004480475,0.0010248473,0.023302248,0.0001855717],"about_ca_topic_score_codex":0.00016790145,"about_ca_topic_score_gemma":0.0009519779,"teacher_disagreement_score":0.16414414,"about_ca_system_score_codex":0.00006154926,"about_ca_system_score_gemma":0.00036712977,"threshold_uncertainty_score":0.9878939},"labels":[],"label_agreement":null},{"id":"W2794309234","doi":"10.1016/j.jclinepi.2018.02.020","title":"Letter to the editor in response to “No difference in knowledge obtained from infographic or plain language summary of a Cochrane systematic review: three randomized controlled trials” by Buljan et al. (2017)","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Misinformation and Its Impacts","field":"Social Sciences","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":"Université de Montréal","funders":"","keywords":"Infographic; Randomized controlled trial; Plain language; Medicine; Systematic review; Cochrane collaboration; MEDLINE; Medical physics; Pediatrics; Internal medicine; Computer science; Linguistics; Data mining; Philosophy; Cochrane Library","score_opus":0.12778089043375104,"score_gpt":0.4915827387378329,"score_spread":0.3638018483040819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794309234","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0044180136,0.013513053,0.0006542714,0.96770006,0.007046746,0.006151434,0.000114477836,0.0000119092165,0.000390034],"genre_scores_gemma":[0.000892411,0.015613201,0.000380086,0.96793014,0.01364018,0.000110275876,0.000028779035,0.000022702934,0.0013822005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7015574,0.26529345,0.030025676,0.0005694163,0.0014780796,0.0010760102],"domain_scores_gemma":[0.40102193,0.5818828,0.014942509,0.0008034832,0.00089196867,0.00045732406],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4404639,0.00045658296,0.023179417,0.00074568414,0.00007685983,0.000044075445,0.0015656925,0.001303572,0.00038160663],"category_scores_gemma":[0.8931302,0.00020878739,0.002402029,0.0005883982,0.00065452565,0.00015413214,0.00012433346,0.0032180876,0.00009768262],"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":[0.11490837,0.00007036566,0.000043464956,0.0019585309,0.0003401846,0.00003116642,0.003010042,0.0000013259087,0.0000032086862,0.000012857737,0.8795503,0.000070232934],"study_design_scores_gemma":[0.12320282,0.001098775,0.0006848384,0.09055679,0.00084636325,0.0000067643014,0.00040695953,0.000113525384,2.5493785e-7,0.00037069892,0.7822754,0.00043685306],"about_ca_topic_score_codex":0.0007035691,"about_ca_topic_score_gemma":0.0025640256,"teacher_disagreement_score":0.45266625,"about_ca_system_score_codex":0.0001167263,"about_ca_system_score_gemma":0.0012415872,"threshold_uncertainty_score":0.99999297},"labels":[],"label_agreement":null},{"id":"W2796645918","doi":"10.1016/j.jclinepi.2018.04.008","title":"Scoping review identifies significant number of knowledge translation theories, models, and frameworks with limited use","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":235,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Ottawa; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Partenariat Canadien Contre Le Cancer","keywords":"Knowledge translation; Scalability; Computer science; Data science; Sustainability; Psychological intervention; Management science; Process (computing); Knowledge management; Process management; Medicine; Database; Engineering; Ecology","score_opus":0.8906711163336964,"score_gpt":0.7572769685257655,"score_spread":0.1333941478079309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796645918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61254454,0.005875737,0.31207007,0.06298861,0.0025097837,0.002278739,0.000032682958,0.000033723773,0.0016661477],"genre_scores_gemma":[0.85510653,0.039658047,0.048286293,0.055369575,0.0014268691,0.000029921306,0.0000029222374,0.00002547857,0.00009436448],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97765535,0.014403737,0.0070403707,0.00024232449,0.00021421337,0.00044402116],"domain_scores_gemma":[0.81207174,0.17887539,0.006513047,0.00034299493,0.0017554485,0.00044136314],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050265644,0.00013192861,0.0019376966,0.00009103987,0.00022639119,0.000004107415,0.00021680963,0.0004491747,0.00028964266],"category_scores_gemma":[0.10420041,0.00008451212,0.00013627851,0.00032250307,0.00090384774,0.0004557462,0.00005174181,0.0015368141,0.000023990218],"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":[0.0012790689,0.00017796815,0.8760912,0.012262866,0.0001832158,0.000007209518,0.008304556,0.000035656885,0.00002417924,0.047254458,0.020754177,0.033625446],"study_design_scores_gemma":[0.009209127,0.0047717495,0.44830748,0.2679838,0.0006899293,0.00016798626,0.0026468993,0.006936718,0.00002622624,0.23342735,0.024944259,0.0008884539],"about_ca_topic_score_codex":0.000062624764,"about_ca_topic_score_gemma":0.00018116621,"teacher_disagreement_score":0.4277837,"about_ca_system_score_codex":0.000026344293,"about_ca_system_score_gemma":0.0012907151,"threshold_uncertainty_score":0.9779514},"labels":[],"label_agreement":null},{"id":"W2797138213","doi":"10.1016/j.jclinepi.2018.03.012","title":"PRISMA and AMSTAR show systematic reviews on health literacy and cancer screening are of good quality","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"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":"Systematic review; Medicine; Health literacy; Quality (philosophy); Literacy; Public health; Environmental health; Family medicine; MEDLINE; Psychology; Health care; Pathology; Biology; Political science","score_opus":0.949661926840482,"score_gpt":0.73582548946565,"score_spread":0.21383643737483204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797138213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6717558,0.15793805,0.10049689,0.064887896,0.0019711407,0.0024414456,0.000033067725,0.000003973587,0.0004717499],"genre_scores_gemma":[0.8801354,0.027419461,0.07134824,0.018602567,0.0015012749,0.000022395061,9.4007834e-7,0.000019177862,0.0009505383],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6519029,0.25253564,0.09186021,0.0010245137,0.0022296463,0.00044709677],"domain_scores_gemma":[0.45000544,0.3619861,0.180798,0.0031741404,0.0030063589,0.0010299666],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71071404,0.00027073128,0.024037603,0.00025451873,0.00010145147,0.00007327194,0.00084224535,0.0002028254,0.00047585584],"category_scores_gemma":[0.67915374,0.00010929744,0.002450345,0.00040262338,0.00037658843,0.00019444273,0.00012497262,0.0005784519,0.00004998932],"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":[0.00012189398,0.00011334835,0.768008,0.0073375795,0.0005237865,0.0000034547281,0.0004408594,0.000010533247,0.0000018462794,0.004394374,0.02769539,0.19134897],"study_design_scores_gemma":[0.0010996521,0.00228023,0.8350312,0.019104822,0.00061446015,0.0001167981,0.00045974524,0.005127061,0.0000013651836,0.023086201,0.11280437,0.00027408067],"about_ca_topic_score_codex":0.000038987357,"about_ca_topic_score_gemma":0.000048861577,"teacher_disagreement_score":0.20837961,"about_ca_system_score_codex":0.000018725166,"about_ca_system_score_gemma":0.00011520957,"threshold_uncertainty_score":0.9904516},"labels":[],"label_agreement":null},{"id":"W2797678636","doi":"10.1016/j.jclinepi.2018.04.007","title":"Reply to letter to the editor by C. Faggion: reproducibility and reporting guidelines","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; University of Ottawa","funders":"Cancer Research UK","keywords":"Scopus; Transparency (behavior); Web of science; Medicine; MEDLINE; Library science; Psychology; Computer science; Political science; Meta-analysis; Pathology","score_opus":0.9355852796634873,"score_gpt":0.6917561266056325,"score_spread":0.2438291530578548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797678636","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002528846,0.0011031571,0.026132995,0.94535595,0.023992239,0.0006665311,0.000017962746,0.0000034052189,0.000198916],"genre_scores_gemma":[0.00007945022,0.00007711732,0.026944486,0.7598793,0.20448038,0.000012029942,0.0000033269416,0.000020223259,0.008503711],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.24211577,0.32279995,0.41262966,0.009914772,0.010950032,0.0015898229],"domain_scores_gemma":[0.047298256,0.5056095,0.3928141,0.03194327,0.020967009,0.0013678393],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9253874,0.00059120345,0.024881111,0.00033762722,0.00018414551,0.0002845666,0.0041511487,0.0012165101,0.0017659953],"category_scores_gemma":[0.9912024,0.00020990662,0.0073751905,0.00071445043,0.00037060055,0.00014108368,0.0007388352,0.0038581344,0.0013117065],"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":[0.000028432942,0.0000140771235,0.024613187,0.000026485137,0.00028218972,0.00005060468,0.00003120446,0.000012559923,0.0000011932542,0.0000025430595,0.96291375,0.012023792],"study_design_scores_gemma":[0.00008924728,0.0004047121,0.004833014,0.00014630433,0.00032043768,0.00019612348,0.000016499083,0.000109775865,6.4153403e-7,0.0041337996,0.98954827,0.00020118259],"about_ca_topic_score_codex":0.000036031954,"about_ca_topic_score_gemma":0.0000068160202,"teacher_disagreement_score":0.19481751,"about_ca_system_score_codex":0.00003810812,"about_ca_system_score_gemma":0.00024335225,"threshold_uncertainty_score":0.9994659},"labels":[],"label_agreement":null},{"id":"W2799538654","doi":"10.1016/j.jclinepi.2018.04.018","title":"Randomized controlled trials in pediatric patients had higher completion rates than adult trials: a cross-sectional study","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Children's Hospital Research Institute of Manitoba; University of Manitoba","funders":"NIH Clinical Center; U.S. National Library of Medicine","keywords":"Medicine; Randomized controlled trial; Blinding; Odds ratio; Logistic regression; Population; Clinical trial; Cross-sectional study; Placebo; Odds; Physical therapy; Pediatrics; Internal medicine; Alternative medicine","score_opus":0.827296152204872,"score_gpt":0.7203770708912887,"score_spread":0.1069190813135833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799538654","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97854006,0.00041305693,0.0006202377,0.00861548,0.0075534564,0.0037119582,0.000009405449,0.000016170545,0.0005201897],"genre_scores_gemma":[0.9775012,0.00263066,0.0019423611,0.0035180177,0.013712474,0.000098179364,0.000009688188,0.000029239409,0.0005581918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5598517,0.3424335,0.09188709,0.0013139511,0.0032636833,0.0012500259],"domain_scores_gemma":[0.006523113,0.9620032,0.02234197,0.0005315804,0.007883676,0.0007164945],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.80149865,0.00035357403,0.033174183,0.000687458,0.00011599073,0.000039447896,0.0005069178,0.0016054288,0.001022535],"category_scores_gemma":[0.9881961,0.00018643234,0.006829336,0.00039157548,0.0015449506,0.00013219002,0.0001544591,0.0057970723,0.00010628172],"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":[0.41675386,0.0022298892,0.5778281,0.000030391122,0.00083971454,0.000017538483,0.000023525801,0.0000069537973,0.0000010638005,0.0013572306,0.00073703076,0.00017469047],"study_design_scores_gemma":[0.4195508,0.0052323123,0.54176503,0.00007805223,0.00057884125,0.00000479279,0.000011286206,0.00016502127,6.645947e-7,0.032478552,0.00005689438,0.00007773305],"about_ca_topic_score_codex":0.00009828855,"about_ca_topic_score_gemma":0.00012527769,"teacher_disagreement_score":0.61956966,"about_ca_system_score_codex":0.0001257947,"about_ca_system_score_gemma":0.0011932914,"threshold_uncertainty_score":0.9998907},"labels":[],"label_agreement":null},{"id":"W2803416088","doi":"10.1016/j.jclinepi.2018.04.013","title":"Corrigendum to “Advances in the GRADE approach to rate the certainty in estimates from a network meta-analysis” [J Clin Epidemiol 2018;93:36-44]","year":2018,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Calgary; Impact; University of Toronto; McMaster University","funders":"","keywords":"Certainty; Regret; Pairwise comparison; Grading (engineering); Meta-analysis; Quality of evidence; Computer science; Medicine; Management science; Operations research; Artificial intelligence; Mathematics; Machine learning; Engineering; Pathology","score_opus":0.9279776151856138,"score_gpt":0.6520937459359297,"score_spread":0.2758838692496841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803416088","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002548226,0.19563322,0.4437584,0.21296361,0.11544219,0.008781799,0.00047819538,0.000020291069,0.020374067],"genre_scores_gemma":[0.02873595,0.025754545,0.37362126,0.35112578,0.061418884,0.0015510197,0.000553062,0.0003638611,0.15687564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.37230587,0.4805567,0.13337837,0.004602436,0.0068127443,0.0023438865],"domain_scores_gemma":[0.2381309,0.6424247,0.10255646,0.012697525,0.0026929227,0.0014974913],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8203292,0.0014849586,0.06704596,0.0016567799,0.00028502214,0.00043891958,0.014707188,0.0018089123,0.0033983062],"category_scores_gemma":[0.77793777,0.0004882336,0.033805788,0.0074265623,0.00072563364,0.00035038815,0.0008034364,0.0067558796,0.0013216439],"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":[0.00018014842,0.00023024711,0.03612075,0.000022607264,0.023262283,0.000026817448,0.00027401457,0.033094198,5.194517e-8,0.00085540564,0.90442145,0.0015120503],"study_design_scores_gemma":[0.00027024708,0.00034956055,0.062103707,0.00007564467,0.048245903,0.000022093249,0.00039596853,0.026035583,3.0354567e-8,0.107681096,0.75438994,0.0004302056],"about_ca_topic_score_codex":0.0004931071,"about_ca_topic_score_gemma":0.0038488086,"teacher_disagreement_score":0.16987866,"about_ca_system_score_codex":0.000120538534,"about_ca_system_score_gemma":0.00061926164,"threshold_uncertainty_score":0.99978995},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2803926826","doi":"10.1016/j.jclinepi.2018.04.022","title":"Statistician credit for collaboration requires extending the number of cited authors in research publications","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Impact; St. Joseph’s Healthcare Hamilton; Simon Fraser University; McMaster University","funders":"U.S. National Library of Medicine","keywords":"Statistician; Scopus; Library science; Curriculum; Medical education; MEDLINE; Medicine; Computer science; Political science; Statistics; Mathematics; Law","score_opus":0.9772736588979194,"score_gpt":0.7850173039863724,"score_spread":0.19225635491154702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803926826","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00325922,0.0005287667,0.06336269,0.9266997,0.0033678,0.0010254054,0.00015722771,0.0000017563877,0.0015974467],"genre_scores_gemma":[0.0257683,0.002829156,0.28300452,0.556435,0.07070814,0.00047455725,0.00034935365,0.0001682099,0.06026277],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.43545598,0.42600533,0.126845,0.0018317992,0.008685784,0.0011761009],"domain_scores_gemma":[0.08341009,0.81034195,0.08072365,0.0037999551,0.02146535,0.0002590171],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8224571,0.00028714296,0.012766523,0.0013300779,0.00018922887,0.00024099501,0.0039540334,0.0013507847,0.003965574],"category_scores_gemma":[0.9519541,0.000118832184,0.0033724804,0.0029648612,0.0010520736,0.00030551507,0.00017785872,0.0035769606,0.00025959482],"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":[0.00004059914,0.00003983222,0.043620054,0.00005672309,0.0002474758,0.0000058253527,0.00007491875,0.00001697102,5.773243e-7,0.009342455,0.94256705,0.003987524],"study_design_scores_gemma":[0.00020688999,0.00019935599,0.03154982,0.00013812157,0.00016573242,0.000020055191,0.00017157683,0.0022606286,1.6394935e-7,0.18456703,0.780643,0.000077651974],"about_ca_topic_score_codex":0.000023616432,"about_ca_topic_score_gemma":0.00008008279,"teacher_disagreement_score":0.3843366,"about_ca_system_score_codex":0.00008184902,"about_ca_system_score_gemma":0.0010225364,"threshold_uncertainty_score":0.9999457},"labels":[],"label_agreement":null},{"id":"W2804547333","doi":"10.1016/j.jclinepi.2018.05.010","title":"Health literacy in chronic disease management: a matter of interaction","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":191,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health Research Institute; University of British Columbia; University of Victoria; Vancouver Coastal Health","funders":"","keywords":"Health literacy; Health care; Context (archaeology); Construct (python library); Medicine; Psychological intervention; Literacy; Disease; Health policy; HRHIS; Public relations; Psychology; Public health; Nursing; Political science; Computer science; Pedagogy; Pathology","score_opus":0.30848752863847895,"score_gpt":0.6586244734114906,"score_spread":0.3501369447730116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804547333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9105376,0.000784799,0.023580818,0.049636133,0.006418947,0.00088308775,0.000021107471,0.000016697039,0.008120808],"genre_scores_gemma":[0.94299096,0.0008783735,0.0069840704,0.047186352,0.0016560949,0.00001169226,0.000007691925,0.000009001303,0.0002757596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97419685,0.010510163,0.014451437,0.00019167371,0.00015318138,0.00049670925],"domain_scores_gemma":[0.97732633,0.011625861,0.009687296,0.00036216853,0.0005205276,0.00047780835],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045491166,0.00011918196,0.0016644363,0.00030158553,0.00012670892,0.0000027899425,0.00028689747,0.0002046855,0.0018187216],"category_scores_gemma":[0.0117645385,0.00008468371,0.00028705428,0.00023468096,0.00020182968,0.0008323317,0.00011037114,0.0015331041,0.00040631497],"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":[0.0011325493,0.00014148891,0.88918513,0.0012206165,0.000023943145,0.0000026592907,0.0006139723,0.000015312009,1.9875475e-7,0.002091411,0.017114315,0.08845839],"study_design_scores_gemma":[0.001380459,0.00047418944,0.86341643,0.0012916845,0.000008373702,0.0000026498801,0.00009223125,0.002878558,1.7576023e-7,0.0053817867,0.12502123,0.000052223895],"about_ca_topic_score_codex":0.00008280934,"about_ca_topic_score_gemma":0.000038216134,"teacher_disagreement_score":0.107906915,"about_ca_system_score_codex":0.00031832757,"about_ca_system_score_gemma":0.0009854389,"threshold_uncertainty_score":0.9990938},"labels":[],"label_agreement":null},{"id":"W2804613946","doi":"10.1016/j.jclinepi.2018.04.024","title":"Qualitative research is a fundamental scientific process","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"St. Michael's Hospital; University of Toronto","funders":"University of Toronto","keywords":"Qualitative research; Framing (construction); Epistemology; Engineering ethics; Process (computing); Management science; Sociology; Computer science; Social science; Engineering; Philosophy","score_opus":0.7230013453676123,"score_gpt":0.7349159798712153,"score_spread":0.011914634503602972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804613946","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":[0.954559,0.00043745674,0.0004486114,0.03931487,0.0023378392,0.00016014819,0.0000069526836,0.0000114246795,0.002723682],"genre_scores_gemma":[0.9819022,0.00015794822,0.0051564453,0.0077369027,0.0035050479,0.000003470319,0.0000036580486,0.0000150289425,0.0015193201],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9862063,0.007242086,0.0047296826,0.00046642576,0.0007390014,0.00061652873],"domain_scores_gemma":[0.25246495,0.73463744,0.0036823591,0.0008439964,0.0064432295,0.0019280085],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13043542,0.00013633908,0.002188294,0.0002544143,0.0001930643,0.000019658008,0.000308585,0.00039851578,0.0009670939],"category_scores_gemma":[0.8467732,0.00008830959,0.00071521744,0.000504886,0.0044365553,0.000083344145,0.00009060091,0.0019011538,0.00052518776],"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":[0.004800435,0.0024249768,0.61033505,0.000066731816,0.00046969118,0.0001901092,0.007963952,0.0000014746619,0.000054243596,0.0037191145,0.33190244,0.03807177],"study_design_scores_gemma":[0.011809628,0.035061695,0.5624988,0.005454883,0.0003890969,0.0011151931,0.010029035,0.00073963054,0.0003654684,0.28300044,0.08914131,0.00039483458],"about_ca_topic_score_codex":0.000017817265,"about_ca_topic_score_gemma":0.0000052098453,"teacher_disagreement_score":0.7337413,"about_ca_system_score_codex":0.000055616623,"about_ca_system_score_gemma":0.0012228832,"threshold_uncertainty_score":0.9999462},"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":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2804964104","doi":"10.1016/j.jclinepi.2018.05.011","title":"GRADE guidelines: 20. Assessing the certainty of evidence in the importance of outcomes or values and preferences—inconsistency, imprecision, and other domains","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":288,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; University of Ottawa; University of Calgary; McMaster University; Impact","funders":"Canadian Institutes of Health Research; Arthritis Society; McMaster University","keywords":"Certainty; Grading (engineering); Context (archaeology); Confusion; Population; Psychology; Actuarial science; Medicine; Mathematics; Economics","score_opus":0.9641049926163334,"score_gpt":0.7257662943559037,"score_spread":0.23833869826042975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804964104","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":[0.95968795,0.0039062044,0.006153948,0.029365376,0.000376809,0.000291445,0.0000046171117,6.478598e-7,0.00021298212],"genre_scores_gemma":[0.9696365,0.0012013159,0.021526387,0.007191895,0.00024636654,0.000003353336,9.134756e-8,0.000005260787,0.00018882961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8227887,0.112094104,0.06082199,0.00087700307,0.0030249879,0.00039319377],"domain_scores_gemma":[0.24052699,0.6973947,0.054938614,0.003040186,0.003868439,0.00023103485],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5947376,0.00021848136,0.0076746866,0.000176432,0.00009106653,0.00007477213,0.0018983638,0.0002493845,0.00044757684],"category_scores_gemma":[0.80504674,0.000054361437,0.0014338213,0.0005495357,0.0013667281,0.00021694074,0.000184563,0.0005798736,0.0000057420025],"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":[0.000045563003,0.00003807862,0.9748021,0.000022525322,0.00012889302,0.00000242022,0.0003107444,0.000013326912,0.000007373244,0.00077719474,0.010986136,0.012865673],"study_design_scores_gemma":[0.00031380358,0.00042089215,0.8296962,0.0003301596,0.00021662841,0.00008777204,0.0018702875,0.0019980958,0.0000017419817,0.16033497,0.0046619996,0.00006747704],"about_ca_topic_score_codex":0.000042711476,"about_ca_topic_score_gemma":0.0003004083,"teacher_disagreement_score":0.5853006,"about_ca_system_score_codex":0.00000764574,"about_ca_system_score_gemma":0.00023549741,"threshold_uncertainty_score":0.5246262},"labels":[],"label_agreement":null},{"id":"W2804976203","doi":"10.1016/j.jclinepi.2018.05.009","title":"Applying GRADE to a network meta-analysis of antidepressants led to more conservative conclusions","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"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":"Certainty; Meta-analysis; Grading (engineering); Medicine; Sertraline; Confidence interval; Psychiatry; Antidepressant; Internal medicine; Mathematics","score_opus":0.9587171340199008,"score_gpt":0.7134614192244808,"score_spread":0.24525571479541997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804976203","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":[0.36304274,0.0023083186,0.57014364,0.059169795,0.0018393556,0.0018516115,0.00009186722,0.000005476162,0.0015472033],"genre_scores_gemma":[0.8311719,0.00006473218,0.12857191,0.037972357,0.0008940097,0.000047886708,0.0000025649802,0.000015156033,0.0012594946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8245693,0.10497849,0.065189674,0.0012428508,0.0033866528,0.0006330268],"domain_scores_gemma":[0.48808432,0.43131566,0.0650907,0.0049273046,0.008967917,0.0016141039],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.56671786,0.00038546062,0.041129027,0.001022551,0.00017446188,0.000062938765,0.0030295802,0.00030173775,0.008312772],"category_scores_gemma":[0.7242529,0.00016594691,0.021695783,0.005073949,0.00047001155,0.00014884428,0.0005853583,0.0005971575,0.0004999236],"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":[0.00018108895,0.00016608112,0.5372363,0.0000099784365,0.16152094,0.000018325036,0.00040996,0.017434463,0.00003638197,0.0037786204,0.2752537,0.0039541856],"study_design_scores_gemma":[0.0005847627,0.0012626594,0.47393277,0.000050508657,0.22474498,0.000033774126,0.0006166126,0.022989053,0.000011188658,0.027936053,0.24745974,0.00037790558],"about_ca_topic_score_codex":0.000039760052,"about_ca_topic_score_gemma":0.00011718959,"teacher_disagreement_score":0.46812913,"about_ca_system_score_codex":0.000017914015,"about_ca_system_score_gemma":0.00019244479,"threshold_uncertainty_score":0.99259377},"labels":[],"label_agreement":null},{"id":"W2806287770","doi":"10.1016/j.jclinepi.2018.05.023","title":"Pre-specification of statistical analysis approaches in published clinical trial protocols was inadequate","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":39,"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":"National Institute for Health and Care Research","keywords":"Protocol (science); Missing data; Covariate; Medicine; Statistical analysis; Randomized controlled trial; Population; Outcome (game theory); Clinical trial; Computer science; Data mining; Statistics; Medical physics; Alternative medicine; Machine learning; Surgery; Internal medicine; Pathology; Mathematics","score_opus":0.9655258436062034,"score_gpt":0.7174035722570627,"score_spread":0.24812227134914067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806287770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36077055,0.000100750265,0.62495065,0.0049797962,0.001252022,0.0059062294,0.000014803771,0.0000027201875,0.0020225118],"genre_scores_gemma":[0.8940292,0.000049753584,0.10232541,0.0006139845,0.0023217804,0.00020847353,0.000008379409,0.000012717939,0.00043028875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.45326945,0.31149644,0.22560011,0.0024132235,0.0062897373,0.0009310484],"domain_scores_gemma":[0.33454582,0.52278465,0.12979181,0.005673367,0.0061514024,0.0010529778],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.842193,0.0003225154,0.023157256,0.0014031066,0.000052239244,0.00013816037,0.0030858766,0.0007571274,0.0048684794],"category_scores_gemma":[0.8970345,0.00015088468,0.008001314,0.0031964744,0.0012194135,0.00038470587,0.00020204947,0.0014367861,0.00023421644],"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":[0.010786428,0.001046914,0.8461489,0.000026139727,0.0014601789,0.000009625644,0.0000832058,0.00013811035,7.5868724e-7,0.018254552,0.022994777,0.09905042],"study_design_scores_gemma":[0.008208427,0.0028121423,0.866833,0.000039705887,0.00091196893,0.0000097561515,0.000093090464,0.018936915,0.000001766607,0.07863607,0.023373764,0.00014344121],"about_ca_topic_score_codex":0.00001635606,"about_ca_topic_score_gemma":0.00011095797,"teacher_disagreement_score":0.5332587,"about_ca_system_score_codex":0.00003861837,"about_ca_system_score_gemma":0.00047238226,"threshold_uncertainty_score":0.9960412},"labels":[],"label_agreement":null},{"id":"W2806693647","doi":"10.1016/j.jclinepi.2018.05.022","title":"Abbreviated literature searches were viable alternatives to comprehensive searches: a meta-epidemiological study","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":70,"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; Institute of Health Economics","funders":"University of California, San Francisco","keywords":"MEDLINE; Confidence interval; Medicine; Meta-analysis; Systematic review; Certainty; Internal medicine; Mathematics","score_opus":0.9826878418431775,"score_gpt":0.753594695635839,"score_spread":0.22909314620733845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806693647","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055069436,0.98413384,0.0059690867,0.0030691167,0.0021863189,0.0035417865,0.00012586366,0.000010332171,0.00041293478],"genre_scores_gemma":[0.00008334019,0.9605557,0.027236177,0.0039267633,0.003424318,0.00013847173,0.00002486074,0.00006760614,0.0045428122],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.25772205,0.60021317,0.13076161,0.0037502802,0.006120206,0.0014326867],"domain_scores_gemma":[0.13304298,0.72653204,0.11748545,0.0080016805,0.012255549,0.0026822782],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8088026,0.0021943091,0.15911937,0.0020017636,0.0002591267,0.0005766967,0.0110192355,0.0019939616,0.008911789],"category_scores_gemma":[0.8918397,0.0007545277,0.061884247,0.00369673,0.00089724787,0.00039737456,0.0016414041,0.006480598,0.006489542],"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":[0.00019032076,0.0013606218,0.0072687445,0.003496507,0.054568205,0.00045751757,0.0003999478,0.00010601979,6.749743e-8,0.0009292952,0.46948904,0.46173373],"study_design_scores_gemma":[0.00040957093,0.0031676423,0.0014983721,0.004034011,0.013742533,0.0003771817,0.00026048467,0.00012574867,1.9377795e-8,0.009739242,0.96613073,0.0005144856],"about_ca_topic_score_codex":0.000015362955,"about_ca_topic_score_gemma":0.000013480254,"teacher_disagreement_score":0.49664167,"about_ca_system_score_codex":0.00014129681,"about_ca_system_score_gemma":0.0010021732,"threshold_uncertainty_score":0.99949056},"labels":[],"label_agreement":null},{"id":"W2807551231","doi":"10.1016/j.jclinepi.2018.05.025","title":"Bayesian synthesis using prior information on fracture risk from randomized trials to analyze post-market data","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bone health and osteoporosis research","field":"Medicine","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":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; The Scarborough Hospital; Women's College Hospital; Impact; Institute for Clinical Evaluative Sciences; Western University","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Bayesian probability; Fracture (geology); Econometrics; Statistics; Medicine; Computer science; Mathematics; Internal medicine; Engineering","score_opus":0.35370167861953034,"score_gpt":0.575651415093432,"score_spread":0.22194973647390165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807551231","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":[0.7962488,0.0006409638,0.08882588,0.10902742,0.0023224212,0.0017869289,0.000410679,0.000023692559,0.00071319734],"genre_scores_gemma":[0.82470906,0.0025487037,0.08796256,0.07699024,0.007636158,0.00000930002,0.00007369663,0.000027773845,0.000042509648],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.95825,0.029841317,0.010494993,0.0003507569,0.00053762115,0.00052535493],"domain_scores_gemma":[0.35515705,0.61837196,0.017853266,0.0025765582,0.0028388952,0.003202263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20229158,0.00021206416,0.0076027554,0.0003968605,0.00013446527,0.000019138088,0.00049898686,0.0006624582,0.0017525484],"category_scores_gemma":[0.8750575,0.00012135623,0.001015074,0.0002126657,0.00033824795,0.0003304126,0.00014512039,0.0016962421,0.00011449002],"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":[0.5813485,0.00029138286,0.048278973,0.0000638001,0.001135974,0.000024872714,0.0001225506,0.000053669217,0.000026591131,0.000015979092,0.08936156,0.2792762],"study_design_scores_gemma":[0.18753329,0.0072312765,0.60442525,0.0016204927,0.0037167033,0.00018000205,0.00025017306,0.06531773,0.00010987582,0.0032672693,0.12592052,0.00042745387],"about_ca_topic_score_codex":0.0009701138,"about_ca_topic_score_gemma":0.00005221592,"teacher_disagreement_score":0.672766,"about_ca_system_score_codex":0.0000724678,"about_ca_system_score_gemma":0.0010717718,"threshold_uncertainty_score":0.99916},"labels":[],"label_agreement":null},{"id":"W2808772167","doi":"10.1016/j.jclinepi.2018.06.004","title":"GRADE weak or conditional recommendations mandate shared decision-making. Author Response","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; Impact","funders":"","keywords":"Scopus; Mandate; Presentation (obstetrics); Psychology; Position (finance); Medicine; MEDLINE; Family medicine; Medical education; Political science; Business; Surgery","score_opus":0.6877842005872862,"score_gpt":0.666222613498353,"score_spread":0.021561587088933187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808772167","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":[0.003733209,0.00012435025,0.033830076,0.9533053,0.007828297,0.0005321638,0.00049748074,0.000038229744,0.000110902874],"genre_scores_gemma":[0.0018439115,0.0005605033,0.15458843,0.8062466,0.033032924,0.000017040062,0.0009013081,0.00009353594,0.0027157627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.957991,0.017797438,0.021566493,0.00088660687,0.0009675408,0.0007908955],"domain_scores_gemma":[0.48954034,0.4892704,0.017342716,0.00095360493,0.0023272566,0.00056570506],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.087100685,0.0005466419,0.0054380554,0.00068438076,0.00018401278,0.000035666788,0.0007078495,0.0028691262,0.014777239],"category_scores_gemma":[0.7610991,0.00037592478,0.0021616344,0.00033910063,0.0007701839,0.0003739479,0.00025351872,0.009169686,0.00062083855],"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":[0.024283016,0.00031298972,0.004695067,0.00005513861,0.0008241005,0.001221345,0.000015576792,0.000007727554,0.000002108163,0.000041478495,0.9445915,0.023949929],"study_design_scores_gemma":[0.004797801,0.004984067,0.045503803,0.0013793922,0.0012127004,0.003703029,0.00004222157,0.00037567402,4.7769134e-7,0.020416752,0.91727614,0.00030793843],"about_ca_topic_score_codex":0.000010700048,"about_ca_topic_score_gemma":0.000021934497,"teacher_disagreement_score":0.6739984,"about_ca_system_score_codex":0.00026795518,"about_ca_system_score_gemma":0.002998392,"threshold_uncertainty_score":0.9998693},"labels":[],"label_agreement":null},{"id":"W2809161050","doi":"10.1016/j.jclinepi.2018.06.003","title":"Existing evidence summarization methods cannot guarantee trustworthy patient decision aids","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":12,"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":"Newcastle University; Ottawa Hospital Research Institute","keywords":"Automatic summarization; Decision aids; Trustworthiness; Evidence-based medicine; Process (computing); Knowledge management; Evidence-based practice; MEDLINE; Psychology; Medicine; Computer science; Alternative medicine; Social psychology; Information retrieval; Political science","score_opus":0.8155057381139007,"score_gpt":0.6918002732062957,"score_spread":0.12370546490760503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809161050","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66426516,0.010972376,0.27850962,0.01923739,0.023325277,0.0012845687,0.000015083143,0.000096553485,0.0022939963],"genre_scores_gemma":[0.54965794,0.0020435266,0.43354174,0.012122023,0.0024837102,0.000028732722,0.0000053718745,0.000032729007,0.000084255684],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9282749,0.0571296,0.012884718,0.0004765794,0.0004295681,0.0008046171],"domain_scores_gemma":[0.64357454,0.33356738,0.015859555,0.0015948472,0.004746947,0.00065675145],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050069746,0.0002627545,0.0025202709,0.00029265895,0.0008558777,0.0000060252596,0.0009929185,0.00090120145,0.000368435],"category_scores_gemma":[0.5321016,0.00019796581,0.0005455953,0.00051339064,0.0005714333,0.00038667992,0.00051768793,0.0032683418,0.00015373288],"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":[0.0011553481,0.00008431851,0.5715654,0.0000759732,0.000053564065,0.000004948682,0.001543993,0.00008235826,0.000017967715,0.0036751386,0.007898462,0.41384253],"study_design_scores_gemma":[0.0039593424,0.010639464,0.45124874,0.007762951,0.00023604612,0.000080621445,0.0047299853,0.014914974,0.000037512553,0.12463698,0.38109937,0.00065402925],"about_ca_topic_score_codex":0.0003474308,"about_ca_topic_score_gemma":0.00019065096,"teacher_disagreement_score":0.4820318,"about_ca_system_score_codex":0.00027816024,"about_ca_system_score_gemma":0.0014885297,"threshold_uncertainty_score":0.9990312},"labels":[],"label_agreement":null},{"id":"W2810434445","doi":"10.1016/j.jclinepi.2018.06.011","title":"Improving the conduct of systematic reviews: a process mining perspective","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"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; Toronto Metropolitan University; St. Michael's Hospital","funders":"Medical Research Council; National Health and Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Timeline; Process (computing); Event (particle physics); Systematic review; Computer science; Process mining; Data science; Perspective (graphical); Statistics; Work in process; MEDLINE; Artificial intelligence; Operations management; Mathematics; Engineering; Business process management","score_opus":0.9607683171473247,"score_gpt":0.7224262828857378,"score_spread":0.23834203426158684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810434445","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7436895,0.059063107,0.14718951,0.02805139,0.007309074,0.0049105035,0.0000088438,0.0000067577007,0.009771319],"genre_scores_gemma":[0.9789376,0.00038471297,0.01513656,0.0032480776,0.0014846149,0.000018990455,1.2778929e-7,0.000010966148,0.00077829737],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6379638,0.2507846,0.10674555,0.00092730235,0.0031226226,0.00045612655],"domain_scores_gemma":[0.071109034,0.6661058,0.23938091,0.00549794,0.01726787,0.0006384153],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80061394,0.00026158904,0.022184728,0.0002443463,0.000113125214,0.000068170724,0.003126559,0.00021381422,0.0014391277],"category_scores_gemma":[0.9702465,0.000080378304,0.006491867,0.00086780376,0.0007508019,0.00021759504,0.00012810336,0.0006269876,0.00023047609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006059797,0.0010193477,0.43375552,0.026216056,0.0077232234,0.000055564662,0.018454596,0.00022972375,0.00024364339,0.07483375,0.36946505,0.06739755],"study_design_scores_gemma":[0.006106984,0.015357996,0.078439824,0.053325716,0.018559325,0.003961297,0.14553437,0.11482844,0.00014060352,0.47797236,0.08355951,0.0022135926],"about_ca_topic_score_codex":0.0000093626595,"about_ca_topic_score_gemma":0.000010617398,"teacher_disagreement_score":0.5668548,"about_ca_system_score_codex":0.00002757913,"about_ca_system_score_gemma":0.00035325266,"threshold_uncertainty_score":0.9994737},"labels":[],"label_agreement":null},{"id":"W2811148777","doi":"10.1016/j.jclinepi.2018.06.008","title":"GRADEing the un-GRADE-able: a description of challenges in applying GRADE methods to the ethical and implementation questions of pediatric organ donation guidelines","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Palliative Care and End-of-Life Issues","field":"Medicine","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":"Impact; McGill University; McGill University Health Centre; Montreal Children's Hospital; Canadian Blood Services; Université Laval; McMaster University; Université du Québec à Montréal","funders":"","keywords":"Guideline; Context (archaeology); Variety (cybernetics); Organ donation; Medicine; Donation; Medical education; Psychology; Computer science; Transplantation; Political science; Surgery; Pathology","score_opus":0.757594727477652,"score_gpt":0.6564368736374373,"score_spread":0.1011578538402147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811148777","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":[0.038015604,0.015539774,0.028966438,0.9160327,0.00090707,0.0005006151,0.00001373235,0.0000052232426,0.000018890607],"genre_scores_gemma":[0.062470246,0.23827545,0.37621775,0.30151305,0.02128427,0.000072521216,0.00006980307,0.000070911345,0.000026008265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9842465,0.008850869,0.0059385384,0.00029241704,0.00039963887,0.00027202448],"domain_scores_gemma":[0.95392114,0.039634448,0.004809782,0.00030110442,0.0012392396,0.0000942986],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03955225,0.00021877515,0.0023361028,0.0004048575,0.00005607508,0.0000036370043,0.00028647893,0.0011298747,0.000018052973],"category_scores_gemma":[0.09253584,0.00011943992,0.00040768788,0.00036158893,0.0003629295,0.000059877173,0.00008825388,0.0030552275,5.0455213e-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":[0.00061794,0.00027514386,0.410255,0.0015904636,0.0011588624,0.00004693821,0.0049086493,0.00013618128,0.00050526153,0.0024384107,0.41901666,0.15905048],"study_design_scores_gemma":[0.00415455,0.0043612258,0.36172292,0.0035299454,0.0029820495,0.00025948006,0.0037475678,0.0007511606,0.00042699598,0.040078066,0.5775687,0.00041733586],"about_ca_topic_score_codex":0.00022680685,"about_ca_topic_score_gemma":0.00013691366,"teacher_disagreement_score":0.6145196,"about_ca_system_score_codex":0.00004898212,"about_ca_system_score_gemma":0.000231407,"threshold_uncertainty_score":0.99924475},"labels":[],"label_agreement":null},{"id":"W2883658233","doi":"10.1016/j.jclinepi.2018.07.008","title":"Guidance was developed on how to write a plain language summary for diagnostic test accuracy reviews","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Department of Health and Social Care; National Institute for Health and Care Research; University Hospitals Bristol NHS Foundation Trust","keywords":"Plain language; Test (biology); Plain English; Focus (optics); English language; Computer science; Medicine; Medical physics; Psychology; Linguistics","score_opus":0.8880122351017804,"score_gpt":0.6755900331049229,"score_spread":0.21242220199685746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883658233","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":[0.19792818,0.022589175,0.52144396,0.23938438,0.008185403,0.0049274736,0.00012421684,0.000014552506,0.005402671],"genre_scores_gemma":[0.2867729,0.0070497096,0.529949,0.13432573,0.014424592,0.00020338182,0.000012789074,0.00007425956,0.027187606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8837555,0.06535178,0.04737243,0.0011455195,0.00174534,0.0006294406],"domain_scores_gemma":[0.028515806,0.9256209,0.039088096,0.0029911571,0.0029547124,0.0008293013],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.631438,0.00036633568,0.01445315,0.0003405921,0.00013412784,0.00014086763,0.0027999075,0.00029562172,0.0013309196],"category_scores_gemma":[0.99394816,0.0001576379,0.004849978,0.0007899418,0.00021103767,0.00021093823,0.00017839864,0.0006027794,0.0029605783],"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":[0.000085830805,0.00009719836,0.06374464,0.000038008704,0.00010393274,0.000014975204,0.00009269624,0.000009883546,0.000016036023,0.0006191731,0.7726004,0.16257723],"study_design_scores_gemma":[0.0004692643,0.0014677091,0.064534724,0.0004897589,0.00016590414,0.000039616985,0.00007984039,0.00060453074,0.000007695868,0.00591148,0.9260605,0.0001689631],"about_ca_topic_score_codex":0.0000031210745,"about_ca_topic_score_gemma":0.000058295966,"teacher_disagreement_score":0.8602691,"about_ca_system_score_codex":0.000036813537,"about_ca_system_score_gemma":0.00022032515,"threshold_uncertainty_score":0.999582},"labels":[],"label_agreement":null},{"id":"W2883972376","doi":"10.1016/j.jclinepi.2018.07.009","title":"The Consensus on Exercise Reporting Template (CERT) applied to exercise interventions in musculoskeletal trials demonstrated good rater agreement and incomplete reporting","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiovascular and exercise physiology","field":"Medicine","cited_by":55,"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 de l'Université Laval","funders":"National Institute for Health and Care Research","keywords":"Physical therapy; Psychological intervention; Cohen's kappa; Medicine; Statistic; Physical medicine and rehabilitation; Computer science; Statistics; Psychiatry","score_opus":0.41261459109287957,"score_gpt":0.5395309091082204,"score_spread":0.12691631801534087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883972376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9896524,0.0007590771,0.00070709124,0.0057739057,0.00123357,0.0008987906,0.0000028243956,0.000016593323,0.00095576915],"genre_scores_gemma":[0.9936243,0.0008672498,0.0036169782,0.000772193,0.0009789708,0.000030169072,0.000005755197,0.000024020932,0.00008034617],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9728514,0.0032931434,0.022455601,0.0005444514,0.00027049772,0.00058491103],"domain_scores_gemma":[0.952979,0.018898677,0.025888735,0.00087684067,0.000667431,0.000689262],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11713986,0.00028144618,0.006333296,0.0002517912,0.00019024368,0.000016872968,0.00017392403,0.00034518458,0.00004729913],"category_scores_gemma":[0.18562795,0.0001656745,0.002400529,0.00024876464,0.0005676985,0.000031780986,0.00016996289,0.001096244,0.000030160938],"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":[0.058718655,0.0013152311,0.1558197,0.00063779514,0.0030853683,0.0021619976,0.00045124468,0.00056957855,0.0049033207,0.0010303775,0.016372046,0.75493467],"study_design_scores_gemma":[0.009419488,0.0048773764,0.963262,0.00458507,0.0018658659,0.0022439908,0.0006074465,0.00053945405,0.00075743155,0.007973,0.0034335237,0.00043535046],"about_ca_topic_score_codex":0.00006871262,"about_ca_topic_score_gemma":0.000058341022,"teacher_disagreement_score":0.8074423,"about_ca_system_score_codex":0.000059407143,"about_ca_system_score_gemma":0.00021619652,"threshold_uncertainty_score":0.9090903},"labels":[],"label_agreement":null},{"id":"W2886882810","doi":"10.1016/j.jclinepi.2018.08.006","title":"A digital media strategy to obtain unpublished data for a systematic review yields a very high author response rate","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; McGill University","funders":"Canadian Institutes of Health Research; Consortium canadien en neurodégénérescence associée au vieillissement","keywords":"Computer science; Medicine; Information retrieval; Data science","score_opus":0.9519682119304014,"score_gpt":0.710750143352982,"score_spread":0.24121806857741934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886882810","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008058355,0.9490998,0.0322523,0.008186543,0.00307417,0.0061810873,0.0010955079,0.0000070010196,0.000095552685],"genre_scores_gemma":[0.000008854169,0.97612196,0.009870154,0.0055196467,0.0026195617,0.00023543127,0.00020029544,0.00007694219,0.005347126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.16615207,0.5920174,0.23058416,0.00421108,0.0056344564,0.0014008307],"domain_scores_gemma":[0.013505019,0.81257427,0.15040389,0.015384682,0.006329396,0.0018027327],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.9265431,0.0013355565,0.118625395,0.0013370259,0.00013336915,0.0010526178,0.017382255,0.0016233596,0.0017061371],"category_scores_gemma":[0.99253064,0.0005283472,0.023213206,0.0026127517,0.00035759812,0.0010111433,0.0013802721,0.0020879835,0.0031369242],"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":[0.0002322165,0.00009711589,0.000010465651,0.21529418,0.0022192597,0.0000461607,0.0000086588525,0.0000018129683,3.4227625e-9,0.00039904856,0.6898437,0.09184738],"study_design_scores_gemma":[0.0002401339,0.0009376106,0.000029750143,0.26265678,0.00932767,0.00031017378,0.000027917771,0.00015615922,9.71614e-10,0.005173702,0.7207867,0.00035344603],"about_ca_topic_score_codex":0.0000025167737,"about_ca_topic_score_gemma":0.0000110180645,"teacher_disagreement_score":0.22055689,"about_ca_system_score_codex":0.000121004035,"about_ca_system_score_gemma":0.003420321,"threshold_uncertainty_score":0.9999844},"labels":[],"label_agreement":null},{"id":"W2888184468","doi":"10.1016/j.jclinepi.2018.08.014","title":"Certainty ranges facilitated explicit and transparent judgments regarding evidence credibility","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Sigrid Juséliuksen Säätiö; Jane ja Aatos Erkon Säätiö","keywords":"Certainty; Confidence interval; Medicine; Grading (engineering); Cystectomy; Actuarial science; Surgery; Internal medicine; Bladder cancer; Cancer; Mathematics","score_opus":0.5661620735335602,"score_gpt":0.547328997699373,"score_spread":0.01883307583418714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888184468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96798617,0.0021546497,0.0047695446,0.023255976,0.001063553,0.0002927706,0.000003937859,0.000017300641,0.00045611727],"genre_scores_gemma":[0.9823993,0.0077132434,0.0032480422,0.005528314,0.0010241792,0.0000056137633,0.0000015115799,0.0000104377195,0.00006938563],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935774,0.0020252692,0.0033948426,0.0003843567,0.00024402472,0.0003741004],"domain_scores_gemma":[0.98395336,0.013351019,0.0013638688,0.00037081615,0.00044939647,0.00051153643],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022631632,0.00017711136,0.0028675364,0.00010117061,0.000077988254,0.000006677594,0.00017408389,0.00022934953,0.0002136246],"category_scores_gemma":[0.053178247,0.00011905333,0.0004940119,0.00009610046,0.000465655,0.00013470785,0.00007400638,0.0005748139,0.000019036594],"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":[0.002783248,0.0009421234,0.8945583,0.00032203534,0.00088985835,0.0000849437,0.00050354993,0.00004115317,0.00029419136,0.0009105841,0.031619135,0.067050874],"study_design_scores_gemma":[0.002500785,0.004898075,0.9718243,0.00080925866,0.0004119756,0.00007913825,0.0001858185,0.0005832274,0.00009212072,0.0030424579,0.015454526,0.00011835838],"about_ca_topic_score_codex":0.00007052485,"about_ca_topic_score_gemma":0.000023032451,"teacher_disagreement_score":0.077265956,"about_ca_system_score_codex":0.000053616677,"about_ca_system_score_gemma":0.00009672107,"threshold_uncertainty_score":0.9547972},"labels":[],"label_agreement":null},{"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":"W2888230474","doi":"10.1016/j.jclinepi.2018.08.007","title":"Subgroup analyses are seldom possible and subgroup effects are rare in Cochrane HIV systematic reviews","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Ontario HIV Treatment Network; Population Health Research Institute; St. Joseph’s Healthcare Hamilton; Impact","funders":"","keywords":"Systematic review; Subgroup analysis; Meta-analysis; Study heterogeneity; Medicine; Generalizability theory; MEDLINE; Publication bias; Statistics; Internal medicine; Mathematics; Biology","score_opus":0.29050822245373664,"score_gpt":0.5208990976662901,"score_spread":0.23039087521255341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888230474","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":[0.109026775,0.25034782,0.0011040312,0.6274016,0.0059336256,0.0053861924,0.00041866678,0.000108837856,0.00027245018],"genre_scores_gemma":[0.014426681,0.052234206,0.004064366,0.90639013,0.0210622,0.00010835763,0.00049035024,0.0001863798,0.0010373439],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9572519,0.026911821,0.013265458,0.0010028636,0.00065657636,0.00091139105],"domain_scores_gemma":[0.88770586,0.08919263,0.019970052,0.0015575117,0.000803505,0.0007704362],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.038921144,0.00083046884,0.022356395,0.0006619338,0.00006239322,0.000026787426,0.00073188334,0.0023276717,0.00015769919],"category_scores_gemma":[0.3166293,0.00053017307,0.0023100297,0.0004417824,0.00075786316,0.00017646974,0.00021392564,0.0059371567,0.00019321655],"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":[0.0004405601,0.00012427199,0.31856513,0.06867583,0.00062170153,0.005228426,0.00001642166,0.0000016950244,0.000002663669,0.0000021215085,0.6061805,0.0001406844],"study_design_scores_gemma":[0.0070052897,0.0021325054,0.6405303,0.19862154,0.0037755526,0.0029168855,0.000053875476,0.00027628592,0.0000022256095,0.00068483123,0.14318113,0.0008196157],"about_ca_topic_score_codex":0.000024980705,"about_ca_topic_score_gemma":0.000058524056,"teacher_disagreement_score":0.46299937,"about_ca_system_score_codex":0.00016058344,"about_ca_system_score_gemma":0.00031839192,"threshold_uncertainty_score":0.999715},"labels":[],"label_agreement":null},{"id":"W2890588440","doi":"10.1016/j.jclinepi.2018.08.019","title":"Lack of transparency in reporting narrative synthesis of quantitative data: a methodological assessment of systematic reviews","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":162,"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; McMaster University","keywords":"Transparency (behavior); Systematic review; Narrative review; Medicine; Narrative; MEDLINE; Accounting; Computer science; Political science; Business; Intensive care medicine; Computer security","score_opus":0.9948432497923828,"score_gpt":0.8785193252618085,"score_spread":0.11632392453057427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890588440","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8232793,0.0006339999,0.15252188,0.01785057,0.0016959431,0.0028182834,0.00010068251,0.000006738707,0.0010925892],"genre_scores_gemma":[0.7302659,0.0012048025,0.26596618,0.0023172877,0.00018625059,0.000040487812,0.0000011508943,0.0000069971293,0.000010919166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.73807424,0.18579124,0.0743195,0.0005258028,0.0006056252,0.00068357924],"domain_scores_gemma":[0.11823163,0.7336804,0.14412221,0.0012185938,0.002357449,0.00038968035],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47365928,0.00015490851,0.009008804,0.0002630843,0.00008387026,6.985662e-7,0.00082843605,0.00033536667,0.00026018775],"category_scores_gemma":[0.8964843,0.00009375927,0.00040716803,0.000539617,0.00088954874,0.00021134455,0.00014845736,0.00113627,0.000005182551],"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":[0.00034434226,0.0003094539,0.9365078,0.034405395,0.00018102898,0.000009182215,0.013522538,0.000028122535,0.00033328988,0.010073861,0.0029727018,0.0013122435],"study_design_scores_gemma":[0.0016774476,0.00413722,0.92712444,0.03388321,0.00027816926,0.000023630908,0.019000242,0.0025082014,0.00006804107,0.010305313,0.00081060565,0.00018349526],"about_ca_topic_score_codex":0.0002003271,"about_ca_topic_score_gemma":0.00022318172,"teacher_disagreement_score":0.61984265,"about_ca_system_score_codex":0.000075040116,"about_ca_system_score_gemma":0.0018917596,"threshold_uncertainty_score":0.61582386},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"systematic_review","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2892770417","doi":"10.1016/j.jclinepi.2018.09.007","title":"Evidence to Decision framework provides a structured “roadmap” for making GRADE guidelines recommendations","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","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":"Impact; McMaster University; University of Toronto","funders":"Agency for Healthcare Research and Quality","keywords":"MEDLINE; Medicine; Management science; Political science; Engineering","score_opus":0.604018241002391,"score_gpt":0.6262422499171987,"score_spread":0.02222400891480769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892770417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15514164,0.0012063264,0.5652601,0.2722517,0.005108542,0.00091999274,0.0000060907178,0.000024974437,0.00008063695],"genre_scores_gemma":[0.3254109,0.0016210013,0.6182966,0.0494924,0.0050955536,0.000020591877,0.0000015292478,0.000018859504,0.000042538173],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99340844,0.0008005039,0.0048079477,0.0003627752,0.00022596524,0.00039439034],"domain_scores_gemma":[0.9513283,0.043723542,0.0024440025,0.0004846461,0.0015773431,0.0004421898],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018627752,0.00017990483,0.002362605,0.00020878835,0.00012617376,0.000014852177,0.00033274622,0.0003197679,0.00023456548],"category_scores_gemma":[0.39712638,0.00012132978,0.0006916108,0.00020482189,0.00016246473,0.00012575739,0.00013244174,0.0005298426,0.000027182157],"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":[0.0014045106,0.00032454918,0.047207583,0.00007712032,0.00032511022,0.000012149696,0.00013947589,0.00010931505,0.00005050337,0.008453569,0.49421042,0.4476857],"study_design_scores_gemma":[0.0015728287,0.009004892,0.34394702,0.0062286668,0.00061117706,0.00012459075,0.00014368932,0.0013152482,0.00004687405,0.20864603,0.42813584,0.00022311562],"about_ca_topic_score_codex":0.00001066611,"about_ca_topic_score_gemma":0.000036929807,"teacher_disagreement_score":0.4474626,"about_ca_system_score_codex":0.000058301506,"about_ca_system_score_gemma":0.00022460299,"threshold_uncertainty_score":0.64560443},"labels":[],"label_agreement":null},{"id":"W2893541797","doi":"10.1016/j.jclinepi.2018.09.008","title":"Multimorbidity and comorbidity revisited: refining the concepts for international health research","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":139,"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; Western University; McMaster University","funders":"","keywords":"Comorbidity; Relevance (law); Multimorbidity; MEDLINE; Medicine; Health care; Qualitative research; Gerontology; Family medicine; Psychiatry; Sociology; Social science; Political science","score_opus":0.7790185430529262,"score_gpt":0.6893093930064565,"score_spread":0.08970915004646962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893541797","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":[0.4106466,0.004109455,0.014150069,0.55166924,0.007498218,0.0009669194,0.000044847235,0.00003734,0.010877356],"genre_scores_gemma":[0.96132845,0.0037150285,0.010612231,0.015329832,0.008449764,0.0000075039384,0.000014670493,0.000013918523,0.00052859646],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9934319,0.003236849,0.0024460354,0.00024275901,0.00029096578,0.0003514806],"domain_scores_gemma":[0.95867383,0.037308924,0.0018304711,0.00034276425,0.0014682345,0.0003757775],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06529172,0.00009385926,0.0011586886,0.00009855022,0.00017217168,0.000014015138,0.00026944384,0.00012102858,0.00019268772],"category_scores_gemma":[0.1486171,0.00005521206,0.00028647308,0.00009662125,0.0014189555,0.00007865364,0.00015544397,0.00090197095,0.000011506892],"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":[0.0020200908,0.00026802198,0.22909896,0.0001722179,0.00043341485,0.00002118764,0.000112481546,0.000006565361,0.000006582446,0.027162848,0.63135433,0.10934327],"study_design_scores_gemma":[0.0027969184,0.0025796834,0.5194222,0.00025922104,0.000054674943,0.000063850894,0.00019440416,0.0021988733,0.0000013235303,0.008846446,0.4635337,0.0000487284],"about_ca_topic_score_codex":0.000056073106,"about_ca_topic_score_gemma":0.000022175449,"teacher_disagreement_score":0.5506819,"about_ca_system_score_codex":0.00007950859,"about_ca_system_score_gemma":0.00047571567,"threshold_uncertainty_score":0.9624789},"labels":[],"label_agreement":null},{"id":"W2894278684","doi":"10.1016/j.jclinepi.2018.08.022","title":"GRADE approach to rate the certainty from a network meta-analysis: avoiding spurious judgments of imprecision in sparse networks","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":171,"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; Schwartz/Reisman Emergency Medicine Institute; University of Toronto; McMaster University; Impact","funders":"","keywords":"Confidence interval; Spurious relationship; Meta-analysis; Credible interval; Econometrics; Counterintuitive; Statistics; Coverage probability; Bayesian probability; Sensitivity (control systems); Computer science; Prior probability; Bayes' theorem; Nominal level; Mathematics; Medicine","score_opus":0.9391914965285129,"score_gpt":0.6436390537593569,"score_spread":0.29555244276915593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894278684","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":[0.28303123,0.0060726884,0.70082194,0.0066961017,0.0017647184,0.0007455515,0.0000116815045,0.00000234427,0.00085377065],"genre_scores_gemma":[0.9564528,0.00024415698,0.035961732,0.0055437763,0.001460917,0.000013732934,0.0000029919888,0.000012520686,0.00030735886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.5650221,0.33938697,0.088887155,0.0018789058,0.0038125021,0.001012383],"domain_scores_gemma":[0.54611146,0.38865796,0.057309866,0.004946378,0.0022653402,0.0007090193],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7413326,0.00042592647,0.02846349,0.00059714826,0.00015579865,0.00011345578,0.003907492,0.0004361213,0.0022532921],"category_scores_gemma":[0.49716833,0.00015512227,0.018172784,0.003599832,0.00035150998,0.00016625947,0.00042605287,0.001452221,0.00020296325],"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":[0.00047452416,0.00045274198,0.34269947,0.000008121308,0.091554224,0.000013920331,0.0003932258,0.44317067,0.0000052420305,0.0019163592,0.11155388,0.0077576144],"study_design_scores_gemma":[0.0009200967,0.0007324917,0.33086884,0.000043657663,0.09708286,0.000021218166,0.00044032952,0.4225249,0.0000025465586,0.12596396,0.021058388,0.00034069482],"about_ca_topic_score_codex":0.00014373421,"about_ca_topic_score_gemma":0.00031031854,"teacher_disagreement_score":0.6734216,"about_ca_system_score_codex":0.00003175958,"about_ca_system_score_gemma":0.00010644882,"threshold_uncertainty_score":0.9986588},"labels":[],"label_agreement":null},{"id":"W2894406111","doi":"10.1016/j.jclinepi.2018.09.014","title":"The reporting of safety among drug systematic reviews was poor before the implementation of the PRISMA harms checklist","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"National Natural Science Foundation of China","keywords":"Checklist; Systematic review; Medicine; Drug; MEDLINE; Pharmacology; Psychology; Biology","score_opus":0.8130479154582703,"score_gpt":0.6603973242837804,"score_spread":0.15265059117448987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894406111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91712743,0.0064036897,0.011545022,0.055466533,0.004303642,0.0037876943,0.000008969215,0.0000022530005,0.0013547812],"genre_scores_gemma":[0.9928719,0.0007237441,0.0023501026,0.0014055236,0.0008406205,0.00002122547,6.021281e-7,0.000010320323,0.0017759842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.48894164,0.24673638,0.25846222,0.00081824,0.004457064,0.0005844728],"domain_scores_gemma":[0.20607997,0.24072945,0.54138917,0.005931894,0.005603518,0.00026599946],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8474528,0.00024958566,0.013869745,0.000090739835,0.00034448734,0.00006840273,0.0035000748,0.00015006603,0.0006009919],"category_scores_gemma":[0.8685938,0.000059809907,0.007970419,0.0007629357,0.0010823461,0.00013232017,0.00029153947,0.0006795839,0.000060433307],"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":[0.000038165046,0.00004973015,0.88506263,0.0013011657,0.0007953186,0.000001621104,0.0011828014,0.000020708696,0.000011600468,0.0038181886,0.07476068,0.032957375],"study_design_scores_gemma":[0.0004582704,0.0003503729,0.88792163,0.002593862,0.0015667692,0.00012038539,0.005178663,0.002545718,0.00003940799,0.031999595,0.06710908,0.0001162727],"about_ca_topic_score_codex":0.00005542405,"about_ca_topic_score_gemma":0.00054939993,"teacher_disagreement_score":0.28292695,"about_ca_system_score_codex":0.000029007315,"about_ca_system_score_gemma":0.00020494466,"threshold_uncertainty_score":0.948108},"labels":[],"label_agreement":null},{"id":"W2894460945","doi":"10.1016/j.jclinepi.2018.09.005","title":"Two valid and reliable work role functioning questionnaire short versions were developed: WRFQ 5 and WRFQ 10","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Workplace Health and Well-being","field":"Health Professions","cited_by":21,"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 Work & Health","funders":"","keywords":"Work (physics); Psychology; Applied psychology; Medicine; Gerontology; Engineering","score_opus":0.21351477607436273,"score_gpt":0.5454073974760489,"score_spread":0.3318926214016862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894460945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9513117,0.0028199467,0.0038210202,0.0263995,0.006320659,0.0003374191,0.0000025084892,0.00005292088,0.008934347],"genre_scores_gemma":[0.95604444,0.0061504557,0.016389865,0.013191917,0.006036724,0.000011809145,0.000004626945,0.00003551864,0.0021346356],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98935723,0.005106976,0.0041941004,0.00038555838,0.00017053766,0.0007856143],"domain_scores_gemma":[0.9727834,0.023544211,0.0018157195,0.00027209084,0.00061049574,0.00097410736],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028872095,0.00020971817,0.0016556652,0.0001434306,0.0012529428,0.000008071634,0.00017401723,0.0007238733,0.0005914855],"category_scores_gemma":[0.03967508,0.00015971922,0.00017454507,0.00021794523,0.00045149805,0.00020663075,0.00019874035,0.0025443085,0.00018959571],"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":[0.0008582903,0.000042779746,0.93024826,0.000065351116,0.000050246737,0.0000099299505,0.0001816404,0.000023219452,0.0000021145042,0.002814368,0.0574403,0.008263484],"study_design_scores_gemma":[0.0018225478,0.0011714462,0.7564382,0.0016953425,0.00011110394,0.000054345153,0.0008165642,0.0003137251,0.00000105682,0.022779573,0.21458639,0.00020969142],"about_ca_topic_score_codex":0.00010385352,"about_ca_topic_score_gemma":0.00009558055,"teacher_disagreement_score":0.17381006,"about_ca_system_score_codex":0.00008050727,"about_ca_system_score_gemma":0.0008509022,"threshold_uncertainty_score":0.99998057},"labels":[],"label_agreement":null},{"id":"W2895487096","doi":"10.1016/j.jclinepi.2018.10.001","title":"Potentially missing data are considerably more frequent than definitely missing data: a methodological survey of 638 randomized controlled trials","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Sunnybrook Health Science Centre; University of Toronto; McMaster University; Health Sciences Centre; Impact","funders":"","keywords":"Missing data; Randomized controlled trial; Medicine; Interquartile range; MEDLINE; Statistics; Internal medicine; Mathematics","score_opus":0.9935119669334248,"score_gpt":0.7746832491102746,"score_spread":0.21882871782315017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895487096","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025955847,0.76343733,0.22583126,0.0029741079,0.0038815544,0.002817711,0.0008687315,0.0000043431723,0.00015901009],"genre_scores_gemma":[0.000035952737,0.7933528,0.20263532,0.0014137854,0.0019358998,0.000016581467,0.00034819648,0.000046631925,0.0002148344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.021437116,0.73841363,0.23164861,0.0030005765,0.0047427006,0.00075738895],"domain_scores_gemma":[0.0009495991,0.67365754,0.30747375,0.011175617,0.0059254975,0.0008180301],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.98654014,0.0016252759,0.34941506,0.001353803,0.00022779785,0.00059278955,0.017313635,0.0025877429,0.0034765396],"category_scores_gemma":[0.9981707,0.0005695411,0.052232757,0.0013615552,0.0023566422,0.00053755636,0.002494336,0.0033414564,0.00023004119],"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":[0.023824885,0.00043788407,0.0025525724,0.002907893,0.034102604,0.00018781229,0.000022810225,0.000018209148,1.8712224e-7,0.00034779505,0.1814385,0.75415885],"study_design_scores_gemma":[0.089857735,0.0004202273,0.0014719934,0.020319559,0.0806661,0.000876707,0.00007963556,0.0061522536,3.550316e-8,0.03766381,0.76151454,0.0009773666],"about_ca_topic_score_codex":0.000116244795,"about_ca_topic_score_gemma":0.00006787739,"teacher_disagreement_score":0.75318146,"about_ca_system_score_codex":0.000052430914,"about_ca_system_score_gemma":0.0041196556,"threshold_uncertainty_score":0.99967563},"labels":[],"label_agreement":null},{"id":"W2895828751","doi":"10.1016/j.jclinepi.2018.10.003","title":"Few studies exist examining methods for selecting studies, abstracting data, and appraising quality in a systematic review","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":84,"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; St. Michael's Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; National Health and Medical Research Council; Ontario Ministry of Research, Innovation and Science","keywords":"Data extraction; Systematic review; Critical appraisal; MEDLINE; Quality (philosophy); Cochrane Library; Computer science; Medicine; Reliability (semiconductor); Research design; Data science; Medical physics; Meta-analysis; Alternative medicine; Pathology; Statistics","score_opus":0.9949652348714091,"score_gpt":0.853682752021957,"score_spread":0.1412824828494521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895828751","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014854889,0.9680004,0.02643981,0.00053706917,0.002069279,0.0028371753,0.000016852262,0.000003542686,0.000081008715],"genre_scores_gemma":[0.0000028965903,0.77045393,0.22754559,0.0007758661,0.0009494722,0.0000757967,0.0000062395625,0.000030380832,0.00015983105],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.12831856,0.61909646,0.2456416,0.003370152,0.002583649,0.0009895572],"domain_scores_gemma":[0.004323672,0.7841413,0.20245129,0.0046042325,0.00413957,0.00033996213],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.95927054,0.0010009678,0.13686919,0.000761369,0.0002465498,0.0001883774,0.0045430167,0.00072656706,0.00004328861],"category_scores_gemma":[0.9916886,0.00042321568,0.008298029,0.0015223195,0.00051535066,0.00045052049,0.0011831484,0.0022632102,0.00004953208],"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":[0.0000056947215,0.000031894248,0.00032794042,0.5801297,0.0041654194,0.0000059649374,0.000100094934,5.9687187e-7,8.800384e-9,0.000122217,0.006248382,0.40886214],"study_design_scores_gemma":[0.0002209548,0.00021941641,0.000044403972,0.5903322,0.013625133,0.0004353061,0.0013056855,0.00017586643,3.4726042e-9,0.0060127834,0.38727504,0.00035323174],"about_ca_topic_score_codex":0.000004304472,"about_ca_topic_score_gemma":0.000028223874,"teacher_disagreement_score":0.4085089,"about_ca_system_score_codex":0.00014482958,"about_ca_system_score_gemma":0.00064222375,"threshold_uncertainty_score":0.99982196},"labels":[],"label_agreement":null},{"id":"W2897513422","doi":"10.1016/j.jclinepi.2018.10.011","title":"The Delphi method—more research please","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":146,"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; University of Ottawa","funders":"","keywords":"Delphi method; Delphi; Medicine; Computer science; Artificial intelligence","score_opus":0.8589705172342147,"score_gpt":0.7587421694499694,"score_spread":0.10022834778424528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897513422","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.00018876196,0.0012319981,0.0029964072,0.97889096,0.004657708,0.0004999182,0.000010993896,0.00003728462,0.011485956],"genre_scores_gemma":[0.00029819144,0.015163545,0.042461786,0.7958681,0.13100176,0.000047655114,0.000007489135,0.000100051264,0.015051449],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77565885,0.2059667,0.010426222,0.00091291335,0.0040237657,0.0030115754],"domain_scores_gemma":[0.39469284,0.59149474,0.0058348216,0.0013632332,0.005806537,0.0008078093],"candidate_categories":["metaresearch","sts","open_science","research_integrity"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.5609182,0.00032034074,0.0033600451,0.00054750947,0.001542823,0.00011952813,0.0057675443,0.0048856037,0.0005456346],"category_scores_gemma":[0.73451823,0.00019107167,0.0018828613,0.0007946604,0.012112719,0.0001607478,0.0006943433,0.026496096,0.00031946442],"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":[0.00017988872,0.00003982878,0.0013496148,0.000021443891,0.00016835662,0.0005963139,0.00022413854,8.6724026e-7,3.0466745e-7,0.0037920754,0.9633919,0.030235259],"study_design_scores_gemma":[0.00020029496,0.00060942624,0.0006087099,0.00012985752,0.00003867481,0.000058225858,0.00048672772,0.00003173189,7.5584205e-7,0.14572473,0.851959,0.00015189436],"about_ca_topic_score_codex":0.0011897597,"about_ca_topic_score_gemma":0.00031365675,"teacher_disagreement_score":0.38552806,"about_ca_system_score_codex":0.00034943185,"about_ca_system_score_gemma":0.004614931,"threshold_uncertainty_score":0.99975705},"labels":[],"label_agreement":null},{"id":"W2897619994","doi":"10.1016/j.jclinepi.2018.10.010","title":"Selective outcome reporting is present in randomized controlled trials in lung cancer immunotherapies","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","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":"Medicine; Publication bias; Randomized controlled trial; Scopus; MEDLINE; Family medicine; Clinical trial; Blinding; Trial registration; Systematic review; Reporting bias; Lung cancer; Randomization; Consolidated Standards of Reporting Trials; Meta-analysis; Internal medicine","score_opus":0.24100094364110025,"score_gpt":0.5758553091539602,"score_spread":0.33485436551285996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897619994","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.037916802,0.017177569,0.0015121645,0.93612754,0.0047509167,0.0020096356,0.0000035757053,0.0000127379435,0.00048906944],"genre_scores_gemma":[0.014002881,0.016023386,0.0056901267,0.92945945,0.032598663,0.00016978693,0.00001259625,0.000097775206,0.0019453227],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.86545384,0.06364415,0.0685021,0.0007313855,0.000721197,0.000947355],"domain_scores_gemma":[0.29221863,0.576464,0.12891746,0.000787592,0.0012082395,0.00040411926],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.44059506,0.00051882357,0.056168247,0.0009386146,0.00003700286,0.00001815045,0.00037387322,0.0020752696,0.00050745654],"category_scores_gemma":[0.86862737,0.0002827895,0.008267919,0.00022737985,0.00078110857,0.000069058944,0.00007378462,0.014088891,0.0000033160868],"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":[0.107869245,0.00013614105,0.3920329,0.00029727863,0.00428098,0.0012946174,0.00020621387,0.00008817239,0.000005279252,0.000009957278,0.49068823,0.0030910054],"study_design_scores_gemma":[0.75166553,0.0007544808,0.05178219,0.0061362144,0.0035302984,0.0005544602,0.000029890605,0.02996934,0.000002639551,0.005555626,0.14952374,0.0004955889],"about_ca_topic_score_codex":0.0007336875,"about_ca_topic_score_gemma":0.000012745268,"teacher_disagreement_score":0.64379627,"about_ca_system_score_codex":0.00028053919,"about_ca_system_score_gemma":0.0011905242,"threshold_uncertainty_score":0.99996245},"labels":[],"label_agreement":null},{"id":"W2900449136","doi":"10.1016/j.jclinepi.2018.11.007","title":"The methodological quality of dose-response meta-analyses needed substantial improvement: a cross-sectional survey and proposed recommendations","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"Sichuan University; National Natural Science Foundation of China","keywords":"Checklist; Quartile; Medicine; Confidence interval; Guideline; Cross-sectional study; Quality (philosophy); Meta-analysis; Meta-regression; Quality Score; MEDLINE; Regression analysis; Family medicine; Statistics; Psychology; Internal medicine; Pathology; Mathematics","score_opus":0.991129274460343,"score_gpt":0.7939509931711616,"score_spread":0.19717828128918147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900449136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91676986,0.0008030455,0.07297428,0.0076466864,0.0013196501,0.00031896855,0.00005325886,0.000001955158,0.000112304864],"genre_scores_gemma":[0.96339214,0.00021141667,0.03363918,0.0014255194,0.00045132363,0.0000043091186,0.0000032267117,0.0000073122897,0.00086559803],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2057705,0.69897985,0.089896075,0.0012453044,0.0035645822,0.0005437027],"domain_scores_gemma":[0.0969799,0.8257561,0.0662429,0.0023315225,0.008250993,0.0004386298],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9213249,0.0003019917,0.014490236,0.00027059473,0.0003729343,0.00021788568,0.0019036697,0.00036565572,0.004799542],"category_scores_gemma":[0.94111,0.00010158986,0.008044444,0.00086176826,0.0018317077,0.00021405521,0.00024226398,0.0007538013,0.00007134409],"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":[0.0048199925,0.00021099186,0.9621902,0.000011286413,0.008319306,0.0000016893063,0.000058153222,0.000037387235,0.0007678219,0.0033559934,0.011624487,0.008602652],"study_design_scores_gemma":[0.0006386653,0.0010490887,0.95654887,0.0000029339005,0.00087534013,0.000023576999,0.00012560573,0.0009417083,0.000047461894,0.031949136,0.0077008144,0.00009679637],"about_ca_topic_score_codex":0.00009608456,"about_ca_topic_score_gemma":0.00020628866,"teacher_disagreement_score":0.1267762,"about_ca_system_score_codex":0.000020805866,"about_ca_system_score_gemma":0.0003103513,"threshold_uncertainty_score":0.9961102},"labels":[],"label_agreement":null},{"id":"W2900643103","doi":"10.1016/j.jclinepi.2018.11.015","title":"Stratification by quality induced selection bias in a meta-analysis of clinical trials","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":75,"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":"Australian National University","keywords":"Meta-analysis; Selection bias; Selection (genetic algorithm); Quality (philosophy); Clinical trial; Publication bias; Medicine; MEDLINE; Statistics; Stratification (seeds); Internal medicine; Computer science; Mathematics; Biology; Artificial intelligence; Physics","score_opus":0.9946342775668788,"score_gpt":0.8107698000154119,"score_spread":0.18386447755146695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900643103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9024121,0.00092247705,0.085116774,0.009105383,0.0011749439,0.0004877036,0.000029181329,0.0000022569961,0.00074916106],"genre_scores_gemma":[0.986177,0.00015711701,0.01077114,0.0017213627,0.00064220815,0.000008019675,0.0000059069093,0.000006949728,0.0005102735],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.09855459,0.67281044,0.22345427,0.0013039799,0.0035092118,0.00036750178],"domain_scores_gemma":[0.029668044,0.73724556,0.22284298,0.0030372136,0.00665666,0.0005495578],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.96257156,0.0003219832,0.063720845,0.0011882706,0.000055322907,0.000074776755,0.0018399932,0.00082316436,0.010257735],"category_scores_gemma":[0.9674669,0.00013525097,0.03770872,0.0039020546,0.00039788857,0.00027208347,0.00007429244,0.0011939098,0.00020464914],"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":[0.00035421227,0.0006223393,0.82856774,0.00001247239,0.093592964,0.0000011110848,0.0000734953,0.00017886274,0.00012848528,0.0037031986,0.042754233,0.030010857],"study_design_scores_gemma":[0.00091799145,0.0011927189,0.81933683,0.000008899152,0.11739515,0.0000059735553,0.00017429948,0.01431785,0.00003444606,0.033937994,0.012491117,0.00018674662],"about_ca_topic_score_codex":0.000119628385,"about_ca_topic_score_gemma":0.0005196838,"teacher_disagreement_score":0.0837649,"about_ca_system_score_codex":0.0000239696,"about_ca_system_score_gemma":0.00041404433,"threshold_uncertainty_score":0.990647},"labels":[],"label_agreement":null},{"id":"W2901750293","doi":"10.1016/j.jclinepi.2018.11.009","title":"Analyzing excess risk from matched designs with double controls: author's response","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Influenza Virus Research Studies","field":"Medicine","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":"Frequentist inference; Scopus; Absolute risk reduction; Publication; Medicine; Psychology; Actuarial science; Bayesian probability; Statistics; MEDLINE; Bayesian inference; Mathematics; Economics; Confidence interval; Political science; Law","score_opus":0.5475729073006073,"score_gpt":0.5726156016685513,"score_spread":0.02504269436794404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901750293","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":[0.15428953,0.0043082424,0.011826165,0.8268864,0.0015982107,0.00067869335,0.00013370899,0.000045670455,0.00023338925],"genre_scores_gemma":[0.009708845,0.0040221,0.04622474,0.8785503,0.058076926,0.000046589914,0.000058765745,0.00022747986,0.0030842589],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9632994,0.025170237,0.008416105,0.00087247876,0.00094133447,0.0013004659],"domain_scores_gemma":[0.8019012,0.18269446,0.011163235,0.0011812153,0.0023325337,0.0007273334],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07780698,0.0006836936,0.01063161,0.0005944409,0.00020421669,0.000030962074,0.0008394664,0.0030084683,0.0004964247],"category_scores_gemma":[0.21833672,0.00040212687,0.001887556,0.00029367034,0.002041009,0.00015286531,0.0002290522,0.014332753,0.00020390468],"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":[0.08899549,0.000117861586,0.19371726,0.00007288489,0.005014705,0.003131927,0.000064245316,0.0000262123,0.000024640709,0.0000047042336,0.70775795,0.0010721151],"study_design_scores_gemma":[0.016032582,0.009396722,0.18934707,0.0014653765,0.0028497207,0.00033434943,0.000057754794,0.00014791886,0.000018030252,0.0023978688,0.7774972,0.00045543775],"about_ca_topic_score_codex":0.0005224155,"about_ca_topic_score_gemma":0.000037012178,"teacher_disagreement_score":0.16139816,"about_ca_system_score_codex":0.00024452657,"about_ca_system_score_gemma":0.0018054496,"threshold_uncertainty_score":0.99984306},"labels":[],"label_agreement":null},{"id":"W2902259954","doi":"10.1016/j.jclinepi.2018.11.025","title":"GRADE approach to rate the certainty from a network meta-analysis: addressing incoherence","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":192,"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","funders":"","keywords":"Certainty; Grading (engineering); Meta-analysis; Computer science; Publication bias; Psychology; Data science; Econometrics; Management science; Medicine; Economics; Epistemology; Engineering","score_opus":0.9734267548620819,"score_gpt":0.6898857477839806,"score_spread":0.28354100707810126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902259954","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":[0.056115985,0.0066749877,0.88702995,0.04180716,0.0020946097,0.00068467,0.000020872367,0.0000054193597,0.005566365],"genre_scores_gemma":[0.8402451,0.000068018715,0.1274468,0.026837394,0.0038573162,0.00002064,0.0000029465,0.000013142189,0.0015085964],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5770016,0.34654635,0.070307024,0.0017088474,0.0036297105,0.0008065151],"domain_scores_gemma":[0.36168632,0.5470726,0.07773649,0.0075441184,0.004752989,0.0012075093],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.7531445,0.0004081915,0.029035062,0.00033606333,0.00028605427,0.0003015243,0.0050649694,0.00034208284,0.007068054],"category_scores_gemma":[0.65457094,0.00013081248,0.02386979,0.0030513173,0.00057428994,0.00019211254,0.00038215224,0.0011564307,0.0011437619],"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":[0.00019883548,0.00026713437,0.16288605,0.000008066442,0.21938701,0.000012546673,0.00044638393,0.032621916,0.0000037450966,0.0068944152,0.5658576,0.0114162695],"study_design_scores_gemma":[0.00040199622,0.0004568746,0.25783333,0.00001946347,0.20108289,0.000031746076,0.0004151352,0.07041324,0.0000012356742,0.25930032,0.20970841,0.00033539036],"about_ca_topic_score_codex":0.00007744694,"about_ca_topic_score_gemma":0.00012439898,"teacher_disagreement_score":0.78412914,"about_ca_system_score_codex":0.000019359804,"about_ca_system_score_gemma":0.00018385233,"threshold_uncertainty_score":0.99963397},"labels":[],"label_agreement":null},{"id":"W2902426622","doi":"10.1016/j.jclinepi.2018.11.030","title":"Systematic reviews of clinical practice guidelines: a methodological guide","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":277,"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":"Systematic review; Medicine; Clinical Practice; MEDLINE; Medical physics; Management science; Family medicine; Engineering; Political science","score_opus":0.9430014611751203,"score_gpt":0.7786412487960017,"score_spread":0.16436021237911858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902426622","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":[0.07253639,0.012812491,0.58293504,0.29728445,0.019863127,0.0050713546,0.000017349952,0.000094564966,0.009385263],"genre_scores_gemma":[0.009301072,0.018939063,0.86207986,0.09760134,0.011705463,0.000016625861,0.000007004971,0.000040084706,0.00030949063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.79102343,0.09349345,0.11248763,0.0009774945,0.0012143102,0.0008037085],"domain_scores_gemma":[0.054824255,0.8409457,0.080671646,0.002033216,0.01997424,0.0015509222],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5369455,0.0004068663,0.015010596,0.00023094872,0.00006653051,0.00000884435,0.0006865132,0.0010909442,0.0007872725],"category_scores_gemma":[0.99195987,0.00024126847,0.0040202457,0.0004640685,0.0012421558,0.00042649155,0.00024967606,0.0025704456,0.00028593614],"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":[0.013434987,0.0034151757,0.110130414,0.0080100885,0.003444556,0.00037089642,0.00010183297,0.000019083569,0.00014591898,0.0041268445,0.652986,0.20381422],"study_design_scores_gemma":[0.009414309,0.020601965,0.04946837,0.008563136,0.0064852736,0.004735339,0.0007978771,0.0020321754,0.000025351332,0.00708118,0.8903972,0.00039781033],"about_ca_topic_score_codex":0.00007008421,"about_ca_topic_score_gemma":0.000013502438,"teacher_disagreement_score":0.74745226,"about_ca_system_score_codex":0.00006447001,"about_ca_system_score_gemma":0.0014490476,"threshold_uncertainty_score":0.99973065},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","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":"high"}],"label_agreement":"split"},{"id":"W2903236825","doi":"10.1016/j.jclinepi.2018.11.017","title":"Quality of stepped-wedge trial reporting can be reliably assessed using an updated CONSORT: crowd-sourcing systematic review","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Ottawa Hospital","funders":"Collaboration for Leadership in Applied Health Research and Care - Greater Manchester; Menzies Centre for Australian Studies, King's College London, University of London; Université de Nantes; Universiteit Utrecht; Keele University; University of Southampton; Institut National de la Santé et de la Recherche Médicale; University of Oxford; University of Leicester; National Institute for Health and Care Research; Imperial College London; Gillings School of Public Health; Oxford Brookes University; Medical Research Council; London School of Hygiene and Tropical Medicine","keywords":"Consolidated Standards of Reporting Trials; CRTS; Guideline; Medicine; Randomized controlled trial; Sample size determination; Randomization; Research design; Clinical study design; Medical physics; Family medicine; Clinical trial; Computer science; Statistics; Mathematics; Surgery","score_opus":0.9737117944876668,"score_gpt":0.7516357972270948,"score_spread":0.22207599726057192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903236825","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009896754,0.9822211,0.0074380036,0.00047138153,0.0033728143,0.0051408443,0.00005807448,0.0000074352083,0.00030066268],"genre_scores_gemma":[0.00015546673,0.98216933,0.013136804,0.0018396123,0.0019324382,0.000037542148,0.00005412294,0.00007367667,0.0006010349],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.18626907,0.45137784,0.3541068,0.0020664607,0.005385895,0.00079391827],"domain_scores_gemma":[0.03968208,0.29970464,0.64119816,0.008851672,0.009460274,0.0011031828],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.92437994,0.001289181,0.17242369,0.0009982444,0.00020966814,0.00022554267,0.005787388,0.001741543,0.0022617762],"category_scores_gemma":[0.9674855,0.00056925544,0.037666228,0.0023135426,0.0006826547,0.00038557575,0.00043676177,0.0028427516,0.00014058198],"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":[0.00053831394,0.00077630836,0.0015099501,0.9065521,0.007725891,0.00013308604,0.00005406702,0.000027970164,4.9282323e-7,0.0006141206,0.060951687,0.021116015],"study_design_scores_gemma":[0.0045437543,0.0013028954,0.00009103649,0.53019804,0.040223993,0.0013623157,0.00014786141,0.00067713537,1.1134899e-7,0.0021376829,0.41832957,0.000985627],"about_ca_topic_score_codex":0.000068744295,"about_ca_topic_score_gemma":0.00003277032,"teacher_disagreement_score":0.37635407,"about_ca_system_score_codex":0.00017994411,"about_ca_system_score_gemma":0.003535193,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W2903500752","doi":"10.1016/j.jclinepi.2018.11.026","title":"Conflict of interest is not associated with positive conclusions in toothpaste trials: a systematic survey","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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":"McMaster University; Impact","funders":"Ohio State University","keywords":"Conflict of interest; Scopus; Randomized controlled trial; Medicine; Clinical trial; MEDLINE; Family medicine; Public relations; Political science; Law; Surgery; Internal medicine","score_opus":0.9539952263707302,"score_gpt":0.7237778325642791,"score_spread":0.23021739380645112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903500752","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":[0.16930103,0.002425918,0.00019584711,0.8128268,0.008594107,0.0023585118,0.0035362495,0.000028602453,0.0007329182],"genre_scores_gemma":[0.20796132,0.001371529,0.00009939247,0.78425217,0.005163487,0.000027828108,0.00019187696,0.00006429326,0.00086810044],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.82243395,0.15911974,0.016409976,0.00062203954,0.00035217952,0.0010620917],"domain_scores_gemma":[0.5524378,0.42242995,0.021650042,0.00048642897,0.0021847317,0.0008110284],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1870895,0.00068070414,0.015104235,0.00047055935,0.00013251146,0.000010709476,0.0011649516,0.008969083,0.0014612962],"category_scores_gemma":[0.32821658,0.00045255388,0.0015189281,0.00043391428,0.0020189725,0.00012174051,0.00024467078,0.024161581,0.00005192282],"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":[0.007914774,0.0008317227,0.11020898,0.0041708457,0.005383564,0.0014214511,0.00041854059,0.000029428586,0.00002606948,0.00017502285,0.86901736,0.00040220752],"study_design_scores_gemma":[0.04408431,0.026376858,0.22666208,0.07439356,0.014096071,0.0015739436,0.0004998303,0.00408766,0.00070776005,0.004382141,0.600013,0.003122732],"about_ca_topic_score_codex":0.00013864234,"about_ca_topic_score_gemma":0.00023844768,"teacher_disagreement_score":0.26999617,"about_ca_system_score_codex":0.00024685866,"about_ca_system_score_gemma":0.0014671512,"threshold_uncertainty_score":0.99979264},"labels":[],"label_agreement":null},{"id":"W2903545128","doi":"10.1016/j.jclinepi.2018.11.023","title":"Getting more out of meta-analyses: a new approach to meta-analysis in light of unexplained heterogeneity","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Meta-analysis; Random effects model; Study heterogeneity; Medicine; Subgroup analysis; Intervention (counseling); Confidence interval; Population; Econometrics; Statistics; Internal medicine; Psychiatry; Mathematics; Environmental health","score_opus":0.9712719406525165,"score_gpt":0.7148035791354833,"score_spread":0.2564683615170332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903545128","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":[0.22238354,0.008408563,0.73320097,0.027907671,0.00079711276,0.0010047387,0.00004347561,0.0000040097766,0.0062499535],"genre_scores_gemma":[0.78337836,0.000048936443,0.21041195,0.0036203917,0.0004941995,0.000011289801,0.000002563821,0.000016467418,0.0020158635],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.6994304,0.16458441,0.12757342,0.0020790496,0.005571133,0.0007615708],"domain_scores_gemma":[0.5816959,0.24563672,0.15249737,0.009718713,0.008740122,0.0017111646],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6423867,0.00053419214,0.065009184,0.0020985676,0.000050709587,0.00005167564,0.0038043475,0.00044627392,0.0053485143],"category_scores_gemma":[0.66124797,0.0002132666,0.060439814,0.004202854,0.0003517958,0.0002292476,0.00035052275,0.00071576645,0.00021942369],"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":[0.00025782394,0.0007254638,0.11380053,0.00006739658,0.81937903,0.000011428573,0.00088040746,0.020477975,0.00020486716,0.0017007262,0.04053868,0.0019556864],"study_design_scores_gemma":[0.0008058473,0.0007895279,0.030759566,0.000013790363,0.9099118,0.000025452366,0.0006684021,0.02151759,0.00025390365,0.0136444075,0.02122656,0.0003831558],"about_ca_topic_score_codex":0.000104378734,"about_ca_topic_score_gemma":0.00026243052,"teacher_disagreement_score":0.5609948,"about_ca_system_score_codex":0.000026055292,"about_ca_system_score_gemma":0.00029175627,"threshold_uncertainty_score":0.9955607},"labels":[],"label_agreement":null},{"id":"W2903905844","doi":"10.1016/j.jclinepi.2018.11.028","title":"Noninferiority drug trials fail to report adequate methodological detail: an assessment of noninferiority trials from 2010 to 2015","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Medicine; Drug trial; Clinical trial; Medical physics; Intensive care medicine; Endpoint Determination; MEDLINE; Internal medicine","score_opus":0.9581161805867473,"score_gpt":0.7801152593479854,"score_spread":0.17800092123876188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903905844","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013978213,0.0001257527,0.619411,0.33317724,0.029400364,0.0024401753,0.0011752227,0.00007162786,0.00022045111],"genre_scores_gemma":[0.0002170696,0.00028121794,0.7838761,0.16158998,0.05318554,0.00009215786,0.000045291607,0.00015812056,0.0005544756],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3141035,0.56448334,0.111438416,0.0038656555,0.003479094,0.002629946],"domain_scores_gemma":[0.035899777,0.88773316,0.06550334,0.003952611,0.00426593,0.0026451715],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.769501,0.0016688054,0.0640103,0.00074561883,0.00015647887,0.0000944403,0.0036980705,0.0082901325,0.0051410766],"category_scores_gemma":[0.9888797,0.0011051446,0.009330846,0.0006111462,0.0015699334,0.0002585867,0.0012727783,0.014308487,0.00015727834],"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":[0.003929153,0.00082842127,0.011466362,0.00021341429,0.003327456,0.0019920748,0.00009103993,0.000015684915,0.000053187647,0.0023515741,0.9597966,0.015935024],"study_design_scores_gemma":[0.0041196053,0.007581129,0.02824425,0.0008947496,0.004890888,0.00022143444,0.00004593688,0.00007331302,0.000072098905,0.77278966,0.17993306,0.0011338709],"about_ca_topic_score_codex":0.0004102716,"about_ca_topic_score_gemma":0.000057497888,"teacher_disagreement_score":0.77986354,"about_ca_system_score_codex":0.0003312218,"about_ca_system_score_gemma":0.0027246675,"threshold_uncertainty_score":0.9996059},"labels":[],"label_agreement":null},{"id":"W2905517981","doi":"10.1016/j.jclinepi.2018.11.027","title":"The actor–partner interdependence model in shared decision-making: an illustrative example of its application to the physician–patient dyad in primary care consultations","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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 Laval; Centre intégré de santé et de services sociaux de Chaudière-Appalaches","funders":"Canadian Institutes of Health Research","keywords":"Dyad; Primary care; Primary care physician; Psychology; Family medicine; Medicine; Nursing; Social psychology","score_opus":0.5246632134334842,"score_gpt":0.5956590672874171,"score_spread":0.07099585385393292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905517981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95282507,0.0016205658,0.024180124,0.015872141,0.0013112092,0.0028227274,0.0000850477,0.000016499924,0.0012666129],"genre_scores_gemma":[0.9830029,0.0002559266,0.008529033,0.0076972316,0.0002655616,0.00021094753,0.000012797961,0.00001581541,0.000009799973],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9814066,0.011344345,0.006133887,0.00034228666,0.00031360236,0.00045927244],"domain_scores_gemma":[0.90801996,0.08360668,0.004660808,0.0010302943,0.0024725164,0.00020974432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00869166,0.00016434479,0.0011006757,0.00015890624,0.00043561216,0.0000046658815,0.0011803438,0.00034529288,0.000013646729],"category_scores_gemma":[0.05565859,0.000097813,0.00016224106,0.0004520058,0.000403924,0.00024023029,0.00035821565,0.0019291043,0.00002979997],"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":[0.0060406565,0.0009482293,0.37047,0.00030921353,0.00010726387,0.0000042216416,0.16650884,0.032146093,0.00019228194,0.027635653,0.0058520134,0.38978553],"study_design_scores_gemma":[0.0020730786,0.0021844686,0.823544,0.0023831632,0.0000309313,0.0000039073416,0.039824713,0.08585673,0.000011960556,0.03402381,0.0098012,0.00026202737],"about_ca_topic_score_codex":0.00021810822,"about_ca_topic_score_gemma":0.0054413867,"teacher_disagreement_score":0.453074,"about_ca_system_score_codex":0.0003538203,"about_ca_system_score_gemma":0.0014035412,"threshold_uncertainty_score":0.952296},"labels":[],"label_agreement":null},{"id":"W2906503865","doi":"10.1016/j.jclinepi.2018.12.012","title":"The trajectory of balance skill development from childhood to adolescence was influenced by birthweight: a latent transition analysis in a British birth cohort","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Infant Development and Preterm Care","field":"Medicine","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":"Sunnybrook Health Science Centre; University of Toronto","funders":"Economic and Social Research Council; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Sprint","keywords":"Cohort; Balance (ability); Demography; Cohort study; Pediatrics; Medicine; Developmental psychology; Psychology; Gerontology; Physical therapy; Sociology","score_opus":0.034452379795337364,"score_gpt":0.36277007229699587,"score_spread":0.3283176925016585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906503865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99488515,0.0006377245,0.0019145617,0.0018403379,0.00036994467,0.0002468841,0.000039685965,0.000007655797,0.000058082547],"genre_scores_gemma":[0.9846244,0.0012169742,0.009779967,0.004020064,0.00028933847,0.0000069014627,0.00003604001,0.00001009921,0.000016234517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938411,0.0011405797,0.00405276,0.0003096117,0.0003043926,0.00035153612],"domain_scores_gemma":[0.99416524,0.0035573123,0.0013510884,0.000233027,0.00041133296,0.00028201542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008439731,0.00015746777,0.0020476182,0.0001903044,0.00006785316,0.000007309334,0.00027324323,0.00026007293,0.00008545889],"category_scores_gemma":[0.0061709723,0.0001149062,0.00048679253,0.0004986427,0.0002891326,0.00006794489,0.00003267389,0.0006449365,0.0000042724305],"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":[0.0006276267,0.000092328184,0.98312837,0.000013753201,0.0007317331,0.00003552725,0.0013069719,0.00003227526,0.000110695386,0.0000041023727,0.00072321267,0.013193429],"study_design_scores_gemma":[0.0015189181,0.0005805121,0.9937836,0.0005032651,0.00022825711,0.000038238108,0.00007114425,0.00022036443,0.0002197735,0.00018127315,0.0025167256,0.00013796422],"about_ca_topic_score_codex":0.000118495765,"about_ca_topic_score_gemma":0.0006952536,"teacher_disagreement_score":0.013055465,"about_ca_system_score_codex":0.00006309419,"about_ca_system_score_gemma":0.00042798233,"threshold_uncertainty_score":0.73876756},"labels":[],"label_agreement":null},{"id":"W2911285579","doi":"10.1016/j.jclinepi.2019.01.012","title":"Authors of trials from high-ranking anesthesiology journals were not willing to share raw data","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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 Lethbridge","funders":"","keywords":"Data sharing; Anesthesiology; Raw data; Ranking (information retrieval); Randomized controlled trial; Medicine; Family medicine; Alternative medicine; Computer science; Information retrieval","score_opus":0.9322720691462844,"score_gpt":0.7330792866055981,"score_spread":0.1991927825406863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911285579","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":[0.91668105,0.0016863781,0.0044677276,0.07264124,0.0036838423,0.0005445472,0.00011612068,0.000014878316,0.00016423178],"genre_scores_gemma":[0.9166744,0.0053695976,0.054725036,0.017808313,0.0049428903,0.0000025193938,0.000050455914,0.000054962653,0.0003718542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9372895,0.028887043,0.029168407,0.0014459527,0.0019908445,0.0012182716],"domain_scores_gemma":[0.07904739,0.8960133,0.016350254,0.0034247485,0.0031207313,0.0020435308],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.35957223,0.0003354743,0.011395506,0.00044815114,0.00006705843,0.000017208575,0.0024270099,0.0024698991,0.003229834],"category_scores_gemma":[0.8643405,0.00022163137,0.0016188294,0.00032213467,0.0005788782,0.00022721392,0.0009268361,0.00928533,0.00023877253],"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":[0.01111962,0.0004896279,0.9402628,0.00023243198,0.0012886615,0.0002896884,0.000078557874,0.00067589484,0.002162125,0.0033709789,0.008176293,0.03185334],"study_design_scores_gemma":[0.007893814,0.007552751,0.8476781,0.0043482096,0.0007105853,0.00026581142,0.00014025914,0.0013153274,0.00030485488,0.115124054,0.014346127,0.00032009074],"about_ca_topic_score_codex":0.0001832864,"about_ca_topic_score_gemma":0.000045305762,"teacher_disagreement_score":0.8671263,"about_ca_system_score_codex":0.00006840746,"about_ca_system_score_gemma":0.0016822726,"threshold_uncertainty_score":0.99882513},"labels":[],"label_agreement":null},{"id":"W2913535557","doi":"10.1016/j.jclinepi.2019.02.003","title":"GRADE guidelines: 22. The GRADE approach for tests and strategies—from test accuracy to patient-important outcomes and recommendations","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":139,"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; Cochrane","funders":"","keywords":"Guideline; Certainty; Grading (engineering); Test (biology); Evidence-based medicine; Risk analysis (engineering); Decision aids; Computer science; Evidence-based practice; Medicine; Management science; Alternative medicine; Engineering","score_opus":0.5989376173194414,"score_gpt":0.6210147298016544,"score_spread":0.022077112482213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913535557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67226195,0.0004649511,0.013488098,0.31143728,0.0009808871,0.0012015708,0.00007965406,0.000014609492,0.00007101161],"genre_scores_gemma":[0.6783109,0.002033587,0.25853458,0.05975949,0.001140732,0.000030989362,0.00009132638,0.000033511755,0.00006489446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98875725,0.0012102113,0.0090438705,0.00042465038,0.00023186393,0.00033216787],"domain_scores_gemma":[0.7621014,0.23152134,0.0047147986,0.0004458594,0.00073337305,0.00048320313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018851638,0.00022766089,0.0019545467,0.000094687326,0.00008684047,0.00003107276,0.00019933732,0.00024969463,0.000074440344],"category_scores_gemma":[0.49141014,0.00012927988,0.00038868957,0.0001277128,0.00016675107,0.00030350653,0.00012697105,0.0008742308,0.0000059513677],"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":[0.00044067024,0.00042875807,0.9134519,0.000034357814,0.00024608933,0.0000053274575,0.00009262447,0.000058626803,0.00009851086,0.00086653716,0.03523294,0.04904363],"study_design_scores_gemma":[0.0068345047,0.005174716,0.85800004,0.00014964891,0.00070650433,0.0003579459,0.0036628575,0.007516744,0.0000064103638,0.021682259,0.09565586,0.00025251933],"about_ca_topic_score_codex":0.00014105177,"about_ca_topic_score_gemma":0.000038759226,"teacher_disagreement_score":0.4725585,"about_ca_system_score_codex":0.00002891561,"about_ca_system_score_gemma":0.00035805142,"threshold_uncertainty_score":0.6533639},"labels":[],"label_agreement":null},{"id":"W2913648278","doi":"10.1016/j.jclinepi.2019.01.010","title":"An evidence rating service provided valid correlates of the clinical importance of medical articles and journals","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; McMaster University Medical Centre; Queen's University; Impact","funders":"McMaster University","keywords":"Citation; Impact factor; Inclusion (mineral); Reliability (semiconductor); Medicine; MEDLINE; Family medicine; Psychology; Library science; Computer science; Social psychology","score_opus":0.9247268330004164,"score_gpt":0.7062411117352331,"score_spread":0.21848572126518329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913648278","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":[0.96835846,0.0042338753,0.002951943,0.022846593,0.0012239384,0.00031755277,0.0000020675795,0.0000011167377,0.000064476684],"genre_scores_gemma":[0.98794407,0.001193339,0.00641211,0.003982057,0.00037898155,0.0000012241021,1.2814805e-7,0.000007933392,0.00008016894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6886833,0.19018102,0.11171075,0.0011190358,0.007796412,0.00050948915],"domain_scores_gemma":[0.23055993,0.62586516,0.13180159,0.0043997215,0.0062630908,0.0011105291],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.75731915,0.00022946407,0.012202819,0.00015197902,0.000058851056,0.000063689964,0.003550066,0.00052016985,0.0031730386],"category_scores_gemma":[0.85977626,0.00008666141,0.0036243834,0.0007927328,0.00047204498,0.00046672334,0.00032721498,0.0014403391,0.00006483406],"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":[0.00009107528,0.00012953796,0.98094344,0.00007124382,0.0002273673,0.000004271383,0.000102599595,0.00016935148,0.00005914758,0.0011578576,0.0026075523,0.014436535],"study_design_scores_gemma":[0.0006111643,0.0006616463,0.9360379,0.00089319044,0.00030268877,0.0001694446,0.0004312809,0.03133015,0.000014488768,0.028730791,0.0007282794,0.000088958324],"about_ca_topic_score_codex":0.000014941698,"about_ca_topic_score_gemma":0.000049814495,"teacher_disagreement_score":0.45812336,"about_ca_system_score_codex":0.000008743606,"about_ca_system_score_gemma":0.0006352859,"threshold_uncertainty_score":0.9977382},"labels":[],"label_agreement":null},{"id":"W2914102261","doi":"10.1016/s0895-4356(01)00494-2","title":"Response","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Medicine","score_opus":0.8046981321550972,"score_gpt":0.6738220762275523,"score_spread":0.13087605592754492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914102261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7442011,0.00049963954,0.0054169856,0.24716866,0.0016394564,0.00011600475,0.0000015463054,0.000014100826,0.0009424956],"genre_scores_gemma":[0.8988834,0.0013371657,0.038975984,0.057917878,0.0021336407,0.0000010866413,0.0000013727904,0.000016362086,0.0007331045],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98080134,0.008225539,0.010230253,0.00020483579,0.0002583644,0.00027967538],"domain_scores_gemma":[0.8017852,0.19148843,0.005162297,0.0003686633,0.0006292465,0.0005662149],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0779085,0.000108898304,0.001997362,0.00011926783,0.000028160486,0.0000029734806,0.00014222677,0.00028623216,0.002131365],"category_scores_gemma":[0.6938833,0.00007585531,0.00084789447,0.00013041912,0.00020474603,0.00013746605,0.0000400559,0.001206768,0.0003104915],"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":[0.010846935,0.0007659758,0.5014317,0.000013222238,0.00024908385,0.00032467014,0.000033916367,0.000027437345,0.00014668849,0.00055679656,0.28040022,0.20520338],"study_design_scores_gemma":[0.0056561697,0.0052949847,0.57945603,0.00007599697,0.00026429046,0.0017506724,0.00006863341,0.0019505307,0.000010469717,0.0027309,0.40265024,0.00009110343],"about_ca_topic_score_codex":0.000006242388,"about_ca_topic_score_gemma":0.0000016631067,"teacher_disagreement_score":0.6159748,"about_ca_system_score_codex":0.000037411064,"about_ca_system_score_gemma":0.00015125914,"threshold_uncertainty_score":0.99878085},"labels":[],"label_agreement":null},{"id":"W2914721755","doi":"10.1016/j.jclinepi.2019.01.005","title":"A scoping review describes methods used to identify, prioritize and display gaps in health research","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":207,"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":"European Commission","keywords":"Prioritization; Medicine; Identification (biology); Systematic review; MEDLINE; Medical education; Data science; Management science; Computer science; Political science; Engineering","score_opus":0.9908724256543674,"score_gpt":0.8498825710887762,"score_spread":0.1409898545655912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914721755","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019448204,0.9704816,0.01563035,0.008115717,0.0014880357,0.0041338955,0.000008882489,0.0000015090617,0.00012056282],"genre_scores_gemma":[0.0000013698975,0.92009866,0.075463474,0.0031173336,0.0005419049,0.000056912355,0.000002654604,0.000030647356,0.00068701594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.07592862,0.7561743,0.15944536,0.0023442993,0.0049162274,0.0011911896],"domain_scores_gemma":[0.06868002,0.8301434,0.09118197,0.005196508,0.0031146267,0.001683489],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.95932335,0.0006959444,0.097506,0.0020486931,0.00011868021,0.00026798117,0.004406376,0.0008396142,0.0011947224],"category_scores_gemma":[0.9455148,0.00030332027,0.012102966,0.003379408,0.00032989067,0.0003033355,0.00090643816,0.004312409,0.0011983158],"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":[0.000008143365,0.00005068612,0.0016522887,0.10735871,0.00026390786,0.000019286801,0.000030397887,0.0000016063182,2.236513e-8,0.00059057306,0.033431374,0.856593],"study_design_scores_gemma":[0.00014185427,0.00029299624,0.0005741749,0.3658126,0.0004415623,0.00017061703,0.00001916202,0.000017894627,2.483265e-9,0.0034607067,0.62891793,0.00015049386],"about_ca_topic_score_codex":0.000025871312,"about_ca_topic_score_gemma":0.00008216419,"teacher_disagreement_score":0.8564425,"about_ca_system_score_codex":0.00016295892,"about_ca_system_score_gemma":0.0031316404,"threshold_uncertainty_score":0.9999419},"labels":[],"label_agreement":null},{"id":"W2914994635","doi":"10.1016/j.jclinepi.2019.02.005","title":"A modified Delphi and cross-sectional survey to facilitate selection of optimal outcomes and measures for a systematic review on geriatrician-led care models","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; McMaster University; University of Toronto; University of Calgary; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Medicine; Delphi method; Likert scale; Cognition; Quality of life (healthcare); Inclusion (mineral); Cross-sectional study; Gerontology; Scale (ratio); Delphi; Family medicine; Psychology; Nursing; Psychiatry","score_opus":0.8027711671438129,"score_gpt":0.6600448222742312,"score_spread":0.1427263448695817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914994635","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":[0.0006523669,0.98568994,0.0074796723,0.00038518774,0.0005164595,0.0049946522,0.00018201584,0.00001582584,0.000083900144],"genre_scores_gemma":[0.0016835496,0.99451673,0.0029402112,0.00028859262,0.00020658779,0.0001905518,0.000009043209,0.000027637063,0.00013709419],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9674283,0.022543525,0.008280119,0.00055830483,0.00070313516,0.00048658723],"domain_scores_gemma":[0.89105827,0.10077643,0.0054530133,0.00027846865,0.0020659114,0.00036791226],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12118559,0.00035708412,0.010964594,0.00043142374,0.00016114928,0.00003594592,0.0006388606,0.0010324399,0.0000068032705],"category_scores_gemma":[0.2918382,0.00023544474,0.0016019795,0.00037287237,0.00041599068,0.00013863675,0.00011682472,0.0011327948,0.0000034842126],"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":[0.0006768974,0.00016105748,0.019159732,0.91575485,0.0013450709,0.000005028263,0.00036707742,0.00069982396,4.862533e-8,0.0031287465,0.0013564087,0.057345238],"study_design_scores_gemma":[0.0043643895,0.012625602,0.04041006,0.82367605,0.0063959155,0.00029810087,0.000499765,0.001639297,1.1954052e-7,0.011830814,0.09578353,0.002476338],"about_ca_topic_score_codex":0.00028820118,"about_ca_topic_score_gemma":0.00018448409,"teacher_disagreement_score":0.17065261,"about_ca_system_score_codex":0.00021649485,"about_ca_system_score_gemma":0.0012972532,"threshold_uncertainty_score":0.9601158},"labels":[],"label_agreement":null},{"id":"W2918272982","doi":"10.1016/j.jclinepi.2019.02.011","title":"The selection of comparators for randomized controlled trials of health-related behavioral interventions: recommendations of an NIH expert panel","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":233,"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":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Comparator; Selection (genetic algorithm); Medicine; Psychological intervention; Randomized controlled trial; Computer science; Psychiatry; Artificial intelligence","score_opus":0.9294453431774718,"score_gpt":0.7080102448829791,"score_spread":0.2214350982944927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918272982","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":[0.0010904815,0.9830664,0.0013394161,0.0021108754,0.0076197274,0.004558948,0.00013749898,0.000008647787,0.00006802476],"genre_scores_gemma":[0.0011992427,0.9959159,0.0015838206,0.00013278266,0.00035776797,0.0004183286,0.000056637993,0.000026741953,0.00030876315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.85523987,0.09721313,0.04656504,0.0003943311,0.00019055816,0.0003970803],"domain_scores_gemma":[0.7591865,0.18021701,0.05938711,0.0003520593,0.0007233994,0.00013389037],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.20137976,0.00043329052,0.04972408,0.00028240515,0.00011837083,0.000005040778,0.0006663184,0.0011659557,0.00043251936],"category_scores_gemma":[0.06968552,0.00019597965,0.01896426,0.0002664883,0.00092696265,0.000055001772,0.000054417196,0.0013233398,0.000006240854],"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":[0.0546745,0.0026031663,0.0002560628,0.00095142337,0.0054842196,5.9187715e-7,0.00010613088,0.0000020331026,2.3097948e-7,0.003336326,0.011437039,0.9211483],"study_design_scores_gemma":[0.34073836,0.019674813,0.0013460981,0.015509177,0.018534267,0.00012559621,0.00063473725,0.000025960884,3.5207222e-7,0.008885111,0.5940077,0.0005178431],"about_ca_topic_score_codex":0.0001555081,"about_ca_topic_score_gemma":0.000018432465,"teacher_disagreement_score":0.92063046,"about_ca_system_score_codex":0.00004226681,"about_ca_system_score_gemma":0.0002663385,"threshold_uncertainty_score":0.9908606},"labels":[],"label_agreement":null},{"id":"W2919140425","doi":"10.1016/j.jclinepi.2019.02.009","title":"Structured decision-making drives guidelines panels' recommendations “for” but not “against” health interventions","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Toronto; McMaster University; Impact","funders":"University of Oklahoma Health Sciences Center; Agency for Healthcare Research and Quality; American Society of Hematology","keywords":"Psychological intervention; Grading (engineering); Guideline; Medicine; Certainty; Multilevel model; Family medicine; Psychology; Nursing; Statistics; Pathology","score_opus":0.874507398068753,"score_gpt":0.741993377465853,"score_spread":0.13251402060289996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919140425","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":[0.000033049382,0.7913924,0.13664041,0.05938645,0.010220828,0.0019381957,0.00032773722,0.0000305898,0.00003035316],"genre_scores_gemma":[0.00003728929,0.72043467,0.25555912,0.019129042,0.0042784116,0.00002516222,0.00034435163,0.00007703426,0.000114923205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9442941,0.008744802,0.04491329,0.0008630854,0.0004746169,0.0007100965],"domain_scores_gemma":[0.60505176,0.3412373,0.04846423,0.0012594638,0.0031278036,0.00085940975],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07086899,0.0006371627,0.016065167,0.00068235,0.00016022609,0.000026896943,0.0007066489,0.0012430594,0.00036533983],"category_scores_gemma":[0.6513622,0.00044160293,0.009546304,0.00034638058,0.00022583971,0.00025843695,0.00026116354,0.0034547567,0.00007753781],"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":[0.00037195667,0.0002331702,0.00021124672,0.0061329114,0.0011612179,0.000011180972,0.000010195025,0.000028867067,1.0453641e-7,0.00023372755,0.09282903,0.8987764],"study_design_scores_gemma":[0.0022681437,0.002191233,0.0004581225,0.056729246,0.0036313601,0.00057955075,0.000075507734,0.000266603,4.645309e-8,0.00373508,0.92977697,0.0002881366],"about_ca_topic_score_codex":0.000015680518,"about_ca_topic_score_gemma":0.000021453707,"teacher_disagreement_score":0.8984883,"about_ca_system_score_codex":0.0003230424,"about_ca_system_score_gemma":0.004290592,"threshold_uncertainty_score":0.9998036},"labels":[],"label_agreement":null},{"id":"W2921183574","doi":"10.1016/j.jclinepi.2019.03.003","title":"Most noninferiority trials were not designed to preserve active comparator treatment effects","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Western University","funders":"","keywords":"Medicine; Comparator; Engineering","score_opus":0.9516926757785006,"score_gpt":0.7644278044881085,"score_spread":0.18726487129039204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921183574","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":[0.00011250056,0.8537277,0.11439557,0.0016231324,0.019346867,0.009272217,0.0008729246,0.00007326404,0.00057583966],"genre_scores_gemma":[0.000003013509,0.6192602,0.37481663,0.0009040768,0.004527462,0.00011944697,0.00000581765,0.000101059384,0.00026232016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7500936,0.20698747,0.03950533,0.0014200395,0.0007833335,0.0012102373],"domain_scores_gemma":[0.07867682,0.88532895,0.031762358,0.0016602501,0.00093774387,0.0016339018],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.21090518,0.0013734186,0.07314091,0.00037893924,0.00009455302,0.00004043663,0.0017710759,0.0035048896,0.00043055578],"category_scores_gemma":[0.9652413,0.0007908327,0.009964184,0.00048596965,0.000463265,0.000113468624,0.00043329873,0.0038031356,0.0005201738],"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":[0.0026140588,0.00121412,0.000078893514,0.008550378,0.0049070143,0.00014876026,0.000016832126,0.000004108358,4.931192e-7,0.010967643,0.018169846,0.95332783],"study_design_scores_gemma":[0.0052382406,0.012049998,0.00021016314,0.015409753,0.014219281,0.0001336823,0.000005797919,0.000016787506,0.000008564004,0.17103177,0.78087294,0.00080302905],"about_ca_topic_score_codex":0.000017099648,"about_ca_topic_score_gemma":0.00000553269,"teacher_disagreement_score":0.95252484,"about_ca_system_score_codex":0.0005552073,"about_ca_system_score_gemma":0.0029700687,"threshold_uncertainty_score":0.99995077},"labels":[],"label_agreement":null},{"id":"W2923548233","doi":"10.1016/j.jclinepi.2019.03.006","title":"Following Cochrane review protocols to completion 10 years later: a retrospective cohort study and author survey","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; Queen's University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; MEDLINE; Protocol (science); Multivariate analysis; Systematic review; Cochrane Library; Cohort study; Meta-analysis; Family medicine; Alternative medicine; Internal medicine; Pathology","score_opus":0.8668252123045457,"score_gpt":0.696430463642595,"score_spread":0.1703947486619507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923548233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97550106,0.0016178347,0.0018280944,0.004000971,0.00083191117,0.01582208,0.000008345695,0.0000025994364,0.00038710842],"genre_scores_gemma":[0.9827706,0.00057964463,0.006523789,0.0054120664,0.00033605643,0.00044842064,0.0000037204227,0.000020063919,0.0039056025],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6434989,0.2787896,0.06914509,0.0018688579,0.006115922,0.00058163266],"domain_scores_gemma":[0.7757225,0.17876673,0.03705738,0.0036100552,0.0040400373,0.00080332835],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8181804,0.00024170011,0.021378823,0.00022832725,0.000048667585,0.00009731974,0.0012406029,0.0001760983,0.0048385034],"category_scores_gemma":[0.7737156,0.000115208335,0.003062774,0.0007500181,0.00006261128,0.00015211412,0.00018644612,0.0006311723,0.0018080226],"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":[0.00007070892,0.00011171834,0.9375992,0.0000591927,0.00039313,0.000010958331,0.00002930317,0.000007900364,0.0000012113162,0.000048885166,0.05813047,0.003537344],"study_design_scores_gemma":[0.0005383359,0.001425841,0.96176463,0.0006580585,0.00026199128,0.000024254132,0.000026785357,0.00022488444,4.1185316e-8,0.0013896856,0.033580925,0.00010458307],"about_ca_topic_score_codex":0.000021352078,"about_ca_topic_score_gemma":0.00003819756,"teacher_disagreement_score":0.13222359,"about_ca_system_score_codex":0.000037560276,"about_ca_system_score_gemma":0.00010098242,"threshold_uncertainty_score":0.9989692},"labels":[],"label_agreement":null},{"id":"W2924322406","doi":"10.1016/j.jclinepi.2019.03.008","title":"Improving the content validity of the mixed methods appraisal tool: a modified e-Delphi study","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":1060,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université Laval; Armand Frappier Museum; Université de Sherbrooke; McGill University","funders":"","keywords":"Content validity; Delphi method; Delphi; Content (measure theory); Computer science; Medicine; Psychometrics; Mathematics; Clinical psychology; Artificial intelligence","score_opus":0.913647252048127,"score_gpt":0.7217088427898263,"score_spread":0.19193840925830075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924322406","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":[0.0014071348,0.944713,0.022495374,0.0073981956,0.017995058,0.005136712,0.000026271802,0.00004315124,0.00078509777],"genre_scores_gemma":[0.001965791,0.9847728,0.010263158,0.00031607496,0.0023028732,0.00006708709,8.053703e-7,0.000046673176,0.00026472774],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7658667,0.21735807,0.013823005,0.00065191457,0.0013787913,0.0009215453],"domain_scores_gemma":[0.51122373,0.46507037,0.020348221,0.0016989,0.0013320232,0.00032672996],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4035975,0.00041236315,0.00978965,0.00019012294,0.00031690634,0.000036155732,0.005055657,0.0014331427,0.00004831349],"category_scores_gemma":[0.6236115,0.00018297313,0.0052658673,0.0006348238,0.0022798646,0.00012312841,0.0010900039,0.005801183,0.000011969685],"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":[0.00006831619,0.00042642895,0.001550818,0.00080007565,0.00055311644,0.00000870345,0.0002805307,0.0000088898705,4.1927913e-7,0.004985818,0.0041638617,0.987153],"study_design_scores_gemma":[0.00064797746,0.0013065183,0.0022628824,0.0020491846,0.0017355495,0.00004367688,0.0018364069,0.000094186194,4.327856e-7,0.004369773,0.9853548,0.00029864712],"about_ca_topic_score_codex":0.0009549141,"about_ca_topic_score_gemma":0.00014330835,"teacher_disagreement_score":0.9868544,"about_ca_system_score_codex":0.0001762178,"about_ca_system_score_gemma":0.003640884,"threshold_uncertainty_score":0.9998632},"labels":[],"label_agreement":null},{"id":"W2924774711","doi":"10.1016/j.jclinepi.2019.02.010","title":"Corrigendum to “Studies reporting ROC curves of diagnostic and prediction data were incorporated into meta-analyses using corresponding odds ratios” [J Clin Epidemiol. 2007 May;60(5):530-4]","year":2019,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","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":"Sunnybrook Health Science Centre; Health Sciences Centre; University of Toronto; McMaster University","funders":"","keywords":"Diagnostic odds ratio; Odds; Meta-analysis; Medicine; Odds ratio; Statistics; Internal medicine; Mathematics; Logistic regression","score_opus":0.952681044090919,"score_gpt":0.7217629101567035,"score_spread":0.23091813393421556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924774711","genre_codex":"editorial","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","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":[0.022260737,0.24411687,0.1282739,0.08491487,0.5096527,0.0065614665,0.0014586081,0.00021208702,0.0025487968],"genre_scores_gemma":[0.037717793,0.58285505,0.09596774,0.15744536,0.06664626,0.0002416446,0.005379687,0.0005136119,0.053232823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9172896,0.029781017,0.049641654,0.0010750011,0.0010379474,0.0011747385],"domain_scores_gemma":[0.38441944,0.40334237,0.19939335,0.003290453,0.007020026,0.0025343695],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24206176,0.0007157743,0.015001878,0.00088967767,0.000686258,0.000009848463,0.0010447229,0.002844103,0.00043490747],"category_scores_gemma":[0.8940279,0.00048007016,0.0011444755,0.0006002028,0.0005164643,0.00059515965,0.0011333445,0.00930364,0.000055818567],"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":[0.0005672531,0.000061852625,0.08073851,0.0063243387,0.0030770607,0.000037761496,0.00028812938,0.0006737383,0.0000030409647,0.000069644586,0.9059593,0.0021993623],"study_design_scores_gemma":[0.002788611,0.0030491853,0.09879233,0.04563005,0.024349546,0.0002192042,0.0029059567,0.073096134,0.0000013523644,0.0049097002,0.7431405,0.0011173958],"about_ca_topic_score_codex":0.0005676257,"about_ca_topic_score_gemma":0.00018074086,"teacher_disagreement_score":0.65196615,"about_ca_system_score_codex":0.0003378638,"about_ca_system_score_gemma":0.0048832954,"threshold_uncertainty_score":0.9997651},"labels":[],"label_agreement":null},{"id":"W2925030076","doi":"10.1016/j.jclinepi.2019.03.007","title":"The number needed to treat in pairwise and network meta-analysis and its graphical representation","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":53,"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":"Number needed to treat; Number needed to harm; Plot (graphics); Forest plot; Statistics; Pairwise comparison; Mathematics; Econometrics; Computer science; Confidence interval; Relative risk; Meta-analysis; Medicine","score_opus":0.9101426292902045,"score_gpt":0.6740004347000321,"score_spread":0.23614219459017238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925030076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94274515,0.0044812593,0.004416579,0.04698817,0.00034596966,0.0003752187,0.0000018976884,0.0000010349902,0.000644741],"genre_scores_gemma":[0.9865251,0.0011420901,0.004326517,0.00535441,0.00023346601,0.000008603149,5.938173e-7,0.000005817862,0.002403398],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8299187,0.12782842,0.038893104,0.0010338606,0.0018877918,0.00043816568],"domain_scores_gemma":[0.6063795,0.37266672,0.01749572,0.0018306114,0.0010701761,0.00055729045],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52384716,0.00020885082,0.015752375,0.00030325793,0.00007700947,0.00013418467,0.0007980844,0.00022281564,0.0020390686],"category_scores_gemma":[0.44088063,0.000072526615,0.0070041646,0.001981128,0.00011398924,0.00016284284,0.00015246955,0.0005421101,0.000256093],"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":[0.000099664336,0.000026888201,0.9590323,0.0000048261636,0.011516592,0.0000060273073,0.000048125523,0.0015864566,0.000001173597,0.0037535455,0.019520583,0.004403827],"study_design_scores_gemma":[0.0004730479,0.00019323839,0.8668624,0.00000646693,0.033738606,0.00004921187,0.00025482711,0.012709153,5.5068887e-7,0.0698597,0.01572785,0.00012492266],"about_ca_topic_score_codex":0.00003377652,"about_ca_topic_score_gemma":0.00012959735,"teacher_disagreement_score":0.2448383,"about_ca_system_score_codex":0.0000074273453,"about_ca_system_score_gemma":0.000035726272,"threshold_uncertainty_score":0.9988732},"labels":[],"label_agreement":null},{"id":"W2937385524","doi":"10.1016/j.jclinepi.2019.04.002","title":"Established search filters may miss studies when identifying randomized controlled trials","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":36,"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":"Health Technology Assessment international","keywords":"Randomized controlled trial; Randomization; Medicine; Cochrane Library; Surgery","score_opus":0.9617084884340436,"score_gpt":0.7322913021805164,"score_spread":0.22941718625352714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937385524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75737935,0.04391917,0.09303823,0.07359688,0.019487634,0.006371295,0.000010921463,0.000009293015,0.006187216],"genre_scores_gemma":[0.8639578,0.008203634,0.0646096,0.011109531,0.003353355,0.000071470735,0.0000033651747,0.00004050797,0.04865073],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.087096654,0.7239288,0.18174176,0.0012061155,0.0053586243,0.00066806504],"domain_scores_gemma":[0.006561614,0.8804294,0.104753755,0.002445304,0.005291674,0.00051825726],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.97315943,0.0004536116,0.13127764,0.00084008614,0.00009558558,0.00033622296,0.0028492338,0.00040890428,0.017459143],"category_scores_gemma":[0.9881823,0.000152227,0.04032533,0.00051778794,0.0005004009,0.0004295345,0.00026604097,0.0012080616,0.0022063572],"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":[0.11277911,0.00027885268,0.24115427,0.00021817193,0.033038806,0.00006758002,0.001135348,0.0013979729,0.000045780736,0.009779552,0.5713331,0.028771443],"study_design_scores_gemma":[0.4935784,0.00077708723,0.011139496,0.00069483236,0.008263265,0.0001482388,0.0037591334,0.018711597,0.0000070418178,0.40074492,0.061649255,0.0005267591],"about_ca_topic_score_codex":0.000009702513,"about_ca_topic_score_gemma":0.000004169555,"teacher_disagreement_score":0.50968385,"about_ca_system_score_codex":0.000037598245,"about_ca_system_score_gemma":0.00032115413,"threshold_uncertainty_score":0.99857056},"labels":[],"label_agreement":null},{"id":"W2943542684","doi":"10.1016/j.jclinepi.2019.04.023","title":"Characteristics and methods of incorporating randomized and nonrandomized evidence in network meta-analyses: a scoping review","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Michael's Hospital; University of Waterloo; McMaster University; Public Health Ontario; University of Toronto","funders":"","keywords":"Randomized controlled trial; Meta-analysis; Medicine; MEDLINE; Psychology; Surgery; Internal medicine; Political science","score_opus":0.9804609832807286,"score_gpt":0.7795628539234762,"score_spread":0.20089812935725238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943542684","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008862877,0.93203497,0.06255804,0.00065673277,0.0007572473,0.003916091,0.0000060339153,0.0000010236788,0.00006101746],"genre_scores_gemma":[0.000007094197,0.8374904,0.1609527,0.0009941569,0.00035133367,0.00007159432,0.000002687581,0.000021421922,0.000108603024],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.08058827,0.71479094,0.20011616,0.0016788366,0.0023198153,0.00050596474],"domain_scores_gemma":[0.024313208,0.74706084,0.2238372,0.0024841228,0.0019175586,0.00038706625],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9396686,0.000963254,0.25733516,0.0007962234,0.000052787196,0.00012498883,0.0021841072,0.00086160074,0.0009891951],"category_scores_gemma":[0.9644934,0.00035791527,0.036232617,0.0013401612,0.00072647823,0.00031457978,0.0005543382,0.0020946139,0.000036692414],"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":[0.0021148254,0.000058250138,0.0011501447,0.10845054,0.017803637,0.00002093478,0.000019474403,0.000023070254,4.642733e-8,0.00038818436,0.0014711104,0.86849976],"study_design_scores_gemma":[0.022996271,0.00032686038,0.00009822948,0.63834643,0.2543297,0.0004026132,0.0000117195095,0.0020937412,1.3438467e-8,0.0126346545,0.068158396,0.0006013529],"about_ca_topic_score_codex":0.000009035865,"about_ca_topic_score_gemma":0.0000073851606,"teacher_disagreement_score":0.8678984,"about_ca_system_score_codex":0.000025533309,"about_ca_system_score_gemma":0.0010463031,"threshold_uncertainty_score":0.99992406},"labels":[],"label_agreement":null},{"id":"W2943784761","doi":"10.1016/j.jclinepi.2019.04.018","title":"Development of the summary of findings table for network meta-analysis","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":219,"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":"Grading (engineering); Table (database); Stakeholder; Ranking (information retrieval); Computer science; Psychology; Information retrieval; Data mining; Engineering","score_opus":0.9409926138663134,"score_gpt":0.6599909357485194,"score_spread":0.281001678117794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943784761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7001574,0.0105089,0.27049354,0.010739517,0.003334488,0.0015666427,0.000039880273,0.000001737119,0.0031578883],"genre_scores_gemma":[0.6383781,0.0001279069,0.34615228,0.0028978167,0.00034213514,0.000013616045,0.0000028591435,0.000013656722,0.012071681],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.8512735,0.056657672,0.08781651,0.0007603429,0.0030336422,0.00045834557],"domain_scores_gemma":[0.55561364,0.34245482,0.09430631,0.0035534159,0.003801166,0.00027063471],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6773918,0.00021406742,0.028272532,0.00026940714,0.000061020928,0.00002066953,0.0026794826,0.00024818158,0.0055418303],"category_scores_gemma":[0.423443,0.000071998846,0.0276363,0.0016423345,0.00015345962,0.00010325344,0.0002138298,0.00039268826,0.000071092116],"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":[0.00009242017,0.000117392505,0.7381513,0.00006790674,0.12388404,3.626511e-7,0.00008535912,0.013108619,0.000017343864,0.0055720718,0.11579311,0.003110072],"study_design_scores_gemma":[0.0006787987,0.00032388675,0.2890022,0.000042320593,0.15236668,0.00000872551,0.00018723203,0.008462073,0.000039531365,0.047480673,0.5012047,0.00020313894],"about_ca_topic_score_codex":0.000003467653,"about_ca_topic_score_gemma":0.000022755667,"teacher_disagreement_score":0.4491491,"about_ca_system_score_codex":0.000013028779,"about_ca_system_score_gemma":0.00035234066,"threshold_uncertainty_score":0.9953672},"labels":[],"label_agreement":null},{"id":"W2944297570","doi":"10.1016/j.jclinepi.2019.04.011","title":"Measuring clinical uncertainty as a preliminary step to randomized controlled trials","year":2019,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Alberta Hospital; Centre Hospitalier de l’Université de Montréal; Health Sciences Centre","funders":"","keywords":"Randomized controlled trial; Medicine; Clinical trial; MEDLINE; Medical physics; Surgery; Internal medicine; Biology","score_opus":0.944615994858276,"score_gpt":0.6895696071753569,"score_spread":0.2550463876829191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944297570","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034317728,0.0065870723,0.052784007,0.9006487,0.023594268,0.008057274,0.000031767464,0.000007753448,0.0048573525],"genre_scores_gemma":[0.0020518221,0.0020244624,0.019892782,0.90741867,0.034197323,0.00015201261,0.000015708034,0.00007352347,0.034173705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.020406868,0.68215746,0.2860504,0.002306959,0.008138471,0.00093982404],"domain_scores_gemma":[0.0028240217,0.7364043,0.24781561,0.005404291,0.0067354073,0.00081639155],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.98364383,0.0014379851,0.30588627,0.0017091202,0.0001193797,0.0004205656,0.008107457,0.0049516745,0.013255964],"category_scores_gemma":[0.9971225,0.0005128872,0.15108009,0.00081932446,0.0007746824,0.00021465404,0.00062345754,0.010814283,0.011400067],"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":[0.10139309,0.0001201769,0.0044515454,0.00007869503,0.01137411,0.00023436741,0.000020927106,0.00059290335,1.1071277e-7,0.00021227327,0.8668351,0.014686704],"study_design_scores_gemma":[0.13676167,0.0017300649,0.00081977295,0.00061724783,0.00975195,0.0001995263,0.000036178157,0.004145528,3.5371773e-8,0.022459773,0.82305664,0.00042161858],"about_ca_topic_score_codex":0.000024697742,"about_ca_topic_score_gemma":0.0000045423753,"teacher_disagreement_score":0.15480617,"about_ca_system_score_codex":0.00009472282,"about_ca_system_score_gemma":0.0020395038,"threshold_uncertainty_score":0.999837},"labels":[],"label_agreement":null},{"id":"W2945185960","doi":"10.1016/j.jclinepi.2019.05.015","title":"Engaging knowledge users in a systematic review on the comparative effectiveness of geriatrician-led models of care is possible: A cross-sectional survey using the Patient Engagement Evaluation Tool","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Children's Hospital of Eastern Ontario; McMaster University; University of Toronto; University of Calgary; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Likert scale; Scale (ratio); Psychology; Delphi method; Knowledge translation; Medical education; Cross-sectional study; Medicine; Knowledge management; Computer science; Developmental psychology","score_opus":0.8913908117611309,"score_gpt":0.6966296791790486,"score_spread":0.19476113258208227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945185960","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":[0.04370707,0.93860483,0.00018396496,0.000025882573,0.003053268,0.014120711,0.00017616124,0.00000252054,0.00012558527],"genre_scores_gemma":[0.054356106,0.9436912,0.000101135105,0.0010089068,0.0001781733,0.0005242141,0.00010472792,0.00002804353,0.0000074952804],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.71624124,0.26599044,0.016175373,0.0004064739,0.00072372146,0.00046276348],"domain_scores_gemma":[0.7444372,0.23318465,0.019804433,0.0005920513,0.0018692606,0.00011239126],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26473475,0.00044499338,0.011019731,0.0002940811,0.00034680404,0.0000042414495,0.00065337453,0.0006090005,0.00007176098],"category_scores_gemma":[0.037578817,0.00021032653,0.001548344,0.00058604125,0.00018062735,0.00008774364,0.00021284334,0.0035623729,0.000016975371],"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":[0.0005044177,0.00032494165,0.054439694,0.9376305,0.000519618,6.713951e-7,0.0016285025,0.0011095881,2.9270481e-8,0.00037628986,0.000089598005,0.0033761559],"study_design_scores_gemma":[0.001529079,0.0018019457,0.018955117,0.97031814,0.0017554566,0.0000045066677,0.0008165989,0.0033988089,1.9450407e-7,0.00036202322,0.0008318692,0.00022628592],"about_ca_topic_score_codex":0.00015189468,"about_ca_topic_score_gemma":0.000044333512,"teacher_disagreement_score":0.22715594,"about_ca_system_score_codex":0.0011480101,"about_ca_system_score_gemma":0.00444394,"threshold_uncertainty_score":0.99873644},"labels":[],"label_agreement":null},{"id":"W2946263550","doi":"10.1016/j.jclinepi.2019.05.014","title":"A systematic survey identified 36 criteria for assessing effect modification claims in randomized trials or meta-analyses","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":26,"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; Hamilton Health Sciences; University of Toronto; McMaster University; Impact","funders":"Gottfried und Julia Bangerter-Rhyner-Stiftung; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Freiwillige Akademische Gesellschaft","keywords":"Credibility; Randomized controlled trial; MEDLINE; Critical appraisal; Medicine; Systematic review; Meta-analysis; Evidence-based medicine; Psychology; Family medicine; Alternative medicine; Surgery","score_opus":0.986123992205875,"score_gpt":0.786402226976338,"score_spread":0.199721765229537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946263550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5467674,0.0053849528,0.43363336,0.0028364728,0.004294197,0.006924841,0.00002451237,0.000004223804,0.00013005774],"genre_scores_gemma":[0.98083526,0.00016967728,0.015746443,0.0008318683,0.0003704734,0.00021613952,0.000011335961,0.000021113676,0.0017976903],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.03933401,0.80046505,0.15579575,0.0011817787,0.00276236,0.00046104426],"domain_scores_gemma":[0.012461735,0.8581816,0.12314907,0.0026869285,0.0032278008,0.00029285598],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9800065,0.00050393,0.12132371,0.0010712073,0.000069171016,0.00051583,0.0023341842,0.00054215634,0.0041972753],"category_scores_gemma":[0.98793197,0.00016795428,0.037363946,0.0011450072,0.00017718237,0.00056936615,0.00009025287,0.0006653577,0.0004990179],"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":[0.26093456,0.0018351105,0.32218352,0.02995658,0.22136192,0.00007834857,0.0006130636,0.011147097,0.0008353957,0.007067221,0.12917925,0.014807937],"study_design_scores_gemma":[0.17327885,0.0017692421,0.20997228,0.00424414,0.140658,0.00020068791,0.00051540555,0.300087,0.00004677093,0.16715112,0.00097287557,0.0011036092],"about_ca_topic_score_codex":0.000034479064,"about_ca_topic_score_gemma":0.000052486583,"teacher_disagreement_score":0.43406788,"about_ca_system_score_codex":0.00004712677,"about_ca_system_score_gemma":0.00031156823,"threshold_uncertainty_score":0.99671304},"labels":[],"label_agreement":null},{"id":"W2946720231","doi":"10.1016/j.jclinepi.2019.05.002","title":"Defining ranges for certainty ratings of diagnostic accuracy: a GRADE concept paper","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Cochrane; University of Toronto; University of Ottawa; Université de Montréal; Hôpital du Sacré-Cœur de Montréal; McMaster University; Impact","funders":"Allergan; European Commission; Horizon Pharmaceuticals; National Institute for Health and Care Research; U.S. Department of Veterans Affairs; Regeneron Pharmaceuticals; Health Technology Assessment Programme; St. Bonaventure University; World Health Organization","keywords":"Certainty; Operationalization; Grading (engineering); Guideline; Computer science; Context (archaeology); Brainstorming; Test (biology); Systematic review; Management science; Data mining; Medicine; Risk analysis (engineering); MEDLINE; Artificial intelligence; Mathematics; Engineering","score_opus":0.624001324886499,"score_gpt":0.5819193120870017,"score_spread":0.042082012799497304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946720231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7984149,0.013121005,0.020138448,0.1612514,0.004882586,0.0011066624,0.00023052805,0.000017237267,0.00083728094],"genre_scores_gemma":[0.93427604,0.0011539683,0.02506691,0.03815015,0.0011330973,0.000027252336,0.000013698208,0.000031328564,0.00014753599],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9745994,0.0034267355,0.021037152,0.00040859127,0.00007416586,0.0004539565],"domain_scores_gemma":[0.56652665,0.40875855,0.023798244,0.0003923161,0.00025015662,0.00027407534],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13623059,0.00018099387,0.005120152,0.00018024106,0.000057598325,0.000009783999,0.00042191587,0.00040643293,0.00051162497],"category_scores_gemma":[0.6840419,0.00017455203,0.0009404494,0.00008889565,0.00020640703,0.0003444941,0.000050406656,0.00056052324,0.00025402673],"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":[0.00017664369,0.00017368459,0.6531696,0.00035264538,0.00027282763,0.0000011567895,0.0005411359,0.0015054008,0.000003809313,0.29743156,0.044420235,0.0019513196],"study_design_scores_gemma":[0.009476318,0.0029496606,0.4319308,0.00065218756,0.00008149376,0.00004988875,0.0010854634,0.009029363,0.000014130876,0.3196463,0.22452988,0.00055451074],"about_ca_topic_score_codex":0.00013733208,"about_ca_topic_score_gemma":0.000016621036,"teacher_disagreement_score":0.5478113,"about_ca_system_score_codex":0.000097055454,"about_ca_system_score_gemma":0.0003082885,"threshold_uncertainty_score":0.8894324},"labels":[],"label_agreement":null},{"id":"W2947151211","doi":"10.1016/j.jclinepi.2019.05.023","title":"Several reasons explained the variation in the results of 22 meta-analyses addressing the same question","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"","keywords":"Meta-analysis; Medicine; Systematic review; Odds ratio; Guideline; Confidence interval; MEDLINE; Hazard ratio; Absolute risk reduction; Mean difference; Statistics; Internal medicine; Pathology; Mathematics","score_opus":0.9622313822225307,"score_gpt":0.7073287243466567,"score_spread":0.25490265787587396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947151211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6518067,0.005348276,0.058717698,0.27507055,0.0025732943,0.0014029756,0.00002996751,0.0000031955176,0.0050473474],"genre_scores_gemma":[0.98833716,0.00017558175,0.0049646744,0.0052076885,0.00041650288,0.0000072220014,0.0000017682839,0.0000050267267,0.0008843809],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.38138458,0.539971,0.072133794,0.00096078805,0.0050639557,0.00048591534],"domain_scores_gemma":[0.13569571,0.7775182,0.07922151,0.0049894634,0.002422841,0.0001522731],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.79487187,0.0002180613,0.009458083,0.00020559214,0.000108509164,0.00011301256,0.0028682228,0.00021896062,0.0013240601],"category_scores_gemma":[0.78277916,0.000051983014,0.0067789033,0.0009489634,0.00023196769,0.00023869584,0.00010276632,0.0010287707,0.00015427837],"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":[0.0018859016,0.00083425746,0.31725246,0.000082968,0.018564528,0.000030601303,0.0057907347,0.09061187,0.00020365059,0.080744654,0.45311034,0.03088803],"study_design_scores_gemma":[0.00090361317,0.00037407622,0.82492954,0.00007341675,0.005550149,0.00010208592,0.0013023041,0.033158034,0.0000022040633,0.10209446,0.031393062,0.000117072195],"about_ca_topic_score_codex":0.00011052172,"about_ca_topic_score_gemma":0.00009504944,"teacher_disagreement_score":0.5076771,"about_ca_system_score_codex":0.000018050037,"about_ca_system_score_gemma":0.00016463497,"threshold_uncertainty_score":0.99958885},"labels":[],"label_agreement":null},{"id":"W2947409284","doi":"10.1016/j.jclinepi.2019.05.033","title":"Single pivotal trials with few corroborating characteristics were used for FDA approval of cancer therapies","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"University of Toronto; McMaster University; Impact","funders":"Krebsliga Schweiz","keywords":"Medicine; Drug approval; Clinical trial; Cancer drugs; Cancer; Internal medicine; Pharmacology; Drug","score_opus":0.8519589956572093,"score_gpt":0.6813135385636881,"score_spread":0.1706454570935212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947409284","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76751775,0.0002917583,0.22380358,0.0025576488,0.0044385535,0.001103148,0.00017880871,0.000019945632,0.000088845714],"genre_scores_gemma":[0.27214974,0.00020938738,0.724468,0.0006044033,0.0023920878,0.000023477516,0.0000019914974,0.000054584518,0.000096311785],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96624684,0.017443236,0.014946008,0.00044167056,0.00041288038,0.00050935586],"domain_scores_gemma":[0.35321945,0.62931705,0.016031655,0.00040548373,0.0007844105,0.00024197996],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12730555,0.0003288401,0.010630224,0.00009291695,0.000044395598,0.000014932627,0.0004921229,0.0006530146,0.00035956132],"category_scores_gemma":[0.772912,0.0001899184,0.0014301356,0.00013906707,0.0005353748,0.00009547267,0.000069986,0.0010763174,0.000004911905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026748482,0.0022060312,0.63289833,0.0019204313,0.0040768976,0.000027321936,0.00035387295,0.00009659032,0.003773542,0.10069436,0.004199758,0.2230044],"study_design_scores_gemma":[0.020372462,0.02599934,0.030691624,0.0019444581,0.0021810126,0.000057097535,0.00034273224,0.0016875382,0.0012832176,0.9111769,0.0035892026,0.0006743689],"about_ca_topic_score_codex":0.000009538372,"about_ca_topic_score_gemma":0.0000070698675,"teacher_disagreement_score":0.81048256,"about_ca_system_score_codex":0.00004214549,"about_ca_system_score_gemma":0.00038283702,"threshold_uncertainty_score":0.8986226},"labels":[],"label_agreement":null},{"id":"W2947630277","doi":"10.1016/j.jclinepi.2019.05.027","title":"Contacting authors by telephone increased response proportions compared with emailing: results of a randomized study","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; University of Toronto; Women's College Hospital","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.24105451919760054,"score_gpt":0.5806659351350569,"score_spread":0.33961141593745636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947630277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787679,0.00024895137,0.0019673137,0.01000762,0.0010199795,0.007273998,0.00015341568,0.000033599645,0.00052723865],"genre_scores_gemma":[0.9879818,0.00023874763,0.006988426,0.002650885,0.00039713248,0.00083309505,0.0000456198,0.000029813842,0.00083445956],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.918748,0.059662856,0.019775415,0.00052286015,0.0004416349,0.00084918365],"domain_scores_gemma":[0.6687921,0.30407974,0.023533361,0.0008025236,0.0016178333,0.0011743993],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17758894,0.0002471112,0.0068046353,0.00024863303,0.0003251196,0.0000022615932,0.00037769732,0.000534555,0.0005365458],"category_scores_gemma":[0.27461106,0.00015490052,0.00056953105,0.00037620403,0.0003564587,0.00009398181,0.000073132665,0.0029309574,0.000077109165],"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":[0.6058206,0.0014688609,0.32647595,0.00020784944,0.00026316615,0.0000092045175,0.00062629447,0.000081738865,0.00006760931,0.0003819345,0.06377946,0.0008173603],"study_design_scores_gemma":[0.5530295,0.009229495,0.31728426,0.0013470982,0.00056029815,0.000047658505,0.0068144756,0.0013472367,0.000007743974,0.0013114107,0.10866887,0.00035195064],"about_ca_topic_score_codex":0.0007394031,"about_ca_topic_score_gemma":0.00012497517,"teacher_disagreement_score":0.24995591,"about_ca_system_score_codex":0.000104492974,"about_ca_system_score_gemma":0.0034016697,"threshold_uncertainty_score":0.9993693},"labels":[],"label_agreement":null},{"id":"W2947641233","doi":"10.1016/j.jclinepi.2019.05.031","title":"Retrieval of individual patient data depended on study characteristics: a randomized controlled trial","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"Center of Innovation Program; Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Incentive; Medicine; Intervention (counseling); Family medicine; Clinical trial; Trial registration; Actuarial science; Finance; Surgery; Nursing; Business; Internal medicine","score_opus":0.7275640867551437,"score_gpt":0.6633176034157517,"score_spread":0.06424648333939198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947641233","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":[0.9831608,0.00014845606,0.0001238681,0.006333131,0.0036595734,0.005542057,0.000034116078,0.000008370621,0.0009896448],"genre_scores_gemma":[0.9918881,0.0010415401,0.0015819279,0.0034053267,0.0017694561,0.000013171984,0.000022620658,0.000026214146,0.00025161842],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.92582697,0.04165765,0.027659355,0.00095559756,0.003205602,0.0006948126],"domain_scores_gemma":[0.10980717,0.8690241,0.015725685,0.0023359212,0.0022940298,0.0008131146],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37367183,0.00027077016,0.01654496,0.0002908418,0.00003308119,0.000010500306,0.0013389611,0.0011253576,0.00054106006],"category_scores_gemma":[0.9174766,0.0001523978,0.0021831535,0.00016867985,0.0007965877,0.00008639348,0.00066005986,0.0071185976,0.000070244394],"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":[0.9347678,0.0051890486,0.051717333,0.00006210559,0.0029819938,0.00010807155,0.00007010877,0.0000036121385,0.0000076015203,0.0016007737,0.00047923438,0.0030123414],"study_design_scores_gemma":[0.9166204,0.04323971,0.030054957,0.00033824347,0.001261428,0.00003120074,0.00016336533,0.0004515982,0.000004049709,0.007528605,0.00019866522,0.00010777626],"about_ca_topic_score_codex":0.000008673109,"about_ca_topic_score_gemma":0.0000037864352,"teacher_disagreement_score":0.8273664,"about_ca_system_score_codex":0.000040384362,"about_ca_system_score_gemma":0.0019335792,"threshold_uncertainty_score":0.99805546},"labels":[],"label_agreement":null},{"id":"W2947961010","doi":"10.1016/j.jclinepi.2019.05.024","title":"The Clinician Guideline Determinants Questionnaire was developed and validated to support tailored implementation planning","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Toronto General Hospital; University of Toronto","funders":"","keywords":"Guideline; Face validity; Construct validity; Psychological intervention; Medicine; Content validity; Psychology; Applied psychology; Multidisciplinary approach; Psychometrics; Family medicine; Clinical psychology; Nursing","score_opus":0.5122048215191276,"score_gpt":0.6500351998401601,"score_spread":0.1378303783210325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947961010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9344226,0.00015033335,0.007406771,0.05495136,0.0023171583,0.0006491662,0.000005060002,0.000018978648,0.00007853369],"genre_scores_gemma":[0.9413371,0.00052411394,0.027188756,0.029457955,0.0012645023,0.000006958953,0.000034188248,0.000030458403,0.00015597157],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98235255,0.0030444688,0.013351176,0.00040474514,0.00036620625,0.00048084214],"domain_scores_gemma":[0.955362,0.03601258,0.0062525054,0.00044429564,0.001279965,0.0006486094],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05848054,0.00022116229,0.0019614196,0.00014425312,0.00013195406,0.000023512219,0.00024702167,0.00029366117,0.00019315342],"category_scores_gemma":[0.1763411,0.0001406039,0.00036570092,0.00020664572,0.00015340351,0.0002524488,0.00015452763,0.0009485009,0.00010486035],"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":[0.0018215025,0.00006420642,0.74290675,0.000017525343,0.000113026115,0.000041771043,0.000057773457,0.000043540644,0.00007086553,0.00010541789,0.020413019,0.2343446],"study_design_scores_gemma":[0.005967649,0.00590146,0.8807075,0.00017829578,0.00031574,0.0005391895,0.00082919723,0.001073746,0.0000493178,0.0019596985,0.10230019,0.00017801077],"about_ca_topic_score_codex":0.00007197888,"about_ca_topic_score_gemma":0.00012712322,"teacher_disagreement_score":0.23416659,"about_ca_system_score_codex":0.00007792837,"about_ca_system_score_gemma":0.0009171759,"threshold_uncertainty_score":0.96949244},"labels":[],"label_agreement":null},{"id":"W2949729372","doi":"10.1016/j.jclinepi.2019.05.032","title":"A scoping review found increasing examples of rapid qualitative evidence syntheses and no methodological guidance","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":25,"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 Agency for Drugs and Technologies in Health","funders":"University of Sheffield","keywords":"CINAHL; Qualitative research; MEDLINE; Data extraction; Management science; Thematic analysis; Computer science; Systematic review; Critical appraisal; Data science; Medicine; Psychology; Alternative medicine; Nursing; Pathology; Psychological intervention; Sociology; Engineering; Social science","score_opus":0.9947103896578098,"score_gpt":0.8136177345857206,"score_spread":0.18109265507208916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949729372","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022446908,0.97609663,0.01977502,0.0006399914,0.0010714433,0.0017297597,0.000015995585,0.0000020174534,0.00064670783],"genre_scores_gemma":[0.000014984279,0.8662116,0.13191591,0.0011479217,0.00052747154,0.000022850645,0.000001085604,0.00002031788,0.00013784612],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.12507376,0.73897797,0.1302859,0.0018213161,0.0032938104,0.00054722937],"domain_scores_gemma":[0.005048655,0.83189934,0.15578085,0.0029830576,0.0038451748,0.00044288463],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.92673206,0.0008441125,0.10436672,0.00055609865,0.00008076099,0.00010404814,0.0037921588,0.0009376915,0.002960989],"category_scores_gemma":[0.9945975,0.00033706755,0.01816464,0.0010491392,0.0009911249,0.0003992037,0.0006038882,0.0018234735,0.0005028744],"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":[0.000046177534,0.000050445837,0.00068070285,0.13721293,0.0011805224,0.0000074218556,0.000053799344,0.0000014478301,1.10290316e-7,0.0013677401,0.008381947,0.85101676],"study_design_scores_gemma":[0.00006556195,0.00051653926,0.00019219503,0.6007379,0.0039459355,0.00025148052,0.00006817633,0.000022700828,9.23685e-9,0.004385994,0.38957852,0.00023497976],"about_ca_topic_score_codex":0.000014074423,"about_ca_topic_score_gemma":0.000003683859,"teacher_disagreement_score":0.8507818,"about_ca_system_score_codex":0.000046731882,"about_ca_system_score_gemma":0.0012731691,"threshold_uncertainty_score":0.99990815},"labels":[],"label_agreement":null},{"id":"W2950546474","doi":"10.1016/j.jclinepi.2019.05.025","title":"Care and research concepts should be revised to practice outcome-based medical care","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire de Gériatrie de Montréal; Alberta Hospital Edmonton; Health Sciences Centre; Centre Hospitalier de l’Université de Montréal; University of Alberta Hospital; Hôpital Notre-Dame","funders":"","keywords":"Argument (complex analysis); Medical practice; Medical care; Outcome (game theory); Medical research; Work (physics); Patient care; MEDLINE; Best practice; Medicine; Psychology; Medical education; Nursing; Engineering ethics; Political science","score_opus":0.8867226568960868,"score_gpt":0.7919250646716792,"score_spread":0.09479759222440753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950546474","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36937216,0.0059156264,0.0008064941,0.6107963,0.0023993165,0.0010992553,0.000011329714,0.000024215939,0.009575301],"genre_scores_gemma":[0.8189858,0.004193396,0.04098587,0.13274336,0.0022544025,0.000011575104,0.000008385185,0.0000518284,0.00076538307],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.966625,0.019295748,0.008194127,0.00089479674,0.00393672,0.0010536348],"domain_scores_gemma":[0.2700718,0.71336496,0.0019242644,0.001222392,0.0099946335,0.003421929],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.21610306,0.00024237928,0.0039005312,0.0003601544,0.00011099518,0.00002029377,0.0008472878,0.0024189653,0.000946734],"category_scores_gemma":[0.93547064,0.00016549014,0.0008389927,0.00044452038,0.0015711467,0.00011861744,0.0005240095,0.017361091,0.0002095683],"study_design_candidate":"observational","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":[0.0061973175,0.00032469616,0.9287065,0.0013362136,0.00019744861,0.0007001298,0.00056660624,0.000031631884,0.000017459048,0.009197663,0.013347481,0.039376847],"study_design_scores_gemma":[0.015357229,0.03154121,0.22328164,0.0037786046,0.0003266047,0.00048283063,0.008499177,0.00035050037,0.00004170849,0.00634294,0.70958894,0.00040862852],"about_ca_topic_score_codex":0.00007132451,"about_ca_topic_score_gemma":0.00007693251,"teacher_disagreement_score":0.71936756,"about_ca_system_score_codex":0.00022314218,"about_ca_system_score_gemma":0.005913224,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"W2951728926","doi":"10.1016/j.jclinepi.2019.06.012","title":"Collection of antirheumatic medication data from both patients and rheumatologists shows strong agreement in a real-world clinical cohort: the Ontario Best Practices Research Initiative—a rheumatoid arthritis cohort","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Mount Sinai Hospital; Toronto General Hospital; University Health Network","funders":"Canadian Arthritis Network; Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Rheumatoid arthritis; Discontinuation; Erythrocyte sedimentation rate; Physical therapy; Cohort; Internal medicine; Antirheumatic drugs; Rheumatology; Cohen's kappa; Gold standard (test); Kappa; Antirheumatic Agents","score_opus":0.43338686979939456,"score_gpt":0.5408332199712897,"score_spread":0.10744635017189519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951728926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882634,0.004164823,0.000089360416,0.0040758555,0.00081298925,0.0013007801,0.000041196745,0.000006903743,0.0012446897],"genre_scores_gemma":[0.76793116,0.23027672,0.0012735447,0.0002056427,0.00008347426,0.000017538085,0.000109445806,0.000015504233,0.00008697564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9767097,0.013237665,0.0076031047,0.00069315475,0.0011676033,0.00058873853],"domain_scores_gemma":[0.91382,0.07581067,0.007679801,0.0011725688,0.0010206475,0.00049628376],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07791948,0.00023636526,0.0034165352,0.0004170167,0.00013780556,0.00002850283,0.0007077986,0.00038399614,0.0005344202],"category_scores_gemma":[0.11262514,0.00015618607,0.0002691059,0.0003754132,0.0015426539,0.00050161075,0.00042931756,0.0030616834,0.00003487258],"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":[0.0021701732,0.0012192038,0.9662412,0.00004679673,0.0007376771,0.000021503076,0.0002991018,0.000003460378,0.0000031513052,0.00029679935,0.0047951196,0.024165817],"study_design_scores_gemma":[0.0070713903,0.003242952,0.9799555,0.002050571,0.000026507907,0.000060586335,0.0005889727,0.001287459,0.0000034178681,0.0015854476,0.0040102545,0.00011694099],"about_ca_topic_score_codex":0.04866338,"about_ca_topic_score_gemma":0.14643337,"teacher_disagreement_score":0.2261119,"about_ca_system_score_codex":0.00017248438,"about_ca_system_score_gemma":0.0016848699,"threshold_uncertainty_score":0.9992383},"labels":[],"label_agreement":null},{"id":"W2954129194","doi":"10.1016/j.jclinepi.2019.06.015","title":"Statistical significance did not affect time to publication in non-Cochrane systematic reviews: a metaepidemiological study","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"Telecommunications Advancement Foundation","keywords":"Affect (linguistics); Systematic review; Medicine; Meta-analysis; Statistical significance; Cochrane collaboration; MEDLINE; Psychology; Cochrane Library; Internal medicine; Biology","score_opus":0.8716201039842042,"score_gpt":0.6761427288288345,"score_spread":0.19547737515536967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954129194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76684254,0.003119443,0.17990324,0.028323762,0.002661428,0.016647052,0.000028850209,0.000012739072,0.0024609542],"genre_scores_gemma":[0.9468352,0.00024571933,0.036333475,0.01060637,0.0005485405,0.00023877365,0.0000050748567,0.000024398927,0.0051624067],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.25660428,0.5676153,0.16590214,0.0029606812,0.0057209902,0.0011966445],"domain_scores_gemma":[0.13607989,0.78150153,0.071881264,0.005862129,0.0033859618,0.0012892162],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.87193084,0.00056196784,0.045788225,0.0008128988,0.00005393191,0.00015778896,0.003610796,0.00042870932,0.013344611],"category_scores_gemma":[0.9585998,0.00023353536,0.0054666065,0.0017893381,0.00015416357,0.0003371446,0.00026358955,0.0014372377,0.038074374],"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":[0.0005172476,0.0017729725,0.7492699,0.002990389,0.0009849997,0.00007455794,0.00023483773,0.0013182029,0.00008177795,0.0032091544,0.22710308,0.012442895],"study_design_scores_gemma":[0.0019289579,0.004820252,0.9414415,0.0026484325,0.0010326606,0.00012110191,0.0002950024,0.021241356,0.0000012191322,0.007834093,0.018081296,0.0005541295],"about_ca_topic_score_codex":0.00001316868,"about_ca_topic_score_gemma":0.000011626397,"teacher_disagreement_score":0.21388626,"about_ca_system_score_codex":0.00009472594,"about_ca_system_score_gemma":0.0001795097,"threshold_uncertainty_score":0.98755735},"labels":[],"label_agreement":null},{"id":"W2954143103","doi":"10.1016/j.jclinepi.2019.06.004","title":"Letter re: stratification by quality is not recommended in meta-analysis","year":2019,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Australian National University","keywords":"Meta-analysis; Stratification (seeds); Quality (philosophy); Medicine; Internal medicine; Biology; Epistemology; Philosophy","score_opus":0.9750267250948861,"score_gpt":0.7192927886614524,"score_spread":0.2557339364334337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954143103","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043641095,0.0018761158,0.01870161,0.97509897,0.0016105633,0.0005095761,0.00017403139,0.0000020494122,0.0015906839],"genre_scores_gemma":[0.0029542076,0.00031379735,0.008218989,0.9614804,0.0026756283,0.000018437662,0.00010327458,0.000022623784,0.024212638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.3048078,0.4995903,0.18374497,0.003137355,0.0078074345,0.00091212994],"domain_scores_gemma":[0.29879275,0.5123278,0.17672098,0.008743551,0.0031161162,0.000298846],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.81300753,0.0008569717,0.07674535,0.0015786078,0.00005870524,0.0002755248,0.00544275,0.0029835652,0.04763838],"category_scores_gemma":[0.6418371,0.00037497078,0.061023872,0.0021132317,0.00021518065,0.00032757522,0.00018508644,0.007498482,0.0026190917],"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":[0.000032070362,0.00007413333,0.017990693,0.000042119937,0.07116778,0.000020355776,0.000028067327,0.000059756978,0.000001021072,0.00008642923,0.90914255,0.0013550319],"study_design_scores_gemma":[0.00028071774,0.00011994964,0.0072463593,0.000008711478,0.0814489,0.000008172089,0.000018204382,0.0005315042,9.211897e-7,0.011776425,0.898266,0.0002941298],"about_ca_topic_score_codex":0.00006961459,"about_ca_topic_score_gemma":0.00006847585,"teacher_disagreement_score":0.17117038,"about_ca_system_score_codex":0.000084143474,"about_ca_system_score_gemma":0.00028760842,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W29545206","doi":"10.1016/j.jclinepi.2018.03.001","title":"The Relations Among Natural and Civic Place Attachment, Environmental Evaluations, and Pro- Environmental Behaviours","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Place Attachment and Urban Studies","field":"Social Sciences","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":"Place attachment; Environmental quality; Reputation; Sense of place; Environmental psychology; Social psychology; Perception; Natural (archaeology); Psychology; Place identity; Scale (ratio); Geography; Sociology; Ecology; Economic geography; Social science; Urban planning; Cartography","score_opus":0.17022128712608317,"score_gpt":0.47946308671092036,"score_spread":0.3092417995848372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W29545206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9796023,0.008229145,0.000028104972,0.0110379495,0.0005216806,0.00018798825,0.000006213346,0.000006513648,0.00038011707],"genre_scores_gemma":[0.9805349,0.016154995,0.00034317086,0.0003374178,0.00036541448,0.000005222602,0.0000033239664,0.0000056374215,0.0022499224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99488753,0.0029386838,0.0013941687,0.00019018144,0.00029160132,0.00029784744],"domain_scores_gemma":[0.98388743,0.014676227,0.0011188436,0.00009755596,0.000016489277,0.0002034333],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.012453896,0.000118720454,0.0005983061,0.000039855007,0.0013293064,0.000012552252,0.00016019453,0.00016389064,0.00004467413],"category_scores_gemma":[0.006895059,0.00007866266,0.00017610686,0.000039680523,0.0029539256,0.00024466915,0.000092764356,0.00063163444,0.000008058452],"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":[0.000050500774,0.000063686464,0.9879983,5.363544e-7,0.00007054781,0.000006345497,0.0009908831,0.0000058948067,0.0000041623402,0.0005152755,0.0075152307,0.0027786568],"study_design_scores_gemma":[0.0006151731,0.00018187435,0.9781901,0.0000095660525,0.00008801687,0.00003512392,0.0018352648,0.000112342765,5.2488986e-7,0.000926903,0.017922128,0.00008295004],"about_ca_topic_score_codex":0.00004414485,"about_ca_topic_score_gemma":0.0001919987,"teacher_disagreement_score":0.011737543,"about_ca_system_score_codex":0.00008088072,"about_ca_system_score_gemma":0.00008216485,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W2959374711","doi":"10.1016/j.jclinepi.2019.07.003","title":"A guidance was developed to identify participants with missing outcome data in randomized controlled trials","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Impact; McMaster University","funders":"","keywords":"Randomized controlled trial; Missing data; Medicine; Outcome (game theory); Statistics; Surgery; Mathematics","score_opus":0.9695328181265813,"score_gpt":0.7508663805780501,"score_spread":0.2186664375485312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959374711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80882883,0.0025283252,0.14914319,0.0330036,0.0024588965,0.003085882,0.00000849483,0.0000025100403,0.0009402793],"genre_scores_gemma":[0.90096045,0.0001559399,0.08828575,0.0076114973,0.00045441883,0.00002918766,0.0000020874074,0.00001455652,0.0024861326],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.108542666,0.64113593,0.24295487,0.0017888997,0.0046697445,0.0009078674],"domain_scores_gemma":[0.01110389,0.87148625,0.10954627,0.00495984,0.0021627056,0.00074102497],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9664545,0.00037316873,0.10306393,0.0006261999,0.000041769934,0.00021166279,0.004144788,0.00028009646,0.003669197],"category_scores_gemma":[0.98948216,0.00012218105,0.008084062,0.0008715676,0.00016993906,0.00037738337,0.00034907553,0.0007528904,0.0015029173],"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":[0.055072606,0.000113385126,0.91848546,0.000026715486,0.0019184625,0.00003665125,0.000077316196,0.000707445,0.000012514272,0.000624359,0.013537243,0.009387832],"study_design_scores_gemma":[0.36951333,0.0004573509,0.52997154,0.0008166952,0.003149301,0.000082451974,0.00025218076,0.034781754,0.0000015870828,0.029010603,0.031537063,0.00042613922],"about_ca_topic_score_codex":0.000014864342,"about_ca_topic_score_gemma":0.000059271002,"teacher_disagreement_score":0.38851395,"about_ca_system_score_codex":0.000028120363,"about_ca_system_score_gemma":0.0005543633,"threshold_uncertainty_score":0.99927455},"labels":[],"label_agreement":null},{"id":"W2961552777","doi":"10.1016/j.jclinepi.2019.07.005","title":"A randomized trial provided new evidence on the accuracy and efficiency of traditional vs. electronically annotated abstraction approaches in systematic reviews","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; National Research Council Canada","funders":"Agency for Healthcare Research and Quality; Patient-Centered Outcomes Research Institute","keywords":"Abstraction; Computer science; Confidence interval; Software verification; Randomized controlled trial; Odds ratio; Data mining; Medicine; Programming language; Software; Surgery; Internal medicine; Software system","score_opus":0.9429509968337885,"score_gpt":0.632094509033019,"score_spread":0.31085648780076947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961552777","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9452121,0.009277334,0.010511819,0.024199393,0.00082945917,0.0092410995,0.0000016358063,0.000002104231,0.00072501367],"genre_scores_gemma":[0.9939444,0.0021280274,0.0019221115,0.0012474812,0.00032455722,0.00006441519,7.4042214e-7,0.0000068878103,0.00036140153],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.57404643,0.3272236,0.09401342,0.0010372467,0.0032320428,0.00044725987],"domain_scores_gemma":[0.058354244,0.8645419,0.07430615,0.0017764588,0.0007645999,0.00025668426],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7771569,0.00028921053,0.02286611,0.00033194822,0.00004060605,0.00008190505,0.0015044174,0.00026220575,0.00083296647],"category_scores_gemma":[0.94958144,0.00009772418,0.00489393,0.00069086486,0.00024099645,0.00032345232,0.000048204867,0.0010942569,0.00019909127],"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":[0.76179266,0.0022320074,0.018929549,0.0072908825,0.0021186697,0.000014512446,0.000594957,0.0024045538,0.00009213628,0.14582661,0.040884312,0.017819177],"study_design_scores_gemma":[0.6342304,0.009613557,0.037512466,0.020751001,0.0027972064,0.00034419913,0.00058673625,0.07712245,0.000014805034,0.21277915,0.0035568818,0.000691173],"about_ca_topic_score_codex":0.000010261253,"about_ca_topic_score_gemma":0.0000065896775,"teacher_disagreement_score":0.5373182,"about_ca_system_score_codex":0.00003627072,"about_ca_system_score_gemma":0.0005398382,"threshold_uncertainty_score":0.99164045},"labels":[],"label_agreement":null},{"id":"W2965172115","doi":"10.1016/j.jclinepi.2019.07.014","title":"New evidence for concern over the risk of birth defects from medications for nausea and vomitting of pregnancy","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pregnancy and Medication Impact","field":"Medicine","cited_by":26,"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; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Canadian Institutes of Health Research","keywords":"Nausea; Pregnancy; Medicine; Obstetrics; Internal medicine; Biology","score_opus":0.3464966216972064,"score_gpt":0.5424559342680731,"score_spread":0.19595931257086674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965172115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8943129,0.024675732,0.0702752,0.009046407,0.00078050746,0.0008094447,0.00004841324,0.0000048722077,0.000046472585],"genre_scores_gemma":[0.9677449,0.011356041,0.018731426,0.0013245526,0.00066581875,0.000009528302,0.0000033720194,0.000010828863,0.00015357329],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99583757,0.00084356056,0.0028002367,0.00017541139,0.0001595639,0.0001836636],"domain_scores_gemma":[0.8583073,0.13542098,0.005260418,0.00035823422,0.00035400654,0.00029905172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010360506,0.00009645212,0.0015369003,0.000053253396,0.000030382675,0.0000012458487,0.00020339267,0.00022838742,0.00007944827],"category_scores_gemma":[0.1891281,0.000053090087,0.00049269485,0.00006930874,0.0002804502,0.0000878398,0.0000325274,0.00042439724,0.0000013037779],"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":[0.000937434,0.00006658332,0.9501001,0.00023375238,0.00051988545,4.1084917e-7,0.0002035426,0.000012540789,0.0002432681,0.0011072304,0.0030570314,0.04351818],"study_design_scores_gemma":[0.005415059,0.0020911996,0.9673466,0.0052154507,0.0009415315,0.000016383718,0.00007243047,0.0009932341,0.00019762492,0.014738749,0.0029176732,0.000054037806],"about_ca_topic_score_codex":0.000067043526,"about_ca_topic_score_gemma":0.000007768072,"teacher_disagreement_score":0.17876759,"about_ca_system_score_codex":0.000012507406,"about_ca_system_score_gemma":0.000754662,"threshold_uncertainty_score":0.81770223},"labels":[],"label_agreement":null},{"id":"W2966276524","doi":"10.1016/j.jclinepi.2019.07.012","title":"Poor quality patient reported outcome measures bias effect estimates in orthopaedic randomized studies","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University","funders":"","keywords":"Medicine; Prom; Sample size determination; Randomized controlled trial; Patient-reported outcome; Publication bias; Physical therapy; Orthopedic surgery; Statistics; Meta-analysis; Quality of life (healthcare); Internal medicine; Surgery; Mathematics","score_opus":0.9529865251177858,"score_gpt":0.713398364297704,"score_spread":0.23958816082008183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966276524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97910744,0.0069355383,0.0029333492,0.0061127055,0.003336773,0.0010278907,0.0000015965667,0.0000037221228,0.00054099644],"genre_scores_gemma":[0.9890255,0.00055671757,0.006952655,0.0027094716,0.00021203338,0.000018194492,8.964795e-7,0.000010758703,0.00051381625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.26378065,0.54217225,0.18620145,0.0014934153,0.0056714593,0.0006808041],"domain_scores_gemma":[0.019159557,0.8673112,0.107136525,0.002700622,0.0032630642,0.0004290624],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.91246843,0.00042450512,0.048656363,0.00058134797,0.00004832837,0.000063359876,0.0012843392,0.00035306538,0.0012224788],"category_scores_gemma":[0.98478895,0.00015279281,0.013922499,0.0007530529,0.00042524593,0.00019583027,0.00019455893,0.00109343,0.0006574141],"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":[0.005074419,0.00009685362,0.967586,0.000070504284,0.0014807857,0.000043243133,0.00008763804,0.0005206184,0.000002820659,0.00051182765,0.004827946,0.019697374],"study_design_scores_gemma":[0.0460541,0.0011691612,0.8785498,0.0003242305,0.0012326238,0.00015937125,0.00037080343,0.0042907163,0.00000396248,0.05812908,0.009407172,0.0003089543],"about_ca_topic_score_codex":0.000035042656,"about_ca_topic_score_gemma":0.00003766249,"teacher_disagreement_score":0.32513893,"about_ca_system_score_codex":0.000046080793,"about_ca_system_score_gemma":0.00016246244,"threshold_uncertainty_score":0.99969053},"labels":[],"label_agreement":null},{"id":"W2967247666","doi":"10.1016/j.jclinepi.2019.08.004","title":"Most guideline organizations lack explicit guidance in how to incorporate cost considerations","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":21,"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":"Instituto de Salud Carlos III","keywords":"Guideline; MEDLINE; Medicine; Psychological intervention; Cochrane Library; Process (computing); Documentation; Family medicine; Computer science; Alternative medicine; Nursing; Political science; Pathology","score_opus":0.7863082502481794,"score_gpt":0.6668223713742016,"score_spread":0.11948587887397777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967247666","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":[0.000058180372,0.7896512,0.03563013,0.16666894,0.0040650927,0.0034742805,0.00016261273,0.00003551805,0.0002540442],"genre_scores_gemma":[0.000088951136,0.88434935,0.069961146,0.041433223,0.0032153924,0.000040549734,0.00033381564,0.000106495696,0.00047110047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.961889,0.008657044,0.027586855,0.00080562744,0.00045511907,0.0006063543],"domain_scores_gemma":[0.77793777,0.18609466,0.026621513,0.0015798741,0.0064354823,0.0013307179],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049108453,0.00059246167,0.012789209,0.00072788855,0.000065556465,0.000033337084,0.00044721417,0.0012690688,0.00065159117],"category_scores_gemma":[0.7406707,0.00044725454,0.0011889718,0.0014324533,0.00016651241,0.00030015444,0.00027018008,0.0034041856,0.00048855296],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022896416,0.0006455631,0.012982892,0.0021448485,0.0006263152,0.00030115154,0.000022426093,0.00041199537,0.0000012640521,0.0027636392,0.5370312,0.44283974],"study_design_scores_gemma":[0.0023371796,0.0011115782,0.0012528928,0.006027371,0.0018617691,0.0010000545,0.00003846719,0.00025766678,1.7889906e-7,0.0022145808,0.9835613,0.00033697975],"about_ca_topic_score_codex":0.00005923469,"about_ca_topic_score_gemma":0.00017060735,"teacher_disagreement_score":0.69156224,"about_ca_system_score_codex":0.00035981857,"about_ca_system_score_gemma":0.007092908,"threshold_uncertainty_score":0.99979794},"labels":[],"label_agreement":null},{"id":"W2969519704","doi":"10.1016/j.jclinepi.2019.08.006","title":"The ethics of cluster randomized trials: response to a proposal for revision of the Ottawa Statement","year":2019,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa; Western University","funders":"Canadian Institutes of Health Research","keywords":"Statement (logic); Cluster randomised controlled trial; Cluster (spacecraft); Consolidated Standards of Reporting Trials; Randomized controlled trial; Medicine; Family medicine; MEDLINE; Library science; Political science; Computer science; Law; Internal medicine","score_opus":0.7910458866083294,"score_gpt":0.712700578102686,"score_spread":0.07834530850564336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969519704","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016551567,0.0011128343,0.012648939,0.97327536,0.005134047,0.006015113,0.00006351362,0.0000038787057,0.00009118147],"genre_scores_gemma":[0.0013620461,0.011770934,0.052342374,0.9180936,0.009143078,0.00005532087,0.0000102060585,0.00009338085,0.007129063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.26148614,0.6345975,0.09344379,0.0016351815,0.006821625,0.002015748],"domain_scores_gemma":[0.009272017,0.95471394,0.027245976,0.0018281757,0.006661324,0.00027856336],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8720214,0.00039334342,0.016411271,0.00024935554,0.00012151923,0.000012181499,0.001857437,0.005975018,0.00006464378],"category_scores_gemma":[0.99330175,0.00015231912,0.008416538,0.00023194391,0.0030971775,0.000035976173,0.0006096531,0.031051153,0.0000128339925],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.38627404,0.00012056478,0.0003220463,0.0013129255,0.0011216493,0.000012689229,0.00007121606,0.000025920559,0.000016100248,0.0017389123,0.6070645,0.0019194478],"study_design_scores_gemma":[0.089375444,0.0067866263,0.00031436048,0.0050722593,0.0012684922,0.000032939923,0.00003345426,0.00016252554,0.00002859458,0.10003111,0.7967668,0.00012738313],"about_ca_topic_score_codex":0.00002092081,"about_ca_topic_score_gemma":0.000019501818,"teacher_disagreement_score":0.32011643,"about_ca_system_score_codex":0.00013985368,"about_ca_system_score_gemma":0.011733959,"threshold_uncertainty_score":0.99961585},"labels":[],"label_agreement":null},{"id":"W2970056769","doi":"10.1016/j.jclinepi.2019.08.008","title":"Colorectal cancer guidelines seldom include the patient perspective","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact; Health Sciences Centre","funders":"Instituto de Salud Carlos III","keywords":"Guideline; Perspective (graphical); Preference; MEDLINE; Medicine; Colorectal cancer; Family medicine; Inclusion (mineral); Cancer; Psychology; Internal medicine; Computer science; Pathology; Social psychology","score_opus":0.8204643862252715,"score_gpt":0.7181722353778527,"score_spread":0.10229215084741883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970056769","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":[0.0003370374,0.94265586,0.0003349534,0.047950324,0.0069739153,0.001383245,0.000053513577,0.000015799265,0.00029537067],"genre_scores_gemma":[0.00006287091,0.96888065,0.004738097,0.017568393,0.00845008,0.00004043733,0.00002857804,0.000073387135,0.00015748719],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9609569,0.012224122,0.024954805,0.0006663257,0.0006418114,0.0005560755],"domain_scores_gemma":[0.7312726,0.23072046,0.03168031,0.00086680223,0.00484313,0.00061675516],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048075397,0.0005760452,0.012832353,0.00022443847,0.00009292251,0.000013748439,0.0006474354,0.0012680569,0.0005512814],"category_scores_gemma":[0.53893155,0.00028436055,0.00517978,0.00036037088,0.0004775688,0.00014159725,0.00035824458,0.005097697,0.00017766791],"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":[0.00061502494,0.00025912747,0.0021918814,0.0011833983,0.0020268424,0.00006325908,0.000044019285,0.000025421414,1.15388836e-7,0.00037793568,0.101631224,0.8915818],"study_design_scores_gemma":[0.0014922444,0.002660127,0.0009552307,0.0063821543,0.007856804,0.0012391142,0.0002827943,0.00010485871,1.0720648e-7,0.001132444,0.9776533,0.0002408183],"about_ca_topic_score_codex":0.00031654438,"about_ca_topic_score_gemma":0.000069579844,"teacher_disagreement_score":0.8913409,"about_ca_system_score_codex":0.0005260603,"about_ca_system_score_gemma":0.005487121,"threshold_uncertainty_score":0.99996084},"labels":[],"label_agreement":null},{"id":"W2971042416","doi":"10.1016/j.jclinepi.2019.08.007","title":"Training researchers in publication science: why, what, and how","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; Queen's University; Ottawa Public Health; SickKids Foundation; University of Toronto; St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; Hospital for Sick Children","funders":"Canada Research Chairs; Ontario SPOR SUPPORT Unit","keywords":"Medical education; Training (meteorology); MEDLINE; Data science; Medicine; Library science; Computer science; Biology; Geography","score_opus":0.9615521669344763,"score_gpt":0.7569815892662182,"score_spread":0.20457057766825815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971042416","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":[0.8839457,0.0013985785,0.00109942,0.10961985,0.0015511914,0.00013242141,9.063684e-7,0.000002656911,0.0022492756],"genre_scores_gemma":[0.98973984,0.0031911572,0.0036157954,0.0024675657,0.00021887317,0.0000011163993,2.5605962e-7,0.0000047799367,0.00076060044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97752327,0.008062539,0.0051733702,0.000985291,0.0070661916,0.0011893637],"domain_scores_gemma":[0.46088222,0.50913805,0.007637915,0.0017048895,0.01747363,0.003163303],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.61363477,0.00009657439,0.0014468947,0.036549635,0.00008808431,0.0014007752,0.002599847,0.0002591971,0.00026658454],"category_scores_gemma":[0.87481135,0.0000580945,0.00025725283,0.06586586,0.0013520353,0.0033316386,0.00056830613,0.0014300905,0.00006510694],"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":[0.00004624389,0.0000415624,0.5648722,0.0000017854985,0.000004879406,0.000004969927,0.000069709575,0.000015749458,0.000058772795,0.0022594412,0.006006334,0.42661834],"study_design_scores_gemma":[0.0008370933,0.00073045737,0.8733989,0.000028329465,0.0000017507865,0.000040397208,0.001697177,0.008052322,0.0000071938694,0.040627427,0.0745026,0.00007637666],"about_ca_topic_score_codex":0.000013468461,"about_ca_topic_score_gemma":0.000008686905,"teacher_disagreement_score":0.516641,"about_ca_system_score_codex":0.00008662779,"about_ca_system_score_gemma":0.001247482,"threshold_uncertainty_score":0.9996359},"labels":[],"label_agreement":null},{"id":"W2972628632","doi":"10.1016/j.jclinepi.2019.09.009","title":"A scoping review shows that several nonvalidated budget planning tools for randomized trials are available","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; Impact","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Universität Basel","keywords":"Randomized controlled trial; EconLit; Medical physics; MEDLINE; Clinical trial; Plan (archaeology); Medicine; Computer science; Surgery","score_opus":0.9569775467791036,"score_gpt":0.697192559181196,"score_spread":0.2597849875979076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972628632","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":[0.0000032025443,0.9510336,0.019101776,0.012104737,0.006580691,0.010104692,0.00058519153,0.000022917295,0.00046322393],"genre_scores_gemma":[6.4522567e-7,0.94704753,0.013057418,0.034539428,0.003673586,0.00053392386,0.00015957747,0.0001012818,0.0008866362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8176555,0.072279856,0.10740604,0.0013557825,0.0001975293,0.0011053139],"domain_scores_gemma":[0.184389,0.6393793,0.1740132,0.001154313,0.00043692786,0.00062722876],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.72460145,0.00079736207,0.09633509,0.00062569446,0.00014050161,0.00010077905,0.0011949717,0.0018097765,0.0015562614],"category_scores_gemma":[0.86324453,0.0006482087,0.012006598,0.00021356856,0.00024122518,0.0007374584,0.00014540544,0.0019984231,0.0018257375],"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":[0.0030052753,0.00015808496,0.0006882147,0.43742713,0.0037891145,0.000009904531,0.000039609436,0.00011935993,1.5639723e-9,0.003976122,0.5203778,0.030409368],"study_design_scores_gemma":[0.019821923,0.00017071678,0.0000062387817,0.30529797,0.0011411214,0.000067996676,0.000011685358,0.000290436,4.8600044e-9,0.0026936012,0.67005926,0.000439045],"about_ca_topic_score_codex":0.000027019567,"about_ca_topic_score_gemma":0.0000048021243,"teacher_disagreement_score":0.6332665,"about_ca_system_score_codex":0.00044880007,"about_ca_system_score_gemma":0.0024643252,"threshold_uncertainty_score":0.9995969},"labels":[],"label_agreement":null},{"id":"W2972807049","doi":"10.1016/j.jclinepi.2019.09.008","title":"Letter in response to Thompson and Scott Authors’ letter reestablished search filters may miss studies when identifying randomized controlled trials. Language for trial phase necessary when searching for RCT","year":2019,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Randomized controlled trial; Scopus; Medicine; MEDLINE; Psychology; Surgery; Biology","score_opus":0.9058728487789814,"score_gpt":0.7010529576044545,"score_spread":0.20481989117452692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972807049","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04175817,0.0061864126,0.083285965,0.84632397,0.0073284693,0.014958956,0.00012071782,0.0000049544287,0.000032367927],"genre_scores_gemma":[0.0016155117,0.00050982885,0.08036903,0.8632163,0.027061451,0.0010380943,0.000057576002,0.00011870154,0.026013514],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.17828579,0.6958359,0.11625615,0.0028919927,0.0050977725,0.001632429],"domain_scores_gemma":[0.06275195,0.8809736,0.050753452,0.0025199736,0.0025614786,0.00043958897],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.94102764,0.0010282261,0.09532757,0.0029157512,0.00019352323,0.00089518866,0.0031370996,0.0016719055,0.00084599387],"category_scores_gemma":[0.96983355,0.0004474278,0.025065638,0.00042189067,0.0004992297,0.00050441385,0.00044013315,0.0044765,0.000063943306],"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":[0.4131093,0.000058977013,0.000117839976,0.000281864,0.0030632652,0.00008629583,0.0010258568,0.000033810855,0.000022258646,0.000008906924,0.57884514,0.0033464616],"study_design_scores_gemma":[0.51315343,0.0014029621,0.000034489214,0.0009195465,0.002834732,0.000027084581,0.00038004175,0.0025690643,0.0000015070175,0.009843816,0.46845326,0.00038007458],"about_ca_topic_score_codex":0.000025528137,"about_ca_topic_score_gemma":0.000015524489,"teacher_disagreement_score":0.1851377,"about_ca_system_score_codex":0.000119580465,"about_ca_system_score_gemma":0.00062601705,"threshold_uncertainty_score":0.99979776},"labels":[],"label_agreement":null},{"id":"W2972873725","doi":"10.1016/j.jclinepi.2019.09.004","title":"Rapid reviews of medical tests used many similar methods to systematic reviews but key items were rarely reported: a scoping review","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University; University of Toronto; St. Michael's Hospital; Canadian Agency for Drugs and Technologies in Health","funders":"European Social Fund; Instituto de Salud Carlos III; Canada Research Chairs","keywords":"Key (lock); Systematic review; Medicine; Management science; Computer science; MEDLINE; Engineering; Biology","score_opus":0.9726130047355873,"score_gpt":0.7656639066092733,"score_spread":0.206949098126314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972873725","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010308135,0.9242556,0.046804223,0.0040336116,0.0050696624,0.019243788,0.000021199725,0.0000075285257,0.0005633664],"genre_scores_gemma":[1.1468771e-7,0.9000607,0.08810542,0.008316315,0.0013851479,0.0004541176,0.0000149433245,0.00009588595,0.0015673363],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.069311254,0.58982223,0.32667723,0.0031829092,0.009856763,0.0011496205],"domain_scores_gemma":[0.027004138,0.5655604,0.38584313,0.0146220075,0.0043673594,0.0026029667],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.95344895,0.002315497,0.2775731,0.0018125928,0.00012358968,0.00020068415,0.013932785,0.0029622407,0.015363736],"category_scores_gemma":[0.9841883,0.00093349884,0.072871976,0.004033493,0.00043488524,0.00037906657,0.0012565112,0.0051339976,0.006316573],"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":[0.000005956067,0.000090186404,0.00008649399,0.47588688,0.0011697398,0.000057756675,0.0000124789685,8.7447904e-7,4.3428233e-8,0.00012879836,0.12321997,0.39934084],"study_design_scores_gemma":[0.00016294203,0.00028760632,0.000008082766,0.47675818,0.009506649,0.0009960978,0.000008037894,0.000049982675,1.5385979e-8,0.00026441322,0.5115947,0.00036329989],"about_ca_topic_score_codex":0.0000085690845,"about_ca_topic_score_gemma":0.000011299156,"teacher_disagreement_score":0.39897755,"about_ca_system_score_codex":0.00016924672,"about_ca_system_score_gemma":0.0036097176,"threshold_uncertainty_score":0.99931157},"labels":[],"label_agreement":null},{"id":"W2973239684","doi":"10.1016/j.jclinepi.2019.09.010","title":"Comparison of bias adjustment methods in meta-analysis suggests that quality effects modeling may have less limitations than other approaches","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":59,"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":"Weighting; Meta-analysis; Publication bias; Context (archaeology); Computer science; Econometrics; Quality (philosophy); Selection bias; Statistics; Medicine; Mathematics","score_opus":0.9963492713835682,"score_gpt":0.7933603616672651,"score_spread":0.20298890971630312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973239684","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000092193244,0.70715517,0.28976747,0.0005428579,0.00085428916,0.0010474819,0.000027062095,0.000001625575,0.000511866],"genre_scores_gemma":[0.0025748513,0.8083227,0.18671976,0.00037692804,0.00029167454,0.00008814929,0.000021768741,0.000047466132,0.0015566938],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.22874069,0.6299505,0.13409658,0.0021551445,0.0043681776,0.0006888546],"domain_scores_gemma":[0.13424197,0.6999603,0.15807249,0.0055415374,0.0016685749,0.00051512575],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.81280273,0.0011039885,0.16024135,0.0026149445,0.000057895064,0.00010646626,0.0042686174,0.0015221768,0.00089877076],"category_scores_gemma":[0.6666845,0.00044575948,0.09261033,0.002471529,0.0002958758,0.00021465863,0.00036084116,0.0025892116,0.00015422374],"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":[0.000032021322,0.0007356149,0.0542433,0.0055334587,0.2158228,0.0000039907018,0.00021282627,0.037181765,2.9719565e-8,0.0031397385,0.0016304677,0.68146396],"study_design_scores_gemma":[0.0004689857,0.0003734626,0.0039688554,0.0011748619,0.6843278,0.000018802764,0.00074556813,0.084770344,2.48273e-7,0.009516973,0.21398373,0.0006504047],"about_ca_topic_score_codex":0.00009949092,"about_ca_topic_score_gemma":0.00036128503,"teacher_disagreement_score":0.68081355,"about_ca_system_score_codex":0.000096666205,"about_ca_system_score_gemma":0.0005629109,"threshold_uncertainty_score":0.99979943},"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":"W2978031190","doi":"10.1016/j.jclinepi.2019.09.021","title":"Multiple uses of forest plots in presenting analysis results in health research: A Tutorial","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Urban Green Space and Health","field":"Environmental Science","cited_by":38,"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; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"Research Institute of St. Joe's Hamilton","keywords":"Data science; Statistics; Computer science; Geography; Mathematics","score_opus":0.5274029841848205,"score_gpt":0.554777326272263,"score_spread":0.027374342087442494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978031190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916384,0.000114134615,0.00006847484,0.007261887,0.00044102245,0.00016733314,0.0000049379682,0.000002494135,0.00030130483],"genre_scores_gemma":[0.9958158,0.00043295816,0.002760412,0.00046479932,0.0003308725,0.0000015292519,0.0000019834683,0.0000075610515,0.00018408187],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.982589,0.009507235,0.006339714,0.0003802902,0.00048386666,0.00069989235],"domain_scores_gemma":[0.9551225,0.041099127,0.0030650136,0.0003551426,0.000054846623,0.0003034163],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09583226,0.00010390256,0.0022310207,0.0004389607,0.000031668922,0.000003591123,0.00042309775,0.00025051524,0.00013007257],"category_scores_gemma":[0.07565713,0.00007922384,0.00040958487,0.001074218,0.00033482656,0.0001678983,0.00021336034,0.0014068304,0.000048875707],"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":[0.00089764665,0.00027245033,0.97901994,0.000023791199,0.000043245655,0.000012181048,0.00022921382,0.016215174,0.000010078379,0.00010602912,0.002247438,0.0009227917],"study_design_scores_gemma":[0.002124773,0.00089796056,0.98542947,0.000078960526,0.000011181991,0.000002512027,0.000094234754,0.005707229,9.3538614e-7,0.0014011576,0.004195657,0.000055937326],"about_ca_topic_score_codex":0.017200185,"about_ca_topic_score_gemma":0.08005598,"teacher_disagreement_score":0.062855795,"about_ca_system_score_codex":0.00017504075,"about_ca_system_score_gemma":0.00021118895,"threshold_uncertainty_score":0.98934436},"labels":[],"label_agreement":null},{"id":"W2978340128","doi":"10.1016/j.jclinepi.2019.09.024","title":"More comprehensive reporting of methods in studies using respondent driven sampling is required: a systematic review of the uptake of the STROBE-RDS guidelines","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":30,"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","funders":"","keywords":"Respondent; CINAHL; Medicine; Scopus; Family medicine; Sample size determination; MEDLINE; Population; Inclusion (mineral); Quality (philosophy); Systematic sampling; Environmental health; Psychology; Statistics; Psychological intervention; Nursing; Pathology","score_opus":0.9007801005000072,"score_gpt":0.7368348505140716,"score_spread":0.16394524998593563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978340128","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":[0.0023921053,0.9907645,0.0006644689,0.0019171487,0.0016673363,0.0025455635,0.000027154634,0.0000039354886,0.000017810087],"genre_scores_gemma":[0.000034191788,0.9222743,0.07539229,0.0017572911,0.000405093,0.000012310884,0.000001974722,0.000054942833,0.00006758988],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8893145,0.031262536,0.077335365,0.000636873,0.0009266371,0.00052410795],"domain_scores_gemma":[0.59789443,0.14454897,0.24561249,0.0037998185,0.007849842,0.00029449628],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12726961,0.0006007135,0.03762253,0.0003453627,0.000046617613,0.0000022531885,0.0012124635,0.0008302842,0.000012325226],"category_scores_gemma":[0.723195,0.00026313303,0.006337532,0.00088204443,0.0008443431,0.00005913321,0.0007650851,0.0026806155,0.0000010609476],"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":[0.000091536385,0.00012067367,0.002401576,0.94998497,0.002978514,0.000019417284,0.00042042285,0.00020501419,0.000020291185,0.00004819783,0.00058769446,0.043121714],"study_design_scores_gemma":[0.00057034916,0.00042216576,0.0007911863,0.9671567,0.013672749,0.00092287076,0.0021121516,0.00025402033,0.0000026487319,0.00022555678,0.013699423,0.0001701723],"about_ca_topic_score_codex":0.00003153496,"about_ca_topic_score_gemma":0.000003911373,"teacher_disagreement_score":0.5959254,"about_ca_system_score_codex":0.0002357716,"about_ca_system_score_gemma":0.00246481,"threshold_uncertainty_score":0.99998206},"labels":[],"label_agreement":null},{"id":"W2979201572","doi":"10.1016/j.jclinepi.2019.09.018","title":"Reporting of randomized factorial trials was frequently inadequate","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Schulich School of Medicine and Dentistry; Cancer Research UK","keywords":"Factorial; Factorial experiment; Medicine; Clinical trial; Randomized controlled trial; Research design; Psychological intervention; Factorial analysis; Sample size determination; Statistics; Internal medicine; Mathematics; Nursing","score_opus":0.9837821651697639,"score_gpt":0.7642308995158902,"score_spread":0.21955126565387373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979201572","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051638926,0.9524184,0.025667176,0.0005983508,0.017460195,0.00230875,0.000027391869,0.0000019464276,0.0014661399],"genre_scores_gemma":[0.000070322734,0.982401,0.009890521,0.0002660584,0.0052738152,0.000020419591,0.000010120858,0.00003401597,0.0020337235],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.016132519,0.53504413,0.4429302,0.0011896197,0.004246171,0.000457386],"domain_scores_gemma":[0.0023797166,0.5162506,0.4750124,0.0029456876,0.0030518067,0.00035977672],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.98286366,0.0009645573,0.35834908,0.0012236688,0.000053390908,0.00013727778,0.0049540997,0.002047963,0.0061805057],"category_scores_gemma":[0.9975954,0.0003286273,0.14449053,0.0010471442,0.000526484,0.00021403341,0.00032909965,0.0030007998,0.0011341978],"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":[0.0016929541,0.00009035384,0.00072631845,0.0037105207,0.007948029,0.000035052195,0.000020965308,0.000021121845,5.5034366e-8,0.0033350128,0.04466886,0.93775076],"study_design_scores_gemma":[0.012438442,0.00022847361,0.00002887574,0.0057244264,0.016263673,0.00017546744,0.000012887464,0.0000977809,4.0972754e-8,0.03979006,0.92500275,0.00023712474],"about_ca_topic_score_codex":0.00001733941,"about_ca_topic_score_gemma":0.0000021958383,"teacher_disagreement_score":0.93751365,"about_ca_system_score_codex":0.0000664152,"about_ca_system_score_gemma":0.0023515928,"threshold_uncertainty_score":0.99991655},"labels":[],"label_agreement":null},{"id":"W2979656586","doi":"10.1016/j.jclinepi.2019.09.022","title":"Validation of five search filters for retrieval of clinical practice guidelines produced low precision","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Cochrane; University of British Columbia","funders":"","keywords":"Information retrieval; MEDLINE; Guideline; Computer science; Sensitivity (control systems); Filter (signal processing); Medicine; Data mining; Medical physics","score_opus":0.6973041611700598,"score_gpt":0.6894916784184253,"score_spread":0.007812482751634486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979656586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92037004,0.00021191663,0.0152279455,0.058947667,0.003705805,0.0013603618,0.000029690938,0.000009494317,0.00013708854],"genre_scores_gemma":[0.6402626,0.0020496254,0.34349275,0.009543549,0.004131574,0.000004447196,0.00007499752,0.00004933272,0.00039113464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9572049,0.008309833,0.03232538,0.00068126916,0.0010318767,0.0004467515],"domain_scores_gemma":[0.5259165,0.42308572,0.029201034,0.0011960648,0.019979024,0.00062167074],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18407345,0.00023157492,0.0046050046,0.00023422,0.000029169032,0.000005224339,0.00038775505,0.0007029718,0.00021279955],"category_scores_gemma":[0.9052808,0.00016926287,0.0017773136,0.00031823738,0.0003250824,0.00050252996,0.00014454672,0.0015110784,0.000027035276],"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":[0.13178591,0.0043753195,0.5269453,0.001239272,0.002291209,0.00002993641,0.00018857993,0.0045402152,0.006591373,0.0006030485,0.1019597,0.21945016],"study_design_scores_gemma":[0.08156463,0.09198836,0.5976723,0.004221324,0.006534703,0.0010422417,0.0033746655,0.05434645,0.021058321,0.011242456,0.1259285,0.001026036],"about_ca_topic_score_codex":0.00004587903,"about_ca_topic_score_gemma":0.00000145011,"teacher_disagreement_score":0.7212074,"about_ca_system_score_codex":0.000049533686,"about_ca_system_score_gemma":0.0017093463,"threshold_uncertainty_score":0.8401681},"labels":[],"label_agreement":null},{"id":"W2979965235","doi":"10.1016/j.jclinepi.2019.09.025","title":"Overviews of reviews incompletely report methods for handling overlapping, discordant, and problematic data","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":79,"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; University of British Columbia","funders":"National Health and Medical Research Council; Monash University","keywords":"Systematic review; Protocol (science); Missing data; Medicine; Descriptive statistics; Sample size determination; MEDLINE; Population; Completeness (order theory); Interquartile range; Statistics; Medical physics; Psychology; Computer science; Family medicine; Alternative medicine; Pathology; Mathematics; Surgery; Environmental health","score_opus":0.9902519934726101,"score_gpt":0.8027920283479436,"score_spread":0.18745996512466645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979965235","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022101285,0.67093164,0.32429415,0.0003680057,0.0016683574,0.002505542,0.000056016248,0.000001011629,0.00017310529],"genre_scores_gemma":[3.8501943e-7,0.6157415,0.38256708,0.00026615185,0.000537492,0.000029016566,0.0000391945,0.000025287387,0.000793881],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30583742,0.3893199,0.29753134,0.0035723434,0.0028964328,0.0008425792],"domain_scores_gemma":[0.054661226,0.58096194,0.34885892,0.012732971,0.0022045274,0.0005803664],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8998416,0.00093774614,0.121628694,0.0007368217,0.00008369904,0.00014317669,0.007299055,0.00072134455,0.0006796619],"category_scores_gemma":[0.92889297,0.0003673801,0.021430835,0.00093059323,0.00036611586,0.00040923498,0.0014137593,0.0016236661,0.00013543094],"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":[0.000012795572,0.00006917579,0.00078334525,0.032976598,0.0013334884,0.000009667098,0.000012661814,0.0000025977192,1.5186377e-7,0.0008284503,0.053696707,0.9102744],"study_design_scores_gemma":[0.00028275803,0.00032069703,0.00015625404,0.02081291,0.007862642,0.0011615778,0.0000108517,0.0018324275,8.176589e-9,0.02372067,0.9435595,0.00027970105],"about_ca_topic_score_codex":0.0000055926034,"about_ca_topic_score_gemma":0.0000055480946,"teacher_disagreement_score":0.90999466,"about_ca_system_score_codex":0.00003461795,"about_ca_system_score_gemma":0.0009945626,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W2983079501","doi":"10.1016/j.jclinepi.2019.10.014","title":"GRADE guidelines 26: informative statements to communicate the findings of systematic reviews of interventions","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1188,"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; Cochrane; Impact","funders":"","keywords":"Grading (engineering); Certainty; CLARITY; Systematic review; Psychological intervention; Medicine; Psychology; Medical education; MEDLINE; Applied psychology; Nursing; Political science; Mathematics; Engineering","score_opus":0.9806397354455053,"score_gpt":0.7703581198119908,"score_spread":0.21028161563351455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983079501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74773705,0.019983139,0.16429852,0.052735757,0.0041506733,0.0081881285,0.00004725243,0.000005017203,0.0028544655],"genre_scores_gemma":[0.9254409,0.0057858764,0.058821756,0.006704325,0.00015505424,0.000037340764,0.000002328403,0.000018864752,0.0030335377],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.5005208,0.24283472,0.25156355,0.0005941144,0.0039953236,0.000491468],"domain_scores_gemma":[0.40506506,0.38737312,0.19191098,0.0071038185,0.008120141,0.00042687615],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.7451009,0.00023106489,0.020215688,0.0003878062,0.00004461509,0.000037739694,0.0044903094,0.00013932855,0.001895107],"category_scores_gemma":[0.8073615,0.00007832693,0.009592271,0.0008118977,0.00020150293,0.0003026933,0.00044072638,0.0005527588,0.0013916031],"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":[0.00014541496,0.00053776,0.49558955,0.021839442,0.0036209493,0.0000018931497,0.0019368747,0.0021349883,0.00002871162,0.018699527,0.44611585,0.009349046],"study_design_scores_gemma":[0.0037264014,0.006005561,0.32037574,0.07898101,0.0055880486,0.00018453605,0.009340196,0.0218222,0.00003803243,0.12420059,0.42890465,0.0008330187],"about_ca_topic_score_codex":0.000012492678,"about_ca_topic_score_gemma":0.000013123176,"teacher_disagreement_score":0.17770387,"about_ca_system_score_codex":0.000018438313,"about_ca_system_score_gemma":0.00008694707,"threshold_uncertainty_score":0.99938595},"labels":[],"label_agreement":null},{"id":"W2984364880","doi":"10.1016/j.jclinepi.2019.10.015","title":"GRADE guidelines 27: how to calculate absolute effects for time-to-event outcomes in summary of findings tables and Evidence Profiles","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"British Heart Foundation","keywords":"Event (particle physics); Absolute (philosophy); Statistics; Medicine; Psychology; Mathematics; Physics","score_opus":0.827267101805932,"score_gpt":0.6489289759367436,"score_spread":0.1783381258691884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984364880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91779816,0.00281125,0.015440762,0.06167625,0.00089954573,0.0013366834,0.000010583927,0.0000013634279,0.00002541637],"genre_scores_gemma":[0.7211476,0.0010360243,0.2334611,0.01509402,0.0006683968,0.00006210905,0.0000026123298,0.000039171762,0.028488971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93564826,0.02568456,0.0354031,0.0009804402,0.0017738267,0.0005098369],"domain_scores_gemma":[0.66613823,0.31427667,0.015802737,0.0013868265,0.0018817866,0.0005137282],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4355407,0.00027459834,0.013212109,0.00053338654,0.000028537734,0.000058484147,0.0013235767,0.00024196539,0.00039393207],"category_scores_gemma":[0.8119311,0.0001227131,0.0028987632,0.0005161693,0.00008815428,0.00023287178,0.0002390551,0.00031771365,0.00025945666],"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":[0.0001259345,0.000061667706,0.81351006,0.00019959916,0.00023666842,0.0000047730505,0.000043085798,0.001103756,0.00024884107,0.0002521833,0.17564505,0.008568377],"study_design_scores_gemma":[0.0010365475,0.0017252632,0.89682496,0.0018739203,0.00031947566,0.000027650323,0.00006400636,0.014312046,0.00004355123,0.012491092,0.07102458,0.00025692693],"about_ca_topic_score_codex":0.000014265769,"about_ca_topic_score_gemma":0.000016058282,"teacher_disagreement_score":0.3763904,"about_ca_system_score_codex":0.0000220661,"about_ca_system_score_gemma":0.00013111284,"threshold_uncertainty_score":0.90315336},"labels":[],"label_agreement":null},{"id":"W2984542815","doi":"10.1016/j.jclinepi.2019.10.011","title":"Excluding non-English publications from evidence-syntheses did not change conclusions: a meta-epidemiological study","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":421,"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 Agency for Drugs and Technologies in Health; Ottawa Hospital","funders":"","keywords":"English language; Confidence interval; Meta-analysis; Medicine; Systematic review; Inclusion and exclusion criteria; MEDLINE; Limiting; Cochrane Library; Psychology; Alternative medicine; Pathology; Internal medicine; Mathematics education","score_opus":0.9866438556249594,"score_gpt":0.7143336233163583,"score_spread":0.2723102323086011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984542815","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91648525,0.006871262,0.018318284,0.047946475,0.0058539947,0.0024669773,0.0000475318,0.00001812824,0.0019920988],"genre_scores_gemma":[0.96761787,0.0011365892,0.016909972,0.010308771,0.0026612803,0.000111618894,0.0000025034299,0.00001856262,0.001232806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5338129,0.34227264,0.11320795,0.0032382072,0.0063038017,0.0011645034],"domain_scores_gemma":[0.035356797,0.8865687,0.06542705,0.005598186,0.0060088653,0.0010403704],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.75956607,0.0006505835,0.03685863,0.00065054995,0.000227744,0.00025591592,0.0053853146,0.0006324784,0.034146067],"category_scores_gemma":[0.9749899,0.00025451355,0.01568557,0.0013058578,0.0003479153,0.0011648474,0.00095789385,0.0018729472,0.0029207265],"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":[0.00010419578,0.00049538375,0.93079996,0.000010493363,0.0035968157,0.000011919528,0.0004418692,0.00012141162,0.000006777247,0.0015464305,0.05204438,0.010820389],"study_design_scores_gemma":[0.0005460611,0.0014538219,0.85615104,0.00023134201,0.004379001,0.000024118244,0.0021255468,0.004677164,0.0000010325298,0.018266575,0.1118093,0.0003349789],"about_ca_topic_score_codex":0.00009715952,"about_ca_topic_score_gemma":0.000042346994,"teacher_disagreement_score":0.5442961,"about_ca_system_score_codex":0.000056144017,"about_ca_system_score_gemma":0.00024523595,"threshold_uncertainty_score":0.999996},"labels":[],"label_agreement":null},{"id":"W2985969131","doi":"10.1016/j.jclinepi.2019.11.009","title":"Frequent inappropriate use of unweighted summary statistics in systematic reviews of pathogen genotypes or genogroups","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"European and Developing Countries Clinical Trials Partnership; European Commission; Medical Research Council; Alexandria University; Department for International Development; Department for International Development, UK Government","keywords":"Systematic review; Statistics; Pooling; Summary statistics; Epidemiology; Medicine; Meta-analysis; Descriptive statistics; MEDLINE; Mathematics; Biology; Computer science; Pathology; Artificial intelligence","score_opus":0.9622883911138087,"score_gpt":0.6850832624077308,"score_spread":0.27720512870607794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985969131","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000091143134,0.9691203,0.024873044,0.00006369041,0.0016374806,0.003873284,0.00027289306,0.0000011957042,0.00006692063],"genre_scores_gemma":[0.000009248431,0.9224604,0.07606989,0.00022050417,0.00026359735,0.00003846918,0.000031165848,0.000038375332,0.0008683514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3006742,0.4393551,0.2538005,0.0014925667,0.0040014866,0.00067613786],"domain_scores_gemma":[0.22715066,0.4919369,0.271628,0.0053761164,0.003457603,0.00045075343],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7028401,0.00095267716,0.13247615,0.0014738794,0.000029484885,0.00006559039,0.0043337587,0.001328831,0.0020107848],"category_scores_gemma":[0.8497222,0.0003469784,0.018144907,0.0019035705,0.00035199587,0.00024181552,0.00038363787,0.0018797239,0.00060421805],"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":[0.00011417596,0.000445602,0.007708424,0.4315441,0.0033011467,0.000109589004,0.00007791371,0.000053897405,4.528486e-7,0.002869804,0.02736881,0.5264061],"study_design_scores_gemma":[0.00039543738,0.0007452919,0.0008340582,0.09468022,0.008669254,0.00017490752,0.000028360027,0.0005365584,2.7102804e-8,0.0050607976,0.88852,0.0003551114],"about_ca_topic_score_codex":0.000018820054,"about_ca_topic_score_gemma":0.00003255275,"teacher_disagreement_score":0.86115116,"about_ca_system_score_codex":0.000106894746,"about_ca_system_score_gemma":0.001450787,"threshold_uncertainty_score":0.99996763},"labels":[],"label_agreement":null},{"id":"W2987540665","doi":"10.1016/j.jclinepi.2019.11.008","title":"Overall bias methods and their use in sensitivity analysis of Cochrane reviews were not consistent","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Lethbridge","funders":"","keywords":"Systematic review; Meta-analysis; Medicine; Publication bias; Cochrane collaboration; Psychological intervention; MEDLINE; Reporting bias; Cochrane Library; Internal medicine; Biology; Psychiatry","score_opus":0.942833878443125,"score_gpt":0.7039335505284423,"score_spread":0.23890032791468274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987540665","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94956154,0.004723008,0.041132376,0.0033592125,0.0005970929,0.0003586879,0.000015100172,7.866148e-7,0.00025217407],"genre_scores_gemma":[0.90636986,0.0066447495,0.08107472,0.0050385506,0.00010963364,0.0000017930187,0.000002138346,0.00000772338,0.00075083505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4799373,0.4337839,0.082988724,0.0012127452,0.0016477412,0.00042962306],"domain_scores_gemma":[0.16369851,0.7600892,0.07018747,0.0034945132,0.002055533,0.00047475807],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8182604,0.0003028965,0.0347359,0.0009059336,0.000022782006,0.00005607398,0.0006913014,0.00033126897,0.0018894087],"category_scores_gemma":[0.80369854,0.000121479374,0.010077807,0.0012105664,0.0002635251,0.00022761535,0.0001734654,0.000792561,0.000093254486],"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":[0.000100563855,0.00010223812,0.9560052,0.000058447124,0.0017482869,0.000008279388,0.000078204066,0.00094084674,0.00012427577,0.0011520607,0.0035980702,0.036083516],"study_design_scores_gemma":[0.00050471816,0.00023525857,0.9140043,0.00017603008,0.0015260518,0.00004959934,0.000101510144,0.040592298,0.000006324053,0.0037199298,0.038960386,0.0001235886],"about_ca_topic_score_codex":0.000062381456,"about_ca_topic_score_gemma":0.00023353766,"teacher_disagreement_score":0.32630533,"about_ca_system_score_codex":0.000019765263,"about_ca_system_score_gemma":0.00010012022,"threshold_uncertainty_score":0.999836},"labels":[],"label_agreement":null},{"id":"W2988223630","doi":"10.1016/j.jclinepi.2019.11.010","title":"Mapping of reporting guidance for systematic reviews and meta-analyses generated a comprehensive item bank for future reporting guidelines","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":194,"is_retracted":false,"has_abstract":false,"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; University of Ottawa","keywords":"Systematic review; Meta-analysis; MEDLINE; Medicine; Accounting; Business; Political science; Pathology","score_opus":0.9762377715888775,"score_gpt":0.7278926392649833,"score_spread":0.2483451323238942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988223630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3956965,0.14372008,0.43447262,0.014006926,0.0032017133,0.008730084,0.000031746364,0.0000071454333,0.00013321049],"genre_scores_gemma":[0.101816915,0.0021169058,0.88274026,0.007500921,0.0025476604,0.00026395172,0.000009848232,0.000048045713,0.0029554826],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.5260676,0.08270552,0.38665238,0.0016738256,0.0022930999,0.000607571],"domain_scores_gemma":[0.04617668,0.3194657,0.61226267,0.0030218104,0.018734042,0.00033908937],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.79366195,0.0004966285,0.056836892,0.0004392973,0.00010948117,0.00009573118,0.0012186406,0.00038064676,0.00032632033],"category_scores_gemma":[0.97531533,0.00019444377,0.019391933,0.0007510234,0.00011611379,0.00022979033,0.00013665883,0.0004339657,0.00002134793],"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":[0.00039579786,0.00026662563,0.4402336,0.10014805,0.058389153,0.000054591586,0.0007820481,0.0053836904,0.0032441278,0.003562551,0.37336645,0.014173316],"study_design_scores_gemma":[0.003955957,0.0024485749,0.06531973,0.014422553,0.08157568,0.0024778924,0.007000096,0.2856967,0.00014101088,0.04325234,0.49208662,0.00162288],"about_ca_topic_score_codex":0.0000055850855,"about_ca_topic_score_gemma":0.000005939391,"teacher_disagreement_score":0.47989094,"about_ca_system_score_codex":0.000019761983,"about_ca_system_score_gemma":0.00018962227,"threshold_uncertainty_score":0.9904286},"labels":[],"label_agreement":null},{"id":"W2989878445","doi":"10.1016/j.jclinepi.2019.10.009","title":"Should the cost perspective be integrated in clinical guidelines?","year":2019,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Operationalization; Health care; Actuarial science; Psychological intervention; Economic evaluation; Quality of life (healthcare); Health economics; Perspective (graphical); Public economics; Cost effectiveness; Public health; Medicine; Business; Nursing; Risk analysis (engineering); Economics; Computer science; Economic growth","score_opus":0.8820058067851637,"score_gpt":0.6898423068917509,"score_spread":0.19216349989341286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989878445","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009225619,0.007365235,0.0032574064,0.25909752,0.72598994,0.0008957416,0.0005631363,0.0000150788655,0.0018934128],"genre_scores_gemma":[0.0007628063,0.015355462,0.004692265,0.08849684,0.8886202,0.000041095966,0.00010654676,0.00010976322,0.0018150089],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8759627,0.030798197,0.09018875,0.0015406226,0.00042042066,0.0010893577],"domain_scores_gemma":[0.23833352,0.65639883,0.09819298,0.002286271,0.0038464125,0.0009420032],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.56763417,0.0005963667,0.014984421,0.0006435485,0.00010511783,0.00005104637,0.0020924124,0.004795229,0.0005635164],"category_scores_gemma":[0.9087148,0.00046323254,0.0027829083,0.00034925056,0.0007716706,0.00034714106,0.00024278481,0.0105786985,0.0013165312],"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":[0.00029106342,0.00021472006,0.07073874,0.00008103835,0.0003382866,0.00000960155,0.00015060042,0.00030362525,5.1500733e-9,0.015288061,0.91209877,0.00048548993],"study_design_scores_gemma":[0.0026320042,0.00075216475,0.015575112,0.00042682403,0.00005486288,0.000012938602,0.0010279601,0.0023048106,8.8472545e-9,0.033375807,0.94345224,0.00038528672],"about_ca_topic_score_codex":0.0021714924,"about_ca_topic_score_gemma":0.0006819533,"teacher_disagreement_score":0.63762915,"about_ca_system_score_codex":0.0014468558,"about_ca_system_score_gemma":0.0044722063,"threshold_uncertainty_score":0.99978197},"labels":[],"label_agreement":null},{"id":"W2994530656","doi":"10.1016/j.jclinepi.2019.12.005","title":"Systematic review finds that appraisal tools for medical research studies address conflicts of interest superficially","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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":"Nordic Life Science Pipeline (Canada)","funders":"National Institute for Health and Care Research","keywords":"Critical appraisal; Medicine; Data science; Alternative medicine; Computer science; Pathology","score_opus":0.9844980612990476,"score_gpt":0.8193072565164125,"score_spread":0.16519080478263515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994530656","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":[0.00005078032,0.9767062,0.000059724156,0.00893559,0.009606895,0.0040695863,0.00028006954,0.00001653636,0.0002746186],"genre_scores_gemma":[0.00013649045,0.9866881,0.00014068415,0.009378278,0.0028919901,0.0002747761,0.00005868544,0.000071947594,0.00035908533],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.8806978,0.09384121,0.022180287,0.00086652895,0.00086866634,0.0015454905],"domain_scores_gemma":[0.30900902,0.67126447,0.013648302,0.0008861401,0.003217522,0.0019745615],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.24848409,0.0007807892,0.028733505,0.00044012666,0.00019616142,0.000014825416,0.002700689,0.006612608,0.00060926407],"category_scores_gemma":[0.65158355,0.00049321377,0.0046269703,0.00046708356,0.0022771938,0.0002497521,0.00060853537,0.019385492,0.00013670455],"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":[0.00044261338,0.00047501683,0.00008946909,0.7967892,0.004891154,0.00015216324,0.000050088536,0.0000013407196,1.2562758e-7,0.005929989,0.029365618,0.16181318],"study_design_scores_gemma":[0.0009862994,0.0011890674,0.0000039812153,0.36816204,0.006153284,0.0004371874,0.00007634773,0.000028677763,0.0000012058981,0.00041628873,0.62229806,0.00024759115],"about_ca_topic_score_codex":0.0000049446635,"about_ca_topic_score_gemma":0.000015763158,"teacher_disagreement_score":0.5929324,"about_ca_system_score_codex":0.00018092964,"about_ca_system_score_gemma":0.004043754,"threshold_uncertainty_score":0.9997519},"labels":[],"label_agreement":null},{"id":"W2995049945","doi":"10.1016/j.jclinepi.2019.11.019","title":"Grading of Recommendations Assessment, Development, and Evaluations (GRADE) notes: extremely serious, GRADE's terminology for rating down by three levels","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":102,"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","funders":"","keywords":"Terminology; Grading (engineering); Certainty; Stakeholder; Thematic analysis; Context (archaeology); Medicine; Rating system; Psychology; Medical education; Qualitative research; Engineering; Political science; Public relations","score_opus":0.9317008963606049,"score_gpt":0.6954483341648994,"score_spread":0.23625256219570556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995049945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.537464,0.000706732,0.4412118,0.018564608,0.0010475321,0.00070747244,0.000030705385,0.0000024976787,0.00026460737],"genre_scores_gemma":[0.6727981,0.0001387319,0.32526767,0.0010053666,0.00015313462,0.000020910307,0.000012359851,0.000012469471,0.00059125083],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9157015,0.035928003,0.04544547,0.00095798285,0.0014797081,0.00048733645],"domain_scores_gemma":[0.7388879,0.22491342,0.033461176,0.0010473832,0.0014394413,0.00025067732],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38264835,0.00027146758,0.008627522,0.00037266643,0.00017123486,0.000075281365,0.0011308772,0.00030670024,0.0016971704],"category_scores_gemma":[0.37492913,0.0001451279,0.0019785394,0.00036179757,0.00018945616,0.00031549882,0.00013251329,0.00058496307,0.000049170674],"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":[0.00001745577,0.00013416848,0.7479997,0.000051010855,0.0005749846,7.530843e-7,0.00010186185,0.000080992664,0.00031727197,0.0050722193,0.022524368,0.22312517],"study_design_scores_gemma":[0.0023161466,0.00087561173,0.66017014,0.0002236511,0.0006460469,0.00011338639,0.00044585468,0.027139945,0.00006260104,0.14069347,0.16697203,0.000341133],"about_ca_topic_score_codex":0.0000060887996,"about_ca_topic_score_gemma":0.00004500642,"teacher_disagreement_score":0.22278404,"about_ca_system_score_codex":0.000037035203,"about_ca_system_score_gemma":0.00043898483,"threshold_uncertainty_score":0.9992154},"labels":[],"label_agreement":null},{"id":"W2995284626","doi":"10.1016/j.jclinepi.2019.12.013","title":"No clear choice between Newcastle–Ottawa Scale and Appraisal Tool for Cross-Sectional Studies to assess methodological quality in cross-sectional studies of health-related quality of life and breast cancer","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":340,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Cross-sectional study; Intraclass correlation; Reliability (semiconductor); Concurrent validity; Scale (ratio); Medicine; Quality of life (healthcare); Inter-rater reliability; Breast cancer; Psychology; Psychometrics; Rating scale; Clinical psychology; Cancer; Pathology; Nursing; Internal medicine; Developmental psychology; Internal consistency","score_opus":0.7474219891393122,"score_gpt":0.6724955721454314,"score_spread":0.0749264169938808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995284626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98722315,0.004564343,0.0005678388,0.004632363,0.0023534652,0.00041325082,0.00021644722,0.000008100901,0.000021056385],"genre_scores_gemma":[0.9927559,0.0011685202,0.003354752,0.0015060675,0.0010817244,0.000017614366,0.0000065320005,0.000014792556,0.00009409117],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9818119,0.007759333,0.009052706,0.0005609605,0.0004117008,0.00040340086],"domain_scores_gemma":[0.863455,0.12895088,0.0047717835,0.00024163455,0.0022032487,0.00037745805],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07940537,0.00023108258,0.005452937,0.00014844869,0.0000787843,0.000007860706,0.00014917059,0.0005164669,0.000056824378],"category_scores_gemma":[0.14907545,0.00016617092,0.0005821303,0.00019873599,0.0010577376,0.00013505657,0.00016698476,0.00096589024,0.000001290415],"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":[0.0069652684,0.00017699844,0.9879047,0.0011277474,0.0009207305,7.065592e-7,0.00019817188,0.00015203853,0.00006244682,0.0003714897,0.00024478085,0.0018748905],"study_design_scores_gemma":[0.004626284,0.0022700331,0.99056304,0.00018501922,0.0000481277,0.000033936267,0.00032005142,0.000023119252,0.000003902394,0.0013145206,0.00047461945,0.00013733529],"about_ca_topic_score_codex":0.0019842174,"about_ca_topic_score_gemma":0.0010780072,"teacher_disagreement_score":0.12119155,"about_ca_system_score_codex":0.00012749199,"about_ca_system_score_gemma":0.00051195145,"threshold_uncertainty_score":0.9479459},"labels":[],"label_agreement":null},{"id":"W2995432752","doi":"10.1016/j.jclinepi.2019.12.009","title":"A common framework of steps and criteria for prioritizing topics for evidence syntheses: a systematic review","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University; Impact","funders":"World Health Organization","keywords":"Systematic review; MEDLINE; Data science; Computer science; Medicine; Management science; Information retrieval; Biology; Engineering","score_opus":0.9618204236684665,"score_gpt":0.8325617014041096,"score_spread":0.12925872226435697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995432752","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":[0.0000058368523,0.96003205,0.015761,0.011668139,0.0024775956,0.009880135,0.00015269002,0.000006593449,0.00001596724],"genre_scores_gemma":[0.0000072258426,0.93483484,0.039890677,0.023141049,0.0013751845,0.0006371461,0.0000021285741,0.000032525175,0.000079230595],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.93464476,0.037735995,0.026158137,0.000435973,0.00028036864,0.0007447424],"domain_scores_gemma":[0.25316578,0.7148136,0.029869054,0.00067415956,0.0010554375,0.00042199533],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1735517,0.00033577607,0.02016157,0.0001988802,0.00019045817,0.000005870316,0.00084772386,0.0011204456,0.00004249097],"category_scores_gemma":[0.8573989,0.00021284397,0.0017224151,0.00022197605,0.00022499423,0.00016896578,0.00018397051,0.0019682823,0.000013316713],"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":[0.00003334039,0.000014843202,0.00023165195,0.9420084,0.00012420607,7.8935824e-7,0.0001392655,2.6482606e-8,1.2186911e-8,0.002604652,0.005737831,0.049105026],"study_design_scores_gemma":[0.00014971396,0.0005621332,0.000026151545,0.62893647,0.0016120085,0.000027529239,0.00007267217,0.000014818488,2.3947995e-9,0.0018625194,0.3666378,0.00009818567],"about_ca_topic_score_codex":0.000011416474,"about_ca_topic_score_gemma":0.0000068352074,"teacher_disagreement_score":0.68384725,"about_ca_system_score_codex":0.00015216702,"about_ca_system_score_gemma":0.003208289,"threshold_uncertainty_score":0.9943852},"labels":[],"label_agreement":null},{"id":"W2996193623","doi":"10.1016/j.jclinepi.2019.12.011","title":"Group sample sizes in nonregulated health care intervention trials described as randomized controlled trials were overly similar","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Health Centre; Concordia University; McGill University; Jewish General Hospital","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Mitacs","keywords":"Randomization; Randomized controlled trial; Clinical trial; Sample size determination; Intervention (counseling); Psychological intervention; Medicine; Research design; Confidence interval; Psychology; Physical therapy; Statistics; Internal medicine; Psychiatry; Mathematics","score_opus":0.8843798894127456,"score_gpt":0.6915576671450481,"score_spread":0.19282222226769752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996193623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78732085,0.05011571,0.09639343,0.039823398,0.011172092,0.014396355,0.00006688887,0.000010977806,0.0007002745],"genre_scores_gemma":[0.97459334,0.002450312,0.014645936,0.0065236846,0.0011362998,0.00008663778,0.000021333755,0.000021463153,0.0005209932],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.046191238,0.7462983,0.2030687,0.0010505312,0.0028379422,0.00055329903],"domain_scores_gemma":[0.009632653,0.8121894,0.17369992,0.0018679608,0.0020962066,0.0005138972],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.967247,0.0005253927,0.14853376,0.0009051308,0.00006526611,0.00019841643,0.0017548697,0.0006543855,0.01671786],"category_scores_gemma":[0.9873092,0.00019981814,0.051523175,0.00063930626,0.00020116972,0.00038958775,0.00011565707,0.0010940104,0.0005400787],"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":[0.47814992,0.0011042401,0.13795051,0.00034019642,0.013055217,0.000036742713,0.0011707542,0.0009530615,0.000029371968,0.020378849,0.05174142,0.29508972],"study_design_scores_gemma":[0.73117846,0.0034902797,0.039514996,0.001209602,0.0033123062,0.000050464037,0.0020792617,0.010336641,0.0000016483712,0.1753546,0.033032913,0.00043881062],"about_ca_topic_score_codex":0.00026339872,"about_ca_topic_score_gemma":0.00017305784,"teacher_disagreement_score":0.2946509,"about_ca_system_score_codex":0.00010417093,"about_ca_system_score_gemma":0.00043602855,"threshold_uncertainty_score":0.984181},"labels":[],"label_agreement":null},{"id":"W2996289423","doi":"10.1016/j.jclinepi.2019.12.014","title":"Conflict of interest as ethical shorthand: understanding the range and nature of “non-financial conflict of interest” in biomedicine","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":72,"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; University of Toronto","funders":"National Health and Medical Research Council; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; University of Toronto","keywords":"Biomedicine; Conflict of interest; Range (aeronautics); Political science; Engineering; Law; Biology; Bioinformatics","score_opus":0.8751516407534817,"score_gpt":0.6800354644387472,"score_spread":0.19511617631473455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996289423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9665173,0.002852525,0.00019276179,0.027220257,0.0022983495,0.00033919868,0.00003470086,0.000003609661,0.00054129853],"genre_scores_gemma":[0.9820536,0.0039203153,0.00007112404,0.013384175,0.00051349297,0.0000021400303,0.000003205585,0.000012039868,0.0000399356],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9876148,0.0065803933,0.00493285,0.00028299203,0.00013548895,0.00045347092],"domain_scores_gemma":[0.9527419,0.04336518,0.0028739918,0.00023318936,0.00032176563,0.00046392958],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.031245666,0.00022967215,0.002747865,0.00023562222,0.000043653243,0.0000019386507,0.0005164395,0.003410606,0.00053471245],"category_scores_gemma":[0.025462318,0.00014684995,0.00042119055,0.0002596296,0.0021918563,0.0000670232,0.00017048429,0.012194372,0.000004474514],"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":[0.011622609,0.00062947656,0.880584,0.000700047,0.0005956159,0.00009647668,0.001109134,0.000058707607,0.005376309,0.087745376,0.003307008,0.008175259],"study_design_scores_gemma":[0.029827489,0.015457757,0.78423053,0.0029053288,0.0011491266,0.00077521766,0.0034047053,0.005344187,0.008733341,0.06662579,0.08085126,0.0006953066],"about_ca_topic_score_codex":0.000045537636,"about_ca_topic_score_gemma":0.00006949407,"teacher_disagreement_score":0.09635348,"about_ca_system_score_codex":0.000049386737,"about_ca_system_score_gemma":0.00042355718,"threshold_uncertainty_score":0.9978832},"labels":[],"label_agreement":null},{"id":"W2997338746","doi":"10.1016/j.jclinepi.2019.12.012","title":"An approach to explore for a sweet spot in randomized trials","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac pacing and defibrillation studies","field":"Medicine","cited_by":5,"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; Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Canada Research Chairs; BrightFocus Foundation","keywords":"Hazard ratio; Confidence interval; Sweet spot; Randomized controlled trial; Medicine; Internal medicine; Proportional hazards model; Relative risk; Biology","score_opus":0.6341961238485023,"score_gpt":0.5957641643553213,"score_spread":0.03843195949318101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997338746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9534573,0.0007831422,0.030908061,0.0044493196,0.0014848324,0.0011441591,0.00000375475,0.000011104033,0.0077583487],"genre_scores_gemma":[0.95975286,0.00040439857,0.03323327,0.0044520125,0.0019520152,0.000024130843,0.00000443105,0.000013250964,0.00016362268],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.98450613,0.008240746,0.006601456,0.0002510567,0.0001489938,0.00025159493],"domain_scores_gemma":[0.8747764,0.122150294,0.002212972,0.00024612373,0.00030871524,0.00030545532],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13195325,0.00012895736,0.012136945,0.00022861452,0.000015852975,0.000003550272,0.000042246073,0.00024360999,0.000011260172],"category_scores_gemma":[0.3640474,0.00007600239,0.0023684297,0.00011750456,0.000092791706,0.00004986849,0.000020596335,0.00036468636,0.000018459736],"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":[0.49932408,0.00053522264,0.450126,0.00014626079,0.0013215517,0.00000767105,0.00083098677,0.0039141066,0.00012360582,0.0033906153,0.028153745,0.012126167],"study_design_scores_gemma":[0.61069787,0.0052782143,0.29385763,0.0005119709,0.0011622609,0.00069007406,0.0014728645,0.0035979387,0.000023244083,0.016347654,0.066003874,0.00035642824],"about_ca_topic_score_codex":0.00000762979,"about_ca_topic_score_gemma":4.5917764e-7,"teacher_disagreement_score":0.23209417,"about_ca_system_score_codex":0.000023076203,"about_ca_system_score_gemma":0.000141406,"threshold_uncertainty_score":0.8938368},"labels":[],"label_agreement":null},{"id":"W2997440973","doi":"10.1016/j.jclinepi.2019.12.018","title":"Response to the letter to the editor by Sabour et al. (2019) Re: “Collection of antirheumatic medication data from both patients and rheumatologists shows strong agreement in a real-world clinical cohort: Methodological issues to avoid misinterpretation”","year":2019,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Epidemiology","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; University Health Network; University of Toronto; Toronto General Hospital","funders":"","keywords":"Medicine; Cohort; Rheumatoid arthritis; Epidemiology; Cohort study; Internal medicine; Clinical epidemiology; Family medicine","score_opus":0.4941968997133141,"score_gpt":0.5958901506376476,"score_spread":0.10169325092433351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997440973","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.013522034,0.0002071668,0.2623802,0.711721,0.009844704,0.0016935014,0.000587718,0.000014694849,0.000028950572],"genre_scores_gemma":[0.0009959624,0.0013675346,0.3984455,0.59497714,0.0036539142,0.00006723763,0.00016027114,0.000057243727,0.0002752017],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.79316133,0.18507357,0.01759315,0.0018948116,0.0012456198,0.0010315373],"domain_scores_gemma":[0.42438513,0.56509376,0.007568812,0.002117064,0.000493714,0.00034148837],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.23742789,0.0006691673,0.007539928,0.00045462121,0.00010692158,0.0000324438,0.0029156473,0.0017725425,0.00022112534],"category_scores_gemma":[0.8247475,0.00037516677,0.0005823985,0.00043951042,0.00078188186,0.00013813966,0.0012850396,0.0066389865,0.000071081486],"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":[0.00287544,0.00023177144,0.12515944,0.00007266063,0.0004664804,0.000014704076,0.00019202117,0.000034862383,0.000003401044,0.00019890536,0.86788386,0.002866454],"study_design_scores_gemma":[0.0013850117,0.002410025,0.26432154,0.0010967398,0.0003486918,0.000016655045,0.000051185514,0.0014494725,0.0000014381424,0.018937962,0.70958894,0.0003923605],"about_ca_topic_score_codex":0.00082568615,"about_ca_topic_score_gemma":0.00072034786,"teacher_disagreement_score":0.5873196,"about_ca_system_score_codex":0.0002062192,"about_ca_system_score_gemma":0.0003722959,"threshold_uncertainty_score":0.99987},"labels":[],"label_agreement":null},{"id":"W2999143593","doi":"10.1016/j.jclinepi.2019.12.004","title":"Can the Schwarz and Lalouch concept of differentiating between explanatory and pragmatic studies be useful for diagnostic test studies?","year":2020,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health; University of Ottawa","funders":"National Health Research Institutes","keywords":"Test (biology); Medicine; Psychology; Biology","score_opus":0.9021483929136066,"score_gpt":0.6747074716390209,"score_spread":0.2274409212745857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999143593","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09809372,0.21714689,0.0038998297,0.07280963,0.60342336,0.003201178,0.0013719478,0.000007957346,0.000045519188],"genre_scores_gemma":[0.17418845,0.041851036,0.009919039,0.0032923648,0.76989985,0.00012476528,0.000056866567,0.000087702545,0.0005799168],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8494508,0.08170651,0.06319597,0.0013773193,0.0037349071,0.0005344475],"domain_scores_gemma":[0.010800153,0.92041,0.06301505,0.0012004218,0.004215427,0.00035897037],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3930416,0.00053989084,0.028905522,0.000206498,0.0002036898,0.000086476975,0.0016930338,0.0007148346,0.000050455455],"category_scores_gemma":[0.9901576,0.00020741821,0.0031464235,0.0003004972,0.0012790894,0.0001044317,0.00052885624,0.0018060474,0.0000046746773],"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":[0.00001692928,0.000027621869,0.15273449,0.0005890606,0.00359914,0.00000527482,0.00069778564,0.0000046645564,1.2784801e-7,0.00014586136,0.8376006,0.0045784605],"study_design_scores_gemma":[0.0024338374,0.0030844281,0.063254744,0.0023936972,0.011379595,0.000021716696,0.008619898,0.0004310169,9.865505e-7,0.07798862,0.82986367,0.00052781217],"about_ca_topic_score_codex":0.000005916762,"about_ca_topic_score_gemma":0.00004681438,"teacher_disagreement_score":0.83870345,"about_ca_system_score_codex":0.00003253525,"about_ca_system_score_gemma":0.00037019275,"threshold_uncertainty_score":0.98551136},"labels":[],"label_agreement":null},{"id":"W3000568717","doi":"10.1016/j.jclinepi.2019.12.022","title":"A systematic review evaluating screening instruments for gambling disorder finds lack of adequate evidence","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Gambling Behavior and Treatments","field":"Psychology","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":"McMaster University","funders":"","keywords":"PsycINFO; MEDLINE; Medicine; Systematic review; Medical diagnosis; Psychiatry; Population; Clinical psychology; Pathology; Environmental health","score_opus":0.905907760444816,"score_gpt":0.7179625415951713,"score_spread":0.18794521884964477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000568717","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":[0.00013291834,0.9887435,0.0050243977,0.0005952576,0.002488977,0.0029200322,0.000045541958,0.000016679687,0.000032713928],"genre_scores_gemma":[0.00013129927,0.9870953,0.010694299,0.00085618126,0.00058386853,0.00034051167,0.000026882979,0.00009432299,0.00017732274],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.95674217,0.018914375,0.02224044,0.00084703794,0.00053109805,0.0007248663],"domain_scores_gemma":[0.88520014,0.083664685,0.029167002,0.00086919754,0.00065760716,0.0004413434],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053843908,0.00073146075,0.023265015,0.00029786085,0.000082025304,0.000012514388,0.0012014795,0.0010768696,0.00022973829],"category_scores_gemma":[0.20214467,0.00048164703,0.006338365,0.0004772946,0.0002087832,0.00014145153,0.00018783206,0.0020555845,0.00009261015],"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":[0.0001337467,0.00025189586,0.002442653,0.42459163,0.0025951786,0.00004147407,0.000043286946,0.0000023102423,1.2355802e-8,0.00015283305,0.0004266244,0.56931835],"study_design_scores_gemma":[0.0017044371,0.003406843,0.00055241404,0.94504416,0.030286832,0.00039449683,0.000039586987,0.00006258308,1.6525345e-8,0.00025708159,0.017869247,0.0003823173],"about_ca_topic_score_codex":0.00001847961,"about_ca_topic_score_gemma":0.000001078454,"teacher_disagreement_score":0.56893605,"about_ca_system_score_codex":0.00007976228,"about_ca_system_score_gemma":0.00052851555,"threshold_uncertainty_score":0.99976355},"labels":[],"label_agreement":null},{"id":"W3000577482","doi":"10.1016/j.jclinepi.2020.01.002","title":"In response to “Lunny et al. Validation of five search filters for retrieval of clinical practice guidelines produced low precision”","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Information retrieval; Clinical Practice; Computer science; MEDLINE; Medicine; Data mining; Medical physics; Family medicine; Political science","score_opus":0.6888009689182242,"score_gpt":0.6852988507366491,"score_spread":0.003502118181575087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000577482","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.08485717,0.00014999406,0.009513351,0.89916253,0.003940798,0.0021731423,0.0001691564,0.00001085,0.000023014058],"genre_scores_gemma":[0.0018333425,0.0014288164,0.20719351,0.7818906,0.007126047,0.000014308157,0.00017697117,0.00008034322,0.00025608408],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8566562,0.06157469,0.075727515,0.0021276944,0.0027724965,0.0011414322],"domain_scores_gemma":[0.29145375,0.66060245,0.03044119,0.001357354,0.01539025,0.0007550034],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.27627423,0.0005058653,0.008780588,0.0007224403,0.000033367174,0.000011441254,0.0008017787,0.0018708623,0.00013973498],"category_scores_gemma":[0.97596776,0.0004023061,0.0025229703,0.00070803595,0.00043865372,0.00050559896,0.0003411923,0.008203988,0.000024943014],"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":[0.12644674,0.0006555861,0.003922021,0.00037305604,0.0006840652,0.00032790992,0.00009905755,0.0005969491,0.0003500899,0.000008282706,0.85901266,0.007523574],"study_design_scores_gemma":[0.011394731,0.018467337,0.009756204,0.0016065708,0.0011934969,0.00027559302,0.00023037707,0.0015757892,0.00031664965,0.0010502639,0.95380306,0.00032989852],"about_ca_topic_score_codex":0.0000919503,"about_ca_topic_score_gemma":0.000004747992,"teacher_disagreement_score":0.6996935,"about_ca_system_score_codex":0.00014526413,"about_ca_system_score_gemma":0.0050750645,"threshold_uncertainty_score":0.9998429},"labels":[],"label_agreement":null},{"id":"W3001477424","doi":"10.1016/j.jclinepi.2019.12.023","title":"GRADE Guidelines 28: Use of GRADE for the assessment of evidence about prognostic factors: rating certainty in identification of groups of patients with different absolute risks","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":402,"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; Ted Rogers Centre for Heart Research; Toronto General Hospital","funders":"","keywords":"Certainty; Observational study; Grading (engineering); Medicine; Context (archaeology); Randomized controlled trial; Identification (biology); Actuarial science; Psychology; Internal medicine","score_opus":0.9720071128354996,"score_gpt":0.6980668568027285,"score_spread":0.27394025603277106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001477424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81928295,0.00046681036,0.17585753,0.0033487545,0.0002271236,0.0007838466,0.00003154118,5.720719e-7,8.4695193e-7],"genre_scores_gemma":[0.9854364,0.00039444148,0.013865567,0.00018733022,0.000086159955,0.000012250002,0.0000038292233,0.0000075495727,0.0000065137588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.883157,0.03811678,0.07436637,0.00074004126,0.003294063,0.00032572175],"domain_scores_gemma":[0.5619466,0.34354502,0.08743634,0.0013675587,0.0055052745,0.00019921236],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18305798,0.00022904041,0.008610157,0.00019641113,0.00003118726,0.000024447954,0.0013753255,0.00015516373,0.00007318635],"category_scores_gemma":[0.7328447,0.00007928084,0.0025170322,0.00055382715,0.0003187013,0.00024502192,0.000115429604,0.00040166356,6.491198e-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":[0.000112377136,0.00025870357,0.9892187,0.0002281815,0.00035280376,2.8006508e-7,0.00014932352,0.005297652,0.00008296865,0.00048585524,0.00082969136,0.0029834544],"study_design_scores_gemma":[0.00053647714,0.00084156997,0.9233896,0.0004667428,0.0005102782,6.008861e-7,0.00019365648,0.07134741,0.000036710368,0.0024990218,0.00011606311,0.00006186624],"about_ca_topic_score_codex":0.00005461289,"about_ca_topic_score_gemma":0.000035759673,"teacher_disagreement_score":0.54978675,"about_ca_system_score_codex":0.000017906661,"about_ca_system_score_gemma":0.00015858683,"threshold_uncertainty_score":0.8412137},"labels":[],"label_agreement":null},{"id":"W3004101560","doi":"10.1016/j.jclinepi.2020.01.015","title":"A call for consensus guidelines on classification and reporting of methodological studies","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Hamilton Health Sciences; St. Joseph’s Healthcare Hamilton; Population Health Research Institute; McMaster University; Impact","funders":"","keywords":"Consensus conference; MEDLINE; Medicine; Data science; Management science; Family medicine; Political science; Computer science; Library science; Engineering","score_opus":0.9869170641315475,"score_gpt":0.8016263965850122,"score_spread":0.18529066754653523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004101560","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":[0.30282998,0.0016140626,0.024772944,0.6689904,0.00060637644,0.00042216608,0.0000045386637,0.000027222923,0.00073232636],"genre_scores_gemma":[0.6828204,0.0036670803,0.30350462,0.008341191,0.0015978551,0.000009457096,3.645129e-7,0.000008129078,0.000050919632],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9784114,0.01035597,0.010404291,0.00026538564,0.0002916772,0.0002713218],"domain_scores_gemma":[0.61274886,0.3590615,0.023336722,0.00023445387,0.004083705,0.00053473545],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18173738,0.00007906988,0.002104499,0.000055918423,0.000089166584,0.0000037564405,0.0002344923,0.00026319793,0.0000066584603],"category_scores_gemma":[0.94354385,0.00005209316,0.00038608827,0.000116716175,0.0012267635,0.000026765547,0.00006292136,0.0005127438,6.908593e-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":[0.002532696,0.00017165806,0.41526368,0.00016523294,0.0003488188,0.00007588857,0.0011750894,0.00012594063,0.0006819526,0.122690775,0.23869906,0.21806921],"study_design_scores_gemma":[0.002521912,0.00819857,0.2450777,0.0005075807,0.00023948132,0.00009891657,0.013667038,0.007974988,0.0001812374,0.42579478,0.2953493,0.0003884838],"about_ca_topic_score_codex":0.00002942694,"about_ca_topic_score_gemma":0.000014096656,"teacher_disagreement_score":0.7618065,"about_ca_system_score_codex":0.00002290442,"about_ca_system_score_gemma":0.00028105412,"threshold_uncertainty_score":0.8425736},"labels":[],"label_agreement":null},{"id":"W3004184249","doi":"10.1016/j.jclinepi.2020.01.003","title":"Thresholds and innovation: discussion on statistical significance","year":2020,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; University of Ottawa","funders":"","keywords":"Scopus; Statistical significance; Guideline; Value (mathematics); p-value; Medicine; MEDLINE; Psychology; Statistical hypothesis testing; Statistics; Mathematics; Political science; Pathology; Internal medicine; Law","score_opus":0.8888259210256492,"score_gpt":0.6846569297970317,"score_spread":0.20416899122861742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004184249","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052946276,0.00078664924,0.080525115,0.04514177,0.8704428,0.00040705595,0.00017921034,0.00000345562,0.0019844882],"genre_scores_gemma":[0.0041336007,0.0009394085,0.021798804,0.005158709,0.9629284,0.000008094,0.0000554893,0.00003474902,0.004942734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.67728126,0.17259167,0.13596618,0.0025342405,0.011007769,0.0006188746],"domain_scores_gemma":[0.08493826,0.7965768,0.10858461,0.002943337,0.0061015496,0.0008554635],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.6132078,0.00051493064,0.025234869,0.00064102287,0.00009354239,0.00020142665,0.0023200766,0.001578773,0.0030396362],"category_scores_gemma":[0.96448153,0.00017642918,0.003122437,0.0012815596,0.00048534828,0.00014310353,0.00024392731,0.0041402495,0.0007584327],"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":[0.00019789557,0.00006315028,0.011356352,0.00005362594,0.00027629122,0.00004454045,0.00001570585,0.000021982974,4.076233e-7,0.013523823,0.93791723,0.036528986],"study_design_scores_gemma":[0.00040284172,0.0010440148,0.0074802646,0.00014705154,0.00027103766,0.00001115902,0.00002812297,0.0004813565,8.023086e-8,0.09142007,0.89855254,0.000161452],"about_ca_topic_score_codex":0.0000015851823,"about_ca_topic_score_gemma":0.000002478088,"teacher_disagreement_score":0.6239851,"about_ca_system_score_codex":0.000034552704,"about_ca_system_score_gemma":0.0007949094,"threshold_uncertainty_score":0.9997174},"labels":[],"label_agreement":null},{"id":"W3004187495","doi":"10.1016/j.jclinepi.2020.01.013","title":"Predatory publishing dilutes and distorts evidence in systematic reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Dalhousie University","keywords":"Systematic review; Citation; Publishing; Quality of evidence; Grey literature; Promotion (chess); Psychology; Medicine; MEDLINE; Meta-analysis; Biology; Political science; Computer science; Library science","score_opus":0.9755542450549045,"score_gpt":0.6907644937548005,"score_spread":0.284789751300104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004187495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44151077,0.2996189,0.097714685,0.15228908,0.003927353,0.0036363427,0.00000839076,0.000009098763,0.0012854061],"genre_scores_gemma":[0.96086377,0.00842855,0.014797365,0.014507186,0.0010022667,0.000019614807,4.6684548e-7,0.000011864844,0.00036891102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.35364965,0.4657527,0.1737689,0.0018097662,0.004372453,0.0006465484],"domain_scores_gemma":[0.061975356,0.8166722,0.11482325,0.0030926843,0.001989819,0.0014466546],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8018353,0.000262848,0.023794375,0.00024460765,0.000043892498,0.0003518863,0.0022629988,0.00028273187,0.00080654776],"category_scores_gemma":[0.9855073,0.00010739201,0.003636664,0.0007756548,0.000182271,0.0014612669,0.00025305024,0.0011392875,0.00029608334],"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":[0.000038327187,0.00004452884,0.84015656,0.0045704343,0.00014483907,0.000039867668,0.0003520424,0.00007713158,0.000004161001,0.001520841,0.14378299,0.009268275],"study_design_scores_gemma":[0.00090057205,0.0008984352,0.6636981,0.016779622,0.0008895841,0.0002913411,0.0007218177,0.02413228,5.1214994e-7,0.033454902,0.25777796,0.00045492133],"about_ca_topic_score_codex":0.00000533234,"about_ca_topic_score_gemma":0.000014247235,"teacher_disagreement_score":0.51935303,"about_ca_system_score_codex":0.000026801083,"about_ca_system_score_gemma":0.00014239902,"threshold_uncertainty_score":0.9906984},"labels":[],"label_agreement":null},{"id":"W3004255156","doi":"10.1016/j.jclinepi.2020.01.011","title":"Optimal sampling in derivation studies was associated with improved discrimination in external validation for heart failure prognostic models","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Heart Failure Treatment and Management","field":"Medicine","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; University of Toronto","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Japan Cardiovascular Research Foundation; Japan Agency for Medical Research and Development","keywords":"Medicine; Statistic; Population; Cohort; Statistics; Critical appraisal; Cohort study; External validity; Sampling (signal processing); Internal medicine; Mathematics; Pathology; Computer science","score_opus":0.4961104910658282,"score_gpt":0.5456929310196519,"score_spread":0.049582439953823665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004255156","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":[0.00615957,0.8919078,0.0735844,0.023403952,0.00052500743,0.0043745465,0.000011950092,0.000026441627,0.0000063251487],"genre_scores_gemma":[0.002881159,0.85081226,0.14490555,0.00038158038,0.00061161484,0.00019343772,0.00014452178,0.000044548666,0.000025323676],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918724,0.002085999,0.005107833,0.0003966618,0.00019262417,0.000344534],"domain_scores_gemma":[0.97709703,0.01907724,0.0032021292,0.0001367638,0.00033094687,0.00015588521],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011370616,0.00033287393,0.0064375517,0.0003590059,0.000029616986,0.000009479959,0.00010897314,0.0004891629,0.0000040077184],"category_scores_gemma":[0.0554613,0.00020740715,0.00077232113,0.00026725687,0.00008351526,0.0001902026,0.000047922924,0.0010152342,0.0000017421152],"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":[0.0022927786,0.0021986733,0.0403806,0.018147448,0.004259154,0.00022795868,0.00048302268,0.0040406478,0.0000034866516,0.001728641,0.002528204,0.9237094],"study_design_scores_gemma":[0.032123648,0.027951539,0.035805885,0.23017405,0.019960739,0.0004993291,0.00093729113,0.03690148,0.0000032068442,0.015616789,0.59835064,0.0016754084],"about_ca_topic_score_codex":0.0000067973133,"about_ca_topic_score_gemma":0.000049427043,"teacher_disagreement_score":0.92203397,"about_ca_system_score_codex":0.00035412944,"about_ca_system_score_gemma":0.0004791906,"threshold_uncertainty_score":0.952495},"labels":[],"label_agreement":null},{"id":"W3004577559","doi":"10.1016/j.jclinepi.2019.12.021","title":"GRADE guidelines: 21 part 2. Test accuracy: inconsistency, imprecision, publication bias, and other domains for rating the certainty of evidence and presenting it in evidence profiles and summary of findings tables","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":364,"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 Public Health; McGill University; McMaster University Medical Centre; McMaster University","funders":"European Commission","keywords":"Certainty; Operationalization; Test (biology); MEDLINE; Evidence-based medicine; Research design","score_opus":0.9592689633150591,"score_gpt":0.668763848994735,"score_spread":0.2905051143203241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004577559","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":[0.7917432,0.01446528,0.008254199,0.18433417,0.00015485233,0.0009867589,0.000023992547,0.0000015370621,0.000036013535],"genre_scores_gemma":[0.9469834,0.006388499,0.03978589,0.006397442,0.0003162576,0.00002322581,9.981757e-7,0.00001003433,0.000094232404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90355814,0.037345722,0.055539217,0.0011841758,0.001945172,0.00042759153],"domain_scores_gemma":[0.05130843,0.90519434,0.038189333,0.0010862077,0.003902014,0.00031968928],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43112132,0.00019656235,0.00532224,0.0001795875,0.00009147789,0.000111840905,0.00093255774,0.00022052946,0.000087129105],"category_scores_gemma":[0.97453356,0.000078078854,0.0008044839,0.0005856739,0.00047964812,0.0004897067,0.0003037757,0.00045019377,0.000001255646],"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":[0.00006285015,0.000026915077,0.937952,0.00020540073,0.00007418855,6.781735e-7,0.00031020746,0.000039546085,0.00017461248,0.00059465296,0.04329006,0.017268898],"study_design_scores_gemma":[0.0017319373,0.0013016628,0.73720866,0.005836436,0.0007753865,0.00012454708,0.0043155258,0.11035494,0.00013369005,0.051615246,0.08623413,0.0003678523],"about_ca_topic_score_codex":0.00004434658,"about_ca_topic_score_gemma":0.00005718354,"teacher_disagreement_score":0.8678486,"about_ca_system_score_codex":0.0000074961877,"about_ca_system_score_gemma":0.00020356526,"threshold_uncertainty_score":0.5857803},"labels":[],"label_agreement":null},{"id":"W3004798411","doi":"10.1016/j.jclinepi.2020.01.016","title":"Reply to letter to the editor “Forrest plots or caterpillar plots?”","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","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; Impact","funders":"","keywords":"Plot (graphics); Caterpillar; Forest plot; Point (geometry); Scopus; Statistics; Demography; Mathematics; Computer science; Meta-analysis; MEDLINE; Medicine; Ecology; Biology; Sociology","score_opus":0.2037643838711947,"score_gpt":0.45925122399251855,"score_spread":0.25548684012132383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004798411","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":[0.0010222002,0.0002821333,0.00057993934,0.9723817,0.024343604,0.00068764423,0.000020599844,0.000042895386,0.00063928275],"genre_scores_gemma":[0.00016235991,0.00032742115,0.0019648806,0.70886344,0.28413677,0.0000169064,0.000016804188,0.000083916355,0.0044275057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9832133,0.006601842,0.0074478085,0.0008201567,0.0009280919,0.0009887789],"domain_scores_gemma":[0.9027553,0.091626495,0.0026636028,0.0011091115,0.0005060556,0.001339392],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.016068326,0.00062422134,0.0100630745,0.0002499433,0.000098003155,0.000028010352,0.0009642241,0.0018005254,0.00038623431],"category_scores_gemma":[0.18997353,0.00029639679,0.0044648685,0.0003298366,0.00030649258,0.00005787325,0.0002455444,0.00819078,0.0012158223],"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":[0.0027996297,0.00005879517,0.013525956,0.00011094756,0.0007308268,0.010899305,0.000072354225,0.000020380485,0.000001671141,0.000020816047,0.96973354,0.0020258038],"study_design_scores_gemma":[0.0011705161,0.0032527468,0.019074049,0.00035185795,0.00074802816,0.0016864834,0.000012043322,0.000008624203,0.0000014934683,0.000062933555,0.9733074,0.00032388215],"about_ca_topic_score_codex":0.000046376055,"about_ca_topic_score_gemma":0.0000054157877,"teacher_disagreement_score":0.26351824,"about_ca_system_score_codex":0.00011251381,"about_ca_system_score_gemma":0.000690154,"threshold_uncertainty_score":0.9999488},"labels":[],"label_agreement":null},{"id":"W3005727251","doi":"10.1016/j.jclinepi.2019.12.020","title":"GRADE guidelines: 21 part 1. Study design, risk of bias, and indirectness in rating the certainty across a body of evidence for test accuracy","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":383,"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 Public Health; McGill University; Impact; McMaster University","funders":"European Commission","keywords":"Certainty; Test (biology); Guideline; Quality of evidence; Research design; Evidence-based medicine; Systematic review; Psychology; Evidence-based practice; Quality (philosophy); MEDLINE; Medicine; Medical physics; Applied psychology; Meta-analysis; Medical education; Alternative medicine; Statistics; Pathology; Political science","score_opus":0.9877785009089068,"score_gpt":0.7526033643857505,"score_spread":0.23517513652315636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005727251","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89359504,0.0032022875,0.08389865,0.01777195,0.0003106578,0.0011992189,0.000016241282,0.0000011388893,0.0000048078728],"genre_scores_gemma":[0.97656846,0.0012619805,0.020283632,0.0014486051,0.00038354247,0.00001921049,2.2858825e-7,0.000007569197,0.000026771453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.61723137,0.24791163,0.12891275,0.0015645991,0.003651121,0.00072850625],"domain_scores_gemma":[0.034445535,0.8958907,0.06472286,0.0013376634,0.0033249126,0.00027830072],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73627347,0.00023980105,0.011579997,0.00011480535,0.00009165451,0.000055342047,0.0018971466,0.00017910468,0.000108882086],"category_scores_gemma":[0.9896314,0.000083625826,0.0025096005,0.00087749504,0.0003287104,0.00021740825,0.00022897456,0.00068166194,0.000007750053],"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":[0.0001983269,0.00018251775,0.96141297,0.000057876092,0.0002802715,0.000004112567,0.0007497483,0.0019674643,0.000024011262,0.000025201427,0.011126742,0.023970779],"study_design_scores_gemma":[0.001975013,0.003162413,0.8951593,0.00052037556,0.0008358271,0.000024288296,0.006345631,0.07502864,0.000032102525,0.010089319,0.006650904,0.00017615163],"about_ca_topic_score_codex":0.0000486235,"about_ca_topic_score_gemma":0.00006281952,"teacher_disagreement_score":0.6479791,"about_ca_system_score_codex":0.000009469281,"about_ca_system_score_gemma":0.00024582766,"threshold_uncertainty_score":0.79158545},"labels":[],"label_agreement":null},{"id":"W3005782611","doi":"10.1016/j.jclinepi.2020.01.020","title":"CONSORT endorsement improves the quality of reports of randomized clinical trials in dentistry","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":65,"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; Ottawa Hospital","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Consolidated Standards of Reporting Trials; Medicine; Randomized controlled trial; Dentistry; Descriptive statistics; Interquartile range; Clinical trial; Sample size determination; Family medicine; MEDLINE; Research design; Alternative medicine; Surgery; Statistics","score_opus":0.9704371722934915,"score_gpt":0.7607308662501758,"score_spread":0.20970630604331564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005782611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9318328,0.0029891247,0.036461394,0.024502905,0.0026057374,0.0011405334,0.000008671197,0.0000010518849,0.00045780925],"genre_scores_gemma":[0.9867676,0.0010629086,0.00808395,0.0033269678,0.0006038923,0.000008389149,8.61364e-7,0.0000053850517,0.00014004615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.010663864,0.6969745,0.28833142,0.00076343905,0.00300264,0.0002641112],"domain_scores_gemma":[0.004817399,0.76744646,0.2236079,0.0018576152,0.0019190883,0.00035155652],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9786773,0.00023864994,0.060708646,0.00016229347,0.000025466796,0.000029672834,0.0017201179,0.00038286054,0.0019377504],"category_scores_gemma":[0.9940736,0.000082655264,0.024568172,0.00052523805,0.001058948,0.000096810785,0.00021433146,0.0010818541,0.000033011274],"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":[0.012207489,0.00038218923,0.91714424,0.0001113343,0.0024624814,0.000058043435,0.00012699275,0.00013815452,0.00010110784,0.0042405324,0.03622718,0.026800243],"study_design_scores_gemma":[0.07365488,0.0012500737,0.7142717,0.00028555305,0.0035099234,0.00020254048,0.0011776338,0.005973277,0.000060667433,0.16601849,0.033277676,0.00031757425],"about_ca_topic_score_codex":0.000029230667,"about_ca_topic_score_gemma":0.000012745523,"teacher_disagreement_score":0.20287254,"about_ca_system_score_codex":0.000008927592,"about_ca_system_score_gemma":0.00043106027,"threshold_uncertainty_score":0.9989746},"labels":[],"label_agreement":null},{"id":"W3006618179","doi":"10.1016/j.jclinepi.2020.01.019","title":"Conclusions from surveys may not consider important biases: a systematic survey of surveys","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":26,"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; McMaster University; Impact","funders":"Canadian Institutes of Health Research","keywords":"Logistic regression; Critical appraisal; Medicine; Descriptive statistics; Survey research; Association (psychology); Survey data collection; MEDLINE; Family medicine; Psychology; Applied psychology; Alternative medicine; Statistics; Pathology","score_opus":0.8765508983174743,"score_gpt":0.6693486777189396,"score_spread":0.20720222059853477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006618179","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000965716,0.9849722,0.0032590989,0.0014395999,0.006880603,0.0010457353,0.0013054888,0.000026475627,0.000105111714],"genre_scores_gemma":[0.0018420985,0.9929802,0.0027969773,0.00087167096,0.0011730216,0.000015986681,0.00012447836,0.000060839255,0.0001347253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.045061592,0.92666936,0.025726475,0.00087707146,0.0007912678,0.00087421655],"domain_scores_gemma":[0.15077212,0.81785655,0.028140813,0.00077654875,0.0014278251,0.0010261523],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.87367404,0.00070742855,0.031264655,0.0003888131,0.0002838727,0.000019772035,0.0019082881,0.0032419334,0.00077826245],"category_scores_gemma":[0.97027624,0.0004824926,0.0044967774,0.0010101241,0.0028116642,0.0001366475,0.00038592785,0.0036588917,0.00009880564],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044575445,0.0015770004,0.56693506,0.046398092,0.016899386,0.0026462735,0.0018037676,0.000009337362,6.5606264e-7,0.0027603293,0.018092789,0.33841974],"study_design_scores_gemma":[0.002056299,0.0017294348,0.46281168,0.08021921,0.0064180796,0.00025029958,0.00053833827,0.000028891352,3.7209375e-7,0.0023113103,0.44223043,0.0014056609],"about_ca_topic_score_codex":0.013054415,"about_ca_topic_score_gemma":0.007838376,"teacher_disagreement_score":0.42413765,"about_ca_system_score_codex":0.00013491206,"about_ca_system_score_gemma":0.009647816,"threshold_uncertainty_score":0.9999021},"labels":[],"label_agreement":null},{"id":"W3006656913","doi":"10.1016/j.jclinepi.2020.01.022","title":"Promoting effective use of patient-reported outcomes in clinical practice: themes from a “Methods Tool kit” paper series","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre; Queen's University","funders":"Genentech; Patient-Centered Outcomes Research Institute","keywords":"Series (stratigraphy); Medicine; MEDLINE; Medical physics; Family medicine","score_opus":0.2591600500229012,"score_gpt":0.5508583905349517,"score_spread":0.29169834051205046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006656913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9551468,0.00091025216,0.0011413255,0.04046997,0.0017744973,0.00044122932,0.000010197266,0.000016074478,0.000089644804],"genre_scores_gemma":[0.89456147,0.00088579336,0.07638985,0.027027825,0.0010707038,0.000011534261,0.0000058420646,0.000029359337,0.000017620274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9748996,0.014344935,0.009672722,0.00044666446,0.00031237246,0.0003237317],"domain_scores_gemma":[0.81838155,0.17152067,0.008291679,0.00045034534,0.0008472863,0.0005084686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019449202,0.00023514609,0.0047214036,0.00007675303,0.000022563629,0.0000073537963,0.00016611794,0.0005697877,0.00011475696],"category_scores_gemma":[0.59806585,0.00015494565,0.001363276,0.00022428973,0.00035299797,0.00042577134,0.00013443886,0.0021364144,0.000003747816],"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":[0.006493706,0.0005484677,0.84202045,0.000060897873,0.0008566729,0.00030565873,0.0015923287,0.000010518646,0.00010838821,0.000098692435,0.00054546737,0.14735876],"study_design_scores_gemma":[0.0034779091,0.006176722,0.9487661,0.00031651658,0.0005783742,0.00013479435,0.0010443485,0.00020205312,0.00009612871,0.0018690265,0.03718482,0.0001531757],"about_ca_topic_score_codex":0.00030682184,"about_ca_topic_score_gemma":0.00007625737,"teacher_disagreement_score":0.5786167,"about_ca_system_score_codex":0.000036800382,"about_ca_system_score_gemma":0.00039885758,"threshold_uncertainty_score":0.92817765},"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":"W3007440961","doi":"10.1016/j.jclinepi.2020.02.002","title":"Patient Health Questionnaire-9 scores do not accurately estimate depression prevalence: individual participant data meta-analysis","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":208,"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 Manitoba; McGill University; University of Calgary; Concordia University; McGill University Health Centre; Ontario Brain Institute; Jewish General Hospital","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; Medical Research Council; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; H. Lundbeck A/S; Ministerio de Economía, Fomento y Turismo, Chile; Alberta Health Services; Crohn's and Colitis Canada; Multiple Sclerosis Society; Universidade de São Paulo; National Health Research Institutes; Universidade de Macau; Universiteit Stellenbosch; McGill University; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Agency for Healthcare Research and Quality; Ministero della Salute; Alberta Innovates - Health Solutions; Health Resources and Services Administration; Department for International Development; Bundesministerium für Bildung und Forschung; Pennsylvania Department of Health; Cumming School of Medicine, University of Calgary; University of Technology Sydney; Alberta Innovates; National Institute for Health and Care Research; Hotchkiss Brain Institute; Universiteit van Amsterdam; Universität Heidelberg; National Center for Research Resources; National Institute of General Medical Sciences; Duke Global Health Institute, Duke University; Centers for Disease Control and Prevention; National Center for Medical Rehabilitation Research; United States Agency for International Development; Grand Challenges Canada; Academisch Medisch Centrum; Banco Santander; Tehran University of Medical Sciences and Health Services; Research Manitoba; National Institute on Disability and Rehabilitation Research; University of Washington; Pfizer; Faculty of Medicine, McGill University; McGill University Health Centre; Lance Armstrong Foundation; Government of the United Kingdom; Williams; University of Michigan; Eunice Kennedy Shriver National Institute of Child Health and Human Development; U.S. Department of Health and Human Services; National Institute of Mental Health; Hunter Medical Research Institute; Programme Grants for Applied Research; Health Research; Consejo Nacional de Ciencia y Tecnología; ZonMw; National Multiple Sclerosis Society","keywords":"Patient Health Questionnaire; Medicine; Confidence interval; Depression (economics); Meta-analysis; Prevalence; Epidemiology; Internal medicine; Psychiatry; Depressive symptoms; Anxiety","score_opus":0.8860978782947718,"score_gpt":0.6990942912162713,"score_spread":0.1870035870785005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007440961","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":[0.00009340935,0.9902979,0.0005087006,0.004128735,0.0027102449,0.001137199,0.0010600752,0.000031621545,0.000032114698],"genre_scores_gemma":[0.0032485768,0.98846143,0.0028524348,0.0036784564,0.0010451097,0.00012461455,0.00047364578,0.000057605655,0.00005813736],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9408509,0.036989845,0.018811546,0.0015944425,0.0006824767,0.0010707692],"domain_scores_gemma":[0.937836,0.03194045,0.026650285,0.001931098,0.00020099798,0.0014411837],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040441737,0.0008642469,0.025677297,0.00048193472,0.00024260179,0.00005210039,0.0024468026,0.001136003,0.0017196132],"category_scores_gemma":[0.024550121,0.00048587308,0.0067229373,0.00073550263,0.00035020642,0.00031885147,0.00096590427,0.0030215243,0.00027133958],"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":[0.00026936276,0.0006351613,0.006048578,0.0037631686,0.15070574,0.00021770429,0.00009165669,0.000019912291,6.5579153e-10,0.00021635376,0.00948543,0.82854694],"study_design_scores_gemma":[0.0007575763,0.002194006,0.013896144,0.0030007353,0.61582786,0.00023942317,0.000022450313,0.00007002073,1.869965e-8,0.00039581102,0.36314335,0.00045257344],"about_ca_topic_score_codex":0.00016600199,"about_ca_topic_score_gemma":0.00003574506,"teacher_disagreement_score":0.82809436,"about_ca_system_score_codex":0.00007431728,"about_ca_system_score_gemma":0.00095299986,"threshold_uncertainty_score":0.9997593},"labels":[],"label_agreement":null},{"id":"W3009443436","doi":"10.1016/j.jclinepi.2020.01.025","title":"Future of Evidence Ecosystem Series: Evidence synthesis 2.0: when systematic, scoping, rapid, living, and overviews of reviews come together","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"","keywords":"Systematic review; Evidence-based practice; Evidence-based medicine; Grey literature; Data science; MEDLINE; Computer science; Management science; Medicine; Alternative medicine; Political science; Engineering","score_opus":0.9032400499965897,"score_gpt":0.6166514884168275,"score_spread":0.2865885615797622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009443436","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005870508,0.49321935,0.0069284476,0.49231094,0.0035072535,0.0032390535,0.000058022044,0.0000051451607,0.00014472732],"genre_scores_gemma":[0.0036310202,0.5000198,0.054954287,0.42233956,0.015380203,0.00020574589,0.0000037977632,0.0001511974,0.0033144266],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.32858863,0.48724732,0.17364933,0.0025303306,0.007122147,0.00086224696],"domain_scores_gemma":[0.077205546,0.6720607,0.23867817,0.0067100218,0.0046949508,0.00065055443],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.69800216,0.001147078,0.07750128,0.00074856187,0.00009545104,0.00016862543,0.0068865325,0.0019557544,0.006621287],"category_scores_gemma":[0.92923015,0.00047394307,0.01583193,0.0009269759,0.00060547824,0.0008348716,0.00073648663,0.0036105867,0.00042945833],"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":[0.00005715856,0.000039422095,0.019691758,0.11436444,0.0012870214,0.000059785616,0.0003831748,0.0000057979714,0.000003303282,0.000092573624,0.8598942,0.0041213403],"study_design_scores_gemma":[0.00015132516,0.0010400235,0.0014016089,0.36567914,0.004753571,0.00037225324,0.00026931168,0.0003570808,0.0000023173352,0.0028087215,0.62267053,0.0004941257],"about_ca_topic_score_codex":0.000015182217,"about_ca_topic_score_gemma":0.00003231942,"teacher_disagreement_score":0.25138307,"about_ca_system_score_codex":0.0000655318,"about_ca_system_score_gemma":0.0006269706,"threshold_uncertainty_score":0.99977124},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3010283858","doi":"10.1016/j.jclinepi.2020.02.009","title":"Quality control for crowdsourcing citation screening: the importance of assessment number and qualification set size","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":32,"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; Agricultural Research Institute of Ontario; Children's Hospital of Eastern Ontario; University of British Columbia; BC Children's Hospital","funders":"CHEO Research Institute","keywords":"Crowdsourcing; Citation; Computer science; Redundancy (engineering); Quality (philosophy); Set (abstract data type); Data science; World Wide Web","score_opus":0.3021707952112088,"score_gpt":0.5062694162139675,"score_spread":0.20409862100275866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010283858","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":[0.0041307337,0.00013886525,0.5407546,0.45396522,0.0006979042,0.00025211636,0.000014374008,0.000013107263,0.00003304613],"genre_scores_gemma":[0.2842861,0.00012649158,0.15650864,0.55441576,0.0045396728,0.000023962473,0.000014990129,0.000031075215,0.00005330611],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98019964,0.011043964,0.007246155,0.0006190173,0.00046572203,0.00042547935],"domain_scores_gemma":[0.8152775,0.17081343,0.012317409,0.0006681876,0.0007630337,0.00016044124],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047945175,0.00030031332,0.0030706702,0.000060503142,0.00016103357,0.000060298178,0.000951924,0.0007657973,0.0000074338554],"category_scores_gemma":[0.092588894,0.00020224432,0.00097409333,0.00017236176,0.0003973414,0.00018800762,0.00011665482,0.0027653268,0.0000012625551],"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":[0.0003528173,0.000072403534,0.20085122,0.0005708661,0.0007887105,0.00005513505,0.00044272942,0.0007958732,0.000094263065,0.01104091,0.7482396,0.036695506],"study_design_scores_gemma":[0.0071019283,0.0021325347,0.29816678,0.00094151666,0.00071564346,0.00046463075,0.00035520265,0.12796287,0.000021659973,0.13608113,0.42497367,0.001082405],"about_ca_topic_score_codex":0.000018056933,"about_ca_topic_score_gemma":0.0000029658925,"teacher_disagreement_score":0.384246,"about_ca_system_score_codex":0.000036870526,"about_ca_system_score_gemma":0.0003388908,"threshold_uncertainty_score":0.9995353},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3010352759","doi":"10.1016/j.jclinepi.2020.01.026","title":"Guideline developers in the United States were inconsistent in applying criteria for appropriate Grading of Recommendations, Assessment, Development and Evaluation use","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"","keywords":"Guideline; Grading (engineering); Medicine; Certainty; Family medicine; MEDLINE; Evidence-based medicine; Actuarial science; Alternative medicine; Political science; Pathology; Business; Engineering; Mathematics","score_opus":0.7909520812482255,"score_gpt":0.6593998138296027,"score_spread":0.1315522674186228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010352759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82347614,0.000075923854,0.035479132,0.13975552,0.00023484085,0.00095901283,0.000006845553,0.0000033782485,0.000009185875],"genre_scores_gemma":[0.6256011,0.0006953991,0.3513726,0.021850681,0.00019001878,0.00004395905,0.00023360651,0.000011370611,0.0000012472813],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98278403,0.005651936,0.01078741,0.00026524736,0.00028835982,0.00022299933],"domain_scores_gemma":[0.9255963,0.068405345,0.004666317,0.00016460443,0.0009825455,0.00018491266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.083439976,0.0001328834,0.0013430141,0.00023097411,0.00004021465,0.000011210369,0.00013198062,0.00014876563,0.000031290027],"category_scores_gemma":[0.2033437,0.00009007043,0.00015183917,0.0002712071,0.00009029059,0.00020734515,0.00005850523,0.00069403637,4.4818603e-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":[0.0020503101,0.00042670054,0.7252236,0.00017686246,0.00023042208,0.000012294837,0.0011432921,0.0014873503,0.0001063144,0.00045733433,0.008233767,0.26045173],"study_design_scores_gemma":[0.014311218,0.0016478306,0.64629865,0.0004909669,0.00043883699,0.00007517759,0.008914749,0.22588708,0.00002843161,0.004742573,0.09696199,0.00020250418],"about_ca_topic_score_codex":0.00010867856,"about_ca_topic_score_gemma":0.00011456754,"teacher_disagreement_score":0.31589347,"about_ca_system_score_codex":0.000103773564,"about_ca_system_score_gemma":0.00072872284,"threshold_uncertainty_score":0.94379145},"labels":[],"label_agreement":null},{"id":"W3011286478","doi":"10.1016/j.jclinepi.2020.03.006","title":"Reporting guidelines of health research studies are frequently used inappropriately","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":92,"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 Health Economics; University of Ottawa; Ottawa Hospital","funders":"Cancer Research UK","keywords":"Medicine; Guideline; Research design; MEDLINE; Systematic review; Family medicine; Alternative medicine; Reporting bias; Pathology","score_opus":0.9975200409583229,"score_gpt":0.8266172020063054,"score_spread":0.17090283895201752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011286478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5705068,0.024625892,0.024606202,0.3779213,0.0015239272,0.0004704454,0.0000051204465,0.0000035622854,0.00033671464],"genre_scores_gemma":[0.899437,0.0027782223,0.0829361,0.012952208,0.0014814859,0.000004376397,7.570574e-7,0.000015132412,0.00039468388],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.087564416,0.47695944,0.42233887,0.0018559236,0.010240537,0.0010408146],"domain_scores_gemma":[0.028554091,0.45906466,0.4783071,0.0031519367,0.029861461,0.0010607566],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9343997,0.00023305311,0.028285235,0.00036770545,0.00013256032,0.000048430487,0.002188814,0.0002440883,0.000582522],"category_scores_gemma":[0.99269706,0.00009730875,0.005703709,0.001431068,0.00049637223,0.00016417053,0.00035394105,0.0014281634,0.00019848552],"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":[0.00004540517,0.0000575612,0.6391394,0.00013798596,0.00069984805,0.000031805674,0.00036892697,0.00031634964,0.000010319329,0.0011006786,0.32393613,0.03415556],"study_design_scores_gemma":[0.0013118495,0.0028818084,0.48588455,0.0010420643,0.00037304993,0.00016693716,0.012623558,0.007126891,0.000014554131,0.21760604,0.2706724,0.00029629353],"about_ca_topic_score_codex":0.000023232338,"about_ca_topic_score_gemma":0.000018930048,"teacher_disagreement_score":0.3649691,"about_ca_system_score_codex":0.00003487241,"about_ca_system_score_gemma":0.0007372535,"threshold_uncertainty_score":0.9861409},"labels":[],"label_agreement":null},{"id":"W3012971470","doi":"10.1016/j.jclinepi.2020.03.016","title":"Reporting scoping reviews—PRISMA ScR extension","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":469,"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; Royal College of Physicians and Surgeons of Canada; University of Toronto; Sunnybrook Health Science Centre; Toronto Rehabilitation Institute; Ottawa Hospital; St. Michael's Hospital; University of Ottawa","funders":"World Health Organization","keywords":"Dissemination; Reliability (semiconductor); Extension (predicate logic); Work (physics); Psychology; Public relations; Actuarial science; Computer science; Business; Political science; Engineering","score_opus":0.9838119751288401,"score_gpt":0.7476393619638183,"score_spread":0.2361726131650218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012971470","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28623676,0.03435522,0.52036756,0.14804152,0.0050638765,0.0011249401,0.0000017740895,0.000009899376,0.004798445],"genre_scores_gemma":[0.5639188,0.00926164,0.30682093,0.11006147,0.00830047,0.000008490446,0.0000022323925,0.00004040372,0.0015855393],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.315932,0.2727117,0.40340742,0.0021823836,0.004967555,0.0007989395],"domain_scores_gemma":[0.04474094,0.36066723,0.5827182,0.0048341933,0.005105035,0.0019344351],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8542433,0.0002810045,0.02783303,0.00017795572,0.00009807859,0.00009875758,0.001894049,0.00030470456,0.0042948867],"category_scores_gemma":[0.9860847,0.00011655518,0.010520755,0.0008240245,0.00015387383,0.00025406323,0.00024371476,0.0011958884,0.0023971256],"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":[0.000055816745,0.000051447223,0.406236,0.00014978783,0.00019280618,0.000120850054,0.00008945921,0.00033243845,0.000043782027,0.0008002642,0.40058592,0.19134144],"study_design_scores_gemma":[0.00070732005,0.0008677997,0.18653661,0.0020113008,0.0005870186,0.00053308153,0.00019882851,0.020834187,0.0000063741845,0.034311354,0.75307935,0.00032678273],"about_ca_topic_score_codex":0.0000020655757,"about_ca_topic_score_gemma":0.0000016317405,"teacher_disagreement_score":0.35249344,"about_ca_system_score_codex":0.000013179478,"about_ca_system_score_gemma":0.00022827458,"threshold_uncertainty_score":0.99938864},"labels":[],"label_agreement":null},{"id":"W3014233714","doi":"10.1016/j.jclinepi.2020.03.019","title":"Cochrane risk of bias tool was used inadequately in the majority of non-Cochrane systematic reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Université Laval","funders":"","keywords":"Systematic review; Cochrane collaboration; Medicine; Cochrane Library; Meta-analysis; MEDLINE; Internal medicine","score_opus":0.9168510144985633,"score_gpt":0.6535704606308103,"score_spread":0.26328055386775306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014233714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9052059,0.024135482,0.04717333,0.019210089,0.0010760981,0.0025653131,0.000022408862,0.0000018688581,0.00060952775],"genre_scores_gemma":[0.9785261,0.00841253,0.009400094,0.0031223886,0.00042800786,0.000016214242,0.0000011117439,0.000010410974,0.00008315223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.31333977,0.5027059,0.17592092,0.0011450176,0.0062801023,0.0006083147],"domain_scores_gemma":[0.12100341,0.7136367,0.1579278,0.004236205,0.00274825,0.0004476445],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8206199,0.00037110643,0.03832293,0.00030730822,0.000045385266,0.00004122566,0.003925869,0.00037678453,0.0010879566],"category_scores_gemma":[0.9529269,0.00013089705,0.009502615,0.0016602399,0.0003579988,0.00018399183,0.00014542264,0.0014176945,0.00038608996],"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":[0.00041413365,0.00066969014,0.90276504,0.023839667,0.0014872176,0.0000757022,0.0023793315,0.0010615397,0.000080523656,0.0032941548,0.05343232,0.010500689],"study_design_scores_gemma":[0.005906113,0.005513338,0.80903417,0.023040287,0.0073296637,0.00034994338,0.0032791055,0.06353446,0.000042048123,0.059454363,0.021703722,0.000812791],"about_ca_topic_score_codex":0.000041543506,"about_ca_topic_score_gemma":0.000035450612,"teacher_disagreement_score":0.2109308,"about_ca_system_score_codex":0.000016961143,"about_ca_system_score_gemma":0.00021240607,"threshold_uncertainty_score":0.9998252},"labels":[],"label_agreement":null},{"id":"W3014339638","doi":"10.1016/j.jclinepi.2020.03.017","title":"A systematic survey showed important limitations in the methods for assessing drug safety among systematic reviews","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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","funders":"National Key Research and Development Program of China; Sichuan University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Systematic review; Medicine; MEDLINE; Meta-analysis; Cochrane Library; Family medicine; Internal medicine","score_opus":0.9782708995551342,"score_gpt":0.7588959379542538,"score_spread":0.21937496160088044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014339638","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023198183,0.79780155,0.18836117,0.001103625,0.0018637978,0.010674878,0.000026143354,0.0000026871182,0.00016383723],"genre_scores_gemma":[0.000017766723,0.92226046,0.07475397,0.0010995348,0.00058912684,0.00074583135,0.00002364312,0.000049198883,0.00046047894],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.03636026,0.72845984,0.23052025,0.0014572939,0.0025825647,0.0006198098],"domain_scores_gemma":[0.009990575,0.747285,0.23545519,0.0044405926,0.0023356292,0.0004929851],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97107977,0.0012293505,0.15733075,0.0010124878,0.00021525583,0.00067416247,0.008405481,0.000988299,0.00018098761],"category_scores_gemma":[0.99008495,0.00039994525,0.041667216,0.0034097412,0.00030269183,0.0004144884,0.00024899186,0.0030926922,0.0002886954],"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":[0.000015147216,0.00015078064,0.0027733375,0.7995496,0.002715979,0.000033955126,0.000272782,0.000012902266,5.736416e-9,0.0013349121,0.023109866,0.17003076],"study_design_scores_gemma":[0.00029852393,0.00014382582,0.0016278656,0.32478988,0.013514901,0.000325946,0.00053047226,0.0045084357,9.714662e-10,0.0066234428,0.6472053,0.0004314123],"about_ca_topic_score_codex":0.00001034826,"about_ca_topic_score_gemma":0.00015388765,"teacher_disagreement_score":0.62409544,"about_ca_system_score_codex":0.00015900885,"about_ca_system_score_gemma":0.0012625298,"threshold_uncertainty_score":0.99984527},"labels":[],"label_agreement":null},{"id":"W3014456301","doi":"10.1016/j.jclinepi.2020.03.020","title":"Exclusion of studies with no events in both arms in meta-analysis impacted the conclusions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":94,"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; St. Joseph’s Healthcare Hamilton; Impact","funders":"National Natural Science Foundation of China","keywords":"Meta-analysis; Medicine; Environmental health; Pathology","score_opus":0.964455149900288,"score_gpt":0.7093569863493486,"score_spread":0.2550981635509394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014456301","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":[0.88201046,0.01041891,0.011086979,0.09533718,0.00030180224,0.0005606661,0.0000100695015,0.000001416895,0.0002725319],"genre_scores_gemma":[0.9866199,0.0008529455,0.006238293,0.0059686364,0.00013039654,0.000005627552,7.4574564e-7,0.0000061061787,0.00017734432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7194074,0.19296592,0.08171366,0.0011503929,0.0042272145,0.0005354404],"domain_scores_gemma":[0.35360596,0.54420716,0.09288554,0.0038037712,0.0047225393,0.0007750199],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.51497483,0.00028363912,0.029651277,0.0005304555,0.000052736388,0.000014374232,0.0019931155,0.00018940632,0.0024222226],"category_scores_gemma":[0.7072844,0.0000821281,0.011396699,0.0033026598,0.00030093198,0.0001536296,0.0003567026,0.00094009796,0.00009252189],"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":[0.0002465603,0.00017144103,0.93107724,0.000023871957,0.050951373,0.000024182506,0.00083884574,0.009121678,0.0000073513265,0.000287732,0.006581052,0.00066868577],"study_design_scores_gemma":[0.0011896897,0.0011078719,0.8974636,0.00005030626,0.061044224,0.000018393013,0.0020139408,0.016573971,0.0000010389344,0.014645118,0.005724639,0.00016716479],"about_ca_topic_score_codex":0.000035596222,"about_ca_topic_score_gemma":0.00026134378,"teacher_disagreement_score":0.3658014,"about_ca_system_score_codex":0.00002459915,"about_ca_system_score_gemma":0.00018480909,"threshold_uncertainty_score":0.9985039},"labels":[],"label_agreement":null},{"id":"W3016686763","doi":"10.1016/j.jclinepi.2020.03.026","title":"Individual participant data meta-analyses (IPDMA): data contribution was associated with trial corresponding author country, publication year, and journal impact factor","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Health Centre; McGill University; Jewish General Hospital","funders":"Fonds de Recherche du Québec - Santé","keywords":"Medicine; Odds ratio; Impact factor; Confidence interval; Randomized controlled trial; CINAHL; MEDLINE; Meta-analysis; Logistic regression; Internal medicine; Psychological intervention; Psychiatry","score_opus":0.9903826871403237,"score_gpt":0.7473339363049085,"score_spread":0.24304875083541522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016686763","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":[0.6175495,0.013120745,0.23760928,0.1204604,0.0029544744,0.0020607386,0.00610095,0.000019816984,0.00012412081],"genre_scores_gemma":[0.98875916,0.00024161392,0.005897216,0.0029429242,0.0015375526,0.0000037712753,0.00046515523,0.000018115894,0.00013450837],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.7688793,0.16603309,0.05626734,0.0018602788,0.006123335,0.0008366529],"domain_scores_gemma":[0.25254697,0.53610927,0.18596296,0.010437719,0.010940988,0.004002083],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6266367,0.00041896265,0.016914897,0.00036930238,0.00022154301,0.000980592,0.0056309747,0.00041282352,0.005544492],"category_scores_gemma":[0.9282323,0.0001616686,0.002789047,0.0012198876,0.00031574996,0.0016146289,0.0008579052,0.0016232528,0.00010946651],"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":[0.008172589,0.00037239378,0.2694514,0.000012396091,0.05769098,0.00005626727,0.00019178771,0.00032096967,0.000012053336,0.00053792895,0.6515045,0.011676698],"study_design_scores_gemma":[0.026464336,0.0059853,0.54713905,0.00009336013,0.109481834,0.0004355272,0.00071365817,0.11556177,0.0000016626035,0.004863877,0.18857957,0.00068003894],"about_ca_topic_score_codex":0.000013108386,"about_ca_topic_score_gemma":0.000029628216,"teacher_disagreement_score":0.5163323,"about_ca_system_score_codex":0.000027235337,"about_ca_system_score_gemma":0.0009306001,"threshold_uncertainty_score":0.99974906},"labels":[],"label_agreement":null},{"id":"W3016791968","doi":"10.1016/j.jclinepi.2020.04.012","title":"Reporting guidelines for journal and conference abstracts","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Public Health; University of Ottawa; Ottawa Hospital","funders":"","keywords":"Library science; Medicine; Family medicine; Computer science","score_opus":0.9929273461946317,"score_gpt":0.7996835823483579,"score_spread":0.19324376384627384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016791968","genre_codex":"review","genre_gemma":"review","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017676648,0.9341721,0.050815918,0.010966236,0.0030372953,0.0005399891,0.00001401098,0.0000015698106,0.0004351959],"genre_scores_gemma":[0.0000117660065,0.8822871,0.109780505,0.0021350274,0.0048099924,0.0000066692705,0.0000026373773,0.000022661405,0.0009436287],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3470821,0.13897537,0.50717723,0.0018909832,0.0040992354,0.0007750798],"domain_scores_gemma":[0.0149169415,0.40632224,0.56213474,0.0018579789,0.013487002,0.0012810868],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.86814183,0.000659297,0.07851337,0.00047512748,0.00014462207,0.00045279696,0.0029797836,0.0009950353,0.0010108633],"category_scores_gemma":[0.9904045,0.00025357743,0.02539166,0.00047607097,0.00025000804,0.0002283817,0.0002466874,0.002788053,0.00025702233],"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":[0.00000941774,0.000016170676,0.0004475512,0.001135547,0.00075529236,0.000078488134,0.000007652187,0.0000088414545,1.7578392e-8,0.00041686997,0.22852962,0.7685945],"study_design_scores_gemma":[0.00020267976,0.00031185828,0.00026803065,0.0045426646,0.0027042169,0.0044600675,0.00003717552,0.00038614403,5.8449703e-9,0.031879377,0.9550173,0.00019045704],"about_ca_topic_score_codex":9.3969925e-7,"about_ca_topic_score_gemma":0.000002209709,"teacher_disagreement_score":0.76840407,"about_ca_system_score_codex":0.000030050733,"about_ca_system_score_gemma":0.0019196096,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W3017239231","doi":"10.1016/j.jclinepi.2020.02.011","title":"The fragility of trial results involves more than statistical significance alone","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"McMaster University; Impact","funders":"","keywords":"Fragility; Statistical significance; Clinical significance; Stability (learning theory); Statistical analysis; Clinical trial; Statistical power; Statistical hypothesis testing; Statistics; Medicine; Econometrics; Computer science; Mathematics; Internal medicine; Machine learning","score_opus":0.8646482945307179,"score_gpt":0.6803537811364027,"score_spread":0.18429451339431524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017239231","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":[0.15814145,0.0004941341,0.71452814,0.11720365,0.0068348367,0.0013938451,0.00056605024,0.000055667428,0.000782237],"genre_scores_gemma":[0.23566878,0.0007361001,0.7557409,0.0033739489,0.004397907,0.000009801883,0.000001837134,0.000033371583,0.000037385747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9323344,0.040917367,0.02436908,0.00072799873,0.0009114893,0.00073965936],"domain_scores_gemma":[0.15088326,0.8364107,0.010406098,0.0007206054,0.0007407544,0.00083859154],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.131073,0.00029196803,0.005850076,0.00003682973,0.000102859995,0.000012816871,0.0011324366,0.0006524595,0.000089469904],"category_scores_gemma":[0.971268,0.00016435566,0.0012453578,0.00024330313,0.0026708068,0.000068543486,0.00022018667,0.002437795,0.0000135629525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.37375233,0.0017054487,0.0140426755,0.0003392298,0.0012357647,0.00013703543,0.00031207397,0.000057767986,0.000050939834,0.43480128,0.10883254,0.06473291],"study_design_scores_gemma":[0.026102135,0.0052987295,0.016949775,0.00008482905,0.00026440163,0.000008247474,0.00010633471,0.0009078471,0.000048671496,0.94508946,0.0049752663,0.00016431183],"about_ca_topic_score_codex":0.000015267084,"about_ca_topic_score_gemma":0.00000610764,"teacher_disagreement_score":0.840195,"about_ca_system_score_codex":0.000027086746,"about_ca_system_score_gemma":0.00047209222,"threshold_uncertainty_score":0.9998636},"labels":[],"label_agreement":null},{"id":"W3018307241","doi":"10.1016/j.jclinepi.2020.04.016","title":"COVID-19 coronavirus research has overall low methodological quality thus far: case in point for chloroquine/hydroxychloroquine","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":178,"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; Hamilton Health Sciences; McMaster University; Impact","funders":"","keywords":"Hydroxychloroquine; Coronavirus disease 2019 (COVID-19); Chloroquine; Coronavirus; Virology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Medicine; Pandemic; Immunology; Internal medicine; Outbreak; Disease; Malaria; Infectious disease (medical specialty)","score_opus":0.9671013585784821,"score_gpt":0.7779859437677139,"score_spread":0.1891154148107682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018307241","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":[0.00042871406,0.9041355,0.030863017,0.05823105,0.0041196644,0.0016094884,0.00029418667,0.000032954413,0.00028542147],"genre_scores_gemma":[0.00032418143,0.9581958,0.017444532,0.018810458,0.00463066,0.00009178037,0.000034930454,0.000068464775,0.0003992041],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.68465155,0.25011447,0.054348808,0.0039376654,0.004229989,0.0027175457],"domain_scores_gemma":[0.10491545,0.8614503,0.025207242,0.0019468813,0.0020979014,0.0043821833],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7089712,0.0009371433,0.026913505,0.0014740931,0.00044490423,0.00048821236,0.0094103925,0.004853521,0.00067572575],"category_scores_gemma":[0.97137755,0.0005390456,0.006575938,0.0021743728,0.0024725003,0.001119662,0.002288921,0.016577208,0.00017413161],"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":[0.0015009694,0.00031360178,0.0014548729,0.0013493696,0.00026367875,0.003974683,0.00012547021,0.000073109775,8.061806e-8,0.0056167613,0.12549995,0.85982746],"study_design_scores_gemma":[0.0019084762,0.0012663427,0.00032709006,0.0010271955,0.00017593274,0.0050422926,0.00016277244,0.00027861173,3.4194084e-8,0.17768548,0.81169283,0.00043294852],"about_ca_topic_score_codex":0.00073812844,"about_ca_topic_score_gemma":0.00029543947,"teacher_disagreement_score":0.8593945,"about_ca_system_score_codex":0.00090966636,"about_ca_system_score_gemma":0.009925165,"threshold_uncertainty_score":0.9997061},"labels":[],"label_agreement":null},{"id":"W3019956613","doi":"10.1016/j.jclinepi.2020.04.018","title":"Measuring multimorbidity series. An overlooked complexity - Comparison of self-report vs. administrative data in community-living adults: Paper 3. Agreement across data sources and implications for estimating associations with health service use","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Public Health Ontario; University of Toronto; Impact; Institute for Clinical Evaluative Sciences; McMaster University; Women's College Hospital; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Survey data collection; Odds; Count data; Cohort; Cohort study; Odds ratio; Service (business); Missing data; Gerontology; Statistics; Logistic regression; Mathematics; Business","score_opus":0.7654075227167682,"score_gpt":0.5926885148615341,"score_spread":0.17271900785523409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019956613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9489439,0.00016590611,0.0135957515,0.035351474,0.00008801884,0.00076492986,0.0010451574,0.000026128931,0.000018729404],"genre_scores_gemma":[0.84518176,0.0000918849,0.15058753,0.0027964355,0.00019953426,0.0000070184533,0.001121197,0.000013666905,9.842252e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99210316,0.002761834,0.0041400273,0.0004308619,0.00022735923,0.00033675277],"domain_scores_gemma":[0.96861506,0.0216474,0.006928319,0.0015950295,0.0006504362,0.00056375476],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018257186,0.0001890159,0.0022407596,0.000040086303,0.0002590821,0.00002945113,0.0007110542,0.00011336667,0.00001092964],"category_scores_gemma":[0.05251531,0.00015499356,0.000084624764,0.00017521555,0.00029720995,0.0009627644,0.0007549242,0.0009471734,2.1780956e-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":[0.000860324,0.001346244,0.9909599,0.00086661964,0.00053393055,0.000006658122,0.00262487,0.000551194,0.000002608845,0.0002582139,0.00042332849,0.0015661201],"study_design_scores_gemma":[0.0025966398,0.0019172181,0.9134479,0.00057899265,0.00025372856,0.00003593971,0.005580641,0.07494596,4.0067684e-7,0.00017895883,0.00035527692,0.00010832622],"about_ca_topic_score_codex":0.0020800245,"about_ca_topic_score_gemma":0.013112435,"teacher_disagreement_score":0.13699178,"about_ca_system_score_codex":0.000096702286,"about_ca_system_score_gemma":0.0007585294,"threshold_uncertainty_score":0.95546573},"labels":[],"label_agreement":null},{"id":"W3020218337","doi":"10.1016/j.jclinepi.2020.04.019","title":"Measuring multimorbidity series—an overlooked complexity comparison of self-report vs. administrative data in community-living adults: paper 2. Prevalence estimates depend on the data source","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Public Health Ontario; University of Toronto; Impact; Institute for Clinical Evaluative Sciences; University of Alberta; Women's College Hospital; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Series (stratigraphy); Multimorbidity; Data source; Gerontology; Epidemiology; Medicine; Geography; Statistics; Data mining; Computer science; Environmental health; Mathematics; Pathology; Biology; Population","score_opus":0.7396661379205236,"score_gpt":0.5584818237722219,"score_spread":0.18118431414830172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020218337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821683,0.00037478626,0.0015407669,0.01433445,0.00026648416,0.00054488756,0.00013187651,0.000041766612,0.00059665897],"genre_scores_gemma":[0.98743165,0.0003808327,0.009411161,0.0021868134,0.000375083,0.0000029852997,0.00018531337,0.000020785163,0.00000538671],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98595095,0.007622817,0.0049839644,0.00055465003,0.0005186325,0.0003690182],"domain_scores_gemma":[0.927444,0.061174996,0.0063085738,0.0040279985,0.00039594207,0.0006485259],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028825028,0.00028202822,0.0026541331,0.00005921749,0.00013520337,0.00001864125,0.0023413925,0.00019150728,0.0002590024],"category_scores_gemma":[0.18410395,0.00019118193,0.00020792097,0.00016325139,0.00071392197,0.00068405876,0.0015522419,0.0026315749,0.0000058493665],"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":[0.004735562,0.0030747724,0.9831926,0.0013596243,0.00073346,0.00022197097,0.0009575591,0.0008118486,0.00001768301,0.00096734887,0.0019796526,0.0019478702],"study_design_scores_gemma":[0.001979668,0.0034692232,0.88736856,0.0014879489,0.0005281804,0.00012214643,0.0028430554,0.099899076,0.000010585227,0.00053574034,0.0015846193,0.00017121402],"about_ca_topic_score_codex":0.00040406533,"about_ca_topic_score_gemma":0.000702449,"teacher_disagreement_score":0.15527894,"about_ca_system_score_codex":0.000060635834,"about_ca_system_score_gemma":0.000543435,"threshold_uncertainty_score":0.9996694},"labels":[],"label_agreement":null},{"id":"W3020513844","doi":"10.1016/j.jclinepi.2020.04.001","title":"Methodological challenges in studying the COVID-19 pandemic crisis","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":30,"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; Bruyère; University of Ottawa","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Context (archaeology); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Knowledge base; Set (abstract data type); Public relations; 2019-20 coronavirus outbreak; Publishing; Process (computing); Political science; Health care; Data science; Engineering ethics; Computer science; Medicine; History; Disease; Law; Engineering; Infectious disease (medical specialty); World Wide Web","score_opus":0.976812486063741,"score_gpt":0.6981448662993325,"score_spread":0.27866761976440857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020513844","genre_codex":"commentary","genre_gemma":"empirical","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":[0.13173087,0.010791331,0.06962806,0.7863048,0.0007582528,0.0004121158,0.0000040939685,0.000087536326,0.00028296787],"genre_scores_gemma":[0.70385617,0.035189766,0.04902974,0.20963842,0.0022229447,0.00002490105,4.1437565e-7,0.000028028287,0.000009608327],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.926254,0.06146912,0.010191248,0.00082009326,0.00041068986,0.0008548705],"domain_scores_gemma":[0.3177428,0.6755935,0.0050599333,0.00048525952,0.00020439859,0.00091414433],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18279034,0.00036139888,0.0060627116,0.000092062895,0.00014975439,0.0000072303214,0.001235412,0.0007125958,0.00016990877],"category_scores_gemma":[0.905848,0.00017926849,0.0013957463,0.00032126403,0.0006741602,0.00008692672,0.0006069526,0.0032219891,0.00002419626],"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":[0.0010423684,0.000350589,0.8806287,0.00019998508,0.0004095034,0.00018974577,0.0012843473,0.0007962449,0.0000056378294,0.047293417,0.050141223,0.017658243],"study_design_scores_gemma":[0.0017660458,0.0015458268,0.16046008,0.00003559198,0.00015386753,0.00014109547,0.0020512964,0.0004725632,4.22264e-7,0.7381253,0.095006384,0.0002414903],"about_ca_topic_score_codex":0.000046314835,"about_ca_topic_score_gemma":0.00008585503,"teacher_disagreement_score":0.7230577,"about_ca_system_score_codex":0.00015125854,"about_ca_system_score_gemma":0.0002411003,"threshold_uncertainty_score":0.9990776},"labels":[],"label_agreement":null},{"id":"W3021024869","doi":"10.1016/j.jclinepi.2020.04.003","title":"Erratum to “A systematic survey identified 36 criteria for assessing effect modification claims in randomized trials or meta-analyses” [J Clin Epidemiol. 2019;113:159-67]","year":2020,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Hamilton Health Sciences; University of Toronto; McMaster University; Impact","funders":"","keywords":"Credibility; Meta-analysis; Randomized controlled trial; Systematic review; Medicine; Psychology; Family medicine; MEDLINE; Epistemology; Surgery; Internal medicine; Philosophy; Political science; Law","score_opus":0.978919574672684,"score_gpt":0.7614501478138681,"score_spread":0.21746942685881587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021024869","genre_codex":"methods","genre_gemma":"other","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":[0.0014890408,0.040948946,0.76969063,0.033809558,0.1292232,0.02346279,0.0005148512,0.000025920674,0.0008350486],"genre_scores_gemma":[0.07778517,0.020587368,0.27463764,0.061361734,0.058125757,0.00961789,0.0035500727,0.0012886091,0.49304575],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.018302249,0.72899294,0.24217726,0.00355071,0.005767765,0.0012090647],"domain_scores_gemma":[0.010091278,0.7486168,0.226436,0.0058542127,0.0075101187,0.0014915935],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.98036283,0.002198218,0.26923603,0.0027767094,0.0002508847,0.0014103989,0.008267523,0.0040147225,0.003442021],"category_scores_gemma":[0.99576294,0.00087658863,0.08942024,0.0034606871,0.00048308127,0.0008042744,0.00050154456,0.0057348507,0.0012604025],"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":[0.021615053,0.00017791316,0.00092539284,0.0053582503,0.026753766,0.000038115493,0.000058214202,0.00061851,0.00000624717,0.00013186752,0.943296,0.0010206741],"study_design_scores_gemma":[0.116932586,0.0039737397,0.03063889,0.019708334,0.38826758,0.00030791233,0.00042719868,0.16510102,0.0000066104985,0.13508253,0.13535921,0.004194368],"about_ca_topic_score_codex":0.00013289327,"about_ca_topic_score_gemma":0.00027117107,"teacher_disagreement_score":0.8079368,"about_ca_system_score_codex":0.0002444932,"about_ca_system_score_gemma":0.0020821558,"threshold_uncertainty_score":0.9996262},"labels":[],"label_agreement":null},{"id":"W3022004267","doi":"10.1016/j.jclinepi.2020.05.007","title":"Controversy and Debate Series on Core Outcome Sets: The SOLAR (Standardized Outcomes Linking Across StakeholdeRs) system and hub and spokes model for direct core outcome measures in health care and its relation to GRADE","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Cochrane; McMaster University; Impact","funders":"","keywords":"Outcome (game theory); Health care; Medicine; Core (optical fiber); Intervention (counseling); Guideline; Harmonization; Health technology; Public health; Nursing; Computer science; Political science","score_opus":0.7682114307894629,"score_gpt":0.6152901256422321,"score_spread":0.1529213051472308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022004267","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":[0.11411356,0.0039174873,0.002429854,0.87602913,0.00072428165,0.0022258817,0.00046579813,0.000056307043,0.0000376716],"genre_scores_gemma":[0.7842338,0.0045619346,0.0039288267,0.20601012,0.0010250394,0.000057027704,0.000015160047,0.00006507243,0.00010300226],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882372,0.005281225,0.004279743,0.0006756925,0.00069443724,0.0008317219],"domain_scores_gemma":[0.9506615,0.045522597,0.0027354625,0.00023444329,0.00042065667,0.0004253385],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04001952,0.0004042618,0.0041452004,0.00019136841,0.000692938,0.0001199945,0.00043478995,0.0011809908,7.2714744e-7],"category_scores_gemma":[0.08065573,0.00026457044,0.00037580924,0.00014795735,0.00087986805,0.00022121635,0.00020949317,0.0034815357,2.9738018e-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":[0.0028076055,0.00002854328,0.9270739,0.0023075773,0.00039985892,0.0002542112,0.01593072,0.0005027468,0.0000022488407,0.004668735,0.03848979,0.0075340434],"study_design_scores_gemma":[0.025413213,0.013613435,0.38423154,0.009352971,0.0010425474,0.00045403553,0.05170044,0.04087086,0.000003953254,0.05892824,0.41089213,0.0034966315],"about_ca_topic_score_codex":0.00030957788,"about_ca_topic_score_gemma":0.0013452742,"teacher_disagreement_score":0.67012024,"about_ca_system_score_codex":0.00030934106,"about_ca_system_score_gemma":0.00041778677,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W3022123041","doi":"10.1016/j.jclinepi.2020.04.020","title":"Measuring multimorbidity series: an overlooked complexity—comparison of self-report vs. administrative data in community-living adults—paper 1: introduction","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Public Health Ontario; University of Toronto; Impact; Institute for Clinical Evaluative Sciences; McMaster University; Women's College Hospital; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Multimorbidity; Scopus; Medicine; Public health; Health care; Gerontology; Epidemiology; Population; Population health; Chronic condition; Subject (documents); Family medicine; Chronic disease; MEDLINE; Disease; Library science; Nursing; Environmental health; Pathology; Political science; Computer science","score_opus":0.6639154465498319,"score_gpt":0.5530112711734071,"score_spread":0.11090417537642483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022123041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9758872,0.00020525286,0.0010017544,0.021173434,0.00071770337,0.00033601894,0.000018526722,0.000040201554,0.00061992643],"genre_scores_gemma":[0.98288506,0.0002543391,0.013578192,0.0011887085,0.001952007,0.000002314251,0.00011278383,0.000018720684,0.000007882766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98633957,0.006557384,0.005957294,0.000440518,0.000381231,0.00032402918],"domain_scores_gemma":[0.9832786,0.00963498,0.004796147,0.0012820252,0.0004534855,0.0005547883],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020529393,0.00023301027,0.003131373,0.0001157375,0.00007362349,0.000009946176,0.0006884441,0.00022854756,0.000290543],"category_scores_gemma":[0.101793095,0.00019802024,0.0003111546,0.00021738511,0.00052863965,0.0007470156,0.00043607346,0.0022634857,0.000004773211],"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":[0.006202455,0.0038136756,0.9769114,0.0010605736,0.00084310916,0.00026939172,0.0018327616,0.0005525566,0.000085096945,0.0015375242,0.003965777,0.0029256816],"study_design_scores_gemma":[0.0032508627,0.0049971314,0.96553963,0.00046650387,0.00042096764,0.0002026046,0.005290694,0.013028258,0.00001876695,0.00075205235,0.0058530658,0.00017946401],"about_ca_topic_score_codex":0.00033791547,"about_ca_topic_score_gemma":0.0004907873,"teacher_disagreement_score":0.081263706,"about_ca_system_score_codex":0.000096174874,"about_ca_system_score_gemma":0.0005501589,"threshold_uncertainty_score":0.9833845},"labels":[],"label_agreement":null},{"id":"W3022767606","doi":"10.1016/j.jclinepi.2004.01.001","title":"International differences in major depression prevalence: what do they mean?","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Treatment and Access","field":"Psychology","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":"Scopus; CIDI; Epidemiology; Comorbidity; National Comorbidity Survey; Depression (economics); Psychiatry; Psychiatric epidemiology; MEDLINE; Medicine; Population; Major depressive disorder; Psychology; Clinical psychology; Gerontology; Demography; Environmental health; Internal medicine; Political science","score_opus":0.27774685300860047,"score_gpt":0.5625707210048725,"score_spread":0.284823867996272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022767606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760338,0.0051978608,0.000187653,0.007747913,0.008141723,0.00016737496,0.0000028892207,0.000007651442,0.0025131118],"genre_scores_gemma":[0.9855871,0.010089172,0.0011261243,0.0019180418,0.0010217937,0.000011106032,0.0000022588035,0.000008720043,0.00023565804],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99321336,0.0024541456,0.0034730823,0.0003108261,0.00020087058,0.00034770634],"domain_scores_gemma":[0.9889277,0.008510176,0.0020456535,0.00020896304,0.00008457835,0.00022288784],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0096707065,0.00015293842,0.0012402921,0.00015676928,0.00004804454,0.000018440673,0.0005689891,0.00035229817,0.0011632463],"category_scores_gemma":[0.0035431373,0.000095526906,0.00032625598,0.00006575225,0.0001405523,0.0003796834,0.00007713683,0.0008240328,0.00010077007],"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":[0.0008348838,0.000687144,0.86416787,0.000018611396,0.00008550847,0.000092119815,0.00034832687,0.000015736237,0.0000022451343,0.0028233146,0.0002498637,0.13067439],"study_design_scores_gemma":[0.0041778916,0.00063145126,0.9412106,0.00058094575,0.00002963693,0.000106028085,0.0004275989,0.000008244136,0.000004972164,0.05202144,0.00071455777,0.00008660214],"about_ca_topic_score_codex":0.00011490391,"about_ca_topic_score_gemma":0.00005663664,"teacher_disagreement_score":0.13058779,"about_ca_system_score_codex":0.000071576345,"about_ca_system_score_gemma":0.000053416996,"threshold_uncertainty_score":0.99974984},"labels":[],"label_agreement":null},{"id":"W3023552461","doi":"10.1016/j.jclinepi.2011.06.004","title":"GRADE guidelines: 9. Rating up the quality of evidence","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiovascular Syncope and Autonomic Disorders","field":"Medicine","cited_by":1332,"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":"Quality (philosophy); Medicine; MEDLINE; Quality of evidence; Randomized controlled trial; Surgery; Political science","score_opus":0.8737776950481684,"score_gpt":0.6260377094438844,"score_spread":0.247739985604284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023552461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92887133,0.0109431,0.021035187,0.03444614,0.0027469965,0.00024871234,0.0000016423913,0.000012012408,0.0016948761],"genre_scores_gemma":[0.9720393,0.0042457986,0.014561693,0.007975162,0.0009628799,0.0000016924088,4.5623403e-7,0.000011220055,0.00020180338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98850465,0.0040321597,0.00685029,0.00017408199,0.00023155287,0.00020729566],"domain_scores_gemma":[0.9706132,0.023981474,0.0040314295,0.0005397714,0.00065245293,0.00018169775],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07354182,0.000111372625,0.0024930928,0.000048423968,0.000029816225,0.0000015429916,0.00029009182,0.00018434352,0.0001249136],"category_scores_gemma":[0.24752067,0.000052608793,0.0020338816,0.00009613348,0.0004194001,0.00008185221,0.000066694556,0.0006794822,0.0000130855115],"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":[0.0014446131,0.00028138552,0.77025336,0.00012915724,0.0013064672,0.000033177104,0.00043832065,0.00009100483,0.00019187164,0.0037417628,0.021837175,0.20025171],"study_design_scores_gemma":[0.0025949331,0.0010500549,0.96651816,0.0006891345,0.0004885751,0.0003215764,0.00076693646,0.00028022856,0.00011226347,0.009016822,0.018043797,0.00011753074],"about_ca_topic_score_codex":0.0001580571,"about_ca_topic_score_gemma":0.000009065418,"teacher_disagreement_score":0.20013419,"about_ca_system_score_codex":0.000014036543,"about_ca_system_score_gemma":0.00034227912,"threshold_uncertainty_score":0.95398366},"labels":[],"label_agreement":null},{"id":"W3024509053","doi":"10.1016/j.jclinepi.2020.04.028","title":"Delphi consensus on core criteria set selecting among health-related outcome measures (HROM) in primary health care","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"University of Toronto; McMaster University; Impact","funders":"Health Canada; Government of Ontario; McMaster University","keywords":"Delphi method; Outcome (game theory); Core (optical fiber); Delphi; Set (abstract data type); Medicine; Health care; MEDLINE; Primary care; Consensus conference; Family medicine; Computer science; Political science; Statistics; Mathematics","score_opus":0.7617082329822493,"score_gpt":0.6563067722474677,"score_spread":0.10540146073478163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024509053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61729544,0.0016531294,0.0002378526,0.37773672,0.0009806583,0.0005642922,0.000013689854,0.000077884644,0.0014403138],"genre_scores_gemma":[0.95407814,0.0009672247,0.0057965782,0.038320027,0.00078286114,0.000005432972,0.0000042551383,0.000025976244,0.00001952801],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9652092,0.024148371,0.0083162,0.0004899531,0.0007593823,0.0010769344],"domain_scores_gemma":[0.9545916,0.038944013,0.0044794953,0.00023165719,0.0005640083,0.0011892605],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08857439,0.0002145028,0.0032119849,0.00023743382,0.0003185235,0.000020373167,0.00075006566,0.0006384716,0.00007831243],"category_scores_gemma":[0.22924447,0.00018244084,0.000525655,0.0006396253,0.00096866745,0.0000905628,0.00012108324,0.0036496227,0.000017581366],"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":[0.00075699145,0.00012093073,0.87876964,0.00011273122,0.00007273942,0.00019958474,0.008066888,0.00019921297,0.0000075330804,0.0012826744,0.07829476,0.032116346],"study_design_scores_gemma":[0.0030204682,0.0064710644,0.9395241,0.00071732706,0.000021860225,0.000068866044,0.009869177,0.000659285,0.0000029512842,0.007534921,0.031662453,0.00044753944],"about_ca_topic_score_codex":0.0032266306,"about_ca_topic_score_gemma":0.0021920695,"teacher_disagreement_score":0.33941668,"about_ca_system_score_codex":0.0007267111,"about_ca_system_score_gemma":0.003114868,"threshold_uncertainty_score":0.998649},"labels":[],"label_agreement":null},{"id":"W3024636579","doi":"10.1016/j.jclinepi.2020.05.012","title":"Controversy and Debate Series on Core Outcome Sets. Paper 2: Debate on Paper 1 from the perspective of OMERACT [Outcome Measures in Rheumatology]","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Institute for Work & Health; University of Toronto; University of Ottawa","funders":"","keywords":"Outcome (game theory); Perspective (graphical); Medicine; Core (optical fiber); Series (stratigraphy); Rheumatology; Alternative medicine; Internal medicine; Family medicine; Computer science; Artificial intelligence; Economics; Pathology; Mathematical economics; Biology","score_opus":0.5457569856888365,"score_gpt":0.5810090735576304,"score_spread":0.03525208786879397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024636579","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":[0.029357785,0.00080426404,0.000024899926,0.9657923,0.0014944033,0.00052521314,0.000103694634,0.000026661086,0.001870781],"genre_scores_gemma":[0.28624544,0.007436099,0.00072275574,0.7035624,0.0017526349,0.000020069516,0.000010080068,0.00005840742,0.00019212517],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718547,0.019250076,0.00626371,0.000719094,0.0010701304,0.0008423002],"domain_scores_gemma":[0.8152005,0.1787788,0.004617976,0.00051101536,0.0006151851,0.00027651526],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.030410634,0.0004692482,0.0053527057,0.00024347816,0.00021063356,0.000032516145,0.001502765,0.0021576204,0.00029285392],"category_scores_gemma":[0.32329473,0.00028600686,0.0011207393,0.0002711721,0.003332487,0.00024677222,0.00022110085,0.0103808325,0.000031298423],"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":[0.0023584084,0.000114783325,0.50021696,0.00004562235,0.0005533252,0.0010332463,0.0011969025,0.0000146104585,0.000005810884,0.015789906,0.4768263,0.0018440898],"study_design_scores_gemma":[0.0022698694,0.0023064301,0.21664205,0.00067670405,0.00019338603,0.00008808754,0.0026724841,0.000021537671,0.0000020783816,0.19197208,0.58263975,0.0005155503],"about_ca_topic_score_codex":0.0057541584,"about_ca_topic_score_gemma":0.001794226,"teacher_disagreement_score":0.2928841,"about_ca_system_score_codex":0.00028199932,"about_ca_system_score_gemma":0.0006548567,"threshold_uncertainty_score":0.99995923},"labels":[],"label_agreement":null},{"id":"W3024899947","doi":"10.1016/j.jclinepi.2020.05.003","title":"A search filter to identify pragmatic trials in MEDLINE was highly specific but lacked sensitivity","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Randomized controlled trial; Sensitivity (control systems); Confidence interval; Medicine; Clinical trial; Filter (signal processing); Computer science; Data mining; Surgery; Internal medicine","score_opus":0.9548075711189307,"score_gpt":0.703447435217891,"score_spread":0.25136013590103967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024899947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.739167,0.00047954233,0.10371628,0.15447593,0.0011818033,0.0006309812,0.00001742913,0.0000027936562,0.00032829217],"genre_scores_gemma":[0.93668294,0.00030854277,0.041381735,0.018579122,0.0024482724,0.0000058033706,0.0000030187816,0.000015688931,0.0005748778],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.16196735,0.68394256,0.14584187,0.0017863421,0.0055801077,0.0008817689],"domain_scores_gemma":[0.09565403,0.8501981,0.04684791,0.002722757,0.0028257065,0.0017515017],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.89371043,0.000338767,0.030416634,0.0005594319,0.000049825954,0.0001702246,0.0017202547,0.00037301006,0.0053861886],"category_scores_gemma":[0.9535029,0.00015190692,0.0076726773,0.001458023,0.00017738742,0.00023922363,0.00030737364,0.0014529667,0.004465943],"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":[0.0009447005,0.00036159417,0.31729072,0.0001231278,0.0008169058,0.0006008729,0.00072087435,0.0035719702,0.0011349986,0.0020214412,0.6210153,0.051397473],"study_design_scores_gemma":[0.0034166186,0.001472607,0.6716802,0.00035138347,0.00053238217,0.0002576949,0.0008768515,0.037263144,0.00008282148,0.032909542,0.25066668,0.0004900782],"about_ca_topic_score_codex":0.000013098205,"about_ca_topic_score_gemma":0.000028655713,"teacher_disagreement_score":0.37034863,"about_ca_system_score_codex":0.000038669466,"about_ca_system_score_gemma":0.00024579102,"threshold_uncertainty_score":0.9963092},"labels":[],"label_agreement":null},{"id":"W3025529179","doi":"10.1016/j.jclinepi.2020.04.030","title":"The importance of decision intent within descriptions of pragmatic trials","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":16,"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; Western University; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Pragmatism; Clinical trial; Research design; Clinical study design; Psychology; Management science; Medicine; Computer science; Epistemology; Sociology; Pathology","score_opus":0.9648960528797748,"score_gpt":0.7082879014526782,"score_spread":0.2566081514270966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025529179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56550807,0.005615535,0.37950015,0.045858487,0.0023813166,0.00059370766,0.000013563757,0.0000014730446,0.0005276769],"genre_scores_gemma":[0.919333,0.0010083009,0.075510114,0.0034534442,0.00045806429,0.000003998177,5.670176e-7,0.000007621105,0.0002248966],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2750207,0.38533267,0.33086452,0.0012112161,0.006996443,0.00057448645],"domain_scores_gemma":[0.039119396,0.77413625,0.17950325,0.0023788637,0.004341746,0.000520506],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8151177,0.00017999737,0.01844334,0.00013638775,0.00006227229,0.000037171543,0.002372617,0.00019418688,0.001253453],"category_scores_gemma":[0.97899526,0.000058546015,0.008034934,0.0007080645,0.00039989944,0.0001295217,0.0001530573,0.00062501413,0.00010906269],"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":[0.00058527745,0.00017651812,0.66045964,0.000069554895,0.0012189767,0.000010104466,0.00036886754,0.0017934284,0.00010257736,0.030975394,0.2447561,0.059483528],"study_design_scores_gemma":[0.0019274597,0.0023613477,0.23296472,0.000483746,0.0016713163,0.00011746674,0.0021490534,0.04032763,0.000030981962,0.6260986,0.09166176,0.00020592187],"about_ca_topic_score_codex":0.000002012562,"about_ca_topic_score_gemma":0.000012677298,"teacher_disagreement_score":0.59512323,"about_ca_system_score_codex":0.000010646015,"about_ca_system_score_gemma":0.00026779278,"threshold_uncertainty_score":0.99965954},"labels":[],"label_agreement":null},{"id":"W3026023260","doi":"10.1016/j.jclinepi.2020.04.025","title":"An overview of platform trials with a checklist for clinical readers","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":134,"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; University of British Columbia","funders":"","keywords":"Checklist; Medicine; Clinical trial; Medical physics; MEDLINE; Psychology; Pathology; Political science","score_opus":0.9831555363446806,"score_gpt":0.8034965836444816,"score_spread":0.17965895270019894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026023260","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":[0.000005084929,0.8355852,0.15632899,0.0010826392,0.0038993615,0.0024352733,0.00051908067,0.000033289125,0.00011113122],"genre_scores_gemma":[4.256458e-7,0.52791744,0.46617708,0.00071869744,0.005016352,0.000039113296,0.000008667919,0.00010252253,0.00001968481],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7723377,0.123850875,0.09977867,0.0017824308,0.0010435646,0.0012067975],"domain_scores_gemma":[0.08248743,0.8438683,0.0695947,0.0014285852,0.0011186461,0.0015023124],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.43032318,0.0010594818,0.07683411,0.0002583585,0.00006299204,0.00002143377,0.0022393116,0.003976396,0.00024780937],"category_scores_gemma":[0.96680707,0.00058449,0.015187721,0.00047231655,0.001853308,0.00015999515,0.00019686409,0.005333739,0.000015985977],"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":[0.0030868556,0.00097207545,0.000129657,0.020086622,0.003910355,0.0000621636,0.000013100056,5.392331e-7,1.5478335e-8,0.0593193,0.01603388,0.89638543],"study_design_scores_gemma":[0.0032459665,0.008656575,0.00003352133,0.013557683,0.00971359,0.00012658742,0.000018641553,0.000030115107,1.06877316e-7,0.40065846,0.56358707,0.00037165915],"about_ca_topic_score_codex":0.0000037216992,"about_ca_topic_score_gemma":0.0000034786985,"teacher_disagreement_score":0.8960138,"about_ca_system_score_codex":0.00008727506,"about_ca_system_score_gemma":0.002963554,"threshold_uncertainty_score":0.9996607},"labels":[],"label_agreement":null},{"id":"W3027437879","doi":"10.1016/j.jclinepi.2020.04.026","title":"Quality and risk of bias appraisals of systematic reviews are inconsistent across reviewers and centers","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":67,"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":"Medicine; Interquartile range; Confidence interval; Systematic review; Publication bias; Reliability (semiconductor); MEDLINE; Surgery; Internal medicine; Biology","score_opus":0.9721662925162776,"score_gpt":0.7176930539635952,"score_spread":0.25447323855268245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027437879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85689586,0.114540756,0.015645115,0.010517711,0.0007063505,0.0014906653,0.00005635703,0.0000016193887,0.00014557711],"genre_scores_gemma":[0.8689923,0.106430344,0.019426666,0.004793494,0.0002606994,0.000010870578,8.712857e-7,0.000012663528,0.00007208868],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.39429584,0.4402826,0.1607586,0.0012015539,0.003018223,0.00044314668],"domain_scores_gemma":[0.09767225,0.5852872,0.3088566,0.0032868553,0.0037213627,0.001175737],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7628012,0.00029604053,0.036266703,0.00011161934,0.000049570386,0.000039449504,0.0011183697,0.00023220798,0.00017418334],"category_scores_gemma":[0.95724285,0.000120254765,0.0060182232,0.0005033153,0.000584475,0.00014196441,0.00025006948,0.00059233326,0.00003794868],"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":[0.000063181644,0.00005612019,0.9635451,0.01598287,0.00072103605,0.0000029412913,0.00026688102,0.000018540022,0.0000046615955,0.00035955364,0.010560403,0.008418741],"study_design_scores_gemma":[0.001323986,0.0009092925,0.93604463,0.011360754,0.002571701,0.00010704457,0.0025094408,0.0017286444,0.0000025302184,0.0058221025,0.03734501,0.0002748387],"about_ca_topic_score_codex":0.0000133115645,"about_ca_topic_score_gemma":0.000012283101,"teacher_disagreement_score":0.2966236,"about_ca_system_score_codex":0.000007882539,"about_ca_system_score_gemma":0.00006224335,"threshold_uncertainty_score":0.97804093},"labels":[],"label_agreement":null},{"id":"W3027704254","doi":"10.1016/j.jclinepi.2020.04.011","title":"Primum non nocere: appropriate evidence assessment and fair judgment over time","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Cervical Cancer and HPV Research","field":"Medicine","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":"University of Ottawa","funders":"","keywords":"Overdiagnosis; Medicine; Context (archaeology); Natural history; Cervical screening; Family medicine; General surgery; Gynecology; History; Pathology; Cervical cancer; Internal medicine","score_opus":0.39382929705999475,"score_gpt":0.5689705975752608,"score_spread":0.17514130051526605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027704254","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":[0.0022509703,0.0020764773,0.0015114222,0.99019456,0.0011544463,0.00052277284,0.000015566924,0.000016442678,0.002257319],"genre_scores_gemma":[0.00530601,0.008696361,0.0050473427,0.9569943,0.02245285,0.000012459232,0.000031789546,0.000062310544,0.0013965627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98846394,0.0036099656,0.005486572,0.0007487359,0.00096710277,0.00072366826],"domain_scores_gemma":[0.9634407,0.03146605,0.0030837639,0.0005168517,0.0006064638,0.0008861446],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.015552975,0.0004183461,0.005891456,0.00017744655,0.000058226044,0.000022208875,0.00047226148,0.0016231899,0.0035649245],"category_scores_gemma":[0.02919978,0.00027625455,0.0013014134,0.00015871807,0.0005525442,0.00011196485,0.0003898022,0.011856967,0.000102941594],"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":[0.0013628954,0.00011195064,0.036517307,0.0008837666,0.0005633375,0.0014003764,0.000012318916,0.0000025008824,0.000015318008,0.000015277274,0.92374814,0.035366833],"study_design_scores_gemma":[0.0031599624,0.0060819993,0.36884558,0.00060420105,0.0006780426,0.00034137475,0.000003465829,0.0016874339,0.0000027184446,0.0032105998,0.6151079,0.00027671733],"about_ca_topic_score_codex":0.00002646085,"about_ca_topic_score_gemma":0.0000014716256,"teacher_disagreement_score":0.33232826,"about_ca_system_score_codex":0.0002664571,"about_ca_system_score_gemma":0.0017232837,"threshold_uncertainty_score":0.99996895},"labels":[],"label_agreement":null},{"id":"W3028885010","doi":"10.1016/j.jclinepi.2020.05.022","title":"Counterfactual clinical prediction models could help to infer individualized treatment effects in randomized controlled trials—An illustration with the International Stroke Trial","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Acute Ischemic Stroke Management","field":"Medicine","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":"Impact; Population Health Research Institute; McMaster University","funders":"NIHR Oxford Biomedical Research Centre; Cancer Research UK; National Institute for Health and Care Research; NIHR Bristol Biomedical Research Centre","keywords":"Counterfactual thinking; Medicine; Aspirin; Randomized controlled trial; Stroke (engine); Clinical trial; Logistic regression; Population; Cohort; Intensive care medicine; Internal medicine; Psychology","score_opus":0.33938022282509095,"score_gpt":0.5013817380823635,"score_spread":0.16200151525727258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028885010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76996434,0.00016225944,0.13160208,0.08845023,0.0025669073,0.006294146,0.000029931261,0.000028002805,0.00090211973],"genre_scores_gemma":[0.96249557,0.0008112205,0.0064310865,0.023228792,0.006488556,0.0002746159,0.000041953113,0.000028252753,0.00019995302],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9599512,0.024970628,0.013307528,0.0005503907,0.00084060454,0.00037961281],"domain_scores_gemma":[0.8088724,0.18079053,0.008479655,0.00043582253,0.0005893802,0.00083222636],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11580242,0.00035536892,0.012844066,0.0002070012,0.000039533457,0.000028575387,0.00036901364,0.00050283177,0.00010451965],"category_scores_gemma":[0.24813275,0.00015944372,0.0024011515,0.00012647882,0.00031969816,0.00020303697,0.000076221535,0.0012748494,0.000009576911],"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":[0.9571124,0.0009231762,0.01163653,0.0000120465165,0.00499419,0.00006112557,0.00031026822,0.004286752,0.000025279141,0.0004170687,0.011640694,0.00858047],"study_design_scores_gemma":[0.9087501,0.019754777,0.0038910946,0.00012505286,0.0030320787,0.000032383025,0.00020423187,0.05692822,0.000011968611,0.00020844466,0.0069402433,0.00012138997],"about_ca_topic_score_codex":0.000022648483,"about_ca_topic_score_gemma":0.000017537106,"teacher_disagreement_score":0.19253124,"about_ca_system_score_codex":0.00015899864,"about_ca_system_score_gemma":0.000580666,"threshold_uncertainty_score":0.91046745},"labels":[],"label_agreement":null},{"id":"W3030758089","doi":"10.1016/j.jclinepi.2020.05.024","title":"“One more time”: why replicating some syntheses of evidence relevant to COVID-19 makes sense","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; Bruyère; University of Ottawa","funders":"Australian Research Council","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Sense (electronics); Betacoronavirus; Coronavirus Infections; Pandemic; Virology; MEDLINE; Computational biology; Medicine; Computer science; Biology; Chemistry; Pathology; Outbreak","score_opus":0.96969517280465,"score_gpt":0.7014217309523658,"score_spread":0.2682734418522842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030758089","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19716632,0.004321866,0.13549605,0.66143996,0.0005129806,0.0006665315,0.0000203385,0.0000089687865,0.00036697238],"genre_scores_gemma":[0.6406967,0.001430032,0.14262903,0.21241684,0.0019087129,0.000011015888,8.576463e-7,0.000028635646,0.0008781748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7510347,0.14750963,0.09383992,0.0019567579,0.004984255,0.00067475653],"domain_scores_gemma":[0.09032429,0.8313001,0.06861546,0.004152205,0.0030770171,0.0025309713],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.56469834,0.00028181588,0.016101547,0.00026887815,0.00008304521,0.00006217958,0.0023198666,0.00028323918,0.0030902415],"category_scores_gemma":[0.9868575,0.00012611036,0.005074538,0.00093729165,0.00034624443,0.00027900582,0.0003445901,0.0007765208,0.0013346631],"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":[0.00089842966,0.00028360312,0.21675463,0.00047985194,0.0013475444,0.00014781501,0.0009799488,0.0063229003,0.0013625673,0.004419583,0.6821292,0.08487389],"study_design_scores_gemma":[0.0010538598,0.004473678,0.089266844,0.0022386657,0.0021654791,0.00062701775,0.0013668448,0.05514191,0.00013124857,0.1018349,0.740827,0.0008725153],"about_ca_topic_score_codex":0.000016818376,"about_ca_topic_score_gemma":0.0000026715134,"teacher_disagreement_score":0.68379045,"about_ca_system_score_codex":0.000032361186,"about_ca_system_score_gemma":0.00041687815,"threshold_uncertainty_score":0.99944293},"labels":[],"label_agreement":null},{"id":"W3032569556","doi":"10.1016/j.jclinepi.2020.05.025","title":"What to do with all the AGREEs? The AGREE portfolio of tools to support the guideline enterprise","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":77,"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; North York General Hospital; Juravinski Cancer Centre; McMaster University; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Portfolio; Medicine; Business; Finance; Pathology","score_opus":0.5865754284296243,"score_gpt":0.599006532574351,"score_spread":0.012431104144726701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032569556","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":[0.21634676,0.00025231272,0.017907074,0.7632141,0.0011373009,0.0008878353,0.000010535698,0.000007872897,0.00023617834],"genre_scores_gemma":[0.4963765,0.0012809131,0.010492398,0.4885267,0.0031616364,0.000011085514,0.000010501377,0.000027831924,0.0001124342],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9825307,0.0040226313,0.011824263,0.00040912736,0.0007386941,0.0004745897],"domain_scores_gemma":[0.86603636,0.120382324,0.008860346,0.001425213,0.0020605293,0.0012352483],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053766523,0.0002524656,0.002210371,0.000063642954,0.00007489198,0.000038712413,0.0009979228,0.00019885525,0.0007572256],"category_scores_gemma":[0.32236513,0.000094694384,0.0008434622,0.00038669212,0.00038736803,0.00031860798,0.00034098237,0.0016660925,0.000102256345],"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":[0.009076441,0.00028039495,0.110169806,0.000023161501,0.00082524744,0.00013424348,0.0008190946,0.0012517598,0.00007725618,0.00048064537,0.692178,0.18468393],"study_design_scores_gemma":[0.003478713,0.0144154485,0.18003546,0.0002092378,0.0011036592,0.0007224881,0.0036564586,0.00048964715,0.000029378363,0.0011223842,0.7945692,0.00016794197],"about_ca_topic_score_codex":0.00005759688,"about_ca_topic_score_gemma":0.000079357174,"teacher_disagreement_score":0.28002974,"about_ca_system_score_codex":0.00003552884,"about_ca_system_score_gemma":0.0006383248,"threshold_uncertainty_score":0.9743465},"labels":[],"label_agreement":null},{"id":"W3032991425","doi":"10.1016/j.jclinepi.2020.05.031","title":"The number needed to treat for net effect (NNTnet) as a metric for measuring combined benefits and harms","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact; Programs for Assessment of Technology in Health Research Institute","funders":"","keywords":"Metric (unit); Medicine; Number needed to treat; Mathematics; Statistics; Internal medicine; Economics; Operations management; Confidence interval; Relative risk","score_opus":0.7632467246204355,"score_gpt":0.5823184958693426,"score_spread":0.18092822875109293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032991425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57676435,0.0035136181,0.019455886,0.39712268,0.0013867988,0.001391836,0.000078546254,0.000014763007,0.00027151115],"genre_scores_gemma":[0.7600716,0.0019421317,0.025432022,0.2071407,0.0047976202,0.000264654,0.00001152276,0.000081005965,0.00025877796],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9849473,0.0023644038,0.011661093,0.00045419112,0.00006682668,0.00050618564],"domain_scores_gemma":[0.8044351,0.18661918,0.007622095,0.00027952582,0.00022834954,0.00081579294],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13081457,0.00019783294,0.0036840125,0.00013223509,0.0002201519,0.00004098211,0.0003868332,0.00028553896,0.000035725603],"category_scores_gemma":[0.46566275,0.00015606827,0.0006807018,0.00017891749,0.00009496438,0.00016447855,0.00006287979,0.00037207708,0.00016821854],"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":[0.005076358,0.00015813681,0.48244587,0.0007657562,0.0007328319,0.0000018545145,0.00064206566,0.0022064853,0.0000021773005,0.15096594,0.3261734,0.030829148],"study_design_scores_gemma":[0.02524663,0.016866783,0.19150527,0.00031864966,0.00026893936,0.00008187785,0.0005898211,0.043697942,0.000026165286,0.15207975,0.56834346,0.00097470137],"about_ca_topic_score_codex":0.00010749823,"about_ca_topic_score_gemma":0.000014707992,"teacher_disagreement_score":0.33484817,"about_ca_system_score_codex":0.0001053415,"about_ca_system_score_gemma":0.00013743313,"threshold_uncertainty_score":0.8950093},"labels":[],"label_agreement":null},{"id":"W3033209191","doi":"10.1016/j.jclinepi.2020.05.026","title":"Authors of clinical trials seldom reported details when declaring their individual and institutional financial conflicts of interest: a cross-sectional survey","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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":"Impact; McMaster University","funders":"","keywords":"Descriptive statistics; Actuarial science; Medicine; Accounting; Cross-sectional study; Clinical trial; Data source; Business; Sample size determination; Conflict of interest; Family medicine; Finance; Statistics","score_opus":0.9771231176201945,"score_gpt":0.7489594473271703,"score_spread":0.2281636702930242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033209191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867755,0.0009643597,0.0016072942,0.005619608,0.0041354876,0.00032582422,0.00044099905,0.000015210047,0.00011567263],"genre_scores_gemma":[0.98469365,0.0009593814,0.0015428301,0.0100689195,0.0026544856,0.000004425625,0.000038622136,0.000014847625,0.00002284775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.92736584,0.049520712,0.021484744,0.00065956876,0.0003266884,0.0006424722],"domain_scores_gemma":[0.7975274,0.18077205,0.017080866,0.00030872348,0.0017443318,0.0025666554],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.20331353,0.00031464506,0.005056956,0.00014070499,0.00016952591,0.000011380943,0.0006021719,0.0031068898,0.00069058663],"category_scores_gemma":[0.4747561,0.0002396945,0.0012201408,0.00021980051,0.0024055894,0.00020802866,0.00029401717,0.007851391,0.0000059181293],"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":[0.010275701,0.00051477243,0.9629902,0.00014333177,0.0012032096,0.00008085489,0.0001975457,0.00036974187,0.00024464997,0.0031755373,0.0018866014,0.018917806],"study_design_scores_gemma":[0.0056911474,0.001559393,0.9593444,0.000070010625,0.00027866717,0.00020946628,0.000024532945,0.0023559078,0.0004345583,0.0051873345,0.024664331,0.00018027856],"about_ca_topic_score_codex":0.000036193745,"about_ca_topic_score_gemma":0.00003409092,"teacher_disagreement_score":0.27144256,"about_ca_system_score_codex":0.000025694866,"about_ca_system_score_gemma":0.0017543838,"threshold_uncertainty_score":0.9981873},"labels":[],"label_agreement":null},{"id":"W3033424552","doi":"10.1016/j.jclinepi.2020.06.004","title":"A framework for identifying and mitigating the equity harms of COVID-19 policy interventions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":188,"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; Ottawa Hospital; Impact; Bruyère; University of Ottawa","funders":"Department of Health and Social Care; National Institute for Health and Care Research","keywords":"Psychological intervention; Health equity; Loneliness; Socioeconomic status; Equity (law); Public health; Stigma (botany); Public economics; Health care; Medicine; Environmental health; Political science; Economic growth; Economics; Population; Psychiatry; Nursing","score_opus":0.8299256790388747,"score_gpt":0.7274923724334583,"score_spread":0.10243330660541639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033424552","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":[0.15767878,0.0031922783,0.5167821,0.31998545,0.0017408693,0.0003953332,0.000043561693,0.000013872682,0.00016776739],"genre_scores_gemma":[0.8949468,0.0005236564,0.0162021,0.0862256,0.0020374437,0.000012040143,0.0000019688812,0.000013030723,0.000037349495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918612,0.003317232,0.0041123754,0.00024914386,0.000108388595,0.00035163484],"domain_scores_gemma":[0.9145496,0.08029655,0.004028009,0.00022572116,0.00012112681,0.00077902194],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021966634,0.00011524661,0.0013785409,0.00007634894,0.00013244122,0.0000070411556,0.00038476035,0.00028251312,0.00018219768],"category_scores_gemma":[0.19252676,0.00007596919,0.00096913904,0.00016818024,0.00046648426,0.000055130316,0.00021006785,0.0009999829,0.0000063131956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021704377,0.00046880488,0.27874288,0.0023149883,0.00062120677,0.000024597874,0.0061913417,0.00006752715,0.000049507456,0.5724336,0.019894794,0.1170203],"study_design_scores_gemma":[0.0039041024,0.0041452767,0.18297984,0.0005731276,0.00027285385,0.00014986486,0.003995617,0.0005164245,0.000009572523,0.756997,0.04627817,0.00017818813],"about_ca_topic_score_codex":0.00031689485,"about_ca_topic_score_gemma":0.000030920877,"teacher_disagreement_score":0.73726803,"about_ca_system_score_codex":0.00006906099,"about_ca_system_score_gemma":0.0007185521,"threshold_uncertainty_score":0.8142749},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W3033853719","doi":"10.1016/j.jclinepi.2020.06.005","title":"A large number of COVID-19 interventional clinical trials were registered soon after the pandemic onset: a descriptive analysis","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 and healthcare impacts","field":"Medicine","cited_by":29,"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","funders":"","keywords":"Medicine; Clinical trial; Pandemic; Psychological intervention; Public health; Family medicine; Coronavirus disease 2019 (COVID-19); Disease; Internal medicine; Infectious disease (medical specialty); Nursing","score_opus":0.7851796230022935,"score_gpt":0.676869061421896,"score_spread":0.10831056158039754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033853719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67285955,0.0017324608,0.04516329,0.27864566,0.0009145896,0.00046641173,0.00013150959,0.000019365101,0.0000671489],"genre_scores_gemma":[0.88718575,0.0017534364,0.001277129,0.1075297,0.0020906394,0.000007779077,0.000014545575,0.000017008295,0.00012401988],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94937104,0.032450948,0.016599488,0.00053017645,0.0004988934,0.0005494739],"domain_scores_gemma":[0.7350981,0.23786145,0.020730792,0.0010837878,0.0012872219,0.003938642],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14354229,0.0002604624,0.0077307993,0.00018387425,0.00006735373,0.000008335508,0.00039933465,0.00078505685,0.002187644],"category_scores_gemma":[0.6327009,0.00014547458,0.007017826,0.00050043693,0.0006567914,0.000090080284,0.00015779222,0.0026012706,0.000042931846],"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":[0.023993416,0.0006194475,0.9418187,0.00024184385,0.003841003,0.00019269425,0.0005494373,0.000015606925,0.0000022931783,0.0003489095,0.025040304,0.0033363379],"study_design_scores_gemma":[0.008440374,0.0037948396,0.9089907,0.00026453583,0.0044461777,0.00040551598,0.0005679632,0.0008409054,5.6271796e-7,0.00533063,0.066777684,0.00014015239],"about_ca_topic_score_codex":0.00012926535,"about_ca_topic_score_gemma":0.00027431583,"teacher_disagreement_score":0.48915863,"about_ca_system_score_codex":0.00014619007,"about_ca_system_score_gemma":0.002833446,"threshold_uncertainty_score":0.9996998},"labels":[],"label_agreement":null},{"id":"W3034078120","doi":"10.1016/j.jclinepi.2020.05.030","title":"Using GRADE in situations of emergencies and urgencies: certainty in evidence and recommendations matters during the COVID-19 pandemic, now more than ever and no matter what","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Cochrane; McMaster University; Impact","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Pandemic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Certainty; Coronavirus Infections; Medicine; Betacoronavirus; Virology; Philosophy; Outbreak; Disease","score_opus":0.9390059490544685,"score_gpt":0.6656707537537824,"score_spread":0.2733351953006862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034078120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8075422,0.0028580641,0.0031020045,0.18611823,0.00017865321,0.00019169561,0.0000035456944,6.0863243e-7,0.000005018891],"genre_scores_gemma":[0.96317506,0.012724146,0.004725835,0.019208455,0.00009773421,0.000004319253,4.7193987e-7,0.0000054138523,0.000058563288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95024383,0.030089445,0.018117744,0.00056847226,0.000731967,0.00024856857],"domain_scores_gemma":[0.84674567,0.14038625,0.011282406,0.00068003486,0.00044843552,0.0004571702],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16158344,0.00015915357,0.0037722245,0.00022637038,0.00008858275,0.00007502296,0.0004930124,0.00012599136,0.00084911636],"category_scores_gemma":[0.3247806,0.000074237265,0.00055328844,0.00047479058,0.00036894088,0.0005608059,0.00018612487,0.00047221835,0.000013988484],"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":[0.000029288032,0.000017078317,0.9899039,0.00007244083,0.000057145637,0.0000024159126,0.0012269398,0.0007642836,0.000057050143,0.00003517918,0.0073938556,0.00044037699],"study_design_scores_gemma":[0.0004365467,0.00006603812,0.96883565,0.00022246844,0.00011753983,0.000106052226,0.004423281,0.015498201,9.44325e-7,0.0051038964,0.0050904085,0.00009895015],"about_ca_topic_score_codex":0.00006626878,"about_ca_topic_score_gemma":0.00022030069,"teacher_disagreement_score":0.16690978,"about_ca_system_score_codex":0.000026379803,"about_ca_system_score_gemma":0.000102055594,"threshold_uncertainty_score":0.9297229},"labels":[],"label_agreement":null},{"id":"W3034535291","doi":"10.1016/j.jclinepi.2020.05.034","title":"Meta-analysis of noninferiority and equivalence trials: ignoring trial design leads to differing and possibly misleading conclusions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Meta-analysis; Equivalence (formal languages); Randomized controlled trial; Medicine; Clinical trial; Publication bias; MEDLINE; Research design; Relative risk; Internal medicine; Statistics; Confidence interval; Mathematics","score_opus":0.9869927355597652,"score_gpt":0.7219632874836904,"score_spread":0.26502944807607476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034535291","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.580962,0.003564662,0.40227538,0.012198324,0.00035422426,0.00054805604,0.000011802481,0.0000022149495,0.00008336091],"genre_scores_gemma":[0.9352579,0.00051843113,0.0604647,0.0031375703,0.00048427007,0.000007383625,3.718487e-7,0.000008833783,0.0001205075],"study_design_codex":"observational","study_design_gemma":"meta_analysis","domain_scores_codex":[0.6544354,0.24277253,0.09694009,0.0017765637,0.0034382972,0.00063711265],"domain_scores_gemma":[0.16606389,0.76596624,0.062034123,0.0019770511,0.002121309,0.0018373817],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.67835075,0.00034168203,0.044179883,0.0006439221,0.00012509656,0.00013276032,0.0012868785,0.00027194357,0.0015859324],"category_scores_gemma":[0.8654001,0.00015220964,0.013210112,0.001617244,0.0002537971,0.00021984802,0.0004498631,0.0006591276,0.000022392045],"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":[0.018523877,0.0004085961,0.53317314,0.000284289,0.36140335,0.00009629118,0.002648648,0.021375418,0.0015200757,0.005168774,0.012715591,0.042681973],"study_design_scores_gemma":[0.014595261,0.0077207997,0.14335899,0.000116284915,0.7051539,0.00007381091,0.00089729874,0.10390774,0.000072692914,0.017295394,0.006006494,0.0008013154],"about_ca_topic_score_codex":0.000010171818,"about_ca_topic_score_gemma":0.000006047243,"teacher_disagreement_score":0.5231937,"about_ca_system_score_codex":0.000013126586,"about_ca_system_score_gemma":0.0001431376,"threshold_uncertainty_score":0.99932677},"labels":[],"label_agreement":null},{"id":"W3034875569","doi":"10.1016/j.jclinepi.2020.05.029","title":"How personalized are benefit and harm results of randomized trials? A systematic review","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Impact; Canada Research Chairs; McMaster University; University of Toronto; University of Alberta","funders":"","keywords":"Randomized controlled trial; Medicine; Harm; MEDLINE; Intensive care medicine; Psychology; Internal medicine; Biology","score_opus":0.9177432494998558,"score_gpt":0.7146996155668064,"score_spread":0.20304363393304936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034875569","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":[1.9338641e-7,0.9582942,0.023470305,0.009739428,0.001947525,0.0060249385,0.00043797586,0.000021060387,0.00006435853],"genre_scores_gemma":[2.110798e-7,0.723243,0.27361068,0.0012095704,0.0015792262,0.000114425275,0.000003832935,0.00007064724,0.00016841436],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.4358693,0.43535528,0.12505333,0.0014863258,0.0013813012,0.00085447036],"domain_scores_gemma":[0.014416812,0.84759945,0.13495143,0.0009988823,0.001160504,0.0008729144],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.5881517,0.0010405781,0.2009697,0.00026148336,0.000045833764,0.00003397042,0.0013319582,0.0020962167,0.00008006813],"category_scores_gemma":[0.9976561,0.00053492596,0.0228755,0.00042364316,0.0016690743,0.00008478799,0.00032735764,0.0038944017,0.000010538874],"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":[0.013057623,0.00017902874,7.811785e-7,0.8340548,0.0068499106,0.00009561571,0.000011916457,2.8671563e-8,6.6108607e-9,0.027784396,0.00713951,0.11082637],"study_design_scores_gemma":[0.04119019,0.00045446868,2.9260997e-7,0.5339638,0.053703252,0.00023304381,0.000011537828,0.0000129320415,2.0193646e-8,0.30265218,0.06750135,0.0002769122],"about_ca_topic_score_codex":0.0000018249542,"about_ca_topic_score_gemma":4.6093328e-7,"teacher_disagreement_score":0.4214525,"about_ca_system_score_codex":0.00006848696,"about_ca_system_score_gemma":0.00064286886,"threshold_uncertainty_score":0.9997102},"labels":[],"label_agreement":null},{"id":"W3035764452","doi":"10.1016/j.jclinepi.2020.06.013","title":"Systematic scoping review identifies heterogeneity in outcomes measured in adolescent depression clinical trials","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","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 Toronto; Centre for Addiction and Mental Health; SickKids Foundation; Institute for Clinical Evaluative Sciences; Hospital for Sick Children","funders":"","keywords":"Depression (economics); Medicine; Clinical trial; MEDLINE; Gerontology; Internal medicine; Biology","score_opus":0.6620696836874698,"score_gpt":0.6103483430394249,"score_spread":0.0517213406480449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035764452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.662888,0.20769417,0.0028906777,0.10343346,0.018726347,0.00394461,0.000011528957,0.000044210232,0.00036702293],"genre_scores_gemma":[0.886411,0.054241296,0.00043079405,0.0570829,0.0017466411,0.00002383873,0.0000061174637,0.000022847931,0.000034531404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93268883,0.043569796,0.022344694,0.00056416227,0.00037856173,0.0004539787],"domain_scores_gemma":[0.960037,0.031915,0.007098994,0.00027719536,0.00017165749,0.00050017814],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12522359,0.0002573999,0.008220068,0.00012235594,0.000035347723,0.000009548624,0.00046187345,0.00045951002,0.00020808363],"category_scores_gemma":[0.21123216,0.00016534593,0.0019500637,0.0002279366,0.00012770214,0.00008758221,0.00009287193,0.0014444469,0.0001423192],"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":[0.00052766385,0.0007344952,0.9721201,0.017036231,0.00022232588,0.00007793371,0.00007668208,0.000012593719,0.0000020561772,0.00013167289,0.005636045,0.003422174],"study_design_scores_gemma":[0.0025386084,0.00013460222,0.8149549,0.18142474,0.0000929116,0.000019157702,0.000040680476,0.000011930221,6.589269e-7,0.0005499767,0.00009760497,0.00013425996],"about_ca_topic_score_codex":0.000008937297,"about_ca_topic_score_gemma":0.00005348974,"teacher_disagreement_score":0.22352307,"about_ca_system_score_codex":0.000039951006,"about_ca_system_score_gemma":0.00022330844,"threshold_uncertainty_score":0.90076643},"labels":[],"label_agreement":null},{"id":"W3036085357","doi":"10.1016/j.jclinepi.2020.06.023","title":"PRECIS-2 for retrospective assessment of RCTs in systematic reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pain Management and Placebo Effect","field":"Neuroscience","cited_by":39,"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; University of Toronto; St. Michael's Hospital; Western University; Centre for Family Medicine","funders":"","keywords":"Randomized controlled trial; Blinding; Medicine; Systematic review; Psychological intervention; Consolidated Standards of Reporting Trials; Alternative medicine; MEDLINE; Family medicine; Nursing; Surgery","score_opus":0.603272032124381,"score_gpt":0.5806354462849824,"score_spread":0.022636585839398538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036085357","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":[0.2117041,0.003441801,0.71063733,0.048437905,0.0054638167,0.012255935,0.000027755725,0.000043726715,0.00798763],"genre_scores_gemma":[0.98258984,0.0019106156,0.0077844346,0.0072067888,0.00041454847,0.000033903547,3.8575885e-7,0.000009470099,0.00005002224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94593,0.045592483,0.00759254,0.00035757493,0.00022636658,0.00030105826],"domain_scores_gemma":[0.76614535,0.22691393,0.006447731,0.00021366078,0.0000964471,0.0001828913],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13016623,0.00012928723,0.0039598155,0.00008531666,0.000018610754,0.0000041009857,0.00042011146,0.00014021187,0.00002528059],"category_scores_gemma":[0.68200284,0.00008209269,0.0007657156,0.00021810345,0.000104700426,0.00009980009,0.000056380355,0.00057375437,0.000008743068],"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":[0.0011940481,0.00052622834,0.8988051,0.027073937,0.00014327107,0.00006293317,0.00020386447,0.0009783742,0.0025178082,0.036651865,0.027299952,0.00454264],"study_design_scores_gemma":[0.009769165,0.013447184,0.6290708,0.014263375,0.00062409934,0.00004861084,0.000080315156,0.2438704,0.00056722807,0.06567503,0.021911155,0.0006726061],"about_ca_topic_score_codex":0.0000011706732,"about_ca_topic_score_gemma":0.0000016753311,"teacher_disagreement_score":0.7708857,"about_ca_system_score_codex":0.00003538473,"about_ca_system_score_gemma":0.000071852744,"threshold_uncertainty_score":0.8956769},"labels":[],"label_agreement":null},{"id":"W3037186027","doi":"10.1016/j.jclinepi.2020.06.028","title":"Social media can have an impact on how we manage and investigate the COVID-19 pandemic","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":205,"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; Impact; McMaster University","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Social media; Betacoronavirus; Medicine; Virology; Computer science; World Wide Web; Outbreak; Pathology; Disease","score_opus":0.8207876949093603,"score_gpt":0.6465048583167491,"score_spread":0.17428283659261123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037186027","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":[0.47176737,0.00021140756,0.00004616221,0.52600354,0.0017008854,0.00018862692,0.0000046119294,0.00001445762,0.000062931365],"genre_scores_gemma":[0.9156111,0.0033292365,0.0002908132,0.06796384,0.012771498,0.000013024387,0.0000022174893,0.000011817618,0.0000064881297],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98027015,0.01699279,0.0016755761,0.0002575637,0.00034270488,0.00046124286],"domain_scores_gemma":[0.77308613,0.2203338,0.003299534,0.00017002362,0.00020926955,0.0029012254],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034581102,0.00014505716,0.0012523397,0.000060656803,0.00051666977,0.0000276764,0.0004922983,0.00049865013,0.00005586523],"category_scores_gemma":[0.54123396,0.000089912006,0.0003152079,0.00020238543,0.0019421282,0.00013688319,0.000040996958,0.001492695,0.0000052862897],"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":[0.00025750077,0.000046852176,0.86751485,0.000022342621,0.000056934343,0.000012091773,0.0653713,0.00002336897,0.000001381955,0.008108104,0.026037404,0.032547854],"study_design_scores_gemma":[0.0009060209,0.0009309201,0.72405773,0.00002058367,0.00008444726,0.000013909666,0.012027337,0.00014858283,2.2737919e-7,0.093992084,0.1676571,0.00016104979],"about_ca_topic_score_codex":0.00126154,"about_ca_topic_score_gemma":0.0027464726,"teacher_disagreement_score":0.50665283,"about_ca_system_score_codex":0.00022156723,"about_ca_system_score_gemma":0.0019219314,"threshold_uncertainty_score":0.99410194},"labels":[],"label_agreement":null},{"id":"W3037616222","doi":"10.1016/j.jclinepi.2020.06.027","title":"Few evaluative studies exist examining rapid review methodology across stages of conduct: a systematic scoping review","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Grey literature; Systematic review; Critical appraisal; Context (archaeology); Protocol (science); MEDLINE; Medicine; Psychology; Computer science; Management science; Applied psychology; Alternative medicine; Pathology; Engineering","score_opus":0.9936317159314613,"score_gpt":0.8732081211453524,"score_spread":0.12042359478610887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037616222","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":[0.015969343,0.6779898,0.005350927,0.29225785,0.0025808327,0.00556844,0.00004300877,0.000028036033,0.00021180799],"genre_scores_gemma":[0.004938216,0.58898133,0.0265666,0.37861842,0.0007004503,0.00014307756,0.0000014469281,0.000018698689,0.000031750667],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.71964335,0.24383889,0.033902995,0.000641393,0.00076725194,0.0012061095],"domain_scores_gemma":[0.2208247,0.7294433,0.043832414,0.00072192383,0.0040696794,0.0011079803],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38523462,0.00027384612,0.012043117,0.000081755934,0.00030737245,0.0000018717909,0.00073766895,0.00028076262,0.00053250405],"category_scores_gemma":[0.8946265,0.00017653118,0.00058972964,0.0006196844,0.0008164763,0.00022771054,0.00036495156,0.0019810428,0.00009474583],"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":[0.00008476877,0.000026119927,0.017591238,0.9335897,0.00036424937,0.000013737783,0.006756829,0.000004949451,0.000019614215,0.000640527,0.037822947,0.0030853178],"study_design_scores_gemma":[0.0017383775,0.0021732068,0.005604665,0.9786455,0.000616235,0.000046098554,0.007670624,0.000019519037,0.0000048250085,0.0012091093,0.0020679315,0.00020388521],"about_ca_topic_score_codex":0.000015168894,"about_ca_topic_score_gemma":0.000017971422,"teacher_disagreement_score":0.5093919,"about_ca_system_score_codex":0.000113836606,"about_ca_system_score_gemma":0.0026725633,"threshold_uncertainty_score":0.8606756},"labels":[],"label_agreement":null},{"id":"W3039041742","doi":"10.1016/j.jclinepi.2020.06.029","title":"Rapid review methods more challenging during COVID-19: commentary with a focus on 8 knowledge synthesis steps","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Disaster Response and Management","field":"Health Professions","cited_by":122,"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; Wilfrid Laurier University; Bruyère; University of Manitoba; Canadian Agency for Drugs and Technologies in Health; St. Michael's Hospital; Sunnybrook Health Science Centre; University of Ottawa; University of Calgary; George & Fay Yee Centre for Healthcare Innovation; Impact; Health Sciences Centre; Ottawa Hospital; McMaster University Medical Centre; Cochrane; University of Toronto; McMaster University; Canada Research Chairs; Queen's University","funders":"World Health Organization","keywords":"Coronavirus disease 2019 (COVID-19); Focus (optics); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Computer science; Virology; Psychology; Pathology; Physics; Infectious disease (medical specialty)","score_opus":0.67112702438043,"score_gpt":0.6831310116647211,"score_spread":0.012003987284291084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039041742","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":[0.000001635069,0.8936936,0.004461876,0.09617484,0.001356223,0.001860485,0.000026337326,0.000043639488,0.0023813292],"genre_scores_gemma":[0.0000013894139,0.91874486,0.006478012,0.0719653,0.002149446,0.00030063768,0.0000090812,0.00010293574,0.00024835338],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8842009,0.10209068,0.011789257,0.00076126365,0.00028245142,0.0008754881],"domain_scores_gemma":[0.7590851,0.22548164,0.012683837,0.0009386796,0.00017682274,0.0016338866],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080178544,0.0007855729,0.017624624,0.00042969018,0.00043723008,0.000005036187,0.0011908798,0.00093604124,0.000805737],"category_scores_gemma":[0.13000181,0.0004598471,0.002985003,0.00040290045,0.0002555137,0.000089917856,0.00065711985,0.0060840845,0.00025090412],"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":[0.0005746492,0.00021141638,0.00004905754,0.11397231,0.0016869495,0.00036364648,0.00020879619,0.000001382594,3.8034758e-9,0.0005586546,0.0854225,0.79695064],"study_design_scores_gemma":[0.0008314486,0.00076536817,0.000038997474,0.15906258,0.0033975886,0.00010137202,0.00031971035,0.000005675087,1.0474928e-8,0.0002607113,0.8349033,0.00031324208],"about_ca_topic_score_codex":0.000017321476,"about_ca_topic_score_gemma":0.000008749974,"teacher_disagreement_score":0.79663736,"about_ca_system_score_codex":0.0005204963,"about_ca_system_score_gemma":0.0018748959,"threshold_uncertainty_score":0.9997853},"labels":[],"label_agreement":null},{"id":"W3039419960","doi":"10.1016/j.jclinepi.2020.06.032","title":"Open synthesis and the coronavirus pandemic in 2020","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Biomedical and Engineering Education","field":"Engineering","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 Ottawa; Bruyère; McMaster University; Impact","funders":"","keywords":"Pandemic; Globe; Coronavirus disease 2019 (COVID-19); Coronavirus; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Population; Economic growth; Humanity; Development economics; Global health; Public health; Political science; Geography; Socioeconomics; Environmental health; Medicine; Virology; Disease; Health care; Economics; Infectious disease (medical specialty); Outbreak; Nursing","score_opus":0.40115545310524786,"score_gpt":0.5260158993419257,"score_spread":0.12486044623667786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039419960","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":[0.000022006081,0.9950784,0.00043517747,0.0022178362,0.0018510151,0.00020252651,0.000005625914,0.000014519184,0.00017288886],"genre_scores_gemma":[0.00014305225,0.9974064,0.0008213741,0.00037462948,0.0011867922,0.000024645009,0.0000021698954,0.000026894186,0.000014045158],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99285483,0.0023741012,0.004287819,0.00018371476,0.00008153059,0.00021798298],"domain_scores_gemma":[0.94632673,0.052239724,0.0009850117,0.00017517291,0.000021314663,0.00025205326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016606096,0.00022787438,0.006062717,0.00006318512,0.000014095908,0.000013204317,0.0008303297,0.0006363951,0.000045409277],"category_scores_gemma":[0.038941957,0.00011790231,0.00057735795,0.00018310106,0.00025244453,0.000057984907,0.00016382357,0.0021726582,0.000023816152],"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":[0.000025624642,0.000012596108,0.00017721875,0.0021631606,0.00017444695,0.000014752943,0.000011226469,0.000030387024,6.715493e-9,0.00022860352,0.0036293834,0.9935326],"study_design_scores_gemma":[0.00042270764,0.000042303214,0.0007422732,0.0035196757,0.0002813281,0.00022325349,0.0000044049116,0.00087404624,5.531429e-9,0.0012451254,0.9925289,0.000115979696],"about_ca_topic_score_codex":0.000015309957,"about_ca_topic_score_gemma":0.000005003316,"teacher_disagreement_score":0.9934166,"about_ca_system_score_codex":0.000050834737,"about_ca_system_score_gemma":0.00018670807,"threshold_uncertainty_score":0.96915346},"labels":[],"label_agreement":null},{"id":"W3040345322","doi":"10.1016/j.jclinepi.2020.06.040","title":"Assessing concordance of financial conflicts of interest disclosures with payments’ databases: a systematic survey of the health literature","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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":"McMaster University; Impact","funders":"American University of Beirut","keywords":"Concordance; Conflict of interest; Payment; MEDLINE; Systematic review; Medicine; Database; Actuarial science; Accounting; Meta-analysis; Family medicine; Finance; Business; Political science; Internal medicine; Computer science","score_opus":0.9216621055580043,"score_gpt":0.7231068243185425,"score_spread":0.19855528123946187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040345322","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":[0.003808885,0.9885315,0.00024812287,0.0020855532,0.002649957,0.0012465086,0.0013874532,0.000005800965,0.00003622276],"genre_scores_gemma":[0.034121614,0.961014,0.00038534036,0.0037114483,0.00062531297,0.000015595939,0.00007034862,0.000035219295,0.000021140215],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9148011,0.06956796,0.014292494,0.0004625242,0.0002968156,0.0005791057],"domain_scores_gemma":[0.8902945,0.078965336,0.028458904,0.00054950424,0.0009770973,0.00075466995],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.047669794,0.0005418904,0.01489227,0.00014085032,0.00010257927,0.000007572324,0.0012936157,0.0015386819,0.00006454117],"category_scores_gemma":[0.092522226,0.00028023333,0.0015047488,0.00071027124,0.0015235437,0.0001651474,0.00029463373,0.009120368,0.000002165501],"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":[0.0030631088,0.0016390721,0.11260457,0.6871409,0.0038514098,0.000173248,0.0004193754,0.00003756398,0.000004299672,0.0049156826,0.005639204,0.18051155],"study_design_scores_gemma":[0.0036967285,0.004175537,0.030325733,0.41129723,0.004847092,0.0007172641,0.000097243596,0.000151978,0.000026755346,0.00030737923,0.54377925,0.0005777901],"about_ca_topic_score_codex":0.000075078926,"about_ca_topic_score_gemma":0.000094712545,"teacher_disagreement_score":0.53814006,"about_ca_system_score_codex":0.00008488283,"about_ca_system_score_gemma":0.0044436455,"threshold_uncertainty_score":0.999965},"labels":[],"label_agreement":null},{"id":"W3040346338","doi":"10.1016/j.jclinepi.2020.06.024","title":"External validation demonstrated the Ottawa SAH prediction models can identify pSAH using health administrative data","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Intracranial Aneurysms: Treatment and Complications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hamilton Health Sciences; McMaster University; University of British Columbia; Health Sciences Centre; Centre hospitalier de l'Université Laval; Université Laval; Manitoba Health; University of Ottawa; Centre Hospitalier de l’Université de Montréal; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Medicine; Logistic regression; Predictive value; Internal medicine","score_opus":0.6159851394050244,"score_gpt":0.5493395171656862,"score_spread":0.06664562223933823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040346338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5933927,0.0006954478,0.19865975,0.20560914,0.00075221696,0.0004926855,0.00016295865,0.000030434076,0.00020463741],"genre_scores_gemma":[0.9753682,0.000489796,0.012403386,0.009711938,0.0018656953,0.0000025955705,0.00011436733,0.000012796844,0.000031213556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931959,0.0025342114,0.0034836344,0.00032304283,0.00020551814,0.00025768948],"domain_scores_gemma":[0.9920165,0.00411069,0.002665881,0.0004104826,0.00033981583,0.00045665549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067951134,0.0001540363,0.0012200421,0.00004429891,0.00017482258,0.000014779423,0.0003794293,0.00017909237,0.00006750034],"category_scores_gemma":[0.008319284,0.00009455143,0.00029128572,0.00017535489,0.00022660996,0.00022044586,0.000066337,0.0009450825,0.000009103231],"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":[0.005259588,0.0025284875,0.8231827,0.0002103341,0.0024247395,0.00033303018,0.001178068,0.010841818,0.0018133504,0.020414488,0.04376847,0.08804495],"study_design_scores_gemma":[0.004840466,0.0070245136,0.49506444,0.00035382324,0.001247312,0.0035032441,0.00045467235,0.45304465,0.00007258685,0.031243693,0.002912729,0.00023787012],"about_ca_topic_score_codex":0.00009671399,"about_ca_topic_score_gemma":0.00002416883,"teacher_disagreement_score":0.44220284,"about_ca_system_score_codex":0.000058437454,"about_ca_system_score_gemma":0.0009550636,"threshold_uncertainty_score":0.9959561},"labels":[],"label_agreement":null},{"id":"W3040674444","doi":"10.1016/j.jclinepi.2020.06.034","title":"Is it always possible to complete a systematic review in 2 weeks? Further thoughts and considerations","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Systematic review; Medicine; MEDLINE; Political science","score_opus":0.957996256029118,"score_gpt":0.7099015670895068,"score_spread":0.24809468893961117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040674444","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":[0.0000018297695,0.9366024,0.0032899778,0.055942472,0.0006835624,0.0028387737,0.00004560218,0.0000019016668,0.0005934525],"genre_scores_gemma":[0.000008935957,0.9500297,0.011447787,0.037028052,0.00059509673,0.00006980514,0.0000029561945,0.000026464551,0.0007912371],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5017119,0.32595813,0.16638878,0.0020190014,0.0032796226,0.00064255367],"domain_scores_gemma":[0.2423632,0.6203525,0.12769736,0.005288283,0.00263776,0.0016608654],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.59147173,0.00079028466,0.10026003,0.0007510731,0.00008321364,0.0002311462,0.00233721,0.0006583966,0.0039606374],"category_scores_gemma":[0.84992945,0.0003240615,0.013783052,0.0016054574,0.00018618653,0.00017774061,0.00035214712,0.0018689105,0.00385582],"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":[0.00000700447,0.00009006442,0.00043020575,0.412411,0.0018964421,0.00017346145,0.00019418832,0.0000039459815,1.1104045e-8,0.0018531262,0.52366793,0.05927261],"study_design_scores_gemma":[0.00014198296,0.00019028177,0.00004728018,0.23990753,0.0046224254,0.0006969393,0.000040244562,0.00012712154,1.4940807e-9,0.012490159,0.7415197,0.00021634756],"about_ca_topic_score_codex":0.0000037053162,"about_ca_topic_score_gemma":0.000031204094,"teacher_disagreement_score":0.2943944,"about_ca_system_score_codex":0.000057407302,"about_ca_system_score_gemma":0.00079209916,"threshold_uncertainty_score":0.99992114},"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":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3040816027","doi":"10.1016/j.jclinepi.2020.07.002","title":"Evidence-based medicine in times of crisis","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare cost, quality, practices","field":"Health Professions","cited_by":38,"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; MEDLINE; Political science; Law","score_opus":0.956033202650429,"score_gpt":0.742951585242856,"score_spread":0.21308161740757303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040816027","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":[0.19481595,0.00408205,0.001986066,0.79636246,0.0016197404,0.00026490443,0.0000035903997,0.0000127442345,0.00085247715],"genre_scores_gemma":[0.7646878,0.0040017064,0.0046798135,0.22419833,0.0023864731,0.000004708726,9.605656e-7,0.000014137662,0.000026084463],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9072475,0.076406665,0.01500233,0.00034538368,0.00042058996,0.0005775238],"domain_scores_gemma":[0.5855325,0.3994928,0.01259142,0.0003900412,0.0010697375,0.00092349236],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1396044,0.00016577661,0.0040189014,0.00018344996,0.0000734396,7.3003e-7,0.00054516655,0.00073350745,0.0027696176],"category_scores_gemma":[0.7206113,0.000110812165,0.0004039784,0.00038735312,0.00043190925,0.000271956,0.0001063059,0.0041880123,0.000109744564],"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":[0.0017317297,0.00010923078,0.905986,0.00058931194,0.000049569117,0.000039825994,0.00074473256,0.00006818648,0.000015648176,0.0030159482,0.081390284,0.006259551],"study_design_scores_gemma":[0.0041200104,0.005173412,0.9082243,0.0045306436,0.00013258422,0.0000074299824,0.0030832284,0.0014164385,0.000008142099,0.019369666,0.053760875,0.00017327594],"about_ca_topic_score_codex":0.00087843335,"about_ca_topic_score_gemma":0.00010666536,"teacher_disagreement_score":0.5810069,"about_ca_system_score_codex":0.0000762924,"about_ca_system_score_gemma":0.0020758847,"threshold_uncertainty_score":0.998142},"labels":[],"label_agreement":null},{"id":"W3043456460","doi":"10.1016/j.jclinepi.2020.07.010","title":"Different meanings of equipoise and the four quadrants of uncertainty","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Clinical equipoise; Medicine; Medical physics; Clinical trial; Internal medicine","score_opus":0.7796509454157181,"score_gpt":0.5642552751964578,"score_spread":0.21539567021926032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043456460","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":[0.03603407,0.0044230027,0.00230001,0.9542696,0.0020649936,0.00038688502,0.0001638937,0.000004907533,0.00035266814],"genre_scores_gemma":[0.10673958,0.0044265673,0.0015370077,0.88124245,0.00584021,0.000009671494,0.000014978489,0.00004182866,0.000147703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.945958,0.014309514,0.038466528,0.0005803457,0.0001889776,0.0004965871],"domain_scores_gemma":[0.7700743,0.15629895,0.07246577,0.0006068559,0.0002929919,0.00026111503],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13483141,0.0003253095,0.012136277,0.00025860683,0.00005869208,0.000009443259,0.00083187525,0.0010835163,0.00019508695],"category_scores_gemma":[0.3267163,0.00023489252,0.0015399936,0.00009671791,0.001146846,0.000111604364,0.00016581835,0.0029926498,0.000044306857],"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":[0.0004897972,0.00006418789,0.07069648,0.0012767187,0.00089740317,0.000015207684,0.00045758163,0.00012545723,2.1273775e-7,0.026911898,0.8986616,0.00040342385],"study_design_scores_gemma":[0.007667475,0.0014194811,0.05970476,0.00095942226,0.00026530403,0.00009178419,0.0002219063,0.007274524,4.964518e-7,0.45269334,0.46921295,0.0004885387],"about_ca_topic_score_codex":0.0003978593,"about_ca_topic_score_gemma":0.00002224044,"teacher_disagreement_score":0.42944866,"about_ca_system_score_codex":0.00010469514,"about_ca_system_score_gemma":0.00030035613,"threshold_uncertainty_score":0.9993075},"labels":[],"label_agreement":null},{"id":"W3043698465","doi":"10.1016/j.jclinepi.2020.07.006","title":"Replication Research Series-Paper 1 : A concept analysis and meta-narrative review established a comprehensive theoretical definition of replication research to improve its use","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Canada Research Chairs; Ottawa Hospital; University of Ottawa; University of Toronto; Dalhousie University; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Replication (statistics); Series (stratigraphy); Meta-analysis; Narrative review; Computer science; Narrative; Psychology; Biology; Medicine; Philosophy; Linguistics; Psychotherapist; Virology; Pathology","score_opus":0.9643020589119686,"score_gpt":0.7416468744429461,"score_spread":0.22265518446902255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043698465","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011194915,0.9656239,0.0045181233,0.025140796,0.00019038981,0.0038612946,0.00018443605,0.0000038706075,0.00036521736],"genre_scores_gemma":[0.00023989688,0.97724026,0.01906098,0.0022660254,0.00037100137,0.00033693438,0.00007592722,0.00003393075,0.00037501755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30768698,0.58040345,0.09670723,0.0051706303,0.009021757,0.0010099337],"domain_scores_gemma":[0.110414185,0.74080455,0.08110502,0.015769454,0.049946,0.0019607833],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7392755,0.00075132126,0.061722267,0.0023290438,0.0002495772,0.00031180866,0.0037734527,0.0010552311,0.0038411035],"category_scores_gemma":[0.94964343,0.000343242,0.016424427,0.011154972,0.001818487,0.00074515725,0.0009547214,0.0043409867,0.0003198269],"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":[0.00035183577,0.00035016926,0.00032018218,0.012355185,0.037555244,0.0000494136,0.00051874365,0.000009875766,0.000005540602,0.17076287,0.18418427,0.5935367],"study_design_scores_gemma":[0.0001706443,0.0012566661,0.00054525817,0.0027927537,0.039701376,0.00011447681,0.00018214493,0.00010737467,6.0549496e-7,0.033503033,0.9213765,0.0002491648],"about_ca_topic_score_codex":0.000021946958,"about_ca_topic_score_gemma":0.000012511073,"teacher_disagreement_score":0.7371922,"about_ca_system_score_codex":0.00013584463,"about_ca_system_score_gemma":0.0012212059,"threshold_uncertainty_score":0.99990195},"labels":[],"label_agreement":null},{"id":"W3044113370","doi":"10.1016/j.jclinepi.2020.07.012","title":"Over half of the WHO guidelines published from 2014 to 2019 explicitly considered health equity issues: a cross-sectional survey","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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; Ottawa Hospital; Impact; Bruyère; University of Ottawa","funders":"","keywords":"Disadvantaged; Equity (law); Health equity; Psychology; Evidence-based medicine; Social determinants of health; Medicine; MEDLINE; Public health; Environmental health; Family medicine; Political science; Nursing; Economics; Economic growth","score_opus":0.8970521750018086,"score_gpt":0.6736515440681483,"score_spread":0.22340063093366025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044113370","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":[0.44604665,0.0037366964,0.0078374,0.5373365,0.0035035263,0.00040604174,0.0009574251,0.0000112506705,0.00016450149],"genre_scores_gemma":[0.50745386,0.0013318592,0.01269641,0.47213182,0.0058992514,0.000012352045,0.00005064587,0.000048807895,0.00037496473],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95122397,0.010925697,0.0362086,0.00079992233,0.00024384267,0.00059798924],"domain_scores_gemma":[0.89962834,0.06553948,0.031679627,0.00091122574,0.0011352461,0.0011061067],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22472711,0.0002324452,0.005400963,0.00015798098,0.00013140123,0.000054137305,0.0010210149,0.00045773466,0.0013923356],"category_scores_gemma":[0.5639144,0.0001970699,0.000892502,0.00023542171,0.0002779852,0.00042729554,0.0003403934,0.00089993747,0.00043463294],"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":[0.00011681157,0.000043575183,0.58326817,0.000033286353,0.000101638856,2.5932434e-7,0.00011368708,0.00082354835,5.2898116e-7,0.005159261,0.41026774,0.000071511],"study_design_scores_gemma":[0.0011587214,0.00037488693,0.89173406,0.00006422892,0.0000043855925,0.0000044720973,0.00004008951,0.0027181196,5.6544076e-7,0.029262869,0.074495524,0.00014204708],"about_ca_topic_score_codex":0.011996822,"about_ca_topic_score_gemma":0.00091875077,"teacher_disagreement_score":0.33918732,"about_ca_system_score_codex":0.00022853023,"about_ca_system_score_gemma":0.0012546311,"threshold_uncertainty_score":0.99952054},"labels":[],"label_agreement":null},{"id":"W3044702960","doi":"10.1016/j.jclinepi.2020.07.013","title":"Citation impact was highly variable for reporting guidelines of health research: a citation analysis","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","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":"Institute of Health Economics; University of Ottawa; Ottawa Hospital","funders":"Cancer Research UK","keywords":"Citation; Impact factor; Publishing; Citation analysis; Medicine; Guideline; Bibliometrics; Citation impact; Web of science; MEDLINE; Library science; Meta-analysis; Computer science; Political science; Internal medicine; Pathology","score_opus":0.9883880526495334,"score_gpt":0.8212683432552055,"score_spread":0.16711970939432796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044702960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34539166,0.0012654263,0.5673429,0.084982425,0.00058711256,0.00023991086,0.00002875163,0.000004986847,0.00015683565],"genre_scores_gemma":[0.8487971,0.00072910805,0.14736924,0.0022131247,0.0007797178,0.0000033306703,0.000008318348,0.000008682234,0.000091401635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.83756566,0.047815293,0.093025,0.0021560348,0.016937248,0.0025007885],"domain_scores_gemma":[0.091177784,0.7580022,0.07371744,0.0011226214,0.073594786,0.002385153],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.74660784,0.0001269041,0.003831485,0.030158538,0.00018268498,0.00015348614,0.0014473282,0.00027957305,0.00020545564],"category_scores_gemma":[0.9857547,0.00007515684,0.0018919818,0.1299754,0.0002874334,0.0004188049,0.00022807725,0.0008958499,0.000012765863],"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":[0.0004407853,0.00014509053,0.6705056,0.000027469656,0.000475904,0.0000052009277,0.00012702346,0.015619052,0.00012491747,0.0022853527,0.16987681,0.1403668],"study_design_scores_gemma":[0.00097551435,0.004649951,0.6756068,0.000032190248,0.000085406085,0.000008539611,0.00048389588,0.18537937,0.000016160238,0.117562644,0.015101338,0.00009821258],"about_ca_topic_score_codex":0.00023993294,"about_ca_topic_score_gemma":0.000008526804,"teacher_disagreement_score":0.74638784,"about_ca_system_score_codex":0.000099642886,"about_ca_system_score_gemma":0.0019919404,"threshold_uncertainty_score":0.98083377},"labels":[],"label_agreement":null},{"id":"W3044934574","doi":"10.1016/j.jclinepi.2020.07.011","title":"Describing deprescribing trials better: an elaboration of the CONSORT statement","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deprescribing; Consolidated Standards of Reporting Trials; Medicine; Clinical trial; Research design; Polypharmacy; Delphi method; Psychological intervention; Nursing; Computer science; Intensive care medicine","score_opus":0.9863202984269701,"score_gpt":0.7451602299940759,"score_spread":0.24116006843289417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044934574","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024420346,0.9620107,0.029524593,0.0036493347,0.003109094,0.0012341008,0.00005519518,0.0000018787772,0.00017094253],"genre_scores_gemma":[0.00023941888,0.97964543,0.016488567,0.0019234597,0.0015533641,0.00001294889,0.000008183979,0.000024705649,0.00010392731],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.14905179,0.6181464,0.22676446,0.0013216207,0.004273763,0.000441978],"domain_scores_gemma":[0.0730637,0.5519226,0.3651137,0.005096727,0.0039004819,0.00090277864],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.86154515,0.00059436675,0.07571697,0.0003976448,0.00010551693,0.00016088896,0.0047512734,0.00073597865,0.001881594],"category_scores_gemma":[0.94151914,0.00020030918,0.02606438,0.0012367177,0.00030526755,0.00030541566,0.00034772902,0.0019260169,0.00018560396],"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":[0.000019574196,0.000065262546,0.0054506254,0.0005965148,0.0014722886,0.000009282208,0.00003342245,0.000043446104,2.4402078e-7,0.0008776202,0.030493196,0.9609385],"study_design_scores_gemma":[0.00026844977,0.0002808901,0.0003200068,0.0035638276,0.0051377113,0.00006389764,0.00006853885,0.00034593182,2.2146237e-7,0.004869247,0.98492503,0.00015623719],"about_ca_topic_score_codex":0.0000056024746,"about_ca_topic_score_gemma":0.00000930368,"teacher_disagreement_score":0.9607823,"about_ca_system_score_codex":0.000065466586,"about_ca_system_score_gemma":0.0017792583,"threshold_uncertainty_score":0.9990308},"labels":[],"label_agreement":null},{"id":"W3047547227","doi":"10.1016/j.jclinepi.2020.06.031","title":"Effectiveness research: stable principles, dynamic methods","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Ottawa Hospital; Bruyère; University of Ottawa","funders":"Universiteit Maastricht; Ottawa Hospital Research Institute; University of Ottawa","keywords":"Medicine","score_opus":0.9484895998342344,"score_gpt":0.7269748109743435,"score_spread":0.22151478885989095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047547227","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":[0.23608822,0.010477285,0.43620872,0.30957216,0.0033147314,0.0007631607,0.00007098348,0.000037428792,0.0034673146],"genre_scores_gemma":[0.6037802,0.0031113094,0.32898524,0.060122956,0.003487372,0.0000412293,0.000011304936,0.000088907116,0.00037149797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8988689,0.068724826,0.030358693,0.00088732864,0.00018467288,0.00097556086],"domain_scores_gemma":[0.67783743,0.30169865,0.017939698,0.0006797766,0.00057584833,0.001268617],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58995533,0.00018201311,0.0054695066,0.00029433222,0.00014387284,0.000021933549,0.000735492,0.0004818681,0.0004008507],"category_scores_gemma":[0.64673626,0.00018140646,0.0007158888,0.00033793648,0.00036029017,0.00034769662,0.00017419831,0.0019011511,0.001016938],"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":[0.00073960214,0.00038282387,0.52015793,0.001257061,0.0006407519,0.000022365193,0.0006542514,0.003878011,0.000018603034,0.42300746,0.044207614,0.0050335047],"study_design_scores_gemma":[0.0019418565,0.001469679,0.38843971,0.0001835887,0.000016713664,0.00003145687,0.00028337556,0.034064043,0.000004938599,0.20154099,0.37175277,0.00027087066],"about_ca_topic_score_codex":0.00010525748,"about_ca_topic_score_gemma":0.000009559235,"teacher_disagreement_score":0.36769196,"about_ca_system_score_codex":0.00033560806,"about_ca_system_score_gemma":0.0005670406,"threshold_uncertainty_score":0.99976087},"labels":[],"label_agreement":null},{"id":"W3048211970","doi":"10.1016/j.jclinepi.2020.08.002","title":"Abbreviated and comprehensive literature searches led to identical or very similar effect estimates: a meta-epidemiological study","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Institute of Health Economics; University of Alberta","funders":"","keywords":"Interquartile range; Meta-analysis; Confidence interval; Medicine; Odds ratio; MEDLINE; Epidemiology; Statistics; Systematic review; Internal medicine; Mathematics; Biology","score_opus":0.9657825327774562,"score_gpt":0.7373159784020075,"score_spread":0.22846655437544872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048211970","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059164286,0.98380446,0.006010921,0.00456506,0.0012461068,0.003678452,0.000056721175,0.000011328486,0.000035331734],"genre_scores_gemma":[0.00014478016,0.973561,0.020205524,0.004390755,0.0012765676,0.00011584032,0.000014957355,0.000054581236,0.00023602172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.35168427,0.5268719,0.11291221,0.0033443097,0.004151956,0.001035326],"domain_scores_gemma":[0.11836913,0.81235003,0.059819687,0.0037207394,0.0031903957,0.0025500068],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.65717435,0.0022846272,0.18118617,0.0011588108,0.00017743459,0.0005645743,0.0049922173,0.0018434811,0.0028388405],"category_scores_gemma":[0.95434874,0.00070771464,0.043487135,0.0032226245,0.0005618383,0.00027348098,0.0013700783,0.005560776,0.0015128099],"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":[0.0007511529,0.00062727946,0.0113522485,0.0064770095,0.051405083,0.0026392918,0.00015866791,0.00007999734,9.162844e-8,0.00033451302,0.1296183,0.79655635],"study_design_scores_gemma":[0.0007525465,0.0062327664,0.002774846,0.004219295,0.03344564,0.0013661206,0.00006581525,0.00059915934,1.2755401e-8,0.002857459,0.9471851,0.00050121953],"about_ca_topic_score_codex":0.0000039070906,"about_ca_topic_score_gemma":0.000005131004,"teacher_disagreement_score":0.8175668,"about_ca_system_score_codex":0.0000732152,"about_ca_system_score_gemma":0.0006131437,"threshold_uncertainty_score":0.9995374},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"systematic_review","genre":"review","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":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3049553812","doi":"10.1016/j.jclinepi.2020.08.007","title":"Risk of bias assessment of test comparisons was uncommon in comparative accuracy systematic reviews: an overview of reviews","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Birmingham Biomedical Research Centre; National Institute for Health and Care Research; Amsterdam University Medical Centers","keywords":"Confidence interval; Publication bias; Test (biology); Medicine; Systematic review; Statistics; Meta-analysis; Index (typography); MEDLINE; Medical physics; Mathematics; Computer science; Pathology","score_opus":0.9865851928587221,"score_gpt":0.776050256368858,"score_spread":0.2105349364898641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049553812","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009237858,0.9892524,0.0037982685,0.0002604,0.00073594204,0.005364003,0.00012797509,0.0000015095309,0.00036714095],"genre_scores_gemma":[0.00055812165,0.9739243,0.02485002,0.00021822247,0.00025808768,0.00008914462,0.000017720926,0.000027146532,0.00005726093],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.19646989,0.54862905,0.2494812,0.0014129077,0.0035232408,0.00048369315],"domain_scores_gemma":[0.04596586,0.55904645,0.386421,0.0052382015,0.0027131354,0.00061537244],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7885139,0.0012467202,0.2172336,0.0011744164,0.000049446022,0.000050305203,0.005916705,0.00092159107,0.0010966819],"category_scores_gemma":[0.90993714,0.0005066344,0.034225248,0.003509508,0.00058090466,0.000341791,0.00049746945,0.003294335,0.00024625033],"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":[0.00003374351,0.0019771364,0.08228045,0.54855627,0.003822822,0.000030592728,0.0002559115,0.0001392695,2.4201958e-7,0.0024481749,0.055940997,0.30451438],"study_design_scores_gemma":[0.00038733555,0.0012499483,0.0037843443,0.20196739,0.010171321,0.00008005677,0.00012264114,0.0020800834,4.96791e-8,0.0013397879,0.77851194,0.00030507916],"about_ca_topic_score_codex":0.000041659714,"about_ca_topic_score_gemma":0.000103146536,"teacher_disagreement_score":0.72257096,"about_ca_system_score_codex":0.00012046032,"about_ca_system_score_gemma":0.0013126197,"threshold_uncertainty_score":0.9998165},"labels":[],"label_agreement":null},{"id":"W30533055","doi":"10.1016/s0895-4356(00)00268-7","title":"Multiple sclerosis in the Faroe Islands","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":204,"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":"Demography; Multiple sclerosis; Residence; Population; Quarter (Canadian coin); Asymptomatic; Transmission (telecommunications); Medicine; Geography; Epidemiology; Surgery; Internal medicine","score_opus":0.5769158465344985,"score_gpt":0.5387099203427769,"score_spread":0.038205926191721584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30533055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93404967,0.0011201646,0.0007844941,0.06071811,0.00051249244,0.00024093248,0.0000024264798,0.000008048486,0.002563674],"genre_scores_gemma":[0.9703237,0.016257282,0.0023860964,0.009404801,0.0014968764,0.000007834024,0.0000015977283,0.000010527788,0.0001112995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904092,0.004612086,0.0038410898,0.0002268343,0.00039282284,0.00051796],"domain_scores_gemma":[0.92708665,0.070447795,0.0013743306,0.0004360002,0.00034843737,0.00030678965],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03813998,0.00014751061,0.002198227,0.00017544352,0.00006298981,0.000005999786,0.00038685347,0.00024966683,0.00013211434],"category_scores_gemma":[0.23020783,0.000074221476,0.0007419069,0.0002976791,0.00043171353,0.000074344716,0.00008615156,0.001745986,0.000039386498],"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":[0.0010590683,0.00041229866,0.9439905,0.000014052794,0.00011192424,0.00011189253,0.00013939322,0.000021290974,0.000071699134,0.00007194528,0.016118297,0.037877597],"study_design_scores_gemma":[0.0042896457,0.0012115542,0.9559263,0.00015664003,0.00004033682,0.00024986506,0.00027574768,0.0008705102,0.0000034111742,0.0006178426,0.036297675,0.00006046925],"about_ca_topic_score_codex":0.0000560824,"about_ca_topic_score_gemma":0.00008089783,"teacher_disagreement_score":0.19206786,"about_ca_system_score_codex":0.000040809216,"about_ca_system_score_gemma":0.00014146758,"threshold_uncertainty_score":0.9904373},"labels":[],"label_agreement":null},{"id":"W3082162705","doi":"10.1016/j.jclinepi.2020.08.010","title":"Response to “Trials for depressive disorder in adolescents: the emperor's new clothes,” a letter to the editor by Alain Braillon, MD, PhD","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children; Centre for Addiction and Mental Health; SickKids Foundation; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Scopus; Clinical trial; Mental health; Medicine; Systematic review; Psychology; MEDLINE; Psychiatry; Psychotherapist; Internal medicine; Political science","score_opus":0.46700519008197255,"score_gpt":0.5879722394147078,"score_spread":0.12096704933273522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082162705","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":[0.00051072316,0.0009983795,0.014137875,0.97205746,0.009181438,0.0029416922,0.00010965926,0.00002776516,0.000035032353],"genre_scores_gemma":[0.0008106222,0.0007419202,0.001902531,0.85544384,0.13991928,0.00020029207,0.0000055732007,0.00006984059,0.00090611406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.87143046,0.11435018,0.009678892,0.0010705597,0.0016579493,0.001811984],"domain_scores_gemma":[0.6640102,0.32829404,0.0050462536,0.0009990565,0.00076176116,0.00088863674],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1817828,0.00044496142,0.0041771755,0.00029626244,0.0003632532,0.00010796012,0.004407184,0.0022234148,0.00011823579],"category_scores_gemma":[0.73742634,0.00023857754,0.0017741054,0.00061621366,0.0008990633,0.00013236562,0.0004949947,0.00820059,0.00010318482],"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":[0.003584336,0.000064764004,0.003496121,0.000021011061,0.00013402951,0.00008518934,0.00079749856,0.000022624336,0.000016757127,0.000026311101,0.98400706,0.0077443086],"study_design_scores_gemma":[0.0010155659,0.0008838915,0.00086126477,0.00042784307,0.00007039405,0.000005488791,0.00021312674,0.000007599617,0.0000029708183,0.005426836,0.9908292,0.00025581438],"about_ca_topic_score_codex":0.0011753722,"about_ca_topic_score_gemma":0.0010103692,"teacher_disagreement_score":0.55564356,"about_ca_system_score_codex":0.00024882331,"about_ca_system_score_gemma":0.0018123154,"threshold_uncertainty_score":0.9990719},"labels":[],"label_agreement":null},{"id":"W3087770431","doi":"10.1016/j.jclinepi.2020.09.018","title":"GRADE Guidelines 30: the GRADE approach to assessing the certainty of modeled evidence—An overview in the context of health decision-making","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":289,"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 Medical Centre; Hamilton Health Sciences; McMaster University; Impact; Toronto Public Health; Cochrane","funders":"Medical Research Council; National Institutes of Health; Liverpool John Moores University; Public Health Agency; National Institute of Environmental Health Sciences; University of Glasgow; National Institute for Health and Care Research; Universiteit van Amsterdam; American University of Beirut; Public Health Agency of Canada; World Health Organization; University of South Florida; U.S. Environmental Protection Agency; McMaster University; Universiteit Maastricht","keywords":"Certainty; Terminology; Context (archaeology); Multidisciplinary approach; Grading (engineering); Health care; Management science; Conceptual model; Systematic review; Computer science; Medicine; MEDLINE; Engineering; Mathematics","score_opus":0.9483288975400815,"score_gpt":0.6950848543071183,"score_spread":0.25324404323296323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087770431","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":[0.24468625,0.021301491,0.085770175,0.646883,0.000553462,0.0007089293,0.000022350763,0.0000043873915,0.00006994283],"genre_scores_gemma":[0.77887064,0.002861403,0.017260375,0.20033906,0.0006400902,0.000012610765,0.0000010919393,0.000013337538,0.0000013567037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.925452,0.030420406,0.042480707,0.00066710106,0.00033750857,0.0006422535],"domain_scores_gemma":[0.7812666,0.18858655,0.02840789,0.0009922709,0.00043434222,0.00031230508],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34989676,0.00019382249,0.0043973364,0.00014572273,0.00016106333,0.000028105072,0.0015245257,0.0002717909,0.00004090748],"category_scores_gemma":[0.39840987,0.00010968898,0.0006849018,0.00037830026,0.00028160436,0.00029740945,0.000119675744,0.0011839677,0.00001993327],"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":[0.0003141852,0.0007723708,0.33866856,0.0010039185,0.00037785273,0.000002559126,0.017041774,0.13825306,0.0000012609918,0.36922836,0.094727345,0.039608773],"study_design_scores_gemma":[0.0016335023,0.001371133,0.3156693,0.0019947386,0.00004703078,0.000047580783,0.017328346,0.42920473,3.3928833e-7,0.21279389,0.019596709,0.000312686],"about_ca_topic_score_codex":0.0008013492,"about_ca_topic_score_gemma":0.00007174517,"teacher_disagreement_score":0.53418446,"about_ca_system_score_codex":0.0001258884,"about_ca_system_score_gemma":0.0006376477,"threshold_uncertainty_score":0.6694181},"labels":[],"label_agreement":null},{"id":"W3088077495","doi":"10.1016/j.jclinepi.2020.07.019","title":"Evidence-Based Research Series-Paper 2 : Using an Evidence-Based Research approach before a new study is conducted to ensure value","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Academic Writing and Publishing","field":"Arts and Humanities","cited_by":98,"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; University of Ottawa; McMaster University","funders":"Høgskulen på Vestlandet; Parker Institute for Cancer Immunotherapy; Oak Foundation","keywords":"Series (stratigraphy); Value (mathematics); Research design; Evidence-based practice; Computer science; Medicine; Statistics; Alternative medicine; Mathematics; Machine learning","score_opus":0.9329052032033867,"score_gpt":0.60526344196989,"score_spread":0.32764176123349664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088077495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74732053,0.0022221247,0.001426907,0.24639387,0.0008913242,0.00089995866,0.000016815175,0.000060241615,0.0007681979],"genre_scores_gemma":[0.942348,0.00012754051,0.009992483,0.029074406,0.017685406,0.000014312794,0.0000049881637,0.00006210866,0.0006907495],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95206136,0.037953686,0.0055294256,0.0010857,0.0019600005,0.0014098119],"domain_scores_gemma":[0.91685355,0.0740548,0.0017440576,0.00078140106,0.004322974,0.0022432152],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15947443,0.00035220195,0.002585914,0.00058568525,0.0009013475,0.00037419627,0.0019249803,0.000657212,0.0014787978],"category_scores_gemma":[0.35529163,0.00025689937,0.0005533843,0.0007041986,0.0012909416,0.0024564017,0.00033179997,0.008196647,0.000039791455],"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":[0.012634513,0.0028224539,0.22274667,0.00052026164,0.0006566902,0.00036148433,0.07719609,0.010647358,0.00038979968,0.021978427,0.6209984,0.029047862],"study_design_scores_gemma":[0.013335385,0.10843352,0.04833702,0.012804167,0.0008593895,0.00019611992,0.11833543,0.123596095,0.000086043474,0.041823324,0.52983433,0.002359142],"about_ca_topic_score_codex":0.0018219416,"about_ca_topic_score_gemma":0.00013721785,"teacher_disagreement_score":0.21731947,"about_ca_system_score_codex":0.00016317368,"about_ca_system_score_gemma":0.0037921402,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"W3088518226","doi":"10.1016/j.jclinepi.2020.07.022","title":"Supporting effective participation in health guideline development groups: The Guideline Participant Tool","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact; Cochrane","funders":"","keywords":"Guideline; Grading (engineering); Medicine; Psychology; Knowledge translation; Medical education; Applied psychology; Family medicine; Computer science; Engineering; Knowledge management; Pathology","score_opus":0.6625583741484894,"score_gpt":0.6702799736686993,"score_spread":0.007721599520209899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088518226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50465864,0.00057727564,0.081836194,0.41124487,0.0007038715,0.0009270234,0.0000027419353,0.000022172506,0.000027215552],"genre_scores_gemma":[0.78587395,0.0002940993,0.0690068,0.1425687,0.0021591028,0.000026458194,0.000034809298,0.00002453842,0.000011557068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95030737,0.010009252,0.037602384,0.0005522333,0.0006106397,0.0009181105],"domain_scores_gemma":[0.8945792,0.08461573,0.017861448,0.0004950126,0.0013663059,0.0010823142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1291607,0.0002438581,0.0030155315,0.000096664364,0.000090118614,0.000009683573,0.00025597893,0.0002314873,0.00026777695],"category_scores_gemma":[0.5443256,0.00015034569,0.0005527906,0.00036136317,0.00017706928,0.00021019058,0.0001391999,0.0016877402,0.00005130469],"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":[0.003500769,0.0007676562,0.5008316,0.00012610097,0.0003727587,0.0001399957,0.0011224728,0.002629784,0.000071624665,0.0004763314,0.052066226,0.43789467],"study_design_scores_gemma":[0.008334069,0.005328964,0.6204636,0.00027132567,0.00033347023,0.0001766723,0.0011239436,0.03572453,0.000046009533,0.0021278341,0.32582754,0.00024206824],"about_ca_topic_score_codex":0.00010032836,"about_ca_topic_score_gemma":0.00010058545,"teacher_disagreement_score":0.4376526,"about_ca_system_score_codex":0.00015054201,"about_ca_system_score_gemma":0.0015670728,"threshold_uncertainty_score":0.8967123},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3088540353","doi":"10.1016/j.jclinepi.2020.08.018","title":"Methods for prospectively incorporating gender into health sciences research","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sex and Gender in Healthcare","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Alberta Health; University of Alberta; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; MEDLINE; Public health; Family medicine; Political science; Nursing","score_opus":0.9232436487303022,"score_gpt":0.7677352318022609,"score_spread":0.1555084169280413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088540353","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":[0.052153558,0.00945729,0.32960144,0.6054064,0.0015089655,0.0010635604,0.0000028784066,0.000026956119,0.00077896897],"genre_scores_gemma":[0.26298946,0.00038101987,0.6962274,0.037328776,0.0030354513,0.000009043912,0.0000011087828,0.000012386506,0.000015367386],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9790659,0.014624052,0.004851102,0.0005185796,0.00034433755,0.0005960522],"domain_scores_gemma":[0.90595824,0.088127375,0.0028839833,0.00022786036,0.0015311565,0.0012713948],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18618493,0.00011560897,0.0022900654,0.00014755377,0.0002861544,0.0000067968417,0.00027719405,0.00026755425,0.00002195162],"category_scores_gemma":[0.32145953,0.000076625794,0.00047405125,0.00045226215,0.00076164876,0.00007382455,0.00008756613,0.0018348953,0.0000058673236],"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":[0.0014299115,0.00016048973,0.5394387,0.0006598747,0.00015667199,0.000015618083,0.0014643552,0.000045195407,0.00008680461,0.024351327,0.0143295955,0.4178614],"study_design_scores_gemma":[0.0035028083,0.03192159,0.3040546,0.00022907868,0.000050706098,0.00029167955,0.0034293192,0.009843536,0.00008076787,0.5853518,0.061072286,0.00017183764],"about_ca_topic_score_codex":0.000048968683,"about_ca_topic_score_gemma":0.0000044885674,"teacher_disagreement_score":0.5680776,"about_ca_system_score_codex":0.00008738041,"about_ca_system_score_gemma":0.0025928975,"threshold_uncertainty_score":0.83799386},"labels":[],"label_agreement":null},{"id":"W3088642850","doi":"10.1016/j.jclinepi.2020.09.033","title":"Methodologically rigorous risk of bias tools for nonrandomized studies had low reliability and high evaluator burden","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":30,"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; Université de Montréal; University of Ottawa; Institute of Health Economics; St. Michael's Hospital; University of Manitoba; Centre Hospitalier de l’Université de Montréal; University of Toronto; George & Fay Yee Centre for Healthcare Innovation","funders":"","keywords":"Inter-rater reliability; Reliability (semiconductor); Medicine; Psychological intervention; Psychology; Physical therapy; Statistics; Mathematics; Psychiatry; Rating scale","score_opus":0.8644908462866121,"score_gpt":0.6267974750429381,"score_spread":0.23769337124367396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088642850","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":[0.851627,0.0019379483,0.09220515,0.052118048,0.0013186838,0.00072044524,0.000033755936,0.000008378008,0.000030613584],"genre_scores_gemma":[0.75040525,0.0055973292,0.23856825,0.0040881,0.0012848717,0.00001797531,8.572713e-7,0.000008997172,0.000028346114],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9162431,0.064301066,0.016478375,0.00097118696,0.0015318675,0.00047444247],"domain_scores_gemma":[0.15772684,0.823528,0.012990868,0.0007457848,0.0043988535,0.0006096778],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45571566,0.0002570131,0.006808425,0.00008502175,0.000117167736,0.000032635777,0.0009845854,0.0004024046,0.00019643028],"category_scores_gemma":[0.9642429,0.00012934404,0.0017763312,0.00025044483,0.0011299124,0.00025886073,0.00027165943,0.00089922623,0.000012073047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.054234277,0.0009717579,0.36623833,0.0002807779,0.0021735588,0.000016375723,0.0009995799,0.02002593,0.00043003025,0.0023038087,0.030974247,0.52135134],"study_design_scores_gemma":[0.02115833,0.011200879,0.18096627,0.00013945477,0.00078712037,0.000012324321,0.0010201712,0.008884717,0.00013386276,0.75783235,0.017572844,0.00029165862],"about_ca_topic_score_codex":0.000017205151,"about_ca_topic_score_gemma":0.000004412062,"teacher_disagreement_score":0.7592269,"about_ca_system_score_codex":0.000031946336,"about_ca_system_score_gemma":0.00023975883,"threshold_uncertainty_score":0.56045526},"labels":[],"label_agreement":null},{"id":"W3088741804","doi":"10.1016/j.jclinepi.2020.07.021","title":"Evidence-Based Research Series-Paper 3: Using an Evidence-Based Research approach to place your results into context after the study is performed to ensure usefulness of the conclusion","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":56,"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; Ottawa Hospital; University of Ottawa; McMaster University","funders":"Høgskulen på Vestlandet; Oak Foundation","keywords":"Series (stratigraphy); Context (archaeology); Medicine; Data science; Computer science; Psychology; Geography","score_opus":0.9850733829720696,"score_gpt":0.7136042393745555,"score_spread":0.27146914359751406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088741804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8228596,0.0013047522,0.0061736684,0.16650668,0.00046897138,0.0025914419,0.000011928055,0.0000023870261,0.000080610065],"genre_scores_gemma":[0.9713862,0.000069260124,0.007804332,0.01943991,0.00085831195,0.00007347375,4.5623727e-7,0.000022665528,0.00034540845],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.40647238,0.5256593,0.047163315,0.0027346485,0.016617255,0.001353043],"domain_scores_gemma":[0.37591368,0.5752675,0.017360859,0.008124452,0.021276869,0.002056633],"candidate_categories":["metaresearch","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.81611615,0.00043187648,0.008942266,0.0006365377,0.0007666978,0.0003276578,0.0077004456,0.0004433783,0.0011663632],"category_scores_gemma":[0.9079122,0.00015685563,0.0028352512,0.004822308,0.0011164593,0.0008050617,0.0014012678,0.0033321907,0.0001801397],"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":[0.04163746,0.0021993492,0.65537435,0.00035069403,0.0008417852,0.00006253891,0.02823752,0.03186085,0.00069087854,0.00023270569,0.1912837,0.047228172],"study_design_scores_gemma":[0.0063028606,0.02839558,0.6073304,0.0062901443,0.0011277416,0.000086103704,0.06459483,0.19552101,0.00037856732,0.003966429,0.08504409,0.0009622726],"about_ca_topic_score_codex":0.00023810455,"about_ca_topic_score_gemma":0.00017646166,"teacher_disagreement_score":0.16366017,"about_ca_system_score_codex":0.0001623766,"about_ca_system_score_gemma":0.0023536752,"threshold_uncertainty_score":0.9997467},"labels":[],"label_agreement":null},{"id":"W3089128767","doi":"10.1016/j.jclinepi.2020.07.020","title":"Evidence-Based Research Series-Paper 1: What Evidence-Based Research is and why is it important?","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":144,"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; McMaster University","funders":"Høgskulen på Vestlandet; Parker Institute for Cancer Immunotherapy; Oak Foundation","keywords":"Series (stratigraphy); Data science; Medicine; Computer science","score_opus":0.9904656403781177,"score_gpt":0.750457322862031,"score_spread":0.24000831751608664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089128767","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083973095,0.056198787,0.00480081,0.8531789,0.0008356388,0.00072550203,0.000007930413,0.0000039551023,0.000275363],"genre_scores_gemma":[0.49629956,0.092692755,0.024862936,0.37918758,0.0036423395,0.00004602893,0.0000018913346,0.000055857196,0.0032110554],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.4514455,0.43768364,0.08603643,0.003676084,0.019109206,0.0020491409],"domain_scores_gemma":[0.11007833,0.8384226,0.026459077,0.005079893,0.017107386,0.0028527228],"candidate_categories":["metaresearch","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.864399,0.00047147146,0.014119916,0.0009855635,0.00043220093,0.0010987772,0.0047460613,0.00077217276,0.03783873],"category_scores_gemma":[0.9381347,0.00022598018,0.0054090302,0.0035559959,0.0019097464,0.003088481,0.0005536936,0.0042705755,0.0015229961],"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":[0.0007530195,0.00007742447,0.19866253,0.00011216592,0.00022084356,0.00010064445,0.00025907482,0.00005389424,0.000055133256,0.00038089318,0.7796044,0.019720018],"study_design_scores_gemma":[0.0010364071,0.004833007,0.03283144,0.003868275,0.00031932828,0.00008097767,0.002044008,0.022048282,0.0000680157,0.041855115,0.8906433,0.00037183],"about_ca_topic_score_codex":0.000046409416,"about_ca_topic_score_gemma":0.000032227803,"teacher_disagreement_score":0.47399133,"about_ca_system_score_codex":0.00007784531,"about_ca_system_score_gemma":0.002110724,"threshold_uncertainty_score":0.9999382},"labels":[],"label_agreement":null},{"id":"W3089182593","doi":"10.1016/j.jclinepi.2019.11.020","title":"A practical guide for using a survey about attitudes and behaviors to inform health care decisions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"Hamilton Health Sciences; St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"National Institute for Health and Care Research; Wellcome Trust","keywords":"Health care; MEDLINE; Medicine; Psychology; Environmental health; Management science; Engineering; Political science","score_opus":0.8945188196243353,"score_gpt":0.7399092753993516,"score_spread":0.15460954422498374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089182593","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":[0.78294885,0.00079577643,0.12931623,0.08529798,0.0011836666,0.00035169328,0.000038429,0.000011782579,0.000055585373],"genre_scores_gemma":[0.3541241,0.0009130811,0.6042799,0.03946271,0.0011657795,0.0000050866274,0.000004098085,0.000014622327,0.000030680643],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.896848,0.09685354,0.004921586,0.00039524623,0.00029604757,0.0006855361],"domain_scores_gemma":[0.5845625,0.4121784,0.0015006543,0.00011170182,0.00059498777,0.0010517548],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28751075,0.00011494478,0.0017229824,0.000084096726,0.00041335047,0.000013639226,0.00025528946,0.00040675423,0.000035035555],"category_scores_gemma":[0.8940893,0.00009064066,0.0003374148,0.00025188204,0.0004935373,0.00015056618,0.00009208248,0.0006782742,0.0000049110317],"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":[0.0108701,0.00008522995,0.9428794,0.000014243402,0.00008060904,0.000015734106,0.0039875535,0.000042445776,0.0000043289874,0.0027481373,0.016808497,0.022463718],"study_design_scores_gemma":[0.00061873643,0.0014955096,0.9183393,0.000039675055,0.00003204716,0.000021296757,0.0012279717,0.000032738582,6.6040667e-7,0.00032021818,0.077781886,0.000089924884],"about_ca_topic_score_codex":0.0007859851,"about_ca_topic_score_gemma":0.0034793452,"teacher_disagreement_score":0.6065785,"about_ca_system_score_codex":0.00006350989,"about_ca_system_score_gemma":0.0023879565,"threshold_uncertainty_score":0.7336576},"labels":[],"label_agreement":null},{"id":"W3089986854","doi":"10.1016/j.jclinepi.2020.09.039","title":"Reply to letter to the editor “the NNTnet metric is not new, not easy to use, and not routinely applied in medical research”","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Scopus; Metric (unit); Number needed to treat; Medicine; Web of science; Information retrieval; MEDLINE; Family medicine; Medical physics; Actuarial science; Alternative medicine; Computer science; Meta-analysis; Marketing; Pathology; Political science; Business","score_opus":0.7834456706747306,"score_gpt":0.5865657730309721,"score_spread":0.19687989764375846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089986854","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":[0.0044926093,0.00026816814,0.0038756174,0.97885877,0.010611289,0.001447332,0.00023896193,0.00001365717,0.00019361345],"genre_scores_gemma":[0.0035194985,0.00042267836,0.004545245,0.8715824,0.11875704,0.00011372194,0.000011106747,0.00007589261,0.00097245304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93724424,0.020399533,0.03685252,0.002256971,0.0011978382,0.0020489134],"domain_scores_gemma":[0.6251839,0.35552716,0.013466646,0.0022815983,0.0006258191,0.002914896],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3065831,0.00050753844,0.0071880007,0.0015074507,0.0002359616,0.00014726949,0.0025084408,0.0017272349,0.0005140854],"category_scores_gemma":[0.64790106,0.00037805852,0.0007507261,0.00115728,0.0003770252,0.00022905903,0.0007991261,0.010535116,0.0035970886],"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":[0.0003964152,0.000030827854,0.012394875,0.00009120635,0.00016035416,0.000043955893,0.00048968813,0.000087257395,1.3333414e-7,0.0014503397,0.98359406,0.0012608727],"study_design_scores_gemma":[0.0008616779,0.0005874894,0.07197505,0.00016821937,0.000019536423,0.000027469712,0.000046049743,0.0003394525,3.7966146e-7,0.0022822483,0.92335886,0.0003335564],"about_ca_topic_score_codex":0.0027547916,"about_ca_topic_score_gemma":0.0002361076,"teacher_disagreement_score":0.34131798,"about_ca_system_score_codex":0.00053420925,"about_ca_system_score_gemma":0.0012197754,"threshold_uncertainty_score":0.99986714},"labels":[],"label_agreement":null},{"id":"W3090053916","doi":"10.1016/j.jclinepi.2020.09.035","title":"Prerandomization run-in periods in randomized controlled trials of chronic diseases: a methodological study","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Impact; McMaster University; Population Health Research Institute","funders":"Medical Research Council; Kidney Research UK","keywords":"Medicine; Randomized controlled trial; Randomization; Placebo; Epidemiology; Clinical trial; Internal medicine; Diabetes mellitus; Physical therapy; Alternative medicine; Pathology","score_opus":0.9354975320853159,"score_gpt":0.7636667749138659,"score_spread":0.17183075717145002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090053916","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005274207,0.8527902,0.1303963,0.00057191646,0.0033981667,0.012650947,0.00007589478,0.000017627066,0.0000462177],"genre_scores_gemma":[0.00004131401,0.72782624,0.26903155,0.00012648987,0.0024064532,0.00049293117,0.0000031993,0.000058768208,0.000013059025],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.0970511,0.7723615,0.12778154,0.0011742022,0.0008673416,0.0007643234],"domain_scores_gemma":[0.016890308,0.907364,0.07395164,0.0007474192,0.0004711506,0.0005754992],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.7640396,0.0010391249,0.24388911,0.00086252665,0.000028159395,0.000019164425,0.001361219,0.0024011317,0.0006360597],"category_scores_gemma":[0.99741733,0.00052004075,0.02730155,0.0007944478,0.0010913957,0.00008004332,0.00030812778,0.0048576347,0.000007583214],"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":[0.363821,0.0040325136,0.00043423593,0.007127185,0.0064994735,0.00030241258,0.000058322956,0.00004823094,3.8263952e-8,0.012260314,0.00028861975,0.6051277],"study_design_scores_gemma":[0.5177563,0.002771136,0.000058084843,0.011159747,0.017730681,0.000026806514,0.000026944725,0.0005845291,2.0456742e-8,0.44277212,0.0067810914,0.00033257564],"about_ca_topic_score_codex":0.000010886968,"about_ca_topic_score_gemma":0.000010256647,"teacher_disagreement_score":0.6047951,"about_ca_system_score_codex":0.00025987637,"about_ca_system_score_gemma":0.0025321555,"threshold_uncertainty_score":0.9997251},"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":"W3091320646","doi":"10.1016/j.jclinepi.2020.09.027","title":"Changing research culture toward more use of replication research: a narrative review of barriers and strategies","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Ottawa Hospital; University of Ottawa; University of Toronto; Dalhousie University; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Narrative review; Replication (statistics); Context (archaeology); Narrative; Promotion (chess); Psychology; Engineering ethics; Political science; Medicine; Politics; Psychotherapist; Engineering; Biology","score_opus":0.9878972800188794,"score_gpt":0.8000865119228544,"score_spread":0.18781076809602504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091320646","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004420173,0.98807055,0.0010494066,0.008825368,0.00024567224,0.0013557071,0.000039523333,0.0000012234705,0.000368359],"genre_scores_gemma":[0.000065958935,0.9920517,0.006207343,0.0006420457,0.00047550365,0.00003331191,0.000009469632,0.000018733503,0.0004958992],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.25330928,0.6104196,0.12229156,0.0027391207,0.010226612,0.0010138782],"domain_scores_gemma":[0.19589218,0.6258136,0.14121954,0.007999198,0.02740401,0.0016714539],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8274901,0.0004625368,0.045542665,0.0014267908,0.00014633889,0.00012427305,0.0032057774,0.0008707619,0.0008349114],"category_scores_gemma":[0.9487911,0.00019311212,0.0091973115,0.004412224,0.0016178113,0.00039192374,0.00064742274,0.0041848733,0.00005039616],"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":[0.00004710622,0.00005349182,0.00036280707,0.06843784,0.0015597051,0.00002792545,0.0019486061,0.0000034220536,3.3441563e-7,0.008093864,0.26715028,0.6523146],"study_design_scores_gemma":[0.00009008433,0.0005649856,0.00006601852,0.0579494,0.00080657576,0.000094260395,0.004188914,0.00007244161,9.003803e-8,0.006894109,0.92915815,0.000114979026],"about_ca_topic_score_codex":0.000007678486,"about_ca_topic_score_gemma":0.0000018837042,"teacher_disagreement_score":0.66200787,"about_ca_system_score_codex":0.000060521077,"about_ca_system_score_gemma":0.0023446686,"threshold_uncertainty_score":0.9981125},"labels":[],"label_agreement":null},{"id":"W3091337614","doi":"10.1016/j.jclinepi.2020.09.037","title":"Developing trustworthy recommendations as part of an urgent response (1–2 weeks): a GRADE concept paper","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Public Health Agency of Canada; University of Ottawa; University of Toronto; McMaster University; Impact; McMaster University Medical Centre","funders":"Medical Research Council; Manchester Biomedical Research Centre; National Institute for Health and Care Research; AllerGen; Chief Scientist Office; Networks of Centres of Excellence of Canada; Scottish Government; Canadian Allergy, Asthma and Immunology Foundation","keywords":"Trustworthiness; Medicine; MEDLINE; Medical education; Computer science; Political science; Computer security","score_opus":0.7105331333403934,"score_gpt":0.6390855052000718,"score_spread":0.07144762814032157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091337614","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":[0.4740516,0.00015687275,0.006255346,0.51820326,0.0010381937,0.00021805835,0.000011706548,0.000014809803,0.000050124516],"genre_scores_gemma":[0.6693924,0.0014609173,0.10801681,0.21805334,0.0029147877,0.000005803578,0.000055188717,0.000033813398,0.00006695267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97574234,0.011015678,0.012204272,0.00036799954,0.00033022757,0.000339496],"domain_scores_gemma":[0.8787165,0.109745376,0.008418385,0.0004232524,0.00097263575,0.0017238104],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03669325,0.00018369325,0.0024912213,0.0000973044,0.000052671723,0.0000048392358,0.00023992946,0.0003244937,0.0021226243],"category_scores_gemma":[0.62193453,0.00014314418,0.00073321216,0.00025515017,0.00027769915,0.000326853,0.00008710828,0.0012987088,0.000034919005],"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":[0.071017355,0.00262967,0.212445,0.00016517245,0.002118566,0.0005416489,0.0014017717,0.0007025966,0.0012735345,0.010023791,0.26010856,0.43757233],"study_design_scores_gemma":[0.008611186,0.012117294,0.1571856,0.0002405106,0.0006615486,0.000520032,0.0011639807,0.0012573947,0.00016170954,0.009050926,0.8087917,0.0002381449],"about_ca_topic_score_codex":0.000034783498,"about_ca_topic_score_gemma":0.000011291456,"teacher_disagreement_score":0.58524126,"about_ca_system_score_codex":0.00006130915,"about_ca_system_score_gemma":0.0020714556,"threshold_uncertainty_score":0.99878955},"labels":[],"label_agreement":null},{"id":"W3091560510","doi":"10.1016/j.jclinepi.2020.09.025","title":"An algorithm provided as initial guidance for reporting registry records and published protocols in systematic reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Saskatchewan; Saskatchewan Health","funders":"University of Bristol","keywords":"Systematic review; Terminology; Psychological intervention; MEDLINE; Transparency (behavior); Computer science; Medicine; Algorithm; Scientific literature; Data mining; Nursing","score_opus":0.9411542076993163,"score_gpt":0.718777948153474,"score_spread":0.2223762595458424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091560510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06406118,0.007481056,0.7648022,0.07185901,0.0025413767,0.08735548,0.00002656663,0.00001932403,0.001853772],"genre_scores_gemma":[0.07817486,0.0005243125,0.87435776,0.03128134,0.005816498,0.008643271,0.000009814485,0.0000653545,0.0011267931],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.39115965,0.2799804,0.32189605,0.0026783748,0.0034087647,0.0008767583],"domain_scores_gemma":[0.14219816,0.34941998,0.4951812,0.005667455,0.0056438446,0.0018893535],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8221611,0.00034423854,0.027011702,0.0002290828,0.00007226004,0.00034139567,0.00212245,0.00040178566,0.00038857694],"category_scores_gemma":[0.9854829,0.00015457362,0.004038575,0.00074599846,0.00014071775,0.00073585997,0.00012528304,0.000951447,0.00006463178],"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":[0.0006035148,0.00044117527,0.51937,0.023208736,0.000567784,0.00025775636,0.000627682,0.0000982716,0.000023805982,0.0023837918,0.23949565,0.21292178],"study_design_scores_gemma":[0.0067499424,0.010722125,0.095654644,0.02452832,0.0014269145,0.0021879908,0.0016373406,0.24642202,0.000013445383,0.22743125,0.38192198,0.0013040068],"about_ca_topic_score_codex":0.000009252,"about_ca_topic_score_gemma":0.000010686085,"teacher_disagreement_score":0.4237154,"about_ca_system_score_codex":0.000028407849,"about_ca_system_score_gemma":0.00045631357,"threshold_uncertainty_score":0.9874333},"labels":[],"label_agreement":null},{"id":"W3091777199","doi":"10.1016/j.jclinepi.2020.07.023","title":"Reply to Kelly Farrah and David Kaunelis regarding our study “Validation of five search filters for retrieval of clinical practice guidelines produced low precision”","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Cochrane; University of British Columbia","funders":"","keywords":"Clinical Practice; Medicine; Medical physics; Information retrieval; Psychology; Computer science; Family medicine","score_opus":0.6928547970336905,"score_gpt":0.662740426607522,"score_spread":0.03011437042616849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091777199","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":[0.13801397,0.00020323247,0.006986765,0.84735453,0.0040320796,0.0032444405,0.00012406507,0.000017978633,0.00002296543],"genre_scores_gemma":[0.017889949,0.0013781812,0.19709274,0.75871795,0.024229892,0.000020937145,0.00020769794,0.00012819932,0.00033443343],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92083514,0.021941677,0.05211293,0.00204614,0.0022134315,0.00085068296],"domain_scores_gemma":[0.55303365,0.37667167,0.04296066,0.0020105056,0.024167087,0.0011564314],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16528338,0.0005915846,0.009576727,0.0005062501,0.00008593822,0.000024170817,0.00075718877,0.0015035466,0.000033687185],"category_scores_gemma":[0.9495561,0.0004556344,0.002148116,0.0005388198,0.00029404025,0.00047079232,0.00049904553,0.006579203,0.000009770697],"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":[0.032512266,0.00091720687,0.031117372,0.0007170337,0.0018892863,0.0002589695,0.00026059017,0.00025540477,0.00009633717,0.0000034138577,0.90802795,0.023944147],"study_design_scores_gemma":[0.025961662,0.061094675,0.027126102,0.0029223557,0.009008318,0.00076084,0.005252348,0.0022493608,0.00038986618,0.0009521188,0.86344546,0.00083691475],"about_ca_topic_score_codex":0.00016471044,"about_ca_topic_score_gemma":0.0000034863829,"teacher_disagreement_score":0.78427273,"about_ca_system_score_codex":0.000095776435,"about_ca_system_score_gemma":0.0023300794,"threshold_uncertainty_score":0.9997927},"labels":[],"label_agreement":null},{"id":"W3091820138","doi":"10.1016/j.jclinepi.2020.09.041","title":"Defining Rapid Reviews: a systematic scoping review and thematic analysis of definitions and defining characteristics of rapid reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":396,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Systematic review; CINAHL; MEDLINE; PsycINFO; Data extraction; Cochrane Library; Thematic analysis; Scope (computer science); Computer science; Data science; Medicine; Management science; Meta-analysis; Qualitative research; Sociology; Pathology; Social science; Political science","score_opus":0.8899209002194405,"score_gpt":0.7277204437820118,"score_spread":0.16220045643742864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091820138","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":[0.056873858,0.84782976,0.018619917,0.067811206,0.00073812006,0.007249245,0.00020042663,0.000027024485,0.0006504271],"genre_scores_gemma":[0.043564145,0.83655757,0.029451877,0.090182446,0.00011340626,0.0001015805,0.000008382732,0.00001685675,0.0000037605512],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9404888,0.03346216,0.024965186,0.00033964138,0.00026096383,0.00048321797],"domain_scores_gemma":[0.7825035,0.1793575,0.036108702,0.0005143736,0.0007010093,0.0008149167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11592088,0.00022532133,0.011503225,0.00031156087,0.00019670122,0.0000035954913,0.00031695896,0.00021765687,0.00035218798],"category_scores_gemma":[0.5558416,0.00015238,0.0006931356,0.0010837323,0.0003490457,0.0001615998,0.0001606663,0.001008926,0.00003110854],"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":[0.00006107569,0.000060399125,0.15228988,0.81805176,0.00073088263,0.0000037376283,0.003748514,0.0000023620003,0.000011721757,0.0098126605,0.0043971953,0.01082982],"study_design_scores_gemma":[0.0020221933,0.0018184475,0.08509707,0.8912774,0.012968416,0.00005884866,0.0013432195,0.0010988289,9.861042e-7,0.0015465474,0.002350156,0.00041791017],"about_ca_topic_score_codex":0.000010570435,"about_ca_topic_score_gemma":0.00001021101,"teacher_disagreement_score":0.43992075,"about_ca_system_score_codex":0.00002750782,"about_ca_system_score_gemma":0.0006287944,"threshold_uncertainty_score":0.9103455},"labels":[],"label_agreement":null},{"id":"W3092043383","doi":"10.1016/j.jclinepi.2020.09.014","title":"Erratum to “Controversy and debate series on core outcome sets. Paper 3:debate on paper 1 from the perspective of GRADE [Grading of Recommendations Assessment, Development and Evaluation]” [Journal of Clinical Epidemiology 125C (2020) 216-221]","year":2020,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; Cochrane","funders":"","keywords":"Outcome (game theory); Health care; Medicine; Grading (engineering); Population; Perspective (graphical); Actuarial science; Political science; Computer science; Business; Engineering; Environmental health","score_opus":0.633235307309604,"score_gpt":0.6457146337335498,"score_spread":0.01247932642394578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092043383","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":[0.06839574,0.004165287,0.0016052804,0.8711617,0.039216477,0.0023920399,0.00031530776,0.000037602425,0.012710542],"genre_scores_gemma":[0.56245923,0.12152872,0.19015759,0.090726204,0.028152822,0.0001630912,0.00022754684,0.000345263,0.0062395013],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9426328,0.039272364,0.014958183,0.0009043283,0.0014186967,0.0008136537],"domain_scores_gemma":[0.7935023,0.1858358,0.016630854,0.0005724962,0.0025278374,0.0009307597],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1481222,0.00051694445,0.006963707,0.00034000372,0.00036905447,0.00002951162,0.0013917771,0.0017933765,0.00034628058],"category_scores_gemma":[0.41845763,0.00033958032,0.0012510432,0.00038819603,0.002346466,0.0003286988,0.00040846976,0.0072562704,0.0000046932337],"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":[0.0017745779,0.00040322804,0.14806923,0.000055261375,0.0016385894,0.000050948627,0.001811242,0.00005685152,0.000007499846,0.01790737,0.8020541,0.026171073],"study_design_scores_gemma":[0.00242476,0.0050579496,0.42316368,0.0011579148,0.0006769424,0.00005985852,0.006055289,0.00024916863,0.0000028617076,0.13454328,0.42617795,0.00043033296],"about_ca_topic_score_codex":0.000557871,"about_ca_topic_score_gemma":0.0010313719,"teacher_disagreement_score":0.7804355,"about_ca_system_score_codex":0.00043622113,"about_ca_system_score_gemma":0.0042268177,"threshold_uncertainty_score":0.99990565},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3092343537","doi":"10.1016/j.jclinepi.2020.10.002","title":"A framework for practical issues was developed to inform shared decision-making tools and clinical guidelines","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"Impact; McMaster University","funders":"Helse Sør-Øst RHF; Sykehuset Innlandet HF","keywords":"Clinical decision making; Management science; MEDLINE; Computer science; Medicine; Data science; Family medicine; Engineering; Political science","score_opus":0.8966904454186121,"score_gpt":0.7328196296699897,"score_spread":0.1638708157486224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092343537","genre_codex":"commentary","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":[0.03150697,0.001968318,0.25985217,0.70052487,0.004302536,0.0015889205,0.00006185418,0.000057197634,0.00013717856],"genre_scores_gemma":[0.03980634,0.001908867,0.7858667,0.1686041,0.0036803945,0.00006362925,0.00000809966,0.000035452616,0.000026419677],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97039557,0.009400564,0.01845732,0.00055760524,0.0003910987,0.0007978523],"domain_scores_gemma":[0.431689,0.5511044,0.00965068,0.0009301406,0.0047028046,0.0019229766],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.03131797,0.0002855983,0.0035696013,0.00013061824,0.000552264,0.00001979275,0.00088547595,0.0014496596,0.0002383511],"category_scores_gemma":[0.9166366,0.0002122145,0.00064565794,0.00036281213,0.00024115987,0.00044116293,0.0008748793,0.004284431,0.00015569168],"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":[0.0052081947,0.00011511956,0.56364805,0.00023425021,0.00019749987,0.000013173905,0.0018869956,0.00003159829,4.4764496e-7,0.026015742,0.21975121,0.18289772],"study_design_scores_gemma":[0.002345553,0.0029162192,0.24330261,0.0023525392,0.000109799126,0.000025190877,0.0028299408,0.0035938,2.2370708e-7,0.12209712,0.62012964,0.0002973786],"about_ca_topic_score_codex":0.000012510798,"about_ca_topic_score_gemma":0.00003810683,"teacher_disagreement_score":0.88531864,"about_ca_system_score_codex":0.00008818548,"about_ca_system_score_gemma":0.002564375,"threshold_uncertainty_score":0.9998467},"labels":[],"label_agreement":null},{"id":"W3092985072","doi":"10.1016/j.jclinepi.2020.10.007","title":"Cochrane Rapid Reviews Methods Group offers evidence-informed guidance to conduct rapid reviews","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1157,"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; Cochrane; Ottawa Hospital; Canadian Agency for Drugs and Technologies in Health; University of Ottawa","funders":"Donau-Universität Krems; Ottawa Hospital Research Institute","keywords":"Systematic review; Interim; Medicine; Cochrane collaboration; MEDLINE; Evidence-based medicine; Family medicine; Alternative medicine; Medical education; Pathology; Political science","score_opus":0.9707839184494348,"score_gpt":0.7507483730391079,"score_spread":0.22003554541032688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092985072","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036692226,0.32802168,0.50924844,0.14856347,0.0049246512,0.0027208948,0.000008539158,0.000010336165,0.0028327596],"genre_scores_gemma":[0.0031422342,0.18924038,0.66748077,0.13573681,0.0030984585,0.0000575195,0.0000027888461,0.000031104908,0.0012099387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.21596795,0.57188475,0.20253524,0.0029488374,0.005248254,0.001414954],"domain_scores_gemma":[0.074070945,0.7493689,0.15829493,0.0084885545,0.0050652353,0.0047114044],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8554755,0.0007568916,0.04492948,0.00042053996,0.00014311673,0.00017737114,0.0059258463,0.000532195,0.019574871],"category_scores_gemma":[0.9787758,0.00032657344,0.016293695,0.0023973966,0.0003991413,0.00073822564,0.00043008834,0.0017976768,0.0076091536],"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":[0.00015205386,0.00004436909,0.007961277,0.00027075192,0.00022818705,0.0000115733765,0.00014800948,0.00003076081,0.000093675466,0.00049635774,0.5883952,0.40216783],"study_design_scores_gemma":[0.00051315967,0.0017208919,0.009695281,0.0013106274,0.0005836805,0.0000873843,0.00009317729,0.0010896996,0.0000087216695,0.003190225,0.9814007,0.00030642044],"about_ca_topic_score_codex":0.000005194652,"about_ca_topic_score_gemma":0.0000071134555,"teacher_disagreement_score":0.4018614,"about_ca_system_score_codex":0.00006691647,"about_ca_system_score_gemma":0.00041053712,"threshold_uncertainty_score":0.99991864},"labels":[],"label_agreement":null},{"id":"W3094687831","doi":"10.1016/j.jclinepi.2020.11.004","title":"New methodological approaches were able to effectively reduce immeasurable time bias in case-only designs","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"National Research Foundation of Korea","keywords":"Econometrics; Statistics; Computer science; Economics; Mathematics","score_opus":0.9799927020036421,"score_gpt":0.7030028591691723,"score_spread":0.2769898428344698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094687831","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":[0.106285445,0.0002002569,0.8541237,0.036012717,0.0011424796,0.0008212554,0.000017366041,0.000053515516,0.0013432457],"genre_scores_gemma":[0.02833001,0.000055603396,0.96306187,0.0057914993,0.0024876697,0.000010513714,3.9065247e-7,0.000052506355,0.00020992116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8842964,0.098598465,0.014308881,0.0011327807,0.00055067346,0.0011127717],"domain_scores_gemma":[0.17530446,0.8173654,0.004498642,0.0005197484,0.0002993673,0.0020123906],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20216893,0.000447492,0.0083990805,0.00016546615,0.000067075955,0.000022621914,0.0008642003,0.0011477593,0.0007764414],"category_scores_gemma":[0.9572718,0.00031076136,0.0013608264,0.000601031,0.00032774615,0.00013252991,0.00027606517,0.0031455716,0.00022750108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020583875,0.002265217,0.08152336,0.00057219557,0.0016277229,0.008434317,0.0006007893,0.0021455695,0.0009930229,0.10533566,0.24238318,0.5335351],"study_design_scores_gemma":[0.00375109,0.0059879115,0.013405878,0.00025118858,0.00030348607,0.0020513637,0.00009446411,0.0015306592,0.00022607746,0.9699163,0.002045667,0.0004359348],"about_ca_topic_score_codex":0.000042171,"about_ca_topic_score_gemma":0.000006909932,"teacher_disagreement_score":0.86458063,"about_ca_system_score_codex":0.0000976761,"about_ca_system_score_gemma":0.0006952489,"threshold_uncertainty_score":0.99993443},"labels":[],"label_agreement":null},{"id":"W3094722022","doi":"10.1016/j.jclinepi.2020.10.009","title":"Conducting high quality scoping reviews-challenges and solutions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":305,"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; Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Quality (philosophy); Medicine; Environmental health; Physics","score_opus":0.9938437470288377,"score_gpt":0.7551957118594051,"score_spread":0.23864803516943256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094722022","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27756977,0.26482967,0.117660694,0.33370703,0.0026751878,0.0007645132,0.0000071635845,0.000006862097,0.0027791234],"genre_scores_gemma":[0.8453565,0.059484642,0.0707556,0.020922186,0.0031161532,0.000006086701,0.0000010916411,0.000014280218,0.00034345489],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5468714,0.33315113,0.11559895,0.0014367431,0.0023533169,0.00058841944],"domain_scores_gemma":[0.17860304,0.6827293,0.13059624,0.0031256003,0.003185182,0.0017606622],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7442183,0.0002027769,0.016951418,0.00010274494,0.00010531687,0.000055922512,0.0010380009,0.00022111196,0.0013521676],"category_scores_gemma":[0.9274217,0.000089866044,0.0035462508,0.0002721532,0.00025096416,0.0002351353,0.00021125433,0.00081175094,0.0005535972],"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":[0.00007654777,0.000118833465,0.13599552,0.0006549201,0.0007262641,0.000020022988,0.0007342057,0.00016144861,0.000044345554,0.065105684,0.111234404,0.6851278],"study_design_scores_gemma":[0.0017521528,0.0013544515,0.33787218,0.0018486955,0.0010329647,0.00026416668,0.0027102223,0.0035502748,0.0000028164131,0.22517487,0.42384517,0.0005920143],"about_ca_topic_score_codex":0.000004046908,"about_ca_topic_score_gemma":0.000010371751,"teacher_disagreement_score":0.6845358,"about_ca_system_score_codex":0.0000082094275,"about_ca_system_score_gemma":0.00011115338,"threshold_uncertainty_score":0.9995607},"labels":[],"label_agreement":null},{"id":"W3095428976","doi":"10.1016/j.jclinepi.2020.11.001","title":"Response to letter from Chou regarding “Systematic reviews that include only published data may overestimate the effectiveness of analgesic medicines for low back pain”","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","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 Health and Medical Research Council; Memorial University of Newfoundland; Neuroscience Research Australia","keywords":"Analgesic; Medicine; Alternative medicine; Physical therapy; Anesthesia; Pathology","score_opus":0.2741945122028666,"score_gpt":0.4905930740504148,"score_spread":0.2163985618475482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095428976","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0065887873,0.002687751,0.023660181,0.95962584,0.0025928852,0.0046843486,0.00010834812,0.0000133600815,0.000038487986],"genre_scores_gemma":[0.007530016,0.00069598487,0.012056369,0.967132,0.011754689,0.000089890105,0.00050361024,0.00009116582,0.00014630434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8572551,0.12801783,0.012073127,0.0011476442,0.0008630041,0.00064329774],"domain_scores_gemma":[0.47971067,0.50835985,0.008761632,0.0021453116,0.0006401522,0.00038240902],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2651506,0.00055548863,0.011332553,0.00030700013,0.00007418704,0.00002272082,0.0015361137,0.0012189704,0.00010851044],"category_scores_gemma":[0.784893,0.00026595398,0.0022674706,0.00030939636,0.0005323689,0.00020924053,0.00037142923,0.0036863252,0.000032232932],"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":[0.0081722345,0.000073160874,0.011809968,0.08262008,0.00094747794,0.00006294014,0.000043573185,0.000010415682,0.00014093587,0.000007878419,0.8954274,0.00068392267],"study_design_scores_gemma":[0.006873997,0.006455378,0.14227194,0.15549183,0.0024918395,0.000094196155,0.000054033142,0.001456874,0.000008671979,0.0044381265,0.6798259,0.00053721614],"about_ca_topic_score_codex":0.000034620916,"about_ca_topic_score_gemma":0.0000067866367,"teacher_disagreement_score":0.51974237,"about_ca_system_score_codex":0.000115950585,"about_ca_system_score_gemma":0.0005437222,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W3096048661","doi":"10.1016/j.jclinepi.2020.10.017","title":"Guidelines rarely used GRADE and applied methods inconsistently: A methodological study of Australian guidelines","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":30,"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; Cochrane; Impact; McMaster University Medical Centre","funders":"National Health and Medical Research Council","keywords":"Medicine; Psychology; Medical education","score_opus":0.9682711305030808,"score_gpt":0.7802301119052686,"score_spread":0.1880410185978122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096048661","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":[0.000901047,0.936025,0.013276659,0.044463098,0.0023000867,0.0028967187,0.000037769594,0.000048836508,0.00005074677],"genre_scores_gemma":[0.000032518074,0.57385856,0.41995156,0.0036809524,0.0023233504,0.000024041166,0.000024750398,0.000058927875,0.000045362394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87753326,0.0551548,0.064085834,0.0015325497,0.0009298405,0.0007637215],"domain_scores_gemma":[0.64018416,0.31578746,0.038698938,0.0011057339,0.0028138957,0.0014098189],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16685994,0.0009500181,0.029287292,0.0005265861,0.00007001121,0.00001659778,0.00075557287,0.0018668484,0.00014639666],"category_scores_gemma":[0.7432834,0.0005922052,0.003799821,0.00069291925,0.000666889,0.00013160161,0.0005854212,0.004568067,0.0000127910935],"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":[0.0010530563,0.0010314153,0.0031471886,0.0032605706,0.003261144,0.00018252776,0.00004633165,0.000013003396,0.000003759184,0.00019429385,0.022381373,0.9654253],"study_design_scores_gemma":[0.0059923567,0.0073237102,0.001828745,0.0035253107,0.015842803,0.0016070196,0.0006908994,0.00008300891,7.64089e-7,0.002110814,0.9605717,0.00042288477],"about_ca_topic_score_codex":0.00007270402,"about_ca_topic_score_gemma":0.000018948187,"teacher_disagreement_score":0.9650025,"about_ca_system_score_codex":0.00009097061,"about_ca_system_score_gemma":0.0017337773,"threshold_uncertainty_score":0.9996529},"labels":[],"label_agreement":null},{"id":"W3097480854","doi":"10.1016/j.jclinepi.2020.10.016","title":"Using GRADE evidence to decision frameworks to choose from multiple interventions","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; McMaster University Medical Centre; Impact","funders":"European Commission; World Health Organization","keywords":"Guideline; Grading (engineering); Psychological intervention; Pairwise comparison; Health care; Computer science; Evidence-based medicine; Intervention (counseling); Medicine; Management science; Risk analysis (engineering); Nursing; Artificial intelligence; Engineering; Alternative medicine; Political science","score_opus":0.9464815887369123,"score_gpt":0.6915180779174621,"score_spread":0.25496351081945023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097480854","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":[0.40143055,0.0017305543,0.41784638,0.1770111,0.0016688616,0.00024329418,0.000046251334,0.00000889027,0.0000141237115],"genre_scores_gemma":[0.5410136,0.00031330387,0.30976975,0.1462215,0.0026349972,0.000008292434,0.0000022043262,0.000022155362,0.000014181971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97233164,0.0038093152,0.0226852,0.00063246454,0.00010853143,0.00043284276],"domain_scores_gemma":[0.83646345,0.14773281,0.013046871,0.0006185155,0.00026733443,0.0018710099],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089843564,0.00018658082,0.0038611703,0.0002618306,0.00009665419,0.000030788837,0.0007108167,0.00058375864,0.0005486839],"category_scores_gemma":[0.7101669,0.00019630161,0.0011189576,0.00028100345,0.00007027826,0.00039978727,0.00020156421,0.0013522313,0.0017004929],"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":[0.00060359493,0.00021686661,0.8720761,0.00010485531,0.0002169303,0.000008897069,0.00094157795,0.028053395,0.0000072486714,0.0052382676,0.087155394,0.005376907],"study_design_scores_gemma":[0.002526319,0.0014853603,0.7742031,0.0026761903,0.000056067944,0.000016467508,0.00043871283,0.05275591,0.0000040572204,0.11056201,0.054775227,0.0005005615],"about_ca_topic_score_codex":0.00043002327,"about_ca_topic_score_gemma":0.000057664805,"teacher_disagreement_score":0.6203233,"about_ca_system_score_codex":0.00022013331,"about_ca_system_score_gemma":0.0001764664,"threshold_uncertainty_score":0.9990768},"labels":[],"label_agreement":null},{"id":"W3098103627","doi":"10.1016/j.jclinepi.2020.09.002","title":"Commentary: Quest for using sound evidence when making decisions about screening","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Sound (geography); Psychology; Medicine; Acoustics; Physics","score_opus":0.8867284770193304,"score_gpt":0.688140582223396,"score_spread":0.19858789479593442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098103627","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":[0.00086980243,0.0013868294,0.39299476,0.6013755,0.0027618902,0.0005523915,0.000027602442,0.000015940546,0.00001527325],"genre_scores_gemma":[0.0015245635,0.0008103663,0.32566836,0.6475267,0.024279667,0.0000069958987,0.00008545171,0.00007297001,0.000024921292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9708358,0.0076613585,0.019270686,0.0008153899,0.0006507518,0.0007660057],"domain_scores_gemma":[0.5320744,0.44826448,0.017007284,0.00070190954,0.0015132029,0.00043871393],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04662226,0.0005032361,0.006503007,0.0003363917,0.0001936556,0.000040676292,0.00071207376,0.0017203513,0.00019796279],"category_scores_gemma":[0.6942418,0.00040254433,0.0027243372,0.00019122974,0.0005179497,0.0003897467,0.0003177131,0.009090436,0.000018087529],"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":[0.0025419758,0.00008533652,0.050034575,0.00021423583,0.0010441004,0.0005470116,0.000020842104,0.000071549475,0.0000044076796,0.00006378501,0.92041135,0.024960825],"study_design_scores_gemma":[0.003808059,0.0024288418,0.0056740255,0.0060682977,0.003951134,0.0007102679,0.00007904469,0.0068646404,6.3024635e-7,0.036146082,0.9339518,0.00031717448],"about_ca_topic_score_codex":0.00008474301,"about_ca_topic_score_gemma":0.0000269353,"teacher_disagreement_score":0.64761955,"about_ca_system_score_codex":0.0002544064,"about_ca_system_score_gemma":0.0010299088,"threshold_uncertainty_score":0.99984264},"labels":[],"label_agreement":null},{"id":"W3104016668","doi":"10.1016/j.jclinepi.2020.09.012","title":"Editors Epilogue; Looking back and forward in the arena of screening, overdiagnosis, and optimizing outcome: editors’ epilogue","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cervical Cancer and HPV Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Bruyère; Ottawa Hospital","funders":"","keywords":"Overdiagnosis; Scopus; Medicine; Context (archaeology); Family medicine; Alternative medicine; MEDLINE; History; Political science; Law; Pathology","score_opus":0.3007173394739633,"score_gpt":0.5078620905283047,"score_spread":0.20714475105434138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104016668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5227552,0.010098063,0.01279892,0.44061035,0.009875243,0.001088794,0.000041783907,0.000022075421,0.0027095606],"genre_scores_gemma":[0.93738955,0.004798688,0.0077188313,0.015211409,0.034840398,0.0000046359587,0.0000052127007,0.000021296388,0.0000099829895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931755,0.0020655154,0.003622316,0.00032111877,0.00039858703,0.0004169701],"domain_scores_gemma":[0.9623454,0.035222284,0.0013584873,0.00021325213,0.00026695433,0.0005936044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016461913,0.00018407927,0.0026007034,0.00012499151,0.000046944726,0.000009946499,0.00027235787,0.0003748616,0.00023749811],"category_scores_gemma":[0.06898479,0.00011032583,0.0004489773,0.00020927165,0.0005845474,0.00010977154,0.00019589622,0.0021038721,0.0000038257267],"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":[0.0012574614,0.000116753465,0.9112267,0.00021704078,0.0001244673,0.00006549062,0.00018424068,0.00006269807,0.000007773389,0.00011876872,0.06411403,0.02250458],"study_design_scores_gemma":[0.0041272365,0.0032439034,0.94754106,0.00015530316,0.00015081842,0.00010113442,0.00035224616,0.0010780757,0.000013154064,0.0009159694,0.042208627,0.000112457004],"about_ca_topic_score_codex":0.00007996037,"about_ca_topic_score_gemma":0.000014808619,"teacher_disagreement_score":0.42539895,"about_ca_system_score_codex":0.00002267593,"about_ca_system_score_gemma":0.00014186541,"threshold_uncertainty_score":0.93885756},"labels":[],"label_agreement":null},{"id":"W3104172677","doi":"10.1016/j.jclinepi.2020.11.007","title":"A meta-research study revealed several challenges in obtaining placebos for investigator-initiated drug trials","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pain Management and Placebo Effect","field":"Neuroscience","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; Impact","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Cancer Research UK; Medical Research Council; National Institute for Health and Care Research; NIHR Bristol Biomedical Research Centre","keywords":"Medicine; Placebo; Randomized controlled trial; Alternative medicine; Drug trial; Clinical trial; Drug; Meta-analysis; Family medicine; Medical physics; Psychiatry; Internal medicine; Pathology","score_opus":0.9597744127864302,"score_gpt":0.6432830640147714,"score_spread":0.31649134877165874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104172677","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.834749,0.0022000894,0.003264365,0.15333839,0.0012975123,0.004047871,0.00001743652,0.00006201705,0.001023306],"genre_scores_gemma":[0.9820801,0.0017307762,0.0016835675,0.013009022,0.0012693492,0.00011021579,0.0000010373715,0.000026853428,0.000089077104],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.62403625,0.36307475,0.010054546,0.0010243322,0.00075039983,0.0010597599],"domain_scores_gemma":[0.21279643,0.781594,0.004069123,0.0003520283,0.00027499715,0.0009134174],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5427868,0.00027419382,0.0057670893,0.00035774318,0.00011756016,0.000024295381,0.0008867259,0.00025889004,0.0000985757],"category_scores_gemma":[0.8962307,0.00018510732,0.0012848973,0.0004868566,0.00030649645,0.00022937835,0.00020053015,0.0021406882,0.000029397766],"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":[0.03692415,0.0037253757,0.71684295,0.0009717047,0.006846914,0.0019820468,0.010457726,0.008594972,0.0016564829,0.014205843,0.15510164,0.042690177],"study_design_scores_gemma":[0.10842789,0.049703263,0.23206104,0.00097624556,0.009179173,0.00016533128,0.0126256095,0.25992155,0.001230076,0.17429563,0.14832684,0.003087353],"about_ca_topic_score_codex":0.000011114713,"about_ca_topic_score_gemma":0.00001757832,"teacher_disagreement_score":0.48478192,"about_ca_system_score_codex":0.000028702845,"about_ca_system_score_gemma":0.00033941166,"threshold_uncertainty_score":0.9300344},"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":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3104398108","doi":"10.1016/j.jclinepi.2020.09.043","title":"Cervical screening and overdiagnosis: continuation of Controversy and Debate","year":2020,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Overdiagnosis; Medicine; Continuation; Intensive care medicine; Internal medicine; Computer science","score_opus":0.42631420624365307,"score_gpt":0.5973015582155502,"score_spread":0.17098735197189713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104398108","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043501522,0.007838769,0.02510291,0.15833049,0.763597,0.0011479764,0.0002218325,0.000033903896,0.0002256018],"genre_scores_gemma":[0.0562859,0.022948943,0.031000858,0.011286766,0.8782144,0.0000059149706,0.00015054416,0.000064453016,0.00004221544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9824665,0.004122108,0.012037331,0.00047296772,0.00061544636,0.00028565258],"domain_scores_gemma":[0.48412523,0.49244907,0.019821217,0.00036143474,0.0022602524,0.0009827908],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.031664744,0.00028444646,0.0056400266,0.00013531317,0.000033123364,0.000010456586,0.00014764923,0.0015424587,0.00006548294],"category_scores_gemma":[0.74236447,0.0002214782,0.0007307866,0.00009509232,0.00045925096,0.00018539897,0.00013799366,0.0032473293,0.0000028874904],"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":[0.0053359806,0.00014219017,0.11381811,0.00029938438,0.0008390473,0.00006402781,0.0000278846,0.0000035978248,0.000019492187,0.00011260197,0.830449,0.04888868],"study_design_scores_gemma":[0.014341672,0.0063692825,0.1470885,0.0009940317,0.003042949,0.00012703573,0.00014007014,0.00069059513,0.000005110633,0.0019907379,0.8249981,0.00021190837],"about_ca_topic_score_codex":0.00011120674,"about_ca_topic_score_gemma":0.000022228405,"teacher_disagreement_score":0.71069974,"about_ca_system_score_codex":0.000031984404,"about_ca_system_score_gemma":0.0006730692,"threshold_uncertainty_score":0.9997538},"labels":[],"label_agreement":null},{"id":"W3108559480","doi":"10.1016/j.jclinepi.2020.10.021","title":"COVID-19, health inequities, and methodology’s mission","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","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":"Ottawa Hospital; University of Ottawa; Bruyère","funders":"","keywords":"Life expectancy; Public health; Scopus; Disadvantaged; Health equity; Demography; Gerontology; Political science; Medicine; Psychology; Economic growth; Geography; Sociology; MEDLINE; Population; Economics; Law","score_opus":0.8519633924336855,"score_gpt":0.6873041980733657,"score_spread":0.16465919436031973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108559480","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":[0.019098002,0.0050135204,0.013086671,0.96070635,0.0013927345,0.00010864254,0.0000043634036,0.000018652005,0.00057107856],"genre_scores_gemma":[0.06805928,0.020322232,0.040777676,0.8672799,0.0034007283,6.863963e-7,0.0000010979519,0.000008836244,0.00014957701],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97009796,0.024749637,0.004184926,0.00021800022,0.00019359424,0.00055587856],"domain_scores_gemma":[0.88807565,0.10391908,0.0031234156,0.000103849154,0.00011957984,0.0046584276],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08984898,0.00009494527,0.0023253665,0.00004624032,0.00033188466,0.000008187521,0.00026775696,0.00033558096,0.00046319488],"category_scores_gemma":[0.57101065,0.00006905158,0.00028817874,0.000108450295,0.0006469331,0.000099709774,0.00007430397,0.0008362139,0.000007835088],"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":[0.00030208714,0.0000394464,0.5383544,0.00026297287,0.000043849443,0.000021851813,0.0036295375,0.00003361717,3.9820483e-7,0.1184388,0.31055316,0.028319877],"study_design_scores_gemma":[0.0006336308,0.0005557458,0.053092156,0.00003068774,0.000011815715,0.000013494528,0.0024113632,0.000052291613,1.2188094e-7,0.031911388,0.9112226,0.00006470297],"about_ca_topic_score_codex":0.0029943092,"about_ca_topic_score_gemma":0.00042825373,"teacher_disagreement_score":0.60066944,"about_ca_system_score_codex":0.00008788817,"about_ca_system_score_gemma":0.0047406373,"threshold_uncertainty_score":0.937192},"labels":[],"label_agreement":null},{"id":"W3109222706","doi":"10.1016/j.jclinepi.2020.11.018","title":"GRADE Concept Paper 1: Validating the “F.A.C.E” instrument using stakeholder perceptions of feasibility, acceptability, cost, and equity in guideline implement","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":16,"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; McGill University; Impact; Public Health Agency of Canada; Bruyère; University of Ottawa","funders":"European Centre for Disease Prevention and Control; Public Health Agency of Canada; World Health Organization","keywords":"Guideline; Stakeholder; Brainstorming; Stakeholder engagement; Knowledge translation; Grading (engineering); Knowledge management; Stakeholder analysis; Face validity; Process management; Computer science; Medical education; Medicine; Business; Public relations; Engineering; Political science","score_opus":0.9573684455090367,"score_gpt":0.7838099502496856,"score_spread":0.17355849525935108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109222706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7990555,0.000042071933,0.007432128,0.19186835,0.00046607887,0.0009589394,0.00006515006,0.00000630781,0.00010543577],"genre_scores_gemma":[0.9032388,0.00014586942,0.016223209,0.07967644,0.0006857287,0.000012502262,0.000003582603,0.000010382452,0.0000034873528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9564707,0.026171159,0.0154657625,0.00044873002,0.00053084374,0.0009127647],"domain_scores_gemma":[0.9400997,0.051899634,0.006268125,0.0003950333,0.0006146829,0.00072281004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09052704,0.00017465459,0.0018660781,0.00008458578,0.00032446362,0.0000062140207,0.00054107956,0.00023942353,0.00249156],"category_scores_gemma":[0.122284874,0.000112078786,0.00025142287,0.00034952193,0.0006284587,0.000281588,0.0008005278,0.0018080489,0.000005273003],"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":[0.00008326826,0.00006855046,0.97787845,0.0000832062,0.000020611673,0.0000013105324,0.004202239,0.00028230052,0.0001553467,0.0012941302,0.0055915117,0.0103390515],"study_design_scores_gemma":[0.00310266,0.00060157455,0.96067727,0.000076293014,0.00004316576,0.000010408955,0.012142107,0.0026674797,0.0000072611156,0.00577687,0.014781961,0.000112939204],"about_ca_topic_score_codex":0.0007074175,"about_ca_topic_score_gemma":0.00046458808,"teacher_disagreement_score":0.11219191,"about_ca_system_score_codex":0.00027193976,"about_ca_system_score_gemma":0.001729529,"threshold_uncertainty_score":0.9984203},"labels":[],"label_agreement":null},{"id":"W3110061291","doi":"10.1016/j.jclinepi.2020.11.020","title":"Evidence, values, and masks for control of COVID-19","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Infection Control and Ventilation","field":"Medicine","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":"McMaster University; Impact","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Betacoronavirus; Coronavirus Infections; Medicine; MEDLINE; Virology; Biology; Internal medicine; Outbreak","score_opus":0.45424916367350326,"score_gpt":0.5513267322392843,"score_spread":0.09707756856578104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110061291","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":[0.05555437,0.0027136926,0.80300456,0.13774432,0.00058513856,0.00029872498,0.000005886693,0.000008199701,0.00008510682],"genre_scores_gemma":[0.95666623,0.00075635995,0.00337151,0.03764343,0.0015109999,0.0000023067178,9.994609e-7,0.0000053070594,0.000042848184],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958034,0.0011635075,0.002686348,0.00013130809,0.0000907445,0.0001246538],"domain_scores_gemma":[0.95900613,0.037897263,0.0021557575,0.0000786714,0.000354206,0.00050797197],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014095717,0.00007157676,0.0017021237,0.000051317787,0.000026383888,0.0000014844527,0.000051469135,0.0002021993,0.00008221166],"category_scores_gemma":[0.2627121,0.00004840194,0.0005182824,0.000051469357,0.00015800321,0.0000615479,0.000011355857,0.0003415157,0.0000021659514],"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":[0.009581525,0.000098553886,0.9604295,0.00029650787,0.00033877126,0.000011742062,0.00005521383,0.00044673865,0.0001658069,0.0021503877,0.013649774,0.012775486],"study_design_scores_gemma":[0.022483388,0.01502924,0.7813321,0.0003088928,0.0013858185,0.00035239014,0.000056228102,0.08318679,0.000022745679,0.021225128,0.074483626,0.00013369437],"about_ca_topic_score_codex":0.000004598318,"about_ca_topic_score_gemma":5.53053e-7,"teacher_disagreement_score":0.90111184,"about_ca_system_score_codex":0.000013378076,"about_ca_system_score_gemma":0.00030074245,"threshold_uncertainty_score":0.7434984},"labels":[],"label_agreement":null},{"id":"W3110744755","doi":"10.1016/j.jclinepi.2020.12.006","title":"Systematic review and narrative review lead experts to different cancer trial predictions: a randomized trial","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Ottawa; Wilfrid Laurier University; Ottawa Hospital; McGill University","funders":"","keywords":"Randomized controlled trial; Medicine; Narrative review; Confidence interval; Colorectal cancer; Clinical trial; Systematic review; MEDLINE; Family medicine; Cancer; Internal medicine; Intensive care medicine","score_opus":0.895906543173014,"score_gpt":0.6844062984471154,"score_spread":0.21150024472589857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110744755","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":[0.008824091,0.69229877,0.02621113,0.25375533,0.003017663,0.015686108,0.000012532331,0.000005705672,0.00018866966],"genre_scores_gemma":[0.013592625,0.7463817,0.0033835324,0.22915186,0.004027503,0.0017864376,0.0000028944455,0.000028206077,0.0016452582],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.4699974,0.39396685,0.13047169,0.0014377101,0.0036526793,0.00047365497],"domain_scores_gemma":[0.22484966,0.63437057,0.12996344,0.0036855997,0.0047274968,0.0024032253],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.5686761,0.0004400062,0.062236346,0.00016003073,0.00010238505,0.00008024396,0.0015133637,0.0002292946,0.0029727016],"category_scores_gemma":[0.9503764,0.00015855825,0.010805238,0.00069589884,0.00022395235,0.00016975883,0.0001646656,0.00069891656,0.0001498816],"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":[0.3215702,0.00018373472,0.00015650984,0.05273387,0.0028710098,0.000010017674,0.00046762926,0.000015654505,3.6565697e-7,0.00037874246,0.6195741,0.0020381263],"study_design_scores_gemma":[0.8273998,0.0034248203,0.000050447317,0.13029444,0.018384475,0.0000714381,0.00041443092,0.0019998443,1.3041358e-7,0.0037558167,0.013856998,0.0003473603],"about_ca_topic_score_codex":0.0000033096812,"about_ca_topic_score_gemma":0.0000044596086,"teacher_disagreement_score":0.6057172,"about_ca_system_score_codex":0.000031589338,"about_ca_system_score_gemma":0.00020595032,"threshold_uncertainty_score":0.9991013},"labels":[],"label_agreement":null},{"id":"W3111011457","doi":"10.1016/j.jclinepi.2020.11.024","title":"Minimal important difference estimates for patient-reported outcomes: A systematic survey","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":124,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Guelph; University of Alberta; Humber River Regional Hospital; McMaster University; Impact; Ted Rogers Centre for Heart Research; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Medicine; MEDLINE","score_opus":0.859382985978733,"score_gpt":0.6347980568868787,"score_spread":0.22458492909185424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111011457","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":[0.0002736327,0.9782846,0.007888842,0.00563532,0.004279673,0.0026731512,0.00090933853,0.000024515477,0.0000309241],"genre_scores_gemma":[0.00014230593,0.97760284,0.012946773,0.007777202,0.00097110175,0.0002515576,0.00012786502,0.00010463678,0.00007569183],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.8837917,0.015235087,0.09901016,0.0010365751,0.00015933985,0.00076712976],"domain_scores_gemma":[0.47371948,0.3721599,0.15161566,0.0010307418,0.00048492945,0.0009892879],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26764798,0.00074511353,0.045253333,0.0004825475,0.0001099493,0.000042934636,0.0010556666,0.0013374282,0.00008706034],"category_scores_gemma":[0.79760903,0.00059073005,0.004801472,0.00024747907,0.00021876926,0.00017569994,0.00014232521,0.0014506368,0.0003017027],"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":[0.00022993534,0.0007625787,0.4322374,0.47957122,0.009946373,0.000082132916,0.00028953538,0.000013362995,4.4059068e-9,0.016280035,0.035349775,0.02523766],"study_design_scores_gemma":[0.003051132,0.003337478,0.053076215,0.07748028,0.0025633585,0.0005943472,0.00014700447,0.0031255498,7.50477e-9,0.031503636,0.8233646,0.0017563654],"about_ca_topic_score_codex":0.00013433794,"about_ca_topic_score_gemma":0.000035787754,"teacher_disagreement_score":0.7880148,"about_ca_system_score_codex":0.00041137062,"about_ca_system_score_gemma":0.0016538124,"threshold_uncertainty_score":0.99995905},"labels":[],"label_agreement":null},{"id":"W3111084917","doi":"10.1016/j.jclinepi.2020.12.013","title":"A patient-focused, theory-guided approach to survey design identified barriers to and drivers of clinical trial participation","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Breast Cancer Network; Robarts Clinical Trials; Multiple Sclerosis Society of Canada; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Clinical trial; Medicine; Family medicine; Psychology; Political science","score_opus":0.9022561088871075,"score_gpt":0.6879807488890172,"score_spread":0.21427535999809033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111084917","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":[0.88144183,0.000057979025,0.09125492,0.024458585,0.0012512667,0.0012349376,0.000013831005,0.000013668955,0.0002729927],"genre_scores_gemma":[0.9187557,0.00039794142,0.05800913,0.021595823,0.0011244237,0.000017191272,0.0000046088007,0.000031599247,0.00006358472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9270433,0.04979963,0.019603658,0.0011704513,0.0015155064,0.0008674241],"domain_scores_gemma":[0.30989224,0.6696163,0.006968808,0.001110624,0.003700404,0.008711624],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24795736,0.00024591997,0.004758492,0.00019189744,0.00007100424,0.000013887915,0.00052441366,0.0012332853,0.00012779639],"category_scores_gemma":[0.9456306,0.00017960908,0.0009946726,0.00049275684,0.0009593765,0.00009783312,0.00034931,0.0040227473,0.00003393196],"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":[0.33171758,0.0011760613,0.6083928,0.0001759755,0.0009376982,0.00005705496,0.0011404264,0.0011230096,0.0000715654,0.005890826,0.024481706,0.024835324],"study_design_scores_gemma":[0.08585978,0.06752864,0.8006918,0.00045449435,0.00074550393,0.000033823093,0.0005964967,0.0050627384,0.00014516695,0.035933845,0.0024772782,0.0004704572],"about_ca_topic_score_codex":0.000035697827,"about_ca_topic_score_gemma":0.000015359297,"teacher_disagreement_score":0.69767326,"about_ca_system_score_codex":0.000037527207,"about_ca_system_score_gemma":0.0018673142,"threshold_uncertainty_score":0.99827504},"labels":[],"label_agreement":null},{"id":"W3111486665","doi":"10.1016/j.jclinepi.2020.11.026","title":"The HIV care cascade in Manitoba, Canada: Methods, measures, and estimates to meet local needs","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nine Circles Community Health Centre; Health Sciences Centre; Manitoba Health; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Human immunodeficiency virus (HIV); Cascade; Gerontology; Environmental health; Medicine; Family medicine; Engineering","score_opus":0.30010449119205634,"score_gpt":0.525086468700696,"score_spread":0.22498197750863963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111486665","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":[0.21322356,0.025744403,0.109922014,0.64732397,0.0006717408,0.0006305209,0.000037644266,0.00001623443,0.0024299202],"genre_scores_gemma":[0.9371078,0.002110301,0.039329175,0.019779481,0.0013390322,0.000011103468,0.0000051358556,0.000026908621,0.000291087],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938467,0.002884246,0.0024850357,0.00016562743,0.00022948919,0.00038888448],"domain_scores_gemma":[0.97595704,0.021717353,0.00052916707,0.00018306306,0.0003681335,0.001245266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011552368,0.00011764058,0.0014334436,0.000090146306,0.000068423054,0.000007428281,0.00023345271,0.00016027453,0.000030339086],"category_scores_gemma":[0.14713049,0.00006732849,0.0003008353,0.000201512,0.00025593274,0.000037844256,0.000099254125,0.0010292343,0.000005979918],"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":[0.0012502116,0.00005316868,0.31883812,0.000083520994,0.00023927378,0.000296601,0.00024520003,0.00013790822,0.00005270276,0.001043363,0.43990415,0.23785579],"study_design_scores_gemma":[0.0034661172,0.009659251,0.3258283,0.0005390068,0.00020832774,0.00063357264,0.008165254,0.010797487,0.0001359667,0.0019468097,0.6384148,0.00020507158],"about_ca_topic_score_codex":0.030776095,"about_ca_topic_score_gemma":0.2826034,"teacher_disagreement_score":0.7238842,"about_ca_system_score_codex":0.0001158756,"about_ca_system_score_gemma":0.0009234523,"threshold_uncertainty_score":0.975678},"labels":[],"label_agreement":null},{"id":"W3111748504","doi":"10.1016/j.jclinepi.2020.12.002","title":"Modeling the coronavirus disease 2019 pandemic: A comprehensive guide of infectious disease and decision-analytic models","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 epidemiological studies","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":"Institute for Clinical Evaluative Sciences; Public Health Ontario; Toronto Public Health; Health Sciences Centre; Toronto Rehabilitation Institute; Sunnybrook Health Science Centre; St. Michael's Hospital; University of Toronto; University Health Network","funders":"Canada Research Chairs; Ontario Ministry of Health and Long-Term Care","keywords":"Pandemic; Conceptualization; Infectious disease (medical specialty); Public health; Management science; Disease; Decision support system; Computer science; Psychological intervention; Medicine; Data science; Risk analysis (engineering); Coronavirus disease 2019 (COVID-19); Artificial intelligence; Engineering","score_opus":0.7736942247470593,"score_gpt":0.6276286767366139,"score_spread":0.14606554801044536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111748504","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":[0.00057899003,0.8941865,0.10177004,0.0018869117,0.0006002635,0.0008028683,0.00011972886,0.00003194487,0.000022781356],"genre_scores_gemma":[0.00089988695,0.98786896,0.0067237257,0.0033952515,0.0009889966,0.000028017861,0.0000070734604,0.00006588084,0.000022180007],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97067064,0.01129621,0.01596605,0.0009091837,0.00052176503,0.0006361731],"domain_scores_gemma":[0.6629087,0.3252419,0.009203085,0.0008308419,0.00065556145,0.0011599244],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.024174634,0.0008588331,0.018016031,0.0001895001,0.00016973348,0.000014470097,0.0011969366,0.000780441,0.000031883654],"category_scores_gemma":[0.437214,0.00043326837,0.0053407517,0.00031719438,0.001044717,0.00012645051,0.0011495803,0.0031097045,0.000015571639],"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":[0.0009326151,0.00036354622,0.0060955477,0.0074676364,0.0038141103,0.00024501552,0.000036015266,0.01947986,1.5250313e-8,0.013682302,0.008623706,0.93925965],"study_design_scores_gemma":[0.00073055323,0.00034170513,0.0004881805,0.005869691,0.0075003076,0.0000839034,0.000012834066,0.072782375,4.92145e-10,0.64128387,0.2705413,0.00036527822],"about_ca_topic_score_codex":0.00006858219,"about_ca_topic_score_gemma":0.000014040051,"teacher_disagreement_score":0.93889433,"about_ca_system_score_codex":0.00018522942,"about_ca_system_score_gemma":0.0013043123,"threshold_uncertainty_score":0.9998119},"labels":[],"label_agreement":null},{"id":"W3113503952","doi":"10.1016/j.jclinepi.2020.09.016","title":"Erratum to “What to do with all the AGREEs? The AGREE Portfolio of tools to support the guideline enterprise” [Journal of Clinical Epidemiology 125C (2020) 191-197]","year":2020,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; McMaster University; North York General Hospital; Juravinski Cancer Centre; University of Ottawa","funders":"","keywords":"Guideline; Portfolio; Medical education; Psychology; Political science; Medicine; Business; Law; Finance","score_opus":0.49823768358886694,"score_gpt":0.5906480917213064,"score_spread":0.09241040813243945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113503952","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.010410572,0.003243317,0.027996155,0.8855493,0.067926675,0.0032107234,0.00013498671,0.000023602524,0.0015046771],"genre_scores_gemma":[0.019498967,0.033851933,0.05595962,0.8051926,0.07730519,0.000068276255,0.0002775712,0.00032549855,0.007520355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.86102897,0.044794705,0.08652249,0.002167525,0.00307338,0.0024129255],"domain_scores_gemma":[0.41676694,0.4729869,0.087195344,0.005530043,0.011738348,0.0057824356],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.2694089,0.0013030438,0.016817234,0.00051236013,0.00021250926,0.0000893072,0.004809286,0.0025684286,0.0012311345],"category_scores_gemma":[0.77827466,0.0005761076,0.005993958,0.0012314375,0.0016432512,0.0005527944,0.0016048793,0.017150804,0.00021345423],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014739977,0.00060264184,0.03775862,0.00009833148,0.0032116238,0.0006335889,0.0003045811,0.0006774335,0.0000050034105,0.00019915003,0.8528103,0.088958696],"study_design_scores_gemma":[0.004083153,0.029178292,0.090098344,0.0013917575,0.0039138314,0.0037485494,0.0015893326,0.00019316582,0.0000014582764,0.0023138928,0.8630161,0.00047210118],"about_ca_topic_score_codex":0.00018457342,"about_ca_topic_score_gemma":0.00037733957,"teacher_disagreement_score":0.5088657,"about_ca_system_score_codex":0.00023298775,"about_ca_system_score_gemma":0.0072865514,"threshold_uncertainty_score":0.9999721},"labels":[],"label_agreement":null},{"id":"W3115955909","doi":"10.1016/j.jclinepi.2020.12.025","title":"The movement for adopting or adapting clinical guidelines and recommendations","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"MEDLINE; Movement (music); Medicine; Political science","score_opus":0.866602208224401,"score_gpt":0.6856403647273035,"score_spread":0.18096184349709754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115955909","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.00045948155,0.0009823521,0.027586514,0.9639378,0.005982135,0.0009383476,0.000045147637,0.00002464533,0.000043548986],"genre_scores_gemma":[0.00006145026,0.014007872,0.2147246,0.72681886,0.043711204,0.00002232039,0.000099200945,0.000060637787,0.0004938553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95415485,0.008834331,0.034937844,0.00080451305,0.0005233935,0.0007450686],"domain_scores_gemma":[0.40469864,0.56621486,0.02466428,0.0006664235,0.0031318364,0.0006239872],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10057722,0.0004303991,0.0050393385,0.000108227905,0.00031274965,0.000040964853,0.00047768984,0.0014006294,0.0000987586],"category_scores_gemma":[0.830837,0.00023881905,0.0020222173,0.00015016462,0.0005463269,0.00015554085,0.00028113148,0.0077795135,0.000012883646],"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":[0.0018079515,0.00006172574,0.0147118345,0.000113205184,0.0007291043,0.00010660512,0.000008507969,0.000004954553,4.5403849e-7,0.00007221997,0.74288106,0.23950236],"study_design_scores_gemma":[0.004362468,0.0048568943,0.0029886991,0.00054135255,0.0015325632,0.00018949891,0.00028922182,0.0029523822,2.5973478e-7,0.004484071,0.97758865,0.00021392974],"about_ca_topic_score_codex":0.000027137323,"about_ca_topic_score_gemma":0.000038797316,"teacher_disagreement_score":0.73025984,"about_ca_system_score_codex":0.00007297362,"about_ca_system_score_gemma":0.0015486019,"threshold_uncertainty_score":0.99989575},"labels":[],"label_agreement":null},{"id":"W3123139272","doi":"10.1016/j.jclinepi.2021.01.001","title":"Challenges in applying the GRADE approach in public health guidelines and systematic reviews: a concept article from the GRADE Public Health Group","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Cochrane; McMaster University; Impact","funders":"World Health Organization; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Government of the United Kingdom; Global Challenges Research Fund; Medical Research Council; Masarykova Univerzita","keywords":"Public health; Systematic review; Guideline; Thematic analysis; Management science; Nominal group technique; MEDLINE; Psychology; Medicine; Knowledge management; Medical education; Public relations; Computer science; Qualitative research; Political science; Sociology; Engineering; Nursing; Social science","score_opus":0.9135985250287794,"score_gpt":0.6447142120824063,"score_spread":0.26888431294637305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123139272","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":[0.04331419,0.15206085,0.0069374456,0.7952192,0.0005336957,0.0018994949,0.0000042656234,0.000010683478,0.000020212807],"genre_scores_gemma":[0.6326303,0.194899,0.025070265,0.14547154,0.001670422,0.00019390615,0.000027924352,0.000029624243,0.0000070351584],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.88156766,0.08401933,0.031348877,0.0009815709,0.0007968915,0.0012856796],"domain_scores_gemma":[0.8106543,0.17606926,0.010904796,0.0009871535,0.00057137123,0.0008131472],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21459481,0.0002529034,0.0046252706,0.000121273224,0.00011790732,0.000036545516,0.00038370138,0.0002442097,0.00002250773],"category_scores_gemma":[0.5186501,0.00012888195,0.00051104906,0.00051122124,0.00034822017,0.00029664964,0.00018917232,0.0022420797,0.0000052304467],"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":[0.00021327894,0.00243087,0.47254607,0.0050048167,0.00054907275,0.000091566944,0.0035779788,0.000070502545,0.00001005206,0.015465939,0.016515365,0.4835245],"study_design_scores_gemma":[0.010746044,0.0018025077,0.83237076,0.0073291566,0.0002277219,0.0016732255,0.028995499,0.013248205,4.0597948e-7,0.017107569,0.08616954,0.00032936299],"about_ca_topic_score_codex":0.00046051116,"about_ca_topic_score_gemma":0.001409425,"teacher_disagreement_score":0.6497476,"about_ca_system_score_codex":0.00018926433,"about_ca_system_score_gemma":0.0012094467,"threshold_uncertainty_score":0.9740845},"labels":[],"label_agreement":null},{"id":"W3123445536","doi":"10.1016/j.jclinepi.2021.05.026","title":"The impact of gender on researchers’ assessment: A randomized controlled trial","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diversity and Career in Medicine","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Medicine; Curriculum; Test (biology); Poisson regression; Psychology; Pedagogy; Surgery; Environmental health","score_opus":0.5552186311346601,"score_gpt":0.6364482714848058,"score_spread":0.08122964035014568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123445536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7856993,0.002667164,0.0012390708,0.07227096,0.00724811,0.0015017717,0.000005278178,0.00000954718,0.12935878],"genre_scores_gemma":[0.98595977,0.008490718,0.00042111002,0.001585472,0.0023894159,0.00000574321,9.2379094e-7,0.000004202499,0.0011426539],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.92882115,0.065606624,0.0040147593,0.00015613947,0.0009945956,0.00040673683],"domain_scores_gemma":[0.6751144,0.31992716,0.003305248,0.00022070543,0.0010484942,0.00038399827],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2791015,0.00008298804,0.0038566364,0.000055938053,0.00022466021,0.000018207578,0.0005553708,0.00027208406,0.00053412555],"category_scores_gemma":[0.51809305,0.000038243044,0.0027282962,0.00014677946,0.0018752085,0.00005762482,0.00006248779,0.0011411477,0.0000053251883],"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":[0.9211915,0.00030317178,0.0051053097,0.000002468249,0.0013111487,0.000043588527,0.00046420287,0.0000709664,0.0000013668948,0.04969156,0.01819562,0.0036190639],"study_design_scores_gemma":[0.9344792,0.0014879955,0.0055475906,0.00003075693,0.00019649391,0.0000035724825,0.00291535,0.00010823399,3.0500001e-7,0.050277773,0.004909075,0.000043666398],"about_ca_topic_score_codex":0.00017954898,"about_ca_topic_score_gemma":0.000029663348,"teacher_disagreement_score":0.25432053,"about_ca_system_score_codex":0.00007186202,"about_ca_system_score_gemma":0.0025598258,"threshold_uncertainty_score":0.7423167},"labels":[],"label_agreement":null},{"id":"W3123655209","doi":"10.1016/j.jclinepi.2021.01.012","title":"The MethodologicAl STandards for Epidemiological Research (MASTER) scale demonstrated a unified framework for bias assessment","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Ottawa","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Epidemiology; Scale (ratio); Medicine; Psychology; Data science; Environmental health; Management science; Computer science; Geography; Engineering; Pathology","score_opus":0.9952468051792783,"score_gpt":0.8342322883289569,"score_spread":0.16101451685032142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123655209","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001391435,0.5284225,0.4601567,0.0067195166,0.002208298,0.002103089,0.0001249618,0.0000031904067,0.00024787773],"genre_scores_gemma":[0.000008929674,0.6210845,0.37509656,0.0006536051,0.0020293735,0.00030146178,0.000023733512,0.000032537297,0.00076927594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.08979548,0.76110274,0.1372108,0.0029926319,0.0070078843,0.0018904463],"domain_scores_gemma":[0.00831324,0.8805874,0.08744124,0.004859119,0.017720321,0.001078665],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.9730609,0.0011142675,0.089015335,0.00069061405,0.0008773278,0.0006490329,0.008263671,0.0039739427,0.001215993],"category_scores_gemma":[0.9909374,0.00036106058,0.047719985,0.0024168594,0.0018684169,0.00013179849,0.00078218774,0.0077567124,0.000082753366],"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":[0.00014691889,0.00015109208,0.0015384397,0.0010316408,0.0018933814,0.000015578224,0.000007036806,0.00002145133,1.8875973e-8,0.09208643,0.15070371,0.75240433],"study_design_scores_gemma":[0.00031190237,0.0012310502,0.00029721795,0.0029087965,0.0016679197,0.00013517425,0.00015207069,0.0008124098,1.5571315e-8,0.31240958,0.679854,0.00021989511],"about_ca_topic_score_codex":0.0000017639543,"about_ca_topic_score_gemma":0.000011069205,"teacher_disagreement_score":0.7521844,"about_ca_system_score_codex":0.00028305355,"about_ca_system_score_gemma":0.00597675,"threshold_uncertainty_score":0.9998841},"labels":[],"label_agreement":null},{"id":"W3126226315","doi":"10.1016/j.jclinepi.2021.02.003","title":"Updating guidance for reporting systematic reviews: development of the PRISMA 2020 statement","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2856,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Ottawa Hospital; Wilfrid Laurier University; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council; Australian Research Council; University of Ottawa","keywords":"Checklist; Systematic review; Guideline; CLARITY; Statement (logic); MEDLINE; Medical education; Management science; Medicine; Computer science; Psychology; Political science; Engineering; Pathology","score_opus":0.952323577334981,"score_gpt":0.7087015725636854,"score_spread":0.24362200477129559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126226315","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18163355,0.027969422,0.75635874,0.02407151,0.005355551,0.0034240303,0.0000061985766,0.000002735234,0.0011782657],"genre_scores_gemma":[0.12981616,0.0008868822,0.8606625,0.004251851,0.0007356395,0.000088290144,0.0000021551095,0.000018423565,0.0035380675],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.36488378,0.21412139,0.41499454,0.0012193805,0.0041909376,0.0005899709],"domain_scores_gemma":[0.06348605,0.343419,0.58032763,0.0043665436,0.008038027,0.0003627752],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86671543,0.00022999365,0.020059112,0.000076123586,0.00013368526,0.000055841905,0.0017425676,0.00015298075,0.000584194],"category_scores_gemma":[0.97535676,0.00008201712,0.0073930616,0.0006279586,0.00009090945,0.00010925719,0.0002633225,0.0004324723,0.00006948917],"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":[0.000060076567,0.00040310825,0.526326,0.02726666,0.0027664069,0.00003913825,0.0010457278,0.00082690775,0.00020767987,0.0064552776,0.34152696,0.093076065],"study_design_scores_gemma":[0.0014245459,0.00037037415,0.1546526,0.027064923,0.002148891,0.00059513387,0.0030314997,0.010996271,0.00027370022,0.06184815,0.73708165,0.0005122789],"about_ca_topic_score_codex":5.1929055e-7,"about_ca_topic_score_gemma":0.0000083439445,"teacher_disagreement_score":0.3955547,"about_ca_system_score_codex":0.000042529064,"about_ca_system_score_gemma":0.0007617915,"threshold_uncertainty_score":0.99448913},"labels":[],"label_agreement":null},{"id":"W3126658456","doi":"10.1016/j.jclinepi.2021.01.026","title":"Patient reported outcome measures in clinical trials should be initially analyzed as continuous outcomes for statistical significance and responder analyses should be reserved as secondary analyses","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Placebo; Sample size determination; Sertraline; Statistical significance; Internal medicine; Randomized controlled trial; Clinical trial; Student's t-test; Kidney disease; Physical therapy; Statistics; Antidepressant; Mathematics","score_opus":0.9814801580777365,"score_gpt":0.7622337642869753,"score_spread":0.21924639379076116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126658456","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8758247,0.004929754,0.05775246,0.055640813,0.0021409802,0.0017876893,0.00027078902,0.000013652036,0.001639157],"genre_scores_gemma":[0.92526025,0.0010152532,0.04209691,0.029353114,0.0006122772,0.00005349742,0.000038067166,0.000045726803,0.0015248791],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.43521315,0.384403,0.1701722,0.0030927716,0.005988235,0.0011306338],"domain_scores_gemma":[0.059586484,0.8424387,0.08404249,0.0035018919,0.008707095,0.0017233632],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7597288,0.0008127558,0.043792993,0.0011209534,0.00018410508,0.00040018838,0.0017006987,0.0012395199,0.004756897],"category_scores_gemma":[0.98141056,0.0004040692,0.013391222,0.0015776686,0.0008812958,0.00040901557,0.0003801304,0.002629508,0.000040856645],"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":[0.00338525,0.000841817,0.901174,0.00008053287,0.006623811,0.0019802384,0.00011936626,0.0004015867,0.00018967278,0.0026151,0.049951103,0.032637514],"study_design_scores_gemma":[0.0056173564,0.0021959865,0.87535185,0.0001267263,0.0047069625,0.00046253475,0.0015990449,0.0019510618,0.000041172243,0.062362358,0.044998042,0.00058690336],"about_ca_topic_score_codex":0.0001807829,"about_ca_topic_score_gemma":0.0004283072,"teacher_disagreement_score":0.45803568,"about_ca_system_score_codex":0.000069659254,"about_ca_system_score_gemma":0.0018750594,"threshold_uncertainty_score":0.9998411},"labels":[],"label_agreement":null},{"id":"W3127020330","doi":"10.1016/j.jclinepi.2021.02.004","title":"Methodological review showed that time-to-event outcomes are often inadequately handled in cluster randomized trials","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":21,"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 Public Health; Ottawa Hospital; University of Ottawa","funders":"Agence Nationale de la Recherche","keywords":"CRTS; Medicine; Sample size determination; Cluster randomised controlled trial; Cluster (spacecraft); Randomized controlled trial; Statistics; Internal medicine; Computer science; Mathematics","score_opus":0.9893545515730493,"score_gpt":0.7782744662550622,"score_spread":0.21108008531798705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127020330","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007882122,0.93421334,0.030555768,0.027347876,0.0022791945,0.0051835245,0.000027102584,0.0000038115213,0.00038148402],"genre_scores_gemma":[0.0000020744421,0.93754554,0.034730457,0.02076097,0.0007852876,0.0002197235,0.000017496834,0.000041495703,0.0058969394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.029220555,0.76368773,0.20003341,0.0020867058,0.0041996194,0.00077199144],"domain_scores_gemma":[0.008755832,0.7863463,0.19720119,0.0041285004,0.0025475598,0.0010205792],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9753419,0.0015011082,0.34773186,0.0014570715,0.000071618306,0.00023366993,0.0059150276,0.0021243307,0.0286039],"category_scores_gemma":[0.9951221,0.0005110334,0.110318914,0.002138673,0.00041402061,0.00020245744,0.00089012575,0.0038074458,0.0048830975],"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":[0.0012645362,0.00019650992,0.0008736222,0.005207759,0.004290696,0.00013920115,0.000007865986,0.000022266533,4.782194e-9,0.00013162149,0.22607417,0.76179177],"study_design_scores_gemma":[0.012818701,0.0001611875,0.000345668,0.0471701,0.012494439,0.00023833098,0.000011506326,0.00009909657,6.5786625e-9,0.005380275,0.92085475,0.00042592437],"about_ca_topic_score_codex":0.000004133973,"about_ca_topic_score_gemma":0.000008220183,"teacher_disagreement_score":0.76136583,"about_ca_system_score_codex":0.00013910275,"about_ca_system_score_gemma":0.001112191,"threshold_uncertainty_score":0.9997738},"labels":[],"label_agreement":null},{"id":"W3127452838","doi":"10.1016/j.jclinepi.2021.01.020","title":"Meta-epidemiological study of publication integrity, and quality of conduct and reporting of randomized trials included in a systematic review of low back pain","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University","funders":"Nova Scotia Health Research Foundation","keywords":"Epidemiology; Medicine; Randomized controlled trial; Meta-analysis; Systematic review; Alternative medicine; Physical therapy; MEDLINE; Quality (philosophy); Family medicine; Pathology; Biology","score_opus":0.9912844200426721,"score_gpt":0.7778416060630851,"score_spread":0.2134428139795871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127452838","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017830638,0.9876224,0.002560011,0.00088209426,0.00021088621,0.0068671615,0.000025385187,7.712799e-7,0.000048267364],"genre_scores_gemma":[0.0020465418,0.98891747,0.008407664,0.0003507638,0.00006961629,0.00012989258,0.000010565622,0.000012728986,0.000054773227],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.004704196,0.6517854,0.3401321,0.0009584415,0.0021985346,0.00022136378],"domain_scores_gemma":[0.0021575436,0.5635743,0.4261558,0.0021802548,0.0057305866,0.00020150137],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.98813087,0.0007863164,0.38129476,0.00097175833,0.000023499506,0.000029349081,0.0019604205,0.0010188346,0.0009279879],"category_scores_gemma":[0.9980498,0.00027367007,0.03826809,0.0017661554,0.000845027,0.0001664101,0.00058196735,0.0018909761,0.0000026953708],"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":[0.000592596,0.00087014795,0.0068263626,0.9433362,0.022599474,0.000005820507,0.000085233274,0.0000022006438,4.074282e-7,0.0015120425,0.0013156793,0.022853835],"study_design_scores_gemma":[0.017903926,0.0016790562,0.0010618689,0.8426777,0.120287076,0.00021255163,0.00079520495,0.00028141093,3.4891593e-7,0.011826768,0.00278969,0.0004843819],"about_ca_topic_score_codex":0.00007620513,"about_ca_topic_score_gemma":0.000024271305,"teacher_disagreement_score":0.34302667,"about_ca_system_score_codex":0.000030558997,"about_ca_system_score_gemma":0.0008020817,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W3128032696","doi":"10.1016/j.jclinepi.2021.01.019","title":"A conversation on health research collaborations and career with Dr. Gordon Guyatt: A commentary","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare cost, quality, practices","field":"Health Professions","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":"Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Conversation; Medical education; Coursework; Psychology; Multidisciplinary approach; Interpersonal communication; Capstone; Session (web analytics); Sociology; Medicine; Social psychology; Social science; Computer science","score_opus":0.9616696195844868,"score_gpt":0.7529541212475688,"score_spread":0.20871549833691805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128032696","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":[0.3133173,0.0009409651,0.00063182606,0.6832002,0.0010760486,0.00041253472,0.000025514906,0.0000110261835,0.00038460878],"genre_scores_gemma":[0.5453318,0.008130262,0.008263336,0.43547875,0.0024062183,0.000037397833,0.000041145493,0.000035537894,0.0002755566],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8852901,0.10791171,0.005137702,0.00039411976,0.00053509243,0.0007312641],"domain_scores_gemma":[0.77156353,0.21866098,0.0046035703,0.0005194532,0.0036253815,0.0010270616],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13508582,0.0001533871,0.0019062373,0.0001998842,0.00076043763,0.00001004134,0.00019935501,0.0005005945,0.00020373579],"category_scores_gemma":[0.17555504,0.00011197007,0.00012575052,0.0005065204,0.0005128112,0.0002492606,0.00013888093,0.0053597772,0.00005316073],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001238616,0.00031941105,0.72029823,0.00027572727,0.00013970383,0.00007260686,0.002187673,0.000015502748,0.000003441217,0.008039397,0.25716925,0.01024042],"study_design_scores_gemma":[0.0036456885,0.005250405,0.56214345,0.0010271673,0.00004599962,0.00006799251,0.019427234,0.00016072199,0.0000023066389,0.008870581,0.39921412,0.00014435053],"about_ca_topic_score_codex":0.0011799557,"about_ca_topic_score_gemma":0.0051603606,"teacher_disagreement_score":0.24772143,"about_ca_system_score_codex":0.0003855744,"about_ca_system_score_gemma":0.005809301,"threshold_uncertainty_score":0.99982685},"labels":[],"label_agreement":null},{"id":"W3128850065","doi":"10.1016/j.jclinepi.2021.01.018","title":"The impact of gender on scientific writing: An observational study of grant proposals","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ottawa Hospital","funders":"","keywords":"Observational study; Inclusion (mineral); Psychology; English language; Curriculum; Tone (literature); Medical education; Social psychology; Medicine; Mathematics education; Pedagogy; Linguistics","score_opus":0.9770931054240265,"score_gpt":0.7804160686956477,"score_spread":0.19667703672837877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128850065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956257,0.0005088069,0.0005241336,0.0016495811,0.0012436563,0.00014291098,0.000014240681,0.0000015048178,0.00028948265],"genre_scores_gemma":[0.99805945,0.00016418795,0.0012209025,0.00011832529,0.00024036269,8.521875e-7,0.0000011877914,0.0000052084297,0.00018950694],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95952696,0.018447332,0.012819061,0.00076982187,0.0077641574,0.0006726739],"domain_scores_gemma":[0.5428513,0.4170698,0.010564758,0.001833872,0.026713256,0.000967007],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3714783,0.00011920015,0.0017751188,0.0069832243,0.00022650273,0.00023700861,0.002242755,0.00017190863,0.0002139379],"category_scores_gemma":[0.7190562,0.00005277173,0.001005624,0.033383675,0.0008242397,0.0002915061,0.00035245763,0.0008033774,0.000012527256],"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":[0.00026463307,0.0022548502,0.9542604,0.0000024756712,0.000114563,0.000021418335,0.000092300375,0.0012501593,0.00022887772,0.0020414966,0.006806043,0.03266276],"study_design_scores_gemma":[0.00083906786,0.004164272,0.9445912,0.000009896587,0.000011618052,0.000023817413,0.0009545124,0.003829844,0.00004640884,0.04499982,0.0004791346,0.00005037485],"about_ca_topic_score_codex":0.00004049791,"about_ca_topic_score_gemma":0.000016671667,"teacher_disagreement_score":0.41667566,"about_ca_system_score_codex":0.000040600156,"about_ca_system_score_gemma":0.0017232066,"threshold_uncertainty_score":0.98716223},"labels":[],"label_agreement":null},{"id":"W3130366085","doi":"10.1016/j.jclinepi.2021.02.012","title":"A proposed framework to guide evidence synthesis practice for meta-analysis with zero-events studies","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":119,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Health and Medical Research Council; Australian Research Council; Medical Research Council","keywords":"Meta-analysis; Zero (linguistics); Computer science; Systematic review; MEDLINE; Management science; Data science; Medicine; Engineering","score_opus":0.971732739367156,"score_gpt":0.7545947620858241,"score_spread":0.21713797728133188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130366085","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":[0.0062466715,0.017183792,0.81931573,0.15580305,0.0006080235,0.0006316492,0.0000132054265,0.0000028334505,0.00019503792],"genre_scores_gemma":[0.07598507,0.0014705432,0.8950612,0.022100486,0.00046424413,0.000113942304,5.7842016e-7,0.0000186023,0.0047853366],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.70869756,0.21424502,0.06908827,0.0020269365,0.0052654417,0.00067678216],"domain_scores_gemma":[0.022211239,0.89811224,0.055646278,0.004317467,0.018957105,0.0007556612],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.722029,0.00044587904,0.03839309,0.0005556308,0.00015987527,0.00014713297,0.0024136463,0.00033623664,0.0029326188],"category_scores_gemma":[0.9903779,0.00016881166,0.0249345,0.0031530566,0.00019042692,0.0005012047,0.0002739714,0.0007812796,0.00034210455],"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":[0.00082977297,0.0006050245,0.07945089,0.00012505933,0.6620307,0.00016968606,0.00034218776,0.00784287,0.000005310543,0.0073379227,0.22943486,0.011825732],"study_design_scores_gemma":[0.00029412788,0.0013108201,0.008896799,0.00018902398,0.610489,0.00021516731,0.0016556092,0.00095831876,0.000020684398,0.09109833,0.2845223,0.0003498128],"about_ca_topic_score_codex":0.000006494738,"about_ca_topic_score_gemma":0.000037434587,"teacher_disagreement_score":0.6864863,"about_ca_system_score_codex":0.000056254783,"about_ca_system_score_gemma":0.00064678455,"threshold_uncertainty_score":0.9979788},"labels":[],"label_agreement":null},{"id":"W3130770662","doi":"10.1016/j.jclinepi.2021.02.013","title":"Commentary: Online Platform of Minimal Important Difference estimates for patient reported outcomes: potential and challenges","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Treasury Board of Canada Secretariat; University of Toronto","funders":"","keywords":"MEDLINE; Medicine; Value (mathematics); Computer science; Data science; Psychology; Actuarial science; Business; Political science; Law","score_opus":0.7426981341542074,"score_gpt":0.5493508663577381,"score_spread":0.19334726779646927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130770662","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":[0.117106855,0.02276029,0.0013100294,0.8545249,0.0028953254,0.00046856067,0.00090897904,0.000007665929,0.000017374648],"genre_scores_gemma":[0.007111449,0.020107912,0.03956182,0.9281596,0.0044610356,0.000029869152,0.0004476661,0.000065939974,0.000054727163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9591383,0.0017709507,0.03765374,0.00073265936,0.00014219045,0.0005622028],"domain_scores_gemma":[0.8791961,0.06786326,0.05166173,0.0006193832,0.00037388166,0.00028564403],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06146147,0.00041463363,0.0104822265,0.00033596766,0.00006601274,0.000014520514,0.00041387978,0.0014550512,0.00008983154],"category_scores_gemma":[0.15703292,0.00038134327,0.0013233762,0.000051156854,0.00034470964,0.00014932823,0.00014950256,0.001829079,0.000003693515],"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":[0.00022284458,0.0004831471,0.33666563,0.002169077,0.002096123,0.00011960325,0.00024411021,0.000025170206,3.4801224e-7,0.001899403,0.65403116,0.0020433876],"study_design_scores_gemma":[0.0042210715,0.0034661111,0.41254982,0.0009960645,0.00037778664,0.0003948702,0.0006613503,0.003847502,7.9639585e-7,0.075194865,0.4975557,0.00073405163],"about_ca_topic_score_codex":0.00017225402,"about_ca_topic_score_gemma":0.000045601217,"teacher_disagreement_score":0.15647545,"about_ca_system_score_codex":0.00015006243,"about_ca_system_score_gemma":0.00035395572,"threshold_uncertainty_score":0.99986386},"labels":[],"label_agreement":null},{"id":"W3132345133","doi":"10.1016/j.jclinepi.2021.02.010","title":"Use of GRADE in evidence syntheses published in high-impact-factor nutrition journals: A methodological survey","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":29,"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":"Certainty; Randomized controlled trial; Medicine; Meta-analysis; Impact factor; Internal medicine; Mathematics","score_opus":0.9933118149706269,"score_gpt":0.76347348769658,"score_spread":0.22983832727404696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132345133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9577529,0.007186509,0.02109133,0.012874057,0.00080981565,0.00023774187,0.000026571937,0.0000011084436,0.000019952273],"genre_scores_gemma":[0.9422333,0.0054977485,0.05102148,0.00088417367,0.00026067247,0.0000046509895,0.0000015955783,0.000007814285,0.000088554574],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.1774245,0.72240454,0.09432298,0.0012902425,0.003864147,0.00069357763],"domain_scores_gemma":[0.049510963,0.89866346,0.044854153,0.0019593234,0.004484211,0.0005278577],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8097677,0.00031535912,0.022128273,0.0010787974,0.000029114737,0.00024500568,0.0018995907,0.00063294516,0.009693976],"category_scores_gemma":[0.9927271,0.00013956479,0.0056437775,0.0026871026,0.00027598802,0.0012419852,0.00021843416,0.001817601,0.000052278814],"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":[0.00026364735,0.0005792751,0.9725313,0.000035940393,0.00019928755,0.000119944605,0.00003209696,0.0006720285,0.000059842678,0.00026719918,0.0112581765,0.013981222],"study_design_scores_gemma":[0.00041862953,0.00033431823,0.9619062,0.00097299594,0.000077396006,0.00016278324,0.00007114001,0.0014335229,0.000013799555,0.032863583,0.0016340404,0.00011159334],"about_ca_topic_score_codex":0.00024193367,"about_ca_topic_score_gemma":0.00060354377,"teacher_disagreement_score":0.18295936,"about_ca_system_score_codex":0.00007794742,"about_ca_system_score_gemma":0.0005669877,"threshold_uncertainty_score":0.99238926},"labels":[],"label_agreement":null},{"id":"W3133671156","doi":"10.1016/j.jclinepi.2021.03.005","title":"The methodological quality is insufficient in clinical practice guidelines in the context of COVID-19: systematic review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 British Columbia; Research Canada","funders":"Vienna Science and Technology Fund","keywords":"Coronavirus disease 2019 (COVID-19); Context (archaeology); Systematic review; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Medicine; Quality (philosophy); Virology; Political science; Geography; Pathology; Outbreak; Disease","score_opus":0.9503954303746001,"score_gpt":0.8003138229141645,"score_spread":0.15008160746043553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133671156","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016992657,0.7845984,0.0016104747,0.20911151,0.0015165018,0.003055242,0.000022070579,0.0000058176047,0.000062971776],"genre_scores_gemma":[0.0000086949385,0.76172495,0.013690959,0.22345212,0.0009598214,0.00008165016,0.000024928651,0.000027551489,0.000029340104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30603546,0.5109243,0.17787866,0.0016156591,0.0024133814,0.0011325665],"domain_scores_gemma":[0.019345636,0.904514,0.06878766,0.002199025,0.004447118,0.0007065475],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7279567,0.00065055717,0.03244626,0.00024870882,0.00008890096,0.000021594684,0.0016950185,0.0016492726,0.000120639634],"category_scores_gemma":[0.9933257,0.00028128902,0.007494143,0.0012258512,0.0010634641,0.00016223737,0.00040726966,0.0081494525,0.000026191985],"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":[0.0007982027,0.0020443618,0.0013175653,0.39281327,0.0014982,0.00059736235,0.00009887202,0.0000042722513,1.24761526e-8,0.003313389,0.07216799,0.5253465],"study_design_scores_gemma":[0.0017757696,0.0013026732,0.00033649668,0.19874881,0.0075533944,0.0021904376,0.0016008293,0.00002602812,6.0581713e-9,0.0005724312,0.7856986,0.00019452417],"about_ca_topic_score_codex":0.00028613073,"about_ca_topic_score_gemma":0.00015873897,"teacher_disagreement_score":0.7135306,"about_ca_system_score_codex":0.00031572283,"about_ca_system_score_gemma":0.00807569,"threshold_uncertainty_score":0.99996394},"labels":[],"label_agreement":null},{"id":"W3133841502","doi":"10.1016/j.jclinepi.2021.02.027","title":"Vancouver Coastal Health informed COVID-19 response by applying rapid review methodology: reply to Tricco","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"","keywords":"Knowledge translation; Key (lock); Coronavirus disease 2019 (COVID-19); Public health; Unit (ring theory); 2019-20 coronavirus outbreak; Value (mathematics); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Political science; Public relations; Computer science; Medicine; Knowledge management; Psychology; Nursing; Virology; Computer security","score_opus":0.9298042477970201,"score_gpt":0.7845715293545353,"score_spread":0.14523271844248475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133841502","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012460857,0.0043879,0.04068239,0.94006777,0.010944754,0.0030252156,0.0005170344,0.00005041903,0.00019991449],"genre_scores_gemma":[0.0000034863945,0.0390335,0.054315817,0.89558846,0.0071741007,0.00034644039,0.00010153237,0.000071844035,0.0033648382],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5435058,0.4055238,0.043852355,0.0016111224,0.0016545854,0.003852331],"domain_scores_gemma":[0.23120986,0.7160567,0.045336757,0.0015491147,0.0017507708,0.0040967716],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4580278,0.0006796649,0.012009143,0.00081771234,0.00089928845,0.000009798102,0.0016739498,0.0025205535,0.0033491722],"category_scores_gemma":[0.9233418,0.0005276615,0.0015255649,0.0013242346,0.0005671859,0.0002503829,0.00067043566,0.01749285,0.0003234307],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011106582,0.000028197986,0.002963262,0.0049122064,0.00012475582,0.00018238896,0.00065452134,0.000003134313,0.0000011646338,0.000026881933,0.9809708,0.009022044],"study_design_scores_gemma":[0.0023485506,0.001720017,0.0012179732,0.0033448816,0.00009487255,0.00015640131,0.00052781135,0.0000036295025,1.7034877e-7,0.00083684165,0.9893865,0.00036236126],"about_ca_topic_score_codex":0.00092536357,"about_ca_topic_score_gemma":0.0005405157,"teacher_disagreement_score":0.465314,"about_ca_system_score_codex":0.0016308404,"about_ca_system_score_gemma":0.060579292,"threshold_uncertainty_score":0.9997175},"labels":[],"label_agreement":null},{"id":"W3134666042","doi":"10.1016/j.jclinepi.2021.03.004","title":"Will COVID-19 result in a giant step backwards for women in academic science?","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diversity and Career in Medicine","field":"Social Sciences","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":"Institute for Work & Health; Queen's University; McMaster University; University of Toronto; University of Ottawa; St. Michael's Hospital","funders":"Status of Women Canada; Ontario Institute for Cancer Research; University of Ottawa","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Betacoronavirus; Medicine; Psychology; Virology; Internal medicine","score_opus":0.4201592905406056,"score_gpt":0.582938191001399,"score_spread":0.1627789004607934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134666042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7705414,0.0008966299,0.0023889868,0.21667504,0.0033940743,0.00023101596,0.000012547581,0.0000096567,0.005850597],"genre_scores_gemma":[0.9153054,0.0073486087,0.0056769904,0.06771849,0.0023272394,0.000008287928,0.000002092638,0.000008227439,0.0016046729],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99009603,0.00499026,0.0029996599,0.00034534012,0.0006705938,0.0008981003],"domain_scores_gemma":[0.96133906,0.03544175,0.0013198667,0.00017554447,0.00050239003,0.0012213696],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20863047,0.000087953085,0.0014400567,0.00026021563,0.00015799119,0.000012614568,0.0009550124,0.00046798761,0.00016640426],"category_scores_gemma":[0.5335362,0.00007235958,0.0002533406,0.0007834681,0.0021229459,0.0003705443,0.00014783173,0.0013965501,0.0000055005057],"study_design_candidate":"observational","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":[0.0013311255,0.0003132699,0.84096044,0.00006809206,0.000047004905,0.0005155326,0.013624984,0.00041350294,0.000042292202,0.078307666,0.029179335,0.035196725],"study_design_scores_gemma":[0.0052224225,0.0007397588,0.17565319,0.00016146387,0.000021054164,0.000032483294,0.04415286,0.00030166024,0.0000022151464,0.1597259,0.6138257,0.0001613222],"about_ca_topic_score_codex":0.0003097252,"about_ca_topic_score_gemma":0.0012267556,"teacher_disagreement_score":0.6653073,"about_ca_system_score_codex":0.00067190087,"about_ca_system_score_gemma":0.0068657384,"threshold_uncertainty_score":0.9987644},"labels":[],"label_agreement":null},{"id":"W3135331978","doi":"10.1016/j.jclinepi.2021.02.025","title":"Certainty of evidence and intervention's benefits and harms are key determinants of guidelines’ recommendations","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; McMaster University; University of Toronto","funders":"Agency for Healthcare Research and Quality; Cardiff University; National Institute for Health and Care Excellence; American Society of Hematology","keywords":"Intervention (counseling); Certainty; Voting; Psychology; Actuarial science; Medicine; Family medicine; Political science; Business; Nursing","score_opus":0.8663638519486667,"score_gpt":0.6824059268349363,"score_spread":0.18395792511373044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135331978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.886686,0.0036340335,0.0021000064,0.10680381,0.0006281331,0.00011664597,0.000018222981,0.000003075905,0.000010051961],"genre_scores_gemma":[0.9155707,0.023591056,0.05417743,0.006173033,0.00041520782,0.0000017442087,0.0000076346805,0.000011548712,0.00005166149],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98603815,0.0027679177,0.010569859,0.00025941443,0.0001988961,0.00016579058],"domain_scores_gemma":[0.9105196,0.075343326,0.0101737445,0.0003243146,0.0033122976,0.0003267274],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029399293,0.000121833946,0.0021839747,0.000103872044,0.000028069318,0.0000037924876,0.00010067789,0.00028081232,0.00018448127],"category_scores_gemma":[0.5727855,0.00008535995,0.0004513414,0.00013345416,0.00026897457,0.00018962155,0.00015577313,0.00071296253,0.000001272992],"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":[0.0005300287,0.00021848823,0.7412579,0.0001642416,0.0001236379,0.000022466675,0.000022956117,0.00001655938,0.000069461006,0.00015318663,0.004572968,0.2528481],"study_design_scores_gemma":[0.003524152,0.0017500506,0.9800325,0.0032258665,0.0005752697,0.00079815416,0.00057859643,0.0015483287,0.00020631331,0.00290895,0.004763243,0.00008855852],"about_ca_topic_score_codex":0.00007852462,"about_ca_topic_score_gemma":0.00016007361,"teacher_disagreement_score":0.5433862,"about_ca_system_score_codex":0.000017468701,"about_ca_system_score_gemma":0.00025329355,"threshold_uncertainty_score":0.9994377},"labels":[],"label_agreement":null},{"id":"W3135655776","doi":"10.1016/j.jclinepi.2021.02.026","title":"GRADE notes: How to use GRADE when there is “no” evidence? A case study of the expert evidence approach","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster Children's Hospital; McMaster University; Health Sciences Centre; Impact","funders":"","keywords":"Medicine; MEDLINE; Family medicine; Psychology; Political science","score_opus":0.9718583240214864,"score_gpt":0.6896530339907196,"score_spread":0.2822052900307668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135655776","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":[0.90135306,0.007814187,0.023823235,0.06467824,0.0014588727,0.0008267157,0.0000044530025,0.0000023813284,0.000038862905],"genre_scores_gemma":[0.9496164,0.0009021108,0.036536433,0.010403265,0.00061986485,0.000019617144,1.1814856e-7,0.000014959015,0.0018872448],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7219108,0.22699857,0.04375573,0.001677849,0.0050753444,0.0005817628],"domain_scores_gemma":[0.36206833,0.58214283,0.04094959,0.0077256463,0.006213935,0.0008996918],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43650207,0.0003998534,0.01320813,0.00022640376,0.00016162205,0.00026653512,0.003700754,0.00033492173,0.0014570085],"category_scores_gemma":[0.91668785,0.00015052572,0.0068553295,0.0012936936,0.00027308858,0.00063825154,0.0006545169,0.001179749,0.00014570757],"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":[0.000094819945,0.0010477644,0.79141486,0.000058084617,0.0009549166,0.00068355846,0.004136421,0.000310993,0.00004981466,0.0001383409,0.19185811,0.009252336],"study_design_scores_gemma":[0.0036595091,0.0090280445,0.6562632,0.004631327,0.0048607998,0.020430492,0.06477671,0.023277896,0.0000896411,0.031527184,0.17993452,0.0015207152],"about_ca_topic_score_codex":0.00022012554,"about_ca_topic_score_gemma":0.00016632854,"teacher_disagreement_score":0.48018578,"about_ca_system_score_codex":0.000038022004,"about_ca_system_score_gemma":0.00043875352,"threshold_uncertainty_score":0.9994558},"labels":[],"label_agreement":null},{"id":"W3137162530","doi":"10.1016/j.jclinepi.2021.03.007","title":"Why trials lose participants: A multitrial investigation of participants’ perspectives using the theoretical domains framework","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"NIHR Imperial Biomedical Research Centre; Medical Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; National Institute for Health and Care Research; University of Aberdeen; NIHR Newcastle Biomedical Research Centre; Scottish Government","keywords":"Attendance; Clinical trial; Set (abstract data type); Medicine; Psychology; Relevance (law); Family medicine","score_opus":0.9386496870343114,"score_gpt":0.757094244292999,"score_spread":0.1815554427413124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137162530","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":[0.0029908943,0.9671455,0.009315121,0.016727824,0.002534977,0.001196972,0.000033270357,0.0000111775,0.000044287248],"genre_scores_gemma":[0.0020147893,0.9605551,0.025966968,0.003616087,0.0077218427,0.000024897156,0.0000076876695,0.00007289369,0.000019748153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8072363,0.14861073,0.038937714,0.0012846102,0.0022379428,0.0016927127],"domain_scores_gemma":[0.02400412,0.94867724,0.020742238,0.0017376551,0.003236472,0.001602268],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.38629815,0.0005766731,0.024996145,0.00030386227,0.00013255507,0.000027118142,0.0010520251,0.0047248937,0.0007519904],"category_scores_gemma":[0.9717813,0.0002898855,0.008555415,0.0007454724,0.008336521,0.00008616328,0.0004791155,0.016948115,0.000013645744],"study_design_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":[0.004665697,0.0021547535,0.008329648,0.01356508,0.012904282,0.0006438841,0.0012228297,0.0000558832,0.0000057908865,0.81793976,0.0034833117,0.13502906],"study_design_scores_gemma":[0.005970603,0.0052225487,0.00064454717,0.12932847,0.026796833,0.000498376,0.0015082955,0.00061598636,0.000006668631,0.6555747,0.17319557,0.0006374341],"about_ca_topic_score_codex":0.000022813765,"about_ca_topic_score_gemma":0.000009758962,"teacher_disagreement_score":0.80006653,"about_ca_system_score_codex":0.00022790939,"about_ca_system_score_gemma":0.008476971,"threshold_uncertainty_score":0.99995536},"labels":[],"label_agreement":null},{"id":"W3137366277","doi":"10.1016/j.jclinepi.2021.02.009","title":"Recommendation mapping of the World Health Organization's guidelines on tuberculosis: A new approach to digitizing and presenting recommendations","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Hamilton Health Sciences; McMaster University","funders":"National Institute for Health and Care Research; McMaster University; World Health Organization","keywords":"Guideline; Usability; Computer science; Process (computing); Data science; Medicine; Pathology; Human–computer interaction","score_opus":0.679436045331498,"score_gpt":0.6132541748590509,"score_spread":0.06618187047244717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137366277","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":[0.06908175,0.00010638285,0.05593636,0.87232375,0.0011306094,0.00034731653,0.0000075152266,0.000012106537,0.0010542087],"genre_scores_gemma":[0.17820385,0.0022695307,0.611721,0.20289949,0.003523948,0.000005003718,0.00012558498,0.000054708707,0.0011968798],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9886224,0.002974494,0.007664582,0.00031024232,0.00020754783,0.0002206972],"domain_scores_gemma":[0.95518154,0.035900064,0.0060616583,0.0004175676,0.0019476176,0.00049158296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020261182,0.00012855788,0.0013774472,0.00017154851,0.00010930816,0.000014840181,0.00012982628,0.00011086742,0.0002088826],"category_scores_gemma":[0.43986672,0.00009032624,0.00028130817,0.0007871172,0.000057587375,0.00016624632,0.00017153613,0.0007364119,0.0000049122023],"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":[0.00016616017,0.00053044263,0.37443045,0.00011326197,0.00032952806,0.0000024334224,0.00022588749,0.0004964095,0.00007995357,0.0022664724,0.26797196,0.35338706],"study_design_scores_gemma":[0.0043607033,0.0006460202,0.5914801,0.0012685861,0.00036806872,0.000578775,0.0018568351,0.0032055788,0.00014914878,0.00552611,0.39034042,0.00021966321],"about_ca_topic_score_codex":0.00005703435,"about_ca_topic_score_gemma":0.00005456143,"teacher_disagreement_score":0.66942424,"about_ca_system_score_codex":0.00007067984,"about_ca_system_score_gemma":0.0009334098,"threshold_uncertainty_score":0.70221615},"labels":[],"label_agreement":null},{"id":"W3141256924","doi":"10.1016/j.jclinepi.2021.03.001","title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4097,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; Public Health Ontario; University of Toronto; St. Michael's Hospital; Queen's University; McMaster University; Ottawa Hospital; Impact; University of Ottawa","funders":"National Eye Institute; National Health and Medical Research Council; National Institutes of Health; University of Ottawa; Medical Research Council; National Institute for Health and Care Research","keywords":"Checklist; Systematic review; Guideline; Statement (logic); Terminology; Presentation (obstetrics); MEDLINE; Medicine; Management science; Computer science; Medical physics; Psychology; Engineering; Pathology; Political science","score_opus":0.9529759625155869,"score_gpt":0.7323717919197811,"score_spread":0.22060417059580584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141256924","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023279086,0.039429445,0.8154419,0.11018296,0.006965286,0.00364603,0.000014613804,0.000007012853,0.0010336393],"genre_scores_gemma":[0.041190617,0.018080525,0.8553581,0.050041847,0.00783697,0.00024015148,0.00010231626,0.00009215189,0.027057325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.22484314,0.34737945,0.42225698,0.001407341,0.0033821184,0.00073097926],"domain_scores_gemma":[0.05601105,0.42439795,0.49866006,0.0066357017,0.01345266,0.00084259274],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9347234,0.0003113154,0.024589937,0.000102983366,0.0002589353,0.00027318127,0.0022897245,0.00024336275,0.0017299382],"category_scores_gemma":[0.97967863,0.00010496713,0.009267234,0.00072031503,0.0001333692,0.00025633627,0.00016589843,0.0006625035,0.00029914753],"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":[0.00004347852,0.00010103261,0.014893772,0.00074514654,0.00068402675,0.00005101028,0.000046467827,0.00018590299,0.00001034287,0.0027671326,0.9513727,0.029098997],"study_design_scores_gemma":[0.00037825052,0.0002802087,0.0018691471,0.00054044503,0.0007301054,0.00034653183,0.0004274478,0.019206744,0.0000023367825,0.054298934,0.9218008,0.00011903782],"about_ca_topic_score_codex":0.0000017871082,"about_ca_topic_score_gemma":0.000026068703,"teacher_disagreement_score":0.1688321,"about_ca_system_score_codex":0.000030555588,"about_ca_system_score_gemma":0.00045057386,"threshold_uncertainty_score":0.99918264},"labels":[],"label_agreement":null},{"id":"W3142748285","doi":"10.1016/j.jclinepi.2021.03.031","title":"Data-driven methods distort optimal cutoffs and accuracy estimates of depression screening tools: a simulation study using individual participant data","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Maternal Mental Health During Pregnancy and Postpartum","field":"Medicine","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":"Women's College Hospital; University of Toronto; University of Alberta; International Society for Equity in Health; Concordia University; University of Calgary; McGill University; Jewish General Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health; Canadian Institutes of Health Research; Merck Canada; H. Lundbeck A/S; Servier; National Center of Neurology and Psychiatry; Ministério da Saúde; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Department of Families, Housing, Community Services and Indigenous Affairs; Japan Society for the Promotion of Science; Conselho Nacional de Desenvolvimento Científico e Tecnológico; University of Oxford; Werner Otto Stiftung; Faculty of Medicine, McGill University; Pfizer; Australian Government; University of Connecticut; Chulalongkorn University; Medical Research Council; Department of Health and Social Care; McGill University Health Centre; Programme Grants for Applied Research; McGill University; Jewish General Hospital; Novo Nordisk; National Institute for Health and Care Research; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Wellcome Trust; University of Southampton; National Health and Medical Research Council; AstraZeneca; Fundação de Amparo à Pesquisa do Estado de São Paulo; Patrick and Catherine Weldon Donaghue Medical Research Foundation; National Science Foundation","keywords":"Cutoff; Statistics; Mathematics; Population; Sample size determination; Sensitivity (control systems); Youden's J statistic; Sample (material); Accuracy and precision; Medicine; Receiver operating characteristic; Physics","score_opus":0.8143274349187795,"score_gpt":0.6621871020375919,"score_spread":0.15214033288118756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142748285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92187095,0.0053844335,0.071340784,0.00048269753,0.00055618014,0.00024183502,0.00010895401,0.000007920666,0.0000062576178],"genre_scores_gemma":[0.71032,0.00026997528,0.28864604,0.00035938932,0.0003037329,9.38213e-7,0.00008484953,0.000010852502,0.0000042128095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9907921,0.004143798,0.004076575,0.00044223046,0.000252308,0.0002929637],"domain_scores_gemma":[0.9457318,0.04855795,0.0037355558,0.0011628397,0.00025899196,0.0005528692],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02085634,0.00015489243,0.0020939617,0.00006888578,0.00007877976,0.000011890993,0.00041126218,0.00018212308,0.00004522477],"category_scores_gemma":[0.11026588,0.000112017464,0.00011931635,0.00008464244,0.00014999135,0.00046191088,0.0010447963,0.0007036391,5.703387e-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":[0.001778584,0.0007964778,0.9414723,0.0005432594,0.00061951706,0.00023784564,0.00017944555,0.00665486,0.000051851308,0.000013192184,0.00004552777,0.047607154],"study_design_scores_gemma":[0.0019043806,0.00094367244,0.691144,0.0023064376,0.0016372092,0.00039087157,0.0001782255,0.30081633,0.00006195604,0.000102674945,0.00042918322,0.0000850484],"about_ca_topic_score_codex":0.000034074714,"about_ca_topic_score_gemma":0.000006288287,"teacher_disagreement_score":0.29416147,"about_ca_system_score_codex":0.000009902875,"about_ca_system_score_gemma":0.00032638386,"threshold_uncertainty_score":0.8972287},"labels":[],"label_agreement":null},{"id":"W3146722253","doi":"10.1016/j.jclinepi.2021.03.021","title":"A review of pragmatic trials found a high degree of diversity in design and scope, deficiencies in reporting and trial registry data, and poor indexing","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; University of Ottawa; Western University; Ottawa Hospital","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Scope (computer science); Diversity (politics); Search engine indexing; Medicine; Degree (music); Statistics; Computer science; Data science; Information retrieval; Mathematics; Sociology","score_opus":0.9687313912327855,"score_gpt":0.7461160419528333,"score_spread":0.2226153492799522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146722253","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":[0.0042608446,0.9915724,0.0006516522,0.0016054824,0.00029376626,0.0015591942,0.000017724933,0.0000017595046,0.000037179176],"genre_scores_gemma":[0.00026349287,0.97372663,0.025129743,0.0005528333,0.00027668898,0.000006980239,0.000011260107,0.000016565673,0.000015821872],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.83016783,0.08305859,0.08216094,0.001919813,0.0017381582,0.00095468847],"domain_scores_gemma":[0.029126264,0.9035254,0.064171195,0.0014064441,0.0012093378,0.00056132884],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.56852317,0.00030802964,0.024117118,0.00040273595,0.00004473361,0.00000889013,0.0005906281,0.0016098918,0.000019358902],"category_scores_gemma":[0.9721058,0.00020253942,0.00080151996,0.000502449,0.0015031183,0.00011779763,0.002003792,0.006073213,1.792016e-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":[0.0053972327,0.0005462046,0.025657998,0.32159454,0.000707304,0.0008048898,0.00004360535,0.0000014195168,4.142463e-7,0.00085711794,0.000608155,0.6437811],"study_design_scores_gemma":[0.02229113,0.0038836456,0.0050165015,0.9365771,0.0038364735,0.0016123691,0.000097488606,0.00008004585,1.7659994e-7,0.012895573,0.013428199,0.0002812896],"about_ca_topic_score_codex":0.00017588351,"about_ca_topic_score_gemma":0.00008684741,"teacher_disagreement_score":0.8204668,"about_ca_system_score_codex":0.00007166723,"about_ca_system_score_gemma":0.0045625125,"threshold_uncertainty_score":0.99968624},"labels":[],"label_agreement":null},{"id":"W3148417023","doi":"10.1016/j.jclinepi.2021.03.034","title":"Getting trustworthy guidelines into the hands of decision-makers and supporting their consideration of contextual factors for implementation globally: recommendation mapping of COVID-19 guidelines","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":55,"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; Cochrane; Impact; McMaster University Medical Centre","funders":"Canadian Institutes of Health Research; World Health Organization","keywords":"Contextualization; Transparency (behavior); Context (archaeology); Computer science; Guideline; Knowledge management; Process (computing); Process management; Data science; Business; Medicine","score_opus":0.6778366091659175,"score_gpt":0.6588268511399318,"score_spread":0.0190097580259857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148417023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73193496,0.00044888153,0.17602392,0.09057061,0.0005464236,0.00042148112,0.000039987306,0.000005427679,0.000008318296],"genre_scores_gemma":[0.83961964,0.0015264637,0.14628151,0.011804018,0.00058656966,0.0000052861337,0.00015403166,0.000017175513,0.0000053286626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9781869,0.0024109313,0.018465625,0.00033670492,0.00034107658,0.00025878186],"domain_scores_gemma":[0.79950213,0.17326327,0.019437442,0.00033387585,0.0071547953,0.0003085049],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05485522,0.00020528844,0.002363309,0.00016550189,0.00011388817,0.000009966513,0.00014739626,0.0002559698,0.00017706366],"category_scores_gemma":[0.680745,0.00013413343,0.00070679234,0.00023889977,0.00032280028,0.00024251144,0.00011974964,0.00038913943,1.6676893e-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":[0.0017768521,0.00013243733,0.53574157,0.0002670706,0.000612099,0.000005419174,0.0009676974,0.00047141954,0.002077814,0.0008148238,0.017221415,0.43991137],"study_design_scores_gemma":[0.058759145,0.012464985,0.43460882,0.002404893,0.0039133937,0.0011732074,0.19147342,0.048527826,0.009061024,0.12988266,0.10679043,0.0009402031],"about_ca_topic_score_codex":0.0003021603,"about_ca_topic_score_gemma":0.00048077316,"teacher_disagreement_score":0.6258898,"about_ca_system_score_codex":0.00006757869,"about_ca_system_score_gemma":0.0016702047,"threshold_uncertainty_score":0.9732255},"labels":[],"label_agreement":null},{"id":"W3149805768","doi":"","title":"Canadian Acute Respiratory Illness and Flu Scale (CARIFS) : Development of a valid measure for childhood respiratory infections.","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Respiratory viral infections research","field":"Medicine","cited_by":18,"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":"Respiratory system; Medicine; Respiratory illness; Intensive care medicine; Scale (ratio); Respiratory disease; Pediatrics; Internal medicine; Geography; Lung","score_opus":0.23255201222140193,"score_gpt":0.5045944868821503,"score_spread":0.2720424746607483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149805768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99383646,0.0012874488,0.0008874563,0.0016656165,0.00048070285,0.00061328465,0.000022507242,0.000016096066,0.0011904527],"genre_scores_gemma":[0.98242503,0.00035824932,0.006704098,0.008618851,0.0014277779,0.0000652475,0.0000054604257,0.00006325763,0.00033200553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9914067,0.002509608,0.00475216,0.00039697305,0.00033818113,0.00059638865],"domain_scores_gemma":[0.99082226,0.0052756188,0.0012146316,0.0004309365,0.0010473497,0.0012092085],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024939317,0.00024542678,0.0023525849,0.000643853,0.000304912,0.000010692251,0.00022759235,0.0006815903,0.00037002904],"category_scores_gemma":[0.022327572,0.00019234364,0.0006075975,0.00037803143,0.0004977984,0.00017305053,0.00004102068,0.0013694251,0.00002296047],"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":[0.0010825396,0.00062764925,0.6510423,0.00013138034,0.0010004076,0.000047609046,0.00023462619,0.00006336739,0.00055369793,0.00016908601,0.008368418,0.33667892],"study_design_scores_gemma":[0.003858579,0.003692902,0.67538327,0.00024090252,0.00024670444,0.00019820427,0.000045144374,0.000029150984,0.00059473625,0.0005829394,0.31492838,0.00019907345],"about_ca_topic_score_codex":0.0005627479,"about_ca_topic_score_gemma":0.006524566,"teacher_disagreement_score":0.33647984,"about_ca_system_score_codex":0.00025318592,"about_ca_system_score_gemma":0.0047549983,"threshold_uncertainty_score":0.9859078},"labels":[],"label_agreement":null},{"id":"W3152804121","doi":"10.1016/j.jclinepi.2021.03.026","title":"GRADE guidelines 32: GRADE offers guidance on choosing targets of GRADE certainty of evidence ratings","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":305,"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 Agency of Canada; McMaster University; Impact","funders":"Canadian Institutes of Health Research; Mitacs; International Life Sciences Institute; Parker Institute for Cancer Immunotherapy; Oak Foundation","keywords":"Certainty; Medicine; Medical physics; Statistics; Mathematics","score_opus":0.9148936130712134,"score_gpt":0.6506686795966241,"score_spread":0.2642249334745893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152804121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5646331,0.015373739,0.0146812955,0.40102413,0.003616384,0.00032310555,0.00008592332,0.0000146265065,0.0002477172],"genre_scores_gemma":[0.8595048,0.0070038303,0.07308806,0.05797408,0.0021371327,0.0000100168145,0.000009046652,0.000046080964,0.00022691731],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9542284,0.00806285,0.03617589,0.0007001674,0.00023916771,0.0005934986],"domain_scores_gemma":[0.8811542,0.08277827,0.033866,0.0007878522,0.00097413815,0.00043953914],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16190857,0.0002887865,0.006534679,0.00033109658,0.00009389896,0.000011990555,0.00066550163,0.0006307376,0.00018849182],"category_scores_gemma":[0.5739999,0.00026643949,0.0012550644,0.00030125616,0.000423556,0.0003272922,0.00010520517,0.0011976341,0.000058369613],"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":[0.00025142403,0.00061335653,0.7943528,0.00096812885,0.0005100557,0.00002016816,0.00046256714,0.008886826,0.00015427874,0.08782684,0.10458226,0.0013712924],"study_design_scores_gemma":[0.0045983884,0.0023656713,0.6698883,0.0047896393,0.00012348485,0.00016755547,0.0008984641,0.020614356,0.00064032647,0.22771858,0.06734161,0.0008536403],"about_ca_topic_score_codex":0.0003219833,"about_ca_topic_score_gemma":0.00003938597,"teacher_disagreement_score":0.4120913,"about_ca_system_score_codex":0.00021159947,"about_ca_system_score_gemma":0.00069797144,"threshold_uncertainty_score":0.9999788},"labels":[],"label_agreement":null},{"id":"W3153730307","doi":"10.1016/j.jclinepi.2021.03.033","title":"Shifting the focus away from binary thinking of statistical significance and towards education for key stakeholders: revisiting the debate on whether it's time to de-emphasize or get rid of statistical significance","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":21,"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; St. Joseph’s Healthcare Hamilton; Population Health Research Institute; McMaster University; Impact","funders":"","keywords":"Statistical thinking; Statistical significance; Psychology; Value (mathematics); Statistical analysis; Statistics; Mathematics; Mathematics education","score_opus":0.7716640081536473,"score_gpt":0.598722625629407,"score_spread":0.1729413825242403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153730307","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":[0.15478332,0.002054606,0.77215075,0.0686307,0.00055803644,0.0008773009,0.00025693508,0.0000026765154,0.0006856861],"genre_scores_gemma":[0.70332295,0.0003302941,0.28674585,0.0077024885,0.0011780587,0.00003208799,0.000008196433,0.0000260854,0.0006539902],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91976404,0.055272605,0.02186295,0.0008483037,0.0018165719,0.00043550893],"domain_scores_gemma":[0.5224938,0.45740557,0.016256033,0.0014079635,0.0021032207,0.00033341997],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2975067,0.00026576084,0.0061997175,0.000104579776,0.0001672195,0.0001201302,0.001278299,0.00019281017,0.0023936993],"category_scores_gemma":[0.67954725,0.00010408576,0.0011675612,0.00044419375,0.000436027,0.00011281275,0.00014436775,0.0006544945,0.000039152797],"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":[0.0016859741,0.000522534,0.03567936,0.00033823404,0.0014776543,0.00005554305,0.0026391214,0.0022509377,0.0008228245,0.04017326,0.12286203,0.7914925],"study_design_scores_gemma":[0.0021014614,0.0032630374,0.2500092,0.0024142638,0.0024059028,0.00016265508,0.008040365,0.05359699,0.00027696518,0.5719024,0.10516143,0.00066529476],"about_ca_topic_score_codex":0.00005763344,"about_ca_topic_score_gemma":0.000020091053,"teacher_disagreement_score":0.7908272,"about_ca_system_score_codex":0.000039676845,"about_ca_system_score_gemma":0.0012039922,"threshold_uncertainty_score":0.9985182},"labels":[],"label_agreement":null},{"id":"W3154361643","doi":"10.1016/j.jclinepi.2021.03.032","title":"COVID-19 and the research scholarship ecosystem: help!","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Research Data Management Practices","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Data sharing; Coronavirus disease 2019 (COVID-19); Scholarship; Context (archaeology); Biomedicine; Public relations; Pandemic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Best practice; Political science; MEDLINE; Business; Knowledge management; Medicine; Alternative medicine; Computer science; Geography","score_opus":0.7883535317563503,"score_gpt":0.6525941602921894,"score_spread":0.13575937146416084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154361643","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02396934,0.0050686174,0.31156802,0.65565455,0.0012422784,0.0002239655,0.0000029325925,0.000016668433,0.0022536286],"genre_scores_gemma":[0.74546117,0.072101496,0.109947145,0.06730282,0.002703428,0.000020719146,0.000003246781,0.000022608068,0.0024373804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.90075654,0.09315826,0.003832375,0.00062117854,0.0009559326,0.0006757397],"domain_scores_gemma":[0.45706904,0.5336421,0.0034019279,0.0023696057,0.0016859983,0.0018313532],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39498416,0.00010397042,0.0012940036,0.00020562748,0.00029633794,0.00057948934,0.003343124,0.00018517389,0.000048387174],"category_scores_gemma":[0.81577796,0.00005866299,0.00031125944,0.0006027142,0.0007324037,0.005828948,0.002385508,0.0028876057,0.00004274549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028895852,0.00010051461,0.049091857,0.00009189934,0.00017309029,0.0006053902,0.00004666871,0.000060723178,0.0000044057633,0.9165981,0.020785246,0.012153192],"study_design_scores_gemma":[0.003035719,0.00042430396,0.039733227,0.00005861125,0.0000243321,0.0008954713,0.00014935956,0.003657292,0.0000054468187,0.26129135,0.69062865,0.00009622364],"about_ca_topic_score_codex":0.000030197682,"about_ca_topic_score_gemma":0.00006909414,"teacher_disagreement_score":0.7214918,"about_ca_system_score_codex":0.00006416355,"about_ca_system_score_gemma":0.0017061045,"threshold_uncertainty_score":0.9994128},"labels":[],"label_agreement":null},{"id":"W3156592931","doi":"10.1016/j.jclinepi.2021.04.001","title":"GRADE Guidance: 31. Assessing the certainty across a body of evidence for comparative test accuracy","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":67,"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; Cochrane; Impact; McMaster University Medical Centre","funders":"Academisch Medisch Centrum; ACE Foundation; McMaster University","keywords":"Test (biology); Certainty; Medicine; Statistics; Medical physics; Mathematics; Biology","score_opus":0.9825961619498428,"score_gpt":0.7889337429083145,"score_spread":0.19366241904152826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156592931","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68788177,0.010883329,0.23658718,0.06132388,0.0022243697,0.0006500399,0.000030279889,0.0000022242107,0.00041695044],"genre_scores_gemma":[0.9563865,0.00054542895,0.038172357,0.0032209272,0.0007769553,0.000010998216,9.618402e-7,0.000006390882,0.0008794709],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.76968366,0.14242956,0.08261061,0.0012159481,0.003347015,0.0007132075],"domain_scores_gemma":[0.026915615,0.9038513,0.059665896,0.002411288,0.0068726065,0.0002833289],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.64218825,0.00024964134,0.013503112,0.00007714931,0.00020468484,0.00020468114,0.0025373253,0.00023662939,0.0005609734],"category_scores_gemma":[0.9720685,0.0000849553,0.0071153496,0.0007869559,0.000566716,0.00044347256,0.00023702534,0.00081520295,0.000072227274],"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":[0.00008019479,0.00033286226,0.7848622,0.00009475442,0.0007135142,0.000019633353,0.00045396254,0.00097642554,0.00029250744,0.0022616424,0.19249056,0.017421737],"study_design_scores_gemma":[0.00080569665,0.0005154612,0.768615,0.00058086106,0.0005393695,0.00016814626,0.0023827937,0.02578723,0.00009659589,0.065419726,0.13491932,0.00016978815],"about_ca_topic_score_codex":0.000006385981,"about_ca_topic_score_gemma":0.000015672476,"teacher_disagreement_score":0.7614217,"about_ca_system_score_codex":0.000027732796,"about_ca_system_score_gemma":0.00070218235,"threshold_uncertainty_score":0.9230457},"labels":[],"label_agreement":null},{"id":"W3158443220","doi":"10.1016/j.jclinepi.2021.04.011","title":"Intent to share Annals of Internal Medicine's trial data was not associated with data re-use","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital","funders":"Agence Nationale de la Recherche","keywords":"Randomized controlled trial; Annals; Medicine; Meta-analysis; MEDLINE; Hazard ratio; Family medicine; Internal medicine; Confidence interval; Geography","score_opus":0.9889106146198559,"score_gpt":0.7496580865869323,"score_spread":0.23925252803292352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158443220","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6059795,0.0025972894,0.09334042,0.28421888,0.008867699,0.001281296,0.001490998,0.0000076038673,0.0022162832],"genre_scores_gemma":[0.8642837,0.0015150021,0.038938884,0.081093684,0.005422707,0.0000068217387,0.0004810725,0.00005242974,0.00820572],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77202064,0.13973,0.08002261,0.0020973254,0.005548347,0.00058105023],"domain_scores_gemma":[0.07464646,0.7677179,0.11576094,0.02364082,0.016382087,0.0018517766],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6730331,0.0003038487,0.017836327,0.00033021357,0.000046591384,0.000103116574,0.009096929,0.00030504682,0.0081652645],"category_scores_gemma":[0.9772381,0.00012179519,0.00197688,0.0010218493,0.00030607267,0.00059402327,0.0021319126,0.0010785843,0.00016481517],"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":[0.0041612033,0.00027936476,0.09388594,0.000015700014,0.0018620039,0.00012359576,0.00006457182,0.00006992402,0.0000064058318,0.00033844172,0.8836994,0.015493402],"study_design_scores_gemma":[0.01614614,0.0054242928,0.23506795,0.0020779122,0.002011461,0.00023038167,0.00085046235,0.016355166,0.000009727691,0.007630505,0.7137962,0.00039979164],"about_ca_topic_score_codex":0.0000392629,"about_ca_topic_score_gemma":0.00025802763,"teacher_disagreement_score":0.6973742,"about_ca_system_score_codex":0.000016876813,"about_ca_system_score_gemma":0.0005427751,"threshold_uncertainty_score":0.99674493},"labels":[],"label_agreement":null},{"id":"W3160029048","doi":"10.1016/j.jclinepi.2021.04.017","title":"Customized guidance/training improved the psychometric properties of methodologically rigorous risk of bias instruments for non-randomized studies","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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":"Queen's University; Université de Montréal; University of Ottawa; Institute of Health Economics; St. Michael's Hospital; University of Manitoba; Centre Hospitalier de l’Université de Montréal; University of Toronto; George & Fay Yee Centre for Healthcare Innovation","funders":"","keywords":"Medicine; Randomized controlled trial; Reliability (semiconductor); Physical therapy; Statistic; Medical physics; Psychology; Statistics; Surgery","score_opus":0.8685239314559975,"score_gpt":0.6052991067119616,"score_spread":0.26322482474403586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160029048","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":[0.92130476,0.0063944915,0.059939843,0.008230703,0.0031535176,0.0008202739,0.000011734339,0.000004353143,0.00014029456],"genre_scores_gemma":[0.8447378,0.007174741,0.14642188,0.0011447329,0.00035587416,0.000034695528,3.376886e-7,0.000007966535,0.000121950754],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9197899,0.05810966,0.019586395,0.00063931127,0.0013792216,0.00049549463],"domain_scores_gemma":[0.31797293,0.64055556,0.030697273,0.0013556895,0.009134057,0.00028445717],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4737074,0.00024910225,0.008235257,0.00027479243,0.00014173203,0.000018038796,0.0013133329,0.00031314022,0.000057078865],"category_scores_gemma":[0.9235801,0.000099661986,0.0031655477,0.0008404949,0.0020874017,0.00014162176,0.00024299712,0.0008086676,0.0000029682787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15415882,0.0016346296,0.24556921,0.00025886757,0.007193858,0.0000050775516,0.0026465713,0.0026762492,0.00460898,0.0017209197,0.005271794,0.57425505],"study_design_scores_gemma":[0.2052322,0.0053784307,0.09562595,0.00096006045,0.0019423515,0.00005326868,0.01178065,0.011588357,0.004111021,0.65589124,0.0069460697,0.00049041095],"about_ca_topic_score_codex":0.000016385859,"about_ca_topic_score_gemma":0.000011107014,"teacher_disagreement_score":0.6541703,"about_ca_system_score_codex":0.000033540353,"about_ca_system_score_gemma":0.0004686317,"threshold_uncertainty_score":0.7691118},"labels":[],"label_agreement":null},{"id":"W3160101482","doi":"10.1016/j.jclinepi.2021.05.006","title":"PRIME-IPD SERIES Part 2. Retrieving, checking, and harmonizing data are underappreciated challenges in individual participant data meta-analyses","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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":"NIHR School for Primary Care Research; Versus Arthritis; Arthritis Research UK; Fonds de Recherche du Québec - Santé; National Institute for Health and Care Research; Chartered Society of Physiotherapy Charitable Trust","keywords":"Meta-analysis; Raw data; Scopus; Web of science; Prime (order theory); Computer science; MEDLINE; Psychology; Medicine; Mathematics; Political science; Pathology","score_opus":0.9968824841567647,"score_gpt":0.727063582579804,"score_spread":0.26981890157696076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160101482","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010320685,0.30572644,0.0012767686,0.6889527,0.0018716976,0.00041668306,0.00052956573,0.000005393361,0.00018872417],"genre_scores_gemma":[0.0141859315,0.23493056,0.053236436,0.66740334,0.021737209,0.000047366964,0.0028078898,0.00023272594,0.0054185223],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5595705,0.3257905,0.10119167,0.005209221,0.0069057005,0.0013324053],"domain_scores_gemma":[0.23110406,0.51738065,0.21203533,0.03409401,0.0043345573,0.001051387],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7337509,0.0010297787,0.050696805,0.0009141424,0.00014515004,0.00067705614,0.012942104,0.002152054,0.0036803987],"category_scores_gemma":[0.87234896,0.00048377184,0.0058786985,0.0011520409,0.00062345597,0.0012092049,0.004680445,0.0069410726,0.00008760648],"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":[0.000032342767,0.000103252736,0.026364762,0.00017621127,0.029601293,0.00069607643,0.000095943586,0.000024907991,3.8937486e-7,0.000048385064,0.93335986,0.009496603],"study_design_scores_gemma":[0.0003947082,0.00016171676,0.024316799,0.00043492462,0.039011486,0.0003083919,0.00057213375,0.0012067052,6.92677e-7,0.0051895417,0.92798567,0.00041722064],"about_ca_topic_score_codex":0.000025199754,"about_ca_topic_score_gemma":0.00033280038,"teacher_disagreement_score":0.32846645,"about_ca_system_score_codex":0.000024285115,"about_ca_system_score_gemma":0.0008085493,"threshold_uncertainty_score":0.9997614},"labels":[],"label_agreement":null},{"id":"W3161532978","doi":"10.1016/j.jclinepi.2021.05.001","title":"PRIME-IPD SERIES Part 3. The PRIME-IPD tool fills a gap in guidance for preparing IPD for analysis","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; Centre for Global Health Research; University of Toronto; Hospital for Sick Children; Bruyère; University of Ottawa","funders":"Bill and Melinda Gates Foundation","keywords":"Scopus; Deworming; Computer science; Prime (order theory); Psychology; Data science; MEDLINE; Medicine; Mathematics; Political science","score_opus":0.9151699621005248,"score_gpt":0.6649642439179964,"score_spread":0.25020571818252846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161532978","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.0030407433,0.009556108,0.2970462,0.6812371,0.0049718455,0.0029725838,0.00020119983,0.0000069363364,0.00096728554],"genre_scores_gemma":[0.003134785,0.0027009938,0.16051798,0.7560448,0.022706466,0.00078034704,0.0001968259,0.00012400698,0.05379378],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7309939,0.16065545,0.10030244,0.0027826321,0.003875615,0.0013899002],"domain_scores_gemma":[0.3627346,0.50936437,0.114053115,0.008064684,0.005440098,0.00034317534],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.65228134,0.0008390457,0.03473118,0.00089801,0.00022017068,0.00040551496,0.00516763,0.0019129408,0.0020249935],"category_scores_gemma":[0.853224,0.00036344817,0.02790115,0.001973699,0.00045685895,0.000353457,0.0004168177,0.0033472786,0.00009678325],"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":[0.00014385208,0.000073989846,0.044154115,0.00018105152,0.004945918,0.00003251935,0.00006423517,0.000842425,0.0000012258761,0.00047146573,0.93962765,0.009461545],"study_design_scores_gemma":[0.00059086,0.00036846913,0.010987253,0.00033034154,0.004570108,0.000075927084,0.00007302757,0.006391845,0.0000027263677,0.024933964,0.9513272,0.00034824418],"about_ca_topic_score_codex":0.000014727927,"about_ca_topic_score_gemma":0.00015910575,"teacher_disagreement_score":0.36825937,"about_ca_system_score_codex":0.00010302366,"about_ca_system_score_gemma":0.00093932904,"threshold_uncertainty_score":0.99988174},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","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":"W3163184725","doi":"10.1016/j.jclinepi.2021.04.016","title":"Development and application of health outcome descriptors facilitated decision-making in the production of practice guidelines","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; Impact; Cochrane","funders":"American Society of Hematology","keywords":"Grading (engineering); Guideline; Outcome (game theory); Medicine; MEDLINE; Management science; Medical education; Psychology; Engineering; Political science; Pathology","score_opus":0.8154269030275445,"score_gpt":0.6521289707657062,"score_spread":0.1632979322618383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163184725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68410254,0.0074353097,0.095765054,0.21122871,0.0010952867,0.00029786426,0.000008729838,0.000002813325,0.000063676176],"genre_scores_gemma":[0.6888694,0.0010696993,0.2912456,0.018582182,0.00020427856,0.000007987313,0.0000027685621,0.0000066936022,0.000011370472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96211815,0.0058583533,0.031360626,0.00033488695,0.00011495998,0.00021302295],"domain_scores_gemma":[0.8811345,0.08233494,0.034695547,0.0005136321,0.0011979409,0.00012341232],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29162106,0.0000917952,0.0024540536,0.0001873564,0.00005285205,0.0000045174784,0.0001900014,0.00014922791,0.000011621949],"category_scores_gemma":[0.6409738,0.000077206365,0.00015993444,0.00021089552,0.00010912008,0.00022434293,0.00003767846,0.00034481144,0.000009579054],"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":[0.000115228824,0.0003353535,0.89091194,0.00034048216,0.0001116654,0.0000014137946,0.0028754126,0.0016309635,0.0000021249205,0.028148703,0.0073944097,0.06813228],"study_design_scores_gemma":[0.00066836475,0.00021797877,0.8390118,0.00040501886,0.000012229659,0.000088041874,0.005685308,0.0018196963,0.0000021193957,0.03415985,0.11781022,0.00011935775],"about_ca_topic_score_codex":0.0001319292,"about_ca_topic_score_gemma":0.00010253115,"teacher_disagreement_score":0.34935275,"about_ca_system_score_codex":0.0001230205,"about_ca_system_score_gemma":0.000505242,"threshold_uncertainty_score":0.7294252},"labels":[],"label_agreement":null},{"id":"W3163523960","doi":"10.1016/j.jclinepi.2021.04.018","title":"Guidelines that use the GRADE approach often fail to provide complete economic information for recommendations: A systematic survey","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":9,"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; McMaster University Medical Centre; Impact; Cochrane","funders":"NCMIC Foundation","keywords":"Economic evaluation; Likert scale; Guideline; Thematic analysis; Systematic review; Population; Transparency (behavior); Actuarial science; Computer science; Psychology; Medicine; MEDLINE; Qualitative research; Business; Environmental health","score_opus":0.9860703963055393,"score_gpt":0.8158425010373498,"score_spread":0.1702278952681895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163523960","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":[0.00003851688,0.5612767,0.18865134,0.21109132,0.012380492,0.022959605,0.0034675046,0.000053698895,0.00008083497],"genre_scores_gemma":[0.0000032674195,0.8534434,0.044856705,0.09810242,0.0015559255,0.001404486,0.00037276157,0.000036948997,0.0002241039],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.86729074,0.09679397,0.034039788,0.00047584117,0.00036802533,0.0010316643],"domain_scores_gemma":[0.584797,0.38761884,0.024712168,0.0007437958,0.0015818721,0.0005463139],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24204782,0.00042607225,0.010356957,0.0004406839,0.00061789807,0.00005404671,0.0013673436,0.00079725956,0.00007769147],"category_scores_gemma":[0.6314163,0.000235584,0.0015258957,0.00038952357,0.00015770437,0.00075188844,0.0003265959,0.002189134,0.00025933987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000449577,0.000028437513,0.0017483374,0.08825742,0.00041073613,5.361376e-7,0.00072324526,0.00008187833,2.0615982e-9,0.002395877,0.8115222,0.09478642],"study_design_scores_gemma":[0.00055694755,0.0001743223,0.0005288434,0.025584962,0.00036687677,0.00004362901,0.0006760913,0.0005232028,1.1597778e-9,0.0002478018,0.9711105,0.00018681107],"about_ca_topic_score_codex":0.0004774623,"about_ca_topic_score_gemma":0.00034650584,"teacher_disagreement_score":0.3893685,"about_ca_system_score_codex":0.000564564,"about_ca_system_score_gemma":0.0070542614,"threshold_uncertainty_score":0.9985748},"labels":[],"label_agreement":null},{"id":"W3163530790","doi":"10.1016/j.jclinepi.2021.04.020","title":"Time to improve the reporting of harms in randomized controlled trials","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":67,"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; University of Ottawa; Ottawa Public Health; University of Alberta","funders":"National Institute for Health and Care Research","keywords":"Randomized controlled trial; Scopus; Medicine; Systematic review; Harm; MEDLINE; Consolidated Standards of Reporting Trials; Family medicine; Psychology; Internal medicine; Political science","score_opus":0.9262887401023894,"score_gpt":0.7085619410152538,"score_spread":0.21772679908713555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163530790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7311294,0.010719599,0.0675289,0.17217238,0.0049204165,0.0042184195,0.000008190334,0.0000023586556,0.0093003],"genre_scores_gemma":[0.9009122,0.000939461,0.048824936,0.019332312,0.0026531396,0.00009154283,0.0000015419746,0.0000226971,0.027222168],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.023153631,0.61479276,0.3585112,0.0006869624,0.002530738,0.00032469942],"domain_scores_gemma":[0.0020141164,0.7233387,0.26971537,0.001619516,0.003097706,0.00021453484],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9817893,0.00021250166,0.107194826,0.00029912198,0.000032756638,0.00006218442,0.00132321,0.00023735865,0.010152492],"category_scores_gemma":[0.998597,0.000059714046,0.030644283,0.0007222136,0.00023524492,0.00007876505,0.00014944168,0.00069758244,0.00043588135],"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":[0.17050952,0.0010433941,0.15233718,0.000119195036,0.0185557,0.0004598631,0.00081125373,0.007770574,0.0015654431,0.009098948,0.39073694,0.24699199],"study_design_scores_gemma":[0.4830991,0.0009286537,0.045143016,0.0007387755,0.0077000055,0.00046985343,0.0010800461,0.064611815,0.000106535284,0.30086026,0.09479051,0.00047145126],"about_ca_topic_score_codex":0.000005640608,"about_ca_topic_score_gemma":0.000005852686,"teacher_disagreement_score":0.31258956,"about_ca_system_score_codex":0.000012804491,"about_ca_system_score_gemma":0.0004929888,"threshold_uncertainty_score":0.99075234},"labels":[],"label_agreement":null},{"id":"W3164979178","doi":"10.1016/j.jclinepi.2021.05.007","title":"PRIME-IPD SERIES Part 1. The PRIME-IPD tool promoted verification and standardization of study datasets retrieved for IPD meta-analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; Centre for Global Health Research; University of Toronto; Hospital for Sick Children; Bruyère; University of Ottawa","funders":"Hospital for Sick Children; Bruyère Research Institute; Bill and Melinda Gates Foundation","keywords":"Standardization; Computer science; Meta-analysis; Prime (order theory); Data mining; Missing data; Data quality; Artificial intelligence; Machine learning; Medicine","score_opus":0.94154916197496,"score_gpt":0.683125887889487,"score_spread":0.25842327408547294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164979178","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":[0.21457326,0.007904795,0.7510805,0.022221642,0.000884005,0.002510247,0.0007279973,0.000005271664,0.00009226245],"genre_scores_gemma":[0.94115716,0.0009989943,0.054128267,0.0014223703,0.00038259107,0.000043716027,0.00018975022,0.000021813335,0.0016553454],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.81223077,0.13803412,0.045251478,0.0012178331,0.0029251843,0.00034064127],"domain_scores_gemma":[0.7709048,0.1474656,0.06657466,0.0067335214,0.007983051,0.00033838197],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.56021243,0.00030136775,0.01666402,0.00022301533,0.00017577883,0.0001659415,0.0012631202,0.0002497324,0.0017074879],"category_scores_gemma":[0.70694727,0.00012235224,0.0073878067,0.0018302875,0.00028953914,0.00037413824,0.00018351055,0.00045559142,0.00001585609],"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":[0.0017749271,0.002395592,0.47316784,0.00020165289,0.35854414,0.00003429451,0.0011596556,0.004574947,0.00023052022,0.007522735,0.105803676,0.04459002],"study_design_scores_gemma":[0.0020437606,0.0023389151,0.29455656,0.000027056672,0.2801594,0.00008343776,0.0017213087,0.010034402,0.00031918281,0.025945919,0.3823565,0.00041356345],"about_ca_topic_score_codex":0.00000519059,"about_ca_topic_score_gemma":0.000038372065,"teacher_disagreement_score":0.7265839,"about_ca_system_score_codex":0.000019957035,"about_ca_system_score_gemma":0.00038909508,"threshold_uncertainty_score":0.9992051},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3165335631","doi":"10.1016/j.jclinepi.2021.05.008","title":"A Cross-sectional literature survey showed the reporting quality of multicenter randomized controlled trials should be improved","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Consolidated Standards of Reporting Trials; Checklist; Multicenter study; Medicine; Multicenter trial; Randomized controlled trial; Research design; Clinical trial; Family medicine; Statistics; Internal medicine; Psychology","score_opus":0.9643053919343881,"score_gpt":0.7459725136268671,"score_spread":0.21833287830752102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165335631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9269161,0.009640622,0.040510587,0.01473188,0.0057944297,0.0017506955,0.00007039675,0.000002629495,0.000582632],"genre_scores_gemma":[0.97798264,0.00064085226,0.010206753,0.0058638756,0.001278085,0.000030050758,0.000015447185,0.000011564483,0.003970745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.022951419,0.701457,0.2709925,0.0008974336,0.0033485852,0.00035302306],"domain_scores_gemma":[0.002310316,0.7032506,0.28044438,0.0019415361,0.011811001,0.0002421476],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.98429847,0.00036274423,0.07872656,0.00021756209,0.00013026272,0.00037952705,0.0015587694,0.00064367446,0.005292093],"category_scores_gemma":[0.9984449,0.00011001654,0.044472735,0.00075096614,0.0005991078,0.00019820573,0.00018761285,0.0015901335,0.000018077892],"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":[0.060799893,0.00020467756,0.9255434,0.00003721912,0.0046824664,0.000016685435,0.00008175172,0.0001473904,0.0001659945,0.00089335424,0.0060185483,0.0014086207],"study_design_scores_gemma":[0.10033414,0.00008884876,0.87916076,0.00008195931,0.00084787776,0.00008291918,0.00006644174,0.0070731984,0.00000930848,0.009764603,0.002376735,0.0001131894],"about_ca_topic_score_codex":0.000036168938,"about_ca_topic_score_gemma":0.00007856037,"teacher_disagreement_score":0.0510665,"about_ca_system_score_codex":0.000019853498,"about_ca_system_score_gemma":0.00059758296,"threshold_uncertainty_score":0.9956172},"labels":[],"label_agreement":null},{"id":"W3165472090","doi":"10.1016/j.jclinepi.2021.05.011","title":"Reporting quality of trial protocols improved for non-regulated interventions but not regulated interventions: A repeated cross-sectional study","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Michael's Hospital; University of Toronto; McMaster University; Impact","funders":"Magyar Tudományos Akadémia; University of Oxford; Bundesamt für Gesundheit; Astellas Pharma; Alexander von Humboldt-Stiftung; Albert-Ludwigs-Universität Freiburg; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Psychological intervention; Medicine; Interquartile range; Checklist; Randomized controlled trial; Protocol (science); Consolidated Standards of Reporting Trials; Family medicine; MEDLINE; Physical therapy; Alternative medicine; Nursing; Pathology; Internal medicine; Psychology","score_opus":0.9672992180469149,"score_gpt":0.7689387552238727,"score_spread":0.1983604628230422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165472090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9065472,0.000112154914,0.07932591,0.0009766541,0.0020050588,0.0109295985,0.00004001671,0.000006061568,0.000057386027],"genre_scores_gemma":[0.964004,0.0000074610557,0.028602542,0.00023005733,0.0007808749,0.0012161749,0.000022972663,0.00002064005,0.005115313],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.56216884,0.13740022,0.29477483,0.001881607,0.0031929093,0.00058160664],"domain_scores_gemma":[0.25796005,0.23163585,0.47541597,0.005957242,0.02832845,0.0007024426],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7915203,0.00035499674,0.018687924,0.00045463373,0.00019157009,0.00023154497,0.0015385723,0.0005406649,0.002426194],"category_scores_gemma":[0.94631827,0.00019253339,0.029424751,0.001126892,0.00030522994,0.00030183376,0.00030080648,0.0009486297,0.00002957406],"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":[0.015128242,0.0044586537,0.96163416,0.0006227303,0.0042405617,0.000031710595,0.00007552199,0.00048529654,0.0007847779,0.00064182974,0.004444771,0.007451755],"study_design_scores_gemma":[0.02158793,0.0038016145,0.9510828,0.0006152578,0.0005900675,0.00010565665,0.00026586832,0.004427382,0.00008971816,0.016626542,0.00062207185,0.00018506058],"about_ca_topic_score_codex":0.000039402847,"about_ca_topic_score_gemma":0.00009442124,"teacher_disagreement_score":0.3042088,"about_ca_system_score_codex":0.00006157668,"about_ca_system_score_gemma":0.00063940184,"threshold_uncertainty_score":0.99848574},"labels":[],"label_agreement":null},{"id":"W3166022305","doi":"10.1016/j.jclinepi.2021.05.025","title":"A systematic review that is ``rapid'' and ``living'': A specific answer to the COVID-19 pandemic","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Centre for Disability Prevention and Rehabilitation; Ontario Tech University","funders":"","keywords":"Systematic review; Pandemic; Flexibility (engineering); Management science; Coronavirus disease 2019 (COVID-19); Field (mathematics); Scientific evidence; Computer science; Adaptation (eye); Scientific literature; Risk analysis (engineering); Quality (philosophy); Formative assessment; Data science; Evidence-based medicine; Engineering ethics; MEDLINE; Medicine; Psychology; Alternative medicine; Disease; Political science; Pathology; Biology; Engineering; Infectious disease (medical specialty); Mathematics; Epistemology","score_opus":0.9643761334497902,"score_gpt":0.7145632635645739,"score_spread":0.24981286988521634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166022305","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022774375,0.964107,0.011492358,0.018985864,0.0020883137,0.003071083,0.000036514743,0.0000039015645,0.00021273711],"genre_scores_gemma":[0.00000250092,0.925806,0.0020422898,0.068423964,0.0010794376,0.000102667334,0.0000035268188,0.00003622929,0.0025034167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.33079648,0.5117706,0.14812087,0.0027031389,0.005720753,0.0008881654],"domain_scores_gemma":[0.10096015,0.74697524,0.13834155,0.009115687,0.0023990024,0.0022083598],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8366814,0.0010863525,0.10959872,0.0006577011,0.00021239428,0.0003850819,0.006416128,0.0009982481,0.010626505],"category_scores_gemma":[0.9301101,0.00035652742,0.029899603,0.002132959,0.0003700723,0.0001587701,0.00079258933,0.0027556624,0.0023745375],"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":[0.0000026278403,0.000043215983,0.0011757198,0.24052791,0.002237086,0.000049339444,0.00006854285,0.0000011082784,1.3346345e-9,0.0003511709,0.6023969,0.1531464],"study_design_scores_gemma":[0.00006920402,0.000112797585,0.000044926033,0.23339228,0.009052297,0.0028224576,0.00006975831,0.00001016079,2.608217e-10,0.00085193774,0.75333756,0.00023663987],"about_ca_topic_score_codex":0.0000044376516,"about_ca_topic_score_gemma":0.000012060322,"teacher_disagreement_score":0.23520467,"about_ca_system_score_codex":0.00013966508,"about_ca_system_score_gemma":0.001349117,"threshold_uncertainty_score":0.99988866},"labels":[],"label_agreement":null},{"id":"W3168725204","doi":"10.1016/j.jclinepi.2021.05.023","title":"Update on the JCE GRADE series and other GRADE article types","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; Cochrane; Impact; University of Ottawa","funders":"","keywords":"Guideline; Computer science; Medicine; Library science; Pathology","score_opus":0.7677585192801761,"score_gpt":0.5821394852189936,"score_spread":0.18561903406118252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168725204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52208585,0.0032311939,0.0008360663,0.4717982,0.0009993059,0.00008169443,0.00002073735,0.0000065042013,0.0009404311],"genre_scores_gemma":[0.72422814,0.002449236,0.00639124,0.26459673,0.0017662494,0.0000067822466,0.0000016363717,0.000024787872,0.0005352019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98684067,0.0043633464,0.008184154,0.0002805974,0.000051551102,0.00027971392],"domain_scores_gemma":[0.9597901,0.034123447,0.005429976,0.00035344934,0.00008116266,0.00022187822],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08229746,0.00011523249,0.0019160405,0.00006829974,0.00010359822,0.000021606947,0.0002050518,0.00019982431,0.00054351985],"category_scores_gemma":[0.13075973,0.00008917844,0.00028769174,0.00008907508,0.00024755835,0.00016682128,0.00004870611,0.000567405,0.00050729327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048954902,0.0001022007,0.34780332,0.000023660683,0.00012935272,0.0000055315695,0.00011655683,0.00011534412,0.0000013091804,0.60912997,0.042267498,0.0002562774],"study_design_scores_gemma":[0.00063669495,0.00029211,0.18123628,0.000054933687,0.000013802884,0.00010115638,0.0002827433,0.0008984322,0.000011006837,0.4516617,0.3646863,0.00012482263],"about_ca_topic_score_codex":0.000036749978,"about_ca_topic_score_gemma":0.00004396998,"teacher_disagreement_score":0.3224188,"about_ca_system_score_codex":0.000044068274,"about_ca_system_score_gemma":0.0001273679,"threshold_uncertainty_score":0.94496787},"labels":[],"label_agreement":null},{"id":"W3169513989","doi":"10.1016/j.jclinepi.2021.05.021","title":"RIGHT for acupuncture: An extension of the RIGHT statement for clinical practice guidelines on acupuncture","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":30,"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":"Checklist; Medicine; Acupuncture; CLARITY; Guideline; Transparency (behavior); Alternative medicine; MEDLINE; Quality (philosophy); Health care; Family medicine; Medical education; Psychology; Pathology; Computer science","score_opus":0.7175726937963919,"score_gpt":0.69735566566699,"score_spread":0.02021702812940185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169513989","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":[0.14521636,0.00168884,0.11194474,0.72292024,0.015125189,0.0027061468,0.00015520955,0.000027596176,0.0002156851],"genre_scores_gemma":[0.05200829,0.0053062136,0.62010103,0.30883774,0.01278727,0.00004400197,0.00018304033,0.0000942327,0.0006381778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96901244,0.007366982,0.021561217,0.0007966682,0.0007298544,0.0005328212],"domain_scores_gemma":[0.5889626,0.3663654,0.022858037,0.001935062,0.018938012,0.0009408487],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.095294185,0.0004570857,0.0047224048,0.00009124131,0.00015047882,0.000013445534,0.00045864034,0.0008463271,0.0002428167],"category_scores_gemma":[0.8377342,0.00019147742,0.0034550314,0.00022479486,0.0003705666,0.00035291567,0.00015364378,0.0017902948,0.0000066475145],"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":[0.026142292,0.0042883507,0.023231322,0.00026851954,0.0017509984,0.00012709765,0.000043048014,0.0006445841,0.00045326576,0.0060309335,0.81708586,0.119933724],"study_design_scores_gemma":[0.010649593,0.009439411,0.05166745,0.0003543963,0.0029349066,0.0005739505,0.00026151477,0.002241356,0.00042717464,0.020122025,0.9011263,0.00020190972],"about_ca_topic_score_codex":0.000009933694,"about_ca_topic_score_gemma":0.00004204563,"teacher_disagreement_score":0.74244004,"about_ca_system_score_codex":0.000088152716,"about_ca_system_score_gemma":0.0018705922,"threshold_uncertainty_score":0.931585},"labels":[],"label_agreement":null},{"id":"W3169933308","doi":"10.1016/j.jclinepi.2021.05.019","title":"Resource use during systematic review production varies widely: a scoping review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":89,"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":"Donau-Universität Krems","keywords":"Data extraction; Scopus; Critical appraisal; Resource (disambiguation); Systematic review; Grey literature; Resource management (computing); Production (economics); Computer science; Protocol (science); Medicine; MEDLINE; Knowledge management; Database; Alternative medicine; Political science","score_opus":0.9595601394769535,"score_gpt":0.7215685962135804,"score_spread":0.23799154326337313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169933308","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014013406,0.9853232,0.0016448114,0.0043800524,0.002497872,0.0060318373,0.000008664961,0.0000068554036,0.00010529162],"genre_scores_gemma":[1.3013026e-7,0.98287463,0.004728471,0.0057901847,0.0014112577,0.00015799179,0.000016383803,0.000057877638,0.004963048],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.23746629,0.5242237,0.22938602,0.002558182,0.0055944063,0.0007714037],"domain_scores_gemma":[0.049120538,0.53255486,0.39423862,0.014285248,0.008581724,0.0012189936],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8285503,0.0012511037,0.17928208,0.0007199636,0.00022507661,0.00035653726,0.004774972,0.0009407936,0.0027134323],"category_scores_gemma":[0.9809317,0.00052281347,0.044589814,0.0029675525,0.00033898186,0.0006049734,0.00061497267,0.0031827572,0.0012256212],"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":[0.0000026547325,0.000054253207,0.000069926544,0.86578846,0.0016409805,0.00007894045,0.0000042888564,0.0000027912238,3.146853e-9,0.00016756011,0.091820434,0.040369697],"study_design_scores_gemma":[0.000048776958,0.000046692105,0.000008024747,0.5856413,0.016399128,0.0018869177,0.0000061734963,0.000002671622,4.3510924e-9,0.00016398284,0.3955678,0.0002284642],"about_ca_topic_score_codex":0.0000018338349,"about_ca_topic_score_gemma":0.000004363562,"teacher_disagreement_score":0.3037474,"about_ca_system_score_codex":0.00014352587,"about_ca_system_score_gemma":0.0017690011,"threshold_uncertainty_score":0.99972236},"labels":[],"label_agreement":null},{"id":"W3170903019","doi":"10.1016/j.jclinepi.2021.05.024","title":"Clinical practice guidelines in low and middle income countries: experiences from colombia","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University","funders":"Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Low and middle income countries; Medicine; Family medicine; Environmental health; Geography; Developing country; Economic growth; Economics","score_opus":0.5671589686277575,"score_gpt":0.6262713090067045,"score_spread":0.05911234037894697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170903019","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.17391653,0.0060293865,0.000485277,0.8112662,0.00768068,0.00042527588,0.000040154362,0.000017047749,0.00013944879],"genre_scores_gemma":[0.0018825679,0.027544253,0.100533016,0.84075767,0.02878378,0.000020026082,0.0001377759,0.00006413591,0.0002767807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9368567,0.019316163,0.040571608,0.001313605,0.0011054709,0.0008364737],"domain_scores_gemma":[0.4827679,0.48474923,0.024734924,0.0010796504,0.0059091724,0.00075911393],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09309972,0.00059559447,0.009264918,0.00030222375,0.000069072834,0.000049143488,0.00056685717,0.004002355,0.00092703756],"category_scores_gemma":[0.8586263,0.00046527546,0.0015210945,0.0003133216,0.0012301204,0.0005763158,0.00037608543,0.011930941,0.000050217564],"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":[0.0022195573,0.000348658,0.23262486,0.00032164925,0.0007781501,0.005840738,0.00016868344,0.000005994308,3.76756e-7,0.00001665477,0.7481527,0.009522018],"study_design_scores_gemma":[0.0062594716,0.0025716026,0.0809451,0.00422944,0.0011674099,0.0013529946,0.0018834234,0.000366434,7.146479e-7,0.0014031426,0.89944124,0.00037900676],"about_ca_topic_score_codex":0.00079787086,"about_ca_topic_score_gemma":0.00015928512,"teacher_disagreement_score":0.7655266,"about_ca_system_score_codex":0.00015051669,"about_ca_system_score_gemma":0.0032061073,"threshold_uncertainty_score":0.99998623},"labels":[],"label_agreement":null},{"id":"W3173236118","doi":"10.1016/j.jclinepi.2021.06.011","title":"Imputing intracluster correlation coefficients from a posterior predictive distribution is a feasible method of dealing with unit of analysis errors in a meta-analysis of cluster RCTs","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"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 of Toronto; University of Ottawa; Ottawa Hospital","funders":"Department of Family and Community Medicine, University of Toronto; Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Statistics; Intraclass correlation; Posterior probability; Missing data; Posterior predictive distribution; Meta-analysis; Bayesian probability; Medicine; Data mining; Mathematics; Computer science; Bayesian inference; Bayesian linear regression; Reproducibility","score_opus":0.8103490865513325,"score_gpt":0.6313172244738505,"score_spread":0.179031862077482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173236118","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":[0.43724796,0.0004953752,0.56085455,0.0009400355,0.00008216546,0.00015021415,0.00019126141,5.339084e-7,0.00003792362],"genre_scores_gemma":[0.9256811,0.000039614024,0.07368973,0.00041156664,0.00003282146,0.0000026111397,0.000051826264,0.0000069453845,0.000083781444],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.85780585,0.09038074,0.04778047,0.0009727017,0.0027406982,0.00031952604],"domain_scores_gemma":[0.75087976,0.16857523,0.07129105,0.0020150545,0.0069677522,0.00027117995],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.3359773,0.00030363284,0.025848716,0.0014220929,0.000037847396,0.000028502198,0.00087896077,0.00036625867,0.002184072],"category_scores_gemma":[0.29954067,0.00014640237,0.013831282,0.006873981,0.00021532664,0.00020939416,0.00019673238,0.0005908375,0.0000049133146],"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":[0.00034640785,0.00021856498,0.63482684,0.00002575645,0.12444565,0.000007555293,0.00045877212,0.23750024,0.000024883742,0.00012525862,0.000102985745,0.0019171111],"study_design_scores_gemma":[0.0005463839,0.00025321994,0.38726708,0.00004426855,0.20273072,0.0000098020655,0.00061429106,0.40716216,0.000041369036,0.0011998201,0.00005168708,0.00007919555],"about_ca_topic_score_codex":0.00020460451,"about_ca_topic_score_gemma":0.00031743757,"teacher_disagreement_score":0.48843315,"about_ca_system_score_codex":0.00003547568,"about_ca_system_score_gemma":0.00025061774,"threshold_uncertainty_score":0.9987281},"labels":[],"label_agreement":null},{"id":"W3173459791","doi":"10.1016/j.jclinepi.2021.06.013","title":"Informing the GRADE evidence to decision process with health equity considerations: demonstration from the Canadian rheumatoid arthritis care context","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto; Research Canada; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Equity (law); Medicine; Guideline; Socioeconomic status; Health equity; Indigenous; Context (archaeology); Population; Health care; Public health; Family medicine; Political science; Nursing; Environmental health; Geography; Pathology","score_opus":0.754987732001804,"score_gpt":0.6012658536636262,"score_spread":0.15372187833817785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173459791","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":[0.27050686,0.03611997,0.018985355,0.6719851,0.0013672003,0.0006854507,0.00010394654,0.0000085798165,0.00023753755],"genre_scores_gemma":[0.834372,0.0032430012,0.009326973,0.15247998,0.00052919064,0.000023871926,0.000009335089,0.000010853333,0.000004810183],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98153055,0.0042001423,0.013245267,0.00039563488,0.0001615763,0.0004668427],"domain_scores_gemma":[0.87450206,0.1133711,0.009989815,0.0006086243,0.00078528264,0.0007430884],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09396733,0.0001609526,0.0022023667,0.00010844856,0.00073720235,0.000112149326,0.00039412314,0.00022754597,0.00020274658],"category_scores_gemma":[0.33958602,0.00011265096,0.00026189492,0.00019208797,0.00023391526,0.0005107953,0.00005846423,0.00083786243,0.00013293908],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001442053,0.000059125174,0.7784249,0.00006966689,0.00021295871,0.000018550669,0.008614925,0.0035072623,1.274061e-7,0.10013801,0.060349714,0.048460513],"study_design_scores_gemma":[0.003107613,0.0010404061,0.6950206,0.0035549547,0.000019186358,0.00052095647,0.022183163,0.0023607465,0.0000034107036,0.20563184,0.06609932,0.0004577679],"about_ca_topic_score_codex":0.04190768,"about_ca_topic_score_gemma":0.60232013,"teacher_disagreement_score":0.5638651,"about_ca_system_score_codex":0.0005676304,"about_ca_system_score_gemma":0.006720673,"threshold_uncertainty_score":0.9989103},"labels":[],"label_agreement":null},{"id":"W3173469077","doi":"10.1016/j.jclinepi.2021.06.021","title":"Cluster randomized trials of individual-level interventions were at high risk of bias","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"European and Developing Countries Clinical Trials Partnership; Collaboration for Leadership in Applied Health Research and Care - Greater Manchester; European Commission; Medical Research Council; Department for International Development; Department for International Development, UK Government; National Institute for Health and Care Research","keywords":"Psychological intervention; Cluster (spacecraft); Randomized controlled trial; Cluster randomised controlled trial; Medicine; Environmental health; Internal medicine; Psychiatry; Computer science","score_opus":0.9842656149338989,"score_gpt":0.7452617721036193,"score_spread":0.23900384283027953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173469077","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030386043,0.9539716,0.03864694,0.0008068988,0.0038675335,0.0015964457,0.0006120145,0.0000010978082,0.00019357726],"genre_scores_gemma":[0.00008992581,0.96549904,0.030266479,0.00027465375,0.00089461333,0.00003060794,0.00004758403,0.000026460268,0.0028706333],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.060055166,0.6701666,0.2646531,0.001013979,0.0037588817,0.00035226924],"domain_scores_gemma":[0.010596545,0.6445908,0.33803603,0.0029919557,0.003423012,0.00036164242],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.96159375,0.00080171454,0.23740312,0.001403363,0.00007019456,0.00007944618,0.0048143775,0.0016131073,0.021258865],"category_scores_gemma":[0.9896906,0.00029608863,0.1797477,0.0012023111,0.00083901617,0.00013467354,0.0009760091,0.0022268973,0.00037286893],"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":[0.001222975,0.00031764124,0.001549761,0.005336641,0.02303977,0.000012643059,0.000026350654,0.00004105214,9.837423e-9,0.0017316142,0.17526783,0.7914537],"study_design_scores_gemma":[0.021744708,0.00035325057,0.00062915846,0.022936238,0.061166376,0.000165829,0.000043247397,0.000051864485,9.396487e-8,0.022266518,0.87037903,0.00026371022],"about_ca_topic_score_codex":0.000018246104,"about_ca_topic_score_gemma":0.000024722125,"teacher_disagreement_score":0.79119,"about_ca_system_score_codex":0.00004790685,"about_ca_system_score_gemma":0.00095681555,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W3174162851","doi":"10.1016/j.jclinepi.2021.04.014","title":"Corrigendum to GRADE guidelines 6. Rating the quality of evidence-imprecision. J Clin Epidemiol 2011;64:1283–1293","year":2021,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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","funders":"","keywords":"Rule of thumb; Regret; Sample size determination; Confidence interval; Statistics; Quality (philosophy); Paragraph; Medicine; Sample (material); Standard deviation; Mathematics; Computer science; Algorithm; Philosophy","score_opus":0.9896614526333349,"score_gpt":0.7703811704882573,"score_spread":0.21928028214507767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174162851","genre_codex":"commentary","genre_gemma":"other","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039398796,0.15153274,0.24709761,0.31660166,0.27250552,0.002647394,0.00017739827,0.000013848645,0.005483945],"genre_scores_gemma":[0.005431807,0.04660542,0.27496246,0.07409286,0.050217174,0.0000941729,0.00006496877,0.00019716991,0.548334],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.11703253,0.54094476,0.3208176,0.0040652337,0.015482931,0.001656955],"domain_scores_gemma":[0.025608456,0.6982181,0.2384028,0.0113718435,0.024796745,0.0016020532],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9151432,0.0012780124,0.05929847,0.0009378849,0.000315523,0.00026466636,0.011896419,0.0026238733,0.0115287155],"category_scores_gemma":[0.9875094,0.00046204965,0.030183673,0.001915413,0.0007908783,0.00040079467,0.0015348537,0.0069995793,0.0017277327],"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":[0.000118768854,0.00012613276,0.037279505,0.00015870234,0.0010647402,0.000023701818,0.000074143114,0.0004357543,0.000008359851,0.00085980556,0.8927948,0.06705557],"study_design_scores_gemma":[0.00037869607,0.0005770072,0.05151105,0.0019518851,0.0013505701,0.0001216028,0.0005220257,0.0028246392,0.0000026458606,0.043140244,0.8971418,0.0004777923],"about_ca_topic_score_codex":0.00021227098,"about_ca_topic_score_gemma":0.000358661,"teacher_disagreement_score":0.54285,"about_ca_system_score_codex":0.00010927574,"about_ca_system_score_gemma":0.0028259982,"threshold_uncertainty_score":0.9999972},"labels":[],"label_agreement":null},{"id":"W3174891973","doi":"10.1016/j.jclinepi.2021.06.015","title":"“Evidence-based checklists” for identifying predatory journals have not been assessed for reliability or validity: An analysis and proposal for moving forward","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":25,"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; Ottawa Hospital","funders":"","keywords":"Reliability (semiconductor); Matching (statistics); Scale (ratio); Scope (computer science); Guideline; Computer science; Quality (philosophy); Medicine","score_opus":0.9363805130465965,"score_gpt":0.7299491902987689,"score_spread":0.2064313227478276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174891973","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":[0.3535864,0.0007379166,0.62956464,0.014365474,0.00099374,0.00060747756,0.00013262844,0.000006509051,0.000005185455],"genre_scores_gemma":[0.6320565,0.001107616,0.36292472,0.0021179498,0.0012837965,0.000063003274,0.000013280245,0.00002471936,0.00040841382],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97599655,0.008363111,0.009894365,0.0014172271,0.0032990542,0.0010297141],"domain_scores_gemma":[0.28872564,0.67166585,0.009446396,0.0013397909,0.02696158,0.0018607602],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.466217,0.0002739962,0.0041077896,0.0128956,0.00046749084,0.0011388531,0.0019738378,0.00067062705,0.00019555073],"category_scores_gemma":[0.92802197,0.00016897071,0.0029359532,0.018435445,0.00048011003,0.0016635904,0.0003641664,0.0008896163,0.000001482325],"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":[0.003535638,0.0006013237,0.904924,0.00018058743,0.00053258217,0.00002143541,0.000035203535,0.0013943627,0.00047531392,0.00043917107,0.0057824003,0.08207803],"study_design_scores_gemma":[0.0034022212,0.0039876434,0.6410055,0.00013723424,0.0008390463,0.00003250107,0.00037300267,0.24147785,0.0011809529,0.09960552,0.007657991,0.00030055264],"about_ca_topic_score_codex":0.000024235424,"about_ca_topic_score_gemma":0.0001449057,"teacher_disagreement_score":0.6872709,"about_ca_system_score_codex":0.00016023598,"about_ca_system_score_gemma":0.0038954415,"threshold_uncertainty_score":0.9998981},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":["metaresearch","scholarly_communication"],"domain":"evaluation","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3175765542","doi":"10.1016/j.jclinepi.2021.06.023","title":"An economic valuation technique identified different inpatient care experience as priorities for older Canadians than a traditional approach","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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; Trinity Western University; Ottawa Hospital; Ministry of Health; Providence Health Care; Western University; Centre for Advancing Health Outcomes; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Valuation (finance); Bivariate analysis; Logit; Actuarial science; Health care; Confidence interval; Missing data; Medicine; Psychology; Econometrics; Computer science; Economics; Accounting","score_opus":0.7306202332527644,"score_gpt":0.5748736770126317,"score_spread":0.15574655624013267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175765542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8438505,0.0015085528,0.13613021,0.013640231,0.0029461158,0.0008555967,0.00038476533,0.000016082317,0.0006679228],"genre_scores_gemma":[0.96508545,0.00028467915,0.022878962,0.009314966,0.0018456323,0.00028975983,0.00014703056,0.00003009929,0.00012339879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9833707,0.003299118,0.012196871,0.00061525096,0.00009417801,0.00042387872],"domain_scores_gemma":[0.977477,0.013675907,0.007566723,0.000460551,0.00031993765,0.0004998975],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03814149,0.00021119932,0.0028116682,0.00025550238,0.00017560991,0.000043437412,0.00039067105,0.0004280631,0.00028713697],"category_scores_gemma":[0.03828362,0.00022980283,0.00066909293,0.000061372506,0.00018462543,0.0004677653,0.000028853186,0.0004604921,0.00004077725],"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":[0.00020017698,0.0006400556,0.481472,0.00059113425,0.00034886773,0.000007554487,0.00875805,0.0032991634,0.000011074391,0.4910041,0.011686984,0.001980849],"study_design_scores_gemma":[0.0030383102,0.001394588,0.6791777,0.00020121493,0.000054432574,0.00017138431,0.010417655,0.013990775,0.000043547887,0.27815259,0.01275602,0.00060179987],"about_ca_topic_score_codex":0.0008783029,"about_ca_topic_score_gemma":0.00072592986,"teacher_disagreement_score":0.21285152,"about_ca_system_score_codex":0.0007799964,"about_ca_system_score_gemma":0.0013097677,"threshold_uncertainty_score":0.9904358},"labels":[],"label_agreement":null},{"id":"W3177981602","doi":"10.1016/j.jclinepi.2021.06.029","title":"Pilot and feasibility studies for pragmatic trials have unique considerations and areas of uncertainty","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; National Institute for Health and Care Research","keywords":"Flexibility (engineering); Mindset; Management science; Intervention (counseling); Clinical trial; Outcome (game theory); Identification (biology); Computer science; Risk analysis (engineering); Psychology; Medicine; Artificial intelligence; Nursing; Engineering","score_opus":0.9440043682199685,"score_gpt":0.7555908106863763,"score_spread":0.18841355753359212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177981602","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":[0.8124478,0.010096186,0.00413895,0.17142405,0.0006789464,0.00094005023,0.000035953588,0.000006621966,0.0002314853],"genre_scores_gemma":[0.9290171,0.020363932,0.044153564,0.005664904,0.0005390844,0.000012532587,0.0000034815034,0.000010962545,0.00023438685],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9738139,0.015493323,0.009674674,0.0004017522,0.0003316594,0.00028468657],"domain_scores_gemma":[0.031286504,0.9592636,0.0037729342,0.0004131775,0.004772927,0.00049081823],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19296113,0.00012893564,0.005062027,0.00007276616,0.000071655115,0.000006104003,0.00007134196,0.000396505,0.000049240898],"category_scores_gemma":[0.9745152,0.00008245288,0.00055059005,0.0000616776,0.0018051899,0.000048123657,0.00013427586,0.001970109,3.5583747e-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":[0.0060817334,0.0014021347,0.805154,0.002549549,0.0024518329,0.00012351641,0.00026178526,0.00007407131,0.00043251566,0.16998355,0.007342413,0.0041428725],"study_design_scores_gemma":[0.005566559,0.005243682,0.15256855,0.00077658624,0.00043433355,0.0002923849,0.0004813266,0.00039573337,0.00006808516,0.8337961,0.00031416645,0.000062540035],"about_ca_topic_score_codex":0.000014026662,"about_ca_topic_score_gemma":0.0003092141,"teacher_disagreement_score":0.9437703,"about_ca_system_score_codex":0.00003881464,"about_ca_system_score_gemma":0.001857096,"threshold_uncertainty_score":0.8559253},"labels":[],"label_agreement":null},{"id":"W3178709502","doi":"10.1016/j.jclinepi.2021.07.008","title":"Reconciling contrasting guideline recommendations on red and processed meat for health outcomes","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":9,"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":"Texas AgriLife Research","keywords":"Guideline; Warrant; Limiting; Consumption (sociology); Environmental health; Health benefits; Business; Medicine; Scientific evidence; Agriculture; Red meat; Public economics; Marketing; Economics; Engineering; Geography; Finance; Social science","score_opus":0.46905142580687764,"score_gpt":0.5919021033877785,"score_spread":0.12285067758090085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178709502","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":[0.06576703,0.0022996257,0.011721833,0.91871053,0.0009172442,0.00022481225,0.000023392968,0.000010163933,0.0003253764],"genre_scores_gemma":[0.31398356,0.0154590495,0.39563385,0.27055246,0.00377262,0.00001662316,0.000095608906,0.00003209411,0.00045413172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9950416,0.0006403194,0.0038127957,0.00019423789,0.00009098762,0.00022004596],"domain_scores_gemma":[0.9640479,0.032942493,0.001725911,0.000094627576,0.0009137315,0.00027533667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011499739,0.00009804858,0.0020326257,0.00004077586,0.00011289118,0.0000039827833,0.000039351587,0.00011869454,0.000039658244],"category_scores_gemma":[0.17307249,0.00006746213,0.00037699658,0.0000569359,0.000066450986,0.000038513987,0.000022647519,0.0004072051,8.584524e-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":[0.0023588263,0.0007704126,0.5911367,0.00030413546,0.0007182849,0.00003159688,0.00003233789,0.00003182352,0.0000413116,0.0027810424,0.3011802,0.10061335],"study_design_scores_gemma":[0.013344025,0.006036746,0.4762006,0.0012040784,0.00025763875,0.00050993764,0.0005414192,0.0012651404,0.000040501225,0.02698536,0.473426,0.00018854355],"about_ca_topic_score_codex":0.0000035418068,"about_ca_topic_score_gemma":0.000014726502,"teacher_disagreement_score":0.6481581,"about_ca_system_score_codex":0.000030573043,"about_ca_system_score_gemma":0.0003259772,"threshold_uncertainty_score":0.83389306},"labels":[],"label_agreement":null},{"id":"W3181906237","doi":"10.1016/j.jclinepi.2021.07.002","title":"Clinical trials in COVID-19 management & prevention: A meta-epidemiological study examining methodological quality","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"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; Centre Hospitalier Universitaire de Sherbrooke; University of Ottawa; Wilfrid Laurier University; Canada Research Chairs; Ted Rogers Centre for Heart Research; Impact; McMaster University; Toronto General Hospital; University Health Network; Western University; University of Toronto; St. Michael's Hospital","funders":"Ministry of Science and Technology of the People's Republic of China; Canadian Institutes of Health Research; Hamilton Health Sciences","keywords":"Epidemiology; Coronavirus disease 2019 (COVID-19); Medicine; 2019-20 coronavirus outbreak; Meta-analysis; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Environmental health; Clinical trial; Virology; Pathology; Outbreak; Disease; Biology","score_opus":0.9987921871698525,"score_gpt":0.867504502810874,"score_spread":0.13128768435897853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181906237","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019853577,0.7955807,0.19429733,0.0022175119,0.0034731394,0.0037493063,0.000027345528,0.0000091454,0.00044701644],"genre_scores_gemma":[0.000030077721,0.818634,0.17263383,0.0041986536,0.0020196822,0.00028291045,0.000032907694,0.00003607587,0.0021318784],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.006067404,0.69535553,0.289338,0.0038440549,0.0045018285,0.00089316716],"domain_scores_gemma":[0.0025281894,0.7461243,0.24073689,0.006868635,0.0017192855,0.0020226703],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.99485594,0.0020806855,0.3296279,0.0017811788,0.00018970169,0.00036815443,0.008811731,0.0038303204,0.028642423],"category_scores_gemma":[0.99633706,0.00077253627,0.13725856,0.0034042688,0.0008705351,0.00030212948,0.0020714109,0.008342013,0.0010011947],"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":[0.00017420574,0.002309082,0.051802684,0.0019546342,0.031164711,0.0005896478,0.00002850381,0.00010051566,1.426177e-9,0.0031578306,0.058253955,0.8504642],"study_design_scores_gemma":[0.0015606512,0.0011531054,0.014684416,0.0015951963,0.04205083,0.00025529834,0.0004459899,0.000020217336,2.6511837e-10,0.03301458,0.9046761,0.0005436332],"about_ca_topic_score_codex":0.000013639638,"about_ca_topic_score_gemma":0.000081084276,"teacher_disagreement_score":0.8499206,"about_ca_system_score_codex":0.000260466,"about_ca_system_score_gemma":0.0020588741,"threshold_uncertainty_score":0.99977666},"labels":[],"label_agreement":null},{"id":"W3185203671","doi":"10.1016/j.jclinepi.2021.07.010","title":"A modeling approach to derive baseline risk estimates for GRADE recommendations: Concepts, development, and results of its application to the American Society of Hematology 2019 guidelines on prevention of venous thromboembolism in surgical hospitalized patients","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","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; McMaster University; Impact","funders":"National Institute for Health and Care Research","keywords":"Guideline; Baseline (sea); Medicine; Venous thromboembolism; Risk assessment; Transparency (behavior); Confidence interval; Intensive care medicine; Risk analysis (engineering); Internal medicine; Computer science; Pathology","score_opus":0.19486023156322682,"score_gpt":0.490098712396345,"score_spread":0.2952384808331182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185203671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88708967,0.0008047123,0.098948255,0.011952875,0.00013330921,0.0010004352,0.000050469916,0.0000037506418,0.000016556025],"genre_scores_gemma":[0.7286362,0.0050965506,0.26431587,0.0016634708,0.00010995878,0.00006319846,0.00009509741,0.000013785232,0.0000058449295],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934551,0.00096451177,0.0048896503,0.00031380414,0.00017102859,0.00020591916],"domain_scores_gemma":[0.98996794,0.005427067,0.0031812622,0.00023326563,0.0010608978,0.00012957897],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0103456965,0.00014448196,0.0027733308,0.00010444249,0.000038194594,0.0000017456784,0.00014090497,0.00012532089,0.0000018736986],"category_scores_gemma":[0.025247347,0.000099960635,0.00034760105,0.0002468156,0.00011368657,0.000034184002,0.000092414375,0.00023798662,4.9507605e-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":[0.009506886,0.026435882,0.14234015,0.001709025,0.0036975844,0.0000060783273,0.0044317152,0.13083765,0.0002733469,0.008918806,0.043626018,0.62821686],"study_design_scores_gemma":[0.023070991,0.014640818,0.6985096,0.0030280524,0.00155454,0.00005386323,0.0023750688,0.225402,0.0021301596,0.0063425135,0.022367576,0.000524848],"about_ca_topic_score_codex":0.00007849269,"about_ca_topic_score_gemma":0.000019788507,"teacher_disagreement_score":0.627692,"about_ca_system_score_codex":0.000031078947,"about_ca_system_score_gemma":0.00018460161,"threshold_uncertainty_score":0.9829634},"labels":[],"label_agreement":null},{"id":"W3186848610","doi":"10.1016/j.jclinepi.2021.07.011","title":"GRADE guidelines 33: Addressing imprecision in a network meta-analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":89,"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 Health Network; Impact; McMaster University","funders":"","keywords":"Certainty; Confidence interval; Context (archaeology); Computer science; Meta-analysis; Interval (graph theory); Statistics; Medicine; Mathematics","score_opus":0.9880881395648715,"score_gpt":0.7575602546365781,"score_spread":0.23052788492829346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186848610","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":[0.12695523,0.111524455,0.5970998,0.155594,0.005330973,0.00055137294,0.000030806583,0.000007612818,0.0029057565],"genre_scores_gemma":[0.41161653,0.0032213621,0.54457897,0.029015372,0.0037567134,0.000014265654,0.000011177862,0.000033315286,0.0077522798],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.44722924,0.36730325,0.17620192,0.0021334172,0.006170241,0.00096192333],"domain_scores_gemma":[0.29751346,0.5874042,0.09787003,0.006173685,0.010089164,0.00094948086],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7981485,0.0003955684,0.045119554,0.0007913511,0.00009213722,0.00020230025,0.0023321074,0.0004981391,0.0146676125],"category_scores_gemma":[0.887246,0.00016491913,0.042651247,0.004701137,0.00015979039,0.00028172185,0.00032856906,0.0012658531,0.00034492172],"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":[0.000059214322,0.00021637134,0.4589712,0.000013913419,0.08801247,0.00026117763,0.000041455485,0.079720065,0.0000056574368,0.0021200567,0.33416265,0.036415774],"study_design_scores_gemma":[0.00073654694,0.00018871081,0.22770412,0.00005075311,0.15510577,0.00023499916,0.00019955746,0.05908228,0.00000263336,0.22734685,0.32901332,0.00033443864],"about_ca_topic_score_codex":0.000016171294,"about_ca_topic_score_gemma":0.00022921369,"teacher_disagreement_score":0.2846613,"about_ca_system_score_codex":0.000026342888,"about_ca_system_score_gemma":0.00036415874,"threshold_uncertainty_score":0.9862331},"labels":[],"label_agreement":null},{"id":"W3191198632","doi":"10.1016/j.jclinepi.2021.07.021","title":"Evaluating tests for diagnosing COVID-19 in the absence of a reliable reference standard: pitfalls and potential solutions","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"SARS-CoV-2 detection and testing","field":"Medicine","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Diagnostic test; 2019-20 coronavirus outbreak; Pandemic; Diagnostic accuracy; Medicine; Computer science; Pathology; Pediatrics; Radiology","score_opus":0.6092105048534818,"score_gpt":0.6004669986547454,"score_spread":0.008743506198736428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191198632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96398646,0.0013661275,0.023091644,0.010845561,0.00037684184,0.00017650802,0.000006129485,0.0000062372274,0.00014450027],"genre_scores_gemma":[0.949478,0.00033737146,0.03990345,0.009946759,0.00031161122,0.0000057367724,0.0000011889389,0.000006523794,0.000009393564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948926,0.001879133,0.0025755253,0.00020326351,0.00020100197,0.00024845285],"domain_scores_gemma":[0.90668356,0.0897411,0.002296789,0.0002702312,0.0008224257,0.00018591249],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032321837,0.000085991014,0.0011108007,0.00008120155,0.00009986332,0.000006468731,0.00009801064,0.00017858528,0.000016944288],"category_scores_gemma":[0.46064383,0.000057241898,0.00022796271,0.00018176477,0.00022494505,0.00005579932,0.000045852066,0.0007161482,5.910376e-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":[0.0026084112,0.00071828795,0.91713923,0.00049875723,0.00021522629,0.000567351,0.00048561612,0.0021365483,0.028303927,0.005200926,0.0043922253,0.037733477],"study_design_scores_gemma":[0.020372234,0.011817459,0.7771398,0.0023539355,0.0006876888,0.013193725,0.001899175,0.044015493,0.0022858828,0.10719701,0.018632175,0.00040546927],"about_ca_topic_score_codex":0.000050084032,"about_ca_topic_score_gemma":0.000038359347,"teacher_disagreement_score":0.428322,"about_ca_system_score_codex":0.000050248454,"about_ca_system_score_gemma":0.0010445317,"threshold_uncertainty_score":0.9964283},"labels":[],"label_agreement":null},{"id":"W3193585774","doi":"10.1016/j.jclinepi.2021.08.010","title":"The fragility index can be used for sample size calculations in clinical trials","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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 Toronto; Sunnybrook Health Science Centre","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Institute of Allergy and Infectious Diseases; Cornell University; Patient-Centered Outcomes Research Institute","keywords":"Index (typography); Sample size determination; Fragility; Statistics; Sample (material); Clinical trial; Medicine; Mathematics; Computer science; Internal medicine; Physics; Thermodynamics","score_opus":0.9328040477738299,"score_gpt":0.7552170319925443,"score_spread":0.17758701578128555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193585774","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":[0.116906494,0.0002977865,0.7591231,0.111432925,0.010476242,0.0012167139,0.00037291733,0.000030025865,0.00014379181],"genre_scores_gemma":[0.08150492,0.0008310563,0.90582824,0.007318762,0.0042879716,0.000044168744,0.0000027894232,0.00004363462,0.00013846654],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76783985,0.18225761,0.047243327,0.0009232272,0.0006796693,0.00105632],"domain_scores_gemma":[0.0061995867,0.9798992,0.011011907,0.001005443,0.00121956,0.0006642494],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.546707,0.00030046082,0.009328758,0.00006358137,0.00018057083,0.000030926676,0.0007604477,0.0013240478,0.0002997264],"category_scores_gemma":[0.9979534,0.00018184571,0.0038673088,0.0003399364,0.0010861938,0.00006222762,0.00020084615,0.0029768178,0.0000029684666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027931205,0.0015839112,0.584811,0.000093997805,0.00094922545,0.000058928,0.0000508483,0.00009655962,0.000008462099,0.307454,0.022023443,0.08007653],"study_design_scores_gemma":[0.0049660513,0.0005258479,0.16072714,0.00007656523,0.000263361,0.000016351698,0.00006663128,0.0015146952,0.000008308883,0.8155723,0.016115233,0.00014749172],"about_ca_topic_score_codex":0.000042171407,"about_ca_topic_score_gemma":0.0005776126,"teacher_disagreement_score":0.79764163,"about_ca_system_score_codex":0.00008378665,"about_ca_system_score_gemma":0.0013938872,"threshold_uncertainty_score":0.99997246},"labels":[],"label_agreement":null},{"id":"W3194292172","doi":"10.1016/j.jclinepi.2021.08.013","title":"Clinical Epidemiology in China series. Paper 4: The reporting and methodological quality of Chinese clinical practice guidelines published between 2014 and 2018: A systematic review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; McMaster University","funders":"National Office for Philosophy and Social Sciences","keywords":"MEDLINE; Medicine; Checklist; Declaration; China; Family medicine; CLARITY; Psychology; Political science","score_opus":0.8971186279548576,"score_gpt":0.7600381467061853,"score_spread":0.13708048124867234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194292172","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006773989,0.8602804,0.0018387048,0.13206497,0.002236573,0.0027831062,0.00003094474,0.000019983954,0.00006791361],"genre_scores_gemma":[0.000035180965,0.84276736,0.11488638,0.037774388,0.0042483206,0.00006107386,0.00010160551,0.00007221777,0.000053468262],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.26526445,0.4368536,0.2921639,0.0029726515,0.0013233048,0.0014221024],"domain_scores_gemma":[0.009198852,0.7885151,0.19432555,0.002458258,0.0042684055,0.0012338349],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8125482,0.0011530131,0.07332603,0.00031633957,0.00011435458,0.000029958817,0.00101312,0.0036525098,0.00016911016],"category_scores_gemma":[0.99646777,0.00057580887,0.008035925,0.0008323256,0.0023170076,0.0008156725,0.0012072601,0.011832829,0.000010182673],"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":[0.0006330818,0.00067516643,0.37111238,0.26890108,0.0037467873,0.00029769712,0.000016183882,9.374192e-7,4.1048526e-8,0.00044073118,0.028926013,0.3252499],"study_design_scores_gemma":[0.0036562518,0.0034536156,0.24398905,0.27621365,0.024894523,0.010173933,0.00014385197,0.000028779517,5.501286e-9,0.006138279,0.4305931,0.00071495574],"about_ca_topic_score_codex":0.00021321578,"about_ca_topic_score_gemma":0.000054904154,"teacher_disagreement_score":0.4016671,"about_ca_system_score_codex":0.00010726693,"about_ca_system_score_gemma":0.0030026403,"threshold_uncertainty_score":0.9996693},"labels":[],"label_agreement":null},{"id":"W3194350603","doi":"10.1016/j.jclinepi.2021.08.006","title":"Understanding treatment-subgroup effect in primary and secondary prevention of cardiovascular disease: An exploration using meta-analyses of individual patient data","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","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":"McMaster University","funders":"","keywords":"Medicine; Psychological intervention; Relative risk; Meta-analysis; Data extraction; Subgroup analysis; Primary prevention; MEDLINE; Confidence interval; Family medicine; Disease; Internal medicine; Psychiatry","score_opus":0.8962166196897385,"score_gpt":0.6219740416892733,"score_spread":0.27424257800046525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194350603","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":[0.0024308166,0.9419656,0.05429868,0.00004727454,0.00029815506,0.0008695075,0.000077459954,0.0000033346384,0.000009163751],"genre_scores_gemma":[0.0023115424,0.9933417,0.0030799517,0.000046108962,0.0002623329,0.0000142523095,0.00091334194,0.000027527069,0.0000032634614],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9394577,0.05192655,0.0073143584,0.00054342975,0.00054215133,0.00021577606],"domain_scores_gemma":[0.98744243,0.005530668,0.005464432,0.0010305014,0.0001818712,0.00035010575],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070335545,0.000335993,0.014970292,0.0004388261,0.00003263161,0.0000062067065,0.00019520128,0.00055138144,0.000041718282],"category_scores_gemma":[0.011045669,0.00021740753,0.0070701735,0.00028516384,0.0001640807,0.00042501595,0.00015703849,0.0008139882,2.8569968e-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":[0.000087813474,0.00051927665,0.00040215557,0.011659401,0.048475336,0.00009712061,0.000023067943,0.00018630845,3.7625168e-7,0.000025175232,0.00001603073,0.9385079],"study_design_scores_gemma":[0.010764085,0.013830296,0.007370032,0.03797462,0.83378786,0.0009888606,0.00026411645,0.0007957097,0.000003974378,0.0016311161,0.09190334,0.0006860121],"about_ca_topic_score_codex":0.000024329725,"about_ca_topic_score_gemma":0.0000031261714,"teacher_disagreement_score":0.9378219,"about_ca_system_score_codex":0.0002517149,"about_ca_system_score_gemma":0.0017196798,"threshold_uncertainty_score":0.9996535},"labels":[],"label_agreement":null},{"id":"W3194499814","doi":"10.1016/j.jclinepi.2021.08.009","title":"Pearls on science, collaboration, and mentorship in health research: A masterclass conversation with Dr. John Ioannidis","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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. Joseph’s Healthcare Hamilton; Population Health Research Institute; McMaster University; Impact","funders":"","keywords":"Mentorship; Conversation; Enthusiasm; Passion; Medical education; Library science; Psychology; Medicine; Computer science","score_opus":0.9637595246206594,"score_gpt":0.7301382971367617,"score_spread":0.2336212274838977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194499814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80625385,0.001348827,0.0036227147,0.18555522,0.00068224024,0.00036168977,0.000003446981,0.00000112483,0.0021708661],"genre_scores_gemma":[0.9853997,0.0007125263,0.007431884,0.0048650466,0.0002468882,0.0000040319937,0.0000010112443,0.0000055405476,0.0013333522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.67611176,0.26640382,0.047185194,0.001579628,0.007871834,0.00084777374],"domain_scores_gemma":[0.54361284,0.38855708,0.044844277,0.0035629757,0.017649358,0.0017735028],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7912361,0.0001465549,0.006049868,0.0008934739,0.00015695934,0.00026635572,0.00081644027,0.00013774612,0.0006784452],"category_scores_gemma":[0.727821,0.00006673395,0.00053940644,0.0034059505,0.00080971996,0.00035129522,0.00010579041,0.0008616393,0.00012249518],"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":[0.00022660324,0.00019699211,0.8995642,0.000046563615,0.000098194265,0.00004820879,0.0010206538,0.0003406843,0.000013339421,0.02222414,0.062084146,0.014136266],"study_design_scores_gemma":[0.0013128289,0.0019316936,0.8180869,0.00031727817,0.00003622257,0.00010153978,0.0056205164,0.0042293486,0.00000791358,0.051694106,0.116542265,0.00011937221],"about_ca_topic_score_codex":0.000017918337,"about_ca_topic_score_gemma":0.00019762057,"teacher_disagreement_score":0.18069017,"about_ca_system_score_codex":0.0001088833,"about_ca_system_score_gemma":0.0022893513,"threshold_uncertainty_score":0.74284995},"labels":[],"label_agreement":null},{"id":"W3194553102","doi":"10.1016/j.jclinepi.2021.08.008","title":"Methodological options of the nominal group technique for survey item elicitation in health research: A scoping review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":37,"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; McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"CINAHL; Nominal group; Nominal group technique; MEDLINE; Scopus; Protocol (science); Medicine; Transparency (behavior); Family medicine; Computer science; Applied psychology; Psychology; Alternative medicine; Knowledge management; Nursing; Psychological intervention; Pathology","score_opus":0.985554542922434,"score_gpt":0.8264290461240076,"score_spread":0.15912549679842647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194553102","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024697997,0.9567023,0.024253199,0.013341922,0.0005404493,0.005037377,0.000027600747,0.0000071334575,0.00008755606],"genre_scores_gemma":[0.0000043178998,0.9182549,0.08000589,0.0007123966,0.0005117865,0.00044115895,0.00001236326,0.000021934735,0.00003525823],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.449952,0.52794355,0.018916266,0.0007343378,0.0012336535,0.0012202143],"domain_scores_gemma":[0.3099502,0.6752148,0.011477419,0.00066548097,0.0022934612,0.00039860874],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7412996,0.00023772515,0.010406019,0.00052374153,0.0002792042,0.000014868428,0.0019469613,0.0013271258,0.000057756846],"category_scores_gemma":[0.87886155,0.00014685742,0.0027425669,0.0020808587,0.0018085012,0.00009470542,0.00038016372,0.004944752,0.0000018842383],"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":[0.00006259342,0.00034979024,0.0008714891,0.06840657,0.00011027831,0.00001168553,0.00006557566,0.0000022653549,3.1270423e-7,0.025738915,0.013848275,0.89053226],"study_design_scores_gemma":[0.0001632039,0.00073635194,0.0009523651,0.5056415,0.000073970616,0.000043951655,0.000081035636,0.000003054261,1.0547325e-7,0.011419006,0.4807457,0.00013974668],"about_ca_topic_score_codex":0.0010092168,"about_ca_topic_score_gemma":0.0022113323,"teacher_disagreement_score":0.8903925,"about_ca_system_score_codex":0.00048212265,"about_ca_system_score_gemma":0.009283533,"threshold_uncertainty_score":0.99996936},"labels":[],"label_agreement":null},{"id":"W3194642833","doi":"10.1016/j.jclinepi.2021.08.019","title":"GRADE Notes 2: Criteria for searching non-randomized or indirect evidence should be defined early in the guideline production process","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; Cochrane","funders":"","keywords":"Guideline; Randomized controlled trial; Process (computing); Medicine; Production (economics); Computer science; Surgery; Economics","score_opus":0.9647484098054768,"score_gpt":0.7370392871635606,"score_spread":0.22770912264191623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194642833","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6104082,0.0020706917,0.14857702,0.23584613,0.0017454246,0.001275983,0.0000050478407,0.000002382255,0.00006914264],"genre_scores_gemma":[0.88246053,0.0008323763,0.10302557,0.011348159,0.0017408446,0.000078636425,0.0000033511174,0.000014264455,0.00049627235],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6383643,0.27441525,0.08079341,0.0015728472,0.004141577,0.00071260345],"domain_scores_gemma":[0.09055588,0.86780924,0.03311523,0.0023860256,0.005836886,0.0002967514],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8234025,0.0002680896,0.014073999,0.00032903833,0.00012545293,0.00020105757,0.0019454478,0.00026464497,0.00076551165],"category_scores_gemma":[0.98072076,0.00009240035,0.0047945515,0.0012132917,0.00031710154,0.0004157559,0.000096839205,0.0010203173,0.0000305958],"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":[0.048522603,0.0014930725,0.44845587,0.000840882,0.0025838464,0.00028663015,0.007364151,0.0054160804,0.0004346804,0.002867632,0.35149756,0.13023701],"study_design_scores_gemma":[0.05302155,0.0027321568,0.20784424,0.0028315932,0.0035825272,0.0017783358,0.004129867,0.11484607,0.00026653887,0.54158235,0.06637381,0.0010109587],"about_ca_topic_score_codex":0.000018607905,"about_ca_topic_score_gemma":0.00010832849,"teacher_disagreement_score":0.593394,"about_ca_system_score_codex":0.000019734765,"about_ca_system_score_gemma":0.00062043313,"threshold_uncertainty_score":0.9620704},"labels":[],"label_agreement":null},{"id":"W3195005844","doi":"10.1016/j.jclinepi.2021.08.012","title":"Clinical Epidemiology in China series. Paper 1: Evidence-based medicine in China: An oral history study","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"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":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Chinese Academy of Medical Sciences; Capital Medical University; National Natural Science Foundation of China; Lanzhou University","keywords":"China; Economic shortage; Medicine; Alternative medicine; Family medicine; Evidence-based medicine; MEDLINE; Medical education; Quarter (Canadian coin); Epidemiology; Traditional medicine; Political science; History; Law","score_opus":0.9333743691033017,"score_gpt":0.6887830481756219,"score_spread":0.24459132092767988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195005844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88270813,0.017869953,0.0064599463,0.08466798,0.0069144564,0.00065465027,0.0000025640554,0.000005879339,0.00071644917],"genre_scores_gemma":[0.94054496,0.0034407533,0.025094923,0.02689355,0.0023084409,0.000022367303,0.000005481615,0.00003125344,0.0016582878],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.20704195,0.64378804,0.14241101,0.002702933,0.0029792686,0.0010768167],"domain_scores_gemma":[0.17866942,0.72996074,0.078738205,0.007684946,0.0030284442,0.0019182449],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.88457596,0.00062675565,0.03964883,0.0009171775,0.00006785481,0.000026806294,0.0033472686,0.0009896135,0.016815754],"category_scores_gemma":[0.95785934,0.00030122724,0.006001656,0.0015170856,0.001186932,0.0009144465,0.00030908323,0.0038943721,0.0002785091],"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":[0.00045684655,0.00133002,0.9093713,0.000026695381,0.00021746423,0.0005467107,0.0002143238,0.0012313216,0.0000025503405,0.0014015266,0.05378811,0.031413134],"study_design_scores_gemma":[0.0024155343,0.0033491605,0.89828473,0.00033491678,0.0002695231,0.00014072446,0.00046095395,0.0040467307,8.976592e-8,0.032815643,0.057660114,0.00022187164],"about_ca_topic_score_codex":0.0003444297,"about_ca_topic_score_gemma":0.0023816226,"teacher_disagreement_score":0.08617271,"about_ca_system_score_codex":0.00025249226,"about_ca_system_score_gemma":0.0016628082,"threshold_uncertainty_score":0.999944},"labels":[],"label_agreement":null},{"id":"W3195266702","doi":"10.1016/j.jclinepi.2021.08.014","title":"Clinical Epidemiology in China series. Paper 3: The methodological and reporting quality of systematic reviews and meta-analyses published by China' researchers in English-language is higher than those published in Chinese-language","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"National Office for Philosophy and Social Sciences","keywords":"MEDLINE; Meta-analysis; English language; Medicine; Systematic review; Chinese language; China; Protocol (science); Quality Score; Quality (philosophy); Medical physics; Psychology; Alternative medicine; Linguistics; Pathology; Mathematics education","score_opus":0.971362352550121,"score_gpt":0.7473260955267289,"score_spread":0.22403625702339214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195266702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84182465,0.11519535,0.0010686455,0.03915416,0.00066085416,0.0013564379,0.000017627606,0.0000043113037,0.00071796565],"genre_scores_gemma":[0.944506,0.011665663,0.034520738,0.006952425,0.0004009269,0.000114873896,0.000012628319,0.000030590538,0.0017961836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.057031196,0.75683486,0.17992732,0.0025927708,0.002556627,0.001057203],"domain_scores_gemma":[0.032106407,0.7927721,0.16569863,0.0064122407,0.0020333875,0.0009772376],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9440182,0.0007257812,0.061855115,0.0007407795,0.00008174846,0.00024269252,0.00257433,0.0011137897,0.0044896905],"category_scores_gemma":[0.99202883,0.0002615007,0.008854493,0.0030266093,0.0011412406,0.001074694,0.0008748624,0.0042881845,0.000008787489],"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":[0.00019042949,0.0003294588,0.9816354,0.0016703126,0.0018294016,0.00014033873,0.0021548276,0.000035091092,0.00003834456,0.00077716226,0.009056481,0.0021427553],"study_design_scores_gemma":[0.0010502735,0.00024553275,0.96163464,0.00047703504,0.0015340928,0.00012812798,0.002713076,0.0005025611,0.0000021494716,0.03029541,0.0011626309,0.0002544782],"about_ca_topic_score_codex":0.00060312974,"about_ca_topic_score_gemma":0.0009018079,"teacher_disagreement_score":0.10352969,"about_ca_system_score_codex":0.000056131346,"about_ca_system_score_gemma":0.00031219923,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W3196269529","doi":"10.1016/j.jclinepi.2021.08.018","title":"Response to Weinfurt and Cappelleri on “Patient reported outcome measures in clinical trials should be initially analyzed as continuous outcomes for statistical significance and responder analyses should be reserved as secondary analyses”","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Impact; University of Manitoba; McMaster University; Population Health Research Institute","funders":"","keywords":"Clinical trial; Randomization; Outcome (game theory); Medicine; Statistical significance; Statistical power; Baseline (sea); Patient-reported outcome; Clinical significance; Physical therapy; Statistics; Internal medicine; Quality of life (healthcare); Mathematics","score_opus":0.9500332984706102,"score_gpt":0.7334671665296986,"score_spread":0.21656613194091168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196269529","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12932205,0.0007261349,0.051812895,0.80696446,0.004482487,0.0042899963,0.0019502395,0.00008009175,0.00037165475],"genre_scores_gemma":[0.009716562,0.0009134417,0.40375346,0.5810184,0.0034067999,0.00016643996,0.00006300638,0.00024833152,0.00071357685],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.68330884,0.244938,0.0635458,0.0035648413,0.002630694,0.0020118116],"domain_scores_gemma":[0.100060135,0.8705854,0.02302443,0.001794613,0.0027077915,0.0018276374],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.40102667,0.001668679,0.03377798,0.001515746,0.00019747161,0.00017618416,0.0012747592,0.00659106,0.0007394861],"category_scores_gemma":[0.9881882,0.0011922269,0.0046137827,0.00087064103,0.0021105257,0.0001680435,0.00067273015,0.0136718815,0.000008830328],"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":[0.15362808,0.0019122364,0.025627162,0.0007655681,0.011867286,0.022105597,0.00018443888,0.00009158942,0.0002520032,0.0033800658,0.76212895,0.018056992],"study_design_scores_gemma":[0.032345884,0.034005903,0.11869044,0.0021851002,0.012027589,0.0010873734,0.00059617945,0.00037100352,0.00010965981,0.5885821,0.20678325,0.0032155016],"about_ca_topic_score_codex":0.00023088517,"about_ca_topic_score_gemma":0.00009361682,"teacher_disagreement_score":0.62564737,"about_ca_system_score_codex":0.0002501601,"about_ca_system_score_gemma":0.0027782298,"threshold_uncertainty_score":0.999606},"labels":[],"label_agreement":null},{"id":"W3199254532","doi":"10.1016/j.jclinepi.2021.09.017","title":"Reporting transparency and completeness in trials: Paper 1: Introduction - Better reporting for disruptive clinical trials using routinely collected data","year":2021,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McGill University; Jewish General Hospital","funders":"","keywords":"Randomized controlled trial; Clinical trial; Medicine; Randomization; Health care; Transparency (behavior); Family medicine; Medical physics; Surgery; Computer science; Pathology; Political science","score_opus":0.9870001386006326,"score_gpt":0.7797982772088923,"score_spread":0.20720186139174035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199254532","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023234975,0.005128706,0.17090493,0.014274456,0.7836575,0.0021426198,0.0006247023,0.0000053123904,0.00002681748],"genre_scores_gemma":[0.0014262885,0.0018660731,0.09325316,0.00071849255,0.9016956,0.000027197386,0.0005064568,0.000058058013,0.00044864355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.02083554,0.48573264,0.48484612,0.0037250167,0.004130654,0.00073004165],"domain_scores_gemma":[0.00034048402,0.5510505,0.43897006,0.0035153294,0.0057490314,0.00037463027],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.9847037,0.0008440502,0.10613722,0.0007539974,0.00021471204,0.0003688531,0.0029342985,0.0030104069,0.0010465904],"category_scores_gemma":[0.99933356,0.00041663245,0.016290177,0.00125338,0.00038617477,0.00061397837,0.000535021,0.0046713655,0.0000065441154],"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":[0.0008270547,0.0001850305,0.0739396,0.00019231162,0.0021258236,0.00012835841,0.00005228227,0.00014002968,0.0000091815555,0.000020230627,0.88536763,0.03701248],"study_design_scores_gemma":[0.0036803402,0.00055617746,0.023001036,0.0009843027,0.006181095,0.00021043504,0.00032363972,0.016387483,3.826523e-7,0.0106956465,0.93747836,0.000501125],"about_ca_topic_score_codex":0.00007616703,"about_ca_topic_score_gemma":0.00023033592,"teacher_disagreement_score":0.11803815,"about_ca_system_score_codex":0.0001250333,"about_ca_system_score_gemma":0.0029240316,"threshold_uncertainty_score":0.9998666},"labels":[],"label_agreement":null},{"id":"W3199384863","doi":"10.1016/j.jclinepi.2021.09.012","title":"Reporting transparency and completeness in Trials: Paper 2 - reporting of randomised trials using registries was often inadequate and hindered the interpretation of results","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; Ottawa Hospital; Centre for Family Medicine; Institute for Clinical Evaluative Sciences; Children's Hospital of Eastern Ontario; McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research; National Institute for Health and Care Research; Department of Health and Social Care; Government of Canada; Steno Diabetes Center Aarhus; Wellcome Trust; Medical Research Council; University of Ottawa","keywords":"Consolidated Standards of Reporting Trials; Medicine; Clinical trial; Data quality; Randomized controlled trial; Research design; Trial registration; Completeness (order theory); MEDLINE; Medical physics; Family medicine; Statistics; Internal medicine","score_opus":0.9639259368281086,"score_gpt":0.6993507195125478,"score_spread":0.2645752173155608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199384863","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9316907,0.0052624145,0.053247884,0.008663379,0.0004994325,0.00047550906,0.000009718479,7.314723e-7,0.00015025897],"genre_scores_gemma":[0.98663324,0.0008743309,0.011967238,0.00032964945,0.000142127,0.0000028528275,0.0000022439767,0.0000053389367,0.000042969285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.104596585,0.41309825,0.47843415,0.0011592451,0.0023267174,0.0003850435],"domain_scores_gemma":[0.0072914287,0.52901363,0.46004587,0.0012029625,0.0023063044,0.00013975955],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9237108,0.0002009078,0.02919426,0.00022580258,0.000061869214,0.00005976835,0.0004528406,0.00023810503,0.00010713503],"category_scores_gemma":[0.99260765,0.00008033297,0.0037823298,0.00052617,0.00037895347,0.00020544209,0.00007993811,0.0005034897,3.346359e-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":[0.018201118,0.00025518745,0.6062014,0.0006522977,0.0030681754,0.00025199592,0.0042650383,0.007339167,0.0025778487,0.001572713,0.00233592,0.3532791],"study_design_scores_gemma":[0.04059056,0.0008208669,0.6090946,0.0036235019,0.0049055805,0.0014196519,0.008392831,0.12804016,0.00033326703,0.19921245,0.0031190536,0.00044742116],"about_ca_topic_score_codex":0.000063240586,"about_ca_topic_score_gemma":0.000061011626,"teacher_disagreement_score":0.3528317,"about_ca_system_score_codex":0.000012285885,"about_ca_system_score_gemma":0.000397312,"threshold_uncertainty_score":0.98521835},"labels":[],"label_agreement":null},{"id":"W3199432622","doi":"10.1016/j.jclinepi.2021.09.010","title":"Reporting transparency and completeness in trials: Paper 3 – trials conducted using administrative databases do not adequately report elements related to use of databases","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; Western University; Ottawa Hospital; Jewish General Hospital","funders":"Steno Diabetes Center Aarhus; Medical Research Council; National Institute for Health and Care Research; Wellcome Trust","keywords":"Consolidated Standards of Reporting Trials; Medicine; Clinical trial; MEDLINE; Database; Transparency (behavior); Data extraction; Family medicine; Cochrane Library; Randomized controlled trial; Research design; Computer science; Statistics; Surgery; Internal medicine","score_opus":0.9944785617407608,"score_gpt":0.7868130592167126,"score_spread":0.20766550252404814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199432622","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01403297,0.9672921,0.012204911,0.0006187181,0.002265635,0.0025897606,0.0009544571,0.000002919427,0.000038561328],"genre_scores_gemma":[0.0009767215,0.9150179,0.08275301,0.0004099237,0.0003342197,0.000027912374,0.0002843662,0.0000381958,0.00015772384],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.08204102,0.4919698,0.4192448,0.0025642568,0.0035494165,0.000630714],"domain_scores_gemma":[0.013176374,0.57568425,0.40361643,0.0036615792,0.0032347017,0.0006266829],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9046634,0.00093489385,0.13468213,0.0012012447,0.00008987597,0.00017683672,0.0015311083,0.0006530655,0.0032543489],"category_scores_gemma":[0.9911097,0.00042911674,0.015243543,0.0021121597,0.00034925956,0.00069843966,0.00036451823,0.0018069991,0.000016183245],"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":[0.0004251969,0.0006439316,0.06912317,0.0047726096,0.009056697,0.0039370186,0.000109066066,0.00012923067,0.000020514017,0.0018057681,0.008483388,0.90149343],"study_design_scores_gemma":[0.0010116813,0.00032702668,0.0032672065,0.023470221,0.009959474,0.0027274645,0.0002259111,0.00016113408,0.0000012500568,0.0005356834,0.9578459,0.00046704995],"about_ca_topic_score_codex":0.00010393738,"about_ca_topic_score_gemma":0.00007837845,"teacher_disagreement_score":0.9493625,"about_ca_system_score_codex":0.00006278354,"about_ca_system_score_gemma":0.0027561057,"threshold_uncertainty_score":0.99981606},"labels":[],"label_agreement":null},{"id":"W3200069738","doi":"10.1016/j.jclinepi.2021.09.023","title":"A few panel members dominated guideline development meeting discussions: Social network analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Impact; Shell (Canada); McMaster University; University of Toronto","funders":"Agency for Healthcare Research and Quality","keywords":"Guideline; Betweenness centrality; Grading (engineering); Medicine; Conversation; Closeness; Psychology; Applied psychology; Family medicine; Medical education; Centrality; Statistics; Engineering; Pathology; Mathematics","score_opus":0.837852655225503,"score_gpt":0.7511068376676926,"score_spread":0.08674581755781041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200069738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4792018,0.00039552126,0.06858599,0.44205517,0.0059367465,0.00054290594,0.000024561887,0.000058815156,0.0031985096],"genre_scores_gemma":[0.41839126,0.00076483533,0.3033388,0.26662907,0.00882459,0.00004724355,0.00005094758,0.000043016316,0.0019102474],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.94299,0.03704507,0.017779732,0.00043539566,0.0005082171,0.0012415724],"domain_scores_gemma":[0.8690882,0.11572733,0.0118225245,0.00035182582,0.0020183024,0.0009918741],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14063749,0.00020523104,0.003367725,0.00024617877,0.0011298758,0.000006629882,0.00045248886,0.0005453918,0.0021640547],"category_scores_gemma":[0.273525,0.00013921413,0.00083987025,0.0017326091,0.00022752599,0.00014049302,0.00030575358,0.0020480151,0.000097168406],"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":[0.00023250052,0.0001063082,0.63496023,0.000076266195,0.0010301354,0.000071786126,0.0031749308,0.0019704893,0.000014144842,0.0017117746,0.33176562,0.024885805],"study_design_scores_gemma":[0.0019761026,0.00009062617,0.4517107,0.0001718858,0.00039846188,0.000015156004,0.002991671,0.0014597843,0.0000024522064,0.0032976437,0.5376988,0.00018672412],"about_ca_topic_score_codex":0.00008955684,"about_ca_topic_score_gemma":0.0007024861,"teacher_disagreement_score":0.23475279,"about_ca_system_score_codex":0.00023594464,"about_ca_system_score_gemma":0.0042824913,"threshold_uncertainty_score":0.9987481},"labels":[],"label_agreement":null},{"id":"W3200212953","doi":"10.1016/j.jclinepi.2021.09.011","title":"Reporting transparency and completeness in trials: Paper 4 - reporting of randomised controlled trials conducted using routinely collected electronic records – room for improvement","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; Western University; Ottawa Hospital; Jewish General Hospital","funders":"Canadian Institutes of Health Research; National Institute for Health and Care Research; Department of Health and Social Care; Steno Diabetes Center Aarhus; Wellcome Trust; Medical Research Council; University of Ottawa","keywords":"Consolidated Standards of Reporting Trials; Medicine; Randomized controlled trial; MEDLINE; Electronic health record; Sample size determination; Research design; Family medicine; Statistics; Health care; Surgery; Mathematics","score_opus":0.9521031685245965,"score_gpt":0.691188109010931,"score_spread":0.26091505951366556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200212953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8800378,0.004664981,0.10892322,0.0025454967,0.0011781508,0.0025305299,0.000012893526,0.0000021580704,0.000104756386],"genre_scores_gemma":[0.96640486,0.0007149523,0.031241158,0.0007194394,0.00053946686,0.00006267572,0.000008365748,0.000018233004,0.00029086907],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.09687859,0.34434295,0.55403113,0.0015662637,0.002300488,0.0008805853],"domain_scores_gemma":[0.0062499633,0.5204033,0.46674734,0.0011158463,0.0052358247,0.00024767633],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.94983333,0.00039680023,0.08443497,0.00046623318,0.00010850027,0.00009884775,0.00062068104,0.00043057842,0.001275862],"category_scores_gemma":[0.9952955,0.00018073755,0.015143659,0.0010341294,0.00012199963,0.0001934856,0.00005999688,0.0007531953,8.9788705e-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":[0.067706235,0.0014015089,0.7127243,0.00075862027,0.01856116,0.0002899216,0.00054121175,0.004867436,0.05327742,0.0026616275,0.0068070646,0.13040343],"study_design_scores_gemma":[0.40373066,0.0043043313,0.1724558,0.0018553145,0.017524157,0.001106949,0.0025377497,0.19883506,0.0008813368,0.18572985,0.009917426,0.0011213678],"about_ca_topic_score_codex":0.000048747548,"about_ca_topic_score_gemma":0.0001542716,"teacher_disagreement_score":0.54026854,"about_ca_system_score_codex":0.0000678267,"about_ca_system_score_gemma":0.002011455,"threshold_uncertainty_score":0.9996371},"labels":[],"label_agreement":null},{"id":"W3200235637","doi":"10.1016/j.jclinepi.2021.09.018","title":"Focus groups and interviews with the public led to the development of a template for a GRADE Plain Language Recommendation (PLR)","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"McMaster University; Impact","funders":"","keywords":"Plain language; Credibility; Focus group; Guideline; Disk formatting; Plain English; Checklist; Public health; Health care; Worksheet; Medicine; Perception; Medical education; Computer science; Psychology; Nursing","score_opus":0.6653895496318437,"score_gpt":0.5970784886643711,"score_spread":0.06831106096747264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200235637","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":[0.30588666,0.0024152168,0.04231165,0.6473403,0.0008625607,0.0010613523,0.000016895141,0.000009236723,0.00009609914],"genre_scores_gemma":[0.9191357,0.00037654198,0.062389046,0.017446375,0.0003414835,0.00020494273,0.000018768125,0.000017305374,0.00006982777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.979783,0.015181288,0.0043971147,0.000189781,0.00011929741,0.00032952125],"domain_scores_gemma":[0.93052334,0.06441191,0.0037248936,0.00046074463,0.00067381945,0.0002053127],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023591354,0.00011743499,0.0010928278,0.00006023808,0.0004406812,0.0000046020073,0.00044940403,0.00019879689,0.0000581932],"category_scores_gemma":[0.04902662,0.000056153796,0.00016423447,0.00018642293,0.00011587601,0.000080644946,0.00028388435,0.0012000869,0.000006458176],"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":[0.0023865616,0.00050763093,0.3352373,0.0008756247,0.00075009075,0.0000067008323,0.07729553,0.000024024934,0.000075211545,0.0134175625,0.07403008,0.49539372],"study_design_scores_gemma":[0.004809112,0.0016150785,0.19611295,0.0010447531,0.000102436024,0.00007066338,0.055751104,0.0007073167,0.00003578254,0.006549012,0.7329827,0.00021911006],"about_ca_topic_score_codex":0.000026722497,"about_ca_topic_score_gemma":0.0029147973,"teacher_disagreement_score":0.6589526,"about_ca_system_score_codex":0.000069395646,"about_ca_system_score_gemma":0.000886335,"threshold_uncertainty_score":0.95898384},"labels":[],"label_agreement":null},{"id":"W3200374194","doi":"10.1016/j.jclinepi.2021.09.002","title":"Domperidone increases harmful cardiac events in Parkinson's disease: A Bayesian re-analysis of an observational study","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","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":"Montreal Heart Institute; Bell (Canada); McGill University; Université de Montréal; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Frequentist inference; Prior probability; Credible interval; Medicine; Domperidone; Bayesian probability; Relative risk; Confidence interval; Observational study; Internal medicine; Statistics; Bayesian inference; Mathematics","score_opus":0.22477499002992185,"score_gpt":0.4888004608138724,"score_spread":0.26402547078395056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200374194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932687,0.0015108068,0.00017706965,0.00437414,0.00043893055,0.00017327155,0.000028234532,0.000005754035,0.000023092498],"genre_scores_gemma":[0.9939111,0.00090678554,0.0019117667,0.0021444529,0.0009775021,0.000008552641,0.00008268156,0.000012505066,0.000044666616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9857384,0.009135666,0.004098992,0.00040885792,0.0003072241,0.00031089206],"domain_scores_gemma":[0.9834592,0.013164219,0.0018265937,0.00048953557,0.00055652956,0.0005039371],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012294996,0.00018289495,0.0049228147,0.000322081,0.000036474714,0.0000016114419,0.00014172184,0.00023598575,0.00022130781],"category_scores_gemma":[0.05051241,0.00014306791,0.0021671674,0.0007852321,0.0001785823,0.00010959819,0.000069406844,0.0008942904,0.0000024415672],"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":[0.0040548593,0.0023608082,0.983251,0.000021728187,0.004663928,0.0012079421,0.000035797122,0.0021465344,0.00010895074,0.00016866365,0.00027152163,0.0017083187],"study_design_scores_gemma":[0.002355976,0.0014001966,0.9888089,0.00006246847,0.0040354435,0.00005227133,0.00014000572,0.0009180544,0.000010321426,0.0014854281,0.00062701385,0.00010396195],"about_ca_topic_score_codex":0.000077100085,"about_ca_topic_score_gemma":0.000071415685,"teacher_disagreement_score":0.038217414,"about_ca_system_score_codex":0.000049436694,"about_ca_system_score_gemma":0.0008506707,"threshold_uncertainty_score":0.95748556},"labels":[],"label_agreement":null},{"id":"W3200589665","doi":"10.1016/j.jclinepi.2021.09.016","title":"Commentary on controversy and debate 4 paper series: Questionable utility of the relative risk in clinical research","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa","funders":"","keywords":"Odds; Series (stratigraphy); Probabilistic logic; Relative risk; Meta-analysis; Point (geometry); Systematic review; Resource (disambiguation); Odds ratio; Cochrane collaboration; MEDLINE; Medicine; Computer science; Epistemology; Mathematics; Philosophy; Confidence interval; Biology; Cochrane Library; Pathology; Internal medicine","score_opus":0.9036224762763756,"score_gpt":0.6843450714432695,"score_spread":0.2192774048331061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200589665","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021886192,0.0032581154,0.0005664406,0.9694688,0.002384385,0.00055716623,0.00006872819,7.419492e-7,0.0018094755],"genre_scores_gemma":[0.025300764,0.009370041,0.0045566238,0.95141065,0.004591579,0.000012036878,0.000011983747,0.000024040995,0.0047222655],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.3445165,0.5821104,0.0673921,0.0012962496,0.004157819,0.00052692596],"domain_scores_gemma":[0.08504391,0.8459603,0.060198434,0.004201599,0.004294943,0.00030078238],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8254656,0.0003723679,0.020160586,0.00036577083,0.00014364807,0.00006807953,0.002470724,0.0017918828,0.0032096873],"category_scores_gemma":[0.9202622,0.00014651785,0.0075098746,0.00081273954,0.0019164168,0.00025643755,0.00057451817,0.013805993,0.00007736749],"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":[0.00013752346,0.000084415464,0.3741745,0.000029161682,0.00048030054,0.00005682962,0.000023148443,0.000011048089,4.5792156e-8,0.0004009543,0.62170863,0.0028934272],"study_design_scores_gemma":[0.00053651776,0.000438603,0.2797671,0.0003214201,0.00024546465,0.000029603807,0.000087531655,0.00028781124,8.282036e-8,0.10645084,0.6117606,0.00007442656],"about_ca_topic_score_codex":0.00013187257,"about_ca_topic_score_gemma":0.00016293686,"teacher_disagreement_score":0.26384994,"about_ca_system_score_codex":0.000053635944,"about_ca_system_score_gemma":0.00057053193,"threshold_uncertainty_score":0.999504},"labels":[],"label_agreement":null},{"id":"W3204875472","doi":"10.1016/j.jclinepi.2021.09.028","title":"A taxonomy and framework for identifying and developing actionable statements in guidelines suggests avoiding informal recommendations","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"University of Ottawa; Université Laval; Impact; The Quebec Population Health Research Network; McMaster University; St. Joseph’s Healthcare Hamilton; Public Health Agency of Canada; Bruyère; Cochrane","funders":"World Health Organization","keywords":"Guideline; Standardization; Taxonomy (biology); Process (computing); Process management; Presentation (obstetrics); Conceptual framework; Computer science; Identification (biology); Knowledge management; Management science; Psychology; Medicine; Business; Engineering; Sociology; Pathology","score_opus":0.8277265735514102,"score_gpt":0.6885333178676506,"score_spread":0.13919325568375962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204875472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43856564,0.00059943536,0.45209506,0.10726836,0.0011056369,0.00032425867,0.0000065634813,0.0000068188665,0.000028236966],"genre_scores_gemma":[0.14312851,0.0068512447,0.83328587,0.015789121,0.000823023,0.000023011928,0.000031523712,0.000013751526,0.000053925687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99066377,0.0011979734,0.0074923206,0.0002444796,0.00012641169,0.00027501813],"domain_scores_gemma":[0.91090965,0.08378123,0.0036206266,0.00016061007,0.0012552437,0.00027264666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03055766,0.00012344547,0.0012881429,0.0001577164,0.00010393944,0.000021221045,0.00005887485,0.0002363675,0.00005670352],"category_scores_gemma":[0.4301783,0.00010770224,0.00017570819,0.00015908747,0.00007827852,0.00062038953,0.00010855468,0.0009567704,0.0000016610546],"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":[0.0007781699,0.00013098205,0.75633365,0.00021226118,0.0002604663,0.000035135236,0.00009482373,0.00006121289,0.00004597168,0.0076880027,0.006275048,0.22808428],"study_design_scores_gemma":[0.009608774,0.000907969,0.62030655,0.0018141028,0.00036765388,0.0009795082,0.004012874,0.004129458,0.00007357736,0.09324272,0.2642711,0.0002857144],"about_ca_topic_score_codex":0.000029271616,"about_ca_topic_score_gemma":0.00008956193,"teacher_disagreement_score":0.39962065,"about_ca_system_score_codex":0.000058711794,"about_ca_system_score_gemma":0.0006593524,"threshold_uncertainty_score":0.9982449},"labels":[],"label_agreement":null},{"id":"W3205958333","doi":"10.1016/j.jclinepi.2021.10.001","title":"More work needed on decision analysis for shared decision-making: A scoping review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":9,"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; University of Toronto; McMaster University; Impact","funders":"","keywords":"Data extraction; Psychological intervention; Decision analysis; Inclusion (mineral); Decision aids; Decision support system; R-CAST; Multiple-criteria decision analysis; Research design; Meta-analysis; Population; MEDLINE; Management science; Psychology; Applied psychology; Computer science; Medicine; Business decision mapping; Alternative medicine; Operations research; Data mining; Nursing; Social psychology; Statistics; Engineering; Environmental health","score_opus":0.8410875817743056,"score_gpt":0.722644684016217,"score_spread":0.1184428977580887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205958333","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":[0.000007637399,0.9678017,0.016176056,0.0064271153,0.0048382403,0.0045448346,0.00009311622,0.00003208264,0.00007921917],"genre_scores_gemma":[0.000008194052,0.89567244,0.07775772,0.02405309,0.0016278073,0.00058241485,0.00015198765,0.000096988006,0.000049358037],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.919138,0.04467553,0.033330273,0.0010737376,0.0006998304,0.0010825898],"domain_scores_gemma":[0.4081792,0.55299455,0.03264628,0.0027192864,0.0026887045,0.0007720128],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.049412295,0.00078757585,0.02786748,0.0011212656,0.0006878423,0.000013672287,0.0024589465,0.0028820653,0.0009910332],"category_scores_gemma":[0.66003406,0.0005400494,0.010597519,0.0027616837,0.00020717135,0.00014225955,0.00082410313,0.0075366427,0.00013886977],"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":[0.00037177044,0.00015294913,0.002937751,0.06642824,0.0015779454,0.000019688983,0.00008556801,0.000054963803,3.1626038e-10,0.00019113497,0.055783175,0.8723968],"study_design_scores_gemma":[0.00054414704,0.0002813118,0.0003506525,0.5741648,0.003607787,0.00001102886,0.000100579666,0.000032656477,3.412228e-10,0.00086971564,0.4197977,0.0002396116],"about_ca_topic_score_codex":0.000012484505,"about_ca_topic_score_gemma":0.000038038906,"teacher_disagreement_score":0.8721572,"about_ca_system_score_codex":0.0005785852,"about_ca_system_score_gemma":0.006526458,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W3208267072","doi":"10.1016/j.jclinepi.2021.10.010","title":"Reassembling the fragility index: a demonstration of statistical reasoning","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Fragility; Index (typography); Statistical analysis; Statistics; Psychology; Medicine; Computer science; Mathematics; Physics; World Wide Web; Thermodynamics","score_opus":0.5784651397073408,"score_gpt":0.590029371624033,"score_spread":0.011564231916692203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208267072","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":[0.0048895604,0.00028531504,0.48559502,0.50743896,0.0008325654,0.00013204131,0.000048460486,0.000010538135,0.0007675636],"genre_scores_gemma":[0.20805737,0.0007206031,0.25874573,0.5189934,0.012878644,0.000019881503,0.000062242376,0.000053093223,0.0004690661],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.968668,0.015477141,0.013472739,0.00064113404,0.0013168217,0.0004241697],"domain_scores_gemma":[0.6710325,0.3089209,0.016104227,0.0013085802,0.0024508967,0.00018290806],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.11256364,0.00022598526,0.0033703826,0.00018241706,0.00012764777,0.00004708046,0.0015929369,0.0015072862,0.00022870043],"category_scores_gemma":[0.47017708,0.00012204738,0.0011997866,0.00048615955,0.00093575375,0.00009858961,0.000233299,0.006047854,0.000008338321],"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":[0.00006561767,0.000054910513,0.044299293,0.000014211191,0.00007388428,0.00006251403,0.000011476797,0.00010559908,0.000002098281,0.009114731,0.9143008,0.03189489],"study_design_scores_gemma":[0.00025909458,0.00037191235,0.07856063,0.00029128126,0.0001390614,0.00040123795,0.000057488105,0.008007712,0.000006351809,0.35879597,0.55293494,0.00017427793],"about_ca_topic_score_codex":0.000057992256,"about_ca_topic_score_gemma":0.000014142159,"teacher_disagreement_score":0.3613658,"about_ca_system_score_codex":0.000034065833,"about_ca_system_score_gemma":0.00083664746,"threshold_uncertainty_score":0.99978894},"labels":[],"label_agreement":null},{"id":"W3208518640","doi":"10.1016/j.jclinepi.2021.10.019","title":"Small differences in EQ-5D-5L health utility scores were interpreted differently between and within respondents","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Impact; University of Alberta","funders":"Alberta Innovates; EuroQol Research Foundation","keywords":"Pairwise comparison; EQ-5D; Ordinal Scale; Confidence interval; Valuation (finance); Demography; Psychology; Preference; Ordinal data; Population; Time-trade-off; Statistics; Medicine; Quality of life (healthcare); Mathematics; Economics","score_opus":0.8279226762337704,"score_gpt":0.5692187134880978,"score_spread":0.25870396274567253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208518640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91326696,0.0048983437,0.00485679,0.07510322,0.0014553878,0.00019921435,0.00008670859,0.000009309071,0.00012406828],"genre_scores_gemma":[0.97723883,0.001552069,0.0042815944,0.016103696,0.00064021355,0.0000055777177,0.000011588481,0.000016739938,0.00014967746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95939285,0.0142869605,0.02491363,0.0007197089,0.00010243698,0.0005844226],"domain_scores_gemma":[0.9201989,0.061394095,0.01695105,0.0005436919,0.00016900263,0.0007432591],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14260778,0.00023286253,0.00616426,0.00034518843,0.00008911777,0.00003264849,0.00041765705,0.00045842803,0.00020254422],"category_scores_gemma":[0.17698416,0.00022554096,0.00040868102,0.00016383224,0.00029324164,0.00022424501,0.00016723709,0.0012922734,0.000056725596],"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":[0.00012213069,0.00012820131,0.9872721,0.00015648453,0.000116992174,0.0000071182517,0.00050902023,0.000005882032,1.6928969e-7,0.008269612,0.0019546452,0.0014576808],"study_design_scores_gemma":[0.001327557,0.0004390148,0.914607,0.0003236717,0.000008535172,0.000020994854,0.00034187068,0.0011757335,5.1555014e-7,0.08048948,0.0011118305,0.00015382547],"about_ca_topic_score_codex":0.0005054653,"about_ca_topic_score_gemma":0.0009758201,"teacher_disagreement_score":0.07266509,"about_ca_system_score_codex":0.00017581962,"about_ca_system_score_gemma":0.0006655148,"threshold_uncertainty_score":0.91972935},"labels":[],"label_agreement":null},{"id":"W3209356982","doi":"10.1016/j.jclinepi.2021.10.017","title":"Challenges of evidence synthesis during the 2020 COVID pandemic: a scoping review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":30,"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":"Coronavirus disease 2019 (COVID-19); Pandemic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Betacoronavirus; Coronavirus Infections; MEDLINE; Medicine; Geography; Virology; Political science; Outbreak; Infectious disease (medical specialty); Disease","score_opus":0.9844143236810919,"score_gpt":0.7589569010387264,"score_spread":0.22545742264236557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209356982","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005915874,0.98686266,0.00085265643,0.00965227,0.0011675517,0.001216107,0.000008304196,0.0000021036665,0.00023243137],"genre_scores_gemma":[0.000011101149,0.9948866,0.0020133718,0.0013884477,0.0012808787,0.00005861243,6.5045583e-7,0.000025663714,0.00033467048],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.2643984,0.5457953,0.18162008,0.0021324907,0.005356605,0.0006971083],"domain_scores_gemma":[0.032560173,0.7801163,0.1777232,0.0059577734,0.0030740856,0.0005684625],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.83047885,0.000757164,0.09555651,0.0003339912,0.000119711214,0.000077221644,0.0069251275,0.0008655552,0.0052642333],"category_scores_gemma":[0.97572714,0.00023561009,0.036711697,0.001370371,0.0004887809,0.00021762631,0.0006957695,0.00244592,0.00041073211],"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":[0.0000060791526,0.000040947813,0.0012264599,0.109913416,0.0013627936,0.0000435589,0.000011472239,0.000004968837,1.5182705e-8,0.00020649546,0.011430078,0.8757537],"study_design_scores_gemma":[0.00004601551,0.000063347856,0.0002595625,0.47540864,0.004872341,0.00086564664,0.000026709504,0.0000064480114,1.3784342e-8,0.0005263644,0.5177754,0.00014948485],"about_ca_topic_score_codex":0.0000024571568,"about_ca_topic_score_gemma":0.000018224133,"teacher_disagreement_score":0.8756042,"about_ca_system_score_codex":0.00006860868,"about_ca_system_score_gemma":0.0022768944,"threshold_uncertainty_score":0.99985546},"labels":[],"label_agreement":null},{"id":"W3211348622","doi":"10.1016/j.jclinepi.2021.10.026","title":"Missing trials in drug regulatory dossiers may have good reasons, but should be predefined and transparent","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Attention Deficit Hyperactivity Disorder","field":"Medicine","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":"Medicine; Drug; Drug trial; Clinical trial; Pharmacology; Internal medicine","score_opus":0.5526088569767381,"score_gpt":0.5541708205289659,"score_spread":0.0015619635522278186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211348622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8538992,0.0047033546,0.0016423776,0.13832545,0.0006229691,0.00018147008,0.000009273734,0.00001073891,0.00060520065],"genre_scores_gemma":[0.981947,0.0026138304,0.007396252,0.0064434963,0.00054153433,0.0000034147104,0.000010150529,0.000025415104,0.0010188861],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98004514,0.01211058,0.0067063207,0.0004259364,0.0003197738,0.00039223235],"domain_scores_gemma":[0.9433848,0.051910143,0.0033992103,0.00040489764,0.00030479368,0.000596118],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04893736,0.0002185629,0.004934308,0.00016860066,0.00005064814,0.000011491153,0.00010344135,0.0005239083,0.0003044727],"category_scores_gemma":[0.20380265,0.00016601854,0.0010627749,0.00012881432,0.0003102832,0.00012595051,0.000040549407,0.0016416184,0.0000023117166],"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":[0.0017430895,0.0007049018,0.9690322,0.000108770015,0.000380139,0.000517544,0.0001267967,0.00015350948,0.00046287116,0.0005721796,0.004704404,0.021493582],"study_design_scores_gemma":[0.00826113,0.00040517567,0.97250223,0.0006151235,0.0005786548,0.0012402061,0.0012370634,0.00045772924,0.00006919171,0.0016537829,0.012806949,0.00017278362],"about_ca_topic_score_codex":0.00004457116,"about_ca_topic_score_gemma":0.00007960097,"teacher_disagreement_score":0.1548653,"about_ca_system_score_codex":0.00007668721,"about_ca_system_score_gemma":0.0006963494,"threshold_uncertainty_score":0.97931916},"labels":[],"label_agreement":null},{"id":"W3211391531","doi":"10.1016/j.jclinepi.2021.11.026","title":"GRADE guidance 24 optimizing the integration of randomized and non-randomized studies of interventions in evidence syntheses and health guidelines","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":160,"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; McMaster University; Impact","funders":"Medical Research Council; McMaster University","keywords":"Randomized controlled trial; Psychological intervention; Systematic review; Guideline; Evidence-based practice; Evidence-based medicine; Medicine; MEDLINE; Alternative medicine; Confounding; Medical education; Family medicine; Nursing","score_opus":0.9577948241457491,"score_gpt":0.8003939491537894,"score_spread":0.15740087499195976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211391531","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35935378,0.039684873,0.057300948,0.5403652,0.0016997613,0.0015311571,0.000011477026,0.0000053982476,0.00004737559],"genre_scores_gemma":[0.7840996,0.11440802,0.0819026,0.01914866,0.00027824155,0.00007723397,3.9096145e-7,0.000008135975,0.00007710709],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.89628273,0.07772325,0.024823526,0.00033467571,0.0003488742,0.0004869163],"domain_scores_gemma":[0.21900314,0.7588939,0.018725676,0.00036304342,0.0027397703,0.00027443818],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28017437,0.00013255375,0.005660057,0.00019304841,0.00017563908,0.0000030723897,0.00021801531,0.00014239605,0.000028619499],"category_scores_gemma":[0.83730346,0.00007150324,0.00057231646,0.00024831248,0.0017844344,0.00020437114,0.0001843774,0.0008550406,6.4122986e-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":[0.24801202,0.00059500826,0.47162214,0.013077925,0.0023124404,0.000026865404,0.092035495,0.0014508083,0.0005298552,0.060291562,0.04893321,0.06111267],"study_design_scores_gemma":[0.6388362,0.001357278,0.13651818,0.08236827,0.0006340947,0.00010173703,0.050487366,0.013968084,0.00010271983,0.07418936,0.0010773396,0.0003593543],"about_ca_topic_score_codex":0.00050113467,"about_ca_topic_score_gemma":0.00089644775,"teacher_disagreement_score":0.6811707,"about_ca_system_score_codex":0.000053473606,"about_ca_system_score_gemma":0.0011859572,"threshold_uncertainty_score":0.74121195},"labels":[],"label_agreement":null},{"id":"W3211885944","doi":"10.1016/j.jclinepi.2021.11.010","title":"International alliance and AGREE-ment of 71 clinical practice guidelines on the management of critical care patients with COVID-19: a living systematic review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Memorial University of Newfoundland","funders":"Deanship of Scientific Research, King Saud University; King Saud University; National Institute for Health and Care Research","keywords":"Alliance; Coronavirus disease 2019 (COVID-19); Medicine; Clinical Practice; 2019-20 coronavirus outbreak; Family medicine; MEDLINE; Intensive care medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pandemic; Virology; Political science; Pathology","score_opus":0.7374149352238119,"score_gpt":0.7070982109307433,"score_spread":0.03031672429306853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211885944","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":[0.000026643935,0.9411336,0.0020245092,0.052840084,0.0013477132,0.0023999384,0.000050808663,0.0000061888927,0.00017048384],"genre_scores_gemma":[0.000051221516,0.9126788,0.049794663,0.036643993,0.00066465227,0.00005037135,0.0000501717,0.000038535785,0.000027624954],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9489438,0.016858062,0.031909026,0.0006928502,0.0012739064,0.0003223532],"domain_scores_gemma":[0.46959543,0.47680882,0.041060865,0.001529914,0.010079564,0.0009254154],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08449894,0.0004853156,0.012704624,0.00011962906,0.00005350387,0.000011536365,0.0006652262,0.00052491267,0.00017999552],"category_scores_gemma":[0.8486252,0.00025135351,0.0022288798,0.0002832424,0.0006670964,0.00016167334,0.00040234416,0.0021362219,0.000007801419],"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":[0.00048575745,0.0016167207,0.0024540315,0.7482331,0.0053041284,0.00020948837,0.000029121677,0.000005027069,3.364284e-9,0.0020153313,0.011062633,0.22858465],"study_design_scores_gemma":[0.001288728,0.0023435925,0.00055016,0.5559538,0.023339756,0.00035251127,0.0005130766,0.000016288672,7.2836026e-9,0.000055599303,0.4154166,0.00016989092],"about_ca_topic_score_codex":0.000011790198,"about_ca_topic_score_gemma":0.0000026374482,"teacher_disagreement_score":0.76412624,"about_ca_system_score_codex":0.00018862696,"about_ca_system_score_gemma":0.0015396556,"threshold_uncertainty_score":0.99999386},"labels":[],"label_agreement":null},{"id":"W3211916623","doi":"10.1016/j.jclinepi.2021.11.009","title":"Visual transformation for guidelines presentation of the strength of recommendations and the certainty of evidence","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"","keywords":"Grading (engineering); Guideline; Presentation (obstetrics); Certainty; MEDLINE; Unification; Systematic review; Medicine; Computer science; Medical education; Medical physics; Pathology; Surgery; Mathematics","score_opus":0.8014676261089568,"score_gpt":0.6912918824105951,"score_spread":0.1101757436983617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211916623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5472594,0.0007143367,0.044572096,0.40610468,0.0007533492,0.00053687097,0.0000245574,0.0000019725223,0.00003271685],"genre_scores_gemma":[0.9648652,0.0054649166,0.025321437,0.0039398507,0.00035471295,0.000005492949,0.000014618721,0.000006334341,0.000027430802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98572737,0.004164374,0.00962906,0.00012374266,0.00024583633,0.00010959929],"domain_scores_gemma":[0.82753754,0.1608215,0.008016996,0.00024450524,0.0033015641,0.000077928664],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03416627,0.00007969697,0.0013391607,0.00004785665,0.000036509748,0.0000019906563,0.0001259043,0.00016976245,0.000053842996],"category_scores_gemma":[0.5112984,0.000037988426,0.00062906387,0.00016002478,0.0004290789,0.00015721384,0.00004251422,0.00045042724,1.5106959e-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":[0.016846688,0.00103291,0.26481923,0.0010272799,0.0011909703,0.0000015455332,0.0010556269,0.0010914442,0.0026774532,0.016997423,0.028377676,0.66488177],"study_design_scores_gemma":[0.04384119,0.006855296,0.7324704,0.0044916105,0.0054887407,0.00038595079,0.008887485,0.09315018,0.011212746,0.072881535,0.020072045,0.00026284374],"about_ca_topic_score_codex":0.00007235838,"about_ca_topic_score_gemma":0.000058096823,"teacher_disagreement_score":0.6646189,"about_ca_system_score_codex":0.00001263956,"about_ca_system_score_gemma":0.0004613296,"threshold_uncertainty_score":0.99452907},"labels":[],"label_agreement":null},{"id":"W3212147538","doi":"10.1016/j.jclinepi.2021.11.012","title":"Guidelines developed under pressure. The case of the COVID-19 low-quality “rapid” guidelines and potential solutions","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":15,"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; Impact; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Scarcity; Public health; Quality (philosophy); Investment (military); Business; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Public relations; Evidence-based medicine; Medicine; MEDLINE; Political science; Economics; Nursing; Disease; Virology","score_opus":0.8282594287562877,"score_gpt":0.6738185397503147,"score_spread":0.15444088900597297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212147538","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":[0.2600966,0.0049462877,0.067245804,0.66471857,0.0024944048,0.00036235142,0.00004440011,0.000012713793,0.000078872894],"genre_scores_gemma":[0.7254969,0.006919992,0.052401472,0.21080974,0.0037194423,0.000006125517,0.000016642725,0.000032970736,0.00059670024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97115135,0.012125409,0.015494541,0.00042139494,0.00040778398,0.00039949597],"domain_scores_gemma":[0.8027503,0.16764636,0.015955646,0.0017164471,0.010749234,0.0011820183],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.079044156,0.0002261438,0.002199307,0.000065827444,0.00025848983,0.000013322967,0.00032080407,0.00040943484,0.0004039714],"category_scores_gemma":[0.7609097,0.0001173106,0.0010267529,0.00031551503,0.00094696746,0.000149263,0.0004375203,0.0013080436,0.0000047109743],"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":[0.0035109778,0.0013642152,0.18537764,0.00059160526,0.0034819483,0.002173803,0.00017115341,0.011788305,0.0009697098,0.021015305,0.6790373,0.09051807],"study_design_scores_gemma":[0.016055034,0.0012672874,0.36323047,0.00042743373,0.0056051007,0.097145386,0.0033839808,0.012469566,0.00010705078,0.075451195,0.42431203,0.00054546166],"about_ca_topic_score_codex":0.00051743403,"about_ca_topic_score_gemma":0.00046846652,"teacher_disagreement_score":0.6818655,"about_ca_system_score_codex":0.00004416649,"about_ca_system_score_gemma":0.0033376166,"threshold_uncertainty_score":0.9483178},"labels":[],"label_agreement":null},{"id":"W3212400812","doi":"10.1016/j.jclinepi.2021.11.011","title":"Many trials of hydroxychloroquine for SARS-CoV-2 were redundant and potentially unethical: an analysis of the NIH clinical trials registry","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 Clinical Research Studies","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Department of Medicine, Ottawa Hospital","keywords":"Hydroxychloroquine; Clinical trial; Pandemic; Coronavirus disease 2019 (COVID-19); Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; MEDLINE; Virology; Internal medicine; Outbreak; Disease","score_opus":0.6597320813274339,"score_gpt":0.6771168350503699,"score_spread":0.01738475372293602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212400812","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83444005,0.0023020613,0.01881078,0.1414933,0.0017803336,0.00091382297,0.000193973,0.00001144434,0.000054240216],"genre_scores_gemma":[0.9518315,0.0183512,0.014038904,0.012836337,0.002608571,0.0000123305035,0.000023581546,0.00003676477,0.00026077116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8950787,0.06356218,0.03861367,0.0009973742,0.0010471116,0.00070092623],"domain_scores_gemma":[0.051967956,0.909962,0.030855693,0.0021675124,0.0040994724,0.00094734714],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.40791294,0.00033580128,0.020480366,0.00031702532,0.00009922643,0.000011663129,0.0007048406,0.0013135883,0.00009556163],"category_scores_gemma":[0.96972054,0.00018363919,0.009799022,0.0007214918,0.0027859916,0.00008758758,0.0004846507,0.0027824547,9.619826e-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":[0.048117977,0.006016811,0.7481234,0.0017240908,0.047169015,0.00028123322,0.00011933939,0.00067646377,0.016372269,0.0076013897,0.01849704,0.10530094],"study_design_scores_gemma":[0.02216235,0.01232458,0.8505197,0.0011550174,0.030839304,0.000067952,0.00019278482,0.009670235,0.0019127823,0.03124098,0.039567143,0.00034714886],"about_ca_topic_score_codex":0.000082663835,"about_ca_topic_score_gemma":0.00008892897,"teacher_disagreement_score":0.84639984,"about_ca_system_score_codex":0.00005111234,"about_ca_system_score_gemma":0.0024354737,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W3212942281","doi":"10.1016/j.jclinepi.2021.11.006","title":"Sex and Gender Appraisal Tool-Systematic Reviews-2 and Participation-To-Prevalence Ratio assessed to whom the evidence applies in sepsis reviews","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; Institute of Gender and Health; Ottawa Hospital; Health Canada; Jewish General Hospital; University of Ottawa; McGill University","funders":"European Social Fund; Instituto de Salud Carlos III","keywords":"Systematic review; Critical appraisal; Medicine; Population; Meta-analysis; MEDLINE; Gender equity; Psychology; Demography; Family medicine; Alternative medicine; Environmental health; Pathology; Social science; Sociology; Political science","score_opus":0.7128288999713099,"score_gpt":0.6158957247445076,"score_spread":0.09693317522680234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212942281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83689934,0.10390635,0.0036892337,0.053263083,0.0003785142,0.0018159215,0.0000016113968,0.0000049382224,0.00004101995],"genre_scores_gemma":[0.83296084,0.124146864,0.011249627,0.030716587,0.00046277308,0.00035056449,0.0000010072673,0.000012961794,0.00009874024],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9856223,0.008361285,0.005172577,0.00037921837,0.00020054205,0.00026409156],"domain_scores_gemma":[0.9037382,0.09323595,0.0018717215,0.00046873713,0.00026543345,0.0004199666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03552689,0.0001886344,0.0035984623,0.000068849055,0.00006292186,0.000026626596,0.00012293571,0.00013949414,0.00006571072],"category_scores_gemma":[0.326254,0.00009745912,0.00031929908,0.00023064138,0.00012427176,0.00010141647,0.000090685404,0.00041625963,0.000032937973],"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":[0.00009431842,0.00035010252,0.9755424,0.005817386,0.00014644886,0.0000503586,0.0005701979,0.000036001333,0.000052189298,0.00041176385,0.00737486,0.009553956],"study_design_scores_gemma":[0.0007244147,0.00070683484,0.9795113,0.009514729,0.0006322534,0.00015996318,0.00010910384,0.00022201032,0.000020332305,0.000576115,0.00771789,0.0001050301],"about_ca_topic_score_codex":0.0000066453736,"about_ca_topic_score_gemma":0.000037949798,"teacher_disagreement_score":0.2907271,"about_ca_system_score_codex":0.00003496277,"about_ca_system_score_gemma":0.00017092554,"threshold_uncertainty_score":0.993128},"labels":[],"label_agreement":null},{"id":"W3213531386","doi":"10.1016/j.jclinepi.2021.10.028","title":"A systematic survey identified methodological issues in studies estimating anchor-based minimal important differences in patient-reported outcomes","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","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":"Population Health Research Institute; McMaster University; Hamilton General Hospital; Hamilton Health Sciences; Impact","funders":"","keywords":"PsycINFO; Generalizability theory; MEDLINE; Systematic review; Coding (social sciences); Medicine; Computer science; Psychology; Information retrieval; Applied psychology; Statistics","score_opus":0.7631553362834169,"score_gpt":0.6364630617814303,"score_spread":0.1266922745019866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213531386","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":[0.034322705,0.9594046,0.00025758153,0.00073854683,0.0043457006,0.0008951677,0.000016638009,0.000013169055,0.0000058772134],"genre_scores_gemma":[0.0038525579,0.98616445,0.008732407,0.0005975525,0.00043592023,0.000094028626,0.00004587725,0.00003886296,0.00003834722],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.9076782,0.06194934,0.028322812,0.00082432176,0.00058709824,0.0006382139],"domain_scores_gemma":[0.65594465,0.31976542,0.022125525,0.00079217984,0.00093711744,0.000435125],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09935046,0.00068856956,0.0388251,0.00063124916,0.000032952383,0.000017523056,0.00039447186,0.0012345014,0.00005531597],"category_scores_gemma":[0.6412401,0.00038317213,0.0035534604,0.0007071491,0.0003597426,0.00006461527,0.00015856422,0.0029781614,0.0000028273732],"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":[0.000318608,0.0005475035,0.83612186,0.10428724,0.0025251445,0.0053915055,0.00019138993,0.00000563398,3.9081453e-8,0.000025125108,0.0003392205,0.05024673],"study_design_scores_gemma":[0.003931859,0.0031805881,0.3674979,0.608505,0.0065571074,0.0019636694,0.0015661564,0.00038017528,1.7869804e-7,0.0007840902,0.004642634,0.0009906194],"about_ca_topic_score_codex":0.0004727441,"about_ca_topic_score_gemma":0.0020889074,"teacher_disagreement_score":0.54188967,"about_ca_system_score_codex":0.00023997515,"about_ca_system_score_gemma":0.0014159549,"threshold_uncertainty_score":0.999862},"labels":[],"label_agreement":null},{"id":"W3213880547","doi":"10.1016/j.jclinepi.2021.11.001","title":"Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","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":"Schwartz/Reisman Emergency Medicine Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Health care; Evidence-based practice; Evidence-based medicine; Real world evidence; Computer science; Medicine; Alternative medicine; Economics; Pathology","score_opus":0.6211548340976271,"score_gpt":0.5750288304756365,"score_spread":0.0461260036219906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213880547","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":[0.00017317051,0.7024844,0.23705812,0.057296455,0.0019809108,0.00096052256,0.000008699441,0.000032061427,0.000005614806],"genre_scores_gemma":[0.00074005115,0.924507,0.06275554,0.010687394,0.0010960777,0.00008373316,0.000008607641,0.000045989065,0.000075580945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9584046,0.024444913,0.013989366,0.0014254106,0.0004985276,0.001237163],"domain_scores_gemma":[0.7735104,0.214801,0.008022286,0.0013238393,0.001413443,0.00092903036],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09056282,0.0006484656,0.011307881,0.0006776213,0.00018175546,0.00008959671,0.0029274854,0.0011755448,0.00003577991],"category_scores_gemma":[0.44127235,0.0004429453,0.003307767,0.0011238756,0.00029931744,0.0005932054,0.00065868814,0.0040233852,0.00001965418],"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":[0.00015028573,0.000230817,0.0053415345,0.007190407,0.000107222986,0.00016283468,0.0002312728,0.0033488919,4.560598e-7,0.007823633,0.0004554889,0.97495717],"study_design_scores_gemma":[0.00039789497,0.0028313508,0.0002734164,0.037705824,0.00020394423,0.00007306077,0.00021279113,0.023191663,0.000009648922,0.0059407754,0.9283947,0.0007649549],"about_ca_topic_score_codex":0.00033005976,"about_ca_topic_score_gemma":0.00043993772,"teacher_disagreement_score":0.9741922,"about_ca_system_score_codex":0.0005421545,"about_ca_system_score_gemma":0.003359228,"threshold_uncertainty_score":0.99980223},"labels":[],"label_agreement":null},{"id":"W3214981747","doi":"10.1016/j.jclinepi.2021.11.029","title":"Epidemiology and development economics two sides of the same coin in impact evaluation","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Ottawa Hospital; University of Ottawa","funders":"Public Health Agency; London School of Hygiene and Tropical Medicine","keywords":"Epidemiology; Medicine; Environmental health; Pathology","score_opus":0.8080482947226801,"score_gpt":0.6291859897399928,"score_spread":0.1788623049826873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214981747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9326104,0.0077419756,0.0016420808,0.056090496,0.0013325339,0.00025450563,0.000025594105,0.0000026081543,0.00029982885],"genre_scores_gemma":[0.9599905,0.0018784355,0.017891275,0.01963066,0.00052316644,0.00001148819,0.0000075789253,0.0000168268,0.000050051567],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95417035,0.016889786,0.02784477,0.0005227723,0.00006988599,0.0005024426],"domain_scores_gemma":[0.8701304,0.10370301,0.02481288,0.0006101236,0.0003918409,0.00035171444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30898234,0.00017977276,0.0047110664,0.00022251275,0.00006545315,0.0000049193363,0.0003220938,0.00035497872,0.0002750283],"category_scores_gemma":[0.39304063,0.00015118983,0.00051205116,0.00013434293,0.00031695366,0.00021196374,0.00012477068,0.00067746843,0.000047018042],"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":[0.000047988557,0.000097504206,0.9615533,0.000052062453,0.00014057165,9.2610117e-7,0.00020876786,0.007863272,6.456285e-7,0.025926486,0.0012114764,0.0028970006],"study_design_scores_gemma":[0.0016013326,0.000120103505,0.84498984,0.00009371504,0.000013347057,0.000060818038,0.0001911891,0.008577327,0.000003562807,0.13964096,0.004592535,0.00011528709],"about_ca_topic_score_codex":0.0003217004,"about_ca_topic_score_gemma":0.0007241095,"teacher_disagreement_score":0.11656347,"about_ca_system_score_codex":0.00046353554,"about_ca_system_score_gemma":0.0017521515,"threshold_uncertainty_score":0.7115481},"labels":[],"label_agreement":null},{"id":"W3215479306","doi":"10.1016/j.jclinepi.2021.11.034","title":"The patient engagement evaluation tool was valid for clinical practice guideline development","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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 Ottawa; St. Michael's Hospital; McGill University; Jewish General Hospital; McMaster University","funders":"Jewish General Hospital; Canada Research Chairs; Public Health Agency; Public Health Agency of Canada; University of Ottawa","keywords":"Cronbach's alpha; Confirmatory factor analysis; Guideline; Construct validity; Psychology; Medicine; Clinical psychology; Psychometrics; Statistics; Structural equation modeling; Mathematics","score_opus":0.8719190841228359,"score_gpt":0.7199832919261779,"score_spread":0.15193579219665798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215479306","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":[0.5929719,0.015700098,0.09349028,0.19625843,0.08459684,0.00870829,0.00005380808,0.000052814838,0.008167504],"genre_scores_gemma":[0.047127165,0.01793241,0.5898942,0.33206603,0.010542372,0.0007308399,0.00040378896,0.000071826165,0.0012314008],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9090447,0.06350243,0.024996448,0.0005081718,0.000966685,0.0009816102],"domain_scores_gemma":[0.7260633,0.25529888,0.011950919,0.00057052664,0.0055102813,0.0006060836],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30585858,0.00021010924,0.0017330579,0.000048582828,0.0012097579,0.000007127385,0.0003318332,0.00048926956,0.0003356972],"category_scores_gemma":[0.35049623,0.00012670204,0.000676097,0.00011988592,0.00012894675,0.0001323134,0.00024972117,0.0021854732,0.00011407187],"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":[0.0021782597,0.0010060973,0.10389969,0.00020252292,0.0003708764,0.000013867611,0.00055675436,0.000099009594,0.0000013040915,0.0043897755,0.33235922,0.55492264],"study_design_scores_gemma":[0.0035660823,0.0018791307,0.019349294,0.00033007405,0.00018829144,0.000010898437,0.0020670823,0.0012010898,0.000007837426,0.0052635022,0.9660115,0.00012517518],"about_ca_topic_score_codex":0.000009543601,"about_ca_topic_score_gemma":0.00004220914,"teacher_disagreement_score":0.6336523,"about_ca_system_score_codex":0.0003425549,"about_ca_system_score_gemma":0.005932782,"threshold_uncertainty_score":0.99970263},"labels":[],"label_agreement":null},{"id":"W3215495292","doi":"10.1016/j.jclinepi.2021.11.024","title":"GRADE concept paper 2: Concepts for judging certainty on the calibration of prognostic models in a body of validation studies","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"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; Ted Rogers Centre for Heart Research","funders":"British Heart Foundation","keywords":"Certainty; Inference; Calibration; Econometrics; Computer science; Medicine; Statistics; Artificial intelligence; Mathematics","score_opus":0.2834012222335031,"score_gpt":0.5316164983690372,"score_spread":0.24821527613553412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215495292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884524,0.0013434122,0.042179134,0.067157365,0.00052822643,0.0002799217,0.0000032105336,0.0000036075448,0.000052687803],"genre_scores_gemma":[0.98881423,0.00078099174,0.005565737,0.004453282,0.00034480702,0.000006250775,0.00000574487,0.000009179625,0.000019796502],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99400514,0.00253247,0.0029605706,0.00015661126,0.00017654659,0.00016865821],"domain_scores_gemma":[0.94255483,0.05472899,0.0020091669,0.00015766089,0.00045762683,0.00009172917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013026645,0.00009381092,0.0016700006,0.00006438509,0.000025859408,0.000001976272,0.0000947061,0.00013504854,0.00001928746],"category_scores_gemma":[0.19893986,0.000054215583,0.00038655425,0.00010842173,0.00038567407,0.000070581824,0.000028168193,0.00070047064,1.2285092e-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":[0.002617079,0.0019316915,0.67939574,0.0008887597,0.0017888857,0.00013497814,0.0027965354,0.1270429,0.0062649366,0.13408026,0.009480731,0.033577494],"study_design_scores_gemma":[0.0102391355,0.0044339434,0.13409412,0.003345955,0.00069262594,0.00016218843,0.0021067152,0.67872316,0.003112139,0.16181698,0.0010607949,0.00021227056],"about_ca_topic_score_codex":0.000007989419,"about_ca_topic_score_gemma":0.0000014655091,"teacher_disagreement_score":0.5516802,"about_ca_system_score_codex":0.00002417045,"about_ca_system_score_gemma":0.00025026465,"threshold_uncertainty_score":0.8078078},"labels":[],"label_agreement":null},{"id":"W3216018196","doi":"10.1016/j.jclinepi.2021.11.031","title":"New methods facilitated the process of prioritizing questions and health outcomes in guideline development","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University; Impact; Cochrane","funders":"American Society of Hematology","keywords":"Guideline; Medicine; Rating scale; Scale (ratio); Prioritization; Randomized controlled trial; Evidence-based medicine; Family medicine; Actuarial science; Psychology; Management science; Alternative medicine; Surgery; Pathology; Engineering; Business","score_opus":0.9091262219885365,"score_gpt":0.833848691589012,"score_spread":0.07527753039952456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216018196","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":[0.2588765,0.0007827989,0.17032233,0.5681868,0.0012275343,0.00046140913,0.000009289407,0.000009642328,0.00012368406],"genre_scores_gemma":[0.062297292,0.0007961155,0.83048594,0.10578084,0.00030096655,0.000013267494,0.0000027086955,0.000010110852,0.00031278178],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95761335,0.027926873,0.013425895,0.00023487273,0.00023471573,0.00056429976],"domain_scores_gemma":[0.85761786,0.1326599,0.007382669,0.00031621242,0.0012863403,0.0007370495],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14832051,0.00010725834,0.0019348584,0.00013238516,0.00022924624,0.0000020201724,0.00023931073,0.00018094426,0.00012684394],"category_scores_gemma":[0.25113025,0.00006533624,0.00011540292,0.0003843578,0.00015462228,0.0001018106,0.00011300177,0.0013022735,0.000005037597],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027835833,0.00003744837,0.8945819,0.00012362687,0.000029218718,0.0000032994235,0.0055292537,0.000035332516,0.000009381461,0.0017254599,0.008039355,0.08985787],"study_design_scores_gemma":[0.001235608,0.00015571131,0.90099293,0.00020334794,0.0000072791854,0.00001848107,0.0032036812,0.00012467302,0.0000050832464,0.0092366645,0.084762454,0.00005405986],"about_ca_topic_score_codex":0.00043003468,"about_ca_topic_score_gemma":0.0010469477,"teacher_disagreement_score":0.6601636,"about_ca_system_score_codex":0.00011577259,"about_ca_system_score_gemma":0.011661638,"threshold_uncertainty_score":0.9939413},"labels":[],"label_agreement":null},{"id":"W3216910947","doi":"10.1016/j.jclinepi.2021.11.037","title":"A pilot living clinical practice guidelines approach was feasible and acceptable to guideline panel members","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Western University; Parkwood Institute; Lawson Health Research Institute","funders":"","keywords":"Guideline; Data extraction; Resource (disambiguation); Medicine; Protocol (science); Process (computing); MEDLINE; Family medicine; Medical education; Alternative medicine; Computer science; Pathology","score_opus":0.7877881800782537,"score_gpt":0.6617434496896374,"score_spread":0.1260447303886163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216910947","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":[0.25395352,0.0054716333,0.16109227,0.56334245,0.0079978,0.0011578337,0.000021818865,0.00010083185,0.0068618604],"genre_scores_gemma":[0.049493536,0.006524273,0.74365395,0.19253732,0.006897635,0.00000915886,0.000025833793,0.00006169109,0.0007965794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95727307,0.010820193,0.029070908,0.0011287621,0.00085772126,0.00084933767],"domain_scores_gemma":[0.5792347,0.37830597,0.017662719,0.001980479,0.018916642,0.003899488],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14859661,0.00042152448,0.0049222363,0.00022497262,0.00013178874,0.0000473269,0.00038948093,0.0005315004,0.00070274033],"category_scores_gemma":[0.9252303,0.0003300963,0.0011597809,0.0005787426,0.00033864746,0.0006949093,0.0005911905,0.0027852817,0.00006535804],"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":[0.0043043564,0.0029939397,0.24625815,0.00012222909,0.0011344702,0.000481484,0.000067882065,0.0007337177,0.00014293702,0.0007642833,0.5705845,0.17241208],"study_design_scores_gemma":[0.00834961,0.008417732,0.1910226,0.0005723117,0.002346822,0.008607908,0.0028128992,0.008483325,0.000013257626,0.0016740941,0.7671823,0.0005171579],"about_ca_topic_score_codex":0.000259157,"about_ca_topic_score_gemma":0.00006899801,"teacher_disagreement_score":0.7766337,"about_ca_system_score_codex":0.00009463822,"about_ca_system_score_gemma":0.0022442779,"threshold_uncertainty_score":0.9999151},"labels":[],"label_agreement":null},{"id":"W3216970755","doi":"10.1016/j.jclinepi.2021.11.030","title":"Large-scale infectious disease testing programs have little consideration for equity: findings from a scoping review","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"SARS-CoV-2 detection and testing","field":"Medicine","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":"Wilfrid Laurier University; Université de Montréal; Institut National de Santé Publique du Québec; University of Ottawa","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Agence Nationale de la Recherche","keywords":"MEDLINE; Medicine; Psychological intervention; Pandemic; Equity (law); Health equity; Clinical study design; Coronavirus disease 2019 (COVID-19); Population; Data extraction; Disease; Family medicine; Infectious disease (medical specialty); Environmental health; Public health; Clinical trial; Nursing; Pathology; Political science","score_opus":0.6583543261055917,"score_gpt":0.6158714478201252,"score_spread":0.042482878285466597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216970755","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":[0.00029004127,0.9877875,0.0071746125,0.0007847018,0.0016273643,0.0020852606,0.00002484612,0.000057856287,0.00016784298],"genre_scores_gemma":[0.000025381325,0.96801704,0.017782873,0.010809873,0.0030417272,0.00012556519,0.00010251806,0.00006665743,0.000028344788],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9853646,0.0038247623,0.009302276,0.0006598608,0.00027723706,0.0005712627],"domain_scores_gemma":[0.89568496,0.09306915,0.008782005,0.00053206336,0.0013370058,0.000594786],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.023796067,0.00045684355,0.011217297,0.0001754775,0.00015444825,0.0000370457,0.00018126653,0.0007598777,0.00006952835],"category_scores_gemma":[0.5080533,0.00033855723,0.003405262,0.0003192288,0.0001622841,0.00010435865,0.00018264963,0.0021209393,0.000014757309],"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":[0.000050812392,0.0003191283,0.0075773885,0.06446557,0.00046949106,0.00018336141,0.000009827627,5.129822e-7,9.1991456e-7,0.000040974654,0.0010588143,0.9258232],"study_design_scores_gemma":[0.0014101098,0.00086278917,0.00011985018,0.63030607,0.0049860794,0.001039869,0.000009418504,0.00025868046,0.0000010223011,0.0010470331,0.35968995,0.00026913287],"about_ca_topic_score_codex":0.000012221405,"about_ca_topic_score_gemma":0.000028501669,"teacher_disagreement_score":0.9255541,"about_ca_system_score_codex":0.00014794517,"about_ca_system_score_gemma":0.0028930663,"threshold_uncertainty_score":0.99990666},"labels":[],"label_agreement":null},{"id":"W4200101691","doi":"10.1016/j.jclinepi.2021.11.038","title":"A few things to consider when deciding whether or not to conduct underpowered research","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 British Columbia; University of British Columbia Hospital","funders":"","keywords":"Observational study; Distrust; MEDLINE; Psychology; Medicine; Psychotherapist; Political science; Pathology","score_opus":0.9839964413951311,"score_gpt":0.7576695438075235,"score_spread":0.2263268975876076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200101691","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039403336,0.0011390836,0.0256333,0.96133745,0.004800582,0.0009170635,0.00001920173,0.0000041104954,0.002208891],"genre_scores_gemma":[0.0009106938,0.00022662655,0.08644041,0.8504715,0.0074149915,0.000017790699,0.0000049936907,0.00005848853,0.054454517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.33772615,0.52784836,0.11412228,0.003880806,0.014326102,0.0020962586],"domain_scores_gemma":[0.07028568,0.86110115,0.044713885,0.0073720193,0.014756118,0.0017711462],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8311655,0.00078517286,0.036477495,0.0019467077,0.000239672,0.0007269739,0.006577918,0.0026097076,0.046155337],"category_scores_gemma":[0.963898,0.00033592083,0.010997886,0.001957086,0.00047737706,0.0003115447,0.0012031142,0.010634234,0.007622058],"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":[0.00019165644,0.00004751019,0.0020173509,0.00006694933,0.0011363205,0.0010475264,0.0003883305,0.000035040925,0.000012303303,0.0004116092,0.9882467,0.006398747],"study_design_scores_gemma":[0.00037592323,0.0006643505,0.0010822127,0.00065572816,0.0003575769,0.0005279509,0.0004603458,0.000087542365,0.0000025546356,0.045026883,0.9504325,0.00032647976],"about_ca_topic_score_codex":0.000053793803,"about_ca_topic_score_gemma":0.000071448514,"teacher_disagreement_score":0.33325276,"about_ca_system_score_codex":0.00017306133,"about_ca_system_score_gemma":0.002201569,"threshold_uncertainty_score":0.9999093},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4200179443","doi":"10.1016/j.jclinepi.2021.12.006","title":"Review of pragmatic trials found that multiple primary outcomes are common but so too are discrepancies between protocols and final reports","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Medicine; Protocol (science); Sample size determination; Clinical trial; MEDLINE; Research design; Randomized controlled trial; Internal medicine; Statistics; Alternative medicine; Pathology; Mathematics","score_opus":0.9729485367312152,"score_gpt":0.7406800862441736,"score_spread":0.2322684504870416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200179443","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000102756625,0.97868735,0.0014323565,0.003624823,0.0008197885,0.015071123,0.00013851954,0.0000033955707,0.00011988145],"genre_scores_gemma":[0.000012875685,0.98521495,0.00965874,0.0023981514,0.0007722613,0.000996004,0.000045496912,0.00003623211,0.0008653037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.33444503,0.4286517,0.22858056,0.0022133512,0.0053653265,0.000744045],"domain_scores_gemma":[0.100081645,0.55312294,0.33855584,0.004854842,0.002767514,0.00061720656],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8025229,0.0010929703,0.16992691,0.0005263069,0.00014759779,0.00027346716,0.0025680484,0.0011230783,0.0009933726],"category_scores_gemma":[0.94922346,0.00042988852,0.034394078,0.0008259052,0.0007123787,0.00034537667,0.00071970926,0.0021550108,0.000051354178],"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":[0.000012977181,0.00014881884,0.34410557,0.10205007,0.0028947357,0.00016162923,0.000008164408,7.232561e-7,8.995513e-9,0.00006764853,0.06647068,0.48407894],"study_design_scores_gemma":[0.00032945475,0.00018624007,0.03758327,0.16636737,0.007462917,0.0006662301,0.00004004974,0.0000036085105,1.3134245e-8,0.0030588515,0.784027,0.00027501825],"about_ca_topic_score_codex":0.000011905341,"about_ca_topic_score_gemma":0.000019161547,"teacher_disagreement_score":0.7175563,"about_ca_system_score_codex":0.00007925911,"about_ca_system_score_gemma":0.0014939763,"threshold_uncertainty_score":0.99991983},"labels":[],"label_agreement":null},{"id":"W4200404522","doi":"10.1016/j.jclinepi.2021.12.022","title":"A memorandum of understanding has facilitated guideline development involving collaborating groups","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Public Health Agency of Canada; McMaster University","funders":"","keywords":"Guideline; Scope (computer science); Memorandum; Memorandum of understanding; Resource (disambiguation); Working group; Medicine; Public relations; Political science; Medical education; Process management; Computer science; Business; Law","score_opus":0.8147930841778158,"score_gpt":0.6106832982175362,"score_spread":0.20410978596027962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200404522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7086519,0.0016642527,0.20667768,0.08020831,0.0021369716,0.00028743604,0.000011187608,0.000022580063,0.00033968757],"genre_scores_gemma":[0.7479728,0.0005136265,0.24333945,0.007258094,0.00077366683,0.0000016803007,0.000046060235,0.000020204314,0.000074455646],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9769852,0.0039832084,0.017860575,0.00034130114,0.0004638312,0.00036586745],"domain_scores_gemma":[0.9003352,0.083682284,0.010853171,0.00045640214,0.004073344,0.0005995851],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05490315,0.00019792338,0.003128149,0.00016354883,0.00009970529,0.000011386893,0.00015462017,0.00035018625,0.00037482867],"category_scores_gemma":[0.5023628,0.00015795395,0.0005816156,0.00049318455,0.0002993616,0.00021100914,0.00012722057,0.0011043599,0.000009414871],"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":[0.0056901136,0.0018942843,0.8403533,0.00059535983,0.0026538614,0.0009838574,0.0012085033,0.001216177,0.006556263,0.0068317493,0.08863096,0.04338554],"study_design_scores_gemma":[0.069430985,0.011344787,0.47016844,0.0046943724,0.0037380434,0.004191319,0.050432734,0.025602449,0.004238588,0.07122397,0.28336656,0.0015677665],"about_ca_topic_score_codex":0.000026221673,"about_ca_topic_score_gemma":0.00011910472,"teacher_disagreement_score":0.44745964,"about_ca_system_score_codex":0.00023094763,"about_ca_system_score_gemma":0.0035463113,"threshold_uncertainty_score":0.9731761},"labels":[],"label_agreement":null},{"id":"W4200604447","doi":"10.1016/j.jclinepi.2021.12.003","title":"Open science failed to penetrate academic hiring practices: a cross-sectional study","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","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":"Ottawa Public Health; University of Ottawa; Hamilton General Hospital; McMaster University; Carleton University; Ottawa Hospital","funders":"","keywords":"Open science; Publishing; Ranking (information retrieval); Medical education; Cross-sectional study; Psychology; Public relations; Political science; Medicine; Computer science; Mathematics","score_opus":0.9633189143454393,"score_gpt":0.8121707407502468,"score_spread":0.1511481735951925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200604447","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":[0.9805101,0.00040753174,0.004240791,0.008370556,0.0044514504,0.0003109331,0.000005596123,0.0000053762474,0.0016976661],"genre_scores_gemma":[0.9812055,0.00030895765,0.012890224,0.003134589,0.0009269191,0.000005692585,3.347589e-7,0.000008970776,0.0015187862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9411407,0.018991001,0.019918943,0.0028694787,0.015213863,0.0018659999],"domain_scores_gemma":[0.40725887,0.52406114,0.023706723,0.0026519867,0.03761988,0.0047014044],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.64896536,0.00018094505,0.002251417,0.017668286,0.000483758,0.0026446534,0.0132699255,0.00034544108,0.0009914777],"category_scores_gemma":[0.9613204,0.00011456937,0.00055320014,0.0907686,0.00079802005,0.0025625408,0.0065538604,0.0027657694,0.00045823515],"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":[0.00028080976,0.0004524617,0.97358483,0.000001456433,0.000040430095,0.00013054484,0.000044264063,0.0007238682,0.00021977769,0.0007029732,0.0036002225,0.02021836],"study_design_scores_gemma":[0.0012075529,0.0013827056,0.9661521,0.000011209063,0.000009565828,0.00015226814,0.00039942723,0.0009412324,0.000049434624,0.01577746,0.013792357,0.00012473286],"about_ca_topic_score_codex":0.00009347742,"about_ca_topic_score_gemma":0.000059113027,"teacher_disagreement_score":0.53388184,"about_ca_system_score_codex":0.00017829397,"about_ca_system_score_gemma":0.0048141046,"threshold_uncertainty_score":0.99992174},"labels":[],"label_agreement":null},{"id":"W4205341401","doi":"10.1016/j.jclinepi.2022.01.010","title":"Methodological systematic review recommends improvements to conduct and reporting when meta-analyzing interrupted time series studies","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Interrupted time series; Interrupted Time Series Analysis; MEDLINE; Systematic review; Series (stratigraphy); Public health","score_opus":0.9893377873707482,"score_gpt":0.7562489225454152,"score_spread":0.23308886482533298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205341401","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":[0.058797147,0.53138614,0.0582905,0.3388436,0.005428849,0.0061640707,0.00004993217,0.000026731646,0.0010129946],"genre_scores_gemma":[0.06280865,0.02083948,0.69041306,0.19347344,0.0012108285,0.0008909545,0.000014082667,0.00009931393,0.030250197],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.24760015,0.55112326,0.19482559,0.001819731,0.0039604516,0.0006708077],"domain_scores_gemma":[0.060305983,0.6051062,0.32361266,0.004869923,0.0050958837,0.0010093668],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9119779,0.00044783787,0.056932565,0.00043905663,0.00026825897,0.00009692286,0.002083977,0.00012989524,0.0091832215],"category_scores_gemma":[0.96941483,0.00017631477,0.010337797,0.0008144911,0.00018103277,0.0002742228,0.0013146229,0.0011928917,0.00014062134],"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":[0.0003512423,0.00034628122,0.034645222,0.037839737,0.097737364,0.0003214314,0.0010634923,0.00026456098,0.00008582789,0.002047842,0.80510706,0.020189913],"study_design_scores_gemma":[0.0024167225,0.015636958,0.008179572,0.025656518,0.2326366,0.009054948,0.011956664,0.0036680375,0.000014001482,0.4172996,0.27113992,0.002340476],"about_ca_topic_score_codex":0.0000033272447,"about_ca_topic_score_gemma":0.0000027826698,"teacher_disagreement_score":0.6321226,"about_ca_system_score_codex":0.000068917645,"about_ca_system_score_gemma":0.00009867356,"threshold_uncertainty_score":0.9995734},"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":"W4205761420","doi":"10.1016/j.jclinepi.2022.01.006","title":"Substantial heterogeneity found in reporting mortality in Cochrane systematic reviews and Core Outcome Sets in COMET database","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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 Ottawa","funders":"University of Ottawa; Pfizer","keywords":"Medicine; Systematic review; MEDLINE; Mortality rate; Meta-analysis; Outcome (game theory); Cochrane Library; Pediatrics; Internal medicine","score_opus":0.8844755581514867,"score_gpt":0.718725118026761,"score_spread":0.16575044012472573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205761420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993217,0.0026538742,0.00015132927,0.002308978,0.00060122117,0.0009494053,0.000007683099,0.000007487312,0.000103004575],"genre_scores_gemma":[0.9950079,0.0024762116,0.0015890278,0.0007389295,0.000115248746,0.00005181734,0.0000028360362,0.0000084575595,0.00000957149],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9160185,0.056687217,0.02496185,0.0005484278,0.00096665934,0.0008173711],"domain_scores_gemma":[0.90259254,0.07944486,0.016651724,0.0006631349,0.00023728106,0.00041048022],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4347424,0.00013893255,0.0042853486,0.00038195658,0.00011656619,0.000012686398,0.00061689666,0.00021588057,0.00006907056],"category_scores_gemma":[0.55713546,0.000114107715,0.0003097542,0.00081472687,0.00050354894,0.00017960055,0.0003427193,0.0023435315,0.0000017352818],"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":[0.0001147118,0.00018098186,0.9959518,0.0013037119,0.000013969411,0.00088683114,0.00023541754,0.000076600445,0.0000054293528,0.0008343461,0.00014068894,0.0002555246],"study_design_scores_gemma":[0.000840854,0.00021223648,0.9895866,0.00154611,0.000020634785,0.00013390424,0.0007804876,0.00082685746,3.9544648e-7,0.005474541,0.00044990404,0.00012746459],"about_ca_topic_score_codex":0.0032604581,"about_ca_topic_score_gemma":0.02475351,"teacher_disagreement_score":0.122393064,"about_ca_system_score_codex":0.00024794423,"about_ca_system_score_gemma":0.00037255156,"threshold_uncertainty_score":0.9999581},"labels":[],"label_agreement":null},{"id":"W4206385207","doi":"10.1016/j.jclinepi.2022.01.004","title":"Standardized wording to improve efficiency and clarity of GRADE EtD frameworks in health guidelines","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":22,"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":"CLARITY; Grading (engineering); Guideline; Transparency (behavior); Medical education; Process management; Medicine; Computer science; Medical physics; Management science; Engineering; Pathology","score_opus":0.5498824615360741,"score_gpt":0.6479038588874745,"score_spread":0.09802139735140036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206385207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70856553,0.0011147658,0.049154527,0.2391753,0.0014824469,0.00045301593,0.000020648278,0.000007672157,0.000026067475],"genre_scores_gemma":[0.84379005,0.0012364488,0.10590292,0.048289735,0.00073076884,0.000007664175,0.000004663157,0.00001771997,0.000020003723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9748954,0.007264728,0.016419547,0.00041754043,0.00054569094,0.00045704996],"domain_scores_gemma":[0.92006105,0.07016525,0.007960974,0.0003947023,0.0007745681,0.00064343616],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11796385,0.000153262,0.0031671738,0.00028999874,0.00007899396,0.00000384288,0.00020771744,0.00030108826,0.00014538747],"category_scores_gemma":[0.46318313,0.00012365729,0.0004566317,0.0004071864,0.00016775186,0.00009029009,0.00028299403,0.0036893913,9.438857e-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":[0.0071983826,0.00093238126,0.762641,0.00018131448,0.00018166186,0.00006938404,0.00022838377,0.005407868,0.00017603984,0.002046716,0.016536424,0.20440045],"study_design_scores_gemma":[0.023420935,0.026342357,0.7928052,0.00080971996,0.00032849552,0.00070847466,0.00239127,0.016945552,0.000020838112,0.04566901,0.09015252,0.0004056349],"about_ca_topic_score_codex":0.00028778322,"about_ca_topic_score_gemma":0.00004854981,"teacher_disagreement_score":0.34521928,"about_ca_system_score_codex":0.00016053818,"about_ca_system_score_gemma":0.0010302608,"threshold_uncertainty_score":0.9986091},"labels":[],"label_agreement":null},{"id":"W4206934887","doi":"10.1016/j.jclinepi.2022.01.013","title":"A review identified challenges distinguishing primary reports of randomized trials for meta-research: A proposal for improved reporting","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; University of Ottawa; Ottawa Hospital","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Randomized controlled trial; Meta-analysis; Medicine; MEDLINE; Research design; Medical physics; Family medicine; Psychology; Internal medicine; Political science; Statistics; Mathematics","score_opus":0.9934473208086363,"score_gpt":0.789167337119375,"score_spread":0.20427998368926126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206934887","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.5938317e-7,0.95048046,0.022317728,0.006217401,0.0038549185,0.01674153,0.00008307064,0.000004203183,0.00029991384],"genre_scores_gemma":[8.557861e-7,0.91642106,0.07618167,0.00063421787,0.0019910117,0.0038099848,0.000055346623,0.00006444987,0.0008413844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.015312199,0.5815471,0.3951866,0.002435235,0.0046726926,0.00084619725],"domain_scores_gemma":[0.0010090882,0.57010394,0.41777498,0.0034231464,0.0073306677,0.0003581561],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9934466,0.001016748,0.29759443,0.0012848697,0.0002852658,0.00018524792,0.004251523,0.0009292899,0.0022451521],"category_scores_gemma":[0.9990833,0.0003853435,0.17876443,0.0012270431,0.00062052306,0.00022829253,0.0007555206,0.0029517168,0.000008693372],"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":[0.0014555687,0.00017032465,0.0000041368357,0.083916254,0.024436135,0.00003631434,0.000023261413,0.0000015096623,8.486284e-8,0.0019544521,0.105961345,0.7820406],"study_design_scores_gemma":[0.0043276767,0.00038834754,0.0000014946821,0.014912707,0.07589485,0.00054661534,0.000027993528,0.00007762874,2.4495355e-8,0.09081743,0.8127729,0.00023228048],"about_ca_topic_score_codex":0.000008085883,"about_ca_topic_score_gemma":0.0000060853276,"teacher_disagreement_score":0.7818083,"about_ca_system_score_codex":0.00012115279,"about_ca_system_score_gemma":0.0046874033,"threshold_uncertainty_score":0.99985987},"labels":[],"label_agreement":null},{"id":"W4207058677","doi":"10.1016/j.jclinepi.2022.01.017","title":"Minimal important changes in standard deviation units are highly variable and no universally applicable value can be determined","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":20,"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; Impact","funders":"Canadian Institutes of Health Research; Shionogi","keywords":"Interquartile range; Statistics; Standard deviation; Mathematics; Medicine","score_opus":0.36576805802673124,"score_gpt":0.46650879546282675,"score_spread":0.10074073743609552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207058677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9650066,0.0003171707,0.0019671437,0.03071079,0.0012422871,0.0002716675,0.00006714102,0.000007082845,0.0004101049],"genre_scores_gemma":[0.984869,0.0004876907,0.0077216346,0.006184082,0.00037966127,0.000011611792,0.0000043666046,0.000010293738,0.00033162785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98494506,0.007791981,0.0051597273,0.0004998126,0.0011997133,0.00040368288],"domain_scores_gemma":[0.95830494,0.03468653,0.0052886344,0.00041588856,0.00097624166,0.00032779202],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11529899,0.00015816845,0.0018161618,0.00026183674,0.00017003024,0.000026336918,0.00069048064,0.00016703499,0.0003387404],"category_scores_gemma":[0.11167263,0.000113204995,0.00016656444,0.0006305911,0.00018494917,0.00013170886,0.0002846539,0.00087317836,0.000002890332],"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":[0.0014961186,0.00018242125,0.97014534,0.00001418399,0.00005161417,0.000053908123,0.00012745937,0.0041036387,0.00016289628,0.003380106,0.014854009,0.0054282793],"study_design_scores_gemma":[0.004162179,0.005672983,0.47048247,0.00008312697,0.0000846743,0.00008234451,0.0018426069,0.00873206,0.00003500386,0.08661543,0.42188668,0.00032042892],"about_ca_topic_score_codex":0.00010655545,"about_ca_topic_score_gemma":0.00056795625,"teacher_disagreement_score":0.4996629,"about_ca_system_score_codex":0.00016984093,"about_ca_system_score_gemma":0.00059710303,"threshold_uncertainty_score":0.9109859},"labels":[],"label_agreement":null},{"id":"W4207076773","doi":"10.1016/j.jclinepi.2022.01.014","title":"A review of high impact journals found that misinterpretation of non-statistically significant results from randomized trials was common","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"National Institute for Health and Care Research","keywords":"Medicine; Randomized controlled trial; Internal medicine","score_opus":0.9548699253795186,"score_gpt":0.7395215659202787,"score_spread":0.2153483594592399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207076773","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005907764,0.93471247,0.057110734,0.0012011456,0.0024328344,0.0027307791,0.0013978467,0.0000014524976,0.00035367024],"genre_scores_gemma":[0.00030169377,0.9766333,0.020940226,0.0010607222,0.0006942734,0.000038785343,0.00015159839,0.000038660477,0.00014072706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.06315664,0.6502116,0.2785344,0.0014626213,0.006105222,0.00052950496],"domain_scores_gemma":[0.0071600247,0.66323936,0.32305604,0.0032474943,0.0027386819,0.00055842235],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.92979735,0.0010567021,0.22568902,0.0011795601,0.00008217839,0.00012017977,0.005304816,0.0009026443,0.026782585],"category_scores_gemma":[0.97967464,0.00040488227,0.07822432,0.0013807091,0.00074701075,0.0002269086,0.0003624998,0.0029104028,0.0001368864],"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":[0.008662267,0.0002627377,0.00011220898,0.012354976,0.010898132,0.000040910265,0.0000421982,0.00004697281,1.8994454e-7,0.0002552831,0.12298448,0.84433967],"study_design_scores_gemma":[0.022724437,0.0012075308,0.0004708699,0.1350167,0.041562848,0.00018671785,0.000040769457,0.00072952115,1.0085765e-7,0.054482475,0.7431263,0.00045178153],"about_ca_topic_score_codex":0.00017627372,"about_ca_topic_score_gemma":0.000006811236,"teacher_disagreement_score":0.84388787,"about_ca_system_score_codex":0.00013530113,"about_ca_system_score_gemma":0.0019990976,"threshold_uncertainty_score":0.9998403},"labels":[],"label_agreement":null},{"id":"W4210352994","doi":"10.1016/j.jclinepi.2022.01.024","title":"Investigators' sense of failure thwarted transparency in clinical trials discontinued for poor recruitment","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"McMaster University; Impact","funders":"Universität Basel; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Discontinuation; Clinical trial; Transparency (behavior); Medicine; Randomized controlled trial; Family medicine; Psychology; Psychiatry; Political science; Surgery; Internal medicine","score_opus":0.9437518522651253,"score_gpt":0.7463537152517279,"score_spread":0.19739813701339737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210352994","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":[0.85697985,0.000939645,0.0029288065,0.13366286,0.0029222912,0.0022657306,0.00011254637,0.000014321049,0.00017392913],"genre_scores_gemma":[0.9531264,0.0024200238,0.030460868,0.011239538,0.0020811842,0.00015196597,0.000027426162,0.00004987795,0.00044277136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.86569345,0.08092095,0.049364563,0.0011445932,0.0017137341,0.0011626947],"domain_scores_gemma":[0.19356261,0.78963435,0.013129832,0.00094602845,0.0013318853,0.0013952657],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5164718,0.00026470565,0.009290282,0.0003590289,0.000082403174,0.0000046227005,0.0005922946,0.001192747,0.00047456037],"category_scores_gemma":[0.86990595,0.00018790332,0.0037547315,0.00042804086,0.0012983256,0.00007409715,0.00021137334,0.009470523,0.0000042706956],"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":[0.024677426,0.0041456334,0.88555425,0.0005366082,0.0012659287,0.00037320633,0.00024858533,0.00023098488,0.00043176176,0.022243053,0.0308103,0.029482279],"study_design_scores_gemma":[0.04358717,0.037822414,0.44530228,0.0013232832,0.0011390893,0.00035800762,0.00095740194,0.0020374276,0.00017960538,0.380607,0.08624149,0.00044485132],"about_ca_topic_score_codex":0.000035103916,"about_ca_topic_score_gemma":0.0001749784,"teacher_disagreement_score":0.7087134,"about_ca_system_score_codex":0.000115406016,"about_ca_system_score_gemma":0.0030633442,"threshold_uncertainty_score":0.99281466},"labels":[],"label_agreement":null},{"id":"W4210425716","doi":"10.1016/j.jclinepi.2022.01.021","title":"Three comments on the RIR method","year":2022,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","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":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine","score_opus":0.40919532073739534,"score_gpt":0.5422486054504764,"score_spread":0.13305328471308103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210425716","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":[0.0007466054,0.00063718646,0.001518058,0.983345,0.003592762,0.00030498716,0.00001063716,0.000013589057,0.0098312115],"genre_scores_gemma":[0.00009430179,0.00097086316,0.0043558097,0.9771035,0.014598219,0.000012271884,0.00002697368,0.00004926989,0.0027888366],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9744674,0.017895952,0.005854623,0.00041591658,0.0007973305,0.0005687844],"domain_scores_gemma":[0.6699569,0.3247692,0.0040572886,0.0007731175,0.00017587349,0.0002676086],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06193694,0.0003854377,0.008842526,0.00017554307,0.00011679552,0.0000075270686,0.00065856596,0.00149296,0.0031101962],"category_scores_gemma":[0.10661688,0.00018833272,0.006628932,0.00014114656,0.00033182953,0.000023651673,0.00014701171,0.014010955,0.00009695145],"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":[0.000974458,0.00012217996,0.058284726,0.000041620122,0.0011740035,0.0035233905,0.00000835867,0.00000938574,1.0622128e-7,0.0027837523,0.92569554,0.007382466],"study_design_scores_gemma":[0.0014336074,0.002379628,0.04745889,0.00011840952,0.0007470681,0.0027240913,0.000011073795,0.000038746817,1.8781505e-7,0.00459789,0.94033873,0.00015167604],"about_ca_topic_score_codex":0.00002173841,"about_ca_topic_score_gemma":0.0000011714577,"teacher_disagreement_score":0.30687326,"about_ca_system_score_codex":0.000103543185,"about_ca_system_score_gemma":0.0003308833,"threshold_uncertainty_score":0.9998033},"labels":[],"label_agreement":null},{"id":"W4213133915","doi":"10.1016/j.jclinepi.2022.02.001","title":"Diagnostic test accuracy network meta-analysis methods: A scoping review and empirical assessment","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":29,"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":"National Institute for Health and Care Research","keywords":"Meta-analysis; Meta-regression; Regression analysis; Statistics; Computer science; Linear regression; Data mining; Regression; Medicine; Mathematics; Pathology","score_opus":0.985372215948839,"score_gpt":0.8120981805749393,"score_spread":0.17327403537389963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213133915","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5505346e-7,0.9239003,0.0670216,0.005468688,0.00094820873,0.0022339937,0.000038458456,0.0000038105923,0.0003848],"genre_scores_gemma":[2.8108636e-7,0.8471478,0.14170806,0.009562758,0.0008345526,0.0002347489,0.000018689185,0.000035807367,0.00045726175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.20537671,0.6140038,0.17229953,0.0027918878,0.0046277577,0.0009002991],"domain_scores_gemma":[0.00827171,0.814717,0.16938114,0.0052317353,0.0014008359,0.0009975709],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.89837044,0.0013252931,0.21544728,0.0011416292,0.00029777279,0.00030603522,0.0056935246,0.0008584116,0.063977],"category_scores_gemma":[0.98490703,0.0005271226,0.1137955,0.0060344585,0.00037876953,0.00027308677,0.0014182185,0.0047124987,0.0002701039],"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":[0.0000018273637,0.00015123509,0.0033468676,0.016498638,0.18940668,0.000063886466,0.000004244793,0.00010292148,2.0399088e-10,0.0001651845,0.098374546,0.691884],"study_design_scores_gemma":[0.000054811546,0.00016709368,0.00018217244,0.0053604534,0.447818,0.00020120226,0.0000042751385,0.00010302711,8.6486034e-11,0.0023969398,0.5434889,0.0002230524],"about_ca_topic_score_codex":0.0000042866322,"about_ca_topic_score_gemma":0.000011980854,"teacher_disagreement_score":0.69166094,"about_ca_system_score_codex":0.00010358144,"about_ca_system_score_gemma":0.0020616862,"threshold_uncertainty_score":0.9999498},"labels":[],"label_agreement":null},{"id":"W4214525864","doi":"10.1016/j.jclinepi.2022.02.011","title":"Biological plausibility in environmental health systematic reviews: a GRADE concept paper","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Cochrane; University of Ottawa; Impact; McMaster University","funders":"","keywords":"Generalizability theory; Systematic review; Certainty; Context (archaeology); Grading (engineering); Management science; Psychology; MEDLINE; Epistemology; Biology; Ecology; Engineering","score_opus":0.945471736437365,"score_gpt":0.6817474349703928,"score_spread":0.26372430146697223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214525864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82889086,0.09332532,0.014818042,0.0517704,0.005113857,0.005535347,0.00008233895,0.0000067447554,0.00045707345],"genre_scores_gemma":[0.97052604,0.0025593063,0.005344376,0.020698974,0.0003185917,0.00007282139,0.0000055626792,0.000008854365,0.00046547945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.21124728,0.65558857,0.12770711,0.0013594462,0.0034388527,0.00065877126],"domain_scores_gemma":[0.4713138,0.4142256,0.10945851,0.003949477,0.00020958774,0.00084302586],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.84543955,0.0003187132,0.028446402,0.00028699054,0.00015617318,0.000035247336,0.0025441444,0.00019283281,0.01585945],"category_scores_gemma":[0.71824783,0.00013194051,0.007175189,0.00063177035,0.00031938567,0.00015463418,0.00042051147,0.0017010102,0.00046254307],"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":[0.00009433408,0.0009515635,0.88862664,0.00068702875,0.00027467913,0.000057440306,0.00046203006,0.00067347405,0.0000065935124,0.00286999,0.094494164,0.01080207],"study_design_scores_gemma":[0.001665902,0.002878637,0.59528285,0.00074923673,0.00020013224,0.00074748887,0.0025610994,0.0030407025,1.9189282e-7,0.06756591,0.32494444,0.00036344866],"about_ca_topic_score_codex":0.000011360523,"about_ca_topic_score_gemma":0.000014928594,"teacher_disagreement_score":0.2933438,"about_ca_system_score_codex":0.00019604724,"about_ca_system_score_gemma":0.00020247577,"threshold_uncertainty_score":0.98597735},"labels":[],"label_agreement":null},{"id":"W4214563712","doi":"10.1016/j.jclinepi.2022.02.009","title":"The use of the GRADE dose–response gradient domain in nutrition evidence syntheses varies considerably","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"Deutsche Forschungsgemeinschaft","keywords":"Medicine; Grading (engineering); Comparability; Observational study; Medical physics; Internal medicine; Mathematics","score_opus":0.9501490119726209,"score_gpt":0.647993840881699,"score_spread":0.30215517109092194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214563712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89160126,0.00631054,0.002697579,0.0969561,0.0018547582,0.00053706666,0.000012335931,0.0000010613879,0.000029295526],"genre_scores_gemma":[0.99005187,0.0014002747,0.004847736,0.003170431,0.00012939819,0.000026979924,1.07591724e-7,0.0000056973645,0.00036748737],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.31351173,0.6232797,0.0575599,0.0007758305,0.0043554716,0.00051738723],"domain_scores_gemma":[0.053903732,0.90896934,0.033672005,0.0023595677,0.00092311314,0.00017221822],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.70291775,0.00018444686,0.00666787,0.00024438664,0.00036304528,0.0001082521,0.0024906504,0.000112799295,0.000913286],"category_scores_gemma":[0.9424222,0.00006335867,0.004178406,0.0009426759,0.00080174603,0.00023064684,0.00040325813,0.0011290107,0.000022304117],"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":[0.0031088584,0.0007586916,0.736137,0.000054807526,0.00054033863,0.00007290087,0.0006576123,0.0073459935,0.000079690326,0.036618486,0.20057033,0.014055288],"study_design_scores_gemma":[0.00037227382,0.00058391434,0.3972014,0.00031688542,0.00015298836,0.00030224994,0.0011294337,0.0022421065,0.0000038788885,0.20448779,0.39310923,0.00009787614],"about_ca_topic_score_codex":0.000027770448,"about_ca_topic_score_gemma":0.000071223825,"teacher_disagreement_score":0.3389356,"about_ca_system_score_codex":0.00005786905,"about_ca_system_score_gemma":0.00036935956,"threshold_uncertainty_score":0.99998415},"labels":[],"label_agreement":null},{"id":"W4220822415","doi":"10.1016/j.jclinepi.2022.03.014","title":"Five common pitfalls in mixed methods systematic reviews: lessons learned","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Trinity Western University; Western University; Wilfrid Laurier University; Queen's University","funders":"","keywords":"Systematic review; Management science; Citation; Process (computing); Computer science; MEDLINE; Data science; Medicine; Engineering; Political science","score_opus":0.9631165317017311,"score_gpt":0.7571042532694495,"score_spread":0.20601227843228154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220822415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28293335,0.119035356,0.37323016,0.18790466,0.022001376,0.007748797,0.000056812172,0.000017407174,0.0070720785],"genre_scores_gemma":[0.61463964,0.009227441,0.3329361,0.027203977,0.0013251216,0.00037949678,0.00001025531,0.00006923921,0.01420875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.06730186,0.8078681,0.12008417,0.0010692566,0.0031284834,0.0005480851],"domain_scores_gemma":[0.060605157,0.8057105,0.12697938,0.0047822758,0.0012964568,0.0006262473],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.93323183,0.00035909115,0.038994405,0.00074214843,0.00016498806,0.00008000913,0.004204437,0.0002465033,0.0055073607],"category_scores_gemma":[0.92329437,0.00016157111,0.010212513,0.0016074511,0.000177849,0.00017699733,0.00058935396,0.0022824344,0.00063731015],"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":[0.00029025666,0.0011750864,0.19799988,0.0043402403,0.0017672213,0.00023806552,0.001052717,0.008780929,0.000028463532,0.037785895,0.4810006,0.26554063],"study_design_scores_gemma":[0.0015304282,0.0012995279,0.09759816,0.001862402,0.001256731,0.0005866908,0.0032331366,0.026800893,0.0000010978965,0.35348237,0.5118718,0.00047672915],"about_ca_topic_score_codex":0.000022118717,"about_ca_topic_score_gemma":0.00004504184,"teacher_disagreement_score":0.33170626,"about_ca_system_score_codex":0.00009782243,"about_ca_system_score_gemma":0.00022540629,"threshold_uncertainty_score":0.99969995},"labels":[],"label_agreement":null},{"id":"W4220930523","doi":"10.1016/j.jclinepi.2022.03.006","title":"The currency and completeness of specialized databases of COVID-19 publications","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Academic Publishing and Open Access","field":"Decision Sciences","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":"McMaster University; Children's Hospital of Eastern Ontario; Canadian Agency for Drugs and Technologies in Health","funders":"Centers for Disease Control and Prevention","keywords":"Coronavirus disease 2019 (COVID-19); Database; Systematic review; Medicine; MEDLINE; 2019-20 coronavirus outbreak; Completeness (order theory); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data collection; Information retrieval; Library science; Computer science; Pathology; Infectious disease (medical specialty); Disease; Statistics; Mathematics; Political science; Outbreak","score_opus":0.7628664202989819,"score_gpt":0.6530062239956689,"score_spread":0.109860196303313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220930523","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":[0.57203096,0.00872451,0.071950324,0.33638042,0.0069228318,0.0003888629,0.00056026905,0.000014927657,0.003026906],"genre_scores_gemma":[0.9851109,0.0026606626,0.0045452253,0.0063869483,0.0007906021,0.000008598431,0.000012425289,0.0000088346505,0.00047580086],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.968033,0.01858974,0.011318487,0.00041243088,0.0013289198,0.00031738958],"domain_scores_gemma":[0.47779083,0.49765006,0.02108854,0.0012040685,0.0015227357,0.0007437715],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18054129,0.00009385373,0.0018621671,0.00025633042,0.00037144823,0.000041354517,0.003223324,0.000092447975,0.000636825],"category_scores_gemma":[0.7069344,0.00005094809,0.00040943563,0.00075392675,0.0011783323,0.0005082898,0.001038955,0.0011775307,0.0000020289767],"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":[0.00029485353,0.00012295746,0.6303847,0.00000624387,0.00005056755,0.0000017229781,0.000082796214,0.0002740861,0.0000047137582,0.093952805,0.23584823,0.038976323],"study_design_scores_gemma":[0.0006480194,0.00017080114,0.1616093,0.000005975299,0.000022618722,0.000064459135,0.0006500797,0.0004675461,0.0000012280989,0.18088952,0.6554237,0.000046772762],"about_ca_topic_score_codex":0.0001250787,"about_ca_topic_score_gemma":0.000029429957,"teacher_disagreement_score":0.5263931,"about_ca_system_score_codex":0.000024699691,"about_ca_system_score_gemma":0.0010850786,"threshold_uncertainty_score":0.8438052},"labels":[],"label_agreement":null},{"id":"W4220939231","doi":"10.1016/j.jclinepi.2022.03.007","title":"GRADE summary of findings tables enhanced understanding of values and preferences evidence","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Hamilton Health Sciences; University of Toronto; McMaster University; Cochrane; Impact; McMaster University Medical Centre","funders":"McMaster University","keywords":"Table (database); Brainstorming; Evidence-based practice; Guideline; Psychology; Scale (ratio); Evidence-based medicine; Computer science; Medical education; Applied psychology; Knowledge management; Medicine; Alternative medicine; Data mining; Artificial intelligence; Geography","score_opus":0.8499002320094508,"score_gpt":0.5885156272916784,"score_spread":0.26138460471777236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220939231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95102245,0.012169288,0.012569338,0.022383472,0.0012134574,0.00019013527,0.00008321195,0.0000046435425,0.00036403062],"genre_scores_gemma":[0.9867406,0.0052310065,0.0051720557,0.0025324377,0.00021865436,0.0000064870205,0.000002375671,0.00000990417,0.000086501066],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9777959,0.005169058,0.016278924,0.00033893203,0.00012750986,0.00028966527],"domain_scores_gemma":[0.89988965,0.08275748,0.016817352,0.00025479053,0.00009738503,0.00018335851],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15453006,0.00012297633,0.003532986,0.00031583424,0.00012031172,0.000005712143,0.00039846962,0.00015612697,0.00033167755],"category_scores_gemma":[0.13480999,0.0001264118,0.00035240792,0.0001552171,0.00039019212,0.00032898865,0.0001479733,0.00055859354,0.000004594453],"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":[0.00021974015,0.00017240776,0.8704011,0.00047972548,0.00021790042,0.0000011628217,0.0011148233,0.0011466817,0.00002899982,0.112018205,0.013853922,0.00034536628],"study_design_scores_gemma":[0.0012095412,0.0019983563,0.22723357,0.0005991049,0.00004164123,0.000026170565,0.004094016,0.0019872054,0.000030150799,0.76036745,0.0021943701,0.00021839175],"about_ca_topic_score_codex":0.00017194306,"about_ca_topic_score_gemma":0.0000142469335,"teacher_disagreement_score":0.6483493,"about_ca_system_score_codex":0.00018154364,"about_ca_system_score_gemma":0.00025637046,"threshold_uncertainty_score":0.8724779},"labels":[],"label_agreement":null},{"id":"W4220953504","doi":"10.1016/j.jclinepi.2022.03.015","title":"The construct of certainty of evidence has not been disseminated to systematic reviews and clinical practice guidelines: author's reply","year":2022,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Cochrane; Impact; Health Sciences Centre","funders":"","keywords":"Grading (engineering); Scopus; Certainty; Systematic review; Quality of evidence; Construct (python library); Psychology; Medicine; Publication bias; Meta-analysis; MEDLINE; Computer science; Philosophy; Epistemology; Political science; Engineering; Pathology; Law","score_opus":0.968278234862471,"score_gpt":0.732174767701637,"score_spread":0.23610346716083397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220953504","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007317974,0.026596615,0.005798056,0.95957226,0.0043600313,0.0027595644,0.000040710718,0.0000025838715,0.00013841386],"genre_scores_gemma":[0.0010597245,0.02452581,0.07282921,0.8934086,0.0035707287,0.00008000457,0.000007395711,0.00005044635,0.0044680554],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.076538175,0.616508,0.2950112,0.0023595067,0.008757975,0.00082512357],"domain_scores_gemma":[0.012248975,0.74151766,0.22613636,0.0059907725,0.0136074945,0.0004987131],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.917027,0.0007762706,0.052828703,0.0005601833,0.00025697972,0.00019846427,0.006908675,0.0015667833,0.0013033487],"category_scores_gemma":[0.99596566,0.00027371844,0.014381308,0.0013627744,0.0015748836,0.00026172376,0.0010073731,0.0072920746,0.00013259266],"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":[0.0002649676,0.000047867918,0.004340967,0.0038208086,0.0015999569,0.00008282401,0.000062355706,0.000021777785,7.8228885e-7,0.00023240238,0.97476846,0.014756814],"study_design_scores_gemma":[0.0002673375,0.0013846618,0.0016029521,0.009214292,0.004290029,0.00070308783,0.0004503018,0.0007520421,2.4183558e-7,0.0027833513,0.97830987,0.00024180888],"about_ca_topic_score_codex":0.00005266524,"about_ca_topic_score_gemma":0.00001113092,"teacher_disagreement_score":0.12500967,"about_ca_system_score_codex":0.000066354296,"about_ca_system_score_gemma":0.0011166802,"threshold_uncertainty_score":0.9999715},"labels":[],"label_agreement":null},{"id":"W4221049808","doi":"10.1016/j.jclinepi.2022.03.017","title":"Using Explicit Thresholds were valuable for judging Benefits and Harms in partially contextualized GRADE Guidelines","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"","keywords":"Guideline; Certainty; Medicine; Coronavirus disease 2019 (COVID-19); Actuarial science; Business; Mathematics; Disease","score_opus":0.8757076099883864,"score_gpt":0.6704513374133007,"score_spread":0.20525627257508572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221049808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9045746,0.0024680905,0.015825788,0.075005054,0.0014546744,0.0006179306,0.000022254007,0.000012557779,0.000019095189],"genre_scores_gemma":[0.86506194,0.0018039843,0.0943973,0.0367142,0.0018719035,0.000035879384,0.000022851782,0.00004277772,0.000049181373],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98394495,0.0031555865,0.011622165,0.000422759,0.0003730721,0.00048146737],"domain_scores_gemma":[0.93168193,0.061238427,0.0055719796,0.00031743833,0.0007812932,0.00040892285],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067288704,0.00019758458,0.002726282,0.00021823787,0.00014409369,0.000009812023,0.00020046743,0.00020597779,0.0002244353],"category_scores_gemma":[0.23441747,0.0001625264,0.0006031105,0.00017685108,0.00011577057,0.00022090865,0.00020354126,0.0012228029,0.0000012188732],"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":[0.0059643146,0.00057960965,0.8992033,0.000070081274,0.00028133363,0.000073677315,0.00009830563,0.015555255,0.0005078736,0.0038110637,0.014130578,0.059724607],"study_design_scores_gemma":[0.07415399,0.013351538,0.33006844,0.00089390075,0.0021925445,0.004182127,0.0042135688,0.33697596,0.00009330993,0.0589907,0.17398849,0.0008954065],"about_ca_topic_score_codex":0.00017705132,"about_ca_topic_score_gemma":0.000115424344,"teacher_disagreement_score":0.56913483,"about_ca_system_score_codex":0.00010426785,"about_ca_system_score_gemma":0.0005807596,"threshold_uncertainty_score":0.9604226},"labels":[],"label_agreement":null},{"id":"W4221059283","doi":"10.1016/j.jclinepi.2022.02.015","title":"Methodological approaches for developing, reporting, and assessing evidence-based clinical practice guidelines: a systematic survey","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":22,"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; McMaster University; Impact; McMaster Children's Hospital","funders":"","keywords":"Usability; Guideline; Systematic review; MEDLINE; Medicine; Clinical Practice; Data science; Medical physics; Computer science; Family medicine; Pathology","score_opus":0.9931637016298127,"score_gpt":0.8054662368782025,"score_spread":0.1876974647516102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221059283","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":[0.000057063757,0.7789171,0.20084386,0.013516441,0.0034976732,0.003090232,0.000019172363,0.000033928725,0.000024538595],"genre_scores_gemma":[0.0000045146576,0.55736524,0.42698205,0.013184085,0.0021314775,0.00013480497,0.00009892952,0.00007007557,0.000028789025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.58576643,0.24338223,0.16547424,0.0024679902,0.0016746166,0.001234492],"domain_scores_gemma":[0.012095791,0.820083,0.16160737,0.0010985616,0.0043427204,0.0007725441],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.74734515,0.0008884068,0.032977905,0.0004661503,0.00022861555,0.000077129305,0.0007649585,0.002137535,0.000088493085],"category_scores_gemma":[0.997223,0.00056284026,0.0064344895,0.0006146432,0.00061705516,0.0006331862,0.00046647643,0.0061258175,0.0000070036517],"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":[0.0013617527,0.00054719305,0.007230655,0.11287218,0.0024155572,0.00028240203,0.0000063688653,0.000014176078,1.2184815e-8,0.00023342582,0.012661896,0.86237437],"study_design_scores_gemma":[0.0023714763,0.004232073,0.003946802,0.09631253,0.0192701,0.0060121557,0.00024038133,0.0013172977,1.7643844e-8,0.00071387156,0.8650348,0.0005484984],"about_ca_topic_score_codex":0.000056990866,"about_ca_topic_score_gemma":0.000010211856,"teacher_disagreement_score":0.8618259,"about_ca_system_score_codex":0.00037776705,"about_ca_system_score_gemma":0.01183563,"threshold_uncertainty_score":0.9996823},"labels":[],"label_agreement":null},{"id":"W4221104835","doi":"10.1016/j.jclinepi.2022.03.003","title":"Data and code availability statements in systematic reviews of interventions were often missing or inaccurate: a content analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":52,"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; University of Ottawa","funders":"National Health and Medical Research Council; Australian Research Council; Monash University; Alexander von Humboldt-Stiftung","keywords":"Citation; Computer science; Systematic review; Scopus; Information retrieval; Data file; Code review; Sample (material); Raw data; Data science; MEDLINE; World Wide Web; Software; Software quality; Database; Software development","score_opus":0.9845596810336735,"score_gpt":0.7518682568062373,"score_spread":0.23269142422743627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221104835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7717259,0.039794117,0.16447687,0.017500304,0.0016598799,0.003804108,0.0008040524,0.0000033410838,0.00023141391],"genre_scores_gemma":[0.9704663,0.0031460398,0.022551063,0.0020268895,0.00008722322,0.000055470442,0.00003149349,0.00001191333,0.0016235868],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.34726128,0.45329657,0.19405921,0.0015868386,0.0033266905,0.00046941987],"domain_scores_gemma":[0.19459642,0.523981,0.26562735,0.011921114,0.003020066,0.00085407874],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8208382,0.00023571671,0.025874382,0.0007757178,0.0000937036,0.00006263554,0.0032093187,0.00010209784,0.007168876],"category_scores_gemma":[0.83655274,0.0000998817,0.0054759225,0.0017538143,0.0002041385,0.00036025525,0.0010005414,0.0007531496,0.0000331033],"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":[0.0002031361,0.00058734143,0.9565487,0.0050411127,0.0029327096,0.000026197695,0.00015235443,0.00039056686,0.000003301647,0.0002344653,0.02450079,0.0093793385],"study_design_scores_gemma":[0.0031364127,0.0022012666,0.68967545,0.006026194,0.016768526,0.00024563563,0.0067489934,0.14863956,4.171157e-7,0.02045665,0.10559823,0.00050265243],"about_ca_topic_score_codex":0.0000318797,"about_ca_topic_score_gemma":0.00037737272,"teacher_disagreement_score":0.26687324,"about_ca_system_score_codex":0.000061722596,"about_ca_system_score_gemma":0.00018526525,"threshold_uncertainty_score":0.9937387},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4221116448","doi":"10.1016/j.jclinepi.2022.03.019","title":"Crowdsourcing trainees in a living systematic review provided valuable experiential learning opportunities: a mixed-methods study","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":12,"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; Centre for Global Health Research; University of Calgary; University of Alberta","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research","keywords":"Experiential learning; Medical education; Systematic review; Medicine; Task (project management); Focus group; MEDLINE; Psychology; Applied psychology; Pedagogy","score_opus":0.27578349570699867,"score_gpt":0.5409955708064101,"score_spread":0.26521207509941147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221116448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8649044,0.124323905,0.003127509,0.004538724,0.000964272,0.001945774,0.0000016926969,0.00003096478,0.0001627362],"genre_scores_gemma":[0.9430361,0.04713721,0.006344665,0.0025350908,0.00027194322,0.00027602835,0.000002578511,0.00003640462,0.00036002247],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.9351901,0.0558254,0.007530006,0.00032023244,0.000577628,0.00055667054],"domain_scores_gemma":[0.93240786,0.061905116,0.004264367,0.00046467478,0.0003705376,0.00058746984],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14668725,0.00019748292,0.0052448255,0.0003476922,0.00019697734,0.000013918459,0.0003292525,0.00009120335,0.0006875389],"category_scores_gemma":[0.27708942,0.0001458299,0.00082394795,0.00027512325,0.0001406677,0.00013639993,0.00024065966,0.0023913388,0.0000028608551],"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":[0.0049308743,0.014801173,0.60977477,0.19033463,0.005514828,0.0077969185,0.04290632,0.0030169778,0.00029912032,0.0014955256,0.014417736,0.104711145],"study_design_scores_gemma":[0.02373813,0.069181606,0.0548108,0.4099198,0.0010185008,0.014608864,0.38802564,0.014954892,0.000012141333,0.0029744739,0.01940407,0.0013511056],"about_ca_topic_score_codex":0.000048717655,"about_ca_topic_score_gemma":0.000009774416,"teacher_disagreement_score":0.55496395,"about_ca_system_score_codex":0.00009733886,"about_ca_system_score_gemma":0.00060300535,"threshold_uncertainty_score":0.9999102},"labels":[],"label_agreement":null},{"id":"W4221117598","doi":"10.1016/j.jclinepi.2022.03.008","title":"An evaluation of the COVID-19 recommendation map identified diverging clinical and public health guidance","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":10,"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; Western University; Université Laval; Impact; The Quebec Population Health Research Network; Queen's University; McMaster University; St. Joseph’s Healthcare Hamilton; Bruyère; Cochrane","funders":"Canadian Institutes of Health Research; World Health Organization","keywords":"Guideline; Divergence (linguistics); Psychological intervention; Public health; Population; Contextualization; Statement (logic); Population health; Medicine; MEDLINE; Psychology; Actuarial science; Family medicine; Interpretation (philosophy); Computer science; Environmental health; Pathology; Political science; Nursing; Business; Linguistics","score_opus":0.862796020190976,"score_gpt":0.707514017496779,"score_spread":0.155282002694197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221117598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.574076,0.00039489346,0.0117234625,0.40991402,0.0033444243,0.0004900377,0.000018862538,0.000009382959,0.000028911578],"genre_scores_gemma":[0.91309446,0.00055669533,0.0057408893,0.07959536,0.0009252449,0.000010601016,0.000045645167,0.000013686596,0.000017405746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9008308,0.07764488,0.019191759,0.00061646296,0.0012424383,0.0004736568],"domain_scores_gemma":[0.88260317,0.091435365,0.022012664,0.0008521199,0.0017816415,0.0013150239],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33627144,0.00012974604,0.001781703,0.0001435583,0.00028590925,0.000009679444,0.00033459242,0.00015854502,0.00087225693],"category_scores_gemma":[0.5093655,0.0000931295,0.0005579116,0.00025087333,0.0004345774,0.00030296374,0.00027991636,0.001647697,0.0000025029665],"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":[0.00067300204,0.0006098804,0.81180066,0.000042443913,0.00014186418,0.0000021913745,0.000092645685,0.00042377517,0.000011764463,0.0005917772,0.0277492,0.1578608],"study_design_scores_gemma":[0.008381732,0.0032757395,0.8711719,0.000032476466,0.00041681537,0.0002852113,0.0012950684,0.017755931,0.0000010690858,0.014168388,0.08311674,0.00009894128],"about_ca_topic_score_codex":0.00019066047,"about_ca_topic_score_gemma":0.000095942996,"teacher_disagreement_score":0.33901846,"about_ca_system_score_codex":0.0002619526,"about_ca_system_score_gemma":0.0035309575,"threshold_uncertainty_score":0.9550602},"labels":[],"label_agreement":null},{"id":"W4221135745","doi":"10.1016/j.jclinepi.2022.03.004","title":"The web-based “Right Review” tool asks reviewers simple questions to suggest methods from 41 knowledge synthesis methods","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"Government of Canada","keywords":"Simple (philosophy); Computer science; Web site; Information retrieval; Data science; World Wide Web; Medicine; The Internet; Epistemology","score_opus":0.8756683636672411,"score_gpt":0.7253858727358627,"score_spread":0.15028249093137835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221135745","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020825237,0.20589824,0.65696055,0.12464415,0.006092474,0.0014241667,0.000088290224,0.000011541423,0.0027980914],"genre_scores_gemma":[0.0027490163,0.02407739,0.9355783,0.033473678,0.0012703042,0.00031680134,0.0000059621248,0.000039849736,0.0024887233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.1331058,0.78401935,0.077240914,0.0016318052,0.0032061494,0.00079598225],"domain_scores_gemma":[0.016012866,0.92837965,0.045011,0.006271962,0.0034063002,0.00091823394],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.8992325,0.00048137744,0.02037451,0.00039485472,0.0007344258,0.00014463271,0.0057418332,0.00024318446,0.025105411],"category_scores_gemma":[0.9582789,0.00019595552,0.011633653,0.0021676654,0.0003206514,0.00014456494,0.0006389401,0.001983648,0.0009992883],"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":[0.00003769705,0.000109763525,0.0069067213,0.00005484353,0.00038298196,0.000007112723,0.000014566959,0.0002971966,0.000008488843,0.0017396027,0.5441547,0.44628632],"study_design_scores_gemma":[0.00019206112,0.00024347295,0.00999944,0.00033497615,0.0012771222,0.000033089986,0.00006269733,0.0064308927,0.0000040011496,0.02995335,0.95126873,0.00020014237],"about_ca_topic_score_codex":0.000024953762,"about_ca_topic_score_gemma":0.000037301685,"teacher_disagreement_score":0.44608617,"about_ca_system_score_codex":0.00012289999,"about_ca_system_score_gemma":0.00091102906,"threshold_uncertainty_score":0.99977857},"labels":[],"label_agreement":null},{"id":"W4223456116","doi":"10.1016/j.jclinepi.2022.04.005","title":"How are randomized clinical trials ethically justified? A systematic scoping review and thematic analysis of reasons that ethically justify randomized clinical trials","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Ottawa Hospital","funders":"Canadian Institutes of Health Research; University of Ottawa; Heart and Stroke Foundation of Canada","keywords":"Randomized controlled trial; Thematic analysis; Normative; Data extraction; Coding (social sciences); Protocol (science); Psychology; Systematic review; Clinical trial; MEDLINE; Medicine; Alternative medicine; Applied psychology; Epistemology; Qualitative research; Sociology; Social science; Pathology; Political science","score_opus":0.9549452113031753,"score_gpt":0.7294765781556601,"score_spread":0.2254686331475152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223456116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012210456,0.26726162,0.45559996,0.2305744,0.0073190373,0.026507065,0.00017564291,0.00002739128,0.00032442418],"genre_scores_gemma":[0.44566453,0.38714296,0.08601521,0.07163257,0.0035948637,0.0021484718,0.000060892067,0.0001792559,0.0035612562],"study_design_codex":"randomized_trial","study_design_gemma":"meta_analysis","domain_scores_codex":[0.006462334,0.74555457,0.23865315,0.0020296553,0.006618222,0.00068206934],"domain_scores_gemma":[0.00084781006,0.71063614,0.27861792,0.0043540634,0.004315634,0.0012284445],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.99554163,0.0011452497,0.2941148,0.0018786242,0.00040686585,0.00043326872,0.0052094203,0.0019249138,0.00532872],"category_scores_gemma":[0.9986799,0.0004770935,0.10820383,0.0035696384,0.0032269566,0.00033720065,0.0010776662,0.007650406,0.000056588433],"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":[0.39392614,0.0032313569,0.05744015,0.12960112,0.2509603,0.00026458193,0.0006553514,0.0013681493,0.000003827653,0.043607585,0.09224504,0.026696423],"study_design_scores_gemma":[0.39644516,0.00091654685,0.0022989376,0.073413834,0.43976632,0.00030724463,0.001267094,0.04283845,2.3395414e-7,0.041002564,0.00084225123,0.00090136926],"about_ca_topic_score_codex":0.000009760233,"about_ca_topic_score_gemma":0.00002399977,"teacher_disagreement_score":0.43345407,"about_ca_system_score_codex":0.000059171656,"about_ca_system_score_gemma":0.0015047413,"threshold_uncertainty_score":0.9997681},"labels":[],"label_agreement":null},{"id":"W4223918414","doi":"10.1016/j.jclinepi.2022.04.006","title":"JBI series paper 2: tailored evidence synthesis approaches are required to answer diverse questions: a pragmatic evidence synthesis toolkit from JBI","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":107,"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":"National Health and Medical Research Council; University of Adelaide","keywords":"Critical appraisal; Evidence-based practice; Systematic review; Evidence-based medicine; Computer science; Management science; Data science; Medicine; MEDLINE; Political science; Engineering; Alternative medicine","score_opus":0.8966550325204948,"score_gpt":0.7093741918876009,"score_spread":0.18728084063289396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223918414","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":[0.00027478737,0.89855564,0.001734917,0.08529805,0.00855337,0.0045995866,0.0006331485,0.00010805194,0.00024243866],"genre_scores_gemma":[0.00011210314,0.93745923,0.02281717,0.032753903,0.0031638264,0.0030314054,0.000009486261,0.000100242636,0.0005526289],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8410432,0.1323986,0.022029316,0.0014885976,0.0013143573,0.0017259683],"domain_scores_gemma":[0.1972277,0.76747155,0.029956922,0.0021609473,0.0009446718,0.0022382385],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.13255545,0.00094875,0.013679373,0.0008548416,0.0013118368,0.00004121921,0.003237969,0.0016154902,0.008571711],"category_scores_gemma":[0.8918855,0.00069343374,0.002331531,0.0014183428,0.0008037288,0.0018536417,0.001383775,0.0056573907,0.0011026397],"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":[0.0005669153,0.00023422709,0.010249212,0.017038437,0.00063150254,0.00010634291,0.001254865,0.00002906197,3.7972714e-7,0.0008938066,0.11515107,0.85384417],"study_design_scores_gemma":[0.00019451555,0.00046593597,0.0037587634,0.07716223,0.0018844291,0.00007333384,0.0024028039,0.000014935318,6.296299e-8,0.0017370622,0.9117649,0.000541001],"about_ca_topic_score_codex":0.00075178035,"about_ca_topic_score_gemma":0.0004330282,"teacher_disagreement_score":0.8533032,"about_ca_system_score_codex":0.0013692837,"about_ca_system_score_gemma":0.013449558,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"W4224111822","doi":"10.1016/j.jclinepi.2022.04.002","title":"The GIN-McMaster guideline tool extension for the integration of quality improvement and quality assurance in guidelines: a description of the methods for its development","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; Impact","funders":"National Health and Medical Research Council; Andrew W. Mellon Foundation; Deutsche Krebshilfe; European Commission; McMaster University; Medical Research Council","keywords":"Guideline; Quality assurance; Medicine; Quality management; Quality (philosophy); Extension (predicate logic); Process management; Operations management; Medical physics; Computer science; Engineering; External quality assessment; Pathology","score_opus":0.8986098985768366,"score_gpt":0.7296762676760437,"score_spread":0.16893363090079294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224111822","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":[0.00067768845,0.5874838,0.38072357,0.02440155,0.0023519082,0.0042992253,0.000053120253,0.0000040930404,0.000005025797],"genre_scores_gemma":[0.00009275361,0.7659596,0.22875679,0.0041615753,0.0005955516,0.0002504558,0.000038949194,0.000028952292,0.000115348004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92613584,0.022637218,0.049342074,0.0006971648,0.0007048439,0.0004828527],"domain_scores_gemma":[0.3487827,0.59453267,0.0500083,0.001289189,0.0051964778,0.00019066648],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30450496,0.00036185706,0.005782493,0.000115421746,0.00017786243,0.000010491892,0.0005656214,0.00046000307,0.00003772193],"category_scores_gemma":[0.7188584,0.00015506988,0.002039681,0.00028228285,0.00030235888,0.00012658752,0.0002893751,0.0014812724,2.562305e-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":[0.0015661938,0.00018531938,0.00041855458,0.0026302321,0.00041542418,1.8971537e-7,0.00004182545,0.000029980125,0.00006554337,0.0005713419,0.0029159507,0.99115944],"study_design_scores_gemma":[0.002735708,0.0011458751,0.0066911974,0.0027028222,0.001457719,0.000029597304,0.00041056098,0.0018648151,0.00001480714,0.0019877832,0.98080623,0.00015290282],"about_ca_topic_score_codex":0.000086919594,"about_ca_topic_score_gemma":0.00022958124,"teacher_disagreement_score":0.99100655,"about_ca_system_score_codex":0.00023077082,"about_ca_system_score_gemma":0.0019382613,"threshold_uncertainty_score":0.7161585},"labels":[],"label_agreement":null},{"id":"W4224121448","doi":"10.1016/j.jclinepi.2022.04.013","title":"Pooling of cohort studies and RCTs affects GRADE certainty of evidence in nutrition research","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Deutsche Forschungsgemeinschaft","keywords":"Certainty; Pooling; Medicine; Randomized controlled trial; Cohort; Empirical evidence; Evidence-based practice; Cohort study; Relative risk; Meta-analysis; Statistical evidence; Internal medicine; Confidence interval; Pathology; Econometrics; Alternative medicine; Economics; Null hypothesis; Computer science; Artificial intelligence","score_opus":0.9892886421241236,"score_gpt":0.7826436628921025,"score_spread":0.20664497923202108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224121448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96222115,0.02521183,0.0005235378,0.011148056,0.00044376575,0.00039170583,0.000002366714,4.2327275e-7,0.000057162433],"genre_scores_gemma":[0.98627186,0.009723087,0.003433309,0.00032820526,0.00013273986,0.000013666876,2.2525532e-7,0.000003619027,0.000093287],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.3363784,0.575785,0.07747908,0.001316807,0.008336777,0.00070399244],"domain_scores_gemma":[0.21319045,0.7495811,0.032348644,0.0014035846,0.0032349443,0.00024128259],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8317484,0.00012672032,0.010987949,0.0007571193,0.000084267034,0.0000128354195,0.001109215,0.00014641156,0.00032248098],"category_scores_gemma":[0.8734676,0.000056950386,0.0017184358,0.0012001507,0.00051346666,0.000120142824,0.0004115752,0.0014399048,0.000006016964],"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":[0.00016630931,0.00017783593,0.9694168,0.00035300356,0.0004527267,0.000019810404,0.00022166513,0.0010574987,0.00006832366,0.0025665073,0.019839676,0.0056598317],"study_design_scores_gemma":[0.00091120845,0.002049448,0.7554114,0.0011856991,0.0002797161,0.00010056209,0.0034156302,0.0046686823,0.00001781807,0.2275441,0.00431315,0.00010258913],"about_ca_topic_score_codex":0.000024884379,"about_ca_topic_score_gemma":0.000020108351,"teacher_disagreement_score":0.22497758,"about_ca_system_score_codex":0.000044748926,"about_ca_system_score_gemma":0.0001611269,"threshold_uncertainty_score":0.7511142},"labels":[],"label_agreement":null},{"id":"W4224271900","doi":"10.1016/j.jclinepi.2022.04.011","title":"Indirectness (transferability) is critical when considering existing economic evaluations for GRADE clinical practice guidelines: a systematic review","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Hamilton Health Sciences; McMaster University; Impact; Cochrane","funders":"NCMIC Foundation","keywords":"EconLit; Grading (engineering); Transferability; CINAHL; Economic evaluation; Guideline; MEDLINE; Systematic review; Checklist; Population; Evidence-based medicine; Psychology; Medical education; Medicine; Computer science; Nursing; Alternative medicine; Psychological intervention; Political science; Pathology","score_opus":0.9520522231143089,"score_gpt":0.7448865542910774,"score_spread":0.2071656688232315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224271900","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":[0.0000019650647,0.8728008,0.01707334,0.09790598,0.0062856134,0.0046855942,0.0007233824,0.00003484718,0.0004884438],"genre_scores_gemma":[0.0000010304417,0.8467585,0.06829958,0.08026747,0.0034241274,0.0009348807,0.000063942614,0.0001251343,0.0001253816],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.78481185,0.060618635,0.15099186,0.0020371147,0.0003561995,0.0011843229],"domain_scores_gemma":[0.12466763,0.7786752,0.09145832,0.0022903918,0.0016859943,0.001222447],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.62809503,0.0008637958,0.042044554,0.00071829796,0.0004135688,0.00007575793,0.001676102,0.0014437225,0.0018606654],"category_scores_gemma":[0.9462537,0.0008406453,0.008065332,0.0002705219,0.000541777,0.000796011,0.00023649902,0.0034821928,0.00067368057],"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":[0.000037096,0.0004221802,0.00024605313,0.79618675,0.002441158,0.000012711881,0.000105993255,0.000030519765,3.888233e-10,0.050380945,0.13466592,0.015470666],"study_design_scores_gemma":[0.00072790234,0.0005167767,0.000008070429,0.13599835,0.0034442244,0.00047765754,0.0001711989,0.0007936603,1.4358283e-9,0.030512638,0.8267764,0.0005731395],"about_ca_topic_score_codex":0.0000806103,"about_ca_topic_score_gemma":0.000015722691,"teacher_disagreement_score":0.71805656,"about_ca_system_score_codex":0.0014311138,"about_ca_system_score_gemma":0.0050187525,"threshold_uncertainty_score":0.9998526},"labels":[],"label_agreement":null},{"id":"W4224871181","doi":"10.1016/j.jclinepi.2022.04.024","title":"Recruitment and implementation challenges were common in stepped-wedge cluster randomized trials: Results from a methodological review","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"CRTS; Cluster (spacecraft); Cluster randomised controlled trial; Randomized controlled trial; Research design; Medicine; Clinical study design; Intervention (counseling); Patient recruitment; Clinical trial; Medical physics; Computer science; Nursing; Surgery; Pathology; Statistics","score_opus":0.99411409522201,"score_gpt":0.802521567571872,"score_spread":0.191592527650138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224871181","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018669929,0.9734796,0.0015164271,0.014198856,0.0020481632,0.008147482,0.00015507774,0.0000025276902,0.0004331487],"genre_scores_gemma":[0.0000021949913,0.9785773,0.016544405,0.0032342244,0.0008313423,0.00050992426,0.000094456984,0.000023294175,0.00018283231],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.025374122,0.7834173,0.18642318,0.0017373041,0.0026115153,0.00043656756],"domain_scores_gemma":[0.017460769,0.8026632,0.17639741,0.0025667965,0.00048181813,0.0004300246],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9724219,0.00089691626,0.1755578,0.00078472553,0.000087325156,0.00009811081,0.0028550783,0.0009491847,0.010682047],"category_scores_gemma":[0.9640941,0.00034253413,0.031070212,0.00068694167,0.00030448323,0.0001674052,0.0007253917,0.0031252885,0.00016595435],"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":[0.003592684,0.00009815815,0.00006405598,0.0028378214,0.0018075014,0.00003593424,0.000051498388,0.0000018147308,1.4226631e-9,0.00037809333,0.04873179,0.94240063],"study_design_scores_gemma":[0.027829396,0.00033374853,0.00016144269,0.010295069,0.008323595,0.000109055676,0.00015836273,0.000048862734,1.5860137e-9,0.024700819,0.9277924,0.00024725773],"about_ca_topic_score_codex":0.000035582438,"about_ca_topic_score_gemma":0.00010895624,"teacher_disagreement_score":0.9421534,"about_ca_system_score_codex":0.0001268099,"about_ca_system_score_gemma":0.0004726432,"threshold_uncertainty_score":0.99990267},"labels":[],"label_agreement":null},{"id":"W4224884314","doi":"10.1016/j.jclinepi.2022.04.023","title":"Causal language use in systematic reviews of observational studies is often inconsistent with intent: a systematic survey","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; McMaster University; Impact; University of Ottawa","funders":"China Scholarship Council","keywords":"Observational study; Systematic review; Medicine; MEDLINE; Psychology; Pathology","score_opus":0.9897340611747545,"score_gpt":0.7407532826178916,"score_spread":0.24898077855686285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224884314","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030852843,0.9925026,0.00066638534,0.00037886578,0.0012023333,0.004803491,0.000097005766,0.0000019461672,0.000038830494],"genre_scores_gemma":[0.00008976415,0.9926673,0.0037121603,0.0016996576,0.00017551954,0.00034595648,0.000026906217,0.000039712908,0.001243034],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.1461501,0.632035,0.21379544,0.0016161766,0.005803805,0.0005994794],"domain_scores_gemma":[0.047752067,0.71302354,0.2304602,0.0047214986,0.0036627466,0.00037995016],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8442437,0.0010370415,0.14926745,0.0015114533,0.00007813837,0.00011267568,0.0041772937,0.00057190564,0.0016652386],"category_scores_gemma":[0.9554045,0.00037859692,0.018061928,0.002790597,0.00040260245,0.00032009202,0.0006031712,0.002177881,0.00024873755],"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":[0.000051561616,0.0002965709,0.031498108,0.9242514,0.007790738,0.00013545204,0.0004129998,0.000029902076,6.5722356e-9,0.0005091406,0.025550172,0.009473995],"study_design_scores_gemma":[0.00071252254,0.0009984948,0.0045821564,0.6533272,0.01699118,0.0010889545,0.0015487816,0.00033172691,5.1601043e-9,0.00090115354,0.31883973,0.00067803735],"about_ca_topic_score_codex":0.00005461113,"about_ca_topic_score_gemma":0.00029223945,"teacher_disagreement_score":0.29328957,"about_ca_system_score_codex":0.00026645002,"about_ca_system_score_gemma":0.0010316885,"threshold_uncertainty_score":0.9998666},"labels":[],"label_agreement":null},{"id":"W4225152530","doi":"10.1016/j.jclinepi.2022.04.012","title":"A multistakeholder development process to prioritize and translate COVID-19 health recommendations for patients, caregivers and the public. A case study of the COVID-19 recommendation map","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Population Health Research Institute; McMaster University; Impact; Cochrane; Bruyère; University of Ottawa; Western University","funders":"Canadian Institutes of Health Research","keywords":"Stakeholder; Psychological intervention; Medicine; Stakeholder engagement; Plain language; Health communication; Public health; Medical education; Nursing; Public relations; Political science","score_opus":0.8585943339859292,"score_gpt":0.735434665113277,"score_spread":0.12315966887265217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225152530","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":[0.38074404,0.000025926243,0.008058176,0.60663927,0.0009078159,0.0034417335,0.00017124927,0.00000703675,0.0000047629874],"genre_scores_gemma":[0.7570457,0.00007385839,0.004555398,0.23761863,0.00009919724,0.00054729474,0.000010913449,0.000011758882,0.000037271937],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.96365976,0.02915895,0.0059810057,0.000362304,0.00030067223,0.00053732784],"domain_scores_gemma":[0.89610803,0.096197054,0.0056893486,0.000250274,0.0005236458,0.0012316711],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.079518475,0.0001402751,0.0011650536,0.00018862233,0.0030066606,0.0000079647,0.0003531748,0.00008882065,0.00015451844],"category_scores_gemma":[0.12605765,0.000086405336,0.00011112873,0.00036349925,0.00027150393,0.00013088336,0.00022580787,0.0010060389,6.0757355e-7],"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":[0.0018773604,0.0007406007,0.51982796,0.00092578743,0.00016391014,0.000009878377,0.2860269,0.0001746111,1.3389547e-7,0.0018056525,0.14187585,0.046571333],"study_design_scores_gemma":[0.018900309,0.0017564831,0.017427105,0.000026165286,0.000039385617,0.00013346088,0.13698895,0.00021444075,3.2117903e-8,0.0015444957,0.8228596,0.000109598215],"about_ca_topic_score_codex":0.0011914098,"about_ca_topic_score_gemma":0.0034771909,"teacher_disagreement_score":0.6809837,"about_ca_system_score_codex":0.0005272791,"about_ca_system_score_gemma":0.0068384944,"threshold_uncertainty_score":0.9987918},"labels":[],"label_agreement":null},{"id":"W4234456008","doi":"10.1016/j.jclinepi.2005.10.017","title":"Simulated computerized adaptive test for patients with lumbar spine impairments was efficient and produced valid measures of function","year":2006,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":86,"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":"Computerized adaptive testing; Item response theory; Discriminant validity; Psychology; Lumbar; Rehabilitation; Physical therapy; Test (biology); Physical medicine and rehabilitation; Discriminant function analysis; Psychometrics; Rating scale; Medicine; Clinical psychology; Machine learning; Developmental psychology; Computer science; Surgery","score_opus":0.09072423280306394,"score_gpt":0.4074716260589953,"score_spread":0.3167473932559314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234456008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97740155,0.00011073716,0.020271776,0.0010321861,0.00041913832,0.0007363512,0.0000047203503,0.000008048478,0.000015484033],"genre_scores_gemma":[0.98800045,0.00001965077,0.01131634,0.00025009387,0.00036336863,0.000002875576,0.000017077738,0.000011830002,0.000018309354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959108,0.0009461394,0.002529741,0.00022345899,0.00020560223,0.00018425094],"domain_scores_gemma":[0.99017406,0.006617336,0.001934646,0.00013911801,0.0009871233,0.00014770176],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007150675,0.00013476907,0.0015537972,0.00009888624,0.000033771525,0.000001734995,0.000046909074,0.00017793849,0.0000047194567],"category_scores_gemma":[0.022881966,0.00007825405,0.00032995158,0.00009592912,0.0002479778,0.000034116874,0.000016265707,0.00025517025,5.2995455e-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":[0.007350376,0.002922634,0.97011673,0.00037243616,0.0002925241,0.0000018930464,0.000021948043,0.005454069,0.0015719783,0.00010712144,0.00049718446,0.011291083],"study_design_scores_gemma":[0.010473108,0.026535649,0.9511038,0.00027990664,0.00019354961,0.0000053794365,0.000010918249,0.01057405,0.000026263797,0.0005744646,0.00015244527,0.000070486414],"about_ca_topic_score_codex":0.000010980855,"about_ca_topic_score_gemma":0.0000018071815,"teacher_disagreement_score":0.023613015,"about_ca_system_score_codex":0.000027348886,"about_ca_system_score_gemma":0.00008825336,"threshold_uncertainty_score":0.9853487},"labels":[],"label_agreement":null},{"id":"W4235092737","doi":"10.1016/j.jclinepi.2010.03.004","title":"CONSORT 2010 Explanation and Elaboration: updated guidelines for reporting parallel group randomised trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1865,"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 Medical Centre; Health Sciences Centre; Ottawa Hospital","funders":"University of California, Irvine; Institut National de la Santé et de la Recherche Médicale; University of Oxford; Ottawa Hospital Research Institute; McMaster University; Johns Hopkins University; Canadian Institutes of Health Research; National Institute for Health and Care Research; Johns Hopkins Bloomberg School of Public Health; University of Pennsylvania","keywords":"Consolidated Standards of Reporting Trials; Checklist; Critical appraisal; Randomized controlled trial; Medicine; Systematic review; Psychological intervention; Statement (logic); MEDLINE; Family medicine; Alternative medicine; Psychology; Nursing; Surgery; Pathology","score_opus":0.9680071537346534,"score_gpt":0.7344937650894412,"score_spread":0.2335133886452122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235092737","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":[0.32750055,0.0010846186,0.6051493,0.05770746,0.0067880186,0.0013813431,0.000014422765,0.0000046447085,0.00036959694],"genre_scores_gemma":[0.1997795,0.00083670154,0.78084683,0.01012318,0.0057598106,0.00006234208,0.000039459832,0.000021258295,0.0025309501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.50535023,0.14869837,0.3409666,0.0014795673,0.0029589355,0.00054627925],"domain_scores_gemma":[0.036915876,0.6047213,0.3405848,0.0021020693,0.015059107,0.0006168067],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9149399,0.00022659611,0.017925553,0.00026847713,0.00011518054,0.00014312897,0.0007297259,0.00044600287,0.0018919932],"category_scores_gemma":[0.9895487,0.000095277144,0.004461514,0.0003087136,0.00017533754,0.00028749465,0.00004617402,0.00065051444,0.00004525565],"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":[0.0015294775,0.000068033485,0.1790103,0.00001782906,0.00065694004,0.000009235648,0.000028473885,0.00015580085,0.0002660678,0.008995053,0.7527797,0.05648304],"study_design_scores_gemma":[0.017297253,0.0005049918,0.114081234,0.000053449072,0.0012290468,0.0003536856,0.00022682955,0.035713747,0.00000937548,0.17175993,0.6584963,0.00027411434],"about_ca_topic_score_codex":0.000004028478,"about_ca_topic_score_gemma":0.000034305216,"teacher_disagreement_score":0.46843436,"about_ca_system_score_codex":0.0000052175674,"about_ca_system_score_gemma":0.00020460729,"threshold_uncertainty_score":0.9990204},"labels":[],"label_agreement":null},{"id":"W4236245776","doi":"10.1016/s0895-4356(01)00490-5","title":"Response","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Medicine; Intensive care medicine","score_opus":0.8857859867285293,"score_gpt":0.6332834365515825,"score_spread":0.2525025501769468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236245776","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":[0.46349284,0.0070520034,0.012853543,0.5070102,0.0042133154,0.00017486404,0.00003080829,0.000019618128,0.0051527754],"genre_scores_gemma":[0.78412396,0.002256378,0.027936742,0.17965266,0.0033833697,0.000007454651,0.0000014923276,0.00003600864,0.002601916],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95629746,0.013280081,0.02949721,0.0003806575,0.00007600587,0.00046861786],"domain_scores_gemma":[0.86257607,0.1166049,0.019691596,0.00048193953,0.00014716842,0.00049830956],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.34728488,0.00013879461,0.0040769596,0.00028057507,0.00007235946,0.000010519166,0.00042529104,0.0003883358,0.0025871817],"category_scores_gemma":[0.5317166,0.0001392994,0.00075814925,0.00011869903,0.00020122729,0.00028525107,0.000041600964,0.0007281947,0.0043320237],"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":[0.00030909842,0.00022950476,0.4064758,0.000032250875,0.0001438447,0.0000121038065,0.00023713117,0.00018084109,6.0368245e-7,0.09089011,0.4997408,0.0017478867],"study_design_scores_gemma":[0.001496107,0.0007686099,0.27420527,0.00005995064,0.000008801184,0.00009781255,0.00009650197,0.0049591796,2.9885945e-7,0.0739982,0.6441291,0.00018015497],"about_ca_topic_score_codex":0.000029098957,"about_ca_topic_score_gemma":0.0000043947693,"teacher_disagreement_score":0.3273576,"about_ca_system_score_codex":0.00014242347,"about_ca_system_score_gemma":0.00009074424,"threshold_uncertainty_score":0.9983246},"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":"W4239166533","doi":"10.1016/s0895-4356(05)00270-2","title":"Editorial Board","year":2005,"lang":"es","type":"paratext","venue":"Journal of Clinical Epidemiology","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","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":"","funders":"","keywords":"Medicine; Family medicine","score_opus":0.27863905509576725,"score_gpt":0.4304686504545248,"score_spread":0.15182959535875756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239166533","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":[0.0013006405,0.013482983,0.00040683165,0.0036380861,0.7146834,0.00014653744,0.0006912133,0.0000062878253,0.265644],"genre_scores_gemma":[0.0011698543,0.08418143,0.0022030235,0.0023541448,0.5354994,0.0000037906957,0.000017466144,0.00004865813,0.37452227],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9754389,0.0015162486,0.020652605,0.0011793791,0.00013026413,0.0010826141],"domain_scores_gemma":[0.9503812,0.021142878,0.02657916,0.00073112367,0.0004540058,0.0007116431],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.05856445,0.00063282525,0.012509151,0.00061619363,0.00018905151,0.000083475476,0.0015305021,0.0025827945,0.03904711],"category_scores_gemma":[0.063895874,0.000600669,0.0042466423,0.00019636503,0.0012097802,0.0003767896,0.00044525866,0.0034886403,0.157274],"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":[0.0003769811,0.00029023906,0.030946739,0.000057126515,0.0014108038,0.000007749343,0.000056950263,0.0005438989,4.4926825e-8,0.010477119,0.95197713,0.0038552405],"study_design_scores_gemma":[0.0022115,0.00074253586,0.008556051,0.00014350747,0.00013832416,0.000016623539,0.00008026902,0.00025038523,1.3253793e-7,0.0061012786,0.9812516,0.00050777453],"about_ca_topic_score_codex":0.000116228286,"about_ca_topic_score_gemma":0.000008700066,"teacher_disagreement_score":0.17918402,"about_ca_system_score_codex":0.00024978752,"about_ca_system_score_gemma":0.00045607364,"threshold_uncertainty_score":0.99964446},"labels":[],"label_agreement":null},{"id":"W4240881189","doi":"10.1016/j.jclinepi.2008.09.003","title":"Erratum to: “Evaluation of a diabetes management program in China demonstrated association of improved continuity of care with clinical outcomes”","year":2008,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Centre for Global Health Research; University of Toronto","funders":"","keywords":"China; Association (psychology); Medicine; Continuity of care; Family medicine; MEDLINE; Psychology; Health care; Political science; Law","score_opus":0.21096392838845845,"score_gpt":0.5687240388145585,"score_spread":0.3577601104261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240881189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87544745,0.003795373,0.00023135442,0.019554533,0.05468575,0.00969991,0.00035231258,0.00005773193,0.0361756],"genre_scores_gemma":[0.9124697,0.018494222,0.031993583,0.018221077,0.0047465563,0.00052338943,0.0007533492,0.00022770968,0.012570455],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94625527,0.028338255,0.022539888,0.0006217075,0.0012222859,0.0010226081],"domain_scores_gemma":[0.9317361,0.030596688,0.03214313,0.0006867919,0.0044039786,0.0004332759],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.08254418,0.0004718884,0.010828732,0.0006126106,0.00009555113,0.0000019466584,0.00072885765,0.0033676787,0.00006060332],"category_scores_gemma":[0.08440831,0.00033134042,0.0015875155,0.0005726749,0.00035693854,0.00011398358,0.00025051006,0.0068991613,0.0000043207706],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077880535,0.0006565062,0.7591597,0.0019452609,0.0008598268,0.0000055307205,0.00025691633,0.00001793414,4.54409e-7,0.000063048115,0.21013506,0.026120951],"study_design_scores_gemma":[0.006375802,0.004832679,0.9647713,0.002203805,0.0009945607,9.2915604e-7,0.0003375061,0.00017670449,4.0823693e-7,0.000891882,0.019189795,0.00022465471],"about_ca_topic_score_codex":0.00025434178,"about_ca_topic_score_gemma":0.0020583877,"teacher_disagreement_score":0.20561157,"about_ca_system_score_codex":0.00095660734,"about_ca_system_score_gemma":0.008820966,"threshold_uncertainty_score":0.9999139},"labels":[],"label_agreement":null},{"id":"W4240932521","doi":"10.1016/s0895-4356(01)00415-2","title":"Response","year":2002,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Number needed to treat; Medicine; Aside; Intensive care medicine; Confidence interval; Relative risk; Philosophy; Internal medicine","score_opus":0.8857859867285293,"score_gpt":0.6332834365515825,"score_spread":0.2525025501769468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240932521","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":[0.46349284,0.0070520034,0.012853543,0.5070102,0.0042133154,0.00017486404,0.00003080829,0.000019618128,0.0051527754],"genre_scores_gemma":[0.78412396,0.002256378,0.027936742,0.17965266,0.0033833697,0.000007454651,0.0000014923276,0.00003600864,0.002601916],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95629746,0.013280081,0.02949721,0.0003806575,0.00007600587,0.00046861786],"domain_scores_gemma":[0.86257607,0.1166049,0.019691596,0.00048193953,0.00014716842,0.00049830956],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.34728488,0.00013879461,0.0040769596,0.00028057507,0.00007235946,0.000010519166,0.00042529104,0.0003883358,0.0025871817],"category_scores_gemma":[0.5317166,0.0001392994,0.00075814925,0.00011869903,0.00020122729,0.00028525107,0.000041600964,0.0007281947,0.0043320237],"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":[0.00030909842,0.00022950476,0.4064758,0.000032250875,0.0001438447,0.0000121038065,0.00023713117,0.00018084109,6.0368245e-7,0.09089011,0.4997408,0.0017478867],"study_design_scores_gemma":[0.001496107,0.0007686099,0.27420527,0.00005995064,0.000008801184,0.00009781255,0.00009650197,0.0049591796,2.9885945e-7,0.0739982,0.6441291,0.00018015497],"about_ca_topic_score_codex":0.000029098957,"about_ca_topic_score_gemma":0.0000043947693,"teacher_disagreement_score":0.3273576,"about_ca_system_score_codex":0.00014242347,"about_ca_system_score_gemma":0.00009074424,"threshold_uncertainty_score":0.9983246},"labels":[],"label_agreement":null},{"id":"W4242434986","doi":"10.1016/s0895-4356(99)00209-7","title":"Response","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychological Testing and Assessment","field":"Psychology","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 Calgary","funders":"","keywords":"Medicine","score_opus":0.5670313776135334,"score_gpt":0.6389338591645439,"score_spread":0.07190248155101053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242434986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9212545,0.0005044966,0.0010012002,0.020699741,0.0028402938,0.000050177023,0.0000020415132,0.000029528159,0.05361801],"genre_scores_gemma":[0.96315885,0.00020736322,0.00900957,0.01857094,0.0015119396,0.0000030155513,5.524581e-7,0.000013549982,0.0075242105],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9784594,0.016352648,0.004337209,0.00028920485,0.00013351483,0.0004280065],"domain_scores_gemma":[0.93216234,0.06545364,0.0015652126,0.0003569976,0.00009783774,0.00036395455],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.054715574,0.00013789226,0.0016676231,0.000068852496,0.000042585965,0.000004142374,0.00042581643,0.00040498818,0.014821226],"category_scores_gemma":[0.047015764,0.00009012027,0.00071208517,0.00013025336,0.0003004989,0.00004304852,0.000018795616,0.001183091,0.00121488],"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":[0.008572768,0.00092826976,0.22326793,0.0000017214663,0.00020323666,0.00040753564,0.00006965419,0.00006832411,0.000018191915,0.0055982796,0.15687966,0.6039844],"study_design_scores_gemma":[0.0012424173,0.0021299187,0.6775518,0.000025602976,0.000020374535,0.00043375476,0.000027110627,0.00001678009,4.997886e-7,0.012563235,0.30590817,0.0000803389],"about_ca_topic_score_codex":0.000006598318,"about_ca_topic_score_gemma":2.2415774e-7,"teacher_disagreement_score":0.60390407,"about_ca_system_score_codex":0.00001530021,"about_ca_system_score_gemma":0.00007091834,"threshold_uncertainty_score":0.9995628},"labels":[],"label_agreement":null},{"id":"W4244528374","doi":"10.1016/j.jclinepi.2017.12.025","title":"Controversy and debate on dengue vaccine series—paper 3: final response to review of a licensed dengue vaccine: inappropriate subgroup analyses and selective reporting may cause harm in mass vaccination programs","year":2018,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mosquito-borne diseases and control","field":"Medicine","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":"McMaster University","funders":"","keywords":"Dengue vaccine; Dengue fever; Medicine; Vaccination; Scopus; Harm; Subgroup analysis; Family medicine; Dengue virus; Virology; Political science; MEDLINE; Internal medicine; Law; Meta-analysis","score_opus":0.31516489331855635,"score_gpt":0.5536772140958426,"score_spread":0.23851232077728624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244528374","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":[0.025603404,0.96569985,0.000184824,0.005648685,0.00035229803,0.002452188,0.000019328887,0.000015118685,0.00002430094],"genre_scores_gemma":[0.006743956,0.9865671,0.0017253173,0.0037562207,0.0009161554,0.000095995434,0.00003260426,0.000063042244,0.00009963657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9741436,0.009732676,0.014178984,0.0009342659,0.0003808734,0.0006296005],"domain_scores_gemma":[0.95925546,0.018597843,0.019210303,0.0006724979,0.0014491843,0.000814696],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04117937,0.00067540084,0.012933724,0.00057968026,0.00006193876,0.000017610162,0.00026199457,0.00080703606,0.00007196256],"category_scores_gemma":[0.25174442,0.00044331173,0.0015479176,0.00068779616,0.00007340885,0.00016798404,0.00012184031,0.0018225536,0.000004176634],"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":[0.03292502,0.0009953389,0.04884368,0.056134515,0.00378245,0.0018416318,0.00008055717,0.0000042708616,0.000033116776,0.00013365032,0.0041291886,0.8510966],"study_design_scores_gemma":[0.017348059,0.020474987,0.35152742,0.21799697,0.0195311,0.0049508843,0.00010673767,0.00016376316,0.0000060989473,0.0004898234,0.36632326,0.0010808759],"about_ca_topic_score_codex":0.00006240007,"about_ca_topic_score_gemma":0.00007035433,"teacher_disagreement_score":0.8500157,"about_ca_system_score_codex":0.0001912764,"about_ca_system_score_gemma":0.0010252981,"threshold_uncertainty_score":0.9998019},"labels":[],"label_agreement":null},{"id":"W4256177974","doi":"10.1016/s0895-4356(03)00291-9","title":"Dialogue on the nature of patient satisfaction","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Assertion; Perspective (graphical); Patient satisfaction; Scopus; Psychological intervention; Psychology; Health care; Consumer satisfaction; MEDLINE; Medicine; Epistemology; Social psychology; Nursing; Computer science; Philosophy; Political science; Marketing; Artificial intelligence","score_opus":0.35507779897967495,"score_gpt":0.5856502980871218,"score_spread":0.23057249910744682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256177974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9450156,0.0002174104,0.00044641388,0.044068377,0.009086415,0.0003656849,0.00001645746,0.0000110994115,0.0007725285],"genre_scores_gemma":[0.97868437,0.00054647104,0.0011045116,0.01853868,0.0010832823,0.000012829664,0.0000018753764,0.000012946709,0.000015017392],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9805184,0.012272114,0.006340792,0.00019025312,0.0003082696,0.00037015206],"domain_scores_gemma":[0.9158047,0.07557899,0.0074488414,0.00035537017,0.0005828662,0.00022926206],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016139816,0.00013884711,0.0014821714,0.000115677314,0.000255558,6.7877517e-7,0.00018687127,0.001019742,0.00025846943],"category_scores_gemma":[0.12738991,0.000076192664,0.00047338437,0.00015081059,0.00022475072,0.00007616172,0.00005228874,0.00534949,0.00009830514],"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":[0.00042745587,0.000046540223,0.9362437,0.000046391295,0.000055222525,0.0000039184943,0.00028009657,0.000708926,0.000005693619,0.048634294,0.0057281777,0.007819588],"study_design_scores_gemma":[0.00088294386,0.001487283,0.9207365,0.00038100695,0.000020268011,0.000009201888,0.00037066385,0.000008427648,0.00001054497,0.071201384,0.0048354333,0.000056367284],"about_ca_topic_score_codex":0.00031944536,"about_ca_topic_score_gemma":0.00016949997,"teacher_disagreement_score":0.11125008,"about_ca_system_score_codex":0.00018007177,"about_ca_system_score_gemma":0.00067081535,"threshold_uncertainty_score":0.9969452},"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":"W4281260399","doi":"10.1016/j.jclinepi.2022.05.005","title":"A systematic survey of methods guidance suggests areas for improvement regarding access, development, and transparency","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University; Impact","funders":"Universität Basel; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Transparency (behavior); Presentation (obstetrics); MEDLINE; Medicine; Subject (documents); Medical education; Computer science; World Wide Web; Political science; Surgery","score_opus":0.9611316603373287,"score_gpt":0.825002751839484,"score_spread":0.13612890849784465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281260399","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":[0.00013160928,0.92576617,0.06458879,0.0010621025,0.0036228134,0.004493896,0.00023066394,0.000012221356,0.00009174146],"genre_scores_gemma":[0.000020897427,0.93247193,0.062884964,0.003352613,0.00033672783,0.0007676625,0.00002344363,0.000041292544,0.00010046055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.82759106,0.12751709,0.04253968,0.00073207397,0.00046856786,0.0011515252],"domain_scores_gemma":[0.431089,0.52520275,0.041646484,0.0005399076,0.0008898929,0.00063193735],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39833194,0.00040501019,0.01457935,0.00044380638,0.00045608848,0.0000070816022,0.0013273417,0.00067861786,0.0001940213],"category_scores_gemma":[0.566378,0.00027343896,0.0009353962,0.00057297753,0.00021961838,0.0001835991,0.00035799947,0.0022815142,0.0000037286075],"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":[0.000087479646,0.000053549356,0.013184985,0.42947334,0.0004958692,0.000002299469,0.00039354683,0.0000012384712,5.9093246e-8,0.00039668454,0.0051676095,0.55074334],"study_design_scores_gemma":[0.0011202055,0.0005729516,0.009689059,0.05609468,0.0005741606,0.000024346991,0.0001128724,0.000020746586,1.02618024e-7,0.0005081956,0.93104446,0.0002382046],"about_ca_topic_score_codex":0.00017132441,"about_ca_topic_score_gemma":0.0002040001,"teacher_disagreement_score":0.92587686,"about_ca_system_score_codex":0.0003762832,"about_ca_system_score_gemma":0.00939765,"threshold_uncertainty_score":0.9999718},"labels":[],"label_agreement":null},{"id":"W4281657659","doi":"10.1016/j.jclinepi.2022.05.012","title":"Differentiating between mapping reviews and scoping reviews in the evidence synthesis ecosystem","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":91,"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; Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Systematic review; Grey literature; Data extraction; Context (archaeology); Scope (computer science); Data science; Inclusion (mineral); Management science; MEDLINE; Medicine; Knowledge management; Computer science; Psychology; Political science; Geography; Engineering","score_opus":0.9541313891114885,"score_gpt":0.7807484447028614,"score_spread":0.17338294440862712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281657659","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":[0.8302435,0.012312284,0.0061040726,0.14632201,0.0019943463,0.0028036218,0.000015439744,0.000009989549,0.00019468162],"genre_scores_gemma":[0.86066705,0.032705527,0.0074326075,0.09632604,0.002304155,0.000515221,7.563694e-7,0.000015403097,0.0000332502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.77096295,0.20898984,0.018434701,0.0003851988,0.00040166292,0.0008256092],"domain_scores_gemma":[0.24500443,0.73279387,0.020913558,0.0006473452,0.00017632394,0.0004644551],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4063342,0.0001405184,0.0031495916,0.00019621741,0.0008262058,0.0000057505463,0.00075248687,0.000124738,0.00034820073],"category_scores_gemma":[0.5507695,0.00008335762,0.00029366644,0.00044552833,0.000088214336,0.00019689678,0.00033356034,0.002654349,0.00003780478],"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":[0.000014374433,0.000010534722,0.95850956,0.00097385683,0.0000073284227,0.0000031604595,0.0022442406,0.000003866505,0.0000030343024,0.00018685812,0.007910175,0.030133022],"study_design_scores_gemma":[0.00046650626,0.0002433844,0.78397864,0.010467752,0.000044565775,0.000029776731,0.0024758892,0.00015192649,1.5774685e-7,0.0011136263,0.20091344,0.0001143184],"about_ca_topic_score_codex":0.00006122004,"about_ca_topic_score_gemma":0.00011083482,"teacher_disagreement_score":0.52595854,"about_ca_system_score_codex":0.00015813441,"about_ca_system_score_gemma":0.00056739716,"threshold_uncertainty_score":0.99964654},"labels":[],"label_agreement":null},{"id":"W4281701339","doi":"10.1016/j.jclinepi.2022.05.022","title":"Searching two or more databases decreased the risk of missing relevant studies: a metaresearch study","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":143,"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":"Recall; Medicine; MEDLINE; Certainty; Systematic review; Database; Information retrieval; Computer science; Psychology; Mathematics","score_opus":0.975306084094992,"score_gpt":0.7712787027413162,"score_spread":0.20402738135367582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281701339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591715,0.0074202544,0.015714483,0.01586704,0.00088465406,0.00081677886,0.00003991345,0.0000019540082,0.000083455336],"genre_scores_gemma":[0.9622655,0.000992765,0.033560775,0.001959569,0.00051142677,0.000026506967,0.0000017261507,0.00001607829,0.0006656355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.29871798,0.6247771,0.06592448,0.0011640317,0.00877225,0.00064416387],"domain_scores_gemma":[0.047616385,0.8892167,0.054936375,0.0044572204,0.0032448426,0.0005284523],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8816891,0.00026178028,0.01505598,0.00048413608,0.00060917495,0.000064987784,0.003994138,0.000043806827,0.004328054],"category_scores_gemma":[0.9527965,0.00008349068,0.0051057055,0.0014556623,0.0005639506,0.00017049674,0.001267086,0.002301612,0.000045843517],"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":[0.000994539,0.0010124798,0.83613515,0.000046197663,0.005924657,0.00025614316,0.0016751139,0.007478031,0.0000064108176,0.0007397435,0.054198932,0.091532625],"study_design_scores_gemma":[0.005712038,0.0075794663,0.497737,0.000271132,0.006648273,0.0009579665,0.13218476,0.078655295,0.000004507007,0.096547954,0.17320883,0.0004927857],"about_ca_topic_score_codex":0.00020112454,"about_ca_topic_score_gemma":0.00012670615,"teacher_disagreement_score":0.33839813,"about_ca_system_score_codex":0.000046647958,"about_ca_system_score_gemma":0.00069439044,"threshold_uncertainty_score":0.9999486},"labels":[],"label_agreement":null},{"id":"W4281713379","doi":"10.1016/j.jclinepi.2022.05.014","title":"A meta-research study of randomized controlled trials found infrequent and delayed availability of protocols","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Impact","funders":"Magyar Tudományos Akadémia; Hungarian Scientific Research Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Protocol (science); Randomized controlled trial; Medicine; Odds ratio; Confidence interval; Clinical trial; Sample size determination; MEDLINE; Alternative medicine; Internal medicine; Pathology; Statistics","score_opus":0.9794468064786996,"score_gpt":0.7624940667660218,"score_spread":0.2169527397126778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281713379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93809307,0.003935625,0.0046059065,0.0031599377,0.00046416145,0.0493011,0.000018496701,0.0000010691226,0.00042063664],"genre_scores_gemma":[0.9881004,0.000113502836,0.004260779,0.00032367045,0.00016721131,0.0064603025,4.390375e-7,0.0000079669635,0.00056571217],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.01179205,0.8055286,0.17469788,0.0007707183,0.0068891817,0.00032161537],"domain_scores_gemma":[0.0070711426,0.8408692,0.14304149,0.0023413023,0.006353833,0.0003230311],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9869179,0.00029588593,0.12462799,0.0008446788,0.00014333977,0.00005651861,0.0022294072,0.0001737315,0.013166388],"category_scores_gemma":[0.98300356,0.00010161886,0.026446275,0.000949686,0.00083704805,0.000118636584,0.0005223411,0.0013760398,0.000014641753],"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":[0.48145473,0.008285694,0.312607,0.00021728151,0.14305592,0.000034543373,0.0017629466,0.0028932402,0.00006540702,0.009096776,0.02986609,0.010660409],"study_design_scores_gemma":[0.5722854,0.015310945,0.024122862,0.00005965385,0.037904024,0.00007874099,0.0052727982,0.009963871,0.0000035329113,0.32365853,0.011077689,0.00026192237],"about_ca_topic_score_codex":0.00007322927,"about_ca_topic_score_gemma":0.000021276224,"teacher_disagreement_score":0.31456175,"about_ca_system_score_codex":0.000031681917,"about_ca_system_score_gemma":0.0005512125,"threshold_uncertainty_score":0.9877357},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4281782972","doi":"10.1016/j.jclinepi.2022.05.009","title":"RETRACTED: Part II: a step-by-step guide to latent class analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":21,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Latent class model; Identification (biology); Class (philosophy); Homogeneous; Latent variable; Computer science; Two step; Population; Econometrics; Statistics; Data mining; Risk analysis (engineering); Data science; Medicine; Environmental health; Mathematics; Machine learning; Artificial intelligence; Applied mathematics","score_opus":0.1789095589051598,"score_gpt":0.5010186250255991,"score_spread":0.3221090661204393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281782972","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":[0.098483875,0.00073106465,0.6588168,0.2352303,0.005626628,0.00024046474,0.000022199607,0.00008355856,0.0007651085],"genre_scores_gemma":[0.46666372,0.0004319521,0.4261127,0.10077372,0.0024141346,0.00003585498,0.000019527179,0.00004295758,0.0035054067],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9749881,0.015862253,0.007002228,0.0007003085,0.00073376787,0.00071334175],"domain_scores_gemma":[0.9687056,0.023960907,0.004804917,0.001103677,0.0004786686,0.00094625424],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05815427,0.00022130509,0.0027780738,0.00044905726,0.00036051872,0.000021665212,0.0023699682,0.00031691403,0.00044522266],"category_scores_gemma":[0.057465807,0.00018149405,0.0013096808,0.0014393687,0.00008730705,0.00015989196,0.001339119,0.0039780377,0.00003271194],"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":[0.00011282461,0.00020059771,0.42417055,0.00000864691,0.00044753245,0.00009462508,0.0000463829,0.021461219,0.0000037109742,0.0047108205,0.5240767,0.024666416],"study_design_scores_gemma":[0.00043867994,0.002296854,0.13844597,0.000012670791,0.00011641278,0.000113537266,0.000017114353,0.1009023,5.583361e-7,0.0004419257,0.7570564,0.00015756652],"about_ca_topic_score_codex":0.00025367262,"about_ca_topic_score_gemma":0.000052967574,"teacher_disagreement_score":0.36817986,"about_ca_system_score_codex":0.00018720559,"about_ca_system_score_gemma":0.00041377882,"threshold_uncertainty_score":0.9983198},"labels":[],"label_agreement":null},{"id":"W4281985242","doi":"10.1016/j.jclinepi.2022.05.008","title":"Part I: A friendly introduction to latent class analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":69,"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. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Latent class model; Class (philosophy); Probabilistic logic; Set (abstract data type); Computer science; Population; Data science; Data mining; Risk analysis (engineering); Machine learning; Artificial intelligence; Medicine; Environmental health","score_opus":0.18078557491138483,"score_gpt":0.47009702053056723,"score_spread":0.28931144561918243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281985242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010168134,0.00015428236,0.8813449,0.10422521,0.003892441,0.00005611425,0.0000019138856,0.000014364111,0.00014259979],"genre_scores_gemma":[0.108506314,0.00010844736,0.87132746,0.01591535,0.0037390983,0.000009184339,0.0000015538767,0.000007722649,0.00038487674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860655,0.00953291,0.003335896,0.00044774957,0.00027830538,0.00033961606],"domain_scores_gemma":[0.99009985,0.006671562,0.0020021354,0.0006107591,0.00020717962,0.00040851993],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047802735,0.00011756557,0.0017925197,0.00034702115,0.00012301195,0.00001365312,0.0010035847,0.00011108947,0.00016854872],"category_scores_gemma":[0.01522729,0.00008954722,0.0010512273,0.0010203276,0.00005581651,0.00014402319,0.00043565052,0.0010934898,0.000011491263],"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":[0.0002930726,0.0004450406,0.036106475,0.0000057007705,0.0012401452,0.00009626029,0.00018529748,0.031670947,0.00003443724,0.3293736,0.24266784,0.3578812],"study_design_scores_gemma":[0.0006575536,0.002981948,0.048642818,0.000004724603,0.00036122213,0.00025575198,0.0000149958805,0.05156547,0.000009443474,0.14292477,0.7523509,0.00023039451],"about_ca_topic_score_codex":0.000008368337,"about_ca_topic_score_gemma":0.000003593747,"teacher_disagreement_score":0.5096831,"about_ca_system_score_codex":0.000056110297,"about_ca_system_score_gemma":0.0001482636,"threshold_uncertainty_score":0.99306786},"labels":[],"label_agreement":null},{"id":"W4282835525","doi":"10.1016/j.jclinepi.2022.06.003","title":"An adapted ‘Ottawa’ method allowed assessing the need to update topic areas within clinical practice guidelines","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":4,"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":"Guideline; Medicine; Process (computing); Strengths and weaknesses; Computer science; Medical physics; Data mining; Data science; Psychology; Pathology","score_opus":0.6862592081129482,"score_gpt":0.7086061955636783,"score_spread":0.02234698745073016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282835525","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":[0.20343634,0.000316422,0.19081952,0.5977111,0.0066658305,0.0006749069,0.000010804296,0.000049721893,0.00031537891],"genre_scores_gemma":[0.12931937,0.0002312897,0.570563,0.2946136,0.0050828313,0.000019032008,0.000031910215,0.000046593188,0.00009238872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9105027,0.05531133,0.031024009,0.0009881173,0.00139618,0.0007776726],"domain_scores_gemma":[0.50113857,0.45174563,0.03256397,0.0028658332,0.009016825,0.0026691542],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29754376,0.0003494846,0.0036771495,0.00022529058,0.0003695677,0.000046221718,0.0009604516,0.00039901663,0.0007495475],"category_scores_gemma":[0.80147845,0.00022854985,0.0013330709,0.0006055939,0.00024260215,0.000705409,0.0004343616,0.0049490673,0.00004131173],"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":[0.008751965,0.003154677,0.33503807,0.000031380525,0.0017555677,0.0007701068,0.00022193065,0.015729887,0.0001790707,0.0063744322,0.253047,0.37494594],"study_design_scores_gemma":[0.0063286545,0.007884755,0.22730435,0.00007502497,0.0018202536,0.0030721468,0.0050996244,0.027789837,0.0000061318297,0.006072156,0.7142294,0.00031763248],"about_ca_topic_score_codex":0.0002089997,"about_ca_topic_score_gemma":0.000050811308,"teacher_disagreement_score":0.5039347,"about_ca_system_score_codex":0.00014652118,"about_ca_system_score_gemma":0.0019319737,"threshold_uncertainty_score":0.9973466},"labels":[],"label_agreement":null},{"id":"W4282836465","doi":"10.1016/j.jclinepi.2022.06.004","title":"Evidence to decision frameworks enabled structured and explicit development of healthcare recommendations","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact; University of Saskatchewan","funders":"Norwegian Institute of Public Health","keywords":"Grading (engineering); Guideline; Computer science; Health care; Evidence-based medicine; Multiple-criteria decision analysis; MEDLINE; Process (computing); Set (abstract data type); Knowledge management; Process management; Management science; Medicine; Operations research; Business; Political science","score_opus":0.8428691520253149,"score_gpt":0.7058200307335881,"score_spread":0.13704912129172675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282836465","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":[0.00069633493,0.9421798,0.025723958,0.02783673,0.002430933,0.0010931891,0.000021164049,0.000009289934,0.000008603157],"genre_scores_gemma":[0.000110343884,0.74477834,0.2484454,0.0058858166,0.000666391,0.000026528276,0.000042711985,0.000030378711,0.000014097913],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9654603,0.008418222,0.024561193,0.000615664,0.0005469119,0.00039769337],"domain_scores_gemma":[0.64414096,0.33568937,0.017678302,0.0006988445,0.00083360675,0.00095892005],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05703932,0.0003569822,0.0089972215,0.0004563906,0.00011485131,0.0000073110655,0.0004138382,0.0011744036,0.0010762883],"category_scores_gemma":[0.56019944,0.00025482042,0.0011619407,0.00046624613,0.00008662198,0.00014312308,0.0004446284,0.005135266,0.000009772786],"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":[0.00059589645,0.00011919284,0.001469286,0.0023341198,0.00035174677,0.000016850627,0.000068256486,0.000004586563,1.5485689e-7,0.00011851947,0.0060413927,0.98888],"study_design_scores_gemma":[0.00079663424,0.001746653,0.0028166433,0.020698188,0.0011521162,0.00040416906,0.00013852041,0.000013665337,1.4148861e-7,0.0015500883,0.97051215,0.00017104857],"about_ca_topic_score_codex":0.000026827913,"about_ca_topic_score_gemma":0.00004591589,"teacher_disagreement_score":0.988709,"about_ca_system_score_codex":0.00027008256,"about_ca_system_score_gemma":0.00327326,"threshold_uncertainty_score":0.9999904},"labels":[],"label_agreement":null},{"id":"W4282923783","doi":"10.1016/j.jclinepi.2022.06.001","title":"A framework is proposed for defining, categorizing, and assessing conflicts of interest in health research","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":49,"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","funders":"","keywords":"Psychology; Management science; Medicine; Data science; Computer science; Economics","score_opus":0.9857795221114751,"score_gpt":0.8145086564333223,"score_spread":0.17127086567815286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282923783","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":[0.000989822,0.9840503,0.0001828401,0.010211972,0.0029672605,0.0012732554,0.00013579054,0.000009548878,0.00017924109],"genre_scores_gemma":[0.0012449173,0.98702824,0.0026756274,0.007757122,0.0010634365,0.0000603653,0.000026439317,0.000053754164,0.00009010536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9223254,0.0620277,0.013205481,0.00076376967,0.0002529338,0.0014247439],"domain_scores_gemma":[0.7457377,0.24250744,0.009614126,0.00035138178,0.00045437948,0.0013350105],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16371393,0.00044445472,0.009281513,0.00068260485,0.0003198767,0.000014569703,0.0008835077,0.0035959245,0.0008534072],"category_scores_gemma":[0.13309409,0.00035032706,0.0011867592,0.0005864602,0.0012742835,0.000113903836,0.00039429168,0.025976868,0.0000073377405],"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":[0.0005773781,0.0006365265,0.0056489455,0.022619417,0.00051940663,0.00007569081,0.000354797,0.0000055767637,2.7086242e-7,0.028883649,0.007882417,0.93279594],"study_design_scores_gemma":[0.0013119004,0.002182124,0.00018944065,0.006901225,0.0003077863,0.00020649089,0.00017838758,0.0001549112,0.0000012131545,0.022199126,0.9661487,0.00021869686],"about_ca_topic_score_codex":0.00005831765,"about_ca_topic_score_gemma":0.000016748483,"teacher_disagreement_score":0.95826626,"about_ca_system_score_codex":0.0002991018,"about_ca_system_score_gemma":0.003996946,"threshold_uncertainty_score":0.99989486},"labels":[],"label_agreement":null},{"id":"W4283031928","doi":"10.1016/j.jclinepi.2022.06.005","title":"Analytical frameworks in colorectal cancer guidelines: development of methods for systematic reviews, their application and practical guidance for their use","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Memorial University of Newfoundland; Impact; Cochrane","funders":"European Commission; McMaster University","keywords":"Systematic review; Guideline; MEDLINE; Critical appraisal; Medicine; Management science; Medical physics; Computer science; Alternative medicine; Pathology; Engineering","score_opus":0.9451447007803343,"score_gpt":0.749362478723358,"score_spread":0.19578222205697626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283031928","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":[0.035669364,0.00786795,0.9458218,0.007209753,0.0004686368,0.002932192,0.000020533666,0.0000012490805,0.000008486062],"genre_scores_gemma":[0.045179736,0.0008944753,0.94940734,0.0029145828,0.00025958393,0.0012354999,0.0000037968905,0.000015333211,0.000089675435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.683344,0.1860994,0.12665847,0.001576192,0.0016438271,0.0006781348],"domain_scores_gemma":[0.22538021,0.70557445,0.063056774,0.0015051082,0.0041229334,0.000360536],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73415077,0.0002874701,0.016086482,0.00030707964,0.00012288975,0.00004702746,0.0009846742,0.00035172456,0.00018738247],"category_scores_gemma":[0.87195826,0.00012525874,0.003213292,0.00066563324,0.0001596358,0.00016588558,0.00021682368,0.00092358806,0.0000033840402],"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":[0.0019632753,0.0012310852,0.28345674,0.01183379,0.003236845,0.0000035080839,0.0016479082,0.004372689,0.00018366963,0.03355349,0.13763888,0.5208781],"study_design_scores_gemma":[0.0012065711,0.00072953256,0.02170302,0.0020407825,0.0007177206,0.00012190441,0.0012139083,0.5703371,0.000017603297,0.056869768,0.3447306,0.00031149178],"about_ca_topic_score_codex":0.0000043432574,"about_ca_topic_score_gemma":0.000021510134,"teacher_disagreement_score":0.5659644,"about_ca_system_score_codex":0.00008689739,"about_ca_system_score_gemma":0.00051476696,"threshold_uncertainty_score":0.99852073},"labels":[],"label_agreement":null},{"id":"W4283155200","doi":"10.1016/j.jclinepi.2022.06.008","title":"Reporting of funding and conflicts of interest improved from preprints to peer-reviewed publications of biomedical research","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Preprint; Peer review; Publishing; Quarter (Canadian coin); Conflict of interest; Library science; Medicine; Political science; Computer science; World Wide Web; History; Law","score_opus":0.9024043707080208,"score_gpt":0.70174097354069,"score_spread":0.20066339716733084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283155200","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":[0.93519264,0.00035706663,0.0038998541,0.058988724,0.000874876,0.00017657992,0.00004064913,0.000003075703,0.00046651613],"genre_scores_gemma":[0.99137914,0.00012237538,0.007252084,0.0005415192,0.00024733797,0.000006328981,0.0000040798636,0.0000065451454,0.00044056785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91989654,0.025961397,0.048768215,0.0012082726,0.0034043982,0.00076120184],"domain_scores_gemma":[0.31251824,0.5583232,0.109485626,0.003108008,0.014340497,0.002224437],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4504625,0.000099005265,0.0029954368,0.0007548479,0.000108383065,0.000032125597,0.0027695654,0.00025755673,0.00074865384],"category_scores_gemma":[0.92792016,0.00006749336,0.00043935294,0.0012719367,0.0008354724,0.0003734554,0.0022746758,0.0022627406,0.0000044744975],"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":[0.00037702217,0.0002797347,0.87121207,0.000025054407,0.00012182598,0.000004223521,0.0006397443,0.000040517185,0.0020487849,0.0033897348,0.04734169,0.07451958],"study_design_scores_gemma":[0.00077453244,0.00082440756,0.7532908,0.0001865596,0.000035593886,0.000061803315,0.0016176867,0.0012736646,0.00017892444,0.07559659,0.16606568,0.00009378002],"about_ca_topic_score_codex":0.00038975105,"about_ca_topic_score_gemma":0.000019111783,"teacher_disagreement_score":0.60737824,"about_ca_system_score_codex":0.00003718165,"about_ca_system_score_gemma":0.0005564146,"threshold_uncertainty_score":0.9830608},"labels":[],"label_agreement":null},{"id":"W4283363864","doi":"10.1016/j.jclinepi.2022.06.010","title":"Serious reporting deficiencies exist in minimal important difference studies: current state and suggestions for improvement","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":18,"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; University of Alberta; McMaster University; Humber River Regional Hospital; Impact","funders":"Canadian Institutes of Health Research","keywords":"PsycINFO; Prom; Medicine; MEDLINE; Credibility; Patient-reported outcome; Psychological intervention; Demographics; Meta-analysis; Quality of life (healthcare); Demography; Psychiatry","score_opus":0.5899982771386796,"score_gpt":0.6001967208828066,"score_spread":0.01019844374412704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283363864","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":[0.01778862,0.9774843,0.00012940628,0.00058425585,0.0031780258,0.0007530628,0.000060159386,0.000006167332,0.000016011789],"genre_scores_gemma":[0.0005290139,0.99774665,0.0005334782,0.00036078106,0.0005526746,0.00015023301,0.000019540437,0.000026731861,0.00008087674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9799126,0.0017508157,0.017041015,0.00054499425,0.00026282662,0.00048776207],"domain_scores_gemma":[0.92660254,0.045464363,0.026712298,0.00041753874,0.00038518923,0.00041807524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037348215,0.0003570944,0.009515392,0.00024465672,0.00008614045,0.0000068341255,0.00019326562,0.00023334696,0.000019739906],"category_scores_gemma":[0.16007437,0.00023305655,0.001640224,0.00020578675,0.0003105393,0.000029329556,0.0002046767,0.0022265282,4.1856876e-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":[0.0001823612,0.00018006164,0.013464357,0.009250499,0.00027611828,0.00015013621,0.00017457464,0.0000011149873,1.2730199e-7,0.00008429309,0.00033907522,0.97589725],"study_design_scores_gemma":[0.001034266,0.003649639,0.0074322587,0.00945244,0.0014052566,0.00087993377,0.0005008957,0.00002120614,5.4423985e-8,0.002112544,0.97325283,0.00025865994],"about_ca_topic_score_codex":0.00004683665,"about_ca_topic_score_gemma":0.00033137164,"teacher_disagreement_score":0.9756386,"about_ca_system_score_codex":0.0002932145,"about_ca_system_score_gemma":0.0015606048,"threshold_uncertainty_score":0.9912526},"labels":[],"label_agreement":null},{"id":"W4283574083","doi":"10.1016/j.jclinepi.2022.06.006","title":"Record linkage and big data—enhancing information and improving design","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"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 Manitoba; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Linkage (software); Record linkage; Computer science; Data science; Observational study; Population; Value (mathematics); Data mining; Medicine; Statistics; Mathematics; Environmental health; Biology","score_opus":0.7736697826487204,"score_gpt":0.5786307282052613,"score_spread":0.19503905444345915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283574083","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":[0.09185232,0.0004296252,0.8900619,0.014090845,0.003186614,0.00013783116,0.00004529113,0.000007787535,0.00018776004],"genre_scores_gemma":[0.76932234,0.0032883491,0.18381453,0.04119122,0.0019577518,0.0000074216464,0.000038260332,0.000013521988,0.00036659202],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98240364,0.010045117,0.0064663035,0.00031767928,0.00053497805,0.00023227287],"domain_scores_gemma":[0.8851509,0.10686593,0.006622736,0.00084314914,0.00021986719,0.0002973977],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23586325,0.00008251047,0.0010425587,0.00022060782,0.0001940132,0.00006809966,0.0009193707,0.00008157671,0.0000846136],"category_scores_gemma":[0.27506512,0.000057491492,0.00009379388,0.00018274254,0.0001553712,0.0010564221,0.0018072816,0.0007144938,0.000010241561],"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":[0.00016342779,0.000024857181,0.0122785885,0.000009186863,0.00002416267,0.0000074450377,0.000085793625,0.00015102736,0.0000035732287,0.0011282766,0.025238536,0.9608851],"study_design_scores_gemma":[0.0012192486,0.0014634291,0.077584326,0.000019215047,0.00005764367,0.00013405299,0.0018720573,0.02437746,0.0000018826338,0.10633928,0.7867826,0.00014878633],"about_ca_topic_score_codex":0.000053096956,"about_ca_topic_score_gemma":0.000024820276,"teacher_disagreement_score":0.96073633,"about_ca_system_score_codex":0.000015217795,"about_ca_system_score_gemma":0.00013705356,"threshold_uncertainty_score":0.7868396},"labels":[],"label_agreement":null},{"id":"W4283785113","doi":"10.1016/j.jclinepi.2022.06.021","title":"A systematic review of meta-research studies finds substantial methodological heterogeneity in citation analyses to monitor evidence-based research","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"European Cooperation in Science and Technology; Høgskulen på Vestlandet","keywords":"Citation; Meta-analysis; Systematic review; MEDLINE; Medicine; Data science; Computer science; Library science; Biology; Pathology","score_opus":0.9989271462429568,"score_gpt":0.8661715247069282,"score_spread":0.1327556215360286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283785113","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019670035,0.98797834,0.003572963,0.002837166,0.0009712327,0.0043809996,0.000029998128,0.0000021371084,0.000030487696],"genre_scores_gemma":[0.00011850324,0.97723866,0.0205019,0.00080761476,0.00037509162,0.00076843286,0.000005457457,0.0000291503,0.00015521405],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.029945279,0.8130878,0.13858275,0.0021206732,0.015274835,0.0009886413],"domain_scores_gemma":[0.008276143,0.8882083,0.08278173,0.0055300407,0.014473214,0.0007305452],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9756878,0.0009049241,0.13914058,0.0060673417,0.00024091167,0.00013120183,0.00867019,0.0008852158,0.004679671],"category_scores_gemma":[0.99272203,0.0003501245,0.039765123,0.013257231,0.000948907,0.00027328776,0.0011925182,0.005960235,0.00029097273],"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":[0.00013508885,0.00042263736,0.00049057294,0.8721437,0.019237164,0.0001529183,0.00007766119,0.00025362786,4.2783137e-7,0.00029619547,0.02913216,0.07765788],"study_design_scores_gemma":[0.00031752422,0.0029926384,0.00030382385,0.76899123,0.04652894,0.00012827909,0.00061803777,0.00022754524,6.800986e-7,0.006589652,0.1727798,0.000521874],"about_ca_topic_score_codex":0.00002838659,"about_ca_topic_score_gemma":0.00003424062,"teacher_disagreement_score":0.14364764,"about_ca_system_score_codex":0.00043460893,"about_ca_system_score_gemma":0.0018440409,"threshold_uncertainty_score":0.9998951},"labels":[],"label_agreement":null},{"id":"W4284884107","doi":"10.1016/j.jclinepi.2022.06.018","title":"Influenza vaccination reduced myocardial infarctions in United Kingdom older adults: a prior event rate ratio study","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Influenza Virus Research Studies","field":"Medicine","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":"Department of Health and Social Care; Medical Research Council; Eisai Canada; Eisai; National Institute for Health and Care Research","keywords":"Medicine; Vaccination; Hazard ratio; Influenza vaccine; Confidence interval; Myocardial infarction; Confounding; Internal medicine; Vaccine efficacy; Rate ratio; Immunology; Pediatrics","score_opus":0.34403476331406063,"score_gpt":0.561574754107972,"score_spread":0.21753999079391134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284884107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98869306,0.00039128106,0.00029755986,0.008138532,0.00122619,0.0011598717,0.000008477347,0.000018979208,0.00006602035],"genre_scores_gemma":[0.9880791,0.00023130255,0.0006414128,0.009956852,0.0008730295,0.00012934332,0.000007937499,0.000023383878,0.000057688532],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97740304,0.014851739,0.0062180506,0.00039847297,0.00059151265,0.0005371871],"domain_scores_gemma":[0.9780403,0.017705012,0.0025810488,0.00038928204,0.000961265,0.0003230974],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04310383,0.00021547738,0.0024311005,0.000993819,0.00026133627,0.000007838121,0.000279845,0.00017710193,0.00036353947],"category_scores_gemma":[0.13171269,0.00016983802,0.0006293629,0.0009511154,0.000121185905,0.00015036462,0.0003293848,0.0030658662,0.000017612236],"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":[0.012644888,0.003320491,0.9475522,0.000048644677,0.0009941406,0.00026477076,0.0014333985,0.0081168385,0.000046853227,0.0003220864,0.002986869,0.022268787],"study_design_scores_gemma":[0.016664151,0.0066330894,0.9584536,0.00011915223,0.00016176142,0.0000926588,0.0015251203,0.0023535707,0.000004586577,0.00033237733,0.013529341,0.0001306131],"about_ca_topic_score_codex":0.00023488874,"about_ca_topic_score_gemma":0.000038622755,"teacher_disagreement_score":0.08860885,"about_ca_system_score_codex":0.000413171,"about_ca_system_score_gemma":0.0007543787,"threshold_uncertainty_score":0.9992341},"labels":[],"label_agreement":null},{"id":"W4285806644","doi":"10.1016/j.jclinepi.2022.07.008","title":"Resources supporting trustworthy, rapid and equitable evidence synthesis and guideline development: results from the COVID-19 evidence network to support decision-making (COVID-END)","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; Public Health Ontario; McMaster University; Queen's University; University of Toronto; St. Michael's Hospital; Université de Montréal; Institut National d'Excellence en Santé et en Services Sociaux; Bruyère; University of Ottawa","funders":"Pan American Health Organization","keywords":"Coronavirus disease 2019 (COVID-19); Trustworthiness; Guideline; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Evidence-based medicine; Coronavirus Infections; Evidence-based practice; Medicine; Computer science; Virology; Political science; Internet privacy; Alternative medicine; Pathology; Outbreak; Disease","score_opus":0.5968622315947864,"score_gpt":0.6057942633176717,"score_spread":0.00893203172288537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285806644","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":[0.59284496,0.006386616,0.047031876,0.351349,0.0014414622,0.0007977976,0.000058540703,0.00004028678,0.000049460214],"genre_scores_gemma":[0.675009,0.003058777,0.14443734,0.17514648,0.002240536,0.000027159895,0.000013675048,0.000032761072,0.000034250912],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96321905,0.012310876,0.020875743,0.0012279844,0.001252327,0.0011140227],"domain_scores_gemma":[0.11409204,0.8696829,0.012585679,0.0010081353,0.00075169874,0.0018795516],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24274066,0.00033463174,0.0026779503,0.00017394876,0.00088698656,0.000052340198,0.00070505246,0.00024516886,0.0017136136],"category_scores_gemma":[0.91101235,0.00023231664,0.00040773157,0.00050059956,0.00037686684,0.00044301097,0.001619428,0.0019189655,0.000011720575],"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":[0.014446894,0.00009687394,0.35678923,0.000039040227,0.00026204798,0.00032931773,0.00065790786,0.005437586,0.000013332359,0.00003721195,0.21084984,0.41104072],"study_design_scores_gemma":[0.0035750633,0.0036806725,0.17699203,0.0012432255,0.0010688868,0.0018780504,0.0023200423,0.0032531489,0.0000028721668,0.007367347,0.79820395,0.00041474192],"about_ca_topic_score_codex":0.00040677507,"about_ca_topic_score_gemma":0.00030530008,"teacher_disagreement_score":0.85737205,"about_ca_system_score_codex":0.00027288683,"about_ca_system_score_gemma":0.002625408,"threshold_uncertainty_score":0.999199},"labels":[],"label_agreement":null},{"id":"W4286256688","doi":"10.1016/j.jclinepi.2022.07.007","title":"Methodological guidance for incorporating equity when informing rapid-policy and guideline development","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National d'Excellence en Santé et en Services Sociaux; Health Canada; Ottawa Hospital; Queen's University; University of Toronto; St. Michael's Hospital; Cochrane; Bruyère; University of Ottawa","funders":"National Institute for Health and Care Research","keywords":"Equity (law); Systematic review; Guideline; Medicine; Health equity; MEDLINE; Public health; Public relations; Political science; Nursing","score_opus":0.9788166259061911,"score_gpt":0.7491205238360007,"score_spread":0.22969610207019042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286256688","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":[0.0462236,0.002228944,0.9179908,0.03034917,0.001131441,0.0004977995,0.000009956966,0.0000035888254,0.0015647045],"genre_scores_gemma":[0.051097885,0.00006805193,0.9310952,0.015653592,0.0010645662,0.000031167492,0.0000035317614,0.000008396774,0.0009776462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5609882,0.25996774,0.17063345,0.0017674665,0.0055837478,0.0010594095],"domain_scores_gemma":[0.08216185,0.78911376,0.12114071,0.0024266872,0.0042120283,0.00094497384],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8840165,0.000248274,0.011573689,0.00039517527,0.00036875845,0.00008114587,0.0020473755,0.00018339985,0.0018257817],"category_scores_gemma":[0.9332391,0.000117036965,0.002872723,0.0004965131,0.00020290494,0.00019513082,0.0012806165,0.000816378,0.000025078527],"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":[0.00015083088,0.000068416106,0.0715989,0.00003261716,0.00029640683,0.000008788744,0.00017563548,0.0013668089,0.000012644906,0.021878738,0.12706825,0.77734196],"study_design_scores_gemma":[0.00049840886,0.00048790892,0.014927447,0.000016390573,0.000073913216,0.00014490365,0.00023309182,0.0099774385,0.0000020408825,0.27411094,0.6994154,0.000112129],"about_ca_topic_score_codex":0.000005555772,"about_ca_topic_score_gemma":0.0000056858994,"teacher_disagreement_score":0.77722985,"about_ca_system_score_codex":0.000081213366,"about_ca_system_score_gemma":0.00085097516,"threshold_uncertainty_score":0.9990867},"labels":[],"label_agreement":null},{"id":"W4289527437","doi":"10.1016/j.jclinepi.2022.07.010","title":"Rasch Measurement Theory's contribution to the psychometric properties of a co-created measure of health and wellness for Indigenous children and youth","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","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":"Centre for Advancing Health Outcomes; Spinal Cord Injury BC; University of British Columbia","funders":"","keywords":"Rasch model; Item response theory; Raw score; Logit; Indigenous; Psychology; Measure (data warehouse); Polytomous Rasch model; Psychometrics; Logistic regression; Level of measurement; Classical test theory; Clinical psychology; Statistics; Developmental psychology; Raw data; Mathematics; Computer science; Data mining","score_opus":0.1900782991931579,"score_gpt":0.4498243666053391,"score_spread":0.2597460674121812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289527437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979907,0.011343515,0.00143126,0.005174945,0.00069815613,0.0013154848,0.00004525848,0.00000402851,0.00008036167],"genre_scores_gemma":[0.9919124,0.0070630726,0.000112051865,0.00053892797,0.00033004297,0.000005030166,0.0000048852135,0.0000061755863,0.000027383137],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98079556,0.015365465,0.002755249,0.00019586264,0.00048602902,0.00040183406],"domain_scores_gemma":[0.99248475,0.003601939,0.0027503963,0.00013052799,0.0007777241,0.0002546917],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12267456,0.000092161485,0.0012158103,0.00019681329,0.0021744494,0.000005557973,0.00026330462,0.00012346903,0.000008529541],"category_scores_gemma":[0.0085333465,0.000051689196,0.00016575598,0.00033768118,0.00044192185,0.000045569912,0.0000053530043,0.0003691015,2.1822322e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004584435,0.0013476253,0.3781907,0.00016172213,0.00066010025,2.4969546e-7,0.48531035,0.0000947405,0.000006531721,0.09265419,0.00048326774,0.036506105],"study_design_scores_gemma":[0.006004103,0.013788373,0.8117676,0.00036031578,0.00037366393,0.00006133242,0.046965428,0.00001360655,0.000089585345,0.0241361,0.096047856,0.0003920358],"about_ca_topic_score_codex":0.007876312,"about_ca_topic_score_gemma":0.0063199606,"teacher_disagreement_score":0.4383449,"about_ca_system_score_codex":0.00012886692,"about_ca_system_score_gemma":0.0073446403,"threshold_uncertainty_score":0.9998182},"labels":[],"label_agreement":null},{"id":"W4289779569","doi":"10.1016/j.jclinepi.2022.07.014","title":"GRADE Guidance 34: update on rating imprecision using a minimally contextualized approach","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":258,"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 Agency of Canada; Impact; McMaster University","funders":"Science and Technology Service Network Plan; Sichuan Province Science and Technology Support Program","keywords":"Grading (engineering); Rating system; Rating scale; Computer science; Statistics; Mathematics; Engineering","score_opus":0.9717871712671292,"score_gpt":0.7284582797004966,"score_spread":0.24332889156663262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289779569","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011132552,0.95542735,0.037886053,0.00055275514,0.003229935,0.0010548485,0.000037903195,0.00000426687,0.0016955585],"genre_scores_gemma":[0.000026032676,0.8971241,0.09802836,0.0023063382,0.0015738275,0.000029502524,0.00001718043,0.000055731904,0.0008388898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.31032708,0.49534863,0.18303584,0.002864722,0.0074605863,0.00096313166],"domain_scores_gemma":[0.21023855,0.55740994,0.22430132,0.0055897934,0.0016019795,0.0008583797],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8096501,0.0011143249,0.08095356,0.0011897223,0.00030040366,0.00026234976,0.0071537406,0.0011244928,0.007719748],"category_scores_gemma":[0.8750084,0.0004786321,0.03604538,0.0018044997,0.00033323918,0.00023691032,0.0007620946,0.004386461,0.00066983653],"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":[0.00007606326,0.00024005336,0.00029884762,0.0009793265,0.0013026446,0.00005679644,0.000022044374,0.00023502964,1.0600542e-7,0.0019692364,0.058596488,0.9362234],"study_design_scores_gemma":[0.00053989515,0.0005017705,0.000048738417,0.002508292,0.0024147148,0.00061499927,0.00008347424,0.00539226,1.0698627e-8,0.005177296,0.98235023,0.00036830208],"about_ca_topic_score_codex":0.0000054223187,"about_ca_topic_score_gemma":0.0000014762517,"teacher_disagreement_score":0.9358551,"about_ca_system_score_codex":0.00021126219,"about_ca_system_score_gemma":0.001248576,"threshold_uncertainty_score":0.9997665},"labels":[],"label_agreement":null},{"id":"W4289938702","doi":"10.1016/j.jclinepi.2022.07.015","title":"GRADE guidance 35: update on rating imprecision for assessing contextualized certainty of evidence and making decisions","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":153,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University Health Network; University of Toronto; McMaster University; Impact; Cochrane","funders":"Manchester Biomedical Research Centre; National Institute for Health and Care Research","keywords":"Operationalization; Certainty; Computer science; Psychology; Actuarial science; Management science; Applied psychology; Engineering; Mathematics; Business","score_opus":0.973894413027669,"score_gpt":0.7439502973849873,"score_spread":0.2299441156426817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289938702","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51642644,0.0049889446,0.45787564,0.01805382,0.0018693896,0.00061545515,0.000020829186,0.0000026115222,0.00014688072],"genre_scores_gemma":[0.88798,0.00037211674,0.106383994,0.004837887,0.00024185154,0.000014871713,9.350155e-7,0.000010675821,0.00015767204],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.69656855,0.20798588,0.08775525,0.0016496639,0.00536898,0.00067166664],"domain_scores_gemma":[0.14958061,0.7812628,0.06482368,0.0019038713,0.0021248579,0.00030417126],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.69420475,0.00025279654,0.011195846,0.00040790965,0.00036349546,0.00011914067,0.0018811749,0.0002065889,0.0010402151],"category_scores_gemma":[0.92192703,0.00011347554,0.0040697157,0.00062240387,0.00023257254,0.0002734513,0.00042203497,0.0011324423,0.000013722379],"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":[0.0010572826,0.0002910675,0.23274279,0.000065371256,0.0005372089,0.000025286352,0.00024463603,0.010076068,0.0002835213,0.022566628,0.102624476,0.62948567],"study_design_scores_gemma":[0.0034236975,0.002914465,0.18400212,0.0019824577,0.00082543987,0.00036521206,0.0021803563,0.18465303,0.00001847939,0.41849867,0.20065953,0.0004765455],"about_ca_topic_score_codex":0.000003612283,"about_ca_topic_score_gemma":0.000004203354,"teacher_disagreement_score":0.6290091,"about_ca_system_score_codex":0.000042269152,"about_ca_system_score_gemma":0.0002286305,"threshold_uncertainty_score":0.999873},"labels":[],"label_agreement":null},{"id":"W4292308201","doi":"10.1016/j.jclinepi.2022.08.004","title":"A review found heterogeneous approaches and insufficient reporting in overviews on adverse events","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Montfort Hospital; University of Ottawa; Cochrane; St. Michael's Hospital; University of British Columbia; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Adverse effect; Medicine; Intensive care medicine; Internal medicine","score_opus":0.9813124514698516,"score_gpt":0.7194544555327035,"score_spread":0.2618579959371481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292308201","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002303,0.99528396,0.0002904746,0.00063577277,0.00146163,0.0014027733,0.000009816109,0.000001550622,0.0006837346],"genre_scores_gemma":[0.000024435642,0.99323386,0.0021516192,0.0037716161,0.00037790494,0.00006346715,0.0000083234345,0.000028199689,0.00034058178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30504826,0.38929442,0.29715222,0.0028005003,0.0048936806,0.0008109191],"domain_scores_gemma":[0.103506744,0.3831559,0.5056566,0.006137774,0.00066385657,0.00087914016],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.83669895,0.00077526795,0.07088851,0.0008841438,0.000101138125,0.00003247259,0.002766893,0.00057105557,0.0034443391],"category_scores_gemma":[0.8941568,0.0003340885,0.021962266,0.0014091715,0.0001533983,0.000107985696,0.00063313585,0.0030054923,0.00027274067],"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":[0.000012345643,0.00025127555,0.0034265348,0.009872505,0.0004984062,0.00015642452,0.0000141270075,0.00011405237,4.3446366e-10,0.00018470788,0.009738182,0.97573143],"study_design_scores_gemma":[0.00018445069,0.00042714804,0.00063692016,0.02184603,0.001580104,0.0013572725,0.000020242693,0.000241447,3.9889664e-10,0.002154871,0.97132057,0.00023094725],"about_ca_topic_score_codex":0.000004471672,"about_ca_topic_score_gemma":0.000009851814,"teacher_disagreement_score":0.97550046,"about_ca_system_score_codex":0.00015125136,"about_ca_system_score_gemma":0.0006102499,"threshold_uncertainty_score":0.9999111},"labels":[],"label_agreement":null},{"id":"W4292416422","doi":"10.1016/j.jclinepi.2022.08.007","title":"An analysis of published trials found that current use of pragmatic trial labels is uninformative","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; Centre for Family Medicine; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Medicine; Clinical trial; Randomized controlled trial; Medical physics; Randomization; Research design; Cluster randomised controlled trial; External validity; Family medicine; Statistics; Psychology; Surgery; Pathology; Social psychology","score_opus":0.9832663869338946,"score_gpt":0.7642912462007239,"score_spread":0.2189751407331707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292416422","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064602157,0.9756108,0.014716453,0.00046547517,0.005122683,0.0026373323,0.00060244784,0.0000025182899,0.0001962709],"genre_scores_gemma":[0.00009232202,0.9926807,0.005764877,0.00038169863,0.0006123799,0.00004800772,0.00011951228,0.000023951217,0.00027653304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.12879711,0.5978316,0.26303023,0.0015009219,0.0082335295,0.0006065815],"domain_scores_gemma":[0.042958587,0.5982798,0.34970427,0.0053237034,0.0031217816,0.00061188114],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8900636,0.0009034913,0.16090678,0.0046535134,0.00009833741,0.00031460865,0.006569887,0.00094588276,0.037378967],"category_scores_gemma":[0.9454116,0.00036881032,0.07195411,0.0060580056,0.00051141164,0.001331345,0.00047710098,0.0026496893,0.00007471321],"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":[0.0008937223,0.0006631033,0.0023398178,0.0025110147,0.02760334,0.000004630912,0.00018704454,0.00027828678,7.0721557e-9,0.0014343427,0.046858877,0.91722584],"study_design_scores_gemma":[0.0030457084,0.0012354167,0.00044305716,0.0012797253,0.061534088,0.000016847902,0.00014688967,0.002252999,1.1116541e-8,0.0040948526,0.92570436,0.00024607324],"about_ca_topic_score_codex":0.000021008376,"about_ca_topic_score_gemma":0.000011669132,"teacher_disagreement_score":0.91697973,"about_ca_system_score_codex":0.000113005975,"about_ca_system_score_gemma":0.0019559849,"threshold_uncertainty_score":0.9998764},"labels":[],"label_agreement":null},{"id":"W4293386320","doi":"10.1016/j.jclinepi.2022.08.002","title":"Priority III: top 10 rapid review methodology research priorities identified using a James Lind Alliance Priority Setting Partnership","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University; University of Toronto; Cochrane; Public Health Agency of Canada; Health Canada; St. Michael's Hospital","funders":"University of Galway; Public Health Agency; Health Research Board; National University of Ireland","keywords":"General partnership; Context (archaeology); Systematic review; Alliance; Stakeholder; Prioritization; Management science; Medicine; Public relations; MEDLINE; Political science; Engineering","score_opus":0.9888648252185492,"score_gpt":0.7822001754623731,"score_spread":0.20666464975617616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293386320","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075806376,0.9850931,0.0032252574,0.0030289532,0.0053375186,0.0024707152,0.00003226502,0.00000855611,0.00072783674],"genre_scores_gemma":[0.0000027057438,0.93897533,0.049893904,0.0018840667,0.0039160317,0.00006779316,0.000018383385,0.00006367137,0.0051781214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.083818235,0.7633314,0.13799722,0.0035227286,0.009459248,0.0018711386],"domain_scores_gemma":[0.03599874,0.8007645,0.14514425,0.00808814,0.00867646,0.0013279313],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9474535,0.0013379174,0.08993637,0.001376078,0.000740837,0.0004082129,0.009541409,0.001982385,0.031035937],"category_scores_gemma":[0.9649126,0.0006930964,0.031412415,0.0041142856,0.0013727134,0.0005016883,0.0020931181,0.011619112,0.0008444697],"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":[0.00004821635,0.000105037834,0.0007204959,0.01379442,0.0014065482,0.00011198152,0.000071306626,0.000005686968,4.0781412e-8,0.00071728684,0.18853393,0.79448503],"study_design_scores_gemma":[0.00033116865,0.00038684072,0.00015443026,0.017174829,0.004357243,0.00064107357,0.00019289968,0.00011976713,4.062543e-8,0.011849601,0.964298,0.000494083],"about_ca_topic_score_codex":0.00003666188,"about_ca_topic_score_gemma":0.000013487808,"teacher_disagreement_score":0.79399097,"about_ca_system_score_codex":0.0004069332,"about_ca_system_score_gemma":0.006040969,"threshold_uncertainty_score":0.9999372},"labels":[],"label_agreement":null},{"id":"W4295642653","doi":"10.1016/j.jclinepi.2022.09.004","title":"A descriptive study found low prevalence of presumed predatory publications in a subset of Cochrane reviews","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Horizon Health Network; Kellogg's (Canada); Dalhousie University; University of New Brunswick; Saint Mary's University","funders":"","keywords":"Systematic review; Citation; Medicine; Grey literature; MEDLINE; Cochrane collaboration; Scope (computer science); Meta-analysis; Cochrane Library; Pathology; Computer science; Library science; Biology","score_opus":0.9315100446189076,"score_gpt":0.6867709663344385,"score_spread":0.24473907828446917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295642653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782436,0.012233054,0.0045902343,0.0020551311,0.0007496791,0.0016300255,0.00005752829,0.000001221792,0.00043953714],"genre_scores_gemma":[0.9910501,0.0015937026,0.00521669,0.0004167234,0.000097451455,0.000085529726,0.000001650513,0.0000073641922,0.0015307902],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.36892805,0.47162676,0.1508816,0.0016103183,0.0063454458,0.000607818],"domain_scores_gemma":[0.41863266,0.3824792,0.18457812,0.00759614,0.006050657,0.0006632256],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72456414,0.00022179564,0.015753414,0.00068610173,0.00006226393,0.000021077236,0.0033105572,0.00012240685,0.0071550393],"category_scores_gemma":[0.78858584,0.000110319736,0.003932536,0.0016149296,0.00031625142,0.00025878017,0.00038083698,0.0009886711,0.0000421747],"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":[0.00014606405,0.0014187825,0.9582981,0.00023313345,0.00028515165,0.000004654234,0.0006823555,0.00045591185,0.000010944036,0.0007897752,0.03324804,0.004427086],"study_design_scores_gemma":[0.00093523535,0.001476988,0.9583846,0.00016782219,0.00039618267,0.00003373917,0.0012025195,0.0017248131,8.1818723e-7,0.00926627,0.026316702,0.00009435358],"about_ca_topic_score_codex":0.000021782467,"about_ca_topic_score_gemma":0.000054637792,"teacher_disagreement_score":0.08914756,"about_ca_system_score_codex":0.0000556745,"about_ca_system_score_gemma":0.0004687872,"threshold_uncertainty_score":0.99885875},"labels":[],"label_agreement":null},{"id":"W4295807651","doi":"10.1016/j.jclinepi.2022.09.005","title":"Peering into the dark corners of knowledge synthesis to understand the influence of predatory journals on systematic reviews","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Publishing; Transparency (behavior); Scholarly communication; Globe; Political science; Scopus; Library science; Public relations; Medicine; Computer science; MEDLINE; Law","score_opus":0.9157832329068454,"score_gpt":0.661831148816518,"score_spread":0.25395208409032743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295807651","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9463262,0.02440668,0.009936695,0.0144659495,0.0015296296,0.0019624098,0.000012095996,0.0000016792651,0.0013586566],"genre_scores_gemma":[0.9945451,0.0012643376,0.0013236129,0.0022371544,0.00015672462,0.000036442176,7.6970395e-8,0.000010054353,0.00042650366],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.47472203,0.4172905,0.10106413,0.0008822087,0.0055357097,0.000505421],"domain_scores_gemma":[0.08447555,0.8047599,0.10227193,0.005079667,0.0029524246,0.00046049635],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7938363,0.00026622877,0.015543307,0.0004012112,0.00025019588,0.000048746897,0.004883306,0.00011709731,0.0012007687],"category_scores_gemma":[0.8968685,0.000086095424,0.0053950283,0.0012863736,0.00038495637,0.00011737147,0.00044742154,0.0011350136,0.00011771809],"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":[0.00088058965,0.001104624,0.20287533,0.013190656,0.005935439,0.000031486867,0.01740193,0.18918204,0.00026438804,0.023446996,0.49638173,0.049304795],"study_design_scores_gemma":[0.0014828572,0.0058272146,0.45625624,0.032300066,0.007569067,0.0007940782,0.048526496,0.011885827,0.000043456854,0.13082722,0.30338645,0.0011010407],"about_ca_topic_score_codex":0.000008988727,"about_ca_topic_score_gemma":0.0000127219255,"teacher_disagreement_score":0.39024648,"about_ca_system_score_codex":0.00008029441,"about_ca_system_score_gemma":0.00029912358,"threshold_uncertainty_score":0.9997123},"labels":[],"label_agreement":null},{"id":"W4296661943","doi":"10.1016/j.jclinepi.2022.08.014","title":"A method was developed for correcting the bias in the usual study weights in meta-analyses","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Meta-analysis; Variance (accounting); Statistics; Publication bias; Mathematics; Standard error; Inverse; Econometrics; Medicine; Confidence interval","score_opus":0.9950472414179307,"score_gpt":0.8096768897543006,"score_spread":0.18537035166363003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296661943","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002845117,0.9740856,0.017102886,0.0027899023,0.0018227157,0.0036211368,0.000014724897,0.0000013384201,0.0002771386],"genre_scores_gemma":[0.0001656684,0.95357865,0.039716497,0.003479049,0.0011058875,0.00076876115,0.0000073450888,0.000044269083,0.001133872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.064175196,0.7884097,0.14010334,0.0018043091,0.0047817254,0.00072574185],"domain_scores_gemma":[0.016817028,0.8689221,0.10931991,0.003761188,0.000985956,0.00019382128],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.94624585,0.00087687996,0.0820236,0.0014125523,0.0002695924,0.0002405955,0.009540591,0.0005368629,0.00400394],"category_scores_gemma":[0.92157435,0.00022312661,0.04149644,0.0041019213,0.00016578069,0.00014925505,0.0005273568,0.0045141787,0.00010205853],"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":[0.000034151115,0.00042510492,0.0049675396,0.0003427306,0.011720646,0.000060134123,0.0005865842,0.00017211676,1.0814323e-9,0.00041592267,0.012798889,0.9684762],"study_design_scores_gemma":[0.000372736,0.0004699618,0.0011844368,0.00024955595,0.032050867,0.00039211614,0.0022480744,0.00056614855,2.6497784e-9,0.009529406,0.9527309,0.00020578373],"about_ca_topic_score_codex":0.000068318855,"about_ca_topic_score_gemma":0.00054067676,"teacher_disagreement_score":0.9682704,"about_ca_system_score_codex":0.00010155185,"about_ca_system_score_gemma":0.0012433168,"threshold_uncertainty_score":0.99778247},"labels":[],"label_agreement":null},{"id":"W4297371750","doi":"10.1016/j.jclinepi.2022.09.012","title":"The role of scoping reviews in reducing research waste","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":38,"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; University of Toronto; St. Michael's Hospital; Queen's University","funders":"National Health and Medical Research Council","keywords":"Environmental science; Environmental health; Waste management; Medicine; Environmental planning; Engineering","score_opus":0.9687339321270803,"score_gpt":0.7552197628177003,"score_spread":0.21351416930937994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297371750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7693574,0.17969775,0.0025580588,0.032847855,0.003544613,0.0015609843,0.000004004451,0.0000012557994,0.01042808],"genre_scores_gemma":[0.9759322,0.0115436185,0.008196545,0.001180301,0.0009394347,0.000039340845,4.516095e-7,0.000012529894,0.0021555847],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.10354698,0.7612653,0.12693268,0.0009801305,0.0064941957,0.0007807683],"domain_scores_gemma":[0.072323605,0.8426907,0.07752677,0.0044302596,0.002647478,0.0003811877],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9444634,0.00013097347,0.01163096,0.00048809656,0.00027374117,0.00004607069,0.003473179,0.00009992547,0.0021337408],"category_scores_gemma":[0.89671224,0.000050060073,0.004050709,0.0016153859,0.00031350646,0.00010067252,0.00058071973,0.002087807,0.00012988296],"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":[0.0001643199,0.00017695857,0.4073565,0.0000701808,0.00017482089,0.000015011969,0.0003758244,0.004337969,0.00006685745,0.0129953325,0.10737201,0.4668942],"study_design_scores_gemma":[0.000411363,0.00073372934,0.022086374,0.00072162744,0.000068996116,0.00008637507,0.0035937342,0.010734649,0.0000074281284,0.22889864,0.7325546,0.00010245929],"about_ca_topic_score_codex":0.000023124901,"about_ca_topic_score_gemma":0.000027591352,"teacher_disagreement_score":0.6251826,"about_ca_system_score_codex":0.000046172812,"about_ca_system_score_gemma":0.00037139203,"threshold_uncertainty_score":0.99877846},"labels":[],"label_agreement":null},{"id":"W4297535932","doi":"10.1016/j.jclinepi.2022.09.013","title":"Commentary: collaborative systematic review may produce and share high-quality, comparative evidence more efficiently","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Health and Medical Research Council; Medical Research Council; Canadian Institutes of Health Research","keywords":"Systematic review; Comparative effectiveness research; Evidence-based medicine; Quality (philosophy); Resource (disambiguation); Computer science; Evidence-based practice; Management science; Process management; Medicine; Knowledge management; Risk analysis (engineering); MEDLINE; Alternative medicine; Business; Political science; Engineering","score_opus":0.9651575200740439,"score_gpt":0.7501909781092431,"score_spread":0.2149665419648008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297535932","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025212501,0.97391057,0.00036886602,0.017959654,0.0016431957,0.0057480587,0.00022372126,0.000004233149,0.00011647249],"genre_scores_gemma":[0.000025040881,0.9810103,0.0027968034,0.01452172,0.00052470755,0.00025563434,0.000045934485,0.000030965548,0.0007888836],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.2802778,0.5636998,0.14633967,0.0024909219,0.006539166,0.00065265346],"domain_scores_gemma":[0.058484875,0.7012739,0.22853656,0.0062788557,0.0044882754,0.00093751703],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7888628,0.001215171,0.1274468,0.000689935,0.00029394677,0.00025700804,0.0062483004,0.0005491672,0.0065565547],"category_scores_gemma":[0.8705448,0.0005078866,0.013876059,0.003102789,0.0006901569,0.00038440505,0.0011975291,0.0032301375,0.0005696472],"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":[0.000026283129,0.00020068111,0.000592056,0.53094035,0.0031773355,0.000051382947,0.00014329291,0.000010928759,5.591653e-9,0.0009816583,0.42913,0.034746043],"study_design_scores_gemma":[0.00016540634,0.0004504551,0.0001361439,0.2951052,0.010124652,0.00026600517,0.00029385163,0.000026294436,6.0689502e-9,0.0006385322,0.69246227,0.00033116536],"about_ca_topic_score_codex":0.0000106846255,"about_ca_topic_score_gemma":0.000007942054,"teacher_disagreement_score":0.2633323,"about_ca_system_score_codex":0.00021133649,"about_ca_system_score_gemma":0.0010554813,"threshold_uncertainty_score":0.99973726},"labels":[],"label_agreement":null},{"id":"W4298625460","doi":"10.1016/j.jclinepi.2022.09.016","title":"Methodological quality in guidelines for enhanced recovery after surgery was suboptimal","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Enhanced Recovery After Surgery","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Intraclass correlation; Medicine; Guideline; Concordance; Confidence interval; MEDLINE; CLARITY; Family medicine; Internal medicine; Psychometrics; Clinical psychology; Pathology","score_opus":0.8837089283562627,"score_gpt":0.6733629387302343,"score_spread":0.21034598962602835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298625460","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":[0.001752361,0.9678217,0.017313143,0.002422463,0.009498381,0.0009730737,0.00007376818,0.00002692158,0.00011815435],"genre_scores_gemma":[0.000016219812,0.90256155,0.08533673,0.006716906,0.004472494,0.00032419985,0.000083961335,0.00009405303,0.00039389232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92224365,0.043319296,0.031600475,0.0011976587,0.0005365098,0.0011024184],"domain_scores_gemma":[0.37267578,0.6068262,0.017848384,0.0010290783,0.00090893224,0.0007116304],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.22584493,0.0008209646,0.033746205,0.00095107115,0.000049054393,0.000009395874,0.000532594,0.0023241022,0.0011879992],"category_scores_gemma":[0.72367054,0.0005454979,0.014857484,0.000562675,0.00035599078,0.00017599828,0.00028858255,0.005004832,0.000020834603],"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":[0.00731821,0.00046743258,0.0033235857,0.008901969,0.0008796717,0.00042554628,0.0000048918405,0.000027513459,6.1999094e-7,0.00002518449,0.014478618,0.96414673],"study_design_scores_gemma":[0.0009769275,0.0015758598,0.003321012,0.009856853,0.0011764962,0.0008098871,0.000011487791,0.00000762093,0.0000012493591,0.0021577938,0.9796053,0.00049947225],"about_ca_topic_score_codex":0.0000126446175,"about_ca_topic_score_gemma":0.000010824831,"teacher_disagreement_score":0.9651267,"about_ca_system_score_codex":0.0003862998,"about_ca_system_score_gemma":0.0029475242,"threshold_uncertainty_score":0.99972504},"labels":[],"label_agreement":null},{"id":"W4299804977","doi":"10.1016/j.jclinepi.2022.09.014","title":"Case studies to explore the optimal use of randomized and nonrandomized studies in evidence syntheses that use GRADE","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":9,"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; Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Randomized controlled trial; Grading (engineering); Medicine; Psychological intervention; Systematic review; Evidence-based medicine; MEDLINE; Certainty; Health care; Evidence-based practice; Alternative medicine; Management science; Nursing; Surgery","score_opus":0.983676731211259,"score_gpt":0.7987945898525314,"score_spread":0.1848821413587276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299804977","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90303594,0.0021339445,0.0006137224,0.0909993,0.0016131721,0.0015784042,0.000017100396,0.000006457133,0.0000019412357],"genre_scores_gemma":[0.93636245,0.015695253,0.008314092,0.03885725,0.00026545546,0.00041990753,1.3726925e-7,0.000012207213,0.0000732378],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.8431686,0.14307474,0.012024253,0.00040353657,0.000555553,0.00077331084],"domain_scores_gemma":[0.097882785,0.893792,0.0068921326,0.0003703304,0.00071481924,0.0003479665],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22533162,0.00019538058,0.005839262,0.00032086606,0.0006623085,0.000005748766,0.00037987687,0.000111963374,0.0000788607],"category_scores_gemma":[0.88908213,0.000104669,0.00047957044,0.00032370823,0.0014609064,0.00045859622,0.0007753839,0.0017398791,0.0000033850956],"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":[0.24541822,0.00029209317,0.52810943,0.00064506585,0.001569381,0.0013976813,0.15956444,0.005199678,0.000017741215,0.0014753914,0.05365339,0.002657483],"study_design_scores_gemma":[0.43897346,0.005297089,0.058622938,0.00599025,0.0013604334,0.004682403,0.44364026,0.0027056974,0.000013985849,0.009360409,0.02850306,0.0008500197],"about_ca_topic_score_codex":0.00037493813,"about_ca_topic_score_gemma":0.00021644404,"teacher_disagreement_score":0.7507172,"about_ca_system_score_codex":0.00015137187,"about_ca_system_score_gemma":0.0006374587,"threshold_uncertainty_score":0.79768413},"labels":[],"label_agreement":null},{"id":"W4302362334","doi":"10.1016/j.jclinepi.2022.10.008","title":"Evidence, values, and masks for control of COVID-19: 2 years later","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare cost, quality, practices","field":"Health Professions","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":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Betacoronavirus; Coronavirus Infections; Medicine; MEDLINE; Virology; Internal medicine; Outbreak; Biology","score_opus":0.9038544843539869,"score_gpt":0.7211588509520753,"score_spread":0.18269563340191153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5756803,0.012768798,0.021222034,0.38238287,0.0061216867,0.0014661498,0.0001436426,0.000025768928,0.00018876477],"genre_scores_gemma":[0.8364834,0.0035945207,0.0050638006,0.15303668,0.0013533393,0.00006417553,0.0000028878815,0.000022722781,0.00037847698],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.92547196,0.06532413,0.007982748,0.00032527634,0.00032205973,0.00057382404],"domain_scores_gemma":[0.6577536,0.3330534,0.0077285776,0.00029557914,0.00042235907,0.000746516],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18935873,0.00012922261,0.0024836676,0.00015582863,0.00037721687,0.0000019598044,0.00039573837,0.0004140286,0.0008401557],"category_scores_gemma":[0.49047053,0.00010298589,0.0004382735,0.00011473125,0.0003659379,0.00017701989,0.00022191212,0.0028715106,0.0000108891845],"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":[0.004053143,0.00015164317,0.91303486,0.0005859224,0.00020992543,0.000029142553,0.0007225982,0.00018990254,0.00001041383,0.004744383,0.06768157,0.0085865185],"study_design_scores_gemma":[0.0053089033,0.0036292758,0.43054822,0.00021768884,0.0002272881,0.00007120483,0.0013476459,0.000749383,3.27487e-7,0.07224469,0.48550647,0.00014888971],"about_ca_topic_score_codex":0.00022670311,"about_ca_topic_score_gemma":0.000033716555,"teacher_disagreement_score":0.4824866,"about_ca_system_score_codex":0.00015216891,"about_ca_system_score_gemma":0.0027119166,"threshold_uncertainty_score":0.9994289},"labels":[],"label_agreement":null},{"id":"W4302362961","doi":"10.1016/j.jclinepi.2022.09.018","title":"The relationship between pragmatism, timing, and study size on impact of randomized trials: a qualitative, hypothesis generating study of trials of systemic corticosteroids for COVID-19","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University","funders":"Schulich School of Medicine and Dentistry, Western University","keywords":"Sample size determination; Randomized controlled trial; Medicine; Clinical trial; Clinical study design; Research design; Pragmatism; MEDLINE; Citation; Guideline; Family medicine; Internal medicine; Statistics; Pathology; Library science; Sociology; Social science; Computer science; Political science","score_opus":0.9886380047000537,"score_gpt":0.7909357125092182,"score_spread":0.19770229219083546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302362961","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1331322,0.837118,0.010791515,0.00028947854,0.0007484756,0.01760494,0.00030075232,0.0000019120966,0.00001269387],"genre_scores_gemma":[0.202595,0.787348,0.007785749,0.000107330445,0.00085314957,0.0009668682,0.000009238187,0.00006538109,0.0002693017],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.012667258,0.7767321,0.20635074,0.00088666583,0.0030710497,0.00029217085],"domain_scores_gemma":[0.0011442809,0.7103215,0.28515562,0.0018392674,0.0012464414,0.00029289993],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97204477,0.0007024502,0.15590897,0.0008761454,0.00026353868,0.000087543594,0.0024263568,0.00049062946,0.00042852675],"category_scores_gemma":[0.99796194,0.00023895045,0.03587613,0.0009826476,0.00044924952,0.00009499756,0.00023169236,0.0011969679,0.0000034449629],"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":[0.028143464,0.0029744748,0.12401277,0.014164723,0.084001735,0.000011208098,0.014063614,0.0011538464,4.044655e-7,0.0011994578,0.012149114,0.71812516],"study_design_scores_gemma":[0.34809348,0.06653333,0.025140472,0.023109159,0.33379123,0.00030378328,0.07502108,0.0017058267,8.122668e-8,0.07914284,0.04537349,0.0017852386],"about_ca_topic_score_codex":0.000056274464,"about_ca_topic_score_gemma":0.000011179874,"teacher_disagreement_score":0.71633995,"about_ca_system_score_codex":0.00012526117,"about_ca_system_score_gemma":0.0016901458,"threshold_uncertainty_score":0.97441167},"labels":[],"label_agreement":null},{"id":"W4303629123","doi":"10.1016/j.jclinepi.2022.09.017","title":"Encounter-based randomization did not result in contamination in a shared decision-making trial: a secondary analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Contamination; Randomized controlled trial; Randomization; Medicine; Surgery","score_opus":0.4721508123250318,"score_gpt":0.592968502972493,"score_spread":0.12081769064746123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303629123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95331544,0.0010567429,0.01748821,0.022078453,0.0036303876,0.0019801008,0.0000792512,0.000023922674,0.00034750748],"genre_scores_gemma":[0.9805478,0.00017203589,0.0064368476,0.012202213,0.0002412421,0.0002938316,0.000066248576,0.000018469882,0.000021336591],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9186193,0.0656502,0.014308069,0.00042281696,0.0004895273,0.0005100866],"domain_scores_gemma":[0.7297185,0.25782746,0.010817429,0.000740456,0.0007012443,0.00019490779],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065023676,0.00017411819,0.0031843293,0.0015661512,0.00035693683,0.0000049489654,0.00075020274,0.00043998522,0.0009587608],"category_scores_gemma":[0.27125236,0.00015436564,0.0007262804,0.0014937867,0.00009642994,0.00022326811,0.00028499536,0.0043398985,0.000008530697],"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":[0.1433719,0.0005192705,0.8098593,0.00006425219,0.00013355452,0.000029276669,0.0020460912,0.025950857,0.0000017221932,0.00033306275,0.0014399783,0.016250769],"study_design_scores_gemma":[0.14488028,0.0013865413,0.7497628,0.0005538132,0.00015050246,0.0000034358038,0.0027151892,0.089750394,2.045483e-7,0.0061542084,0.0044625136,0.00018014268],"about_ca_topic_score_codex":0.00031634784,"about_ca_topic_score_gemma":0.0021709988,"teacher_disagreement_score":0.2062287,"about_ca_system_score_codex":0.000819282,"about_ca_system_score_gemma":0.0019421761,"threshold_uncertainty_score":0.9999545},"labels":[],"label_agreement":null},{"id":"W4303684183","doi":"10.1016/j.jclinepi.2022.10.004","title":"Promoting the quality and transparency of health research in China","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; McMaster University; Hamilton Health Sciences","funders":"","keywords":"Transparency (behavior); Mandate; Clinical trial; Medicine; China; Consolidated Standards of Reporting Trials; Quality (philosophy); Alternative medicine; Data sharing; Data extraction; Data quality; MEDLINE; Business; Political science","score_opus":0.9881267489753272,"score_gpt":0.7959293743421072,"score_spread":0.19219737463321995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303684183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8588729,0.004728491,0.0023987254,0.13293768,0.00034556608,0.00029077992,0.0000041801586,3.355879e-7,0.00042137617],"genre_scores_gemma":[0.9964989,0.00041499035,0.0016428105,0.0012281159,0.000097225544,0.000005345533,2.6519876e-7,0.00000283959,0.000109501],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.04177431,0.8529722,0.09896183,0.000712268,0.0050798394,0.00049956754],"domain_scores_gemma":[0.14699128,0.7612942,0.08654951,0.0031050374,0.0016124649,0.00044753298],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.96181655,0.00009582257,0.009406299,0.00031050213,0.00019846259,0.000021289505,0.0017133924,0.00006889045,0.0011838955],"category_scores_gemma":[0.696339,0.00003618537,0.001752579,0.0010745171,0.00033214834,0.00006590745,0.00020680064,0.0017780135,0.000008543099],"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":[0.00003952933,0.00013639459,0.8538469,0.000049101774,0.000059940397,0.0000029827102,0.0011897001,0.00017142516,0.0000015499803,0.0055258097,0.0058931457,0.13308349],"study_design_scores_gemma":[0.00023317616,0.00051571993,0.83142465,0.000031036616,0.000012036693,0.000030215348,0.00083451846,0.001830465,1.05576525e-7,0.15089475,0.0141669065,0.000026435651],"about_ca_topic_score_codex":0.00009766175,"about_ca_topic_score_gemma":0.000041504365,"teacher_disagreement_score":0.26547754,"about_ca_system_score_codex":0.000025171275,"about_ca_system_score_gemma":0.00035552488,"threshold_uncertainty_score":0.99972916},"labels":[],"label_agreement":null},{"id":"W4303940660","doi":"10.1016/j.jclinepi.2022.10.002","title":"The Global Evidence Commission's report provided a wake-up call for the evidence community","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Frailty in Older Adults","field":"Medicine","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":"McMaster University","funders":"University of Johannesburg","keywords":"Call to action; Commission; Pandemic; Global health; Coronavirus disease 2019 (COVID-19); Value (mathematics); Public relations; Political science; Medicine; Public health; Business; Computer science; Advertising; Nursing; Law; Disease; Pathology","score_opus":0.5527077198780525,"score_gpt":0.580084654338045,"score_spread":0.027376934459992563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303940660","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122967005,0.016820224,0.013391053,0.8355903,0.008979718,0.0018309971,0.000022175434,0.00004679948,0.0003517128],"genre_scores_gemma":[0.9671783,0.002877497,0.004049825,0.020913398,0.0016355113,0.00011638632,0.0000037231314,0.000023824912,0.0032015617],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9749429,0.017302224,0.006155926,0.00030708328,0.0007093592,0.00058251247],"domain_scores_gemma":[0.4296212,0.5579134,0.007816987,0.002397536,0.0015129148,0.0007379332],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12675272,0.00021659097,0.0019549665,0.000031932508,0.001333038,0.000018253833,0.0016134034,0.00021462086,0.00007973518],"category_scores_gemma":[0.6716418,0.00010451284,0.0012338748,0.00025011622,0.00083638733,0.00015248048,0.0006809183,0.004270317,0.0000063047974],"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":[0.008199575,0.0004160059,0.4547875,0.0001251285,0.0005115336,0.00035311218,0.00021664261,0.00035364684,0.000017771332,0.0015606105,0.48126042,0.05219806],"study_design_scores_gemma":[0.0024783711,0.0063513047,0.4657561,0.00089123443,0.00057072245,0.011418072,0.00070813677,0.0030873462,0.000004913453,0.016875861,0.49169832,0.00015962095],"about_ca_topic_score_codex":0.00038570288,"about_ca_topic_score_gemma":0.00015855614,"teacher_disagreement_score":0.8442113,"about_ca_system_score_codex":0.00031463988,"about_ca_system_score_gemma":0.0015315369,"threshold_uncertainty_score":0.9999671},"labels":[],"label_agreement":null},{"id":"W4303940765","doi":"10.1016/j.jclinepi.2022.10.001","title":"Strong and high-quality evidence synthesis needs Cochrane: a statement of support by the GRADE Guidance Group","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; Cochrane; Impact; McMaster University Medical Centre","funders":"","keywords":"Statement (logic); Medicine; Quality of evidence; Group (periodic table); Cochrane collaboration; Quality (philosophy); Family medicine; Cochrane Library; Internal medicine; Randomized controlled trial; Chemistry; Political science; Physics","score_opus":0.8875740891238892,"score_gpt":0.6775982902135222,"score_spread":0.209975798910367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303940765","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87022066,0.013759826,0.053934257,0.05997537,0.0013326164,0.000483839,0.00007720958,0.0000021149328,0.00021408743],"genre_scores_gemma":[0.99004257,0.001533912,0.004950448,0.0026739563,0.00015351795,0.000022143808,0.0000010280619,0.000006665819,0.00061575323],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.43320012,0.4442258,0.11212328,0.0012785766,0.008423699,0.00074855913],"domain_scores_gemma":[0.22545949,0.69347805,0.07629289,0.0030309472,0.0012879824,0.00045061854],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.79198253,0.00022157514,0.010604164,0.0001885726,0.00018171732,0.000050025348,0.0024921945,0.00010295071,0.0060947267],"category_scores_gemma":[0.6959027,0.00009079343,0.0028519565,0.0006493027,0.00047511395,0.00019391917,0.0004277344,0.00080500497,0.00002753998],"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":[0.00023050449,0.00028186536,0.6071613,0.00010268293,0.0007696303,0.00001125159,0.00020404559,0.00058285607,0.000096023105,0.016848342,0.33745503,0.03625645],"study_design_scores_gemma":[0.00094307534,0.0023055943,0.72108173,0.00020879114,0.0012926466,0.00022916672,0.0033638417,0.0026117347,0.000022101902,0.05780899,0.20981291,0.00031939847],"about_ca_topic_score_codex":0.000064986656,"about_ca_topic_score_gemma":0.000010714727,"teacher_disagreement_score":0.24925229,"about_ca_system_score_codex":0.000040076,"about_ca_system_score_gemma":0.00016729638,"threshold_uncertainty_score":0.99481386},"labels":[],"label_agreement":null},{"id":"W4304182950","doi":"10.1016/j.jclinepi.2022.10.010","title":"Update of the agency for healthcare research and quality guidance on using nonrandomized studies in evidence syntheses","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Impact; Cochrane","funders":"","keywords":"Agency (philosophy); Health care; Medicine; Evidence-based medicine; Quality (philosophy); Evidence-based practice; MEDLINE; Quality of evidence; Alternative medicine; Randomized controlled trial; Surgery; Political science; Pathology","score_opus":0.99466794598458,"score_gpt":0.8191765837607234,"score_spread":0.17549136222385653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304182950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9297525,0.025235927,0.0020179623,0.041232254,0.001010616,0.000708814,0.000012867855,3.8256988e-7,0.00002865795],"genre_scores_gemma":[0.9895884,0.00243168,0.0060490305,0.0015866767,0.00015106724,0.00002363824,5.7514537e-8,0.0000042812526,0.00016516841],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.29677004,0.63011754,0.066754706,0.0010369164,0.004778367,0.00054241903],"domain_scores_gemma":[0.019818963,0.9425359,0.032250185,0.0018402963,0.0034008473,0.0001538271],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.88337463,0.000132367,0.010715511,0.0002828152,0.00025134606,0.000019656127,0.0017279787,0.000085815125,0.0002057594],"category_scores_gemma":[0.964765,0.0000508663,0.00239649,0.0008060667,0.00060076994,0.000097292264,0.00045321544,0.000929852,0.000003949219],"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":[0.0049668853,0.00032581182,0.9346747,0.00042507958,0.0005628992,0.0000076355,0.0007950315,0.0025991406,0.000039880775,0.017400566,0.015524591,0.022677781],"study_design_scores_gemma":[0.004439278,0.0030659316,0.41536644,0.0027026092,0.00028666828,0.00007311027,0.005148049,0.009815364,0.000013792283,0.53690684,0.021940526,0.0002413585],"about_ca_topic_score_codex":0.000043182474,"about_ca_topic_score_gemma":0.000059664286,"teacher_disagreement_score":0.5195063,"about_ca_system_score_codex":0.00006025269,"about_ca_system_score_gemma":0.00029975036,"threshold_uncertainty_score":0.7324909},"labels":[],"label_agreement":null},{"id":"W4306762418","doi":"10.1016/j.jclinepi.2022.10.013","title":"How pragmatic are randomized trials of remdesivir and favipiravir for in-hospital treatment of COVID-19: a descriptive methodological review of trial design using the PRECIS-2 framework","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"COVID-19 Clinical Research Studies","field":"Medicine","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":"Western University","funders":"","keywords":"Favipiravir; Research design; Medicine; Randomized controlled trial; Clinical study design; Psychological intervention; Clinical trial; Descriptive statistics; Coronavirus disease 2019 (COVID-19); Family medicine; Disease; Nursing; Pathology; Statistics; Infectious disease (medical specialty); Mathematics","score_opus":0.8903888440951182,"score_gpt":0.7041879044802324,"score_spread":0.18620093961488582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306762418","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":[0.000039739312,0.8378357,0.13189165,0.014145929,0.00077547744,0.015183405,0.0001216019,0.000004268595,0.0000022146862],"genre_scores_gemma":[0.000031869567,0.8958624,0.10135934,0.0011902468,0.0007676147,0.00072222017,0.00000909869,0.00003791264,0.000019318062],"study_design_codex":"randomized_trial","study_design_gemma":"not_applicable","domain_scores_codex":[0.6531048,0.30448872,0.03940618,0.0010583261,0.0011567344,0.0007852681],"domain_scores_gemma":[0.007197957,0.94289684,0.04765018,0.00084328535,0.00083485054,0.00057687116],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.432699,0.0006901821,0.06676027,0.0004559375,0.000081961494,0.0000066342777,0.0006784109,0.0012150524,0.0001002861],"category_scores_gemma":[0.9929601,0.0003084081,0.013212452,0.00061208993,0.0027508866,0.000060814324,0.00031660803,0.0023947002,1.426872e-7],"study_design_candidate":"randomized_trial","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":[0.46235234,0.0026327304,0.0001038842,0.14469749,0.007931685,0.000073578965,0.00018432763,0.000033397828,4.188298e-7,0.00056594773,0.000664198,0.38076],"study_design_scores_gemma":[0.33107588,0.050437126,0.000030255464,0.14022757,0.03190173,0.0000652337,0.0002260636,0.0001577907,7.3492293e-7,0.032466587,0.4130496,0.00036139737],"about_ca_topic_score_codex":0.00003191549,"about_ca_topic_score_gemma":0.0000012555145,"teacher_disagreement_score":0.6459068,"about_ca_system_score_codex":0.0005326491,"about_ca_system_score_gemma":0.0058685467,"threshold_uncertainty_score":0.99996305},"labels":[],"label_agreement":null},{"id":"W4306927028","doi":"10.1016/j.jclinepi.2022.08.017","title":"Understanding how deferred consent affects patient characteristics and outcomes: an exploratory analysis of a clinical trial of prone positioning for COVID-19","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in medical practice","field":"Health Professions","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":"Trillium Health Centre; Sunnybrook Health Science Centre; St. Michael's Hospital; William Osler Health System; Mount Sinai Hospital; Ottawa Hospital; University Health Network; Health Sciences Centre; Sinai Health System; University of Ottawa; University of Toronto; St Joseph's Health Centre","funders":"","keywords":"Informed consent; Clinical trial; Medicine; Exploratory research; Family medicine; Coronavirus disease 2019 (COVID-19); Psychology; Alternative medicine; Disease; Infectious disease (medical specialty); Internal medicine","score_opus":0.8585974383909769,"score_gpt":0.6889582603977699,"score_spread":0.16963917799320705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306927028","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":[0.8705237,0.00009726129,0.090230554,0.033656098,0.0041777636,0.0011034138,0.0001360153,0.000011966802,0.00006320863],"genre_scores_gemma":[0.9764198,0.00045257193,0.0073995516,0.015041733,0.0005527751,0.00006326834,0.000036716774,0.000020057087,0.000013521472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8968636,0.09156873,0.010089462,0.0004192509,0.00062215724,0.0004368059],"domain_scores_gemma":[0.4129494,0.5663611,0.018857384,0.0004196962,0.0005374824,0.0008748764],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21870774,0.00018555736,0.005028942,0.00038559802,0.00065250735,0.000003955576,0.0003284578,0.0006994865,0.00012268206],"category_scores_gemma":[0.7459928,0.00014563263,0.0010763357,0.0003360446,0.0009641757,0.00014817134,0.00029639332,0.0057478985,3.8847986e-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":[0.067481525,0.0019659128,0.89501137,0.0006373095,0.0034566715,0.000041410007,0.0028552557,0.00031408793,0.000015051275,0.022854196,0.003968732,0.0013984594],"study_design_scores_gemma":[0.17741643,0.07167122,0.4774706,0.0008027998,0.015075113,0.000056351866,0.08224936,0.020251893,0.000001866633,0.1416247,0.01248876,0.0008908769],"about_ca_topic_score_codex":0.00002076472,"about_ca_topic_score_gemma":0.00007103622,"teacher_disagreement_score":0.52728504,"about_ca_system_score_codex":0.0002595942,"about_ca_system_score_gemma":0.0028812666,"threshold_uncertainty_score":0.9965459},"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":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4307455432","doi":"10.1016/j.jclinepi.2022.10.018","title":"Instruments assessing risk of bias of randomized trials frequently included items that are not addressing risk of bias issues","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":21,"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; University of Toronto; McMaster University; Impact","funders":"","keywords":"Randomized controlled trial; Medicine; MEDLINE; Risk assessment; Selection bias; Environmental health; Computer science; Internal medicine; Political science; Pathology","score_opus":0.9705842370750276,"score_gpt":0.7035783977506374,"score_spread":0.26700583932439026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307455432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9758417,0.0064424127,0.012265784,0.0020636492,0.0022102275,0.00077620917,0.00014364679,0.000002228748,0.0002541467],"genre_scores_gemma":[0.97172314,0.0036752487,0.023559792,0.0004514617,0.00036058313,0.000012620229,0.0000038688545,0.000016840268,0.00019644885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.14344487,0.71468586,0.13389878,0.00094569667,0.006554111,0.00047066322],"domain_scores_gemma":[0.055930387,0.6182402,0.32071018,0.0021681907,0.0026353754,0.00031566454],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.91600776,0.00042933173,0.058316763,0.0010456945,0.00021852127,0.000090504276,0.002727767,0.00037155784,0.0037441843],"category_scores_gemma":[0.9672363,0.00019306847,0.020458126,0.0010783905,0.0007987693,0.0003731955,0.0005820777,0.0015931432,0.000017610359],"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":[0.0070435964,0.00042777703,0.94092894,0.00011680059,0.0049021835,0.000008138215,0.00032315592,0.002528853,0.00010253556,0.00029746033,0.0070953704,0.036225207],"study_design_scores_gemma":[0.12754664,0.0020665552,0.58439606,0.002269398,0.019837664,0.00013633343,0.0069931108,0.035826184,0.0010877014,0.19861244,0.020424938,0.00080298027],"about_ca_topic_score_codex":0.00024757566,"about_ca_topic_score_gemma":0.000016259908,"teacher_disagreement_score":0.35653284,"about_ca_system_score_codex":0.00004522718,"about_ca_system_score_gemma":0.00042630476,"threshold_uncertainty_score":0.9971665},"labels":[],"label_agreement":null},{"id":"W4307726265","doi":"10.1016/j.jclinepi.2022.10.020","title":"Including nonrandomized studies of interventions in systematic reviews: principles and practicalities","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Health and Medical Research Council; University of Adelaide","keywords":"Systematic review; Psychological intervention; Alternative medicine; Randomized controlled trial; Medicine; Health care; Evidence-based medicine; MEDLINE; Scientific evidence; Management science; Family medicine; Nursing; Political science; Pathology","score_opus":0.9865179549597589,"score_gpt":0.7613329008718588,"score_spread":0.22518505408790013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307726265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74876624,0.20843197,0.018494243,0.01734363,0.0030539834,0.0029657118,0.000011845026,0.0000025216964,0.0009298779],"genre_scores_gemma":[0.9627372,0.012353778,0.021850374,0.0011108984,0.00014898877,0.00012502396,6.343601e-7,0.0000091826305,0.0016639074],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.18041429,0.6446994,0.17074989,0.0007992018,0.0029614286,0.00037581145],"domain_scores_gemma":[0.023262046,0.85667,0.11664343,0.0015998435,0.0016143869,0.00021028891],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8754514,0.00018959206,0.02881894,0.00054654584,0.00010459011,0.000031043404,0.0010877876,0.00008139056,0.0010249157],"category_scores_gemma":[0.968428,0.00008069484,0.00635991,0.0005982969,0.00028846445,0.00018565966,0.0005944153,0.0007672986,0.000023670224],"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":[0.001360211,0.0015434592,0.79601634,0.04370671,0.006117815,0.00008687496,0.0039913026,0.0020028611,0.000012695639,0.097696394,0.037740204,0.009725112],"study_design_scores_gemma":[0.01799252,0.0049631055,0.118632585,0.041967984,0.00791685,0.0013817922,0.059867933,0.019689547,0.0000024396045,0.59366363,0.13306062,0.0008609671],"about_ca_topic_score_codex":0.000004151369,"about_ca_topic_score_gemma":0.000016993772,"teacher_disagreement_score":0.6773838,"about_ca_system_score_codex":0.000040882605,"about_ca_system_score_gemma":0.00009609342,"threshold_uncertainty_score":0.9998883},"labels":[],"label_agreement":null},{"id":"W4308387790","doi":"10.1016/j.jclinepi.2022.11.005","title":"Quasi-experiments are a valuable source of evidence about effects of interventions, programs and policies: commentary from the Campbell Collaboration Study Design and Bias Assessment Working Group","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 Ottawa; Bruyère","funders":"","keywords":"Psychological intervention; Systematic review; Intervention (counseling); Health care; Scopus; Agency (philosophy); Evidence-based practice; Inclusion (mineral); Medicine; Empirical evidence; Evidence-based medicine; Psychology; MEDLINE; Applied psychology; Alternative medicine; Nursing; Social psychology; Political science; Sociology","score_opus":0.8599663479911283,"score_gpt":0.6240365812493867,"score_spread":0.2359297667417416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308387790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9264259,0.01730173,0.029476719,0.024693752,0.0007434085,0.0013347042,0.000015258047,0.00000447055,0.000004110777],"genre_scores_gemma":[0.98122925,0.0012051935,0.010264347,0.0069541843,0.00021808456,0.00009867977,0.0000048393504,0.000012951354,0.000012456181],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96423626,0.022875724,0.0121078305,0.00036954213,0.00016243504,0.00024819816],"domain_scores_gemma":[0.89936024,0.083083175,0.016999807,0.00031259866,0.0001104246,0.00013373155],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14838581,0.0001397096,0.0025093132,0.00014711892,0.00021051784,0.000022490982,0.00032820943,0.00009695725,0.00003945356],"category_scores_gemma":[0.04444606,0.00011497302,0.00025970512,0.00018330938,0.00021296968,0.00020008972,0.00022339296,0.0004891756,0.0000013223785],"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":[0.00013874503,0.0013324958,0.98894215,0.00017683461,0.00034504797,0.0000010451944,0.0025424846,0.00063832744,0.0000015722687,0.00090094993,0.003777633,0.0012026896],"study_design_scores_gemma":[0.0027297805,0.0077717076,0.9503065,0.0011932285,0.000120779136,0.000007084981,0.018757628,0.007606797,0.0000016241219,0.008086539,0.0032581538,0.00016019322],"about_ca_topic_score_codex":0.0021316132,"about_ca_topic_score_gemma":0.00013759639,"teacher_disagreement_score":0.10393975,"about_ca_system_score_codex":0.00020471736,"about_ca_system_score_gemma":0.00012481073,"threshold_uncertainty_score":0.96360296},"labels":[],"label_agreement":null},{"id":"W4308784182","doi":"10.1016/j.jclinepi.2022.11.009","title":"Clinical trial data-sharing policies among journals, funding agencies, foundations, and other professional organizations: a scoping review","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Research Data Management Practices","field":"Computer Science","cited_by":9,"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. Michael's Hospital","funders":"National Institute on Drug Abuse; Australian Research Council; National Institutes of Health","keywords":"Data sharing; Grey literature; Variety (cybernetics); Clinical trial; Professional association; Public relations; MEDLINE; Medicine; Political science; Alternative medicine; Computer science","score_opus":0.908153746142352,"score_gpt":0.7120193478567203,"score_spread":0.19613439828563173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308784182","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":[0.00000507581,0.9487064,0.041008566,0.0032742007,0.004941886,0.001794669,0.000037866856,0.000031882144,0.00019944085],"genre_scores_gemma":[3.0082927e-7,0.97163224,0.021356476,0.0035876173,0.0028786713,0.00005076665,0.000088328314,0.000047560094,0.00035801058],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9412411,0.036296025,0.018948184,0.0015887637,0.0011286505,0.0007972942],"domain_scores_gemma":[0.5423666,0.36967847,0.07495326,0.009618809,0.0012766339,0.0021062053],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.26838496,0.00048795715,0.008530163,0.0007174329,0.00059406343,0.00086353545,0.0117125325,0.00052480627,0.000579655],"category_scores_gemma":[0.57096887,0.00034394977,0.0010706185,0.0016213299,0.0005361553,0.010944378,0.012646916,0.005274586,0.0000225317],"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":[0.00018110432,0.0004023856,0.0052949847,0.027235698,0.0013238465,0.00011599632,0.000019128729,0.0000037110644,3.4944208e-9,0.019394213,0.025765551,0.92026335],"study_design_scores_gemma":[0.0019645381,0.00041017926,0.00018211734,0.10809748,0.0007168189,0.00025867682,0.000017221711,0.0003043726,5.767206e-10,0.0007864707,0.8869887,0.0002734544],"about_ca_topic_score_codex":0.000031194333,"about_ca_topic_score_gemma":0.000019861642,"teacher_disagreement_score":0.91998994,"about_ca_system_score_codex":0.00016799838,"about_ca_system_score_gemma":0.004944551,"threshold_uncertainty_score":0.99990124},"labels":[],"label_agreement":null},{"id":"W4308888785","doi":"10.1016/j.jclinepi.2022.11.001","title":"Updated guidance from the agency for healthcare research and quality effective healthcare program on including nonrandomized studies of interventions in systematic reviews: a work in progress","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Ottawa Hospital","funders":"","keywords":"Psychological intervention; Health care; Agency (philosophy); Medicine; Systematic review; Work (physics); Quality (philosophy); Nursing; MEDLINE; Political science; Sociology; Engineering","score_opus":0.982014728303225,"score_gpt":0.7998266543257554,"score_spread":0.1821880739774696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308888785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76583564,0.1763015,0.00058949913,0.044270813,0.0007612346,0.01220139,0.00003107594,0.0000019260804,0.0000069310445],"genre_scores_gemma":[0.9861007,0.0027492074,0.007412718,0.00074392586,0.000111436726,0.0028140645,0.000004326838,0.000008892108,0.000054734766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.16972877,0.74698335,0.07898319,0.0010567066,0.0026892386,0.00055875594],"domain_scores_gemma":[0.09712797,0.8442664,0.05259822,0.0020713068,0.0037041283,0.00023197797],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.87730646,0.0002261168,0.020012826,0.0004796585,0.00025086963,0.000040628594,0.0015613931,0.00013962234,0.00005802469],"category_scores_gemma":[0.86151785,0.00009122132,0.0036109712,0.0020250317,0.00042698954,0.00008451658,0.00045226357,0.0015907157,0.0000059780796],"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":[0.004517013,0.0014241163,0.88693136,0.015048421,0.0010120041,0.000011095464,0.0034859383,0.00010365275,7.492159e-7,0.0046211826,0.009005221,0.07383923],"study_design_scores_gemma":[0.009729787,0.008147132,0.7281378,0.048800655,0.00041786884,0.000015410635,0.011633349,0.0013963237,6.8484513e-7,0.18707034,0.0043860055,0.0002646497],"about_ca_topic_score_codex":0.00010640093,"about_ca_topic_score_gemma":0.0006161491,"teacher_disagreement_score":0.22026505,"about_ca_system_score_codex":0.0001556004,"about_ca_system_score_gemma":0.00015718822,"threshold_uncertainty_score":0.9945361},"labels":[],"label_agreement":null},{"id":"W4309078432","doi":"10.1016/j.jclinepi.2022.11.008","title":"Heterogeneity in multicentre trial participating centers: lessons from the TOPCAT trial on interpreting trial data for clinical practice","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Heart Failure Treatment and Management","field":"Medicine","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; University of Victoria; McMaster University; University of Toronto","funders":"","keywords":"Protocol (science); Randomized controlled trial; Medicine; Clinical trial; Research design; Warrant; Family medicine; Alternative medicine; Statistics; Internal medicine; Pathology","score_opus":0.7112659938393018,"score_gpt":0.6461480640982241,"score_spread":0.06511792974107766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309078432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79071355,0.00023675339,0.00084644346,0.1952106,0.009673328,0.0031415867,0.00007196342,0.000013869971,0.000091899245],"genre_scores_gemma":[0.9321159,0.00063939387,0.019559784,0.032982346,0.014133331,0.0002994791,0.00017161676,0.000040504197,0.00005764089],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.968885,0.020739164,0.008564674,0.00074228726,0.0004795308,0.0005893378],"domain_scores_gemma":[0.73995346,0.2527062,0.0054585757,0.0013086342,0.00016731267,0.00040582663],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08448405,0.00022396086,0.002693111,0.000074646654,0.0001755264,0.00001813767,0.00069345353,0.00023571744,0.00014000859],"category_scores_gemma":[0.39764398,0.00013894848,0.0011278659,0.00011107692,0.00015085499,0.00015731152,0.0006276849,0.0020895728,0.000008372613],"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":[0.9068035,0.004668135,0.016148528,0.0000073955334,0.0007515665,0.00009942245,0.00011607298,0.00006292547,6.143701e-7,0.00016466857,0.03545139,0.035725813],"study_design_scores_gemma":[0.6773577,0.023330104,0.003244649,0.00010729528,0.00092336314,0.000013598411,0.0006433073,0.004587055,6.264331e-7,0.00021273721,0.28947616,0.0001034548],"about_ca_topic_score_codex":0.00012437846,"about_ca_topic_score_gemma":0.00011599793,"teacher_disagreement_score":0.31315994,"about_ca_system_score_codex":0.00012705516,"about_ca_system_score_gemma":0.00039381042,"threshold_uncertainty_score":0.9427163},"labels":[],"label_agreement":null},{"id":"W4310137708","doi":"10.1016/j.jclinepi.2022.11.017","title":"Challenges with need to improve the reference standard in diagnosis: paper 3: response to mustafa and schunemann","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Radiation Dose and Imaging","field":"Medicine","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":"Gold standard (test); Test (biology); Term (time); Computer science; Standard of care; Medical physics; Medicine; Epistemology; Surgery; Philosophy; Radiology","score_opus":0.21086912422840087,"score_gpt":0.4803818552336238,"score_spread":0.26951273100522294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310137708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64275426,0.0015032382,0.0000909468,0.35508022,0.00017336667,0.00018757541,0.0000027079009,0.0000037385555,0.00020398044],"genre_scores_gemma":[0.95442784,0.0021726042,0.0014898404,0.041493654,0.00027483597,0.00004339433,3.786284e-7,0.0000108003205,0.0000866679],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99383,0.003729775,0.0017180116,0.00024209997,0.00022720269,0.0002528664],"domain_scores_gemma":[0.97903943,0.019577436,0.00064286235,0.00027065107,0.00012909916,0.00034051764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027404586,0.00010300329,0.0011399935,0.00017778526,0.00006994004,0.0000055824394,0.00016944858,0.0000697717,0.00009242701],"category_scores_gemma":[0.054905966,0.000057697376,0.00010092073,0.00017778993,0.00008864463,0.00007880813,0.00011465786,0.0011013703,0.0000043723276],"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":[0.060145497,0.00035082837,0.5782328,0.00003966221,0.00023521666,0.00040421242,0.002126448,0.001299596,0.0002948593,0.0014619244,0.0224903,0.3329186],"study_design_scores_gemma":[0.0022630917,0.008153733,0.76115924,0.00009736431,0.000044045824,0.00018265429,0.0019638825,0.000057186273,0.000011224428,0.00057804363,0.22541703,0.00007246586],"about_ca_topic_score_codex":0.000018624596,"about_ca_topic_score_gemma":0.000038388094,"teacher_disagreement_score":0.33284613,"about_ca_system_score_codex":0.000065186294,"about_ca_system_score_gemma":0.0002870071,"threshold_uncertainty_score":0.95305496},"labels":[],"label_agreement":null},{"id":"W4310256212","doi":"10.1016/j.jclinepi.2022.11.012","title":"Reporting guidelines for surgical technique could be improved: a scoping review and a call for action","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Ottawa Hospital; University of Ottawa","funders":"Chinese Academy of Medical Sciences; AME Publishing; Lanzhou University","keywords":"Call to action; Action (physics); Medicine; Computer science; Medical emergency; Business","score_opus":0.9398515427022504,"score_gpt":0.7735774532047406,"score_spread":0.16627408949750977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310256212","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":[0.0000025774305,0.9355373,0.02129298,0.03346669,0.0014085803,0.008185546,0.000062837215,0.000026700967,0.000016789283],"genre_scores_gemma":[1.7074099e-7,0.8621998,0.116551295,0.016185647,0.0036536672,0.0010307531,0.00019745881,0.00007969649,0.00010153645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9386293,0.0047041695,0.054964118,0.0008377301,0.00031886317,0.0005458106],"domain_scores_gemma":[0.4341975,0.41903788,0.14055192,0.0010653557,0.0041410006,0.0010063503],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20191622,0.0005063841,0.01728852,0.00023837016,0.0001417197,0.000011274321,0.00027076877,0.0010934534,0.00015556593],"category_scores_gemma":[0.8730721,0.00035309335,0.0047387173,0.00022639992,0.00018119178,0.00015700258,0.00020244272,0.002875249,6.769408e-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":[0.00048363867,0.00012927396,0.000074009535,0.12633137,0.0005178849,0.000047577152,0.0000012318894,5.561415e-7,3.9781622e-7,0.000039377683,0.03940407,0.8329706],"study_design_scores_gemma":[0.0022670599,0.0028624644,0.000005286289,0.10042875,0.010022424,0.007041128,0.000011914967,0.000089981055,1.223459e-7,0.0003655668,0.8766669,0.00023842171],"about_ca_topic_score_codex":0.000025077305,"about_ca_topic_score_gemma":0.000016554364,"teacher_disagreement_score":0.8372628,"about_ca_system_score_codex":0.00019265071,"about_ca_system_score_gemma":0.003534701,"threshold_uncertainty_score":0.9998921},"labels":[],"label_agreement":null},{"id":"W4310733292","doi":"10.1016/j.jclinepi.2022.11.023","title":"A call for error management in academic clinical research","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient Safety and Medication Errors","field":"Health Professions","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; Impact","funders":"","keywords":"Harm; Clinical research; Quality (philosophy); Human error; MEDLINE; Quality management; Clinical trial; Medicine; Computer science; Medical emergency; Risk analysis (engineering); Psychology; Operations management; Management system; Pathology; Social psychology","score_opus":0.8979314017132909,"score_gpt":0.7730620624733765,"score_spread":0.12486933923991439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310733292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6270875,0.0011054702,0.018571801,0.32334623,0.020090967,0.0031715927,0.000043169934,0.00003203885,0.0065512895],"genre_scores_gemma":[0.92701316,0.0039294492,0.012457388,0.04684651,0.003545405,0.00061110704,0.000022691682,0.000036998867,0.005537294],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.93034345,0.054908164,0.012716557,0.00043431536,0.0005927092,0.0010048045],"domain_scores_gemma":[0.8193376,0.17363498,0.0055481666,0.00041679383,0.00044871506,0.0006137605],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29362044,0.00011278919,0.0018999839,0.00041004387,0.00048395243,2.0449762e-7,0.00081735296,0.00059720105,0.00043443535],"category_scores_gemma":[0.16970469,0.00008962986,0.00059236726,0.00037587064,0.0003759996,0.000067431356,0.00049033976,0.010900834,0.00007519943],"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":[0.0027857062,0.0004597448,0.7355351,0.000094743205,0.00010060143,0.00003086896,0.00037161875,0.0005298853,5.7246757e-7,0.01660501,0.22603247,0.017453717],"study_design_scores_gemma":[0.0034359093,0.0011205632,0.39503765,0.00009038803,0.000023510414,0.0000057639672,0.0012423017,0.0007611081,2.7090977e-8,0.023689168,0.5745371,0.00005653539],"about_ca_topic_score_codex":0.000017237538,"about_ca_topic_score_gemma":0.00002184787,"teacher_disagreement_score":0.3485046,"about_ca_system_score_codex":0.00023269703,"about_ca_system_score_gemma":0.0010137851,"threshold_uncertainty_score":0.99138105},"labels":[],"label_agreement":null},{"id":"W4310773520","doi":"10.1016/j.jclinepi.2022.11.020","title":"Indicators of questionable research practices were identified in 163,129 randomized controlled trials","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"ZonMw","keywords":"Blinding; Randomized controlled trial; Checklist; Proxy (statistics); Sample size determination; Publication bias; Medicine; Logistic regression; MEDLINE; Impact factor; Consolidated Standards of Reporting Trials; Family medicine; Meta-analysis; Statistics; Psychology; Surgery; Internal medicine","score_opus":0.9659537253604227,"score_gpt":0.7731422889942364,"score_spread":0.19281143636618625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310773520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9050728,0.018683337,0.0070323986,0.051912956,0.005206742,0.0043877074,0.000019500469,0.000002938255,0.007681627],"genre_scores_gemma":[0.987888,0.0014980998,0.0043727574,0.0008571908,0.0005354849,0.00013980536,0.0000021733872,0.0000098077935,0.004696714],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.013345846,0.8360722,0.14230552,0.00076966506,0.0070727156,0.00043401966],"domain_scores_gemma":[0.0019291795,0.7941249,0.19955583,0.0015497688,0.0025557461,0.00028457865],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.98947763,0.00023848092,0.07177835,0.0027014476,0.00017147916,0.00010565714,0.003145909,0.00029511916,0.020028546],"category_scores_gemma":[0.99550444,0.00009647657,0.016644537,0.0021339278,0.0006108762,0.00028348475,0.00040395372,0.0026551476,0.00015135181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17781569,0.0013463752,0.48071548,0.000083724546,0.0056680283,0.000092404545,0.0003361308,0.0036560646,0.000027505152,0.06983161,0.24701639,0.013410604],"study_design_scores_gemma":[0.25409484,0.001099375,0.043941323,0.00016351332,0.00198919,0.00009946784,0.002644935,0.0075205425,0.0000040094938,0.55695516,0.13125907,0.00022857416],"about_ca_topic_score_codex":0.00007460198,"about_ca_topic_score_gemma":0.000025037602,"teacher_disagreement_score":0.48712355,"about_ca_system_score_codex":0.00006306936,"about_ca_system_score_gemma":0.0010643451,"threshold_uncertainty_score":0.99964577},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","metaepi_broad","research_integrity"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4310894423","doi":"10.1016/j.jclinepi.2022.12.001","title":"Improving grading of recommendations assessment, development, and evaluation evidence tables part 4: a three-arm noninferiority randomized trial demonstrates improved understanding of content in summary of findings tables with a new format","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"","keywords":"Randomized controlled trial; Grading (engineering); Medicine; Checklist; Guideline; Systematic review; Medical physics; MEDLINE; Medical education; Psychology; Surgery; Engineering","score_opus":0.9037435414091998,"score_gpt":0.6146359955989356,"score_spread":0.2891075458102642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310894423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8185022,0.0015812237,0.17651305,0.0015484446,0.0004480716,0.001309709,0.000010772693,9.197442e-7,0.00008562364],"genre_scores_gemma":[0.9440174,0.000490887,0.05527101,0.00008277919,0.0000497899,0.000037336184,0.0000052706364,0.000005973737,0.000039568335],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8352111,0.083649136,0.07556294,0.0010310686,0.0039471257,0.00059864897],"domain_scores_gemma":[0.6029126,0.31974047,0.07427088,0.0009496138,0.001820222,0.0003061886],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5793041,0.00021117098,0.010404128,0.0005427061,0.00013408838,0.000044450888,0.0006596791,0.00011334582,0.0008040135],"category_scores_gemma":[0.3224384,0.00010986757,0.0013103657,0.00060216273,0.00029473295,0.00045727906,0.00019331294,0.000555097,2.3478438e-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":[0.078215905,0.00043648313,0.8743039,0.00023910806,0.0014195403,0.000002118762,0.0005743457,0.00096106855,0.00030220745,0.004983358,0.0020534524,0.036508545],"study_design_scores_gemma":[0.5065177,0.005607534,0.052159082,0.0031393457,0.0038474042,0.000114219394,0.012896659,0.30049992,0.00018603336,0.11319601,0.0012237321,0.00061234133],"about_ca_topic_score_codex":0.00025887103,"about_ca_topic_score_gemma":0.0004877812,"teacher_disagreement_score":0.8221448,"about_ca_system_score_codex":0.00014522983,"about_ca_system_score_gemma":0.0016330271,"threshold_uncertainty_score":0.8803384},"labels":[],"label_agreement":null},{"id":"W4311088172","doi":"10.1016/j.jclinepi.2022.11.019","title":"Controversy and debate: challenges with the need to improve the reference standard in diagnosis paper 1: two challenges: absence of a clear cut, easily replicable test for the reference standard; unethical/infeasible inclusion of an invasive procedure in the reference standard","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Manitoba","funders":"","keywords":"Grading (engineering); Gold standard (test); Diagnostic accuracy; Test (biology); Quality of evidence; Reference values; Medical physics; Standard of care; Medicine; Diagnostic test; International standard; Computer science; Pathology; Meta-analysis; Pediatrics; Surgery; Engineering; Radiology","score_opus":0.6980742085642876,"score_gpt":0.5652740455244651,"score_spread":0.13280016303982245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311088172","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":[0.6557063,0.020862857,0.0022250614,0.31412187,0.0002656135,0.0050623245,0.00046226848,0.000006253234,0.0012874671],"genre_scores_gemma":[0.9736439,0.019563174,0.0016866011,0.0046013147,0.0000984376,0.00034184218,0.0000018874947,0.000017793975,0.000045077657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9092199,0.061929334,0.02071805,0.0017700791,0.0054969806,0.00086561084],"domain_scores_gemma":[0.43659565,0.52837694,0.024585143,0.005291923,0.0047248392,0.00042549134],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37486365,0.00041571137,0.006455325,0.00023154203,0.0005498325,0.000088903405,0.0042556496,0.00027332606,0.00025613653],"category_scores_gemma":[0.39546722,0.00013396394,0.0007511441,0.0009860601,0.00085655536,0.0002905037,0.0010595467,0.0023051316,0.000002590338],"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":[0.04819404,0.0023182016,0.28328982,0.0015112925,0.002053937,0.00012194268,0.046242617,0.014097454,0.0004843134,0.19975822,0.041279398,0.36064875],"study_design_scores_gemma":[0.009763717,0.0440192,0.3028697,0.0015788776,0.0010953723,0.00025876117,0.11007028,0.0040532164,0.00008778683,0.20495486,0.32037532,0.0008728855],"about_ca_topic_score_codex":0.00019641503,"about_ca_topic_score_gemma":0.007212061,"teacher_disagreement_score":0.4726243,"about_ca_system_score_codex":0.000103053026,"about_ca_system_score_gemma":0.001050196,"threshold_uncertainty_score":0.9999966},"labels":[],"label_agreement":null},{"id":"W4311459177","doi":"10.1016/j.jclinepi.2022.12.009","title":"Pediatric core outcome sets had deficiencies and lacked child and family input: A methodological review","year":2022,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Population; Pediatrics; Intervention (counseling); Scope (computer science); Family medicine; Medicine; Pediatric research; Outcome (game theory); Psychology; Computer science; Psychiatry; Environmental health; Mathematics","score_opus":0.9403858699779151,"score_gpt":0.7371950553689659,"score_spread":0.20319081460894917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311459177","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":[0.00012919158,0.9885992,0.00016748626,0.0076451693,0.0009182821,0.0009196717,0.000021985537,0.000036581067,0.0015624373],"genre_scores_gemma":[0.000015567979,0.98422855,0.009847523,0.004781851,0.0009829099,0.00004592666,0.0000036272413,0.00002884163,0.00006521433],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.927469,0.06010476,0.009874087,0.00077036326,0.00091178925,0.00086995884],"domain_scores_gemma":[0.7752822,0.21521057,0.007987697,0.00044886043,0.0002771843,0.00079346186],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.25725636,0.00043879097,0.0121074645,0.00035241476,0.0004712862,0.000028566463,0.0014359714,0.0013115451,0.00026811886],"category_scores_gemma":[0.52270794,0.00028565098,0.0019043476,0.00088979345,0.0020320152,0.00012134295,0.00091512606,0.005874019,0.000011923581],"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":[0.000024830033,0.00009198269,0.011334547,0.007007197,0.00009258972,0.00015280017,0.000041018215,1.1800714e-7,2.733689e-9,0.005373876,0.010971509,0.96490955],"study_design_scores_gemma":[0.00016427015,0.000560197,0.003635526,0.0032000844,0.0007715195,0.0005238928,0.00008224095,0.0000015949134,3.3727335e-10,0.0051513063,0.9856569,0.0002524227],"about_ca_topic_score_codex":0.0000720346,"about_ca_topic_score_gemma":0.000018525492,"teacher_disagreement_score":0.97468543,"about_ca_system_score_codex":0.00016958281,"about_ca_system_score_gemma":0.0013634897,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W4311460075","doi":"10.1016/j.jclinepi.2022.12.011","title":"Imputing missing laboratory results may return erroneous values because they are not missing at random","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","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; Institute for Clinical Evaluative Sciences; Institute of Health Services and Policy Research; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Missing data; Statistics; Imputation (statistics); Regression analysis; Abnormality; Linear regression; Regression; Score test; Test (biology); Medicine; Mathematics; Standard deviation; Statistical hypothesis testing; Biology; Psychiatry","score_opus":0.2945736067314565,"score_gpt":0.5166305419911295,"score_spread":0.22205693525967296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311460075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.783232,0.0031096814,0.000486077,0.20905596,0.0030559069,0.00034078138,0.00012634958,0.00005642904,0.000536838],"genre_scores_gemma":[0.9304063,0.00058719155,0.0059758457,0.058548976,0.0038669999,0.000003847809,0.000015736343,0.000054803004,0.0005403561],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.95949787,0.027661817,0.010658066,0.000700289,0.00073878764,0.00074315054],"domain_scores_gemma":[0.6659181,0.30466944,0.024517415,0.0014498731,0.0015924863,0.0018526741],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12514874,0.00034296533,0.00469207,0.00016441554,0.00060817273,0.000026494383,0.00043254503,0.00050183083,0.00033437647],"category_scores_gemma":[0.44011983,0.00025673403,0.001375768,0.00024868242,0.0003561486,0.00018565045,0.00037417532,0.004271716,0.00002177136],"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":[0.19699916,0.003473577,0.6061831,0.00039430917,0.0029258868,0.00686422,0.0013568386,0.0025241151,0.0037385544,0.0005793816,0.10559044,0.069370426],"study_design_scores_gemma":[0.06497728,0.008925781,0.19856372,0.0010736015,0.0026397319,0.0029066529,0.0015405696,0.014844975,0.00014741019,0.0063698427,0.6970464,0.0009640479],"about_ca_topic_score_codex":0.000035388195,"about_ca_topic_score_gemma":0.000016201344,"teacher_disagreement_score":0.59145594,"about_ca_system_score_codex":0.00026656786,"about_ca_system_score_gemma":0.0009709662,"threshold_uncertainty_score":0.9999885},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4312038479","doi":"10.1016/j.jclinepi.2022.11.018","title":"Challenges with need to improve the reference standard in diagnosis paper 4: response to reed","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Hematological disorders and diagnostics","field":"Medicine","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":"Impact; McMaster University","funders":"","keywords":"Scopus; Certainty; Gold standard (test); Test (biology); Medicine; Publication bias; Psychology; MEDLINE; Family medicine; Philosophy; Epistemology; Meta-analysis; Pathology; Political science; Law; Internal medicine","score_opus":0.2934885628222818,"score_gpt":0.49008648826884293,"score_spread":0.19659792544656113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312038479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6166854,0.0009212518,0.0002633435,0.38097432,0.00023318126,0.00032348925,0.00000953051,0.000006585345,0.00058289507],"genre_scores_gemma":[0.9343133,0.0020929645,0.0035613694,0.059699394,0.00016281173,0.00009169163,8.5925967e-7,0.000013610591,0.00006400253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9909523,0.005429923,0.002563687,0.00031576186,0.00033981836,0.00039849468],"domain_scores_gemma":[0.91419584,0.08366118,0.0008406556,0.00044768816,0.0002637914,0.0005908667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0278503,0.00014919246,0.0019859434,0.00013684921,0.000073099,0.0000038877056,0.0003201278,0.00016574672,0.0003010498],"category_scores_gemma":[0.24071568,0.00007558624,0.00023383528,0.00027342007,0.00013587145,0.0000330448,0.00020232765,0.0014843533,0.000015806423],"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":[0.1381882,0.0014730961,0.71431166,0.000051397026,0.00020809763,0.001296773,0.0006963311,0.0013285929,0.00009220777,0.00870996,0.05311851,0.0805252],"study_design_scores_gemma":[0.0029481172,0.027649546,0.7410146,0.00012392212,0.00006082164,0.00017037567,0.0013069797,0.000019624445,0.0000062921627,0.004310544,0.22227255,0.00011661101],"about_ca_topic_score_codex":0.000026510337,"about_ca_topic_score_gemma":0.00010205054,"teacher_disagreement_score":0.32127494,"about_ca_system_score_codex":0.00007179671,"about_ca_system_score_gemma":0.00034412794,"threshold_uncertainty_score":0.9652414},"labels":[],"label_agreement":null},{"id":"W4312208367","doi":"10.1016/j.jclinepi.2022.12.007","title":"Decision criteria for selecting essential medicines and their connection to guidelines: an interpretive descriptive qualitative interview study","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"NIHR Imperial Biomedical Research Centre; National Institute for Health and Care Research; World Health Organization","keywords":"Guideline; Thematic analysis; Essential medicines; Descriptive statistics; Medicine; Qualitative research; Knowledge management; Medical education; Computer science; Nursing; Public health; Pathology","score_opus":0.774910727016984,"score_gpt":0.7075937041644063,"score_spread":0.06731702285257779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312208367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6539345,0.00020043588,0.31768808,0.02456427,0.0026487478,0.00092307804,0.000021237847,0.000013255316,0.0000063946095],"genre_scores_gemma":[0.9076231,0.00010698826,0.070007645,0.020123947,0.0020056216,0.00007078143,0.00001646928,0.000030003488,0.000015453628],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9702343,0.01767307,0.0108214915,0.00060210674,0.00033082158,0.00033825787],"domain_scores_gemma":[0.74930274,0.23662408,0.007976993,0.0004911138,0.0047334917,0.00087156845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.124075264,0.00024578703,0.0027632336,0.00029637484,0.00020556555,0.000013958202,0.00023181034,0.00012926535,0.00024418597],"category_scores_gemma":[0.5730602,0.00017187349,0.0004895195,0.0002777469,0.00014530607,0.00028866218,0.00027205018,0.0011101625,0.000001726438],"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":[0.06812754,0.00524552,0.06489009,0.00018609379,0.0026434234,0.00007847258,0.11897066,0.0005971532,0.00232526,0.000544886,0.06254302,0.67384785],"study_design_scores_gemma":[0.014270984,0.11546502,0.040713042,0.000773924,0.0013319438,0.001231892,0.77156055,0.013665072,0.000050045557,0.02392207,0.01658649,0.00042896284],"about_ca_topic_score_codex":0.00014604113,"about_ca_topic_score_gemma":0.00017693415,"teacher_disagreement_score":0.67341894,"about_ca_system_score_codex":0.00019855799,"about_ca_system_score_gemma":0.00040334227,"threshold_uncertainty_score":0.90194887},"labels":[],"label_agreement":null},{"id":"W4312603894","doi":"10.1016/s0895-4356(22)00249-9","title":"Editorial Board","year":2022,"lang":"es","type":"paratext","venue":"Journal of Clinical Epidemiology","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Medicine; Family medicine","score_opus":0.2949107337477933,"score_gpt":0.4285199353250873,"score_spread":0.133609201577294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312603894","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014478101,0.010795882,0.00020313336,0.0024163327,0.75439763,0.00015734116,0.0012720152,0.0000059399044,0.2293039],"genre_scores_gemma":[0.0008159258,0.07778279,0.0010915499,0.0028504808,0.41731825,0.000011453958,0.000043752694,0.00006590932,0.5000199],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97567517,0.0025258807,0.019381534,0.0012323741,0.00016512065,0.0010199435],"domain_scores_gemma":[0.9442886,0.026209326,0.027826421,0.00076467387,0.0003075947,0.00060336164],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.07322744,0.0005697914,0.011818229,0.00066060014,0.00033708834,0.000070112,0.0017910406,0.0015528881,0.16370519],"category_scores_gemma":[0.06679557,0.0005708954,0.004334334,0.0002604569,0.0010123204,0.0002813785,0.00090016297,0.0044557867,0.08142505],"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":[0.00047188578,0.0003010133,0.038340263,0.000063316125,0.0015194841,0.000015860187,0.00007156003,0.00072940486,3.4641722e-8,0.011780161,0.94532514,0.0013818581],"study_design_scores_gemma":[0.0020231649,0.0011629023,0.005772632,0.00005907325,0.00013229407,0.000019377658,0.00019520505,0.0001622508,5.464148e-8,0.008450837,0.98154193,0.00048026134],"about_ca_topic_score_codex":0.00014611144,"about_ca_topic_score_gemma":0.0000029168968,"teacher_disagreement_score":0.3370794,"about_ca_system_score_codex":0.00032848044,"about_ca_system_score_gemma":0.0005372698,"threshold_uncertainty_score":0.9997433},"labels":[],"label_agreement":null},{"id":"W4312608951","doi":"10.1016/s0895-4356(22)00280-3","title":"Editorial Board","year":2022,"lang":"es","type":"paratext","venue":"Journal of Clinical Epidemiology","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Medicine","score_opus":0.2949107337477933,"score_gpt":0.4285199353250873,"score_spread":0.133609201577294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312608951","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014478101,0.010795882,0.00020313336,0.0024163327,0.75439763,0.00015734116,0.0012720152,0.0000059399044,0.2293039],"genre_scores_gemma":[0.0008159258,0.07778279,0.0010915499,0.0028504808,0.41731825,0.000011453958,0.000043752694,0.00006590932,0.5000199],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97567517,0.0025258807,0.019381534,0.0012323741,0.00016512065,0.0010199435],"domain_scores_gemma":[0.9442886,0.026209326,0.027826421,0.00076467387,0.0003075947,0.00060336164],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.07322744,0.0005697914,0.011818229,0.00066060014,0.00033708834,0.000070112,0.0017910406,0.0015528881,0.16370519],"category_scores_gemma":[0.06679557,0.0005708954,0.004334334,0.0002604569,0.0010123204,0.0002813785,0.00090016297,0.0044557867,0.08142505],"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":[0.00047188578,0.0003010133,0.038340263,0.000063316125,0.0015194841,0.000015860187,0.00007156003,0.00072940486,3.4641722e-8,0.011780161,0.94532514,0.0013818581],"study_design_scores_gemma":[0.0020231649,0.0011629023,0.005772632,0.00005907325,0.00013229407,0.000019377658,0.00019520505,0.0001622508,5.464148e-8,0.008450837,0.98154193,0.00048026134],"about_ca_topic_score_codex":0.00014611144,"about_ca_topic_score_gemma":0.0000029168968,"teacher_disagreement_score":0.3370794,"about_ca_system_score_codex":0.00032848044,"about_ca_system_score_gemma":0.0005372698,"threshold_uncertainty_score":0.9997433},"labels":[{"model":"gemma","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4313478999","doi":"10.1016/j.jclinepi.2022.12.021","title":"Methods for living guidelines: early guidance based on practical experience. Paper 3: selecting and prioritizing questions for living guidelines","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"Department of Health and Aged Care, Australian Government","keywords":"Management science; Gerontology; Medicine; Computer science; Psychology; Data science; Engineering","score_opus":0.772089160938007,"score_gpt":0.7232893581466079,"score_spread":0.04879980279139906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313478999","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":[0.08488132,0.00050289376,0.76177394,0.14930236,0.002368976,0.0010108326,0.000011162817,0.00010147938,0.00004704716],"genre_scores_gemma":[0.058237176,0.000719339,0.9027471,0.0327313,0.005240753,0.0001145032,0.000008031972,0.000070906994,0.00013090631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97935486,0.0053513623,0.013383268,0.0007558274,0.00036871378,0.0007859496],"domain_scores_gemma":[0.44487202,0.5441552,0.005811982,0.0004883898,0.004032863,0.0006395423],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13708839,0.00034213584,0.0026541713,0.00032983473,0.0002986796,0.00004170425,0.00021619308,0.00054188876,0.00004872951],"category_scores_gemma":[0.94501925,0.00027193935,0.0009741048,0.000431526,0.00024141783,0.0005119151,0.00012414291,0.0012143758,0.000006878978],"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":[0.0034911362,0.000690658,0.35506225,0.0005041494,0.0005361913,0.000051079864,0.00046952558,0.001747138,0.002112471,0.0035985268,0.069157705,0.56257915],"study_design_scores_gemma":[0.0055311834,0.010973086,0.26546058,0.004564887,0.001191677,0.00055834,0.0016036555,0.5339344,0.00004116252,0.011171665,0.16432558,0.0006437356],"about_ca_topic_score_codex":0.00006398419,"about_ca_topic_score_gemma":0.0000221227,"teacher_disagreement_score":0.8079309,"about_ca_system_score_codex":0.000096680036,"about_ca_system_score_gemma":0.0010039159,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W4313531161","doi":"10.1016/j.jclinepi.2022.12.022","title":"Methods for living guidelines: early guidance based on practical experience. Paper 5: decisions on methods for evidence synthesis and recommendation development for living guidelines","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"David and Elaine Potter Foundation; Australasian Paediatric Endocrine Group; Australian Diabetes Educators Association; Ian Potter Foundation; Australian Government; State Government of Victoria; Australian Diabetes Society; Equity Trustees; Diabetes Australia; Department of Health and Social Care; Infectious Diseases Society of America; U.S. Department of Health and Human Services","keywords":"Guideline; Process (computing); Context (archaeology); Process management; Management science; Medicine; Identification (biology); Risk analysis (engineering); Computer science; Business; Engineering; Pathology; Ecology","score_opus":0.8683517466686924,"score_gpt":0.7470710874307904,"score_spread":0.12128065923790199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313531161","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":[0.009277485,0.00021432916,0.8116993,0.17542161,0.0019167161,0.0013993328,0.000013042916,0.00004526352,0.000012967935],"genre_scores_gemma":[0.005579861,0.0014691667,0.9512281,0.03873143,0.0021473886,0.00066565623,0.00001454231,0.00007234287,0.000091501664],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9726889,0.00962231,0.01551545,0.0010240114,0.00037248197,0.0007768462],"domain_scores_gemma":[0.17629316,0.813299,0.0057913437,0.0005201865,0.0035268704,0.00056943175],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23670232,0.0004131501,0.0029305036,0.00042848208,0.00033289063,0.000041893047,0.00031822317,0.0005764363,0.00013441511],"category_scores_gemma":[0.98044366,0.00030680603,0.0010490501,0.0003592047,0.00018496996,0.0005454424,0.0001470242,0.0007777215,0.000008717739],"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":[0.0045153853,0.0003162321,0.009710082,0.00012793526,0.00022366077,0.0000026597872,0.00012787584,0.0004219651,0.0003574568,0.00038804655,0.042677015,0.9411317],"study_design_scores_gemma":[0.0037882521,0.009355806,0.08265825,0.0072969226,0.0012142906,0.000091272,0.00093118177,0.39994997,0.00045025157,0.0086452905,0.48498404,0.0006344857],"about_ca_topic_score_codex":0.000016171818,"about_ca_topic_score_gemma":0.00001211444,"teacher_disagreement_score":0.9404972,"about_ca_system_score_codex":0.00017214652,"about_ca_system_score_gemma":0.0012207202,"threshold_uncertainty_score":0.9999384},"labels":[],"label_agreement":null},{"id":"W4315477391","doi":"10.1016/j.jclinepi.2022.12.024","title":"Methods for living guidelines: early guidance based on practical experience. Paper 1: Introduction","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Impact","funders":"Australian Diabetes Educators Association; State Government of Victoria; Australian Diabetes Society; Equity Trustees; Australian Government; Ian Potter Foundation; David and Elaine Potter Foundation; Diabetes Australia; Department of Health and Social Care; Infectious Diseases Society of America; U.S. Department of Health and Human Services","keywords":"Nice; Guideline; Grading (engineering); Excellence; Assisted living; Medicine; Independent living; Living lab; Medical education; Management science; Gerontology; Computer science; Political science; Engineering; World Wide Web","score_opus":0.7663515733829163,"score_gpt":0.7232744044824214,"score_spread":0.043077168900494844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315477391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054729413,0.000091527596,0.5254769,0.41379723,0.005260107,0.00048013218,0.0000038222583,0.00006357107,0.00009731072],"genre_scores_gemma":[0.05164592,0.0004618252,0.87573624,0.056641515,0.015098002,0.000049341008,0.000016442224,0.00005158403,0.0002991584],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9778516,0.0080798315,0.012473992,0.0006109566,0.0004168212,0.00056676834],"domain_scores_gemma":[0.6607307,0.32986084,0.006130467,0.0006829115,0.0020265828,0.000568486],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12929413,0.0002413344,0.0024183423,0.0002785101,0.00009783353,0.000014294812,0.00021137377,0.00047442297,0.0004339746],"category_scores_gemma":[0.89478743,0.00017646776,0.0011322331,0.0004491661,0.0002593552,0.000397105,0.000070063055,0.0013557399,0.00008143215],"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":[0.008227113,0.0009283164,0.16470218,0.0001222493,0.00034320154,0.000067529305,0.00013330056,0.0023314499,0.00092247676,0.0033576228,0.4659388,0.35292578],"study_design_scores_gemma":[0.0045948485,0.008490483,0.3035358,0.00036651507,0.0005051299,0.00025299465,0.0003964248,0.096149676,0.00006711902,0.009095229,0.57627094,0.00027487008],"about_ca_topic_score_codex":0.000021569951,"about_ca_topic_score_gemma":0.0000034768327,"teacher_disagreement_score":0.76549333,"about_ca_system_score_codex":0.00008875509,"about_ca_system_score_gemma":0.00072698144,"threshold_uncertainty_score":0.8965749},"labels":[],"label_agreement":null},{"id":"W4316038951","doi":"10.1016/j.jclinepi.2022.12.023","title":"Methods for living guidelines: early guidance based on practical experience. Paper 4: search methods and approaches for living guidelines","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":25,"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":"Medicine; MEDLINE; Management science; Medical physics; Engineering; Political science","score_opus":0.9740793613632596,"score_gpt":0.8525299430597519,"score_spread":0.12154941830350763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316038951","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":[0.017208947,0.00012947744,0.7672917,0.21204647,0.0020386407,0.0011097789,0.000019031671,0.000045689525,0.00011025692],"genre_scores_gemma":[0.0048825326,0.0003484537,0.89209515,0.09869411,0.003119212,0.0004461651,0.0000017156665,0.00004516206,0.00036747527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9237576,0.05893234,0.014284729,0.00086694065,0.00045561703,0.0017027312],"domain_scores_gemma":[0.34148523,0.65084386,0.004218331,0.00049142045,0.002108233,0.0008529576],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4179558,0.0002991221,0.0025771828,0.000404228,0.00082226365,0.00002036956,0.00057274674,0.0006735897,0.00017481082],"category_scores_gemma":[0.9031839,0.00021463961,0.00056894816,0.0005665475,0.00045635324,0.00042272272,0.0002738469,0.00157682,0.000021604552],"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":[0.0011267003,0.00018649141,0.23052457,0.0010869534,0.00014990405,0.0000057790717,0.007574134,0.0019080976,0.00027996986,0.015421839,0.23556134,0.5061742],"study_design_scores_gemma":[0.0019235975,0.0023666539,0.17851779,0.001310896,0.000078899684,0.000017932265,0.0052226083,0.4106504,0.000015127617,0.011418066,0.38811466,0.00036336257],"about_ca_topic_score_codex":0.00007716909,"about_ca_topic_score_gemma":0.00001879413,"teacher_disagreement_score":0.5919115,"about_ca_system_score_codex":0.00011960267,"about_ca_system_score_gemma":0.0025444645,"threshold_uncertainty_score":0.87527496},"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":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4317214279","doi":"10.1016/j.jclinepi.2023.01.003","title":"A scoping review identifies multiple comments suggesting modifications to SPIRIT 2013 and CONSORT 2010","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Robarts Clinical Trials; University of Ottawa; Wilfrid Laurier University; Canada Research Chairs; Women's College Hospital; University of Toronto","funders":"Medical Research Council","keywords":"Consolidated Standards of Reporting Trials; Medicine; Data science; Alternative medicine; Computer science; Pathology","score_opus":0.9786164488602223,"score_gpt":0.7543760250954039,"score_spread":0.22424042376481834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317214279","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":[0.00002643511,0.97855574,0.004278363,0.012269798,0.0022530057,0.002483511,0.000036928177,0.000005780919,0.00009046459],"genre_scores_gemma":[0.0000024460624,0.9841812,0.009121813,0.003402551,0.0006127871,0.00009526618,0.0000107533615,0.000033412085,0.0025397318],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.68529856,0.16303205,0.14588687,0.001967247,0.0030924631,0.0007228109],"domain_scores_gemma":[0.13497593,0.722803,0.1319912,0.0051723407,0.003659148,0.001398397],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.6701361,0.00064438564,0.05449368,0.0008469674,0.00018976617,0.00024031631,0.0031686635,0.00061787467,0.0011421706],"category_scores_gemma":[0.91420966,0.00030176272,0.010805426,0.0014853044,0.00029146092,0.00020437152,0.0006220113,0.001688574,0.0044834893],"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":[0.0000029413377,0.000049069116,0.004094234,0.036073044,0.00080658897,0.000017653074,0.000010779069,0.000012388447,1.6502131e-8,0.00014912494,0.5026935,0.45609072],"study_design_scores_gemma":[0.00011632008,0.00007562049,0.00071531045,0.22897437,0.002310654,0.00015819387,0.000015279804,0.00013071117,3.291031e-9,0.0012489863,0.7660455,0.00020903765],"about_ca_topic_score_codex":0.000026222404,"about_ca_topic_score_gemma":0.00007228038,"teacher_disagreement_score":0.55977094,"about_ca_system_score_codex":0.00003672748,"about_ca_system_score_gemma":0.0006495825,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W4317790249","doi":"10.1016/j.jclinepi.2023.01.004","title":"Response rates in email vs. mail surveys for urologists: a randomized controlled trial","year":2023,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Sigrid Juséliuksen Säätiö; Academy of Finland; Helsingin ja Uudenmaan Sairaanhoitopiiri","keywords":"Medicine; Randomized controlled trial; Electronic mail; Test (biology); Family medicine; Internet privacy; Internal medicine","score_opus":0.6453839970482458,"score_gpt":0.6194551010827557,"score_spread":0.025928895965490084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317790249","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025966411,0.001135635,0.0069371145,0.9380232,0.022940911,0.0046496284,0.000050163206,0.00005201392,0.00024493627],"genre_scores_gemma":[0.0027665095,0.009085174,0.009696408,0.9208716,0.039606825,0.001158639,0.000059260878,0.00014836999,0.016607208],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.05271073,0.9264634,0.017892025,0.0008610705,0.0005779219,0.0014948482],"domain_scores_gemma":[0.14095446,0.84450877,0.013003295,0.00044618227,0.0007978895,0.00028940072],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.9529652,0.0005584658,0.024119828,0.000985479,0.0002516095,0.000032318796,0.0014337199,0.007160405,0.0002776097],"category_scores_gemma":[0.98802936,0.00037848845,0.007150213,0.0004809126,0.0039936043,0.00013270079,0.00010482751,0.007395752,0.000081155595],"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":[0.6372742,0.00009920476,0.0015033485,0.000011992503,0.00067006995,0.00046356273,0.00014434906,0.000009763525,1.7099936e-7,0.0003690117,0.3592721,0.00018221],"study_design_scores_gemma":[0.6247747,0.0018369921,0.0051202755,0.00006876185,0.00026585287,0.000011997423,0.000050273018,0.0000353673,1.09656256e-7,0.03693516,0.33065787,0.00024264678],"about_ca_topic_score_codex":0.00060929375,"about_ca_topic_score_gemma":0.0008584828,"teacher_disagreement_score":0.08824373,"about_ca_system_score_codex":0.00014955884,"about_ca_system_score_gemma":0.0037118462,"threshold_uncertainty_score":0.9998667},"labels":[],"label_agreement":null},{"id":"W4318392111","doi":"10.1016/j.jclinepi.2023.01.006","title":"The impact of climate change on health needs structured evidence assessment and an evidence to action framework to make decisions: a proposal to adopt the GRADE approach","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Climate Change and Health Impacts","field":"Environmental Science","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":"Cochrane; McMaster University; Impact","funders":"","keywords":"Grading (engineering); Climate change; Certainty; Systematic review; Empirical evidence; Transparency (behavior); Evidence-based practice; Narrative review; Adaptation (eye); Management science; Health impact assessment; Risk analysis (engineering); Environmental resource management; Computer science; MEDLINE; Psychology; Medicine; Public health; Political science; Alternative medicine; Economics; Engineering; Nursing","score_opus":0.8189871847606062,"score_gpt":0.6823216133175649,"score_spread":0.13666557144304126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318392111","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":[0.01567051,0.8494168,0.0034340716,0.11804731,0.0033301495,0.009852525,0.00017374079,0.00004629834,0.000028614511],"genre_scores_gemma":[0.0009764556,0.9777401,0.011558841,0.008054477,0.0014564239,0.00015366836,0.0000040151303,0.00004931882,0.000006690426],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98157007,0.0100124255,0.0058217463,0.00068335125,0.00076188054,0.0011505059],"domain_scores_gemma":[0.9152683,0.07719135,0.004717385,0.00095941446,0.000077996694,0.0017855505],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05413072,0.000512015,0.0046195406,0.00027914354,0.00042010265,0.00005585256,0.001334512,0.00061690854,0.0000338012],"category_scores_gemma":[0.0798311,0.00022838019,0.0009001611,0.0012405876,0.00027942914,0.00021741656,0.0007383769,0.00245792,0.00005856325],"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":[0.0004313104,0.000114568895,0.0047995583,0.0007848208,0.000060010178,0.0000049675095,0.0005016371,0.00036317715,2.903274e-7,0.0002167076,0.004436683,0.98828626],"study_design_scores_gemma":[0.00052274123,0.041872665,0.6993795,0.1140168,0.00062642037,0.00048436265,0.0010210196,0.0006325188,1.296052e-7,0.013442818,0.12703323,0.0009677609],"about_ca_topic_score_codex":0.00036477202,"about_ca_topic_score_gemma":0.00034100938,"teacher_disagreement_score":0.9873185,"about_ca_system_score_codex":0.0008005247,"about_ca_system_score_gemma":0.000585688,"threshold_uncertainty_score":0.9998435},"labels":[],"label_agreement":null},{"id":"W4318815994","doi":"10.1016/j.jclinepi.2023.01.008","title":"Conceptualizing the reporting of living systematic reviews","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"","keywords":"Systematic review; Medicine; MEDLINE; Political science","score_opus":0.990410121264664,"score_gpt":0.7777321611367153,"score_spread":0.2126779601279487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318815994","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008445162,0.98661155,0.006954308,0.00036718947,0.0033350447,0.0022776867,0.000005306217,0.0000033085196,0.00043714666],"genre_scores_gemma":[0.000024970946,0.991879,0.0034122602,0.0004945839,0.0014383142,0.000057698384,0.0000012033383,0.000039771516,0.0026521832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.035588212,0.51454765,0.4445095,0.0011452236,0.003688557,0.0005208396],"domain_scores_gemma":[0.00160832,0.5456257,0.44659072,0.0040031,0.0019308928,0.0002413083],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.9675202,0.0007853551,0.16657177,0.0006713243,0.00013088701,0.00014079838,0.0067420467,0.00090872793,0.0012582488],"category_scores_gemma":[0.9976391,0.0002297414,0.057237715,0.0022545478,0.0004893395,0.00015227517,0.00059474184,0.0025901892,0.0025848653],"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":[0.0000030315964,0.00006931072,0.0024712558,0.32847676,0.004201607,0.0000615291,0.00021653713,0.00003097504,1.7778495e-8,0.003744028,0.1533938,0.5073312],"study_design_scores_gemma":[0.000025425847,0.00009105312,0.00009801234,0.2721344,0.005639938,0.00043576464,0.00021805067,0.00017505443,1.2701021e-9,0.0025579438,0.71847457,0.0001497945],"about_ca_topic_score_codex":0.000004445925,"about_ca_topic_score_gemma":0.0000054091543,"teacher_disagreement_score":0.56508076,"about_ca_system_score_codex":0.00005034039,"about_ca_system_score_gemma":0.0007873675,"threshold_uncertainty_score":0.99971086},"labels":[],"label_agreement":null},{"id":"W4319460179","doi":"10.1016/j.jclinepi.2023.02.003","title":"Synthesis methods other than meta-analysis were commonly used but seldom specified: survey of systematic reviews","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":29,"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 Health and Medical Research Council; University College London; Medical Research Council; Australian Government; McMaster University","keywords":"Meta-analysis; Computer science; Systematic review; Statistical analysis; Statistics; Data mining; Medicine; MEDLINE; Mathematics","score_opus":0.9915261343481144,"score_gpt":0.765881344659471,"score_spread":0.22564478968864343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319460179","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000066862603,0.92130524,0.07291194,0.0004659234,0.001529873,0.0030651134,0.00036752838,0.000007052782,0.00034061875],"genre_scores_gemma":[0.000017626404,0.9482368,0.045259617,0.00041579292,0.00047166753,0.00020580059,0.000017965189,0.000104866456,0.005269846],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.057434686,0.7129217,0.22188073,0.002130522,0.004880503,0.000751863],"domain_scores_gemma":[0.023315238,0.691259,0.2707715,0.010072981,0.0037915881,0.0007896701],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9616933,0.0019176782,0.35028636,0.0035374297,0.0001474907,0.0002643544,0.011802139,0.002183556,0.013510329],"category_scores_gemma":[0.9670755,0.0006997746,0.20297539,0.008369049,0.0005721319,0.00023054612,0.0006353041,0.0035483234,0.0039023252],"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":[0.00003590806,0.00030903774,0.0038190703,0.12182445,0.7158672,0.00003823763,0.00004289189,0.00007955724,2.5365313e-8,0.00068941375,0.04446172,0.11283247],"study_design_scores_gemma":[0.000087275395,0.00011517786,0.0006492815,0.008544774,0.5557016,0.00006525601,0.00004224359,0.00029795335,4.0202636e-8,0.0015365387,0.4325543,0.00040554226],"about_ca_topic_score_codex":0.00024072573,"about_ca_topic_score_gemma":0.0004968127,"teacher_disagreement_score":0.38809258,"about_ca_system_score_codex":0.000089909845,"about_ca_system_score_gemma":0.0008245625,"threshold_uncertainty_score":0.99954534},"labels":[],"label_agreement":null},{"id":"W4319773747","doi":"10.1016/j.jclinepi.2023.02.005","title":"The life and death of living systematic reviews: a methodological survey","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Cochrane; McMaster University; Impact","funders":"","keywords":"Interquartile range; Notice; Medicine; Coronavirus disease 2019 (COVID-19); Family medicine; Demography; Political science; Disease; Internal medicine","score_opus":0.9954337287419338,"score_gpt":0.7942944259214202,"score_spread":0.20113930282051362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319773747","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014730469,0.9841018,0.011716968,0.0003801212,0.001806015,0.0018520708,0.000015435042,0.000002316233,0.00011056773],"genre_scores_gemma":[0.000014954666,0.9898604,0.007742626,0.00037693628,0.0005905618,0.000050513696,0.0000011259634,0.000026449385,0.0013364253],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.036884952,0.77866274,0.18011808,0.001102195,0.002736078,0.00049597863],"domain_scores_gemma":[0.002680971,0.7996908,0.19159162,0.003416297,0.0020339931,0.0005863463],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9745509,0.0007480142,0.13073032,0.00052579027,0.00015598697,0.00017774082,0.005308938,0.001107221,0.0004336104],"category_scores_gemma":[0.9980428,0.00020801729,0.025615612,0.0014445485,0.00044305073,0.00009884475,0.00070124166,0.0022036463,0.000775786],"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":[0.000027728256,0.00011287109,0.024264297,0.22122966,0.007576077,0.000026646892,0.00004201495,0.0000064224123,5.257084e-9,0.007386481,0.08681587,0.65251195],"study_design_scores_gemma":[0.00006481791,0.00034609248,0.009489435,0.13084598,0.006767146,0.00028438022,0.000054134583,0.00021629332,3.6438752e-10,0.009937456,0.8417494,0.00024484957],"about_ca_topic_score_codex":0.000010139421,"about_ca_topic_score_gemma":0.000018461027,"teacher_disagreement_score":0.75493354,"about_ca_system_score_codex":0.000025090689,"about_ca_system_score_gemma":0.00064396916,"threshold_uncertainty_score":0.9971418},"labels":[],"label_agreement":null},{"id":"W4319981900","doi":"10.1016/j.jclinepi.2023.02.011","title":"Sponsorship bias in oncology cost effectiveness analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Economic and Financial Impacts of Cancer","field":"Economics, Econometrics and Finance","cited_by":9,"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; Impact","funders":"","keywords":"Medicine; Odds ratio; Confidence interval; Internal medicine; Logistic regression; Family medicine; Oncology","score_opus":0.5634707887758359,"score_gpt":0.521400565606984,"score_spread":0.042070223168851895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319981900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839903,0.0009827481,0.0041287295,0.004268128,0.0021472103,0.00013878022,0.000033248692,0.0000143212765,0.0042965063],"genre_scores_gemma":[0.9943112,0.00288457,0.00049144594,0.001459491,0.0006257366,0.0000090957255,0.000005771057,0.000015674503,0.00019701172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895748,0.0029182,0.006540702,0.00038701075,0.000030068333,0.0005492433],"domain_scores_gemma":[0.94475186,0.050191276,0.0044239373,0.00027645376,0.00008337701,0.0002730774],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10712338,0.00016187607,0.0046890764,0.0012280308,0.00003418985,0.000009350634,0.00039004648,0.0005603488,0.0002721922],"category_scores_gemma":[0.12327777,0.00015380837,0.0012475447,0.0011681785,0.00022927557,0.00020734726,0.0000689844,0.00092321535,0.0006652009],"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":[0.0006804388,0.00010941219,0.9331901,0.000012160687,0.00039426473,0.000063048436,0.00003480307,0.004134088,5.050836e-7,0.05359776,0.000989075,0.006794369],"study_design_scores_gemma":[0.0012901378,0.00043062086,0.8502152,0.000018092513,0.000044819786,0.000010123162,0.00001553082,0.0015925447,0.0000012743823,0.077625796,0.06863015,0.00012570652],"about_ca_topic_score_codex":0.00018910502,"about_ca_topic_score_gemma":0.00015327829,"teacher_disagreement_score":0.08297488,"about_ca_system_score_codex":0.00022568202,"about_ca_system_score_gemma":0.00018351169,"threshold_uncertainty_score":0.9194044},"labels":[],"label_agreement":null},{"id":"W4320717566","doi":"10.1016/j.jclinepi.2023.01.011","title":"The problems with systematic reviews: a living systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":169,"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":"Medical Research Council; University of Bristol; UK Research and Innovation","keywords":"Systematic review; CLARITY; Medical literature; Management science; MEDLINE; Medicine; Systematic error; Psychology; Engineering ethics; Political science; Pathology; Engineering","score_opus":0.9680148480101375,"score_gpt":0.7197860613257643,"score_spread":0.2482287866843732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320717566","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.62492e-8,0.97686255,0.003921534,0.0013133886,0.0019223834,0.015662948,0.0000070994715,0.0000095322475,0.00030044804],"genre_scores_gemma":[2.4254535e-7,0.9848621,0.001292524,0.0016317408,0.00081279,0.0011873016,0.0000024876092,0.00008915934,0.010121676],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.08469057,0.6205377,0.28537345,0.0017513119,0.006688677,0.0009582819],"domain_scores_gemma":[0.01029152,0.6621551,0.3145192,0.008845639,0.0035174666,0.0006710724],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.94904983,0.0015513063,0.22429766,0.00073431415,0.0003447442,0.00056420465,0.011996569,0.000931152,0.0005063166],"category_scores_gemma":[0.98284113,0.00038604892,0.049367346,0.0038579272,0.0004717205,0.0002583108,0.00055321504,0.003460348,0.012248229],"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":[0.0000015870528,0.000037702866,0.000028783668,0.90854424,0.003679168,0.000028540868,0.000014708661,0.000002487056,1.9913166e-10,0.0006269947,0.06919481,0.017840948],"study_design_scores_gemma":[0.0000398293,0.00017155458,0.0000025082447,0.5662419,0.021779146,0.0008322623,0.000029661505,0.000051728333,4.2979238e-11,0.00095922576,0.4096848,0.00020734835],"about_ca_topic_score_codex":0.0000021824271,"about_ca_topic_score_gemma":0.000020747413,"teacher_disagreement_score":0.34230235,"about_ca_system_score_codex":0.0001286192,"about_ca_system_score_gemma":0.001118935,"threshold_uncertainty_score":0.99985915},"labels":[],"label_agreement":null},{"id":"W4321350270","doi":"10.1016/j.jclinepi.2023.02.018","title":"Differentiating between mapping reviews and evidence gap maps","year":2023,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Disaster Response and Management","field":"Health Professions","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":"Queen's University; University of Toronto; St. Michael's Hospital","funders":"University of Toronto; Queen's University; La Trobe University","keywords":"Scopus; Systematic review; Pollock; Presentation (obstetrics); MEDLINE; Data extraction; Library science; Medicine; Data science; Computer science; Political science; History; Law","score_opus":0.853818918067726,"score_gpt":0.6569140782935189,"score_spread":0.19690483977420714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321350270","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":[0.0046040285,0.0080804555,0.004972443,0.97321886,0.007095308,0.0009095306,0.000015187673,0.000039580304,0.0010645925],"genre_scores_gemma":[0.00030289014,0.03732163,0.0027813637,0.9111479,0.03454945,0.00004634147,0.000028350438,0.00007212806,0.013749953],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93506664,0.04995359,0.013186132,0.0005513027,0.00031405376,0.0009283083],"domain_scores_gemma":[0.771523,0.21327479,0.014134505,0.0005641293,0.00020688174,0.0002967238],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09906542,0.00037720258,0.0064189914,0.0003569871,0.00024470207,0.000009654007,0.0006857604,0.0019032687,0.00017444986],"category_scores_gemma":[0.23126586,0.00025434268,0.0010310956,0.00016839837,0.00020258385,0.00013942379,0.00072253123,0.0106361145,0.00064038875],"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":[0.00004825478,0.000008064111,0.116690844,0.002194145,0.00023519568,0.0001379526,0.00020653912,2.1535209e-7,2.78225e-7,0.00007507416,0.86107546,0.019327981],"study_design_scores_gemma":[0.0004541402,0.000264138,0.083493516,0.01206082,0.0002970287,0.0000072411144,0.00014337277,0.000007870262,8.726036e-9,0.009885747,0.8932026,0.00018350402],"about_ca_topic_score_codex":0.000032118747,"about_ca_topic_score_gemma":0.0000074537425,"teacher_disagreement_score":0.16354364,"about_ca_system_score_codex":0.0000713355,"about_ca_system_score_gemma":0.00027749003,"threshold_uncertainty_score":0.9999909},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4321439062","doi":"10.1016/j.jclinepi.2023.02.001","title":"A cross-sectional analysis identified co-authorship networks and scientific collaboration on reporting guidelines for health research","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Ottawa Public Health; University of Ottawa; Ottawa Hospital","funders":"Instituto de Salud Carlos III; Australian Research Council; Canadian Institutes of Health Research; Centro de Investigación Biomédica en Red de Salud Mental","keywords":"Scopus; Library science; Citation; Medicine; Transparency (behavior); Guideline; Bibliometrics; Family medicine; Political science; MEDLINE","score_opus":0.9481588652058117,"score_gpt":0.7951157538538048,"score_spread":0.15304311135200688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321439062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8535704,0.00022949021,0.027511058,0.1154397,0.0026109756,0.00056581176,0.000021344458,0.000030460249,0.000020775162],"genre_scores_gemma":[0.9672041,0.0007673676,0.01504568,0.01022699,0.004963819,0.000027026417,0.00035376466,0.000030340407,0.0013808891],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9616045,0.008421034,0.027288485,0.0008509074,0.0010516813,0.0007834392],"domain_scores_gemma":[0.6766064,0.27129912,0.032996535,0.0008803518,0.016869139,0.0013484535],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46084908,0.00015379008,0.0025117758,0.0011348405,0.0005706689,0.00012119638,0.00016393402,0.0004340609,0.00006345432],"category_scores_gemma":[0.8605818,0.00011957575,0.00090079085,0.002403535,0.00058115146,0.00021787795,0.00007177894,0.0015146978,0.0000136855015],"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":[0.0021658263,0.00011935146,0.8704579,0.000053496555,0.0005265456,0.000021497937,0.000031495907,0.00894139,0.000016588605,0.0005464892,0.10770977,0.009409665],"study_design_scores_gemma":[0.0019701377,0.0018518305,0.9133616,0.000077207136,0.00023981067,0.000069543064,0.00017782906,0.060356334,0.000003060373,0.005710227,0.016104436,0.000078007266],"about_ca_topic_score_codex":0.000056275014,"about_ca_topic_score_gemma":0.00012893371,"teacher_disagreement_score":0.39973277,"about_ca_system_score_codex":0.00013418515,"about_ca_system_score_gemma":0.0013926611,"threshold_uncertainty_score":0.6580692},"labels":[],"label_agreement":null},{"id":"W4323276282","doi":"10.1016/j.jclinepi.2023.03.001","title":"An extension minimal important difference credibility item addressing construct proximity is a reliable alternative to the correlation item","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","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":"Population Health Research Institute; Hamilton Health Sciences; University of New Brunswick; University of Toronto; McMaster University; Canada Research Chairs; Impact","funders":"","keywords":"Prom; Credibility; Construct (python library); Correlation; Kappa; Cohen's kappa; Inter-rater reliability; Construct validity; Reliability (semiconductor); Statistics; Psychology; Rating scale; Econometrics; Medicine; Psychometrics; Mathematics; Computer science","score_opus":0.3193348981175819,"score_gpt":0.5056353387169866,"score_spread":0.1863004405994047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323276282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9768069,0.00025782475,0.002440812,0.017064493,0.0029593175,0.0003138713,0.000019886831,0.000031234114,0.000105655374],"genre_scores_gemma":[0.989198,0.00039370553,0.0012459011,0.0074553965,0.0015469224,0.000006758591,0.0000104292285,0.000015400125,0.0001274473],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9932905,0.0019060259,0.0035855512,0.00045675942,0.00037745634,0.00038373793],"domain_scores_gemma":[0.97904706,0.016712576,0.002358756,0.0005788848,0.0007529715,0.00054975064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020307705,0.00018331129,0.0017264434,0.00011926451,0.000117710864,0.000012892432,0.00026703888,0.00030856894,0.00009437673],"category_scores_gemma":[0.05748251,0.00010569042,0.0005070253,0.0003394399,0.00029929765,0.00012869223,0.00009252074,0.0012502273,0.000019570194],"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":[0.002192403,0.00011252897,0.9709396,0.00003911325,0.000077534416,0.00008959834,0.0006357091,0.00011716375,0.00016852064,0.00020539426,0.005705046,0.019717412],"study_design_scores_gemma":[0.0010052306,0.001935661,0.9532003,0.00036366202,0.00012615242,0.00019887484,0.00057459675,0.035927553,0.000059153717,0.004112467,0.0023891078,0.000107251915],"about_ca_topic_score_codex":0.00021527827,"about_ca_topic_score_gemma":0.00013100522,"teacher_disagreement_score":0.037174806,"about_ca_system_score_codex":0.00007706104,"about_ca_system_score_gemma":0.0004023033,"threshold_uncertainty_score":0.95045674},"labels":[],"label_agreement":null},{"id":"W4323322532","doi":"10.1016/j.jclinepi.2023.03.002","title":"Heterogeneity across outcomes reported in clinical trials for older adults with depression: a systematic survey","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"St. Joseph’s Healthcare Hamilton; Canadian Partnership Against Cancer; Population Health Research Institute; McMaster University; Impact","funders":"","keywords":"Medicine; Clinical trial; Outcome (game theory); Depression (economics); Clinical psychology; Internal medicine","score_opus":0.9251795049186597,"score_gpt":0.7722094892738397,"score_spread":0.15297001564482005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323322532","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":[0.0032246637,0.97709364,0.0024619556,0.0013885902,0.004904878,0.010600199,0.00018091578,0.00010491758,0.00004025668],"genre_scores_gemma":[0.00054599054,0.99459296,0.0021958665,0.00026765923,0.0015110541,0.00055094535,0.000026614844,0.00009152492,0.00021738908],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.5202297,0.3996154,0.07455159,0.001750756,0.0017704896,0.0020820734],"domain_scores_gemma":[0.18106002,0.77107424,0.043888293,0.0012441732,0.0017410315,0.0009922729],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.78350735,0.0005800899,0.03645935,0.00041231865,0.0002121777,0.000059108475,0.0021709686,0.003627094,0.00002300242],"category_scores_gemma":[0.9305908,0.0003142198,0.0071421587,0.0009584778,0.0012665956,0.0001554699,0.0003361271,0.004185053,0.000028266142],"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":[0.0013841575,0.000766932,0.4739206,0.08610664,0.0030945037,0.0006225051,0.00019752292,0.0000034213572,9.462923e-10,0.000112073634,0.007428139,0.4263635],"study_design_scores_gemma":[0.00881843,0.0024249337,0.282071,0.5351359,0.003394017,0.0003873415,0.0008403233,0.000070954426,3.55854e-8,0.0025652742,0.16284856,0.0014432367],"about_ca_topic_score_codex":0.0008384919,"about_ca_topic_score_gemma":0.008114941,"teacher_disagreement_score":0.44902927,"about_ca_system_score_codex":0.00022290675,"about_ca_system_score_gemma":0.0035199593,"threshold_uncertainty_score":0.999931},"labels":[],"label_agreement":null},{"id":"W4323568000","doi":"10.1016/j.jclinepi.2023.02.010","title":"Methodology and design of platform trials: a meta-epidemiological study","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"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; Juravinski Hospital; Dalhousie University; SickKids Foundation; Public Health Ontario; Hospital for Sick Children; University of British Columbia; Sinai Health System; McMaster University; Toronto General Hospital; Western University; University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; University of Ottawa; University of Calgary","funders":"McMaster University","keywords":"Epidemiology; Research design; Meta-analysis; Medicine; Environmental health; Statistics; Internal medicine; Mathematics","score_opus":0.9970151318499682,"score_gpt":0.8266353721958252,"score_spread":0.17037975965414298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323568000","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008819914,0.6278362,0.3661446,0.0002665324,0.0031125962,0.0024854841,0.00008667146,0.000040537798,0.000018532844],"genre_scores_gemma":[4.821847e-7,0.5130639,0.4851026,0.00017345771,0.0014563276,0.000087325105,9.021789e-7,0.00007326723,0.00004176109],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16752541,0.720143,0.10800839,0.0019348859,0.00095926726,0.0014290002],"domain_scores_gemma":[0.016896077,0.9159472,0.064351305,0.0012450652,0.00069605093,0.0008642878],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.8216716,0.0013708717,0.1377189,0.00071649905,0.00007568372,0.000012665246,0.0018092416,0.004368186,0.00038674875],"category_scores_gemma":[0.9950824,0.0006646689,0.016235678,0.0006774596,0.0018076483,0.00008712089,0.00081334333,0.006391147,0.00003130078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013587823,0.00137686,0.0001470453,0.008728,0.046422265,0.00026824808,0.000033520348,0.000013311028,4.594071e-8,0.05701667,0.0072742905,0.87736094],"study_design_scores_gemma":[0.0019777415,0.0071860813,0.00005870518,0.0028067988,0.07468951,0.00028708339,0.000053896587,0.000039152477,6.268984e-8,0.87154037,0.040941074,0.00041953308],"about_ca_topic_score_codex":0.000012495602,"about_ca_topic_score_gemma":0.0000027600704,"teacher_disagreement_score":0.87694144,"about_ca_system_score_codex":0.00006507904,"about_ca_system_score_gemma":0.0009365477,"threshold_uncertainty_score":0.9999042},"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":"W4324344125","doi":"10.1016/j.jclinepi.2023.03.009","title":"Elicited clinician knowledge did not improve dementia risk prediction in individuals with mild cognitive impairment","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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":"Occupational Cancer Research Centre; Health Sciences Centre; Sunnybrook Health Science Centre; University of British Columbia; Western University; University of Toronto; Dalhousie University; Institute of Population and Public Health; University of Alberta; University of Calgary","funders":"National Institute on Aging","keywords":"Dementia; Medicine; Cohort; Disease; Internal medicine","score_opus":0.16801595213044934,"score_gpt":0.5028946499508236,"score_spread":0.3348786978203742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324344125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920044,0.00035996194,0.00091508153,0.0039058696,0.00082041783,0.00091311266,0.000099057615,0.00004407612,0.0009380106],"genre_scores_gemma":[0.9919546,0.0030090318,0.0008373663,0.0023716574,0.0011358144,0.000052243464,0.00006203973,0.0000354492,0.0005417734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98708194,0.0054449686,0.005466406,0.0005621624,0.0005652625,0.00087922835],"domain_scores_gemma":[0.97348344,0.021916663,0.0027768195,0.0002584862,0.0008891479,0.0006754551],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044759475,0.0002945091,0.0025062102,0.0008193528,0.00009582095,0.000013329559,0.00022683154,0.00045119371,0.00026497667],"category_scores_gemma":[0.034457102,0.00019942899,0.00070358673,0.00082052825,0.00048892864,0.00017291555,0.00016533352,0.0022843776,0.00025683315],"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":[0.0039088163,0.0014711096,0.95257854,0.00006822646,0.0013930751,0.00015588925,0.00014530815,0.000011929666,0.000032231757,0.00003109815,0.0038619768,0.03634182],"study_design_scores_gemma":[0.01590015,0.014632066,0.96277595,0.00067646924,0.0009108612,0.0000692526,0.00048264494,0.0012418116,0.00012697827,0.00082112075,0.0022060103,0.00015666413],"about_ca_topic_score_codex":0.000040174145,"about_ca_topic_score_gemma":0.000044560857,"teacher_disagreement_score":0.036185157,"about_ca_system_score_codex":0.000081754486,"about_ca_system_score_gemma":0.00065229787,"threshold_uncertainty_score":0.9924611},"labels":[],"label_agreement":null},{"id":"W4324387423","doi":"10.1016/j.jclinepi.2023.03.010","title":"A scoping review described diversity in methods of randomization and reporting of baseline balance in stepped-wedge cluster randomized trials","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; University of Ottawa; Ottawa Hospital","funders":"National Center for Advancing Translational Sciences; Canadian Institutes of Health Research; National Institute on Aging; Yale University; National Institutes of Health; Ottawa Hospital Research Institute","keywords":"CRTS; Randomization; Covariate; Randomized controlled trial; Cluster randomised controlled trial; Medicine; Restricted randomization; Cluster (spacecraft); Baseline (sea); Statistics; Computer science; Mathematics; Surgery","score_opus":0.7518524937313131,"score_gpt":0.6968775172016156,"score_spread":0.05497497652969752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324387423","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024426295,0.9694856,0.021591604,0.0004679278,0.0015791851,0.00656288,0.000014312185,0.0000076206757,0.000046602363],"genre_scores_gemma":[0.000026032338,0.9801738,0.018605044,0.00055943336,0.0004367223,0.00009914955,0.000027343329,0.0000253152,0.000047124227],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.38628036,0.49883315,0.11302234,0.00074967416,0.00038629782,0.00072816777],"domain_scores_gemma":[0.22645856,0.61614645,0.15595894,0.00047312208,0.0007413492,0.00022157088],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.70593685,0.000337467,0.04756775,0.00052445516,0.00007296016,0.0000013667835,0.00032699225,0.0012612953,0.000020711897],"category_scores_gemma":[0.86081845,0.00021634542,0.0033182288,0.0005808649,0.0002626383,0.00011842973,0.0004413812,0.0026036531,0.000002638049],"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":[0.038622677,0.00040269698,0.024558624,0.5113405,0.0008614713,0.000034491462,0.0001536309,0.000006524259,9.814279e-7,0.00014119905,0.0012002297,0.422677],"study_design_scores_gemma":[0.14860605,0.00010858991,0.002576246,0.84087825,0.0024201858,0.000017010054,0.000027933804,0.0003961413,1.4295245e-8,0.0028157528,0.001975535,0.00017831917],"about_ca_topic_score_codex":0.00010134184,"about_ca_topic_score_gemma":0.00010541582,"teacher_disagreement_score":0.42249867,"about_ca_system_score_codex":0.00008460185,"about_ca_system_score_gemma":0.0011817254,"threshold_uncertainty_score":0.9996974},"labels":[],"label_agreement":null},{"id":"W4360602558","doi":"10.1016/j.jclinepi.2023.03.018","title":"Reporting guidelines used varying methodology to develop recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"NIHR Oxford Biomedical Research Centre; Manchester Biomedical Research Centre; National Science Foundation; Cancer Research UK; National Institute for Health and Care Research; Health Research Board; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"MEDLINE; Medicine; Political science","score_opus":0.9946494502939603,"score_gpt":0.805700984573983,"score_spread":0.18894846571997737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360602558","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","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":[0.15332028,0.00019695116,0.6090035,0.23081487,0.005326735,0.00025417327,0.0000037180264,0.00001116059,0.0010686389],"genre_scores_gemma":[0.026341576,0.0002558772,0.95071864,0.016563011,0.0016753232,0.000010029303,0.000005231243,0.000017298658,0.0044129933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.19774196,0.39727697,0.397365,0.0021191286,0.004325538,0.0011714248],"domain_scores_gemma":[0.039710496,0.7461818,0.19715293,0.0030103154,0.013086087,0.00085838226],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9301142,0.0002448827,0.01691661,0.00093776773,0.00014683016,0.00008103797,0.0020105294,0.00031939815,0.003420829],"category_scores_gemma":[0.9953086,0.00011425394,0.0041748937,0.0037241732,0.000086431435,0.00017788816,0.00036563378,0.0007604381,0.003068929],"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":[0.000016456019,0.000016479118,0.26460925,0.000006587721,0.00024746376,0.0000308006,0.000103396655,0.0016693008,0.000028642788,0.0013821004,0.5821905,0.14969905],"study_design_scores_gemma":[0.00027932375,0.00018717344,0.14110523,0.00008618531,0.00019118143,0.0002517063,0.00039207976,0.0072771427,0.0000070777173,0.10224393,0.7478171,0.00016188572],"about_ca_topic_score_codex":0.00001030195,"about_ca_topic_score_gemma":0.00001886952,"teacher_disagreement_score":0.34890482,"about_ca_system_score_codex":0.000024155117,"about_ca_system_score_gemma":0.0004634283,"threshold_uncertainty_score":0.9977073},"labels":[],"label_agreement":null},{"id":"W4360602724","doi":"10.1016/j.jclinepi.2023.03.017","title":"Reporting standards for child health research were few and poorly implemented","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":16,"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":"Hospital for Sick Children; Chongqing Medical University","keywords":"Medicine; MEDLINE; Citation; Environmental health; Family medicine; Medical education; Computer science; Library science; Political science","score_opus":0.9538302579202841,"score_gpt":0.8216002288734231,"score_spread":0.132230029046861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360602724","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3258849,0.0020325445,0.0028714775,0.66544026,0.0012375093,0.0009346875,0.00006594529,0.000046518027,0.0014861682],"genre_scores_gemma":[0.88845474,0.048922524,0.028385792,0.025356015,0.0064417645,0.000035644895,0.00003926437,0.000099902885,0.002264363],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94555515,0.014272628,0.03319232,0.0011584287,0.0033381237,0.002483367],"domain_scores_gemma":[0.18988532,0.7800675,0.016798766,0.0011392442,0.009252287,0.0028568818],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.663855,0.00015484566,0.0037586924,0.00044859876,0.00034318134,0.000016239192,0.00032561342,0.0007588281,0.00009673666],"category_scores_gemma":[0.93329674,0.00010815345,0.0008362584,0.00051324506,0.001003963,0.00006809559,0.00034615296,0.008427519,0.000011391269],"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":[0.0042150863,0.00031840883,0.6030036,0.0013653602,0.0005259229,0.00032892745,0.00013798459,0.000009974879,0.000021016915,0.037769504,0.23758869,0.114715524],"study_design_scores_gemma":[0.0055173826,0.01396066,0.53405035,0.001806824,0.000054136384,0.0005611871,0.00056451507,0.00058462884,0.000009769619,0.25556633,0.187203,0.000121219375],"about_ca_topic_score_codex":0.00006543574,"about_ca_topic_score_gemma":0.00013049816,"teacher_disagreement_score":0.7657949,"about_ca_system_score_codex":0.00017541605,"about_ca_system_score_gemma":0.0050356486,"threshold_uncertainty_score":0.99386007},"labels":[],"label_agreement":null},{"id":"W4362584841","doi":"10.1016/j.jclinepi.2023.03.026","title":"Development of an international glossary for clinical guidelines collaboration","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Canadian Institutes of Health Research; Canadian Thoracic Society; Institute of Health Economics; Western University; Impact; The Society of Obstetricians and Gynaecologists of Canada; Public Health Agency of Canada","funders":"","keywords":"Glossary; MEDLINE; Library science; Medicine; Family medicine; Medical education; Political science; Computer science; Linguistics; Philosophy","score_opus":0.9344234930388099,"score_gpt":0.7799451994425372,"score_spread":0.15447829359627274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362584841","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":[0.0018741989,0.9382535,0.01939263,0.013389074,0.023550084,0.0030815369,0.0002801195,0.00006932769,0.00010951615],"genre_scores_gemma":[0.0000025741622,0.68796253,0.30209932,0.0017827408,0.007425391,0.000028959515,0.0005260236,0.00006224572,0.000110202214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93778515,0.005870047,0.05460827,0.00070225756,0.00064122357,0.00039303603],"domain_scores_gemma":[0.76492417,0.18007001,0.0457819,0.00088270736,0.0074958927,0.00084530475],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13314703,0.00044177004,0.011975209,0.00046347015,0.00005713005,0.000012798994,0.0007250705,0.0015635896,0.00009206332],"category_scores_gemma":[0.6397028,0.0003133338,0.003424578,0.0004023898,0.00029029517,0.00033865342,0.00018810498,0.0017665013,0.000049696748],"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":[0.0010838502,0.0006322303,0.0018702699,0.0029821445,0.0020835702,0.00002794951,0.000012870666,0.00000568853,1.8771394e-7,0.00023037914,0.0344816,0.9565893],"study_design_scores_gemma":[0.0031358483,0.0020654958,0.0019285312,0.0064046443,0.0029721027,0.00020432468,0.00010178812,0.00037142713,2.3212007e-7,0.00085640344,0.98173887,0.00022032023],"about_ca_topic_score_codex":0.000005596685,"about_ca_topic_score_gemma":0.000027935896,"teacher_disagreement_score":0.9563689,"about_ca_system_score_codex":0.00015992278,"about_ca_system_score_gemma":0.0077497484,"threshold_uncertainty_score":0.9999319},"labels":[],"label_agreement":null},{"id":"W4362640557","doi":"10.1016/j.jclinepi.2023.03.027","title":"Presentation approaches for enhancing interpretability of patient-reported outcomes in meta-analyses: a systematic survey of Cochrane reviews","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Impact","funders":"","keywords":"Prom; Medicine; Meta-analysis; Systematic review; MEDLINE; Pooling; Cochrane collaboration; Interpretability; Patient-reported outcome; Cochrane Library; Quality of life (healthcare); Pathology; Artificial intelligence; Computer science","score_opus":0.9844325872368183,"score_gpt":0.753615944866866,"score_spread":0.23081664236995225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362640557","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004436709,0.9579287,0.034854993,0.00010552883,0.00095455215,0.005587205,0.00009677842,0.0000018783727,0.000026684693],"genre_scores_gemma":[0.0021701572,0.987751,0.009106587,0.00007872608,0.00008435085,0.00041887967,0.00004417328,0.000042926124,0.00030316893],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.15183774,0.5271349,0.31474215,0.0017623527,0.0039914083,0.0005314581],"domain_scores_gemma":[0.04855862,0.64198095,0.300566,0.004478089,0.0041400352,0.00027634407],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.87216735,0.0008959089,0.18764159,0.0015895596,0.0000313357,0.000048955237,0.0031659524,0.0008690814,0.00042978913],"category_scores_gemma":[0.97452015,0.00033121812,0.055753503,0.002626332,0.00031113223,0.00021072457,0.00027487663,0.001098007,0.00006106361],"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":[0.00014589047,0.0010062994,0.05991031,0.70306844,0.08418638,0.000012194873,0.00033644686,0.0004544334,2.1367478e-7,0.0002696248,0.0034687065,0.14714108],"study_design_scores_gemma":[0.0027065803,0.0034899695,0.036974385,0.29161164,0.5763883,0.00025487843,0.0013465367,0.010583433,0.000001621144,0.0275919,0.04695848,0.0020922944],"about_ca_topic_score_codex":0.00012167233,"about_ca_topic_score_gemma":0.00060466694,"teacher_disagreement_score":0.4922019,"about_ca_system_score_codex":0.00007271988,"about_ca_system_score_gemma":0.00071829424,"threshold_uncertainty_score":0.999914},"labels":[],"label_agreement":null},{"id":"W4362640931","doi":"10.1016/j.jclinepi.2023.03.028","title":"Bypassing phase 2 in cancer drug development erodes the risk/benefit balance in phase 3 trials","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Clinical trial; Medicine; Randomized controlled trial; Clinical study design; Balance (ability); Intensive care medicine; Internal medicine; Physical therapy","score_opus":0.9540781456989651,"score_gpt":0.7867139564248123,"score_spread":0.16736418927415275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362640931","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":[0.0009949291,0.9707039,0.016630396,0.001849212,0.007532366,0.0019211208,0.00027870806,0.000035413545,0.000053926397],"genre_scores_gemma":[0.000006729234,0.7738873,0.22242583,0.000405486,0.0028876713,0.00016636799,0.0000035636672,0.000094818184,0.00012222542],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74491996,0.17685406,0.07432547,0.0014064522,0.0009326501,0.0015614198],"domain_scores_gemma":[0.08923134,0.87260914,0.0365141,0.00087156624,0.00029589015,0.00047796906],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.49476877,0.00084731716,0.035540003,0.00055746344,0.00010523293,0.00003403874,0.0017759319,0.0016789088,0.00030294512],"category_scores_gemma":[0.95222086,0.000447981,0.0038292918,0.0009857,0.00067016884,0.000090957175,0.00035253473,0.0076360065,0.000057768186],"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":[0.00060248846,0.0012810996,0.00082068273,0.0033769612,0.00088435825,0.0001616049,0.000058010613,0.000019690202,3.5746776e-8,0.003320369,0.0051368945,0.9843378],"study_design_scores_gemma":[0.009065119,0.00037784784,0.00027981348,0.031683188,0.0018051785,0.000029969084,0.000023327464,0.0002041627,3.5438015e-7,0.56116986,0.3948958,0.00046539612],"about_ca_topic_score_codex":0.000068597255,"about_ca_topic_score_gemma":0.00023549065,"teacher_disagreement_score":0.9838724,"about_ca_system_score_codex":0.00043126798,"about_ca_system_score_gemma":0.0023237956,"threshold_uncertainty_score":0.99979717},"labels":[],"label_agreement":null},{"id":"W4365142378","doi":"10.1016/j.jclinepi.2023.04.004","title":"The BIGG-REC database makes available all WHO/PAHO evidence informed recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; Impact; Cochrane","funders":"Pan American Health Organization; World Health Organization","keywords":"Guideline; Medicine; Online database; Public health; Grading (engineering); Database; Checklist; Reproductive health; Family medicine; Environmental health; Nursing; Psychology; Computer science; Population; Pathology","score_opus":0.8496067355951106,"score_gpt":0.6853010581716824,"score_spread":0.16430567742342816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365142378","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":[0.10063996,0.0010441592,0.003670132,0.88757485,0.0052974545,0.0005524631,0.000038649843,0.0000774212,0.0011049327],"genre_scores_gemma":[0.12550914,0.40297896,0.10513316,0.32771993,0.015982319,0.000095210184,0.0006221602,0.00017551726,0.021783631],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.982631,0.0046260366,0.011362415,0.0003367262,0.00043969767,0.0006040794],"domain_scores_gemma":[0.5891169,0.40222117,0.006252731,0.00081612647,0.0009824607,0.0006106402],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09038945,0.0001853437,0.0017128814,0.00017987234,0.00018684615,0.000024601464,0.00044888826,0.00026863717,0.0008590879],"category_scores_gemma":[0.7551158,0.00011142924,0.00066533487,0.00047462754,0.00037541558,0.00060825684,0.00022551489,0.0017465751,0.0011998233],"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":[0.0012478234,0.000098330114,0.09107481,0.00003605095,0.00025322477,0.00004200569,0.000028238283,0.000027001806,0.00003856642,0.00044823435,0.84212327,0.06458244],"study_design_scores_gemma":[0.0021216269,0.0013504286,0.08786444,0.0004513757,0.000358353,0.00023776521,0.0002672173,0.0034798966,0.000008782431,0.0026716157,0.90107495,0.000113547634],"about_ca_topic_score_codex":0.00009009173,"about_ca_topic_score_gemma":0.00021679002,"teacher_disagreement_score":0.6647264,"about_ca_system_score_codex":0.00008311261,"about_ca_system_score_gemma":0.0012287842,"threshold_uncertainty_score":0.9995779},"labels":[],"label_agreement":null},{"id":"W4366817706","doi":"10.1016/j.jclinepi.2023.04.005","title":"CONSORT Harms 2022 statement, explanation, and elaboration: updated guideline for the reporting of harms in randomized trials","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa; McMaster University; Impact; Western University; University of Alberta","funders":"Northern Alberta Clinical Trials and Research Centre; National Institute for Health and Care Research","keywords":"Consolidated Standards of Reporting Trials; Checklist; Randomized controlled trial; Medicine; Guideline; Psychological intervention; Family medicine; Psychology; Nursing; Surgery","score_opus":0.9673745806702326,"score_gpt":0.7521512941830216,"score_spread":0.215223286487211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366817706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19388822,0.0052451543,0.602712,0.19097266,0.0034235306,0.0034574803,0.00006524449,0.000005441961,0.00023029548],"genre_scores_gemma":[0.81569076,0.020133296,0.13767807,0.018375231,0.0028630989,0.00031188698,0.00015964897,0.000047114634,0.004740881],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.1740442,0.32150036,0.49927315,0.0011686443,0.0034624077,0.0005512375],"domain_scores_gemma":[0.016963968,0.71690476,0.25990745,0.0011312407,0.0049255635,0.00016698817],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9615017,0.00016701594,0.02258401,0.0004407269,0.0000690757,0.00006492407,0.0007266481,0.00015859386,0.0017360728],"category_scores_gemma":[0.9844508,0.00005910683,0.0038721277,0.0010461272,0.00023638332,0.00017844186,0.0000766314,0.00034086808,0.000024763294],"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":[0.0040147863,0.000044191773,0.11177489,0.000024595063,0.0010514531,0.0000090712965,0.00011744702,0.002281606,0.000024646555,0.0030774695,0.85556424,0.022015618],"study_design_scores_gemma":[0.06287849,0.00034058216,0.048704512,0.00012898166,0.0017177084,0.000055602508,0.0019233244,0.22088191,0.00001986095,0.19569743,0.4674473,0.00020427624],"about_ca_topic_score_codex":0.000011506545,"about_ca_topic_score_gemma":0.000024858427,"teacher_disagreement_score":0.62180257,"about_ca_system_score_codex":0.000010986897,"about_ca_system_score_gemma":0.0002795605,"threshold_uncertainty_score":0.9991765},"labels":[],"label_agreement":null},{"id":"W4367837260","doi":"10.1016/j.jclinepi.2023.04.015","title":"Paper II: thematic framework analysis of registry-based randomized controlled trials provided insights for designing trial ready registries","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"University of Ottawa; Jewish General Hospital; Hospital for Sick Children; McGill University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Centre for Addiction and Mental Health","funders":"Steno Diabetes Center Aarhus; Canadian Institutes of Health Research","keywords":"Thematic analysis; Randomized controlled trial; Conceptual framework; Strengths and weaknesses; Computer science; Research design; Management science; Data science; Medicine; Medical physics; Psychology; Qualitative research; Engineering; Pathology; Sociology","score_opus":0.9014870865458545,"score_gpt":0.7317852094185043,"score_spread":0.1697018771273502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367837260","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":[0.000054575095,0.91565084,0.05724704,0.0076344414,0.0027560368,0.01635033,0.00007453325,0.000044821343,0.00018739089],"genre_scores_gemma":[0.00007125291,0.94301444,0.04854692,0.0013525314,0.004321,0.0011104217,0.00013014811,0.00012554004,0.0013277237],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.6747607,0.19195962,0.12658742,0.0019266823,0.0032837898,0.0014818185],"domain_scores_gemma":[0.008100127,0.9029234,0.08205923,0.0019885341,0.0040762005,0.0008524809],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.66926193,0.00097571977,0.16451147,0.0020811746,0.00018074736,0.000033528107,0.0014804603,0.0076898984,0.00018010443],"category_scores_gemma":[0.99520326,0.00047489605,0.056811873,0.0018423359,0.00244314,0.000081674196,0.00022260529,0.011682342,0.000010376163],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.82831985,0.0008837388,0.000014542268,0.023438003,0.08768028,0.00007629738,0.000037749378,0.000045492812,2.4612405e-7,0.02985305,0.0024298679,0.02722088],"study_design_scores_gemma":[0.5475569,0.005432846,0.0000019487923,0.055079907,0.17935687,0.000012526402,0.000032081025,0.00057038415,3.4188375e-7,0.15867396,0.052979868,0.00030241674],"about_ca_topic_score_codex":0.000020321933,"about_ca_topic_score_gemma":0.000018004976,"teacher_disagreement_score":0.71096385,"about_ca_system_score_codex":0.00018248863,"about_ca_system_score_gemma":0.013328321,"threshold_uncertainty_score":0.9997703},"labels":[],"label_agreement":null},{"id":"W4367840508","doi":"10.1016/j.jclinepi.2023.04.018","title":"GRADE concept 4: rating the certainty of evidence when study interventions or comparators differ from PICO targets","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact; Cochrane","funders":"","keywords":"Psychological intervention; Guideline; Grading (engineering); Medicine; Intervention (counseling); Comparator; Randomized controlled trial; Psychology; Nursing; Internal medicine; Pathology","score_opus":0.9843679570226118,"score_gpt":0.7458867375002816,"score_spread":0.23848121952233026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367840508","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93922323,0.0019938976,0.03127174,0.024723489,0.002119828,0.0005991372,0.00001532523,0.000004318167,0.000049012317],"genre_scores_gemma":[0.9935028,0.0001493828,0.0033053719,0.0014410928,0.00049396086,0.000009612126,0.0000016396001,0.0000073808274,0.0010887395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.59743756,0.2969973,0.09914832,0.0012348853,0.0045706113,0.00061128725],"domain_scores_gemma":[0.28896636,0.6555076,0.05060666,0.0026608587,0.0019049201,0.00035358447],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5386166,0.00024106856,0.011989718,0.00023665467,0.00014113207,0.000082178616,0.0029681048,0.00020618044,0.005096839],"category_scores_gemma":[0.81789047,0.00007304303,0.0067420574,0.0008481695,0.00040292132,0.00016679657,0.00033809937,0.0011135316,0.00040899665],"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":[0.00007543533,0.00022850104,0.7640213,0.000016318294,0.0008820975,0.000018250881,0.0010100359,0.0006924089,0.000007527947,0.00041621196,0.22352238,0.00910954],"study_design_scores_gemma":[0.0006545933,0.0010016664,0.9339744,0.0003505301,0.00068870786,0.0000116254205,0.004921498,0.00802336,0.0000036922459,0.04018213,0.010078035,0.00010977583],"about_ca_topic_score_codex":0.00005304916,"about_ca_topic_score_gemma":0.00014607533,"teacher_disagreement_score":0.35851032,"about_ca_system_score_codex":0.00001661089,"about_ca_system_score_gemma":0.00013830238,"threshold_uncertainty_score":0.99581265},"labels":[],"label_agreement":null},{"id":"W4367840900","doi":"10.1016/j.jclinepi.2023.04.016","title":"Paper I: Heterogeneous use of registry data for participant identification and primary outcome ascertainment is found in registry-based randomized controlled trials: A scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital; Centre for Addiction and Mental Health; McGill University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Jewish General Hospital; University of Ottawa; Hospital for Sick Children","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Clinical trial; Data quality; Randomized controlled trial; Disease registry; Research design; Protocol (science); Data collection; MEDLINE; Outcome (game theory); Family medicine; Alternative medicine; Pathology; Statistics","score_opus":0.9830662714064482,"score_gpt":0.7509399407679219,"score_spread":0.23212633063852628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367840900","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018469085,0.9620501,0.022171188,0.0033779657,0.0009975005,0.01120455,0.00017304342,0.0000023448204,0.0000048704965],"genre_scores_gemma":[0.000012768388,0.98794734,0.007702296,0.0028428945,0.00035067095,0.0005578681,0.00008728476,0.000033869983,0.00046502784],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.15726456,0.49959224,0.33630413,0.0025257308,0.003632467,0.0006808842],"domain_scores_gemma":[0.020323303,0.7295609,0.24174802,0.006362121,0.0016588409,0.00034679915],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9166743,0.0007449769,0.19455755,0.00062596955,0.00005963956,0.00021314542,0.003359869,0.00079169654,0.0003973458],"category_scores_gemma":[0.98178756,0.00029610193,0.029596541,0.00076869194,0.00045734507,0.00025943757,0.00036347128,0.0009213873,0.00004363713],"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":[0.020661708,0.0005418743,0.0014568819,0.37900427,0.02011053,0.000078827296,0.000024730862,0.0002629923,2.0889948e-7,0.00034518613,0.06825193,0.50926083],"study_design_scores_gemma":[0.06478181,0.00022503888,0.00009080817,0.3627122,0.0555187,0.00009727496,0.000011980448,0.0057016187,1.501025e-8,0.003394281,0.506994,0.00047224385],"about_ca_topic_score_codex":0.000011530214,"about_ca_topic_score_gemma":0.000026593105,"teacher_disagreement_score":0.5087886,"about_ca_system_score_codex":0.000065750675,"about_ca_system_score_gemma":0.0016101343,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W4376279940","doi":"10.1016/j.jclinepi.2023.05.004","title":"Researcher-patient partnership generated actionable recommendations, using quantitative evaluation and deliberative dialogue, to improve meaningful engagement","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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":"BC Mental Health & Substance Use Services; Provincial Health Services Authority; Saskatchewan Research Council (Canada); Queen's University; St. Michael's Hospital; Simon Fraser University; University of Ottawa; University of Toronto; Canadian Arthritis Patient Alliance; Arthritis Research Centre of Canada; Research Canada; Canadian Patient Safety Institute; Public Health Ontario; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Alliance; General partnership; Scale (ratio); Public engagement; Medical education; Psychology; Patient participation; Medicine; MEDLINE; Public relations; Political science","score_opus":0.9114899925319653,"score_gpt":0.7037986641745057,"score_spread":0.20769132835745963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376279940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97936404,0.0002597932,0.0025925292,0.012344508,0.0033275909,0.0015862235,0.000036402307,0.000021366319,0.00046756698],"genre_scores_gemma":[0.9050718,0.002431073,0.059676923,0.029323103,0.0019716562,0.0002878426,0.0004886419,0.00005758864,0.0006914057],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9585703,0.03506762,0.0048159594,0.00037061182,0.00048236523,0.0006931465],"domain_scores_gemma":[0.9573171,0.037766233,0.0026244633,0.00019185517,0.0014304852,0.0006698646],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08978345,0.0001628064,0.0010609829,0.0003184504,0.00075278274,0.0000064504598,0.00013531257,0.00027212626,0.0003082389],"category_scores_gemma":[0.053905275,0.00012609907,0.00014153135,0.00043306034,0.00009355702,0.00018334153,0.00018273867,0.0014811578,0.00013544073],"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":[0.007832683,0.0010954492,0.3963125,0.0010787207,0.00094667793,0.00003363227,0.032408904,0.014123949,0.0011645445,0.021678286,0.2883832,0.23494147],"study_design_scores_gemma":[0.015761677,0.029406652,0.21053554,0.0041033514,0.00053964846,0.000014733279,0.069859676,0.3315239,0.00029217164,0.08335605,0.25345805,0.0011485253],"about_ca_topic_score_codex":0.0002247628,"about_ca_topic_score_gemma":0.00015906179,"teacher_disagreement_score":0.31739995,"about_ca_system_score_codex":0.00041246644,"about_ca_system_score_gemma":0.0011135509,"threshold_uncertainty_score":0.9540641},"labels":[],"label_agreement":null},{"id":"W4377101781","doi":"10.1016/j.jclinepi.2023.05.010","title":"The development methods of official GRADE articles and requirements for claiming the use of GRADE – A statement by the GRADE guidance group","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":227,"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; Impact; Cochrane","funders":"","keywords":"Statement (logic); Group (periodic table); Medicine; Political science; Law","score_opus":0.9152006854422359,"score_gpt":0.6583272849034182,"score_spread":0.2568734005388177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377101781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6299165,0.005035048,0.1423695,0.21992975,0.001698195,0.0009400357,0.000090232985,0.000009591487,0.000011148905],"genre_scores_gemma":[0.71079916,0.009080924,0.2549551,0.023354841,0.0012373923,0.00019897286,0.000021841894,0.00007044767,0.0002813335],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.96839666,0.009849168,0.020716432,0.00035148807,0.0001513484,0.000534892],"domain_scores_gemma":[0.8509469,0.13518025,0.013258914,0.00035794577,0.00012686946,0.00012912105],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2826906,0.00015054125,0.0019696192,0.00010633753,0.00031670986,0.000021078285,0.0005053094,0.000153771,0.0000063020043],"category_scores_gemma":[0.14027487,0.00009037656,0.00036275538,0.00017991175,0.00051873043,0.00019836165,0.000121034485,0.00035696028,0.000005721828],"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":[0.0006100738,0.0006351791,0.43161887,0.0006232266,0.0018312901,0.0000011722105,0.0046495404,0.0025685094,0.00011456477,0.28591233,0.2161608,0.055274438],"study_design_scores_gemma":[0.0020637081,0.00070286635,0.2660466,0.00018404885,0.000064126165,0.000008980153,0.0018420868,0.026357267,0.00007870348,0.15324506,0.5491796,0.00022692913],"about_ca_topic_score_codex":0.00011386357,"about_ca_topic_score_gemma":0.00011203696,"teacher_disagreement_score":0.3330188,"about_ca_system_score_codex":0.0001013062,"about_ca_system_score_gemma":0.00017651099,"threshold_uncertainty_score":0.86696696},"labels":[],"label_agreement":null},{"id":"W4377101794","doi":"10.1016/j.jclinepi.2023.05.009","title":"Matured forecast analyses for “systematic and narrative review lead experts to different cancer trial predictions”","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; McGill University; Wilfrid Laurier University; Ottawa Hospital; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Randomized controlled trial; Protocol (science); Medicine; Colorectal cancer; Systematic review; Clinical trial; Intensive care medicine; Narrative review; Medical physics; MEDLINE; Cancer; Alternative medicine; Surgery; Internal medicine; Pathology","score_opus":0.9809273239688449,"score_gpt":0.7848717089134123,"score_spread":0.19605561505543256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377101794","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":[0.0000283644,0.9706813,0.011183911,0.004781028,0.004299265,0.008870218,0.00011353295,0.0000055069527,0.000036872156],"genre_scores_gemma":[0.000006182441,0.9877485,0.0024657217,0.0018673507,0.0025284009,0.0015581712,0.000014854361,0.00004449102,0.0037663237],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6758059,0.18636762,0.13190468,0.001939781,0.0033069039,0.0006750759],"domain_scores_gemma":[0.36980334,0.49900758,0.12333621,0.003402619,0.0034140036,0.0010362649],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.47422504,0.000955779,0.09573582,0.0009925918,0.00018691421,0.00017365025,0.0025595967,0.0008957124,0.0007193649],"category_scores_gemma":[0.84568846,0.000342556,0.025615446,0.001459254,0.00018054896,0.00014633937,0.00026247342,0.0010745636,0.00017556857],"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":[0.00043733465,0.00010977055,0.0000525969,0.19064488,0.0059565613,0.000009030933,0.000112761394,0.000014829222,1.549423e-8,0.00016560763,0.6037376,0.19875903],"study_design_scores_gemma":[0.0018125206,0.0009869451,0.000028071821,0.2484166,0.013375826,0.000095338735,0.00017807592,0.00042523578,6.009773e-9,0.0021712105,0.7322181,0.00029209547],"about_ca_topic_score_codex":0.0000043226246,"about_ca_topic_score_gemma":0.00004583762,"teacher_disagreement_score":0.3714634,"about_ca_system_score_codex":0.0001021259,"about_ca_system_score_gemma":0.00055306096,"threshold_uncertainty_score":0.99990267},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4377141762","doi":"10.1016/j.jclinepi.2023.05.012","title":"Weaving First Nations, Inuit, and Métis principles and values into health research processes","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University; Toronto Rehabilitation Institute; Public Health Ontario; University of Toronto","funders":"","keywords":"Indigenous; Metis; Public health; Conceptual framework; Sociology; Political science; Geography; Medicine; Social science; Ecology; Nursing","score_opus":0.46246087791016344,"score_gpt":0.6041080512299052,"score_spread":0.14164717331974175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377141762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9135736,0.0044782856,0.00007131238,0.07836067,0.0010101044,0.00029458353,0.0000024786157,0.000025594432,0.0021833777],"genre_scores_gemma":[0.57833433,0.41441274,0.0031277833,0.0003890566,0.002124741,0.0000019674897,0.0000015483007,0.000008743265,0.0015990867],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882457,0.008280831,0.0022524719,0.00024172122,0.00034759403,0.00063165853],"domain_scores_gemma":[0.91028666,0.086796366,0.0013381628,0.00011760012,0.00088231394,0.00057886256],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1117637,0.0000779873,0.0008117798,0.0003724763,0.006203394,0.000029374405,0.00022745974,0.0002507856,0.000017612676],"category_scores_gemma":[0.05493527,0.000054885404,0.00006928281,0.0006373975,0.0011640543,0.00020058085,0.0000123174805,0.00070800196,0.000011580695],"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":[0.00005511711,0.00014589178,0.36325505,0.0006124786,0.000046161993,0.0000074231557,0.29516062,0.000017463493,8.321857e-8,0.32856593,0.003477354,0.008656426],"study_design_scores_gemma":[0.00022569842,0.0004980979,0.20267767,0.0002663091,0.0000069064686,0.000015015921,0.008344797,0.00003435002,3.9068723e-7,0.08835317,0.6995061,0.00007147281],"about_ca_topic_score_codex":0.020689217,"about_ca_topic_score_gemma":0.7050075,"teacher_disagreement_score":0.69602877,"about_ca_system_score_codex":0.00012991228,"about_ca_system_score_gemma":0.02024167,"threshold_uncertainty_score":0.99509037},"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":"W4378571919","doi":"10.1016/j.jclinepi.2023.05.021","title":"Use of GRADE in systematic reviews of health effects on pollutants and extreme temperatures: A cross-sectional survey","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Climate Change and Health Impacts","field":"Environmental Science","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":"McMaster University; Impact","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; Science and Technology Department of Gansu Province","keywords":"CINAHL; Pollutant; Environmental health; Medicine; Cochrane Library; Health effect; Cross-sectional study; Meta-analysis; Internal medicine; Pathology; Chemistry; Nursing; Psychological intervention","score_opus":0.76599085920647,"score_gpt":0.578478125559445,"score_spread":0.18751273364702503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378571919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965442,0.0010827851,0.000013601405,0.0013691096,0.00050097035,0.0004524773,0.000026962269,0.0000031576237,0.0000067491733],"genre_scores_gemma":[0.98284614,0.014185297,0.00028592345,0.0025491393,0.000094007315,0.000004330665,0.0000026957166,0.000008343803,0.000024138846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9798189,0.013009096,0.0063514565,0.00021887547,0.00024063034,0.00036106593],"domain_scores_gemma":[0.9389192,0.056477427,0.004135874,0.00018435961,0.000025928322,0.00025722268],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07441334,0.00012703659,0.003032384,0.00014047026,0.000039473754,0.0000045006764,0.00015166782,0.00018863386,0.000059230606],"category_scores_gemma":[0.14608514,0.00008118374,0.00023448103,0.00034437497,0.00022628308,0.000109725916,0.00006984638,0.0004946357,0.000020060928],"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":[0.00016722099,0.00009818079,0.993761,0.00324844,0.000011234195,0.000009050699,0.00007143205,0.00010185688,0.000067003,0.00001892627,0.0013730384,0.0010726074],"study_design_scores_gemma":[0.0005605451,0.0011183172,0.99470705,0.0025682007,0.000005195922,0.000032812637,0.00000714413,0.00017932637,0.000004274175,0.00068181375,0.00008428322,0.000051009592],"about_ca_topic_score_codex":0.00031684968,"about_ca_topic_score_gemma":0.00031656478,"teacher_disagreement_score":0.07167181,"about_ca_system_score_codex":0.000074422824,"about_ca_system_score_gemma":0.000056821846,"threshold_uncertainty_score":0.95308626},"labels":[],"label_agreement":null},{"id":"W4379113007","doi":"10.1016/j.jclinepi.2023.05.017","title":"Methods and results of studies on reporting guideline adherence are poorly reported: a meta-research study","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":16,"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 Health Centre; St. Joseph’s Healthcare Hamilton; Douglas Mental Health University Institute; McGill University; McMaster University; Jewish General Hospital","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Mitacs; Canada Research Chairs","keywords":"Observational study; Medicine; Guideline; Meta-analysis; MEDLINE; Systematic review; Strengthening the reporting of observational studies in epidemiology; Confidence interval; Research design; Family medicine; Internal medicine; Pathology; Statistics","score_opus":0.994072558210708,"score_gpt":0.8392559261093149,"score_spread":0.15481663210139307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379113007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96471256,0.006576656,0.004627836,0.02075793,0.0019597115,0.00081052986,0.000008400283,0.00000687777,0.00053950044],"genre_scores_gemma":[0.83357763,0.0011962866,0.15994613,0.0010526682,0.0006689307,0.000024812309,0.0000011042868,0.000017458626,0.0035149807],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.06435416,0.53903747,0.38436872,0.0025430906,0.008844593,0.00085199025],"domain_scores_gemma":[0.012006041,0.6721749,0.2966605,0.0039922176,0.014701396,0.00046500054],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.97479826,0.0003112533,0.028405126,0.0010632707,0.0001604988,0.000061198196,0.0015335103,0.00024170829,0.00026048702],"category_scores_gemma":[0.99455696,0.00012056777,0.005696741,0.0025062582,0.0005008388,0.0001357629,0.00053753186,0.0014285522,0.00010299634],"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":[0.0005180033,0.0005438544,0.49733293,0.00010730531,0.016539583,0.0007577892,0.0010461548,0.0019352395,0.00003427504,0.0006539429,0.40455714,0.07597378],"study_design_scores_gemma":[0.0027008418,0.010069791,0.6544814,0.0005363456,0.00791377,0.0005006105,0.036755413,0.009799288,0.000034788027,0.21921526,0.057572763,0.0004197066],"about_ca_topic_score_codex":0.000035220255,"about_ca_topic_score_gemma":0.00005018708,"teacher_disagreement_score":0.3469844,"about_ca_system_score_codex":0.000018916864,"about_ca_system_score_gemma":0.00023462564,"threshold_uncertainty_score":0.9860192},"labels":[],"label_agreement":null},{"id":"W4379375183","doi":"10.1016/j.jclinepi.2023.05.027","title":"Systematic reviewers used various approaches to data extraction and expressed several research needs: a survey","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Toronto; Centre for Excellence in Mining Innovation; Public Health Ontario; University of British Columbia; Cochrane; St. Michael's Hospital","funders":"","keywords":"Data extraction; Computer science; Raw data; Data science; Systematic review; Data collection; Variety (cybernetics); Social media; Descriptive statistics; Software; Data mining; Information retrieval; MEDLINE; World Wide Web; Statistics; Artificial intelligence","score_opus":0.993310602315711,"score_gpt":0.745898365536095,"score_spread":0.247412236779616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379375183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.713202,0.012023419,0.20837027,0.05477132,0.005510455,0.0047675264,0.00012564356,0.00002472741,0.0012046348],"genre_scores_gemma":[0.95947254,0.0035288362,0.028069519,0.0021542304,0.001257429,0.000053213822,0.000037603233,0.00004000035,0.0053866305],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.21578337,0.684183,0.08889425,0.0021295648,0.00794474,0.0010650622],"domain_scores_gemma":[0.11670706,0.83805203,0.032731242,0.008157618,0.0031809823,0.0011710702],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9342054,0.00027628968,0.016312703,0.0012777766,0.00016116678,0.00028827955,0.004068067,0.0003414561,0.00047354872],"category_scores_gemma":[0.95080245,0.00012444271,0.001760403,0.0033759733,0.00022641255,0.0004585799,0.0008062647,0.001263914,0.0016949571],"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":[0.0001841133,0.0001707204,0.20515864,0.002942145,0.0011254182,0.00005173018,0.0005695951,0.00080731354,0.000011508301,0.0012830044,0.7766083,0.011087545],"study_design_scores_gemma":[0.0012006662,0.0010079468,0.7070981,0.0043637343,0.0009162873,0.00036197307,0.0027389636,0.15932177,7.9526956e-7,0.03813487,0.0843527,0.0005021567],"about_ca_topic_score_codex":0.00004828939,"about_ca_topic_score_gemma":0.000070495764,"teacher_disagreement_score":0.69225556,"about_ca_system_score_codex":0.000031033327,"about_ca_system_score_gemma":0.00026070263,"threshold_uncertainty_score":0.9990823},"labels":[],"label_agreement":null},{"id":"W4379382853","doi":"10.1016/j.jclinepi.2023.05.025","title":"Part II: A step-by-step guide to latent class analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","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":"St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Latent class model; Class (philosophy); Homogeneous; Identification (biology); Latent variable; Computer science; Population; Econometrics; Risk analysis (engineering); Statistics; Data mining; Data science; Operations research; Medicine; Mathematics; Environmental health; Machine learning; Artificial intelligence","score_opus":0.12307329709533134,"score_gpt":0.4633605833893065,"score_spread":0.3402872862939752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379382853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8885446,0.0006949361,0.07703175,0.03089723,0.0018072198,0.00018210623,0.00006378451,0.000020737558,0.0007575936],"genre_scores_gemma":[0.86377573,0.008288667,0.06937188,0.03535745,0.004903581,0.00004183586,0.00041004736,0.000076240205,0.017774599],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901169,0.0036330067,0.0048175147,0.0005437928,0.00018696152,0.00070180447],"domain_scores_gemma":[0.99226713,0.0038936792,0.0022909702,0.0005521913,0.00042630886,0.00056971575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024901029,0.00023670118,0.0023513108,0.00024772814,0.00012636826,0.0000062787876,0.0005322911,0.00074247085,0.00009366857],"category_scores_gemma":[0.052234128,0.00018682037,0.0015128874,0.00066058815,0.00015690466,0.000004302187,0.0003429602,0.00048848335,0.00011274348],"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":[0.000101648046,0.00007753749,0.34694922,0.0000030086665,0.0010738274,0.000006430291,0.00000438694,0.0032965722,0.0003669187,0.000101661,0.6444012,0.0036176105],"study_design_scores_gemma":[0.00061317557,0.0013566746,0.2938744,0.00000864444,0.0003257201,0.000014452548,0.00003197642,0.001643928,0.000027035336,0.0001813395,0.7017612,0.00016148027],"about_ca_topic_score_codex":0.000047619895,"about_ca_topic_score_gemma":0.00009863231,"teacher_disagreement_score":0.05735999,"about_ca_system_score_codex":0.000030515892,"about_ca_system_score_gemma":0.00019494157,"threshold_uncertainty_score":0.95574933},"labels":[],"label_agreement":null},{"id":"W4380091472","doi":"10.1016/j.jclinepi.2023.04.003","title":"Corrigendum to methodological approaches for developing, reporting, and assessing evidence-based clinical practice guidelines: a systematic survey [Journal of Clinical Epidemiology 146 (2022) 77-85]","year":2023,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; McMaster University; Impact","funders":"","keywords":"Guideline; Checklist; Grading (engineering); Medicine; Medical physics; Computer science; Family medicine; Psychology; Pathology; Engineering","score_opus":0.9787376123107188,"score_gpt":0.75662540289337,"score_spread":0.22211220941734877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380091472","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":[0.0058579016,0.014754385,0.6310507,0.17774795,0.16625412,0.0040561636,0.00008739728,0.00009155,0.00009984943],"genre_scores_gemma":[0.00082155725,0.030924886,0.83384794,0.092974894,0.03726927,0.00010434373,0.00028899274,0.00030499924,0.0034631046],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.37750372,0.3171611,0.2943995,0.0044211224,0.0033426047,0.003171936],"domain_scores_gemma":[0.0113720875,0.7252129,0.2368511,0.0018395649,0.022123722,0.0026006487],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.84520394,0.0015314878,0.042150673,0.0012664987,0.00028701077,0.00009796973,0.0018596294,0.0075757746,0.00007329391],"category_scores_gemma":[0.99860847,0.0010480469,0.00857313,0.001188963,0.0019490734,0.0009524517,0.00086533366,0.016527044,0.000040371182],"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":[0.009845566,0.00089265086,0.20027438,0.0079105925,0.0035956495,0.0007720293,0.000025307902,0.00011757663,8.2106317e-7,0.0002578195,0.73851454,0.037793085],"study_design_scores_gemma":[0.011252848,0.026846668,0.5923334,0.05481766,0.015988037,0.0085179405,0.0013387969,0.0145006785,9.959313e-7,0.007953104,0.2648734,0.0015765202],"about_ca_topic_score_codex":0.00023951939,"about_ca_topic_score_gemma":0.00016718122,"teacher_disagreement_score":0.47364116,"about_ca_system_score_codex":0.00046159164,"about_ca_system_score_gemma":0.02111342,"threshold_uncertainty_score":0.9997434},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4380269675","doi":"10.1016/j.jclinepi.2023.06.006","title":"A new taxonomy is proposed for defining the interests of stakeholders’ representatives in health research: the case of guideline development","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Ottawa; McMaster University; Impact","funders":"Canadian Institutes of Health Research","keywords":"Scopus; Guideline; Stakeholder; Stakeholder engagement; Context (archaeology); Health care; Medicine; Library science; Political science; MEDLINE; Public relations; Computer science; Geography; Pathology","score_opus":0.9494498137416371,"score_gpt":0.7204387851166558,"score_spread":0.22901102862498124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380269675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4979581,0.001099121,0.039352547,0.45848677,0.00068790687,0.0023154775,0.000019328314,0.000009885351,0.00007088902],"genre_scores_gemma":[0.80519986,0.0016312563,0.1804814,0.011685962,0.00070033775,0.000036359517,0.000030065843,0.000030080817,0.00020467471],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9695674,0.010218393,0.018862113,0.00036224068,0.00042926712,0.0005605415],"domain_scores_gemma":[0.6901922,0.29628757,0.010583466,0.0006730599,0.0018783871,0.00038527555],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18805613,0.00013127964,0.0018796369,0.00029598473,0.00008971883,0.000004551719,0.00034026615,0.0001506455,0.00007164635],"category_scores_gemma":[0.4672193,0.000068481684,0.0004540002,0.0006127276,0.0004884232,0.00009508097,0.00019319699,0.0013426187,0.000004214709],"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":[0.0048294687,0.00038229537,0.11243056,0.00029070373,0.0004954193,0.00019916064,0.0029636698,0.00036748374,0.000029678336,0.0024169555,0.39831054,0.47728404],"study_design_scores_gemma":[0.028091704,0.016075075,0.2941349,0.0026288605,0.00036197875,0.0024356518,0.086234175,0.014032888,0.000501307,0.048559424,0.5065948,0.0003492585],"about_ca_topic_score_codex":0.0010455223,"about_ca_topic_score_gemma":0.0008222206,"teacher_disagreement_score":0.4769348,"about_ca_system_score_codex":0.00007940071,"about_ca_system_score_gemma":0.0034261465,"threshold_uncertainty_score":0.8360671},"labels":[],"label_agreement":null},{"id":"W4380758257","doi":"10.1016/j.jclinepi.2023.06.009","title":"A scoping review establishes need for consensus guidance on reporting health equity in observational studies","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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":"Hospital for Sick Children; Canadian Agency for Drugs and Technologies in Health; St. Joseph’s Healthcare Hamilton; London Health Sciences Centre; Ottawa Hospital; Carleton University; Queen's University; International Development Research Centre; Impact; Canadian Association of Emergency Physicians; Public Health Ontario; Dalhousie University; Royal College of Physicians and Surgeons of Canada; University of Toronto; Centre for Global Health Research; Cochrane; Ottawa Public Health; University of Ottawa; Canadian Council on Animal Care; Bruyère; McMaster University","funders":"Canadian Institutes of Health Research; World Health Organization","keywords":"Observational study; Equity (law); MEDLINE; Medicine; Actuarial science; Business; Political science; Pathology","score_opus":0.9823343326318191,"score_gpt":0.7855852011404475,"score_spread":0.19674913149137163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380758257","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":[0.000022569046,0.957156,0.0004614724,0.03631184,0.0036898837,0.0022630575,0.000019621983,0.000011219748,0.000064309505],"genre_scores_gemma":[0.0000013219395,0.9798651,0.009043956,0.009764679,0.0010804262,0.0001044808,0.0000063321845,0.000020419937,0.00011330411],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.8314874,0.045331642,0.11713217,0.0017848423,0.0030190984,0.0012448048],"domain_scores_gemma":[0.08131704,0.77061415,0.14266999,0.0013813946,0.003517926,0.0004994889],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6498553,0.00043375193,0.022148954,0.00041235698,0.000166675,0.000037126185,0.001384899,0.00046182142,0.000024763285],"category_scores_gemma":[0.96221954,0.00024609207,0.0036373085,0.0010737112,0.0003754799,0.00011304158,0.00039170854,0.0017695636,0.00003332535],"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":[0.00005799348,0.0001306095,0.0035521481,0.08411906,0.00022507191,0.000027073122,0.000011899263,0.00016322808,4.4207376e-9,0.00096053345,0.110773236,0.79997915],"study_design_scores_gemma":[0.0003344443,0.0007391296,0.0010634398,0.6029842,0.00014986702,0.00003303307,0.00004070553,0.000032081018,5.7618887e-9,0.0476238,0.34682253,0.00017677006],"about_ca_topic_score_codex":0.000010810178,"about_ca_topic_score_gemma":0.000093789786,"teacher_disagreement_score":0.79980236,"about_ca_system_score_codex":0.0004092932,"about_ca_system_score_gemma":0.0049481285,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W4381337491","doi":"10.1016/j.jclinepi.2023.06.010","title":"Grading of recommendations assessment, development, and evaluation concept article 5: addressing intransitivity in a network meta-analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":59,"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; University Health Network; Impact","funders":"","keywords":"Grading (engineering); Credibility; Certainty; Actuarial science; Trustworthiness; Computer science; Psychology; Economics; Epistemology; Social psychology; Engineering","score_opus":0.8774142831912617,"score_gpt":0.7153976569688053,"score_spread":0.16201662622245638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381337491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9670835,0.0013258095,0.014498116,0.015302867,0.0006595213,0.0003139334,0.000009198433,0.000009775192,0.000797271],"genre_scores_gemma":[0.9810327,0.00018463755,0.017786961,0.0007354636,0.00015460346,0.000020953637,0.000014644076,0.00000722591,0.00006278],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9744258,0.019960938,0.0045900564,0.00027551653,0.0002878866,0.0004598191],"domain_scores_gemma":[0.96301866,0.03429964,0.0020808047,0.00018688513,0.00019651168,0.00021748037],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09739793,0.00010333341,0.0024044705,0.00036648777,0.00007747413,0.0000057046173,0.00014505265,0.00019718515,0.0011621354],"category_scores_gemma":[0.011024934,0.00008157236,0.000516791,0.0008467702,0.00019987077,0.00011623484,0.000057640733,0.0008444245,0.0000065601107],"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":[0.00023283543,0.00037161572,0.7464035,0.0000449885,0.025671516,0.000033442477,0.0010993707,0.004331195,0.000011308721,0.00676175,0.0052447594,0.20979372],"study_design_scores_gemma":[0.0011543643,0.00023269483,0.9688226,0.000023756065,0.006184559,0.000009618249,0.00033988137,0.013933795,0.000009224883,0.008095084,0.0011197334,0.00007468484],"about_ca_topic_score_codex":0.00006398139,"about_ca_topic_score_gemma":0.00024264479,"teacher_disagreement_score":0.22241911,"about_ca_system_score_codex":0.00006631625,"about_ca_system_score_gemma":0.0002638439,"threshold_uncertainty_score":0.9997509},"labels":[],"label_agreement":null},{"id":"W4382045038","doi":"10.1016/j.jclinepi.2023.06.013","title":"Definitions, acceptability, limitations, and guidance in the use and reporting of surrogate end points in trials: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Women's College Hospital; University of Toronto","funders":"National Heart, Lung, and Blood Institute; Medical Research Council; Agency for Healthcare Research and Quality; Cancer Research UK; University of Bristol; National Institute for Health and Care Research; NIHR Bristol Biomedical Research Centre; Manchester Biomedical Research Centre; UK Research and Innovation","keywords":"Medicine; Medical physics; MEDLINE; Political science","score_opus":0.9842358688507592,"score_gpt":0.7174358125071572,"score_spread":0.26680005634360204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382045038","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":[0.001063912,0.9776912,0.00015350431,0.018799331,0.0005058223,0.0016444043,0.000094308234,0.000004416498,0.000043125492],"genre_scores_gemma":[0.00006582749,0.98637533,0.0072638947,0.0058758166,0.00028053674,0.00009458357,0.000015542733,0.000024132045,0.0000043075197],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.7370298,0.07546695,0.18563126,0.0010526489,0.00017988992,0.0006394728],"domain_scores_gemma":[0.14469503,0.6673225,0.18664852,0.0008456748,0.00024835108,0.00023993378],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6875751,0.00027887354,0.021262871,0.00062375894,0.000054011423,0.000028485485,0.00038339844,0.0005277116,0.000037820708],"category_scores_gemma":[0.9333426,0.00021978316,0.0011346727,0.00040128504,0.00029321844,0.00037108874,0.00011965458,0.001264227,0.000024503177],"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":[0.000047552432,0.00033824792,0.39058688,0.32670423,0.0005007049,0.00004467861,0.0005320847,0.000031762447,2.136183e-9,0.05092857,0.006862898,0.22342236],"study_design_scores_gemma":[0.0016247039,0.00034645112,0.16580875,0.56089336,0.00038314515,0.0003190802,0.00023960262,0.00018605797,2.3331492e-9,0.10820662,0.16147518,0.00051702285],"about_ca_topic_score_codex":0.00023515894,"about_ca_topic_score_gemma":0.00049375923,"teacher_disagreement_score":0.59233475,"about_ca_system_score_codex":0.00013274749,"about_ca_system_score_gemma":0.0008562718,"threshold_uncertainty_score":0.9932675},"labels":[],"label_agreement":null},{"id":"W4383340853","doi":"10.1016/j.jclinepi.2023.06.022","title":"Noninferiority margins exceed superiority effect estimates for mortality in cardiovascular trials in high-impact journals","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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":"Impact; McMaster University","funders":"","keywords":"Interquartile range; Medicine; Clinical trial; MEDLINE; Sample size determination; Guideline; Relative risk; Emergency medicine; Confidence interval; Internal medicine; Statistics","score_opus":0.9328234368721308,"score_gpt":0.7624042600171351,"score_spread":0.17041917685499564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383340853","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":[0.0053280653,0.9414306,0.037866496,0.00024503632,0.009078824,0.005201507,0.00077315985,0.000056480552,0.000019808695],"genre_scores_gemma":[0.000062881496,0.789308,0.20575336,0.00006745306,0.00442404,0.00019777768,0.000010825884,0.00016703,0.000008605645],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6475059,0.2729521,0.07438421,0.0017622056,0.0012994948,0.0020960877],"domain_scores_gemma":[0.050098963,0.92207694,0.024547314,0.0016224551,0.00063629675,0.0010180115],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.7395143,0.0014140132,0.113592744,0.0011833259,0.00008003793,0.0000680063,0.0017495438,0.0045402357,0.0001927017],"category_scores_gemma":[0.98679507,0.0008746926,0.03036405,0.00119887,0.0007137425,0.00019467577,0.00038865057,0.007734035,0.00003341947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017910018,0.0011281467,0.14243089,0.04082409,0.017763654,0.001060985,0.000019772016,0.00013813899,1.793202e-7,0.004798367,0.0014351443,0.7886096],"study_design_scores_gemma":[0.008175476,0.0028235626,0.08639856,0.033172816,0.016249552,0.00019191578,0.000005699272,0.00015174785,2.9438218e-7,0.83022594,0.021695266,0.00090919435],"about_ca_topic_score_codex":0.00026020894,"about_ca_topic_score_gemma":0.00007190728,"teacher_disagreement_score":0.82542753,"about_ca_system_score_codex":0.00065438886,"about_ca_system_score_gemma":0.0020103308,"threshold_uncertainty_score":0.999861},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4383371524","doi":"10.1016/j.jclinepi.2023.06.018","title":"A multimethods randomized trial found that plain language versions improved parents’ understanding of health recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","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":"Western University; University of Toronto; Glycemic Index Laboratories; SickKids Foundation; Hospital for Sick Children; McMaster University; Canadian Arthritis Patient Alliance; Institute for Clinical Evaluative Sciences; Impact; Cochrane; University of Alberta","funders":"Canadian Institutes of Health Research; Children's Hospital Foundation; Stollery Children’s Hospital Foundation","keywords":"Randomized controlled trial; Plain language; Medicine; Guideline; Usability; Family medicine; Surgery","score_opus":0.6997567476202897,"score_gpt":0.6848635253824568,"score_spread":0.01489322223783296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383371524","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":[0.41845188,0.00035718587,0.49273366,0.06699444,0.016366022,0.003530465,0.0001037875,0.000104316474,0.001358257],"genre_scores_gemma":[0.84609306,0.0037421929,0.11928997,0.028017903,0.0019251045,0.00011464603,0.00016992299,0.000039396455,0.00060780795],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8992763,0.07782581,0.021491658,0.00028626874,0.00028676435,0.00083316874],"domain_scores_gemma":[0.7679377,0.2151858,0.015763372,0.0003562542,0.00030769917,0.0004491424],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26618612,0.00016604319,0.004123122,0.00038169112,0.00058770186,0.0000048403867,0.00034039043,0.000492077,0.0005620201],"category_scores_gemma":[0.24857433,0.00011192342,0.0009338485,0.0004181533,0.0002972953,0.00044757596,0.00013689547,0.0020569956,0.000044126667],"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":[0.6962493,0.0006633114,0.13329819,0.0011970961,0.0006142325,0.000004193316,0.015024428,0.00014828071,0.0000057317966,0.013069009,0.06918235,0.07054385],"study_design_scores_gemma":[0.8686273,0.0013129952,0.02048048,0.0009359309,0.000097653654,0.000004141824,0.023322525,0.03642081,8.0675915e-7,0.025565356,0.023026764,0.00020522795],"about_ca_topic_score_codex":0.00029343125,"about_ca_topic_score_gemma":0.00003372893,"teacher_disagreement_score":0.42764118,"about_ca_system_score_codex":0.00026501477,"about_ca_system_score_gemma":0.0014739168,"threshold_uncertainty_score":0.89367366},"labels":[],"label_agreement":null},{"id":"W4383371693","doi":"10.1016/j.jclinepi.2023.06.023","title":"Limited online training opportunities exist for scholarly peer reviewers","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Academic Publishing and Open Access","field":"Decision Sciences","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Publishing; Peer review; Medical education; Training (meteorology); Quality (philosophy); Computer science; MEDLINE; Post hoc; Psychology; World Wide Web; Medicine; Political science","score_opus":0.9589372395936933,"score_gpt":0.7114604917111403,"score_spread":0.24747674788255292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383371693","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":[0.000015074133,0.960927,0.0026078853,0.024313923,0.010269821,0.0005757911,0.0003752355,0.00003976995,0.0008754809],"genre_scores_gemma":[0.0000010174732,0.95969,0.010478146,0.006949474,0.008292993,0.00002532278,0.00013176132,0.000087533896,0.0143437665],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9140108,0.03430177,0.045604747,0.0015633143,0.0031843893,0.0013349452],"domain_scores_gemma":[0.1884265,0.7402883,0.058641262,0.0019278707,0.0087517155,0.0019643584],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.47191012,0.0006697355,0.021773411,0.0013731492,0.00022684988,0.0007285985,0.008325898,0.002887493,0.00014142095],"category_scores_gemma":[0.94404465,0.00037914363,0.0077209766,0.0013177313,0.00069988746,0.0025124464,0.00067073375,0.008193637,0.00016120836],"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":[0.000035154884,0.000038405527,0.00011980947,0.0007081788,0.00028753604,0.000037447448,0.000026626923,0.0000033497172,1.0419984e-9,0.0013978934,0.2880308,0.70931476],"study_design_scores_gemma":[0.00044503223,0.0003739085,0.00012545496,0.010855188,0.00078799785,0.00023557118,0.00050694565,0.000043910724,1.1241312e-9,0.058501497,0.9277923,0.0003321936],"about_ca_topic_score_codex":0.000008766137,"about_ca_topic_score_gemma":0.000008425837,"teacher_disagreement_score":0.7255843,"about_ca_system_score_codex":0.00010569811,"about_ca_system_score_gemma":0.0039631017,"threshold_uncertainty_score":0.99986607},"labels":[],"label_agreement":null},{"id":"W4384207768","doi":"10.1016/j.jclinepi.2023.07.003","title":"A novel framework for incorporating patient values and preferences in making guideline recommendations: guideline panel surveys","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"University of Toronto; McMaster University; Impact","funders":"Einstein Stiftung Berlin","keywords":"Guideline; Medicine; Family medicine; Psychology; Pathology","score_opus":0.8110788834820947,"score_gpt":0.6463043998392362,"score_spread":0.16477448364285852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384207768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23734452,0.0039960016,0.4369599,0.30847427,0.009609333,0.0029595185,0.00024341771,0.00015797676,0.00025506574],"genre_scores_gemma":[0.37574425,0.0014998008,0.608154,0.013381268,0.00091555103,0.00014261757,0.000108056505,0.000031106738,0.000023328672],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9583139,0.023993019,0.016391007,0.00041845802,0.00023366268,0.00064998865],"domain_scores_gemma":[0.7781821,0.20775607,0.011299854,0.0006126585,0.0018523965,0.00029692872],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07265286,0.00020829716,0.001964478,0.00037010302,0.00041890988,0.000006196671,0.0004971032,0.000716401,0.000054362987],"category_scores_gemma":[0.38863447,0.00016448155,0.00023726062,0.00048306707,0.00018423786,0.00019354552,0.00043048285,0.0024149537,0.000013959954],"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":[0.00027448378,0.00016312116,0.82088614,0.00021984856,0.00006727554,0.0000021296757,0.0019965842,0.00074819394,0.000005875863,0.0072746184,0.03361719,0.13474451],"study_design_scores_gemma":[0.0025783307,0.0013732008,0.28215033,0.0028595433,0.000040377552,0.000011713712,0.012928818,0.038157366,6.5432175e-7,0.63897455,0.020645762,0.00027938257],"about_ca_topic_score_codex":0.00024600854,"about_ca_topic_score_gemma":0.0003217677,"teacher_disagreement_score":0.6316999,"about_ca_system_score_codex":0.00011404706,"about_ca_system_score_gemma":0.00080460345,"threshold_uncertainty_score":0.9998865},"labels":[],"label_agreement":null},{"id":"W4384945722","doi":"10.1016/j.jclinepi.2023.07.005","title":"Heterogeneous methodology in the development of patient versions of clinical practice guidelines: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":19,"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":"Readability; Terminology; MEDLINE; Relevance (law); Guideline; Dissemination; Medicine; Medical education; Best practice; Computer science; Pathology; Political science","score_opus":0.9589733681723968,"score_gpt":0.7856833721932245,"score_spread":0.17328999597917227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384945722","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":[0.00017207008,0.97865623,0.0026891632,0.013383131,0.002565294,0.0024520599,0.000014395349,0.000009568828,0.000058106703],"genre_scores_gemma":[0.000003872665,0.7393809,0.24620186,0.013441546,0.0008502485,0.000034326615,0.000039035433,0.000042537937,0.000005666894],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7398677,0.10671757,0.14968634,0.0011980078,0.0016258947,0.00090451195],"domain_scores_gemma":[0.121158384,0.7880799,0.08377553,0.0015104269,0.0049461676,0.00052959577],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3381482,0.0005143288,0.021753928,0.00044512484,0.000046574616,0.0000031843151,0.0009207641,0.0012968638,0.000111374015],"category_scores_gemma":[0.933913,0.0002958804,0.004912288,0.0008753819,0.00047036126,0.00013361026,0.00041980014,0.0040873,0.00004566053],"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":[0.00055252545,0.0008162158,0.0004353074,0.049903303,0.0013584791,0.00019591513,0.00006829904,0.000017652692,4.9748206e-8,0.000047686175,0.007810337,0.93879426],"study_design_scores_gemma":[0.0015085594,0.0024560615,0.00018441536,0.31005362,0.0062660887,0.0013966834,0.00030607398,0.000016552833,1.6302023e-7,0.00021000758,0.6774089,0.00019290732],"about_ca_topic_score_codex":0.000039709314,"about_ca_topic_score_gemma":0.00006777315,"teacher_disagreement_score":0.9386013,"about_ca_system_score_codex":0.000099778146,"about_ca_system_score_gemma":0.009116762,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4385077234","doi":"10.1016/j.jclinepi.2023.07.008","title":"Meta-research studies on reporting should transparently report core elements of data collection and results: authors' reply","year":2023,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; St. Joseph’s Healthcare Hamilton; McGill University; McMaster University; Jewish General Hospital","funders":"","keywords":"Core (optical fiber); Data collection; Meta-analysis; Computer science; Medicine; Psychology; Data science; Statistics; Mathematics; Pathology","score_opus":0.9956534469957802,"score_gpt":0.793795361559828,"score_spread":0.20185808543595218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385077234","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073809354,0.004725973,0.0020461734,0.97698444,0.00682959,0.0011149442,0.00024457966,0.000007978217,0.00066536135],"genre_scores_gemma":[0.009411174,0.02824603,0.13297647,0.63185024,0.027108664,0.00017808411,0.0010937979,0.00032180888,0.16881374],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.14212218,0.34543812,0.48483628,0.0060317395,0.02015272,0.00141896],"domain_scores_gemma":[0.018616611,0.5907941,0.3698374,0.0100985225,0.010268207,0.00038514836],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.9503967,0.0006041128,0.04027416,0.0015819516,0.00026384566,0.000115162766,0.0041330284,0.0013563309,0.00037394415],"category_scores_gemma":[0.98259544,0.00025939604,0.007799677,0.001957232,0.0008161669,0.0002558041,0.0007890378,0.0073086065,0.00008057322],"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":[0.0001755655,0.000058444635,0.027231148,0.00022745461,0.014178593,0.0016950808,0.00010484624,0.000053702384,6.56537e-7,0.00003245968,0.95355606,0.00268601],"study_design_scores_gemma":[0.00051295164,0.0012141506,0.007696767,0.00055881025,0.008041244,0.0007493494,0.00041449524,0.001464411,8.7693076e-7,0.024904946,0.95421904,0.00022293789],"about_ca_topic_score_codex":0.000058836176,"about_ca_topic_score_gemma":0.00006277135,"teacher_disagreement_score":0.34513423,"about_ca_system_score_codex":0.00006699638,"about_ca_system_score_gemma":0.00066111545,"threshold_uncertainty_score":0.9999858},"labels":[],"label_agreement":null},{"id":"W4385307760","doi":"10.1016/j.jclinepi.2023.07.010","title":"Sensitivity and specificity of alternative screening methods for systematic reviews using text mining tools","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Hotchkiss Brain Institute; Jewish General Hospital; Université de Montréal; Université Laval; University of Calgary; McGill University; Centre Hospitalier de l’Université de Montréal; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"National Institute of Neurological Disorders and Stroke; National Institute on Aging","keywords":"Medicine; Confidence interval; Sensitivity (control systems); Systematic review; Medical physics; Data mining; MEDLINE; Internal medicine; Computer science; Chemistry","score_opus":0.9742278341042131,"score_gpt":0.7450335572344855,"score_spread":0.2291942768697276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385307760","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17465706,0.0022560845,0.8203869,0.0008500405,0.0007277561,0.0010170201,0.000008895702,0.0000019196882,0.00009433066],"genre_scores_gemma":[0.0898124,0.0009866832,0.9075567,0.0006700109,0.0006659159,0.0000115880175,0.0000011287868,0.0000146892835,0.00028086884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.434616,0.461454,0.10008724,0.0012278316,0.002005875,0.00060903904],"domain_scores_gemma":[0.11279747,0.8034095,0.07945078,0.0015474221,0.0024483416,0.00034648902],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.87594604,0.00028140278,0.02514868,0.0004833008,0.000097640295,0.00008511445,0.0007950637,0.00023103201,0.00013864682],"category_scores_gemma":[0.94109654,0.00012535726,0.0057461155,0.0008714818,0.0002413827,0.00027201048,0.00019914322,0.00043173428,0.000037055303],"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":[0.0002761732,0.00015251932,0.26119536,0.011442836,0.0026428904,0.00004757574,0.0008529164,0.005305608,0.0007756126,0.006415115,0.020713132,0.69018024],"study_design_scores_gemma":[0.00105047,0.0006611373,0.10400921,0.009443421,0.0018202015,0.00037143053,0.0015081671,0.82504475,0.00004653612,0.035425093,0.020240534,0.00037906354],"about_ca_topic_score_codex":0.0000064757146,"about_ca_topic_score_gemma":0.0000046724326,"teacher_disagreement_score":0.8197391,"about_ca_system_score_codex":0.000017470913,"about_ca_system_score_gemma":0.00007628974,"threshold_uncertainty_score":0.98932403},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4385336299","doi":"10.1016/j.jclinepi.2023.07.013","title":"Using evidence to decision frameworks led to guidelines of better quality and more credible and transparent recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; McMaster University; University of Saskatchewan","funders":"Andrew W. Mellon Foundation; National Health and Medical Research Council; Ministerio de Salud y Protección Social; Kaiser Permanente; Norwegian Institute of Public Health; Kidney Health Australia","keywords":"Credibility; Grading (engineering); Guideline; Excellence; Quality (philosophy); Evidence-based medicine; Quality of evidence; Medicine; Medical education; Management science; Process management; Alternative medicine; Political science; Business; Randomized controlled trial; Engineering; Pathology","score_opus":0.9313615963995359,"score_gpt":0.7587076776635762,"score_spread":0.1726539187359597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385336299","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":[0.557525,0.00016770416,0.16115257,0.2804631,0.00049882964,0.0001772169,0.0000068976346,0.00000671807,0.0000019838124],"genre_scores_gemma":[0.4206022,0.0029142788,0.5182264,0.057270575,0.00094900804,0.0000037982797,0.0000059661556,0.000016514701,0.000011279591],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98709947,0.0020114377,0.009959703,0.0003487021,0.00031875283,0.00026196302],"domain_scores_gemma":[0.8609136,0.1339083,0.002752497,0.00035005002,0.0013815645,0.0006940162],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04855972,0.0001428049,0.0019824514,0.0002621223,0.00005495496,0.000007429943,0.00013133102,0.00036690466,0.00008515112],"category_scores_gemma":[0.5623843,0.00010684618,0.00027585978,0.00038552814,0.00014521324,0.00018997908,0.00013631325,0.0009262173,0.0000066736543],"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":[0.0025002845,0.0001149141,0.6525881,0.00008145375,0.00013707533,0.000014241471,0.00016051931,0.0017347868,0.00072706246,0.00008553186,0.035375774,0.3064802],"study_design_scores_gemma":[0.0019166276,0.0017600689,0.97099996,0.0017394046,0.00033652558,0.000093919596,0.00043433433,0.008060161,0.00002927865,0.0075986106,0.006902711,0.0001283893],"about_ca_topic_score_codex":0.00011415137,"about_ca_topic_score_gemma":0.00003806383,"teacher_disagreement_score":0.5138246,"about_ca_system_score_codex":0.000030594936,"about_ca_system_score_gemma":0.00018903604,"threshold_uncertainty_score":0.97970796},"labels":[],"label_agreement":null},{"id":"W4385336753","doi":"10.1016/j.jclinepi.2023.07.014","title":"Qualitative study of guideline panelists: innovative surveys provided valuable insights regarding patient values and preferences","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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; McMaster University; Impact","funders":"","keywords":"Guideline; Thematic analysis; Family medicine; Medicine; Data collection; Psychology; Applied psychology; Qualitative research; Medical education; Statistics","score_opus":0.7808433377963515,"score_gpt":0.658134440819534,"score_spread":0.12270889697681753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385336753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989583,0.0013046452,0.00038063334,0.0052511077,0.0017153291,0.0012967184,0.000022860006,0.000044362227,0.00040133006],"genre_scores_gemma":[0.9932264,0.0009473365,0.0038579607,0.0014421381,0.000300203,0.00008229154,0.000025716212,0.000023998866,0.00009393204],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.83238536,0.1486146,0.01726082,0.0005156272,0.00060086173,0.00062270614],"domain_scores_gemma":[0.78612226,0.19023332,0.015699226,0.0008522851,0.006714595,0.00037831563],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07170694,0.0002515881,0.0031386274,0.00046459248,0.00043340446,0.0000040007826,0.00057551323,0.00046733062,0.000041028918],"category_scores_gemma":[0.2720681,0.00017310196,0.00018907613,0.0010521548,0.0003675904,0.00028192965,0.00060102856,0.0022794968,0.000018652383],"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":[0.0007696287,0.000692966,0.6881849,0.00037818207,0.00046646484,0.000010271647,0.275638,0.00018702817,0.000014855694,0.002231041,0.020636942,0.010789692],"study_design_scores_gemma":[0.0037861853,0.006928433,0.32146987,0.00080338813,0.0000690208,0.000003378273,0.57414424,0.00092773733,0.0000049798455,0.09001144,0.0016401798,0.00021116891],"about_ca_topic_score_codex":0.0007425591,"about_ca_topic_score_gemma":0.00024728142,"teacher_disagreement_score":0.36671504,"about_ca_system_score_codex":0.00010881671,"about_ca_system_score_gemma":0.0011548195,"threshold_uncertainty_score":0.99034065},"labels":[],"label_agreement":null},{"id":"W4385431496","doi":"10.1016/j.jclinepi.2023.07.016","title":"Guidance needed: where should randomized studies which do not assess a health outcome be registered?","year":2023,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Clinical trial; Medicine; Psychological intervention; Randomized controlled trial; Medical journal; Family medicine; Trial registration; Alternative medicine; MEDLINE; Clinical research; Physical therapy; Nursing; Surgery; Pathology","score_opus":0.9796435229918886,"score_gpt":0.7449354040485212,"score_spread":0.2347081189433674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385431496","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037827587,0.028667245,0.013424934,0.9424729,0.012994928,0.0012342875,0.000056948214,0.000013411455,0.0007570708],"genre_scores_gemma":[0.00047792724,0.01737706,0.014857435,0.9212415,0.0129108885,0.00006135864,0.000012741384,0.00008453137,0.032976534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.1488931,0.58613443,0.24855901,0.0033677067,0.011316831,0.0017289143],"domain_scores_gemma":[0.026267989,0.7317395,0.2248434,0.007127282,0.009122843,0.0008989753],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.9070468,0.0012708748,0.11554287,0.0012351164,0.00024633517,0.00042713218,0.0073352093,0.0027708807,0.0023779217],"category_scores_gemma":[0.974589,0.0005261779,0.029956508,0.0018140267,0.0010058059,0.00029639588,0.0007558253,0.010108471,0.0015503953],"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":[0.0015390957,0.00004250559,0.014567946,0.0006636641,0.004842646,0.00018854816,0.000115404146,0.00011498028,3.5092633e-8,0.0005631102,0.9745939,0.0027682073],"study_design_scores_gemma":[0.013992378,0.00035566223,0.0018372544,0.0009428391,0.001524995,0.00015155622,0.00049688667,0.0006492858,1.5927725e-8,0.024182472,0.9554484,0.0004182688],"about_ca_topic_score_codex":0.000082345825,"about_ca_topic_score_gemma":0.00017002695,"teacher_disagreement_score":0.14560509,"about_ca_system_score_codex":0.00015968378,"about_ca_system_score_gemma":0.0014609407,"threshold_uncertainty_score":0.99971896},"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":"W4385652647","doi":"10.1016/j.jclinepi.2023.08.002","title":"Equity issues rarely addressed in the development of COVID-19 formal recommendations and good practice statements: a cross-sectional study","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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 Laval; Trent University; Queen's University; University of Alberta; University of Toronto; Western University; McMaster University; University of Calgary; Impact; University of British Columbia; Ottawa Hospital; Carleton University; Cochrane; Bruyère; University of Ottawa","funders":"Institute of Infection and Immunity; Canadian Institutes of Health Research","keywords":"Disadvantaged; Health equity; Guideline; Equity (law); Grading (engineering); Medicine; Psychology; Family medicine; Public health; Nursing; Political science; Economic growth; Economics","score_opus":0.9037043131901744,"score_gpt":0.7291295796426078,"score_spread":0.17457473354756659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385652647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8303393,0.00064481265,0.007788799,0.1589742,0.0011238819,0.0006299891,0.000094605166,0.000010949113,0.00039345733],"genre_scores_gemma":[0.9508037,0.001177978,0.020978821,0.026289737,0.00052463147,0.00006375107,0.000031933632,0.000014718686,0.0001147092],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96041167,0.010716538,0.027719645,0.00044659298,0.00019921277,0.0005063299],"domain_scores_gemma":[0.89716524,0.08799555,0.014095217,0.0002754053,0.00021188731,0.00025669573],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41896793,0.00012526127,0.0019198002,0.00035833943,0.00021344672,0.000032074262,0.00040862386,0.00018319153,0.000166983],"category_scores_gemma":[0.3401994,0.00010875253,0.0001759496,0.0002654031,0.00015216951,0.000821344,0.00017182369,0.0005983431,0.000092419046],"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":[0.00018544646,0.0005212335,0.96622074,0.00010099136,0.00018382262,0.0000031042334,0.0038295228,0.0005516248,8.26056e-8,0.01739847,0.010430461,0.000574485],"study_design_scores_gemma":[0.00220155,0.00050231745,0.89162767,0.000026462709,0.000008782529,0.000016094247,0.005903765,0.00061247055,8.257657e-8,0.026128758,0.07288029,0.0000917401],"about_ca_topic_score_codex":0.0003230763,"about_ca_topic_score_gemma":0.00035456676,"teacher_disagreement_score":0.13268447,"about_ca_system_score_codex":0.00023353483,"about_ca_system_score_gemma":0.0007601457,"threshold_uncertainty_score":0.66535836},"labels":[],"label_agreement":null},{"id":"W4385988710","doi":"10.1016/j.jclinepi.2023.08.001","title":"GRADE guidance 23: considering cost-effectiveness evidence in moving from evidence to health-related recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McMaster University; Impact; Health Sciences Centre; McMaster University Medical Centre","funders":"Donau-Universität Krems; Newcastle University; World Health Organization","keywords":"Grading (engineering); Guideline; Medicine; Quality of evidence; Evidence-based medicine; Systematic review; Medical physics; MEDLINE; Meta-analysis; Alternative medicine; Engineering; Pathology; Political science","score_opus":0.9087884855361407,"score_gpt":0.6563431720566189,"score_spread":0.2524453134795218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385988710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5526688,0.008496669,0.016205259,0.41822073,0.0034794984,0.0007933277,0.000058586073,0.000039595863,0.000037518155],"genre_scores_gemma":[0.9239447,0.007654225,0.022907998,0.04435236,0.0008703302,0.00011757913,0.000013748378,0.00004372125,0.0000953146],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9497237,0.019112596,0.029277623,0.00089002756,0.00013745212,0.00085855427],"domain_scores_gemma":[0.73708665,0.24921785,0.012426018,0.0005219536,0.00016866776,0.0005788793],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32136127,0.00023095382,0.0047870954,0.0007151852,0.00015261801,0.000028371045,0.0006189503,0.00036181725,0.00019514795],"category_scores_gemma":[0.59285665,0.00026342418,0.00045736338,0.00074935646,0.00014542877,0.00082636334,0.00016788639,0.0011192999,0.0015435929],"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":[0.000115860734,0.00008348347,0.9383641,0.0001812651,0.00010119025,0.0000145236645,0.0006535701,0.012299162,0.0000051125294,0.0077282465,0.037053894,0.0033996054],"study_design_scores_gemma":[0.0008700347,0.0003624273,0.9108609,0.0039738747,0.0000069400407,0.000018525574,0.00029684728,0.009186116,0.0000015731017,0.06221694,0.011971424,0.00023438208],"about_ca_topic_score_codex":0.002091142,"about_ca_topic_score_gemma":0.00053142925,"teacher_disagreement_score":0.37386835,"about_ca_system_score_codex":0.00083045027,"about_ca_system_score_gemma":0.0006743639,"threshold_uncertainty_score":0.9999818},"labels":[],"label_agreement":null},{"id":"W4386070913","doi":"10.1016/j.jclinepi.2023.08.006","title":"Depression screening tool accuracy individual participant data meta-analyses: data contribution was associated with multiple factors","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Treatment and Access","field":"Psychology","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 Health Centre; University of Calgary; McGill University; Jewish General Hospital","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; McGill University; Faculty of Medicine, McGill University; Alberta Innovates; Jewish General Hospital","keywords":"Medicine; Logistic regression; Depression (economics); Minimum Data Set; Odds; Data collection; Meta-analysis; Scale (ratio); Data set; Odds ratio; Gerontology; Statistics; Geography; Cartography","score_opus":0.9592418753023552,"score_gpt":0.7156088594511607,"score_spread":0.24363301585119446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386070913","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":[0.001320537,0.98826164,0.0016621522,0.00033819946,0.0021202508,0.0012383686,0.0049876603,0.00005676267,0.000014402482],"genre_scores_gemma":[0.005245032,0.96892923,0.001108655,0.0005388886,0.0012919123,0.00006481432,0.022566546,0.0001069818,0.00014791469],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95486337,0.02797871,0.013828532,0.0015121598,0.0006592101,0.0011580192],"domain_scores_gemma":[0.7463827,0.22631279,0.023367587,0.0030377198,0.00028469745,0.000614494],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06723867,0.00084057555,0.018074334,0.00034416612,0.0002858868,0.00005033955,0.0043854793,0.001662827,0.0006260567],"category_scores_gemma":[0.2477353,0.00041878695,0.002113202,0.0005633285,0.00030106504,0.0006969951,0.0018457822,0.0032912137,0.00011955921],"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":[0.00075647555,0.0014249001,0.07597771,0.001149705,0.16803688,0.0005492606,0.00005381154,0.000017830083,1.6757378e-8,0.000082756625,0.032249343,0.7197013],"study_design_scores_gemma":[0.0053504445,0.0014333768,0.08341235,0.008997515,0.33070558,0.00015988588,0.00014681809,0.0006082829,1.01261186e-7,0.00020348793,0.56807715,0.000905],"about_ca_topic_score_codex":0.00027923888,"about_ca_topic_score_gemma":0.00018999024,"teacher_disagreement_score":0.7187963,"about_ca_system_score_codex":0.000058938815,"about_ca_system_score_gemma":0.00046338115,"threshold_uncertainty_score":0.9998264},"labels":[],"label_agreement":null},{"id":"W4386214260","doi":"10.1016/j.jclinepi.2023.08.015","title":"Prospective collaborative recommendation development: a novel model for more timely and trustworthy guidelines","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Public Health Agency of Canada; McMaster University; Impact","funders":"","keywords":"Trustworthiness; Computer science; Medicine; Internet privacy","score_opus":0.7532961646152789,"score_gpt":0.6622177522709368,"score_spread":0.09107841234434211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386214260","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":[0.3839733,0.00017755982,0.38209957,0.23089568,0.001177281,0.0014126368,0.000069339665,0.00006293345,0.00013168376],"genre_scores_gemma":[0.20422982,0.00153769,0.7655739,0.025537198,0.0021111914,0.00007492876,0.00019996638,0.000054309738,0.00068099465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9904177,0.00059914467,0.008098786,0.00036948783,0.00019698513,0.00031787192],"domain_scores_gemma":[0.94876075,0.042843003,0.00468458,0.00017143546,0.0031798321,0.0003604141],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035800334,0.00018744459,0.0019173193,0.00020749804,0.00009871619,0.000008524112,0.00010006451,0.00029850318,0.00003358913],"category_scores_gemma":[0.34370407,0.00014084225,0.00031096436,0.00035696733,0.0001894858,0.0002500036,0.000078512225,0.00060927164,0.000012104593],"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":[0.011353397,0.0007132326,0.37666172,0.00017346506,0.0013061959,0.000019181054,0.0009384752,0.0039010493,0.00019601666,0.0023254205,0.16934678,0.4330651],"study_design_scores_gemma":[0.014520726,0.0021963234,0.31469125,0.00019094383,0.00050842913,0.00015925938,0.00090716494,0.58159965,0.00003032452,0.012678871,0.07226128,0.00025580588],"about_ca_topic_score_codex":0.000005170668,"about_ca_topic_score_gemma":0.00002104094,"teacher_disagreement_score":0.5776986,"about_ca_system_score_codex":0.000070820206,"about_ca_system_score_gemma":0.0011645467,"threshold_uncertainty_score":0.9928465},"labels":[],"label_agreement":null},{"id":"W4386248759","doi":"10.1016/j.jclinepi.2023.06.004","title":"Retraction notice to “Part II: a step-by-step guide to latent class analysis” [Journal of Clinical Epidemiology 148 (2022) 170–173]","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Notice; Attribution; Library science; Psychology; Medicine; Computer science; Law; Political science; Social psychology","score_opus":0.5656202302081994,"score_gpt":0.664009602187966,"score_spread":0.0983893719797666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386248759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68090034,0.0016045455,0.06436821,0.20522629,0.044201512,0.0011402672,0.00010925626,0.000076636585,0.0023729461],"genre_scores_gemma":[0.36512524,0.021273429,0.20694718,0.27471426,0.06468726,0.00018218842,0.00020075258,0.0004836175,0.06638607],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9000151,0.05934463,0.035210643,0.001457301,0.001311579,0.002660755],"domain_scores_gemma":[0.8304904,0.14780158,0.014292088,0.0014248342,0.0019470333,0.004044084],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.2731582,0.00055703573,0.009861611,0.0016753289,0.0002597859,0.000015789521,0.0018748131,0.0026324405,0.002311097],"category_scores_gemma":[0.3753061,0.00043535876,0.003673649,0.002507941,0.00059207436,0.00023959347,0.00065076066,0.008203622,0.0014173279],"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":[0.0038004925,0.00074976,0.3302126,0.00003991953,0.0018086577,0.00031095243,0.00005519499,0.000812727,0.000011090631,0.0014259673,0.6206695,0.040103167],"study_design_scores_gemma":[0.002243473,0.008533419,0.4243079,0.0001113644,0.0005310446,0.00025800586,0.00016403745,0.0012294385,0.0000021012154,0.0006585186,0.56172687,0.00023381242],"about_ca_topic_score_codex":0.00031976422,"about_ca_topic_score_gemma":0.0002626496,"teacher_disagreement_score":0.3157751,"about_ca_system_score_codex":0.0003820659,"about_ca_system_score_gemma":0.00097565737,"threshold_uncertainty_score":0.9998098},"labels":[],"label_agreement":null},{"id":"W4386648725","doi":"10.1016/j.jclinepi.2023.09.001","title":"Bias in the measurement of the outcome is associated with effect sizes in randomized clinical trials on exercise therapy for chronic low back pain: a meta-epidemiological study","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Ministero della Salute","keywords":"Medicine; Meta-analysis; Randomized controlled trial; Physical therapy; Publication bias; Confidence interval; Sample size determination; Psychological intervention; Generalizability theory; Reporting bias; Relative risk; MEDLINE; Internal medicine; Psychology; Statistics; Psychiatry","score_opus":0.984737622576596,"score_gpt":0.7406942209587761,"score_spread":0.2440434016178199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386648725","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002671266,0.9595707,0.0011488316,0.0055336813,0.0020097208,0.028978003,0.00004741468,0.000004276655,0.00003612974],"genre_scores_gemma":[0.0030238172,0.99042815,0.00039429415,0.0034700318,0.0007530496,0.0016517236,0.0000048273423,0.00005640254,0.00021772415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.034023967,0.78557223,0.17286031,0.0016987618,0.0051296707,0.0007150431],"domain_scores_gemma":[0.0061500072,0.82400465,0.16394497,0.003920841,0.0017198826,0.000259659],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.9929373,0.0014741712,0.2295196,0.0008424372,0.00010078297,0.00010838131,0.007089126,0.0017220624,0.00078975124],"category_scores_gemma":[0.99137914,0.0003232229,0.10215582,0.0026902414,0.0008551478,0.00007972129,0.00023170991,0.004366605,0.00013036141],"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":[0.030171108,0.003982589,0.077272974,0.0035757576,0.05817657,0.00005288494,0.00017946422,0.0005522222,1.0179136e-8,0.00019506445,0.046140548,0.7797008],"study_design_scores_gemma":[0.31994498,0.035566155,0.036177527,0.0605435,0.14219183,0.00004766651,0.0004736147,0.0050995923,1.038029e-7,0.031163182,0.36684284,0.0019490161],"about_ca_topic_score_codex":0.000019246421,"about_ca_topic_score_gemma":0.00017024406,"teacher_disagreement_score":0.7777518,"about_ca_system_score_codex":0.00019642377,"about_ca_system_score_gemma":0.0012156036,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4386893091","doi":"10.1016/j.jclinepi.2023.09.006","title":"GRADE concept 6: a novel application of external indirect evidence into GRADE ratings of evidence certainty in network meta-analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Hamilton Health Sciences; McMaster University; Impact","funders":"","keywords":"Certainty; Guideline; Grading (engineering); Meta-analysis; Medicine; Psychology; Computer science; Actuarial science; Mathematics; Engineering; Business","score_opus":0.9694566485824524,"score_gpt":0.7012974169378572,"score_spread":0.2681592316445952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386893091","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":[0.2834151,0.019968817,0.6796748,0.015484841,0.0005851089,0.0008274512,0.000011088851,0.000006014225,0.000026747184],"genre_scores_gemma":[0.94454324,0.0010494117,0.052983474,0.00087064825,0.00030063884,0.000027578291,0.000001698219,0.000010241874,0.00021306681],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6796817,0.17608318,0.13364877,0.0023938806,0.0071433084,0.0010491062],"domain_scores_gemma":[0.47243997,0.44428545,0.077590674,0.002809845,0.0024884322,0.00038562308],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6472622,0.0003751207,0.029295217,0.0011625934,0.00006184769,0.00004549619,0.003337178,0.0003871818,0.00092165923],"category_scores_gemma":[0.72839355,0.00016766417,0.017112935,0.0069943895,0.00055941305,0.00043594866,0.00030008194,0.0009673772,0.000068861955],"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":[0.00013309075,0.00020840563,0.8661839,0.000097555996,0.02095654,0.000009467068,0.00049466436,0.09449639,0.0004000878,0.002076931,0.0061004576,0.008842525],"study_design_scores_gemma":[0.0005659109,0.00063244574,0.66686356,0.00032653988,0.05686978,0.000032098244,0.00030676654,0.19904009,0.00006299847,0.07322706,0.0017737221,0.00029905527],"about_ca_topic_score_codex":0.000278811,"about_ca_topic_score_gemma":0.00023655783,"teacher_disagreement_score":0.66112816,"about_ca_system_score_codex":0.000042124193,"about_ca_system_score_gemma":0.00027182745,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W4387122268","doi":"10.1016/j.jclinepi.2023.09.011","title":"GRADE GUIDANCE 38: Updated guidance for rating up certainty of evidence due to a dose-response gradient","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Effects of Radiation Exposure","field":"Medicine","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":"McMaster University; Impact","funders":"","keywords":"Grading (engineering); Credibility; Medicine; Confounding; Certainty; Rating system; Medical physics; Internal medicine","score_opus":0.41878370046278457,"score_gpt":0.5544819225724799,"score_spread":0.1356982221096953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387122268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8667996,0.0007247912,0.0109940525,0.11866681,0.00204979,0.0006919732,0.000015872994,0.000042657855,0.000014429727],"genre_scores_gemma":[0.9538521,0.00023822031,0.0339358,0.010150127,0.0011821411,0.000034659453,0.000006924471,0.00003645318,0.0005635845],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98537105,0.0066212537,0.0065576257,0.00044797582,0.00039896107,0.00060311693],"domain_scores_gemma":[0.88445514,0.10930275,0.0040191053,0.0005261257,0.0010710848,0.0006258078],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07461669,0.00023489197,0.0031226499,0.00034017977,0.000070164155,0.0000050754866,0.0004343337,0.00048624596,0.00003834333],"category_scores_gemma":[0.570517,0.0001615049,0.0009858956,0.00062967004,0.00024162506,0.000118941025,0.00008897239,0.0010012507,0.000038513826],"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":[0.051737536,0.00049582025,0.3992847,0.0007747577,0.000875328,0.0005402206,0.00072618265,0.013795945,0.022500888,0.0030044455,0.4838394,0.022424797],"study_design_scores_gemma":[0.0055286544,0.010468187,0.9365235,0.0018116921,0.00020414521,0.00041271793,0.00011553729,0.012299599,0.0008805551,0.0033565862,0.028156672,0.00024214594],"about_ca_topic_score_codex":0.000016842641,"about_ca_topic_score_gemma":0.0000073053593,"teacher_disagreement_score":0.53723884,"about_ca_system_score_codex":0.00009871989,"about_ca_system_score_gemma":0.00055609,"threshold_uncertainty_score":0.95287687},"labels":[],"label_agreement":null},{"id":"W4387191064","doi":"10.1016/j.jclinepi.2023.09.013","title":"Critical elements of synthesis questions are incompletely reported: survey of systematic reviews of intervention effects","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Medical Research Council; Department of Education and Training; Monash University; Department of Health and Social Care; National Institute for Health and Care Research; Australian Government; National Health and Medical Research Council; McMaster University","keywords":"Psychological intervention; Systematic review; Intervention (counseling); Medicine; Population; Public health; MEDLINE; Family medicine; Environmental health; Nursing","score_opus":0.9592008098824275,"score_gpt":0.7219751309475064,"score_spread":0.23722567893492108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387191064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8874824,0.009421575,0.09441263,0.0024104824,0.0035148687,0.0023050886,0.0000928155,0.000006433693,0.0003537038],"genre_scores_gemma":[0.9906048,0.0011826821,0.0078490535,0.00011299131,0.00008551082,0.000026568598,0.0000031434722,0.000009750319,0.00012546487],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2968544,0.49912512,0.19857164,0.0009248796,0.0040503675,0.00047359738],"domain_scores_gemma":[0.04974025,0.7758551,0.16331394,0.003175732,0.0075680036,0.0003469708],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.81028855,0.00024987577,0.028415171,0.00072206825,0.000035975554,0.000018987035,0.0016056166,0.00027118617,0.00089548394],"category_scores_gemma":[0.98736,0.00011632321,0.008053288,0.0015532176,0.00036088657,0.00015382617,0.00018455082,0.00043823084,0.00018287823],"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":[0.0000683504,0.00043985323,0.9432697,0.024070162,0.0011982489,0.000019516825,0.000028489181,0.000062876155,0.00003506916,0.0016071858,0.02178929,0.0074112057],"study_design_scores_gemma":[0.00026513156,0.0005469807,0.96592695,0.014861113,0.0014377537,0.000045439618,0.00009716811,0.002879249,0.00001686461,0.013347196,0.0004806281,0.00009550568],"about_ca_topic_score_codex":0.00006458075,"about_ca_topic_score_gemma":0.00006194881,"teacher_disagreement_score":0.27672997,"about_ca_system_score_codex":0.000019465466,"about_ca_system_score_gemma":0.00010493616,"threshold_uncertainty_score":0.986009},"labels":[],"label_agreement":null},{"id":"W4387345752","doi":"10.1016/j.jclinepi.2023.09.017","title":"Using PROGRESS-plus to identify current approaches to the collection and reporting of equity-relevant data: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Institute for Clinical Evaluative Sciences; SickKids Foundation; University of Toronto; Hospital for Sick Children; Bruyère; University of Ottawa","funders":"National Health and Medical Research Council; Canada Research Chairs; Medical Research Council; International Association for the Study of Pain","keywords":"Data collection; Equity (law); Data science; Medicine; Psychology; Actuarial science; Computer science; Political science; Business; Statistics; Mathematics","score_opus":0.9868645337259441,"score_gpt":0.8021220626612051,"score_spread":0.18474247106473896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387345752","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":[0.00004936413,0.97771305,0.0014748843,0.01044205,0.0053946953,0.004813106,0.00007020132,0.000017384787,0.000025241678],"genre_scores_gemma":[0.000008564245,0.9890667,0.0070651635,0.0013399668,0.0023068837,0.00011294351,0.00003968244,0.000037464175,0.000022601227],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.94715714,0.018390335,0.03260539,0.0006806286,0.00043770822,0.0007287867],"domain_scores_gemma":[0.8638729,0.061033625,0.07189588,0.0015171958,0.00078594714,0.00089447986],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17016579,0.0003229693,0.010677672,0.00035398532,0.00070144236,0.000009290887,0.0009496457,0.00069812307,0.000022834862],"category_scores_gemma":[0.36041388,0.00019592707,0.0008287016,0.0009480532,0.00019429646,0.00013387985,0.0022574647,0.0038964867,0.00004212493],"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":[0.00006376488,0.00007797587,0.0023416865,0.43701735,0.0002866695,0.000012297303,0.00028819102,0.000038862217,4.594997e-9,0.0009570496,0.022365982,0.53655016],"study_design_scores_gemma":[0.00018180966,0.00021977797,0.0006796228,0.6240864,0.0012137792,0.000061190185,0.000083084815,0.00024382336,1.3290045e-9,0.00063776464,0.37244886,0.00014387522],"about_ca_topic_score_codex":0.000088128,"about_ca_topic_score_gemma":0.00029772279,"teacher_disagreement_score":0.5364063,"about_ca_system_score_codex":0.00022811028,"about_ca_system_score_gemma":0.0050294027,"threshold_uncertainty_score":0.9984016},"labels":[],"label_agreement":null},{"id":"W4387675649","doi":"10.1016/j.jclinepi.2023.10.002","title":"The design of studies testing the effectiveness of risk-guided care has many challenges: a scoping review addressing key considerations","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Frailty in Older Adults","field":"Medicine","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":"McMaster University; University Health Network; Impact; Ted Rogers Centre for Heart Research","funders":"Heart and Stroke Foundation of Canada","keywords":"Observational study; Medicine; Credibility; Clinical study design; Research design; MEDLINE; Randomized controlled trial; Confounding; Health care; Risk assessment; Risk analysis (engineering); Intensive care medicine; Clinical trial; Computer science","score_opus":0.8931984535015859,"score_gpt":0.6424903210268235,"score_spread":0.2507081324747624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387675649","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":[0.00000812001,0.9916274,0.0008108137,0.003508531,0.0012290318,0.0027356895,0.000012633963,0.000018144186,0.00004964609],"genre_scores_gemma":[0.00009691311,0.9926958,0.0059518707,0.00027938696,0.0008114217,0.000096098775,0.0000031766633,0.000059752674,0.0000055636933],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9237306,0.061846435,0.01311779,0.0004420412,0.0004263356,0.00043678598],"domain_scores_gemma":[0.19890583,0.7777148,0.019375969,0.0009562153,0.0028646782,0.00018255724],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12664376,0.00047728088,0.015233828,0.00016149045,0.00032318832,0.000009330979,0.0005152998,0.0005719336,0.0000053370995],"category_scores_gemma":[0.8422599,0.00021630517,0.0023415496,0.00037309722,0.0017717846,0.000054307893,0.0002460295,0.00275564,0.0000068425193],"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":[0.00012139031,0.00008437366,0.00035060348,0.5526605,0.003877718,0.00010169841,0.00028890345,0.00020929886,2.0402248e-7,0.00043789754,0.002053438,0.43981397],"study_design_scores_gemma":[0.00086258847,0.00096400053,0.00092266954,0.9791654,0.007303987,0.00088024803,0.0002603815,0.00003332387,4.2237465e-7,0.0038423727,0.0056009726,0.0001636644],"about_ca_topic_score_codex":0.000018373137,"about_ca_topic_score_gemma":0.000022693595,"teacher_disagreement_score":0.7248248,"about_ca_system_score_codex":0.00011996627,"about_ca_system_score_gemma":0.0029738422,"threshold_uncertainty_score":0.99954504},"labels":[],"label_agreement":null},{"id":"W4387737038","doi":"10.1016/j.jclinepi.2023.10.006","title":"International variation in ethics and contract approval processes for a low-risk observational study of mechanical ventilation discontinuation practices","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in medical practice","field":"Health Professions","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 Toronto; McMaster University; Impact; St. Joseph’s Healthcare Hamilton; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Groupe canadien de recherche en soins intensifs","keywords":"Discontinuation; Observational study; Ethics committee; Medicine; Research ethics; Mechanical ventilation; Family medicine; Emergency medicine; Political science; Internal medicine; Public administration","score_opus":0.7837712543626965,"score_gpt":0.7059176001807144,"score_spread":0.07785365418198209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387737038","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":[0.9319763,0.000046575307,0.02588972,0.038474668,0.0026337884,0.0008781199,0.000015684545,0.000014103478,0.000071009774],"genre_scores_gemma":[0.9854289,0.0014025619,0.01051923,0.0012299691,0.0012874695,0.000064791864,0.000021888189,0.000013851957,0.0000312828],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9567632,0.034558427,0.0073554097,0.00036965674,0.0006412028,0.00031210828],"domain_scores_gemma":[0.45783377,0.5239665,0.015863605,0.0001470487,0.002068892,0.00012023313],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23574997,0.00011609093,0.0011741071,0.0002155054,0.00026906922,0.000006377025,0.0002683119,0.00086345203,0.0000328158],"category_scores_gemma":[0.91936326,0.00009184494,0.000121295365,0.00031878092,0.00014452756,0.000585074,0.00010472888,0.0069400202,0.000004042964],"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":[0.0029845282,0.0012983573,0.96678936,0.0003611457,0.00021868736,0.0000042494244,0.0048410953,0.00063406595,0.00006946273,0.017415706,0.00043937983,0.004943982],"study_design_scores_gemma":[0.0036743681,0.0011083226,0.8913775,0.00031046444,0.00012785295,0.0000030522435,0.0028430766,0.015562311,0.0000011957975,0.08359504,0.0013267994,0.000070027214],"about_ca_topic_score_codex":0.00020674767,"about_ca_topic_score_gemma":0.00067353214,"teacher_disagreement_score":0.68361324,"about_ca_system_score_codex":0.000054740973,"about_ca_system_score_gemma":0.0011325243,"threshold_uncertainty_score":0.995351},"labels":[],"label_agreement":null},{"id":"W4387844508","doi":"10.1016/j.jclinepi.2023.10.012","title":"Prevalence of patient partner authorship and acknowledgment in child health research publications: an umbrella review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":10,"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; Ottawa Hospital; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; SickKids Foundation; Glycemic Index Laboratories; University of Toronto; Trillium Health Centre","funders":"Canadian Institutes of Health Research","keywords":"CINAHL; PsycINFO; MEDLINE; Systematic review; Medicine; Family medicine; Alternative medicine; Nursing; Psychological intervention; Pathology; Political science","score_opus":0.9546587978454939,"score_gpt":0.7624042185403881,"score_spread":0.1922545793051058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387844508","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":[0.00021390208,0.9874643,0.000008388638,0.006000209,0.0018749554,0.0039431336,0.00007833729,0.00001379173,0.0004029711],"genre_scores_gemma":[0.000018969293,0.99306273,0.0006049686,0.004595157,0.00072267326,0.0003598133,0.000101785874,0.00004408889,0.00048980484],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8341315,0.13337915,0.02921932,0.0008638997,0.00085112615,0.0015550259],"domain_scores_gemma":[0.90255314,0.07757801,0.016458124,0.0008822226,0.0009641465,0.0015643289],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23444755,0.0003621989,0.008699718,0.0007488603,0.00033689747,0.0000028853435,0.0007653754,0.0010623902,0.00025301494],"category_scores_gemma":[0.07178901,0.00024076768,0.000722068,0.0009032513,0.0003805141,0.00011315329,0.00042699886,0.007393953,0.00016449185],"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":[0.00005314988,0.00050807867,0.019451654,0.45577258,0.000061802035,0.0000038922412,0.00028127828,3.3937718e-7,5.2664e-10,0.002663496,0.023616228,0.49758753],"study_design_scores_gemma":[0.0003280013,0.0021936684,0.0028301624,0.35881963,0.00009093123,0.0000111527725,0.00006478817,0.0000054624343,2.1720699e-9,0.0026519126,0.6328977,0.000106606465],"about_ca_topic_score_codex":0.000113183756,"about_ca_topic_score_gemma":0.00014773553,"teacher_disagreement_score":0.6092814,"about_ca_system_score_codex":0.00044254694,"about_ca_system_score_gemma":0.00435326,"threshold_uncertainty_score":0.99489605},"labels":[],"label_agreement":null},{"id":"W4387846964","doi":"10.1016/j.jclinepi.2023.10.007","title":"Crowd-sourcing and automation facilitated the identification and classification of randomized controlled trials in a living review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Bruyère; University of Ottawa; Ottawa Hospital; University of Calgary","funders":"Medical Research Council; Canadian Institutes of Health Research; National Health and Medical Research Council; Hospital Research Foundation","keywords":"Medicine; Crowdsourcing; Randomized controlled trial; Systematic review; MEDLINE; Population; Cohen's kappa; Meta-analysis; Artificial intelligence; Machine learning; Family medicine; Physical therapy; Internal medicine; Computer science; World Wide Web","score_opus":0.45875122597952356,"score_gpt":0.5759518388540973,"score_spread":0.11720061287457373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387846964","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":[0.0009463113,0.99045336,0.0005660204,0.0044335206,0.00022124972,0.0033469584,0.0000073287256,0.000009189206,0.000016060596],"genre_scores_gemma":[0.0007913976,0.99847424,0.00020341689,0.00013439862,0.00015084977,0.00015379928,0.000013586562,0.000016644073,0.00006168508],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.87617236,0.09203652,0.030847307,0.0003206312,0.00036547726,0.00025767868],"domain_scores_gemma":[0.28816855,0.6781933,0.032245282,0.00042879765,0.00071610126,0.00024800395],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42225507,0.00022843917,0.033844788,0.00044631588,0.000043286636,0.000015870319,0.0001471598,0.00038517851,0.000024071363],"category_scores_gemma":[0.8293098,0.0001032656,0.0030384648,0.0002698999,0.0005900722,0.000081003454,0.000045692836,0.0010830082,0.0000052337577],"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":[0.008331125,0.00008667236,0.00045671395,0.024938578,0.002296854,0.000007169159,0.00009520648,8.1688154e-7,0.0000027077224,0.0007314213,0.0007275032,0.9623252],"study_design_scores_gemma":[0.18419401,0.00078356726,0.014841014,0.67088187,0.004990846,0.00064549677,0.00016241618,0.00348024,1.248146e-7,0.0061854133,0.113528416,0.00030657678],"about_ca_topic_score_codex":0.000015883355,"about_ca_topic_score_gemma":0.0000075379126,"teacher_disagreement_score":0.96201867,"about_ca_system_score_codex":0.000029421888,"about_ca_system_score_gemma":0.00042709694,"threshold_uncertainty_score":0.9804988},"labels":[],"label_agreement":null},{"id":"W4388108541","doi":"10.1016/j.jclinepi.2023.10.017","title":"Searching a methods topic: practical challenges and implications for search design","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Impact","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Universität Basel","keywords":"Terminology; Search engine indexing; Information retrieval; MEDLINE; Computer science; Citation; Data science; World Wide Web","score_opus":0.9933919604652579,"score_gpt":0.8278810723034243,"score_spread":0.16551088816183357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388108541","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":[0.0066710124,0.0023381538,0.8148856,0.17484576,0.00037976544,0.00034766045,0.0000018598353,0.0000031433513,0.0005270356],"genre_scores_gemma":[0.024646843,0.0066579687,0.96541756,0.0015386028,0.00076219806,0.000023591065,7.208169e-7,0.000010309888,0.00094219274],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.64842427,0.30737776,0.040848363,0.0011361482,0.0015454404,0.0006680208],"domain_scores_gemma":[0.23022926,0.75653994,0.009823449,0.0013048453,0.0016377179,0.00046477432],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.83490473,0.00014516778,0.007115465,0.0003648752,0.00011615806,0.00007619174,0.0008956938,0.0002281292,0.00020620158],"category_scores_gemma":[0.89346457,0.000065131324,0.0024284371,0.0004247525,0.0001893814,0.0001642212,0.00017371115,0.0006686199,0.00014835013],"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":[0.000049497656,0.000045001667,0.014528121,0.000033281645,0.00028789844,0.0000036565837,0.00016749374,0.0001901016,0.00001783871,0.11199726,0.029652592,0.84302723],"study_design_scores_gemma":[0.0002680197,0.00040704763,0.27302402,0.000019934987,0.00013757701,0.000121887206,0.0003188932,0.020186616,0.0000014915959,0.5790589,0.12638897,0.00006663753],"about_ca_topic_score_codex":0.0000011393754,"about_ca_topic_score_gemma":0.0000020411912,"teacher_disagreement_score":0.8429606,"about_ca_system_score_codex":0.000010355984,"about_ca_system_score_gemma":0.00022819218,"threshold_uncertainty_score":0.48639897},"labels":[],"label_agreement":null},{"id":"W4388178426","doi":"10.1016/j.jclinepi.2023.10.016","title":"Clinical judgment shows similar and sometimes superior discrimination compared to prognostic clinical prediction models: a systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"Western University; McMaster University; Impact","funders":"Einstein Stiftung Berlin","keywords":"Systematic review; Clinical judgment; Medicine; MEDLINE; Medical physics; Biology","score_opus":0.7697486684015155,"score_gpt":0.6169569558029101,"score_spread":0.15279171259860536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388178426","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":[0.000317569,0.98262167,0.0004903466,0.0071978807,0.0026017735,0.00658637,0.00008983992,0.00005963157,0.000034910954],"genre_scores_gemma":[0.000092509064,0.9865597,0.00405327,0.006387445,0.0020182007,0.000534032,0.00012716177,0.00010669967,0.000121009885],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.94636613,0.019585716,0.03153215,0.0011799195,0.00070260855,0.00063349213],"domain_scores_gemma":[0.858411,0.12582195,0.011865188,0.0012720836,0.00081808865,0.0018116777],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07648101,0.0008254367,0.03289417,0.00045213793,0.00008699998,0.00002525295,0.0005556318,0.0014695841,0.00005503922],"category_scores_gemma":[0.29296964,0.0004785173,0.0065719234,0.00043160192,0.00040048978,0.00013939582,0.00036860807,0.0025763947,0.00014580775],"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":[0.00022667598,0.0028522871,0.024671929,0.7212809,0.0067189545,0.0003342707,0.000022238628,0.000008957081,3.5377596e-9,0.00016963758,0.034172785,0.20954137],"study_design_scores_gemma":[0.0023646227,0.006818206,0.008657074,0.8623857,0.056699492,0.00084851595,0.000038806633,0.0009505442,6.641854e-9,0.0007346683,0.06010672,0.00039565447],"about_ca_topic_score_codex":0.0000062238637,"about_ca_topic_score_gemma":0.000008053554,"teacher_disagreement_score":0.21648864,"about_ca_system_score_codex":0.00020567879,"about_ca_system_score_gemma":0.0009940709,"threshold_uncertainty_score":0.9998267},"labels":[],"label_agreement":null},{"id":"W4388180784","doi":"10.1016/j.jclinepi.2023.10.005","title":"GRADE guidance 37: rating imprecision in a body of evidence on test accuracy","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Test (biology); Grading (engineering); Sample size determination; Rating scale; Statistics; Sample (material); Computer science; Confidence interval; Mathematics; Engineering","score_opus":0.9563425643518924,"score_gpt":0.7288577227698326,"score_spread":0.22748484158205973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388180784","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":[0.96922547,0.001042065,0.011824363,0.014393132,0.002952668,0.00013097891,0.0000035165076,0.00001893143,0.00040889173],"genre_scores_gemma":[0.95050883,0.0024225025,0.045090668,0.0012374626,0.00062945276,0.00000227096,1.7325239e-7,0.000009462829,0.000099173514],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9614305,0.019773949,0.016011413,0.0007261938,0.0014038861,0.0006540552],"domain_scores_gemma":[0.041989867,0.9459634,0.010380135,0.00073212915,0.00068773737,0.00024675767],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33589596,0.0001747558,0.0029978843,0.0008997353,0.00006277871,0.000020954118,0.0017418354,0.00033095636,0.00006615427],"category_scores_gemma":[0.99495757,0.0000942895,0.0007430693,0.003552208,0.00027983403,0.00032275816,0.00032067433,0.0013268385,0.00007615453],"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":[0.00019374638,0.000103691506,0.75081205,0.0000070973956,0.000010230179,0.00004654893,0.000028823792,0.0012370623,0.0005124688,0.00020563719,0.008793155,0.23804948],"study_design_scores_gemma":[0.0006126172,0.0015987252,0.8909871,0.0005615174,0.0000073312553,0.000030800344,0.00011794296,0.00811046,0.00007852942,0.09604509,0.0017620383,0.000087830944],"about_ca_topic_score_codex":0.000020788279,"about_ca_topic_score_gemma":0.0000045649294,"teacher_disagreement_score":0.9261894,"about_ca_system_score_codex":0.00003071709,"about_ca_system_score_gemma":0.00021869928,"threshold_uncertainty_score":0.68383485},"labels":[],"label_agreement":null},{"id":"W4388209589","doi":"10.1016/j.jclinepi.2023.10.022","title":"Risk of bias assessments in individual participant data meta-analyses of test accuracy and prediction models: a review shows improvements are needed","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Jewish General Hospital","funders":"Birmingham Biomedical Research Centre; NIHR Oxford Biomedical Research Centre; Manchester Biomedical Research Centre; Medical Research Foundation; Medical Research Council; National Institute for Health and Care Research; Department of Health and Social Care; Cancer Research UK","keywords":"Meta-analysis; Test (biology); Publication bias; Risk assessment; Predictive modelling; Statistics; Medicine; Computer science; Machine learning; Internal medicine; Mathematics","score_opus":0.9952257982715195,"score_gpt":0.7820060507785607,"score_spread":0.2132197474929588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388209589","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":[0.00016961517,0.9931312,0.0021291948,0.00046183667,0.0004744197,0.0015118313,0.0020905682,0.0000021857252,0.000029122642],"genre_scores_gemma":[0.00023570674,0.9933726,0.0053798244,0.00051192194,0.00019311055,0.00005546015,0.00008986815,0.000028970371,0.00013252228],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.5784796,0.24242103,0.17081462,0.0021368775,0.005522486,0.00062539225],"domain_scores_gemma":[0.08636697,0.61545646,0.28771722,0.0073472764,0.0025427474,0.0005692849],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7643846,0.0007966795,0.08813755,0.0011903102,0.000048245507,0.000077653174,0.005674565,0.00072891236,0.00073753035],"category_scores_gemma":[0.9302756,0.00031895077,0.0155158285,0.0022024154,0.0003197001,0.00063131104,0.0014525208,0.0019157963,0.000044390286],"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":[0.000030210555,0.0007680699,0.026933923,0.031582985,0.087739795,0.000027413502,0.000030980627,0.00025153832,1.371155e-7,0.00006726365,0.07286426,0.77970344],"study_design_scores_gemma":[0.0009326768,0.0010915296,0.0065270015,0.043492053,0.60047805,0.0000756209,0.00028344156,0.01644991,9.155365e-8,0.013162199,0.317012,0.00049540814],"about_ca_topic_score_codex":0.00012213648,"about_ca_topic_score_gemma":0.00009207166,"teacher_disagreement_score":0.779208,"about_ca_system_score_codex":0.000022483291,"about_ca_system_score_gemma":0.0008019515,"threshold_uncertainty_score":0.99992627},"labels":[],"label_agreement":null},{"id":"W4388440588","doi":"10.1016/j.jclinepi.2023.10.024","title":"Transparency, openness, and reproducible research practices are frequently underused in health economic evaluations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Institute of Health Economics; University of Ottawa; Ottawa Hospital","funders":"Instituto de Salud Carlos III; Centro de Investigación Biomédica en Red de Salud Mental; University of Ottawa","keywords":"Openness to experience; Transparency (behavior); Psychological intervention; MEDLINE; Health care; Economic evaluation; Business; Medicine; Public economics; Accounting; Political science; Nursing; Psychology; Economics; Economic growth","score_opus":0.9562540413191357,"score_gpt":0.7413742190170274,"score_spread":0.21487982230210834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388440588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5340011,0.0055980873,0.00058834965,0.45710003,0.0015160708,0.0005345286,0.000066324654,0.00001828316,0.0005772275],"genre_scores_gemma":[0.9563182,0.022037955,0.0047833803,0.014584195,0.0017090274,0.000058074755,0.000018816892,0.000043336084,0.00044703885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9382324,0.026033903,0.0330544,0.001369085,0.00020092694,0.0011092603],"domain_scores_gemma":[0.85098064,0.11303724,0.034126807,0.00095660443,0.0002589525,0.00063974876],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5574433,0.00016267906,0.0038111876,0.0009815325,0.00020888408,0.000039062845,0.0005035122,0.00033890604,0.00025850657],"category_scores_gemma":[0.36106658,0.00017557933,0.00026635348,0.0004264279,0.00032406356,0.00068387965,0.00008328379,0.0013180946,0.0009269166],"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":[0.000070321476,0.00012271082,0.86421996,0.00025260792,0.000080180595,0.000004733709,0.00048667967,0.002235862,2.1612595e-7,0.077330634,0.054574866,0.00062123075],"study_design_scores_gemma":[0.0012826181,0.0003897911,0.7612027,0.00021809344,0.0000046852947,0.000014267174,0.0012254554,0.0063885204,1.7685355e-7,0.19501422,0.034129165,0.0001303114],"about_ca_topic_score_codex":0.0036624377,"about_ca_topic_score_gemma":0.0031595782,"teacher_disagreement_score":0.44251585,"about_ca_system_score_codex":0.0005397323,"about_ca_system_score_gemma":0.0014159641,"threshold_uncertainty_score":0.999851},"labels":[],"label_agreement":null},{"id":"W4388461137","doi":"10.1016/j.jclinepi.2023.10.021","title":"A scoping review reveals candidate quality indicators of knowledge translation and implementation science practice tools","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Toronto Rehabilitation Institute; University of British Columbia; Toronto General Hospital; McMaster University; Alberta Health Services; St. Michael's Hospital; Impact; University of Calgary; McMaster University Medical Centre; University Health Network; Ottawa Hospital; University of Ottawa; University of Toronto; North York General Hospital; Ted Rogers Centre for Heart Research; Public Health Ontario","funders":"","keywords":"Knowledge translation; Computer science; Quality (philosophy); Data science; Grey literature; Knowledge management; MEDLINE","score_opus":0.9671538677225967,"score_gpt":0.8631581789504704,"score_spread":0.10399568877212628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388461137","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":[0.00013944204,0.9856293,0.00058740174,0.007844703,0.0015236051,0.003850809,0.00012598795,0.000016241815,0.00028249578],"genre_scores_gemma":[0.000033458327,0.98578864,0.00434031,0.00901879,0.00062948006,0.00012781426,0.000015100951,0.000026485735,0.000019943891],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8840741,0.07877342,0.03454689,0.0007200431,0.0008160611,0.0010695264],"domain_scores_gemma":[0.42492762,0.5158777,0.055920858,0.00063562754,0.0016573118,0.0009808793],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3851191,0.00030690606,0.0089262305,0.00091216393,0.00045031725,0.000008669678,0.00075697486,0.0005481492,0.0001510578],"category_scores_gemma":[0.5755744,0.00022040322,0.0006433645,0.0022553992,0.00088889414,0.00079394237,0.00023248701,0.0023370804,0.000068013804],"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":[0.000019298683,0.000020971946,0.0018615873,0.18222947,0.000065178945,0.0000017089338,0.00053451164,7.343001e-8,1.4482134e-7,0.00095446117,0.0022732154,0.8120394],"study_design_scores_gemma":[0.00083721377,0.00035635804,0.00485691,0.35005918,0.0007366976,0.000028987735,0.000391677,0.0000015307368,5.9465492e-8,0.00044184597,0.64208084,0.00020866013],"about_ca_topic_score_codex":0.00013088604,"about_ca_topic_score_gemma":0.00014904897,"teacher_disagreement_score":0.8118307,"about_ca_system_score_codex":0.00028315824,"about_ca_system_score_gemma":0.018322412,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W4388461776","doi":"10.1016/j.jclinepi.2023.11.001","title":"Compelling evidence from meta-epidemiological studies demonstrates overestimation of effects in randomized trials that fail to optimize randomization and blind patients and outcome assessors","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":52,"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; McMaster University; Impact","funders":"","keywords":"Blinding; Meta-analysis; Randomized controlled trial; Medicine; Randomization; Epidemiology; Odds ratio; Publication bias; Confidence interval; Clinical trial; Physical therapy; Internal medicine","score_opus":0.9788432014016687,"score_gpt":0.7284421707616289,"score_spread":0.2504010306400398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388461776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86426914,0.009910137,0.11901033,0.0048221927,0.0006109803,0.0013619416,0.0000060365614,0.0000029488524,0.0000063017033],"genre_scores_gemma":[0.91884214,0.006747136,0.07350974,0.00072124833,0.000104699546,0.000036940317,0.0000031701777,0.0000071840564,0.000027761667],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.37258297,0.52583003,0.09702765,0.001421942,0.0026325975,0.0005047832],"domain_scores_gemma":[0.03177146,0.9227566,0.043040004,0.0006552572,0.0014697541,0.00030691968],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.82175416,0.00038335833,0.05250967,0.000689717,0.000061226376,0.00008023477,0.00064733933,0.0003436211,0.00013999446],"category_scores_gemma":[0.9840029,0.00014734331,0.005390646,0.0007749566,0.00043353904,0.00038635952,0.00021164733,0.000495031,0.00002864398],"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":[0.01511688,0.000055230263,0.95052695,0.00010273502,0.0034036296,0.0000057381644,0.0002454858,0.02404625,0.0000062725408,0.00039260817,0.001391467,0.00470676],"study_design_scores_gemma":[0.0748281,0.0004349796,0.67930794,0.00064265454,0.006391033,0.000004588739,0.000359012,0.12668432,0.0000076097185,0.11110412,0.000028366518,0.00020726524],"about_ca_topic_score_codex":0.000029490046,"about_ca_topic_score_gemma":0.00001555122,"teacher_disagreement_score":0.39692655,"about_ca_system_score_codex":0.000017527032,"about_ca_system_score_gemma":0.000052737432,"threshold_uncertainty_score":0.9615568},"labels":[],"label_agreement":null},{"id":"W4388598851","doi":"10.1016/j.jclinepi.2023.11.007","title":"Minimal clinical datasets for spine-related musculoskeletal disorders in primary and outpatient care settings: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Spondyloarthritis Studies and Treatments","field":"Medicine","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 intégré universitaire de santé et de services sociaux de la Capitale-Nationale; Centre intégré universitaire de santé et de services sociaux de la Mauricie-et-du-Centre-du-Québec; Queen's University; Centre for Interdisciplinary Research in Rehabilitation; St. Michael's Hospital; Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; Ontario Tech University; Public Health Ontario; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; University of Toronto; Université du Québec à Trois-Rivières","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Centre for Chiropractic Research Excellence; National Science Foundation","keywords":"Medicine; CINAHL; Chiropractic; MEDLINE; Health care; Family medicine; Physical therapy; Alternative medicine; Psychological intervention; Nursing; Pathology","score_opus":0.23046521016089022,"score_gpt":0.5607213837574232,"score_spread":0.330256173596533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388598851","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":[0.00038726517,0.9921827,0.000013167657,0.0017593383,0.0016553411,0.003670885,0.00026228782,0.000016514618,0.000052551077],"genre_scores_gemma":[0.0000071924555,0.994069,0.002358837,0.0015198686,0.000717764,0.00014242924,0.0010915132,0.000073142204,0.000020245467],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9791371,0.003980082,0.0152103985,0.0008161255,0.0002406761,0.00061556784],"domain_scores_gemma":[0.96151805,0.030006198,0.007351947,0.00045603467,0.00019572624,0.00047204815],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.019495701,0.00056468113,0.017096546,0.00024576156,0.00007069761,0.00000494305,0.0002455082,0.0010938758,0.00001622315],"category_scores_gemma":[0.09738275,0.00037597178,0.0040914635,0.0002777284,0.00044238084,0.0000657881,0.00029454817,0.0021699504,0.000017716691],"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":[0.00015404008,0.00031123534,0.008022481,0.18795566,0.0010193526,0.00015963837,0.00001206171,1.3875538e-7,1.1077146e-9,0.000012528667,0.0039585656,0.79839426],"study_design_scores_gemma":[0.005690118,0.0056964615,0.008082828,0.57977396,0.0045275385,0.0002786828,0.00003496547,0.000002816769,7.007422e-10,0.000062927684,0.39558,0.00026971658],"about_ca_topic_score_codex":0.000008347792,"about_ca_topic_score_gemma":0.0000653062,"teacher_disagreement_score":0.79812455,"about_ca_system_score_codex":0.00012779237,"about_ca_system_score_gemma":0.0009896148,"threshold_uncertainty_score":0.9998692},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","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":"high"}],"label_agreement":"agree"},{"id":"W4388598893","doi":"10.1016/j.jclinepi.2023.10.001","title":"Operationalizing the GRADE-equity criterion to inform guideline recommendations: application to a medical cannabis guideline","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Western University; McMaster University; Impact; University of Calgary; Cochrane; Bruyère; University of Ottawa","funders":"","keywords":"Operationalization; Guideline; Psychological intervention; Equity (law); Medicine; MEDLINE; PsycINFO; Nursing; Political science","score_opus":0.7269576262956654,"score_gpt":0.6969278720504872,"score_spread":0.030029754245178175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388598893","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":[0.03775918,0.000094396746,0.079618335,0.8752892,0.005102783,0.0014433255,0.000047521367,0.000043575194,0.00060166715],"genre_scores_gemma":[0.040036015,0.0011992161,0.03858526,0.9109846,0.0066455784,0.00046410246,0.0007232481,0.000033893084,0.0013280987],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98033684,0.0053750426,0.012581395,0.00030063634,0.0006918939,0.0007142156],"domain_scores_gemma":[0.97959137,0.014907041,0.0024885554,0.00041414544,0.0010673862,0.0015314916],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.104962684,0.0001674624,0.0011583128,0.0002283195,0.0007700453,0.0000056055837,0.0006505542,0.00038917921,0.0011965834],"category_scores_gemma":[0.08584747,0.000103067185,0.00025413593,0.00067125936,0.000070407645,0.0001224166,0.0005219468,0.0013793543,0.00086622103],"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":[0.00021826709,0.00008158912,0.030917466,0.00006942272,0.000026016562,0.0000020514312,0.0004959597,0.0003614812,0.000005072333,0.0048259953,0.8645719,0.098424755],"study_design_scores_gemma":[0.0007950787,0.00076623634,0.015458007,0.00037795003,0.000016852962,0.000007311865,0.00067153247,0.007431284,0.0000011892249,0.006037459,0.96833855,0.00009856862],"about_ca_topic_score_codex":0.00052396907,"about_ca_topic_score_gemma":0.0007776705,"teacher_disagreement_score":0.103766605,"about_ca_system_score_codex":0.00024165263,"about_ca_system_score_gemma":0.0014924118,"threshold_uncertainty_score":0.9999117},"labels":[],"label_agreement":null},{"id":"W4389001120","doi":"10.1016/j.jclinepi.2023.11.009","title":"A multimethods randomized trial found that plain language versions improved adults understanding of health recommendations","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","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":"St. Joseph’s Healthcare Hamilton; Glycemic Index Laboratories; Western University; University of Toronto; SickKids Foundation; Hospital for Sick Children; Alberta Health; University of Alberta; McMaster University; Public Health Agency of Canada; University of Ottawa; Institute for Clinical Evaluative Sciences; Impact; Cochrane","funders":"Canadian Institutes of Health Research; World Health Organization","keywords":"Usability; Randomized controlled trial; Plain language; Medicine; Guideline; Population; Medical education; MEDLINE; Family medicine; Applied psychology; Psychology; Computer science; Environmental health","score_opus":0.6355295697108351,"score_gpt":0.6763436791266899,"score_spread":0.04081410941585484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389001120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4704749,0.0004000662,0.42297825,0.08384194,0.01631437,0.004233688,0.00011354545,0.00011924903,0.0015239699],"genre_scores_gemma":[0.8087922,0.004105824,0.1534317,0.03048622,0.0022236274,0.00012163233,0.00016484864,0.000043301443,0.0006306883],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9036662,0.073413074,0.021517608,0.00029687662,0.00027931246,0.00082693977],"domain_scores_gemma":[0.75479454,0.22809476,0.015948031,0.0003578037,0.0003529375,0.00045193487],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26259696,0.000168908,0.0041453745,0.00039734654,0.0005713722,0.000004352489,0.00033419905,0.0005279538,0.00057524414],"category_scores_gemma":[0.27050573,0.0001139163,0.0009478433,0.00043273863,0.00029900725,0.0004648364,0.00013080068,0.0021436035,0.00004467738],"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":[0.82616717,0.00043330598,0.031232659,0.0010806286,0.00035943827,0.0000032031176,0.013930144,0.00008032009,0.0000029016028,0.008709012,0.048201054,0.06980019],"study_design_scores_gemma":[0.88331753,0.0014382988,0.013467194,0.001271984,0.00007262467,0.000004229912,0.020126875,0.046091806,6.936414e-7,0.016999248,0.017027931,0.00018156145],"about_ca_topic_score_codex":0.00036467097,"about_ca_topic_score_gemma":0.00004962634,"teacher_disagreement_score":0.33831725,"about_ca_system_score_codex":0.00025545782,"about_ca_system_score_gemma":0.0014941136,"threshold_uncertainty_score":0.931301},"labels":[],"label_agreement":null},{"id":"W4389080821","doi":"10.1016/j.jclinepi.2023.111226","title":"Applying sequence analysis to uncover ‘real-world’ clinical pathways from routinely collected data: a systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":16,"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":"Keele University; Faculty of Medicine and Health, University of Sydney; Department of Health and Social Care; National Institute for Health and Care Research","keywords":"PsycINFO; CINAHL; MEDLINE; Systematic review; Identification (biology); Data science; Medicine; Hierarchical clustering; Data mining; Information retrieval; Cluster analysis; Computer science; Political science; Artificial intelligence","score_opus":0.9149103234974467,"score_gpt":0.7174708670495802,"score_spread":0.19743945644786653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389080821","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":[0.000027001397,0.97816575,0.0054464755,0.0046702,0.0031203926,0.007368059,0.001014795,0.00009913509,0.000088169654],"genre_scores_gemma":[0.0000057988536,0.9526018,0.016761387,0.023106713,0.00440401,0.00029151794,0.0023182079,0.00014385815,0.0003667462],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.8794119,0.041896407,0.07452363,0.0019796297,0.0012723553,0.00091608416],"domain_scores_gemma":[0.34831464,0.57680184,0.06465126,0.005359369,0.0024403445,0.0024325491],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.2045881,0.0010189958,0.054303467,0.0012522222,0.00010890204,0.000040966544,0.0024264294,0.0014962984,0.0003795766],"category_scores_gemma":[0.81951654,0.00066865515,0.010014827,0.005659349,0.0002999152,0.00032033154,0.0012229657,0.0058894674,0.0009157919],"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":[0.00061072153,0.00082951033,0.0077717206,0.5550251,0.049568728,0.001279448,0.000010604394,0.000024928797,6.846547e-8,0.000100786565,0.13419484,0.25058356],"study_design_scores_gemma":[0.001370422,0.0009128423,0.0016779384,0.4009977,0.19124264,0.00017922085,0.000021839032,0.0005827899,3.4942191e-9,0.00032372714,0.40219232,0.0004985518],"about_ca_topic_score_codex":0.0007456673,"about_ca_topic_score_gemma":0.0009885962,"teacher_disagreement_score":0.6149285,"about_ca_system_score_codex":0.00047448662,"about_ca_system_score_gemma":0.0056332736,"threshold_uncertainty_score":0.9998996},"labels":[],"label_agreement":null},{"id":"W4389108503","doi":"10.1016/j.jclinepi.2023.111224","title":"Guideline panel social dynamics influence the development of clinical practice recommendations: a mixed-methods systematic review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University; Impact; University Health Network","funders":"Agency for Healthcare Research and Quality","keywords":"Guideline; Grading (engineering); Cognition; Deliberation; Psychology; Empirical research; Evidence-based medicine; MEDLINE; Applied psychology; Medicine; Medical education; Alternative medicine; Political science; Pathology; Psychiatry","score_opus":0.955781588160322,"score_gpt":0.8588994286528894,"score_spread":0.09688215950743262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389108503","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":[0.0000033856754,0.8290499,0.036662556,0.12215415,0.0070287692,0.004747376,0.000119995675,0.000035312612,0.00019855166],"genre_scores_gemma":[1.7350168e-7,0.7336456,0.20730485,0.05700489,0.0014260891,0.00032039432,0.000035537134,0.00004713784,0.00021530499],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.46065077,0.3949905,0.14085768,0.00087981735,0.0011920421,0.0014291969],"domain_scores_gemma":[0.122840546,0.74572194,0.12493053,0.0011465173,0.004628889,0.0007315555],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.67222345,0.00054860074,0.022166237,0.00034819794,0.00082260853,0.000008130573,0.002444908,0.0016266386,0.00018307871],"category_scores_gemma":[0.926492,0.00030185122,0.0027293288,0.0014264167,0.00064492103,0.000281327,0.0007834706,0.0077668456,0.0005748375],"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":[0.000018317387,0.00006971579,0.00008867492,0.45172685,0.0005388653,0.0000039780657,0.00031087705,7.900864e-7,1.2034226e-9,0.0009778044,0.10407945,0.4421847],"study_design_scores_gemma":[0.00030915072,0.00013364152,0.00024464884,0.25992534,0.0019823385,0.000050449773,0.00080388517,0.000053272106,7.264415e-10,0.00053007377,0.73580045,0.00016675377],"about_ca_topic_score_codex":0.00003187995,"about_ca_topic_score_gemma":0.00008119903,"teacher_disagreement_score":0.631721,"about_ca_system_score_codex":0.000523381,"about_ca_system_score_gemma":0.020668706,"threshold_uncertainty_score":0.9999434},"labels":[],"label_agreement":null},{"id":"W4389248466","doi":"10.1016/j.jclinepi.2023.111232","title":"Validation and impact of algorithms for identifying variables in observational studies of routinely collected data","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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; St. Joseph’s Healthcare Hamilton; Impact","funders":"West China Hospital, Sichuan University; Sichuan University; National Natural Science Foundation of China","keywords":"Observational study; Algorithm; Medicine; Credibility; Population; Statistics; Computer science; Data mining; Mathematics; Internal medicine","score_opus":0.989031435672502,"score_gpt":0.7687645764054144,"score_spread":0.22026685926708756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389248466","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":[0.9506618,0.0011322853,0.045386918,0.0019241136,0.00049301767,0.00028386226,0.00009226991,0.000001015803,0.000024725612],"genre_scores_gemma":[0.90689397,0.0015283484,0.09068474,0.00015903461,0.00029391024,0.0000062204413,0.00004482937,0.000007989468,0.00038093273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.88682276,0.045820363,0.064316824,0.0007950899,0.0019218884,0.00032309655],"domain_scores_gemma":[0.28779203,0.64564025,0.058824573,0.0020071217,0.005552255,0.00018374679],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5749905,0.00012692604,0.008891164,0.00048205798,0.000035832636,0.0000228785,0.0010692988,0.00013933107,0.00015896735],"category_scores_gemma":[0.86813015,0.00005891305,0.0015147998,0.0013351513,0.0001573576,0.0002758682,0.00023604179,0.00019624969,0.000005999734],"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":[0.00008431687,0.000056973542,0.94410735,0.00009052428,0.00089130184,0.0000012337113,0.00009841499,0.0025068019,0.0000648739,0.0010647123,0.045708843,0.005324675],"study_design_scores_gemma":[0.00056937494,0.00023353516,0.83236647,0.00010970468,0.00019019202,0.0000071115337,0.00023394189,0.0887989,0.0000030405427,0.07702612,0.00041923203,0.00004237929],"about_ca_topic_score_codex":0.00002022951,"about_ca_topic_score_gemma":0.000016759841,"teacher_disagreement_score":0.5998199,"about_ca_system_score_codex":0.000016956197,"about_ca_system_score_gemma":0.00026382573,"threshold_uncertainty_score":0.6077822},"labels":[],"label_agreement":null},{"id":"W4389285887","doi":"10.1016/j.jclinepi.2023.111229","title":"Systematic review search strategies are poorly reported and not reproducible: a cross-sectional metaresearch study","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"University of Sussex; University of Washington; Universitetet i Oslo; University of Leeds; University of Miami","keywords":"Systematic review; Operationalization; Guideline; MEDLINE; Information retrieval; Database; Medicine; Computer science; Pathology","score_opus":0.9704793010149019,"score_gpt":0.7579052970968853,"score_spread":0.21257400391801662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389285887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9590428,0.023166062,0.0016439608,0.011844137,0.0013815678,0.0025748373,0.000013571641,0.000013752793,0.00031931055],"genre_scores_gemma":[0.9794293,0.008775932,0.0018297067,0.0023222263,0.0007719213,0.00006983852,0.00000405558,0.000024848387,0.0067721633],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.35966337,0.43910688,0.18161365,0.00391874,0.014461466,0.0012359186],"domain_scores_gemma":[0.29088512,0.5685185,0.11054657,0.011236248,0.017384214,0.0014293307],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.90701103,0.00035200446,0.023675935,0.000846124,0.00022193241,0.00053631363,0.0022897432,0.00026005614,0.0017361237],"category_scores_gemma":[0.9320063,0.0001511186,0.0047538453,0.0027126595,0.00039610165,0.0004669606,0.0004196463,0.0015278198,0.0011024048],"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":[0.000064778236,0.00015114238,0.95717835,0.01438361,0.001974397,0.0002731991,0.00006354913,0.00021803449,0.000002545624,0.00056869414,0.024831714,0.00028995314],"study_design_scores_gemma":[0.00042116927,0.00061671797,0.9816617,0.004313836,0.00084607315,0.0005787934,0.001198363,0.0012305815,3.3299983e-7,0.008530677,0.0004639913,0.00013777615],"about_ca_topic_score_codex":0.000025472978,"about_ca_topic_score_gemma":0.000022833086,"teacher_disagreement_score":0.12941165,"about_ca_system_score_codex":0.000030712832,"about_ca_system_score_gemma":0.0005438344,"threshold_uncertainty_score":0.99967533},"labels":[],"label_agreement":null},{"id":"W4389485810","doi":"10.1016/j.jclinepi.2023.111237","title":"Librarian involvement in systematic reviews was associated with higher quality of reported search methods: a cross-sectional survey","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Vancouver Native Health Society; BC Children's Hospital; University of British Columbia","funders":"","keywords":"Quality (philosophy); Medicine; Cross-sectional study; Family medicine; MEDLINE; Medical education; Pathology; Political science","score_opus":0.9833184243527989,"score_gpt":0.7615110483298714,"score_spread":0.22180737602292755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389485810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745979,0.001906224,0.018551134,0.0014575797,0.001555436,0.0014522986,0.000020917116,0.000006293377,0.00045226119],"genre_scores_gemma":[0.956023,0.0009778406,0.033520386,0.0016725227,0.0003879392,0.00006806971,0.00003985285,0.000033986984,0.007276442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.12280087,0.72466147,0.14604057,0.0011903665,0.0047211586,0.0005855343],"domain_scores_gemma":[0.05952416,0.80071765,0.13020904,0.0035692258,0.0054269275,0.000552965],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.956409,0.0003207014,0.027451172,0.00079910184,0.00006505412,0.00011645543,0.0018862458,0.0004660844,0.0019625495],"category_scores_gemma":[0.9459284,0.00013156825,0.0049532177,0.0036377972,0.00033328412,0.00028613547,0.00021096722,0.0010894364,0.00024335613],"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":[0.00011417948,0.00017126983,0.9902415,0.0010370142,0.00090242253,0.00001795381,0.00005352279,0.0004015503,0.0000057778802,0.00077603,0.0058832355,0.00039553453],"study_design_scores_gemma":[0.0006586898,0.00028150753,0.98515034,0.0010295174,0.00011470382,0.000013476025,0.000059911923,0.0017823612,8.1755667e-7,0.009776826,0.0010164254,0.00011540923],"about_ca_topic_score_codex":0.00010591188,"about_ca_topic_score_gemma":0.000239673,"teacher_disagreement_score":0.07605619,"about_ca_system_score_codex":0.00007862007,"about_ca_system_score_gemma":0.0005055,"threshold_uncertainty_score":0.99894977},"labels":[],"label_agreement":null},{"id":"W4389506386","doi":"10.1016/j.jclinepi.2023.111238","title":"Conduct and reporting of multivariate network meta-analyses: a scoping review","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"","keywords":"Medicine; Psychological intervention; MEDLINE; Multivariate statistics; Meta-analysis; Multivariate analysis; Family medicine; Internal medicine; Statistics; Psychiatry","score_opus":0.9958078153653248,"score_gpt":0.8191627416681674,"score_spread":0.17664507369715743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389506386","genre_codex":"review","genre_gemma":"review","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003092192,0.9907482,0.0049904566,0.0009817625,0.0013917064,0.0016283179,0.000010278691,0.0000033466588,0.00024284123],"genre_scores_gemma":[0.000001594447,0.97055036,0.026255757,0.0011688181,0.0010108309,0.00003519745,0.0000056696276,0.00003925681,0.00093252806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.12979807,0.4083127,0.45470914,0.0021983269,0.004211574,0.00077019323],"domain_scores_gemma":[0.022202276,0.46831954,0.502178,0.0037139924,0.0030566126,0.00052959565],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9241416,0.00094092527,0.22187859,0.00065259397,0.00009617592,0.0000938021,0.003027465,0.0009032239,0.0026841802],"category_scores_gemma":[0.97669435,0.00033354777,0.06798571,0.0025145763,0.00038771046,0.00019259534,0.00061028934,0.0022055386,0.00030691441],"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":[0.000010980048,0.00006283387,0.0007029649,0.14425153,0.056623194,0.00014691817,0.000011530022,0.00012881514,2.72479e-8,0.00088903034,0.07783592,0.7193363],"study_design_scores_gemma":[0.00012399955,0.00018170323,0.00007527239,0.2258444,0.11549099,0.00048067444,0.000008854097,0.00014717295,5.4712537e-9,0.007199948,0.6501886,0.00025838267],"about_ca_topic_score_codex":0.000012404992,"about_ca_topic_score_gemma":0.000013609206,"teacher_disagreement_score":0.7190779,"about_ca_system_score_codex":0.000023461425,"about_ca_system_score_gemma":0.001264181,"threshold_uncertainty_score":0.99991167},"labels":[],"label_agreement":null},{"id":"W4389953647","doi":"10.1016/j.jclinepi.2023.111241","title":"GRADE Concept 7: Issues and Insights Linking Guideline Recommendations to Trustworthy Essential Medicine Lists","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"St. Joseph’s Healthcare Hamilton; McMaster University; McMaster University Medical Centre; Impact","funders":"Government of the United Kingdom; World Health Organization","keywords":"Guideline; Grading (engineering); Prioritization; Medicine; Process (computing); Knowledge management; Medical education; Process management; Computer science; Business; Engineering; Pathology","score_opus":0.7425467177563096,"score_gpt":0.6407627291505426,"score_spread":0.1017839886057671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389953647","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":[0.19087355,0.004761787,0.013118352,0.78546876,0.00503596,0.00027884377,0.000040288018,0.0000388262,0.0003836514],"genre_scores_gemma":[0.5897502,0.019836435,0.08307891,0.28297877,0.022090914,0.000036365265,0.00020957075,0.00010299646,0.0019158574],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9720218,0.0043503167,0.022581063,0.0005051238,0.00010171752,0.00043994465],"domain_scores_gemma":[0.94876724,0.040347867,0.009691003,0.0003537825,0.0002473678,0.0005927163],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13444103,0.00019019752,0.0038832203,0.00059978606,0.0001606939,0.000016619328,0.00035302897,0.0003466066,0.00043906647],"category_scores_gemma":[0.20622669,0.00017971032,0.00029758812,0.0003545381,0.00027233874,0.00027140597,0.00011817856,0.0006479616,0.0004322542],"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":[0.00005374832,0.000077649405,0.106363095,0.00006923659,0.00019575896,0.000008595792,0.0021203756,0.0008805177,0.0000016360839,0.13064267,0.75602275,0.0035639617],"study_design_scores_gemma":[0.0014875598,0.0005919035,0.08530919,0.00024681154,0.000022915117,0.00003042583,0.00064868847,0.006185195,7.576135e-7,0.19349362,0.7117717,0.0002112278],"about_ca_topic_score_codex":0.00027669178,"about_ca_topic_score_gemma":0.00010012382,"teacher_disagreement_score":0.50249,"about_ca_system_score_codex":0.00009067577,"about_ca_system_score_gemma":0.00014255948,"threshold_uncertainty_score":0.8912751},"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":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4390618455","doi":"10.1016/j.jclinepi.2024.111247","title":"Methods proposed for monitoring the implementation of evidence-based research: a cross-sectional study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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; Ottawa Hospital; University of Ottawa; Queen's University; McMaster University; Impact; Public Health Ontario; St. Joseph’s Healthcare Hamilton; University of British Columbia; Cochrane; St. Michael's Hospital","funders":"European Commission","keywords":"Cross-sectional study; Environmental health; Medicine; Pathology","score_opus":0.9929178389305269,"score_gpt":0.8997950533725381,"score_spread":0.09312278555798881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390618455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8664517,0.0002678696,0.067509435,0.056319978,0.007019018,0.002370615,0.000023937688,0.000017357324,0.000020101654],"genre_scores_gemma":[0.9352032,0.00011917046,0.057682496,0.0030539033,0.0036139174,0.00019240158,7.351358e-7,0.000015943066,0.00011826916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9000968,0.08466051,0.012932244,0.00044461462,0.0009264551,0.0009393834],"domain_scores_gemma":[0.53498554,0.45973906,0.0027240515,0.00026466855,0.0020471134,0.0002395609],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47877234,0.000112709524,0.0011082836,0.00036004203,0.0006809215,0.000018359982,0.0005929951,0.00022444395,0.0003169044],"category_scores_gemma":[0.34774324,0.00005838836,0.0004216742,0.00064281427,0.0004974197,0.0003227102,0.000111977475,0.0021528741,0.000017163009],"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":[0.00035699594,0.00005326442,0.9730776,0.00023919674,0.00006728006,0.0000017562003,0.0016970338,0.00006399476,0.0001241046,0.0011948742,0.00436358,0.01876031],"study_design_scores_gemma":[0.0013981856,0.0026408145,0.9651745,0.000283549,0.00003059587,0.0000033983245,0.004891227,0.00060814794,0.00008080719,0.008803095,0.016034741,0.000050929244],"about_ca_topic_score_codex":0.00036353926,"about_ca_topic_score_gemma":0.000059432503,"teacher_disagreement_score":0.37507856,"about_ca_system_score_codex":0.00024604105,"about_ca_system_score_gemma":0.005572624,"threshold_uncertainty_score":0.9885596},"labels":[],"label_agreement":null},{"id":"W4390858342","doi":"10.1016/j.jclinepi.2024.111263","title":"Accessibility of clinical study reports supporting medicine approvals: a cross-sectional evaluation","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":5,"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; St. Michael's Hospital","funders":"Cancer Council South Australia; National Health and Medical Research Council; Medical Research Council","keywords":"Cross-sectional study; Medicine; MEDLINE; Family medicine; Environmental health; Pathology; Political science","score_opus":0.9754818601916025,"score_gpt":0.808792759575731,"score_spread":0.1666891006158715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390858342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963336,0.0019613488,0.02054943,0.002425386,0.009168908,0.0007745321,0.000003412445,0.000004752177,0.0017762262],"genre_scores_gemma":[0.99175614,0.00006569527,0.0040569953,0.00048210187,0.0029487526,0.000011066897,0.0000031893944,0.000010738575,0.0006653353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.13605101,0.43876162,0.4036369,0.0042311703,0.016520971,0.00079833367],"domain_scores_gemma":[0.108483255,0.66604775,0.20321195,0.0055671292,0.015749713,0.0009402136],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9635504,0.0003014415,0.018595431,0.000504372,0.000084900494,0.00015563246,0.001735704,0.00048784277,0.013152716],"category_scores_gemma":[0.9669375,0.00012448896,0.0075487136,0.00123745,0.0007037486,0.0004512868,0.00022836706,0.001573726,0.0001250367],"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":[0.00009213033,0.00038895884,0.913009,0.000056271037,0.0007694789,0.00006950376,0.00008270089,0.0002731462,0.0000019038658,0.00027776003,0.017416183,0.06756296],"study_design_scores_gemma":[0.00054879294,0.0010881764,0.885282,0.00008720697,0.00066989235,0.00025466917,0.00023744584,0.02403478,3.198103e-7,0.08023911,0.007475642,0.00008196315],"about_ca_topic_score_codex":0.000020451973,"about_ca_topic_score_gemma":0.000016210613,"teacher_disagreement_score":0.22728613,"about_ca_system_score_codex":0.00004220455,"about_ca_system_score_gemma":0.0012506628,"threshold_uncertainty_score":0.99597454},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","scholarly_communication","open_science"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4391650918","doi":"10.1016/j.jclinepi.2024.111276","title":"The GRADE Working Group and CINeMA approaches provided inconsistent certainty of evidence ratings for a network meta-analysis of opioids for chronic noncancer pain","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Toronto Western Hospital; McMaster University; University of Toronto; Impact; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Meta-analysis; Concordance; Medicine; Movie theater; Psychology; Transitive relation; Certainty; Chronic pain; Physical therapy; Internal medicine","score_opus":0.9736292731779855,"score_gpt":0.6653577774049535,"score_spread":0.30827149577303203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391650918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010796276,0.16561408,0.7780315,0.042629804,0.00092605496,0.0019437636,0.000020018519,0.0000031191337,0.000035385256],"genre_scores_gemma":[0.918476,0.001891615,0.0765623,0.0014399299,0.0009469317,0.00019774961,0.0000026959424,0.000016949967,0.00046584225],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8278514,0.10172419,0.06590479,0.0014699205,0.0023425673,0.00070713373],"domain_scores_gemma":[0.40338427,0.56770104,0.02646334,0.0012442623,0.00102582,0.00018125423],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.73388934,0.0002998447,0.01898198,0.0003297216,0.00014548445,0.00013272688,0.0013900572,0.0003023482,0.00014012583],"category_scores_gemma":[0.6149355,0.00010133046,0.019622322,0.0014302414,0.00044562246,0.00012823733,0.00014284869,0.0005659824,0.0000010951418],"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":[0.0007929666,0.00017241748,0.106961,0.0019090205,0.34853956,0.0000047406234,0.000508029,0.039332654,0.00002942464,0.085668676,0.08773117,0.32835034],"study_design_scores_gemma":[0.00042172143,0.0014216469,0.0077919,0.0003353717,0.15579093,0.000011804836,0.00034141628,0.68108964,0.0000021996648,0.08741509,0.06520215,0.00017615015],"about_ca_topic_score_codex":0.000015936823,"about_ca_topic_score_gemma":0.0002227738,"teacher_disagreement_score":0.90767974,"about_ca_system_score_codex":0.000038701062,"about_ca_system_score_gemma":0.00033646857,"threshold_uncertainty_score":0.9955823},"labels":[],"label_agreement":null},{"id":"W4391756326","doi":"10.1016/j.jclinepi.2024.111278","title":"Grilling the data: application of specification curve analysis to red meat and all-cause mortality","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Nutritional Studies and Diet","field":"Medicine","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":"McMaster University; Impact","funders":"National Institute on Alcohol Abuse and Alcoholism; U.S. Food and Drug Administration; Yale University; National Institutes of Health; National Institute of Environmental Health Sciences; Arnold Ventures","keywords":"Covariate; Statistics; Hazard ratio; Hazard; Observational study; Quantile; Medicine; Red meat; Specification; Epidemiology; Hazard analysis; Econometrics; Computer science; Mathematics; Internal medicine; Pathology; Engineering; Confidence interval; Reliability engineering; Biology","score_opus":0.7526743507750536,"score_gpt":0.6379973893736931,"score_spread":0.11467696140136052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391756326","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":[0.00012437586,0.9842475,0.0045592226,0.009982261,0.0003904309,0.00046584985,0.00013117814,0.000005355663,0.000093813396],"genre_scores_gemma":[0.00027751745,0.9944402,0.0023183671,0.0006239156,0.0020386523,0.000011597525,0.00024917134,0.000014804327,0.00002576028],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99120724,0.0018014585,0.006080621,0.0004758105,0.0002580255,0.0001768525],"domain_scores_gemma":[0.9789028,0.015791986,0.0038409769,0.0008678542,0.00035778372,0.00023860707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020297872,0.00022061443,0.006285811,0.00020407533,0.000037859274,0.00000606869,0.00037897308,0.0003736719,0.00001282892],"category_scores_gemma":[0.022689097,0.00011040777,0.0014282385,0.00055313477,0.00022154932,0.000040418923,0.00025106888,0.0009966429,0.0000110812725],"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":[0.0004617866,0.0006430468,0.041002527,0.011016785,0.09710034,0.000051917723,0.000026700782,0.000030000554,8.3282583e-7,0.0093898885,0.09030814,0.74996805],"study_design_scores_gemma":[0.00019580308,0.00023361688,0.020291995,0.001425092,0.060635637,0.000067043584,0.0000156084,0.00015391356,2.625213e-8,0.0017825721,0.9151148,0.000083872554],"about_ca_topic_score_codex":0.000038104154,"about_ca_topic_score_gemma":0.00003961174,"teacher_disagreement_score":0.8248067,"about_ca_system_score_codex":0.000037614467,"about_ca_system_score_gemma":0.00012940678,"threshold_uncertainty_score":0.9855432},"labels":[],"label_agreement":null},{"id":"W4391775071","doi":"10.1016/j.jclinepi.2024.111279","title":"Reporting guidelines for traditional Chinese medicine could be improved: a cross-sectional study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Zhejiang Chinese Medical University; National Natural Science Foundation of China","keywords":"Guideline; MEDLINE; Medicine; Family medicine; Medical education; Political science; Pathology","score_opus":0.8981940970894201,"score_gpt":0.7292408308348274,"score_spread":0.16895326625459273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391775071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79193884,0.0008573002,0.030015938,0.16374123,0.012231393,0.00097271305,0.000047080295,0.00006529203,0.00013018788],"genre_scores_gemma":[0.8744095,0.00030902194,0.05693892,0.03136816,0.036298726,0.000046524514,0.00012332818,0.000060489114,0.0004453098],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9587747,0.0015289224,0.03796734,0.00065310294,0.00066222425,0.00041374154],"domain_scores_gemma":[0.6899879,0.27534902,0.025711969,0.0006707846,0.007307123,0.00097320863],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15837371,0.00030235917,0.003497604,0.0002915921,0.00011802234,0.000027704516,0.0002270997,0.00045396687,0.0006026924],"category_scores_gemma":[0.8606069,0.0001869621,0.0016341024,0.00030033872,0.00041111826,0.0003577828,0.00006087515,0.0018605022,0.00000925313],"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":[0.002502743,0.00073052157,0.8988783,0.00014859135,0.00090986816,0.00021418491,0.000046791763,0.00015825508,0.00020890596,0.0007237883,0.08314728,0.012330771],"study_design_scores_gemma":[0.0069379434,0.009608566,0.9107204,0.0002009746,0.0006472046,0.0027710693,0.00021853509,0.014686833,0.0000015304809,0.020336796,0.03370788,0.00016224802],"about_ca_topic_score_codex":0.00010385998,"about_ca_topic_score_gemma":0.000040660787,"teacher_disagreement_score":0.7022332,"about_ca_system_score_codex":0.00011447655,"about_ca_system_score_gemma":0.0012178934,"threshold_uncertainty_score":0.8666314},"labels":[],"label_agreement":null},{"id":"W4391825115","doi":"10.1016/j.jclinepi.2024.111281","title":"A brief note on the common (fixed)-effect meta-analysis model","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Toronto; St. Michael's Hospital","funders":"National Health and Medical Research Council; Medical Research Council","keywords":"Meta-analysis; Random effects model; Confidence interval; Fixed effects model; Statistics; Econometrics; Computer science; Variance (accounting); Interval (graph theory); Mathematics; Medicine; Panel data; Internal medicine","score_opus":0.9511438955217273,"score_gpt":0.7052978236596695,"score_spread":0.24584607186205776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391825115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06400773,0.02187136,0.66043735,0.23015857,0.0029500506,0.0009839567,0.000057702004,0.00001563282,0.019517688],"genre_scores_gemma":[0.9657241,0.00027805878,0.006834778,0.01960995,0.00065979414,0.0000182845,0.000001972823,0.000018055667,0.0068550105],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.65457344,0.271207,0.067436814,0.0014103185,0.0048308866,0.00054152997],"domain_scores_gemma":[0.17484921,0.79179007,0.02691254,0.0047680717,0.0011725144,0.0005075829],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.81335765,0.00043623106,0.033073347,0.0007457441,0.00012725704,0.00034188374,0.0033393938,0.00038465517,0.012302304],"category_scores_gemma":[0.74075407,0.00012462157,0.060520057,0.0021982626,0.00030116527,0.0001847729,0.00017635062,0.0019019623,0.002128686],"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":[0.00014391307,0.0001647431,0.019267434,0.000033012155,0.22231615,0.00010506705,0.00010933981,0.08264464,0.0000031904667,0.11653714,0.5079582,0.050717212],"study_design_scores_gemma":[0.000121498284,0.0004673422,0.0034187238,0.000016904072,0.16893078,0.00004493841,0.000013348364,0.5560628,0.0000015978317,0.14220357,0.1285876,0.00013084497],"about_ca_topic_score_codex":0.000009748683,"about_ca_topic_score_gemma":0.000025474916,"teacher_disagreement_score":0.90171635,"about_ca_system_score_codex":0.000028050632,"about_ca_system_score_gemma":0.00018269468,"threshold_uncertainty_score":0.9986483},"labels":[],"label_agreement":null},{"id":"W4391836696","doi":"10.1016/j.jclinepi.2024.111284","title":"Effect of statin use for the primary prevention of cardiovascular disease among older adults: a cautionary tale concerning target trials emulation","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Lipoproteins and Cardiovascular Health","field":"Medicine","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":"University of Toronto; McGill University Health Centre; Institut universitaire de cardiologie et de pneumologie de Québec; Université de Sherbrooke; Université Laval; Université de Montréal; McGill University; University of Manitoba; Institut National de Santé Publique du Québec; Centre hospitalier de l'Université Laval","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Medicine; Hazard ratio; Myocardial infarction; Marginal structural model; Statin; Internal medicine; Proportional hazards model; Population; Confounding; Clinical endpoint; Stroke (engine); Randomized controlled trial; Confidence interval","score_opus":0.15512423426970928,"score_gpt":0.4709958376543819,"score_spread":0.31587160338467263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391836696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79377955,0.047423556,0.1552837,0.00075992127,0.0009769853,0.0017100701,0.00004881648,0.000009928017,0.0000074583213],"genre_scores_gemma":[0.9901639,0.0041631837,0.0037506428,0.00016463829,0.0015961872,0.000051773262,0.000048589634,0.000022300783,0.00003878195],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9845798,0.010026127,0.004509869,0.00024773699,0.0004384874,0.00019795398],"domain_scores_gemma":[0.9463378,0.05062475,0.002036117,0.0004065666,0.00038690344,0.00020782476],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09398855,0.00014659841,0.0036654337,0.00009955081,0.000042264768,0.0000047031463,0.00009809121,0.00021966426,0.000029880666],"category_scores_gemma":[0.09697308,0.000078700905,0.0055461642,0.00012372031,0.00023739682,0.00015122037,0.00003094745,0.00051302,7.0711184e-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":[0.01933269,0.0004295434,0.25306934,0.009993005,0.019673465,0.00011935891,0.00020687531,0.02679105,0.000044780823,0.0006275919,0.0022830414,0.66742927],"study_design_scores_gemma":[0.009944824,0.0051308763,0.93631107,0.0040061767,0.009309402,0.00007902939,0.00004772288,0.023856224,0.00008795924,0.0013623943,0.009736919,0.00012741491],"about_ca_topic_score_codex":0.00008311962,"about_ca_topic_score_gemma":6.9531103e-7,"teacher_disagreement_score":0.6832417,"about_ca_system_score_codex":0.000055189368,"about_ca_system_score_gemma":0.0005631901,"threshold_uncertainty_score":0.93292946},"labels":[],"label_agreement":null},{"id":"W4391888105","doi":"10.1016/j.jclinepi.2024.111283","title":"Motivations for investigating health inequities in observational epidemiology: a content analysis of 320 studies","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Centre for Global Health Research; Ottawa Public Health; McMaster University; Women's College Hospital; Impact; Ottawa Hospital; St. Michael's Hospital; Public Health Ontario; University of British Columbia; Queen's University; University of Toronto; Royal College of Physicians and Surgeons of Canada; Bruyère; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Observational study; Health equity; Equity (law); Public relations; Social determinants of health; Health care; MEDLINE; Epidemiology; Strengthening the reporting of observational studies in epidemiology; Public health; Psychology; Medicine; Sociology; Political science; Nursing","score_opus":0.9892599149590261,"score_gpt":0.8336088711941276,"score_spread":0.15565104376489847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391888105","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":[0.64186525,0.0021235815,0.029366843,0.32375023,0.0020405303,0.0006283326,0.00016638717,0.00001843267,0.000040399802],"genre_scores_gemma":[0.68827856,0.0038599898,0.10451894,0.2009819,0.0016665569,0.00031851558,0.00004231623,0.000026206493,0.00030701695],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95191014,0.0246893,0.021874212,0.0003937981,0.00025436046,0.0008782215],"domain_scores_gemma":[0.28298083,0.70253277,0.011972133,0.00030279843,0.0016708301,0.0005406545],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20234908,0.00016487426,0.0050025415,0.0010644309,0.00024439054,0.0000021057635,0.00031551265,0.00028260882,0.000102250946],"category_scores_gemma":[0.69225246,0.00011887312,0.0007239946,0.0015117966,0.0006423431,0.0002501338,0.00010844418,0.0013369384,0.000007020622],"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":[0.000042481322,0.000028230568,0.89222246,0.0005720555,0.00065905927,6.356578e-7,0.003054463,0.001143135,0.0000048779402,0.07731775,0.023216126,0.0017387368],"study_design_scores_gemma":[0.00078550837,0.0005009557,0.9175217,0.0007717774,0.00016041886,0.0000017799462,0.0040407525,0.011954135,3.959745e-7,0.050947007,0.013240601,0.00007493657],"about_ca_topic_score_codex":0.00042984993,"about_ca_topic_score_gemma":0.00095269387,"teacher_disagreement_score":0.67784345,"about_ca_system_score_codex":0.0003489714,"about_ca_system_score_gemma":0.004253954,"threshold_uncertainty_score":0.82134944},"labels":[],"label_agreement":null},{"id":"W4392189954","doi":"10.1016/j.jclinepi.2024.111301","title":"The role of scoping reviews in guideline development","year":2024,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"McMaster University; Public Health Ontario; University of Toronto; St. Michael's Hospital; Queen's University","funders":"National Health and Medical Research Council","keywords":"Guideline; Medicine; Pathology","score_opus":0.5247060897271473,"score_gpt":0.6579968706928964,"score_spread":0.1332907809657491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392189954","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007290113,0.073976636,0.0010198228,0.020112693,0.90282536,0.0009434205,0.000011633473,0.000010660881,0.00037076435],"genre_scores_gemma":[0.00019464629,0.0921656,0.04417566,0.0025089458,0.86041725,0.00001861159,0.00011955864,0.00006422372,0.00033553675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9393417,0.008169426,0.050451286,0.00054925616,0.0009376757,0.0005506034],"domain_scores_gemma":[0.40121222,0.55067676,0.042235024,0.0013545408,0.0037886521,0.0007328133],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.20455442,0.00033792708,0.0067626694,0.00025537133,0.00004302626,0.000010308536,0.00053240504,0.001421215,0.000106833075],"category_scores_gemma":[0.77978414,0.00019067594,0.0014046485,0.00026355425,0.0002944436,0.00009053548,0.00024901747,0.0056509986,0.0000757555],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008654353,0.00013303306,0.0038200545,0.00035280106,0.00023139414,0.000034694996,0.000021629856,0.000008847744,0.000003818643,0.00005949814,0.7907008,0.20376797],"study_design_scores_gemma":[0.0016399442,0.0008948335,0.0007909802,0.007656946,0.0004635494,0.00003742814,0.00007376848,0.0001443367,0.0000045740426,0.0044206656,0.98374104,0.0001319231],"about_ca_topic_score_codex":0.000065776425,"about_ca_topic_score_gemma":0.00030189837,"teacher_disagreement_score":0.57522976,"about_ca_system_score_codex":0.00019884447,"about_ca_system_score_gemma":0.00580961,"threshold_uncertainty_score":0.9998751},"labels":[],"label_agreement":null},{"id":"W4392247133","doi":"10.1016/j.jclinepi.2024.111307","title":"Core outcome set developers should consider and specify the level of granularity of outcome domains","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Bruyère; University of Ottawa; McMaster University; Institute for Work & Health; Ottawa Hospital; Impact","funders":"","keywords":"Outcome (game theory); Granularity; Core (optical fiber); Set (abstract data type); Computer science; Mathematics; Programming language; Mathematical economics","score_opus":0.9411956970152316,"score_gpt":0.7090048911897767,"score_spread":0.23219080582545493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392247133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83986175,0.001665306,0.008527697,0.14260215,0.0023166211,0.00047078964,0.00008861295,0.000032433323,0.0044346405],"genre_scores_gemma":[0.98569226,0.0013416216,0.01056825,0.0016943685,0.00039315195,0.0000022200145,6.02849e-7,0.000011883902,0.00029563517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.988406,0.0051879017,0.005156337,0.00024162115,0.00060185447,0.0004062578],"domain_scores_gemma":[0.919789,0.07771645,0.0014753232,0.00027026527,0.0004943999,0.00025453983],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09342133,0.00013617447,0.0019446028,0.00016414103,0.00011721922,0.000014674818,0.00071461283,0.00053881307,0.00017703565],"category_scores_gemma":[0.15783553,0.000079150224,0.0006182146,0.00032518845,0.003754653,0.0001153682,0.00019913359,0.0018288443,0.00000613129],"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":[0.000085179876,0.000045173147,0.8750177,0.0000649885,0.00012778175,0.00006614631,0.00062715594,0.000005782839,0.000018059975,0.107988894,0.011053964,0.004899164],"study_design_scores_gemma":[0.0005459461,0.00038680166,0.74616224,0.00014801652,0.000103201884,0.00011305173,0.0018077397,0.00011836519,0.000020049278,0.18813378,0.062312786,0.00014800965],"about_ca_topic_score_codex":0.00072118244,"about_ca_topic_score_gemma":0.00068938424,"teacher_disagreement_score":0.14583051,"about_ca_system_score_codex":0.00005614873,"about_ca_system_score_gemma":0.000636839,"threshold_uncertainty_score":0.99895656},"labels":[],"label_agreement":null},{"id":"W4392284134","doi":"10.1016/j.jclinepi.2024.111309","title":"Methods used to develop the SPIRIT 2024 and CONSORT 2024 Statements","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa; Women's College Hospital; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Consolidated Standards of Reporting Trials; Medicine; Alternative medicine; Pathology","score_opus":0.7665174124353475,"score_gpt":0.748680114614396,"score_spread":0.01783729782095156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392284134","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":[0.113318846,0.005595401,0.14546947,0.7003011,0.013554723,0.00097213796,0.000015634369,0.00009354504,0.020679165],"genre_scores_gemma":[0.33101395,0.012233066,0.5901115,0.025520176,0.0068068206,0.00007232532,0.0000014681602,0.00008369465,0.03415704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.978113,0.017191662,0.0033544376,0.00032593237,0.00046541588,0.0005495864],"domain_scores_gemma":[0.8930677,0.10511775,0.000552279,0.00021597538,0.0005232321,0.00052303396],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19553915,0.00011947701,0.0010689276,0.00018734772,0.00017567285,0.000073658695,0.00066586473,0.00031181882,0.0008295631],"category_scores_gemma":[0.2416758,0.00007080089,0.00023817467,0.0007317337,0.0010398789,0.0001752126,0.00025066145,0.0015504832,0.00009712165],"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":[0.00010197774,0.00005025415,0.061268043,0.000034262834,0.0002573383,0.0001430002,0.0012981012,0.000011206054,0.000037539787,0.05020336,0.5907194,0.29587552],"study_design_scores_gemma":[0.0001256702,0.0002878222,0.0147124985,0.00010267626,0.000034037806,0.000027000628,0.000673158,0.00012935788,0.000008551922,0.08112485,0.9026928,0.00008155788],"about_ca_topic_score_codex":0.00023719495,"about_ca_topic_score_gemma":0.00024007628,"teacher_disagreement_score":0.6747809,"about_ca_system_score_codex":0.00007950463,"about_ca_system_score_gemma":0.0012416192,"threshold_uncertainty_score":0.90831345},"labels":[],"label_agreement":null},{"id":"W4392381525","doi":"10.1016/j.jclinepi.2024.111315","title":"Reporting of health equity considerations in vaccine trials for COVID-19: a methodological review","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","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":"University of Guelph; McMaster University; Impact","funders":"","keywords":"Health equity; Medicine; Generalizability theory; Socioeconomic status; Residence; Ethnic group; Equity (law); Randomized controlled trial; Sexual orientation; Health care; Clinical trial; Family medicine; Public health; Demography; Psychology; Environmental health; Population; Nursing; Social psychology; Political science; Sociology","score_opus":0.9682600559117902,"score_gpt":0.7912596076440441,"score_spread":0.17700044826774608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392381525","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":[0.0000010767817,0.9002057,0.008881762,0.08708767,0.0018172804,0.0017732794,0.000024824805,0.000012803937,0.00019565706],"genre_scores_gemma":[0.000010184213,0.96285784,0.020138426,0.014677041,0.0021633874,0.000053946016,0.00001047167,0.00001844579,0.0000702621],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.62510145,0.23700316,0.13510898,0.0010494924,0.000592612,0.0011442887],"domain_scores_gemma":[0.112032875,0.7272549,0.15812652,0.00060198404,0.0008835567,0.0011001129],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7455212,0.0003257434,0.03534146,0.00032200385,0.00017427345,0.000014613422,0.00048486446,0.0010428212,0.0004716623],"category_scores_gemma":[0.9775322,0.00019426008,0.006811041,0.0004815525,0.00009189045,0.000093958224,0.00016433757,0.0019974217,0.000005477985],"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":[0.00003839066,0.000121695164,0.00057347835,0.04740875,0.00036115438,0.000084706975,0.00009107674,0.0000030508515,6.8610846e-9,0.02855567,0.16354626,0.7592158],"study_design_scores_gemma":[0.0003964871,0.00047577554,0.00008971491,0.0347413,0.0014535869,0.000120846205,0.000032776043,0.0000011819197,2.7936309e-9,0.118604176,0.8439582,0.0001259732],"about_ca_topic_score_codex":0.0001930751,"about_ca_topic_score_gemma":0.0004646367,"teacher_disagreement_score":0.75908977,"about_ca_system_score_codex":0.00036156428,"about_ca_system_score_gemma":0.018254457,"threshold_uncertainty_score":0.9873111},"labels":[],"label_agreement":null},{"id":"W4392786405","doi":"10.1016/j.jclinepi.2024.111311","title":"Representation of published core outcome sets in practice guidelines","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Impact; McMaster University","funders":"Bundesministerium für Bildung und Forschung; National Institute for Health and Care Research; Medical Research Council; Sanofi; Pfizer; Eli Lilly and Company","keywords":"Outcome (game theory); Representation (politics); Core (optical fiber); Medicine; Computer science; Mathematics; Political science; Mathematical economics","score_opus":0.8447320263119009,"score_gpt":0.7554921065568609,"score_spread":0.08923991975503998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392786405","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":[0.21534726,0.0028409201,0.0070741684,0.7443014,0.0063677165,0.0005053681,0.0000074187847,0.000077570214,0.023478199],"genre_scores_gemma":[0.900931,0.0052279565,0.086236194,0.005160232,0.0018547956,0.0000074073146,0.0000021549783,0.000018053337,0.0005622243],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97945637,0.01051495,0.008600669,0.00030928807,0.00072111556,0.0003975854],"domain_scores_gemma":[0.84202844,0.15187712,0.0028757511,0.00032241637,0.00262605,0.0002702188],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16255063,0.00008260471,0.0013933906,0.0003587518,0.000037033526,0.000028268889,0.0006025325,0.00043139272,0.00017599617],"category_scores_gemma":[0.8302517,0.00006194772,0.00047135097,0.0008388335,0.00057873636,0.00071369077,0.00009851973,0.001372071,0.000015771768],"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":[0.000392776,0.0001940305,0.6129265,0.000052026826,0.00011727147,0.00030870183,0.0006216089,0.00017614156,0.000021607664,0.07395694,0.21661901,0.094613396],"study_design_scores_gemma":[0.00095698907,0.0008567026,0.22235207,0.00053087616,0.00011212692,0.0001318585,0.005000361,0.0037435445,0.00001563103,0.30142498,0.4646546,0.00022025824],"about_ca_topic_score_codex":0.0013922747,"about_ca_topic_score_gemma":0.00032333157,"teacher_disagreement_score":0.73914117,"about_ca_system_score_codex":0.00008288094,"about_ca_system_score_gemma":0.0008294093,"threshold_uncertainty_score":0.8623304},"labels":[],"label_agreement":null},{"id":"W4392948126","doi":"10.1016/j.jclinepi.2024.111328","title":"Only half of the authors of overviews of exercise-related interventions use some strategy to manage overlapping primary studies—a metaresearch study","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Meta-analysis; Psychological intervention; MEDLINE; Data extraction; Systematic review; Medicine; Cochrane Library; Medical physics; Computer science; Pathology","score_opus":0.9767326560069993,"score_gpt":0.7571523398584771,"score_spread":0.21958031614852225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392948126","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":[0.0040096473,0.98909235,0.00040113772,0.0007390671,0.0026801296,0.002868396,0.000076076,0.0000020590994,0.00013116136],"genre_scores_gemma":[0.0016449877,0.9905786,0.002121316,0.000093620445,0.00016762283,0.00003232804,0.0000035609078,0.000037092293,0.0053208657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.56797785,0.25280857,0.17058797,0.0017252979,0.006249492,0.00065082667],"domain_scores_gemma":[0.5099957,0.3024992,0.17176414,0.00841654,0.006598307,0.0007261019],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.66212404,0.00074323814,0.06686962,0.0018315852,0.00007494958,0.00008059326,0.0061194487,0.0006885585,0.0009098577],"category_scores_gemma":[0.60069615,0.00027413617,0.043198656,0.0036934481,0.00059144455,0.0003097198,0.001890727,0.002837905,0.00018433768],"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":[0.00007528307,0.0016179475,0.005464688,0.049513225,0.028842991,0.00005520382,0.00045664716,0.0004003363,4.0804812e-7,0.007916402,0.05106317,0.8545937],"study_design_scores_gemma":[0.00093609886,0.0042602737,0.024317117,0.13356337,0.06523563,0.00013275255,0.0020951235,0.00020711776,1.2025914e-7,0.04199677,0.7266109,0.00064469967],"about_ca_topic_score_codex":0.000059655325,"about_ca_topic_score_gemma":0.000062047395,"teacher_disagreement_score":0.853949,"about_ca_system_score_codex":0.00010221505,"about_ca_system_score_gemma":0.0009287661,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W4393128968","doi":"10.1016/j.jclinepi.2024.111333","title":"An international modified Delphi process supported updating the web-based \"right review\" tool","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University; University of Toronto; St. Michael's Hospital","funders":"National Health and Medical Research Council; Health Research Board","keywords":"CLARITY; Delphi method; Computer science; Set (abstract data type); Process (computing); Delphi; Process management; Medical education; Medicine; Artificial intelligence; Engineering","score_opus":0.8617134244740399,"score_gpt":0.687659149941074,"score_spread":0.17405427453296585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393128968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38290086,0.021311326,0.29682934,0.27396888,0.013007549,0.0014988978,0.000056415996,0.00003360072,0.010393136],"genre_scores_gemma":[0.9638494,0.0023742528,0.0077217636,0.023491085,0.0017429565,0.00001703264,0.000012614876,0.000016324202,0.0007745559],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.82451975,0.09956435,0.06992636,0.0011953524,0.0043354305,0.0004587544],"domain_scores_gemma":[0.61680925,0.32435855,0.047804657,0.0045528295,0.0058244113,0.00065029267],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6682207,0.00026982772,0.008019195,0.00029486412,0.000095479365,0.000278487,0.003985393,0.00022687772,0.012955185],"category_scores_gemma":[0.6699022,0.00009292318,0.005012386,0.0008368686,0.00021385695,0.0005061963,0.00007091709,0.0011724412,0.0006840222],"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":[0.00012419309,0.00031441572,0.13684866,0.00054539106,0.0014886797,0.0001800583,0.000102097474,0.0047677443,0.00002224626,0.02940669,0.65994006,0.1662598],"study_design_scores_gemma":[0.00040463195,0.0002668428,0.023508372,0.0009625951,0.00066768104,0.00021199169,0.000088343724,0.5264258,0.0000025429044,0.037585378,0.40969414,0.00018173284],"about_ca_topic_score_codex":0.0000016472665,"about_ca_topic_score_gemma":0.00000489178,"teacher_disagreement_score":0.58094853,"about_ca_system_score_codex":0.00002527979,"about_ca_system_score_gemma":0.0006677615,"threshold_uncertainty_score":0.9879471},"labels":[],"label_agreement":null},{"id":"W4393132079","doi":"10.1016/j.jclinepi.2024.111332","title":"Validation of case-ascertainment algorithms using health administrative data to identify people who inject drugs in Ontario, Canada","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; SickKids Foundation; Hospital for Sick Children; University of British Columbia; McGill University; Institute for Clinical Evaluative Sciences; University of Ottawa; Vancouver Hospital and Health Sciences Centre; Ontario Drug Policy Research Network; St. Paul's Hospital; Toronto Rehabilitation Institute; Public Health Ontario; Toronto General Hospital; University Health Network; Western University; University of Toronto; Bruyère; Toronto Public Health; Centre for Advancing Health Outcomes; Jewish General Hospital; BC Centre for Disease Control; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Public health; Emergency department; Pharmacoepidemiology; Population; Public health surveillance; Injection drug use; Medical prescription; Family medicine; Drug; Medical emergency; Algorithm; Environmental health; Psychiatry; Drug injection; Pharmacology; Nursing","score_opus":0.48770665766567256,"score_gpt":0.5882311413564911,"score_spread":0.10052448369081857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393132079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97922254,0.0004980474,0.0024194107,0.015734803,0.0016086737,0.00035960143,0.000076918026,0.0000061266323,0.00007386778],"genre_scores_gemma":[0.9841323,0.00015653169,0.012441918,0.0025706452,0.00049912406,0.000002179924,0.000050934508,0.000022604121,0.0001237483],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9897035,0.003046126,0.00587055,0.00049132673,0.00044528718,0.00044321222],"domain_scores_gemma":[0.98129874,0.015412349,0.0018092461,0.00058687065,0.00023418477,0.0006585798],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024900531,0.00020178063,0.0029247445,0.00025202456,0.000040557054,0.000009432561,0.00032619617,0.00021315088,0.00014226105],"category_scores_gemma":[0.024182893,0.00015933569,0.00020521999,0.0003544275,0.000088658,0.00016782139,0.00018125909,0.0015519529,0.000004166873],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014621897,0.00074654457,0.86102325,0.00064758223,0.0010855114,0.0055809096,0.020759968,0.0027431163,0.000104633145,0.00023286672,0.06172543,0.043888018],"study_design_scores_gemma":[0.003716658,0.0074860384,0.9051536,0.0033426678,0.00054750236,0.009185954,0.030594097,0.026086958,0.000120860925,0.0009998087,0.01229377,0.0004720976],"about_ca_topic_score_codex":0.8851311,"about_ca_topic_score_gemma":0.95199746,"teacher_disagreement_score":0.066866376,"about_ca_system_score_codex":0.0011377903,"about_ca_system_score_gemma":0.013355331,"threshold_uncertainty_score":0.99223804},"labels":[],"label_agreement":null},{"id":"W4393219600","doi":"10.1016/j.jclinepi.2024.111336","title":"Randomized controlled trials of switching to a new medication vs continuing a chronic medication may underestimate the risk of adverse events in those continuing because of asymmetric depletion of susceptibles","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","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; St. Michael's Hospital; Sinai Health System","funders":"","keywords":"Medicine; Adverse effect; Randomized controlled trial; Intensive care medicine; Internal medicine","score_opus":0.5116991747776183,"score_gpt":0.6037577730203197,"score_spread":0.09205859824270146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393219600","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":[0.0647161,0.0049172556,0.767059,0.15163332,0.0051890104,0.0062047928,0.00019527628,0.000024921741,0.00006029342],"genre_scores_gemma":[0.28302416,0.01739632,0.68018854,0.011123408,0.0077426406,0.00017438653,0.000026217182,0.0001867222,0.00013759015],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7252874,0.19097647,0.07942755,0.0010468104,0.0023432267,0.0009185865],"domain_scores_gemma":[0.07470493,0.84796375,0.075032964,0.0009114494,0.0011193508,0.0002675421],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4750215,0.00059432915,0.03410593,0.0014904992,0.000023734074,0.0000039670676,0.0012156818,0.0021738624,0.00014725207],"category_scores_gemma":[0.9735036,0.0003282446,0.0060969545,0.0008076746,0.00088458095,0.00008885339,0.00025026122,0.0045782356,0.0000038147436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.57456654,0.002142202,0.028698841,0.014280876,0.037344962,0.000121522746,0.003042163,0.0019397243,0.00071612996,0.032552194,0.13599846,0.16859637],"study_design_scores_gemma":[0.20186546,0.0016807675,0.0030354203,0.018322328,0.0128538385,0.000017877954,0.00009246861,0.0034510654,0.00010035057,0.7577309,0.0005483088,0.00030119394],"about_ca_topic_score_codex":0.0003105901,"about_ca_topic_score_gemma":0.000057763402,"teacher_disagreement_score":0.7251787,"about_ca_system_score_codex":0.00016576573,"about_ca_system_score_gemma":0.0009972524,"threshold_uncertainty_score":0.999917},"labels":[],"label_agreement":null},{"id":"W4393237046","doi":"10.1016/j.jclinepi.2024.111335","title":"Pilot and feasibility trials in surgery are incompletely reported according to the CONSORT checklist: a meta-research study","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"","keywords":"Checklist; Consolidated Standards of Reporting Trials; Medicine; Meta-analysis; Research design; Clinical trial; MEDLINE; Family medicine; Physical therapy; Medical physics; Surgery; Psychology; Internal medicine; Statistics; Biology","score_opus":0.9967516912296144,"score_gpt":0.8157535328632577,"score_spread":0.1809981583663567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393237046","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061758375,0.97965103,0.0003726814,0.0060135587,0.0030503755,0.0045970557,0.000037876493,0.000003080434,0.000098504155],"genre_scores_gemma":[0.008951014,0.9865304,0.0010322204,0.00080920727,0.0016151987,0.00022997502,0.0000027562157,0.000037880378,0.00079132424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.030606724,0.75062364,0.2097117,0.0025750464,0.005716557,0.000766365],"domain_scores_gemma":[0.0059322654,0.86993957,0.11443573,0.0054654377,0.003452156,0.00077485264],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9866453,0.00087276415,0.14989287,0.0025814725,0.00017328154,0.00058663,0.0040363595,0.00053590414,0.0011274216],"category_scores_gemma":[0.9916371,0.00026281658,0.035083454,0.004467773,0.0004812826,0.00015430799,0.001203531,0.005562559,0.0006184678],"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":[0.0001949489,0.0008035767,0.23110333,0.003237168,0.022685654,0.0007205619,0.000107133616,0.000011923044,1.6654505e-8,0.0002481897,0.2780925,0.462795],"study_design_scores_gemma":[0.00024496493,0.0006403392,0.02040681,0.0032667469,0.024891566,0.0004893339,0.0007783501,0.000038904906,1.7445279e-9,0.008935271,0.94005805,0.0002496763],"about_ca_topic_score_codex":0.000085547224,"about_ca_topic_score_gemma":0.00045308613,"teacher_disagreement_score":0.66196555,"about_ca_system_score_codex":0.00013513707,"about_ca_system_score_gemma":0.0017609289,"threshold_uncertainty_score":0.9999824},"labels":[],"label_agreement":null},{"id":"W4393857975","doi":"10.1016/j.jclinepi.2024.111344","title":"GRADE concept paper 8: judging the certainty of discrimination performance estimates of prognostic models in a body of validation studies","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"McMaster University; Impact; Ted Rogers Centre for Heart Research","funders":"","keywords":"Predictive modelling; Medicine; Meta-analysis; Systematic review; Clinical Practice; Prognostic model; Computer science; MEDLINE; Oncology; Internal medicine; Overall survival; Machine learning; Biology; Physical therapy","score_opus":0.5340898900833674,"score_gpt":0.5617877192448818,"score_spread":0.02769782916151442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393857975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98108697,0.005905823,0.00060701696,0.011873858,0.00028954877,0.00019633783,0.0000029798152,0.0000031245552,0.000034353066],"genre_scores_gemma":[0.9921078,0.0057191947,0.0017862065,0.0002672513,0.00009721564,0.0000091417505,0.0000034142804,0.000006609663,0.0000031577251],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99583524,0.000781606,0.002965917,0.0001249088,0.00016747706,0.00012481767],"domain_scores_gemma":[0.96909827,0.029097691,0.001344239,0.00012618107,0.00028992014,0.000043713437],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007278922,0.000095963325,0.0015404439,0.00011119602,0.000013459603,0.0000013528977,0.00007821438,0.00012315647,0.000012712939],"category_scores_gemma":[0.025684059,0.000048180103,0.00033178314,0.00012654488,0.00033351986,0.00009853318,0.000028526862,0.00036921207,4.2040355e-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":[0.00025555352,0.00060071854,0.9711883,0.0005863044,0.00065239164,0.000011134384,0.00090101705,0.0073620826,0.00014197547,0.0064584487,0.00036569432,0.011476354],"study_design_scores_gemma":[0.0014266463,0.0024552136,0.9219092,0.002873388,0.000774479,0.00003044382,0.000675703,0.047062926,0.0018179624,0.02089941,0.000024363082,0.000050241324],"about_ca_topic_score_codex":0.000019612755,"about_ca_topic_score_gemma":0.000002970907,"teacher_disagreement_score":0.0492791,"about_ca_system_score_codex":0.00003393755,"about_ca_system_score_gemma":0.000109687084,"threshold_uncertainty_score":0.982523},"labels":[],"label_agreement":null},{"id":"W4394595724","doi":"10.1016/j.jclinepi.2024.111358","title":"A method was developed for correcting the bias in the usual study weights in meta-analyses: author’s reply","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Universiteit Leiden","keywords":"Group (periodic table); Medicine; Cochrane collaboration; Meta-analysis; Internal medicine; Cochrane Library; Physics","score_opus":0.9561120274595499,"score_gpt":0.747584452092216,"score_spread":0.2085275753673339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394595724","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.004935258,0.0010452871,0.012017035,0.97106296,0.007915251,0.0025073008,0.000016293574,0.000018207615,0.00048242707],"genre_scores_gemma":[0.0025168126,0.00019081279,0.013555274,0.9694559,0.012167767,0.0004769921,0.000026621232,0.000042348835,0.0015674803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8184163,0.15010485,0.02839418,0.00069394556,0.0009723255,0.0014184155],"domain_scores_gemma":[0.37431946,0.6097271,0.014212521,0.0007998235,0.00070867623,0.00023243488],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.45151624,0.0004454947,0.007241882,0.00065264304,0.0004989908,0.000018820137,0.0012962316,0.0022579539,0.0002081249],"category_scores_gemma":[0.42252162,0.0001733459,0.0019223717,0.0006757986,0.00015635454,0.00011358649,0.00018801022,0.028540935,0.0000792806],"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":[0.0003005536,0.00009821637,0.013061278,0.00067657995,0.001398111,0.00013888758,0.008318068,0.00004447986,1.0120696e-8,0.00024240049,0.9678722,0.007849234],"study_design_scores_gemma":[0.0014768423,0.0010540152,0.011756392,0.00070503465,0.0031380472,0.0000866957,0.0053581903,0.0030860098,3.1599637e-8,0.015474046,0.95767784,0.00018685154],"about_ca_topic_score_codex":0.0007445584,"about_ca_topic_score_gemma":0.0008707846,"teacher_disagreement_score":0.45962223,"about_ca_system_score_codex":0.00023949788,"about_ca_system_score_gemma":0.0029223189,"threshold_uncertainty_score":0.9990373},"labels":[],"label_agreement":null},{"id":"W4394602376","doi":"10.1016/j.jclinepi.2024.111360","title":"A brief step-by-step guide on conducting a systematic review and meta-analysis of prognostic model studies","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Ted Rogers Centre for Heart Research; Impact","funders":"","keywords":"Systematic review; Meta-analysis; Medicine; MEDLINE; Intensive care medicine; Internal medicine","score_opus":0.9776746505240534,"score_gpt":0.7435889218324542,"score_spread":0.23408572869159927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394602376","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":[0.0000012112852,0.9830441,0.010724576,0.0024604811,0.00047572106,0.002842518,0.00016673039,0.0000041193584,0.000280566],"genre_scores_gemma":[0.0000053023828,0.9771298,0.011798694,0.003042522,0.00013157925,0.00016415212,0.000008773572,0.000043476353,0.0076756612],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.5636219,0.24251159,0.18618876,0.0023701247,0.0047056307,0.00060203637],"domain_scores_gemma":[0.18143333,0.5866727,0.21899107,0.0062248143,0.005934823,0.00074323756],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.7408726,0.0013576171,0.25987008,0.0017716439,0.000085922424,0.00015164117,0.003476377,0.0008084385,0.0007300408],"category_scores_gemma":[0.89516777,0.0004651002,0.081924945,0.0035669068,0.0005262677,0.0001720734,0.0005387527,0.002232034,0.00025612145],"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":[0.0000024608694,0.00006588134,0.000011936289,0.4022806,0.42031282,0.000017301174,0.000011414453,0.000043730062,3.1834855e-9,0.0010506791,0.17139927,0.0048039053],"study_design_scores_gemma":[0.00006469447,0.0002130959,4.3746545e-7,0.054396298,0.7426251,0.000102902115,0.0000655666,0.0023000261,1.6413076e-9,0.00069719687,0.19929633,0.00023831376],"about_ca_topic_score_codex":0.0000051870566,"about_ca_topic_score_gemma":0.000009967307,"teacher_disagreement_score":0.38218853,"about_ca_system_score_codex":0.000076675264,"about_ca_system_score_gemma":0.00058043766,"threshold_uncertainty_score":0.99991745},"labels":[],"label_agreement":null},{"id":"W4394620875","doi":"10.1016/j.jclinepi.2024.111343","title":"Large scoping reviews: managing volume and potential chaos in a pool of evidence sources","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","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":"Queen's University; Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"National Health and Medical Research Council","keywords":"CHAOS (operating system); Data science; Management science; Computer science; Engineering","score_opus":0.7479294200492211,"score_gpt":0.7059961293290595,"score_spread":0.04193329072016161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394620875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83448654,0.054601025,0.0121320775,0.094224356,0.0038533877,0.00059136923,0.0000020818245,0.000008376258,0.00010077113],"genre_scores_gemma":[0.89967704,0.09178196,0.002329521,0.0039405287,0.0018993538,0.000015030555,5.373894e-7,0.000007218589,0.0003487805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9825362,0.011072214,0.0053466177,0.00023561675,0.00020132432,0.00060802413],"domain_scores_gemma":[0.9617246,0.03578736,0.0017191668,0.00015636695,0.0001881351,0.00042438175],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12019171,0.00008241069,0.0014378508,0.00030947741,0.00012931177,0.0000053953368,0.00023991673,0.00022353542,0.00026389756],"category_scores_gemma":[0.13597947,0.00004964764,0.00018797952,0.00033642148,0.00020298528,0.00029388297,0.000115202456,0.0017164459,0.000060020277],"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":[0.00013271529,0.000062539926,0.92620504,0.004789621,0.000018076833,0.000027622436,0.0021408186,0.000027460499,0.000017960756,0.000633023,0.01807509,0.04787004],"study_design_scores_gemma":[0.00064987503,0.00080979767,0.8718574,0.047287676,0.000024775924,0.000036352696,0.002515061,0.020884203,6.2238894e-7,0.01291097,0.04290668,0.000116554336],"about_ca_topic_score_codex":0.0001416975,"about_ca_topic_score_gemma":0.00006988757,"teacher_disagreement_score":0.09028383,"about_ca_system_score_codex":0.00005235127,"about_ca_system_score_gemma":0.0013914404,"threshold_uncertainty_score":0.9059478},"labels":[],"label_agreement":null},{"id":"W4394686963","doi":"10.1016/j.jclinepi.2024.111357","title":"A method was developed for correcting the bias in the usual study weights in meta-analyses: comment on Walter and Balakrishnan","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Meta-analysis; Weighting; Variance (accounting); Statistics; Mathematics; Publication bias; Inverse; Standard error; Econometrics; Medicine; Confidence interval; Economics","score_opus":0.9801731143303548,"score_gpt":0.7473868855703547,"score_spread":0.2327862287600001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394686963","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011249827,0.0029909199,0.014015323,0.9670604,0.0021624716,0.0022410555,0.000016206879,0.0000015307592,0.00026229137],"genre_scores_gemma":[0.010632677,0.00016881083,0.018984783,0.9654563,0.002997249,0.00020057248,0.000006276267,0.000035113455,0.0015181896],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.30075094,0.59635,0.09446637,0.002350953,0.0051632733,0.0009184513],"domain_scores_gemma":[0.13947256,0.8173554,0.038998913,0.0029585054,0.0010615526,0.00015308349],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.84803194,0.0007289265,0.02940395,0.001052226,0.00014550159,0.0004202366,0.0040456145,0.00083437137,0.0006236541],"category_scores_gemma":[0.64544344,0.0001926335,0.011362853,0.0012900052,0.00019296422,0.00010670708,0.00031475243,0.006617555,0.00010716686],"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":[0.000065325265,0.00017836223,0.021444406,0.000056066074,0.0068652765,0.0001899011,0.0010649054,0.00012513294,2.294356e-8,0.000153585,0.9545691,0.01528794],"study_design_scores_gemma":[0.0006682724,0.00095344096,0.010290689,0.00014058204,0.011475002,0.0002103459,0.0017657527,0.0041305944,1.2291957e-7,0.03142697,0.9387202,0.00021801642],"about_ca_topic_score_codex":0.00008814927,"about_ca_topic_score_gemma":0.0003254575,"teacher_disagreement_score":0.22100538,"about_ca_system_score_codex":0.00006477205,"about_ca_system_score_gemma":0.000279624,"threshold_uncertainty_score":0.9985381},"labels":[],"label_agreement":null},{"id":"W4394859071","doi":"10.1016/j.jclinepi.2024.111366","title":"“We are not invited”: Australian focus group results on how to improve ethnic diversity in trials","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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 Ottawa; Public Health Ontario; Toronto Rehabilitation Institute; University of Toronto","funders":"National Health and Medical Research Council; Medical Research Council","keywords":"Ethnic group; Diversity (politics); Ethnically diverse; Focus group; Cultural diversity; Medicine; Clinical trial; Gerontology; Sociology; Pathology","score_opus":0.9037877892806783,"score_gpt":0.7015553056485554,"score_spread":0.20223248363212287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394859071","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2737306,0.0005937304,0.00042026723,0.7209476,0.0034397026,0.00049362105,0.00006365501,0.000025916375,0.0002848783],"genre_scores_gemma":[0.95341855,0.007400689,0.0037283949,0.028533624,0.0043345145,0.000006985969,0.000004727211,0.000033178352,0.0025393069],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9695561,0.016679697,0.0104692085,0.0010553657,0.0012938038,0.00094583683],"domain_scores_gemma":[0.21851388,0.77388775,0.003689913,0.0010764622,0.0008341877,0.0019977936],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3056071,0.00028357422,0.0052753887,0.0006517488,0.00006750548,0.000023230878,0.0007175675,0.0021387108,0.00008404002],"category_scores_gemma":[0.88494456,0.0001875327,0.0018294373,0.00064756954,0.00053482124,0.00012383575,0.0006409674,0.013373502,0.00013481952],"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":[0.08480103,0.0029328247,0.19183558,0.0013979629,0.0018395204,0.009023477,0.0010982398,0.00018232415,0.0009105666,0.021564918,0.35170215,0.3327114],"study_design_scores_gemma":[0.014319901,0.02629913,0.68148226,0.007707205,0.0004634639,0.0001439595,0.00049128,0.0003511727,0.00023536565,0.20368995,0.0643598,0.00045650383],"about_ca_topic_score_codex":0.000115674935,"about_ca_topic_score_gemma":0.00057790853,"teacher_disagreement_score":0.75720805,"about_ca_system_score_codex":0.0002699067,"about_ca_system_score_gemma":0.00047879625,"threshold_uncertainty_score":0.9991567},"labels":[],"label_agreement":null},{"id":"W4394910161","doi":"10.1016/j.jclinepi.2024.111367","title":"Research Integrity definitions and challenges","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Healthcare cost, quality, practices","field":"Health Professions","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Key (lock); Epidemiology; MEDLINE; Medicine; Data science; Computer science; Political science; Pathology; Computer security","score_opus":0.9892677528996713,"score_gpt":0.7978616850336153,"score_spread":0.19140606786605596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394910161","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23150043,0.06494513,0.00064240705,0.6853312,0.005758099,0.00027432325,0.000014259193,0.000050000843,0.01148413],"genre_scores_gemma":[0.6507246,0.32174397,0.0064281044,0.01528218,0.005494435,0.00002321523,0.0000020267414,0.000028568364,0.0002729155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.877667,0.11404151,0.0066930195,0.00041540773,0.00037829066,0.0008047914],"domain_scores_gemma":[0.46741593,0.52851564,0.001606855,0.00036973058,0.0012953465,0.0007965257],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32846287,0.00013390185,0.0017953526,0.0003446352,0.00042457593,0.000009216411,0.00031684389,0.0010979186,0.00035807534],"category_scores_gemma":[0.45211905,0.00009144865,0.00030531728,0.00024126371,0.0007919517,0.00031120962,0.00024442055,0.015321471,0.000515871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027512544,0.00017239043,0.13482334,0.0015268906,0.00016785042,0.00014623297,0.0012514562,5.8454725e-7,0.0000022382735,0.686911,0.04436704,0.13035586],"study_design_scores_gemma":[0.00032657807,0.00074982713,0.25155067,0.0010049345,0.00003235276,0.00008556661,0.0033488735,0.000098634126,1.5088222e-7,0.29657426,0.4461567,0.00007141479],"about_ca_topic_score_codex":0.00025890936,"about_ca_topic_score_gemma":0.00037010002,"teacher_disagreement_score":0.670049,"about_ca_system_score_codex":0.00011255279,"about_ca_system_score_gemma":0.002166191,"threshold_uncertainty_score":0.9869502},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","research_integrity"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4396495329","doi":"10.1016/j.jclinepi.2024.111374","title":"Reporting of health equity considerations in vaccine trials for COVID-19: author’s reply","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Generalizability theory; Coronavirus disease 2019 (COVID-19); Equity (law); Health equity; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Clinical trial; Medicine; Family medicine; Psychology; Actuarial science; Political science; Business; Public health; Nursing; Virology; Infectious disease (medical specialty); Pathology; Disease","score_opus":0.7956416128210876,"score_gpt":0.6728571771639621,"score_spread":0.12278443565712549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396495329","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.00049099594,0.0057806103,0.0071731023,0.97984135,0.0053373766,0.0007898534,0.000040884977,0.000020091702,0.0005257289],"genre_scores_gemma":[0.009083257,0.0025664126,0.0073898053,0.9610036,0.018918356,0.000020306068,0.000024717658,0.000031042033,0.000962496],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8558841,0.055687163,0.08541093,0.0009770942,0.0007404524,0.0013002887],"domain_scores_gemma":[0.38262275,0.47727737,0.13701425,0.00079279486,0.0014323643,0.0008604605],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.50093967,0.00026057463,0.010851953,0.00044689476,0.00025333586,0.00003031355,0.00042720066,0.0016114549,0.00049691164],"category_scores_gemma":[0.93471205,0.0001985887,0.0026316952,0.0002552233,0.000101615115,0.00013742328,0.000120513316,0.0039854287,0.000004934316],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107889384,0.000056348654,0.025022117,0.00041974106,0.00019726664,0.0003378725,0.0005237061,0.000045435645,3.2719691e-7,0.0065089106,0.96292186,0.0038585248],"study_design_scores_gemma":[0.0008379288,0.00053587346,0.0042847325,0.0003780841,0.00014811242,0.00005537844,0.00012566104,0.000015498083,1.9399808e-7,0.29132047,0.70217896,0.00011909915],"about_ca_topic_score_codex":0.0013900223,"about_ca_topic_score_gemma":0.0016366133,"teacher_disagreement_score":0.47326133,"about_ca_system_score_codex":0.00040989884,"about_ca_system_score_gemma":0.014957703,"threshold_uncertainty_score":0.9996847},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4396768319","doi":"10.1016/j.jclinepi.2024.111385","title":"Epistemic inclusion is necessary for diverse, global, and meaningful research","year":2024,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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":"Memorial University of Newfoundland","funders":"","keywords":"Inclusion (mineral); Epistemology; Management science; Psychology; Sociology; Philosophy; Social science; Economics","score_opus":0.7668998111667518,"score_gpt":0.7022851408509727,"score_spread":0.06461467031577905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396768319","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":[0.006459428,0.012045424,0.00023881803,0.017021071,0.96026343,0.0013976013,0.0009879515,0.000019910422,0.0015663614],"genre_scores_gemma":[0.0014188921,0.029350877,0.0022688194,0.009643715,0.95404154,0.000078490164,0.00035070252,0.00005768192,0.0027892534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9654807,0.020418156,0.01073292,0.00077961,0.0012397069,0.0013489045],"domain_scores_gemma":[0.75995404,0.23120329,0.005460681,0.00040635816,0.0019370285,0.0010386184],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.14789079,0.00036525424,0.004033065,0.0002714306,0.0014343585,0.0000081028265,0.00076761167,0.004009279,0.00018289432],"category_scores_gemma":[0.108057365,0.00025594493,0.0007561519,0.00024045134,0.00046171178,0.00010289269,0.0025811782,0.0100294985,0.00017747507],"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":[0.001918047,0.00011247944,0.029137447,0.0070650224,0.00015562323,0.000025117013,0.00049706176,5.5859584e-7,1.9408002e-7,0.0010784508,0.95277834,0.0072316863],"study_design_scores_gemma":[0.0019643726,0.0034404977,0.00046156388,0.006558282,0.0001203607,0.0000032565124,0.0006250179,0.00008407403,9.3266266e-8,0.1349875,0.8515989,0.00015605756],"about_ca_topic_score_codex":0.00045409688,"about_ca_topic_score_gemma":0.0001730035,"teacher_disagreement_score":0.21078514,"about_ca_system_score_codex":0.0007551668,"about_ca_system_score_gemma":0.00397706,"threshold_uncertainty_score":0.9999893},"labels":[],"label_agreement":null},{"id":"W4396828139","doi":"10.1016/j.jclinepi.2024.111392","title":"High certainty evidence is stable and trustworthy, whereas evidence of moderate or lower certainty may be equally prone to being unstable","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University; University of Toronto","funders":"Agency for Healthcare Research and Quality","keywords":"Certainty; Trustworthiness; Best evidence; Medicine; Psychology; Social psychology; Philosophy; Intensive care medicine; Epistemology","score_opus":0.8821027366395712,"score_gpt":0.6445481323345401,"score_spread":0.23755460430503106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396828139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7572076,0.022527479,0.12361224,0.091966495,0.0028976696,0.0010959199,0.00002393622,0.000011213095,0.00065745035],"genre_scores_gemma":[0.94453,0.0038614604,0.034656253,0.0056237145,0.0005336592,0.000013439417,4.864802e-7,0.000022734961,0.01075823],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8680737,0.072503,0.052428357,0.0020066726,0.004047315,0.00094095204],"domain_scores_gemma":[0.5151003,0.45466688,0.021342972,0.0032799141,0.0043190615,0.0012908935],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5330797,0.00046082056,0.013733498,0.00048765182,0.000121702236,0.00035475602,0.0019901304,0.00039740905,0.008163485],"category_scores_gemma":[0.6749081,0.00020215665,0.0030312755,0.0013639942,0.0003387948,0.001017841,0.00041826916,0.0010732053,0.00023677365],"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":[0.005757909,0.00047787244,0.20832615,0.00198456,0.0032219547,0.0005096446,0.0015441028,0.021172153,0.00024417177,0.03515249,0.49561647,0.22599255],"study_design_scores_gemma":[0.0019362568,0.010428511,0.0573658,0.02037405,0.003950809,0.0008190041,0.0012869319,0.28175926,0.00013804926,0.3232572,0.29708463,0.0015994759],"about_ca_topic_score_codex":0.00022546742,"about_ca_topic_score_gemma":0.00014587361,"teacher_disagreement_score":0.38216388,"about_ca_system_score_codex":0.00007030123,"about_ca_system_score_gemma":0.0009333911,"threshold_uncertainty_score":0.9927432},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4399051901","doi":"10.1016/j.jclinepi.2024.111399","title":"Physicians found an interactive tool displaying structured evidence summaries for multiple comparisons understandable and useful: a qualitative user testing study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Sciences Research and Education","field":"Health Professions","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":"McMaster University; Impact","funders":"Helse Sør-Øst RHF; Norges Forskningsråd","keywords":"Computer science; Qualitative research; Data science; Information retrieval; Human–computer interaction","score_opus":0.8587947024899253,"score_gpt":0.7316452294630865,"score_spread":0.12714947302683877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399051901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.940203,0.00050666777,0.047429923,0.0077568744,0.00303943,0.0009936433,0.000030607018,0.000020621083,0.000019215027],"genre_scores_gemma":[0.97298366,0.00010579919,0.023921851,0.0014337305,0.00139722,0.000054442346,0.0000038739904,0.000014066018,0.000085357366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98197407,0.013376869,0.0033451575,0.0003949287,0.00024043425,0.0006685468],"domain_scores_gemma":[0.6387252,0.3584535,0.0015149353,0.00017719404,0.00074898213,0.00038014216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052693475,0.00014678946,0.0013437874,0.00015090684,0.0007390533,0.00004197263,0.00025404152,0.00018508981,0.000026850454],"category_scores_gemma":[0.3102571,0.00009939767,0.00014847667,0.000283182,0.00039532015,0.0009829783,0.00008838568,0.0017997146,0.0000055937326],"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":[0.0012065179,0.00021661053,0.9363389,0.00036661074,0.00013261083,0.0000057390225,0.038973007,0.00016220148,0.000021474729,0.0012385478,0.014866013,0.006471776],"study_design_scores_gemma":[0.0012990565,0.004941698,0.7005573,0.0016318434,0.000081423284,0.0000072841176,0.22166316,0.04240734,8.1761e-7,0.020898405,0.0063495236,0.0001621868],"about_ca_topic_score_codex":0.000655066,"about_ca_topic_score_gemma":0.0018098089,"teacher_disagreement_score":0.34507665,"about_ca_system_score_codex":0.00019659982,"about_ca_system_score_gemma":0.0018738138,"threshold_uncertainty_score":0.9754514},"labels":[],"label_agreement":null},{"id":"W4399303408","doi":"10.1016/j.jclinepi.2024.111407","title":"The impact of an online course on agreement rates of the certainty of evidence assessment using Grading of Recommendations, Assessment, Development, and Evaluation Approach: a before-and-after study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"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":"Ministério da Saúde; Hospital Moinhos de Vento","keywords":"Certainty; Medicine; Agreement; Statistics; Psychology; Mathematics; Linguistics","score_opus":0.9548444353446619,"score_gpt":0.751862279327699,"score_spread":0.2029821560169629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399303408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99008465,0.0008752629,0.0060860114,0.0019907576,0.00026893395,0.00066184974,0.000010866832,3.8702035e-7,0.000021297925],"genre_scores_gemma":[0.97218186,0.00019197074,0.027472006,0.00006121066,0.000057864687,0.000007643827,0.0000015363455,0.000004599061,0.000021284568],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8574845,0.10233355,0.035995368,0.00068690116,0.0032370212,0.00026264027],"domain_scores_gemma":[0.899604,0.07605934,0.021639708,0.0009970124,0.0015824572,0.00011747227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48823184,0.00018140806,0.0043143053,0.00020576309,0.000080983926,0.000043340904,0.0006992851,0.00010570265,0.00013731138],"category_scores_gemma":[0.10039714,0.000057744917,0.0012839515,0.00042510824,0.00028817722,0.0001770763,0.00015145807,0.0004951387,3.4181377e-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":[0.00007521251,0.000675342,0.87757987,0.0000820812,0.0011762755,5.204919e-7,0.00048285243,0.0019365614,0.000025333977,0.00042633057,0.00028517804,0.11725443],"study_design_scores_gemma":[0.0002954509,0.0010966096,0.83332974,0.00041124495,0.000686074,0.000009247577,0.0016214855,0.15805459,0.000005032754,0.0043907706,0.0000580327,0.00004173075],"about_ca_topic_score_codex":0.000033836564,"about_ca_topic_score_gemma":0.000078918354,"teacher_disagreement_score":0.3878347,"about_ca_system_score_codex":0.00006785752,"about_ca_system_score_gemma":0.0007899828,"threshold_uncertainty_score":0.9071806},"labels":[],"label_agreement":null},{"id":"W4399326145","doi":"10.1016/j.jclinepi.2024.111405","title":"Journal requirement for data sharing statements in clinical trials: a cross-sectional study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Research Data Management Practices","field":"Computer Science","cited_by":9,"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; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Cross-sectional study; Medicine; Clinical trial; Family medicine; Internal medicine; Pathology","score_opus":0.9439353789505746,"score_gpt":0.7690848669978573,"score_spread":0.17485051195271728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399326145","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":[0.09720579,0.0011195788,0.87631094,0.011143602,0.013235636,0.00084089284,0.000027546821,0.000026795606,0.0000892363],"genre_scores_gemma":[0.62050426,0.018445102,0.3405805,0.0040144245,0.015243205,0.0000661437,0.00005374771,0.00007322563,0.0010193712],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90408564,0.048366442,0.04195974,0.0024370812,0.0018011647,0.0013499578],"domain_scores_gemma":[0.5598044,0.41394785,0.018574966,0.00488383,0.001357469,0.0014314977],"candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.72173643,0.0002239786,0.0027945556,0.00060890574,0.00014366372,0.0021802424,0.009073701,0.00024685336,0.000051278377],"category_scores_gemma":[0.5587803,0.00015461392,0.0009090809,0.0004354479,0.0002021798,0.023330199,0.0037266505,0.003031953,0.000025018744],"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":[0.0008421012,0.0012363001,0.8965646,0.000060077895,0.0010583411,0.00049320085,0.00002896856,0.00039409715,0.0000012609562,0.01989098,0.013061188,0.06636889],"study_design_scores_gemma":[0.0054183956,0.004454531,0.6980496,0.00017899307,0.00010439818,0.00017752746,0.000065677035,0.14263193,2.96911e-7,0.0463951,0.1023233,0.0002002366],"about_ca_topic_score_codex":0.000032637938,"about_ca_topic_score_gemma":0.000038376384,"teacher_disagreement_score":0.5357304,"about_ca_system_score_codex":0.00014319105,"about_ca_system_score_gemma":0.0009384627,"threshold_uncertainty_score":0.9992681},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","scholarly_communication"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4399332189","doi":"10.1016/j.jclinepi.2024.111408","title":"A scoping review shows that no single existing risk of bias assessment tool considers all sources of bias for cross-sectional studies","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Public Health Agency of Canada; Carleton University; Health Canada; University of Ottawa","funders":"","keywords":"Cross-sectional study; Medicine; Environmental health; Statistics; Computer science; Mathematics","score_opus":0.9868565187968443,"score_gpt":0.7726991555531322,"score_spread":0.21415736324371215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399332189","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":[0.00032591046,0.9874872,0.0054519987,0.00039933113,0.003601912,0.0022912368,0.0001397566,0.0000037148898,0.000298961],"genre_scores_gemma":[0.000053662854,0.9625994,0.034736592,0.0007439937,0.0009918357,0.00007435572,0.000008292155,0.000036192585,0.0007556884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.66324425,0.17470722,0.15463151,0.0020086286,0.0046913917,0.00071702537],"domain_scores_gemma":[0.08142096,0.7059114,0.20255968,0.002485318,0.0072904387,0.00033220404],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7518174,0.0008626673,0.06964951,0.0007618286,0.00012641006,0.0001640776,0.002318417,0.0007638783,0.0010149835],"category_scores_gemma":[0.9281973,0.00036031945,0.03424598,0.0007986988,0.00092308875,0.0002068219,0.00048194287,0.0017915558,0.00012601001],"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":[0.00004571256,0.00028784527,0.11556754,0.35356426,0.019681592,0.000027448128,0.000051399904,0.000130874,1.3012956e-7,0.0011064921,0.079334974,0.43020174],"study_design_scores_gemma":[0.0003161603,0.0007910268,0.00060409476,0.33177784,0.015631855,0.0002453627,0.000070057766,0.0002327725,1.05862185e-7,0.009862597,0.6401319,0.00033621787],"about_ca_topic_score_codex":0.000005555408,"about_ca_topic_score_gemma":0.0000165569,"teacher_disagreement_score":0.5818233,"about_ca_system_score_codex":0.000110938745,"about_ca_system_score_gemma":0.0016447223,"threshold_uncertainty_score":0.9998982},"labels":[],"label_agreement":null},{"id":"W4399359331","doi":"10.1016/j.jclinepi.2024.111410","title":"Barriers and opportunities faced by public health practitioners in using public health guidance on COVID-19: a knowledge translation exercise for the eCOVID-19 RecMap","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Trent University; Impact; McMaster University; Barrie Urology Group; Public Health Ontario; Toronto Public Health","funders":"Canadian Institutes of Health Research","keywords":"Coronavirus disease 2019 (COVID-19); Knowledge translation; Public health; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Medicine; Betacoronavirus; Family medicine; Medical education; Public relations; Political science; Nursing; Virology; Knowledge management; Computer science; Pathology; Infectious disease (medical specialty)","score_opus":0.966022502951752,"score_gpt":0.7803617295301075,"score_spread":0.18566077342164444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399359331","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":[0.010332018,0.005549936,0.14928551,0.8309573,0.0020673894,0.0015067571,0.00019409841,0.000037250553,0.00006975807],"genre_scores_gemma":[0.230179,0.029254008,0.008647605,0.73022074,0.0010640613,0.00027397115,0.000030575357,0.00005156701,0.0002784963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95346844,0.03473699,0.00930773,0.0005843082,0.00037196322,0.001530575],"domain_scores_gemma":[0.7025106,0.28624594,0.0060620387,0.0003943552,0.00043867406,0.0043484303],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20900914,0.00022565993,0.0017451673,0.00060504366,0.0013001637,0.000039623304,0.0003828621,0.0003603891,0.0001983913],"category_scores_gemma":[0.25647414,0.00015790589,0.00025011913,0.0005457817,0.00052568555,0.0006691278,0.00005426026,0.00190609,0.000009619191],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049230084,0.0001539329,0.02864293,0.0030825252,0.00010753313,0.000008165356,0.036980573,0.00033232002,0.000004000811,0.025846275,0.6811108,0.22323865],"study_design_scores_gemma":[0.0019145168,0.00072998245,0.0026339476,0.00039466217,0.000011853254,0.00001890106,0.008937853,0.012084583,7.2460466e-8,0.003492648,0.96965826,0.00012273186],"about_ca_topic_score_codex":0.0006931122,"about_ca_topic_score_gemma":0.0008500396,"teacher_disagreement_score":0.28854746,"about_ca_system_score_codex":0.0014795669,"about_ca_system_score_gemma":0.04161109,"threshold_uncertainty_score":0.9999939},"labels":[],"label_agreement":null},{"id":"W4399467647","doi":"10.1016/j.jclinepi.2024.111422","title":"Guideline for reporting systematic reviews of outcome measurement instruments (OMIs): PRISMA-COSMIN for OMIs 2024","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":99,"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; McMaster University; Centre for Addiction and Mental Health; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; University of Toronto; Western University; St. Michael's Hospital; Canadian Patient Safety Institute; SickKids Foundation; Toronto Western Hospital; Institute for Work & Health","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Systematic review; Medicine; Medical physics; MEDLINE; Pathology","score_opus":0.9759407494500005,"score_gpt":0.7329664620084522,"score_spread":0.24297428744154836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399467647","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"reporting","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013184737,0.025986938,0.92748564,0.016237058,0.010116781,0.0062799067,0.000032669555,0.000006253548,0.0006700038],"genre_scores_gemma":[0.2198962,0.0025886921,0.7525161,0.008272924,0.004257877,0.0006437518,0.000012731932,0.0000981061,0.011713638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.42196974,0.090269126,0.47901297,0.0019305138,0.005930856,0.00088680873],"domain_scores_gemma":[0.1693872,0.39751372,0.41424853,0.005340467,0.012594734,0.00091535365],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9142995,0.00041720792,0.03264676,0.0004985201,0.00007372666,0.00012339649,0.001816049,0.0003456325,0.0009410213],"category_scores_gemma":[0.9691708,0.00017183759,0.017629175,0.00059528416,0.00010812966,0.00020462854,0.00012105936,0.0005675718,0.00017034331],"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":[0.00015493567,0.00019778783,0.061241966,0.03242885,0.0027237535,0.000012344099,0.00009299216,0.000162635,0.000044303426,0.0035508217,0.8268419,0.07254771],"study_design_scores_gemma":[0.0011635645,0.001056777,0.002188522,0.009098844,0.00400316,0.0001902073,0.00020783051,0.04963153,0.000013168781,0.067864835,0.864279,0.0003026125],"about_ca_topic_score_codex":0.0000040177106,"about_ca_topic_score_gemma":0.0000083321775,"teacher_disagreement_score":0.3072446,"about_ca_system_score_codex":0.00009634421,"about_ca_system_score_gemma":0.0003624335,"threshold_uncertainty_score":0.9999722},"labels":[],"label_agreement":null},{"id":"W4399661562","doi":"10.1016/j.jclinepi.2024.111430","title":"Identification of homelessness using health administrative data in Ontario, Canada following a national coding mandate: a validation study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Homelessness and Social Issues","field":"Health Professions","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":"Toronto Public Health; Public Health Ontario; London Health Sciences Centre","funders":"Schulich School of Medicine and Dentistry, Western University; Schulich School of Medicine and Dentistry; Academic Medical Organization of Southwestern Ontario; Public Health Agency; Public Health Agency of Canada; Canadian Institutes of Health Research; Lawson Health Research Institute","keywords":"Mandate; Identification (biology); Coding (social sciences); Public health; Environmental health; Medicine; Political science; Statistics; Nursing","score_opus":0.6128436571547747,"score_gpt":0.643723459957544,"score_spread":0.03087980280276925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399661562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99139416,0.00036588954,0.002795893,0.001238262,0.0037232651,0.00038732687,0.000046809768,0.000006033983,0.0000423565],"genre_scores_gemma":[0.9987787,0.0000905656,0.00043998493,0.00015364717,0.00044114282,0.0000066114885,0.000041785446,0.0000121999665,0.000035379704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9824286,0.008890113,0.007543999,0.00033553367,0.0004689953,0.0003327628],"domain_scores_gemma":[0.9756107,0.019997489,0.0036016074,0.00024463603,0.00038778092,0.00015782063],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05643276,0.00012568854,0.0023217367,0.00017818785,0.0001859664,0.000009281287,0.00039200182,0.00020651215,0.00006886547],"category_scores_gemma":[0.0194161,0.00010322528,0.00015990573,0.00027530486,0.00005519688,0.0003306519,0.00012414879,0.0014300909,0.0000016729169],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011605664,0.00020881394,0.987566,0.00017418635,0.0002010902,0.000046979152,0.0078054853,0.00020636676,0.000010792192,0.002076873,0.00016067333,0.0014266889],"study_design_scores_gemma":[0.0012250473,0.00030744539,0.94081205,0.001008125,0.0000792771,0.0000017647599,0.04832715,0.0037928864,0.0000032680578,0.0037631635,0.00055409427,0.00012570371],"about_ca_topic_score_codex":0.74577504,"about_ca_topic_score_gemma":0.98317486,"teacher_disagreement_score":0.23739983,"about_ca_system_score_codex":0.00089752185,"about_ca_system_score_gemma":0.015965486,"threshold_uncertainty_score":0.98961306},"labels":[],"label_agreement":null},{"id":"W4399710116","doi":"10.1016/j.jclinepi.2024.111427","title":"Identification of retracted publications and completeness of retraction notices in public health","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Completeness (order theory); Identification (biology); Public health; Medicine; Computer science; Mathematics; Biology; Pathology","score_opus":0.46925259758110227,"score_gpt":0.5655348517299681,"score_spread":0.09628225414886582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399710116","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7051411,0.0020704358,0.010521842,0.278667,0.0022849576,0.00014888003,0.000017141132,0.000014494714,0.0011341101],"genre_scores_gemma":[0.99276376,0.0053067934,0.00094892416,0.00047064424,0.0004266267,9.2276827e-7,0.000003896794,0.0000033591339,0.00007504665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9867099,0.0073521677,0.005240729,0.00017883831,0.00028574598,0.00023259665],"domain_scores_gemma":[0.9647779,0.030710027,0.0036652323,0.00010827216,0.0005612868,0.00017728642],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1037729,0.00005655874,0.0009351069,0.00031257106,0.00006681539,0.000014656363,0.00023793076,0.00085570803,0.00005200349],"category_scores_gemma":[0.1304626,0.000046420937,0.00016335525,0.0004957377,0.00061383366,0.0004802936,0.000018421675,0.002209342,0.0000020648865],"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":[0.000075171265,0.00026413868,0.32856458,0.00020424763,0.00010121408,0.0000020029324,0.0039620763,0.00003451988,0.00018600923,0.5800723,0.0065892152,0.07994453],"study_design_scores_gemma":[0.00019872894,0.00019150571,0.88049835,0.00018555745,0.000021272983,0.00001105753,0.0014994082,0.0024747641,0.000008709597,0.039143704,0.07570886,0.000058088033],"about_ca_topic_score_codex":0.0007876069,"about_ca_topic_score_gemma":0.00044207982,"teacher_disagreement_score":0.55193377,"about_ca_system_score_codex":0.000055541685,"about_ca_system_score_gemma":0.00085839187,"threshold_uncertainty_score":0.9598615},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","research_integrity","scholarly_communication"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4399722044","doi":"10.1016/j.jclinepi.2024.111428","title":"Panel stacking is a threat to consensus statement validity","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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; Impact; Children's Hospital Research Institute of Manitoba; Ottawa Hospital; Alberta Health; McMaster University; Jewish General Hospital; University of Ottawa; Ottawa Public Health; Hamilton Health Sciences","funders":"National Institute of General Medical Sciences; Norwegian Institute of Public Health; HORIZON EUROPE Framework Programme; Università di Bologna; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Pfizer; European Commission; Genentech; AstraZeneca; Eli Lilly and Company; National Science Foundation","keywords":"Delphi method; Transparency (behavior); Delphi; Political science; Scientific consensus; Statement (logic); Public relations; Law and economics; Law; Economics; Computer science","score_opus":0.8741846453546281,"score_gpt":0.7067478297603079,"score_spread":0.16743681559432022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399722044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5194855,0.0010188523,0.021121994,0.44371325,0.0050339787,0.00049891387,0.000026620655,0.00012338201,0.008977555],"genre_scores_gemma":[0.9673559,0.0025999132,0.018960467,0.0074804756,0.0023481601,0.000007922515,5.137755e-7,0.000019652829,0.0012269595],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98457336,0.009746734,0.004015291,0.0003403613,0.0006572952,0.00066695426],"domain_scores_gemma":[0.9267665,0.07098687,0.0007970098,0.00024991835,0.0005109792,0.0006887195],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12032805,0.00012362012,0.001279061,0.00020950414,0.00014671887,0.000048930684,0.000597451,0.0003457535,0.00062675163],"category_scores_gemma":[0.13380104,0.00009223174,0.00057966734,0.00035270804,0.0006269758,0.00009185539,0.00015264118,0.0012951682,0.00018411709],"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":[0.0002834703,0.00016774145,0.09727842,0.000058880174,0.0002216873,0.0006591466,0.0027050823,0.000060579878,0.000030557567,0.041965645,0.7442737,0.11229507],"study_design_scores_gemma":[0.00025450691,0.0010107969,0.015605207,0.00025994272,0.000043917084,0.00004001476,0.0012939224,0.0003148249,0.00003065511,0.16136253,0.8196282,0.00015553125],"about_ca_topic_score_codex":0.0006076014,"about_ca_topic_score_gemma":0.00018217598,"teacher_disagreement_score":0.44787046,"about_ca_system_score_codex":0.00019691455,"about_ca_system_score_gemma":0.0011299332,"threshold_uncertainty_score":0.9058074},"labels":[],"label_agreement":null},{"id":"W4399772083","doi":"10.1016/j.jclinepi.2024.111435","title":"A call for caution when using network methods to study multimorbidity: an illustration using data from the Canadian Longitudinal Study on Aging","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; McMaster University","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation; Government of Canada","keywords":"Multimorbidity; Longitudinal data; Medicine; Longitudinal study; Gerontology; MEDLINE; Data science; Comorbidity; Computer science; Psychiatry; Data mining; Biology; Pathology","score_opus":0.8624709925864251,"score_gpt":0.6731336270346978,"score_spread":0.1893373655517273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399772083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7776007,0.00037011373,0.21057683,0.0073268204,0.0026196023,0.0014192334,0.00003798679,0.000020097783,0.000028623273],"genre_scores_gemma":[0.8813697,0.000011325088,0.11080798,0.0022218034,0.0054964577,0.000006740905,0.000047685364,0.000026367514,0.00001193633],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99071634,0.005492534,0.0024888583,0.0006026999,0.00025912686,0.00044043118],"domain_scores_gemma":[0.98299724,0.014781413,0.0007055067,0.00081060745,0.00019007424,0.0005151325],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041051034,0.00020529114,0.0013281953,0.00015074472,0.00025509027,0.0000835709,0.00046231487,0.00014680249,0.0000649877],"category_scores_gemma":[0.019145451,0.00013501498,0.00024066083,0.00019446806,0.00009736332,0.00025546606,0.00015805202,0.000843848,0.0000034164393],"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":[0.001359565,0.0014871837,0.88481486,0.000056913872,0.0030672855,0.0006885434,0.0010361432,0.045960154,0.000012456978,0.00070322957,0.012242878,0.048570774],"study_design_scores_gemma":[0.0015800031,0.002651013,0.64289147,0.00026632132,0.002172739,0.00002963163,0.0011506567,0.34336004,2.0375015e-7,0.0028592926,0.002914342,0.00012432526],"about_ca_topic_score_codex":0.05261348,"about_ca_topic_score_gemma":0.11360801,"teacher_disagreement_score":0.29739988,"about_ca_system_score_codex":0.00036087917,"about_ca_system_score_gemma":0.0012859214,"threshold_uncertainty_score":0.9891167},"labels":[],"label_agreement":null},{"id":"W4399884212","doi":"10.1016/j.jclinepi.2024.111438","title":"Required knowledge for guideline panel members to develop healthcare related testing recommendations: a developmental study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Guideline; Health care; Medicine; Family medicine; Psychology; Pathology; Political science","score_opus":0.9520082785833398,"score_gpt":0.7979206697537556,"score_spread":0.15408760882958417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399884212","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":[0.27689546,0.0004050679,0.04225106,0.6577142,0.01672269,0.004597583,0.00011703144,0.00019122743,0.0011057112],"genre_scores_gemma":[0.27846056,0.00016252685,0.6005501,0.11585196,0.002989924,0.0004241031,0.00002859986,0.00007719057,0.0014550297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96123886,0.017454512,0.01930896,0.00059877656,0.00028655035,0.0011123294],"domain_scores_gemma":[0.73122203,0.25901678,0.00424182,0.000297668,0.0039224736,0.0012992097],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16329803,0.00023837441,0.0020434754,0.00050701154,0.00069978385,0.000011481063,0.00052963354,0.00039154637,0.00035855014],"category_scores_gemma":[0.57646626,0.00018426066,0.00021612571,0.001819763,0.000105216866,0.00027117383,0.0002454787,0.0017560471,0.00036953134],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027487235,0.00019086758,0.1502081,0.0003351165,0.00019899177,0.000021516002,0.016577061,0.000048234248,0.000017384089,0.0029125018,0.6368985,0.19231682],"study_design_scores_gemma":[0.0032569533,0.0027508591,0.061174434,0.001394273,0.00007599465,0.00008934347,0.016248923,0.0025182785,0.0000012004007,0.005999006,0.90618384,0.00030690109],"about_ca_topic_score_codex":0.00020964144,"about_ca_topic_score_gemma":0.00066121557,"teacher_disagreement_score":0.55829906,"about_ca_system_score_codex":0.0006891689,"about_ca_system_score_gemma":0.010763925,"threshold_uncertainty_score":0.99484414},"labels":[],"label_agreement":null},{"id":"W4400026638","doi":"10.1016/j.jclinepi.2024.111445","title":"A systematic survey of 200 systematic reviews with network meta-analysis (published 2020–2021) reveals that few reviews report structured evidence summaries","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Cochrane; Public Health Ontario; University of British Columbia; St. Michael's Hospital; University of Toronto; Queen's University; McMaster University; University of Ottawa","funders":"Helse Sør-Øst RHF","keywords":"Medicine; Meta-analysis; Psychological intervention; Systematic review; MEDLINE; Grading (engineering); Confidence interval; Quality of evidence; Family medicine; Internal medicine; Psychiatry","score_opus":0.9382758762506878,"score_gpt":0.6543960259368036,"score_spread":0.2838798503138842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400026638","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002204605,0.8701322,0.11236077,0.0055782716,0.0028093671,0.006618507,0.000051188996,0.000009839844,0.00023525216],"genre_scores_gemma":[0.57230526,0.195606,0.18209864,0.008255719,0.0042014485,0.0015284145,0.00014651996,0.00026768047,0.035590336],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.13185067,0.6394655,0.21630873,0.0030943083,0.008186336,0.0010944357],"domain_scores_gemma":[0.052258015,0.69700116,0.22820805,0.012586377,0.008823763,0.0011226643],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.929095,0.0011901116,0.1383029,0.00116866,0.00015892346,0.0009147443,0.005308565,0.00068994594,0.009142287],"category_scores_gemma":[0.95129454,0.00040734958,0.044842456,0.009757795,0.00053519104,0.0012101902,0.00035417368,0.0017772375,0.0005686021],"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":[0.00013679228,0.000096572076,0.2001282,0.16389896,0.23477818,0.00042860923,0.0001417199,0.0016793327,0.000001047356,0.00083636126,0.397554,0.0003202167],"study_design_scores_gemma":[0.00035051897,0.000875993,0.058575597,0.0849344,0.8133007,0.002335592,0.0001688223,0.0064951126,4.592109e-7,0.015695525,0.016327789,0.00093947037],"about_ca_topic_score_codex":0.00010558859,"about_ca_topic_score_gemma":0.00065122533,"teacher_disagreement_score":0.6745262,"about_ca_system_score_codex":0.00008566137,"about_ca_system_score_gemma":0.00071734167,"threshold_uncertainty_score":0.9998378},"labels":[],"label_agreement":null},{"id":"W4400037547","doi":"10.1016/j.jclinepi.2024.111443","title":"Individual patient data meta-analysis estimates the minimal detectable change of the Geriatric Depression Scale-15","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Aging and Gerontology Research","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; University of Calgary; Women's College Hospital; University of Toronto; Jewish General Hospital","funders":"Medical Research Council; Cumming School of Medicine, University of Calgary; National Institutes of Health; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fonds de Recherche du Québec - Santé; Financiadora de Estudos e Projetos; Ministry of Health and Welfare; Alberta Health Services; Alberta Innovates - Health Solutions; Bundesministerium für Bildung und Forschung; Iran University of Medical Sciences; Canadian Institutes of Health Research; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Depression (economics); Scale (ratio); Geriatric Depression Scale; Medicine; Meta-analysis; Gerontology; Psychiatry; Internal medicine; Depressive symptoms; Cartography; Geography; Cognition","score_opus":0.8222918862488282,"score_gpt":0.6417718377610038,"score_spread":0.18052004848782444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400037547","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":[0.00023854224,0.9928516,0.00015087718,0.0026954284,0.0028328998,0.0005808133,0.00038707544,0.00001188588,0.0002508876],"genre_scores_gemma":[0.0016519754,0.9935636,0.0015402616,0.000879973,0.0016523891,0.000114996146,0.000072126524,0.00006211915,0.00046258632],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9644898,0.024121726,0.0090358015,0.0009876948,0.00059159176,0.00077339023],"domain_scores_gemma":[0.92116076,0.06577491,0.009641337,0.0028957238,0.00026021752,0.00026706306],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.052714918,0.0005689509,0.014897913,0.00054596417,0.0001554793,0.000023223593,0.0047715036,0.0015314039,0.00097126834],"category_scores_gemma":[0.026471365,0.00021180772,0.009892598,0.0012709849,0.0010346415,0.00009351857,0.0022375637,0.004858889,0.000110221066],"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":[0.00014183819,0.0003497334,0.009816409,0.0012238253,0.2729072,0.00007223713,0.00026775055,0.0000054916386,8.0378335e-9,0.00010925549,0.05571701,0.65938926],"study_design_scores_gemma":[0.00020712218,0.00046120476,0.004992817,0.00038682003,0.58100456,0.0003815932,0.00008243137,0.00007871699,4.8051334e-8,0.0005408111,0.411656,0.00020785215],"about_ca_topic_score_codex":0.00015822782,"about_ca_topic_score_gemma":0.00008515146,"teacher_disagreement_score":0.65918136,"about_ca_system_score_codex":0.000026384783,"about_ca_system_score_gemma":0.00046467857,"threshold_uncertainty_score":0.999942},"labels":[],"label_agreement":null},{"id":"W4400065567","doi":"10.1016/j.jclinepi.2024.111444","title":"Underserved groups could be better considered within population-based eye health surveys: a methodological study","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ophthalmology and Visual Impairment Studies","field":"Medicine","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 British Columbia","funders":"Buchanan Charitable Foundation; Wellcome Trust","keywords":"Public health; Health equity; Population; Environmental health; Equity (law); Population health; MEDLINE; Epidemiology; Medicine; Optometry; Gerontology; Political science; Nursing","score_opus":0.86126355766,"score_gpt":0.6940423927319896,"score_spread":0.1672211649280103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400065567","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":[0.012798735,0.952241,0.0010058888,0.027030805,0.005029377,0.0017774699,0.000039967395,0.000059441136,0.000017331979],"genre_scores_gemma":[0.007421159,0.96043634,0.010628934,0.018817361,0.0022313455,0.000046054785,0.00013235657,0.00009451813,0.00019191415],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8811405,0.1006881,0.01598001,0.0009606913,0.00046163768,0.0007690872],"domain_scores_gemma":[0.873176,0.115008034,0.010132528,0.0006089213,0.0003461602,0.00072835496],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16933095,0.0008310087,0.02453497,0.0004994563,0.0001626299,0.000013473068,0.00037150906,0.0018623803,0.00018770028],"category_scores_gemma":[0.13867703,0.00046539967,0.004148233,0.00041314628,0.00059734494,0.00006105383,0.0001932082,0.0061402107,0.000052235126],"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":[0.00094635016,0.0057743858,0.8502249,0.019265857,0.01096947,0.002535993,0.00012558274,0.000016937445,1.6012587e-8,0.0003918457,0.023275156,0.086473525],"study_design_scores_gemma":[0.009413642,0.08466164,0.7260602,0.033110667,0.02535786,0.0038114835,0.0006406548,0.00014801232,1.9533205e-8,0.010897911,0.104618706,0.0012791655],"about_ca_topic_score_codex":0.000120055905,"about_ca_topic_score_gemma":0.00004592636,"teacher_disagreement_score":0.12416465,"about_ca_system_score_codex":0.00025203204,"about_ca_system_score_gemma":0.001963043,"threshold_uncertainty_score":0.99977976},"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":"W4400612419","doi":"10.1016/j.jclinepi.2024.111456","title":"Informing pandemic management in Germany with trustworthy living evidence syntheses and guideline development: lessons learned from the COVID-19 evidence ecosystem","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane","funders":"Gemeinsame Bundesausschuss; Bundesministerium für Bildung, Wissenschaft, Forschung und Technologie; Bundesministerium für Gesundheit; Deutsche Forschungsgemeinschaft; Deutsche Krebshilfe; Andrew W. Mellon Foundation; McMaster University; Pfizer; Bundesministerium für Bildung und Forschung","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Public health; German; Guideline; Ecosystem health; Ecosystem; 2019-20 coronavirus outbreak; Environmental resource management; Ecosystem management; Trustworthiness; Environmental planning; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Ecosystem services; Business; Political science; Geography; Medicine; Outbreak; Economics; Computer science; Ecology; Biology; Virology; Nursing; Disease; Computer security; Infectious disease (medical specialty)","score_opus":0.9233409756442261,"score_gpt":0.7494738159588935,"score_spread":0.17386715968533262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400612419","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":[0.5592716,0.0049798926,0.037805792,0.3954309,0.0013366869,0.00093575974,0.000016045626,0.00006173123,0.00016162868],"genre_scores_gemma":[0.8778805,0.017648662,0.01485234,0.088633046,0.0007646726,0.00006975189,4.826984e-7,0.000018997056,0.00013151209],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9733685,0.015483053,0.009298667,0.0005200176,0.00049009436,0.00083962356],"domain_scores_gemma":[0.36305726,0.6319773,0.0035461844,0.00041464277,0.00025871382,0.0007458911],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14800365,0.00021332038,0.0014345885,0.00026221806,0.00049503637,0.000026542535,0.00066852145,0.00025920916,0.00029443225],"category_scores_gemma":[0.43666866,0.0001203622,0.00012366148,0.0004847065,0.00023927339,0.0006718663,0.0003758742,0.0019659975,0.00007136566],"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":[0.0002505852,0.000014766456,0.8584146,0.0006928376,0.0001205363,0.00010111981,0.007934811,0.00035378907,0.0000029997902,0.0014654746,0.010388288,0.12026018],"study_design_scores_gemma":[0.00047800524,0.0002468555,0.46504864,0.023316765,0.00009693068,0.00012302186,0.0054250224,0.0036346873,2.421651e-7,0.001991296,0.49940273,0.0002358],"about_ca_topic_score_codex":0.0004511797,"about_ca_topic_score_gemma":0.004200686,"teacher_disagreement_score":0.61649424,"about_ca_system_score_codex":0.00043329937,"about_ca_system_score_gemma":0.0039811595,"threshold_uncertainty_score":0.87730956},"labels":[],"label_agreement":null},{"id":"W4400618158","doi":"10.1016/j.jclinepi.2024.111459","title":"Evaluation of adherence to STARD for abstracts in a diverse sample of diagnostic accuracy abstracts published in 2012 and 2019 reveals suboptimal reporting practices","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; Ontario Institute for Cancer Research","funders":"Graduate University of Science and Technology, Vietnam Academy of Science and Technology; Council of Ontario Universities","keywords":"Diagnostic accuracy; Medicine; Medical physics; Sample (material); MEDLINE; Radiology; Political science","score_opus":0.9417164680374113,"score_gpt":0.7167972363829926,"score_spread":0.22491923165441863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400618158","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98810667,0.0033219217,0.0028659787,0.003914219,0.0007475007,0.00085205666,0.000024055851,8.825133e-7,0.00016673496],"genre_scores_gemma":[0.9671664,0.00039582743,0.032018546,0.00018251533,0.00015884172,0.000016083084,0.0000026324406,0.000005799348,0.000053339623],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6420664,0.11025838,0.23549427,0.0024466251,0.008679373,0.0010549037],"domain_scores_gemma":[0.012809496,0.81864965,0.16245426,0.0010844333,0.0046842415,0.00031792288],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.83409154,0.00017826573,0.00751366,0.0006714716,0.000018796973,0.0001049877,0.00071385363,0.00023579448,0.0010976862],"category_scores_gemma":[0.99532115,0.00009380946,0.0013550982,0.0007213355,0.00009830869,0.0011243725,0.000112495385,0.0005761248,0.000024222934],"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":[0.00018429976,0.00021245438,0.82317716,0.00025723118,0.00024489997,0.000024366671,0.00033656537,0.012656118,0.00006878862,0.0003024177,0.024669081,0.13786663],"study_design_scores_gemma":[0.0005028701,0.0005561125,0.94005466,0.00059952884,0.00043816457,0.000027008478,0.00033748194,0.008328881,0.0000055864907,0.046574365,0.0024937836,0.000081544764],"about_ca_topic_score_codex":0.0003051193,"about_ca_topic_score_gemma":0.0004967955,"teacher_disagreement_score":0.70839125,"about_ca_system_score_codex":0.00004066037,"about_ca_system_score_gemma":0.000666202,"threshold_uncertainty_score":0.99981546},"labels":[],"label_agreement":null},{"id":"W4400747961","doi":"10.1016/j.jclinepi.2024.111460","title":"Analysis of risk of bias assessments in a sample of intervention systematic reviews, Part II: focus on risk of bias tools reveals few meet current appraisal standards","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University; Queen's University Belfast","keywords":"Sample (material); Systematic review; Focus (optics); Psychology; Risk assessment; Risk analysis (engineering); Environmental health; Medicine; Statistics; Actuarial science; Applied psychology; MEDLINE; Computer science; Business; Political science; Mathematics; Computer security","score_opus":0.9149829694237094,"score_gpt":0.7084217684122412,"score_spread":0.20656120101146813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400747961","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84750485,0.04255717,0.10470532,0.000381157,0.002114573,0.0013151881,0.0012550483,0.0000024013686,0.00016426807],"genre_scores_gemma":[0.9771605,0.01623703,0.0063506383,0.00003082213,0.00013734325,0.000021723468,0.000010119448,0.000012132507,0.00003966913],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5817084,0.28888875,0.12267819,0.0010233446,0.005304039,0.00039731324],"domain_scores_gemma":[0.18031916,0.64826095,0.16333579,0.0034386292,0.0042994935,0.00034597935],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7859156,0.00039845967,0.03500118,0.002095749,0.000034276916,0.000044511344,0.0016424553,0.00031307468,0.0012556915],"category_scores_gemma":[0.92355865,0.00017957906,0.018219844,0.0035885677,0.00027620175,0.00024434747,0.0002179997,0.00088778214,0.00001509547],"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":[0.00025182398,0.0009800064,0.87989247,0.012510775,0.010409124,0.000004423947,0.00023901493,0.0023163406,0.00000393253,0.0043090098,0.012919973,0.07616313],"study_design_scores_gemma":[0.002705211,0.006872973,0.6567934,0.089438945,0.06282173,0.000021170017,0.000955425,0.05915775,0.000029611685,0.100179434,0.020416897,0.0006074509],"about_ca_topic_score_codex":0.00012889443,"about_ca_topic_score_gemma":0.00021229638,"teacher_disagreement_score":0.4013892,"about_ca_system_score_codex":0.00007496694,"about_ca_system_score_gemma":0.00029427643,"threshold_uncertainty_score":0.9996573},"labels":[],"label_agreement":null},{"id":"W4400839665","doi":"10.1016/j.jclinepi.2024.111469","title":"Characteristics, consent patterns, and challenges of randomized trials using the Trials within Cohorts (TwiCs) design - A scoping review","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Botnar Research Centre for Child Health, University of Basel; Neuroscience Center Zurich, University of Zurich; Rising Tide Foundation for Clinical Cancer Research; Swiss Re Foundation; National Science Foundation; Janggen-Pöhn-Stiftung; National Institute for Health and Care Research; Universität Basel; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Randomized controlled trial; Informed consent; Research design; External validity; Clinical study design; Medicine; MEDLINE; Alternative medicine; Clinical trial; Medical physics; Psychology; Surgery; Social psychology; Statistics; Pathology; Political science","score_opus":0.9718206117005075,"score_gpt":0.7674765357561535,"score_spread":0.204344075944354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400839665","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010406584,0.9683119,0.002967671,0.017632369,0.003542184,0.0074601434,0.000043104486,0.000010257477,0.00002196698],"genre_scores_gemma":[0.000013431044,0.98779804,0.0056350934,0.002551108,0.0037844174,0.00008457089,0.0000080588325,0.00008249115,0.000042768275],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.34572613,0.51900184,0.13014577,0.0016891251,0.0023351721,0.0011019544],"domain_scores_gemma":[0.007038307,0.93667877,0.052888215,0.0010538979,0.001652858,0.00068792544],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.8607574,0.0007182882,0.09801937,0.0003707755,0.000065971224,0.000026186484,0.0007144017,0.0026815396,0.00011665735],"category_scores_gemma":[0.9826623,0.00030675178,0.012243218,0.00020457056,0.00250238,0.000046667283,0.0004258297,0.010680001,0.0000093798135],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014242433,0.00021475105,0.00007637007,0.6584989,0.0094293635,0.00031862798,0.00003555194,8.2533734e-7,1.1624421e-7,0.0043474166,0.0007573204,0.31207833],"study_design_scores_gemma":[0.017280465,0.00097513985,0.000009926678,0.91013587,0.0481042,0.0011445748,0.000014109958,0.00005438744,1.8624296e-7,0.011409533,0.010643918,0.00022767612],"about_ca_topic_score_codex":0.000019745556,"about_ca_topic_score_gemma":0.000009442468,"teacher_disagreement_score":0.41767696,"about_ca_system_score_codex":0.00009063424,"about_ca_system_score_gemma":0.009522524,"threshold_uncertainty_score":0.9999385},"labels":[],"label_agreement":null},{"id":"W4400859322","doi":"10.1016/j.jclinepi.2024.111473","title":"Values and preferences in COVID-19 public health guidelines: a systematic review","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; McMaster University; University of Toronto","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Systematic review; Public health; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Medicine; Betacoronavirus; Family medicine; Environmental health; Political science; Virology; Nursing; Pathology; Outbreak; Disease","score_opus":0.9156525187938575,"score_gpt":0.7489224095162269,"score_spread":0.16673010927763054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400859322","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":[0.0000031675572,0.8466946,0.0007645423,0.14882335,0.0012154743,0.0024364777,0.000018971381,0.0000226436,0.000020791706],"genre_scores_gemma":[0.0000025201748,0.90166956,0.0060554594,0.0907137,0.0013071143,0.00007010328,0.000051780153,0.00004703959,0.00008275155],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.88503706,0.04414022,0.0683106,0.0010069861,0.000734923,0.0007701886],"domain_scores_gemma":[0.5935835,0.34556797,0.054085247,0.0014644378,0.001684711,0.0036141165],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26328683,0.0005829582,0.028804744,0.00067236,0.000042730684,0.0000314254,0.0004920916,0.0008548495,0.00011686172],"category_scores_gemma":[0.8855374,0.00031933605,0.0027665435,0.00066982803,0.0003245583,0.00023357726,0.00023535977,0.003883807,0.00007422339],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022155382,0.000096445176,0.00023176374,0.66102284,0.0005948219,0.00009681072,0.000013308739,1.7654646e-7,4.409354e-10,0.000113079106,0.048720542,0.28908804],"study_design_scores_gemma":[0.0005981538,0.0009888151,0.000022335384,0.53441626,0.0060010063,0.0024368989,0.00006355291,0.00002968471,8.596668e-11,0.0028188783,0.4524851,0.00013931491],"about_ca_topic_score_codex":0.00009120161,"about_ca_topic_score_gemma":0.000055760425,"teacher_disagreement_score":0.62225056,"about_ca_system_score_codex":0.00044735565,"about_ca_system_score_gemma":0.01262674,"threshold_uncertainty_score":0.99992585},"labels":[],"label_agreement":null},{"id":"W4401009833","doi":"10.1016/j.jclinepi.2024.111467","title":"Building a composite score for patient self-report of flare in osteoarthritis: a comparison of methods with the Flare-OA-16 questionnaire","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","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 Toronto","funders":"Agence Nationale de la Recherche; Université de Lorraine","keywords":"Flare; Medicine; Osteoarthritis; Physical therapy; Alternative medicine; Physics; Pathology","score_opus":0.1361902123622311,"score_gpt":0.5091167277946782,"score_spread":0.3729265154324471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401009833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93189657,0.014876244,0.04633895,0.0051672175,0.0009164729,0.0007073099,0.000010653292,0.000019370666,0.00006719785],"genre_scores_gemma":[0.86406475,0.00017247321,0.13513593,0.00029620912,0.000264532,0.000023029308,0.000008308259,0.00002006522,0.000014712072],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.99311167,0.00198622,0.0041573774,0.00027196074,0.00020053006,0.0002722261],"domain_scores_gemma":[0.98672426,0.010245929,0.002165617,0.00025314477,0.00044183832,0.00016923559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01121221,0.00018877399,0.0026830772,0.00018634401,0.0000402642,0.0000048144884,0.00013214945,0.0002787395,0.000009300305],"category_scores_gemma":[0.007206274,0.000105711944,0.0006839445,0.00021083083,0.00021589185,0.00007896211,0.000046046778,0.00072566606,6.701398e-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":[0.0039355624,0.00104408,0.3233807,0.00075447984,0.0007159635,0.0007040696,0.000819601,0.00016417186,0.0026749303,0.005614376,0.0009379272,0.65925413],"study_design_scores_gemma":[0.070256114,0.36747107,0.2527615,0.078656435,0.010623153,0.03169423,0.0048847413,0.010357514,0.045732487,0.054751195,0.07113093,0.0016806435],"about_ca_topic_score_codex":0.000021890222,"about_ca_topic_score_gemma":0.000074418196,"teacher_disagreement_score":0.6575735,"about_ca_system_score_codex":0.00006551244,"about_ca_system_score_gemma":0.00037395037,"threshold_uncertainty_score":0.8627104},"labels":[],"label_agreement":null},{"id":"W4401170046","doi":"10.1016/j.jclinepi.2024.111483","title":"Latin American panelists find GRADE-ADOLOPMENT useful and important to contextualize recommendations in their region","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","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 Medical Centre; Impact; McMaster University","funders":"","keywords":"Latin Americans; Political science; Family medicine; Medicine; Geography; Environmental health; Law","score_opus":0.3153632646937759,"score_gpt":0.5024720726038892,"score_spread":0.18710880791011325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401170046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8299079,0.0011829971,0.00083470246,0.16677688,0.0008288645,0.00028213582,0.0000037409131,0.0000138029345,0.00016896462],"genre_scores_gemma":[0.96607286,0.011967177,0.0035856464,0.0176693,0.00046580314,0.000013283764,0.000005301405,0.00001689689,0.0002037443],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947742,0.0010700427,0.0034507082,0.00030303732,0.00011070719,0.00029126133],"domain_scores_gemma":[0.9888998,0.009569304,0.0008975208,0.00019228665,0.00007968662,0.0003613528],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009239391,0.00015293078,0.0021543782,0.00025228108,0.000028159699,0.000011642875,0.00010277921,0.00011830719,0.00006263983],"category_scores_gemma":[0.011221636,0.00010139163,0.0002960457,0.00021964457,0.0001714354,0.000052143623,0.00007728729,0.0006611042,0.00001055354],"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":[0.0002709708,0.00061033206,0.7106343,0.000087785644,0.00034885015,0.00041566143,0.0008849822,0.000023039851,0.0000202844,0.005088595,0.0919384,0.1896768],"study_design_scores_gemma":[0.0006989482,0.0016593232,0.8282871,0.00051893963,0.00008666249,0.0001041898,0.00043865084,0.00026375573,0.0000034783711,0.0029804124,0.16487145,0.00008704432],"about_ca_topic_score_codex":0.00015643028,"about_ca_topic_score_gemma":0.00016307959,"teacher_disagreement_score":0.18958977,"about_ca_system_score_codex":0.00006853539,"about_ca_system_score_gemma":0.00014024817,"threshold_uncertainty_score":0.99710727},"labels":[],"label_agreement":null},{"id":"W4401306099","doi":"10.1016/j.jclinepi.2024.111492","title":"A brief note on the random-effects meta-analysis model and its relationship to other models","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"University of Toronto; St. Michael's Hospital","funders":"National Health and Medical Research Council; Medical Research Council; University of Bristol","keywords":"Random effects model; Meta-analysis; Model selection; Computer science; Econometrics; Fixed effects model; Statistical model; Linear model; Mathematics; Artificial intelligence; Machine learning; Medicine","score_opus":0.9559238903123659,"score_gpt":0.6810858853192303,"score_spread":0.2748380049931356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401306099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033811618,0.012521824,0.85426736,0.095402524,0.00045348293,0.0006061,0.00001571335,0.0000044036005,0.0029169675],"genre_scores_gemma":[0.96276283,0.00014587908,0.009994466,0.020719098,0.00027229727,0.000025008743,3.9156933e-7,0.0000135860055,0.006066438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8549306,0.11115707,0.030257896,0.0009832325,0.0023524496,0.00031878747],"domain_scores_gemma":[0.19121009,0.7922331,0.012336761,0.0024224804,0.0012058096,0.0005917198],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.64090544,0.00030312102,0.016915733,0.0007063764,0.00011232174,0.00023347387,0.0013289725,0.00027759236,0.001441563],"category_scores_gemma":[0.7458375,0.00009679997,0.017837895,0.0016191916,0.00010089289,0.00022959463,0.000111130576,0.0009952312,0.0006624171],"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":[0.00017247944,0.000074823,0.0030575676,0.000029942268,0.06155437,0.000019721985,0.0002969556,0.5036015,0.0000026862717,0.34802425,0.07829999,0.0048656985],"study_design_scores_gemma":[0.0001679443,0.00011161181,0.0016487733,0.00001639843,0.050303854,0.0000122734045,0.00000924817,0.6568105,3.9449455e-7,0.28143808,0.009406463,0.00007443222],"about_ca_topic_score_codex":0.0000037034038,"about_ca_topic_score_gemma":0.000014776145,"teacher_disagreement_score":0.9289512,"about_ca_system_score_codex":0.000015952595,"about_ca_system_score_gemma":0.00012352495,"threshold_uncertainty_score":0.99947125},"labels":[],"label_agreement":null},{"id":"W4401306158","doi":"10.1016/j.jclinepi.2024.111490","title":"Developing reporting checklist items from systematic review findings: a roadmap and lessons to be learned from ACCORD","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Checklist; Systematic review; MEDLINE; Medicine; Psychology; Medical education; Management science; Political science; Engineering","score_opus":0.9685079508447144,"score_gpt":0.7315394618440088,"score_spread":0.23696848900070566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401306158","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":[0.00008974589,0.9627819,0.010370263,0.021630868,0.0028744868,0.00199549,0.00007934108,0.000008585874,0.0001693053],"genre_scores_gemma":[0.000011608595,0.96243775,0.026004689,0.008271796,0.0013318793,0.0000888829,0.00003266645,0.00006205527,0.001758693],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.50124305,0.19424236,0.2951536,0.003674716,0.0047774087,0.00090886594],"domain_scores_gemma":[0.10746222,0.5311597,0.3496155,0.0073014665,0.002839216,0.0016218823],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.7362427,0.0012153068,0.120342106,0.0008721763,0.00015001607,0.0006392646,0.004410735,0.0012414479,0.0011282926],"category_scores_gemma":[0.95997167,0.00050285755,0.02178142,0.00192622,0.00017880525,0.00023776681,0.0010024806,0.0032380458,0.0020303368],"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":[0.000009829922,0.000045482157,0.0009171985,0.4407084,0.0061047035,0.0002654184,0.00012179582,0.000001920565,5.6841635e-8,0.0011862824,0.13715453,0.41348436],"study_design_scores_gemma":[0.000061985076,0.00005706465,0.000070810645,0.38807327,0.015026012,0.00025725746,0.00007491677,0.000068838344,6.460822e-9,0.0077083856,0.58830434,0.00029709205],"about_ca_topic_score_codex":0.00006130573,"about_ca_topic_score_gemma":0.00003505449,"teacher_disagreement_score":0.45114982,"about_ca_system_score_codex":0.0001713076,"about_ca_system_score_gemma":0.0013516122,"threshold_uncertainty_score":0.9997848},"labels":[],"label_agreement":null},{"id":"W4401317985","doi":"10.1016/j.jclinepi.2024.111484","title":"Supplementing systematic review findings with healthcare system data: pilot projects from the Agency for Healthcare Research and Quality Evidence-based Practice Center program","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2,"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":"ClearWay Minnesota; EPCOR; Center for Scientific Review; Agency for Healthcare Research and Quality; Mayo Clinic","keywords":"Workgroup; Health care; Systematic review; Medicine; Evidence-based practice; Agency (philosophy); Data collection; Data quality; MEDLINE; Operations management; Computer science; Engineering; Alternative medicine","score_opus":0.9850712675582161,"score_gpt":0.7840119390380691,"score_spread":0.20105932852014696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401317985","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008276416,0.42499906,0.033116765,0.5172003,0.0016147,0.014379113,0.00035023197,0.000021714297,0.00004174591],"genre_scores_gemma":[0.7378777,0.0412035,0.18186164,0.033587866,0.0032922328,0.001424259,0.00015508477,0.000095465344,0.0005022029],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.39022535,0.51236755,0.08442316,0.003086822,0.008586753,0.0013103458],"domain_scores_gemma":[0.08677875,0.8665061,0.031712867,0.005996986,0.0083417175,0.0006635772],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8715291,0.00036144018,0.013534089,0.00025168277,0.00039102678,0.00067488756,0.0035791849,0.0001986715,0.000087167435],"category_scores_gemma":[0.8584897,0.00012534637,0.0016653801,0.001344676,0.0003317579,0.0008733447,0.0003986327,0.0017412361,0.00006980407],"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":[0.0007000519,0.00048286412,0.16528893,0.62275463,0.0024490573,0.00008996966,0.0004911917,0.0000045999177,9.016629e-7,0.02153467,0.17050429,0.015698858],"study_design_scores_gemma":[0.001577239,0.011441097,0.013765282,0.8025099,0.005355517,0.0005707027,0.006769056,0.016408486,5.977183e-7,0.0069400454,0.13411401,0.00054804335],"about_ca_topic_score_codex":0.0003491428,"about_ca_topic_score_gemma":0.0002824813,"teacher_disagreement_score":0.7296013,"about_ca_system_score_codex":0.00011531376,"about_ca_system_score_gemma":0.0013277545,"threshold_uncertainty_score":0.9251632},"labels":[],"label_agreement":null},{"id":"W4401371343","doi":"10.1016/j.jclinepi.2024.111494","title":"GRADE guidance 39: using GRADE-ADOLOPMENT to adopt, adapt or create contextualized recommendations from source guidelines and evidence syntheses","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Western University; McMaster University; Impact; University of Calgary; Cochrane","funders":"National Institute for Health and Care Research; World Health Organization","keywords":"MEDLINE; Medicine; Medical education; Computer science; Data science; Psychology; Political science","score_opus":0.963323487847732,"score_gpt":0.7895652689510922,"score_spread":0.17375821889663978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401371343","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":[0.27215165,0.0037734155,0.13589741,0.5823628,0.00481111,0.0007888795,0.00009190724,0.000070315145,0.0000525139],"genre_scores_gemma":[0.4504638,0.010306491,0.32201728,0.2113845,0.00441587,0.000081805665,0.000002873253,0.00005984658,0.0012675354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9677556,0.018934218,0.011398765,0.0006203855,0.0004136945,0.00087731524],"domain_scores_gemma":[0.63884693,0.35530278,0.003469888,0.00039887673,0.00086568756,0.0011158669],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065539934,0.00026599682,0.002205164,0.00030273088,0.0005276007,0.000029326915,0.0005356657,0.00035659765,0.0009839007],"category_scores_gemma":[0.5740177,0.00017704634,0.00027609107,0.00046355228,0.00031829855,0.00049002585,0.00029473516,0.0014609813,0.00012132021],"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":[0.0015931326,0.00013623682,0.22090936,0.0006537492,0.00040043241,0.00009402869,0.00847261,0.00070423697,0.00058262155,0.0027337715,0.65971994,0.10399985],"study_design_scores_gemma":[0.0010530464,0.00081939425,0.04250234,0.0130686285,0.00016308922,0.0000954786,0.0034992169,0.008788391,0.000014752938,0.004311852,0.92534727,0.0003365658],"about_ca_topic_score_codex":0.0015223796,"about_ca_topic_score_gemma":0.0003432586,"teacher_disagreement_score":0.50847775,"about_ca_system_score_codex":0.00023218802,"about_ca_system_score_gemma":0.0025494806,"threshold_uncertainty_score":0.9999293},"labels":[],"label_agreement":null},{"id":"W4402042855","doi":"10.1016/j.jclinepi.2024.111509","title":"Stakeholder-informed positivity thresholds for disease markers and risk scores: a methodological framework and an application in obstructive lung disease","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital; St. Paul's Hospital; Centre for Advancing Health Outcomes; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Disease; Medicine; Obstructive lung disease; Lung disease; Pulmonary disease; Internal medicine; Intensive care medicine; Pathology; Lung","score_opus":0.7643163652676652,"score_gpt":0.6209648057094066,"score_spread":0.14335155955825862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402042855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7139419,0.008403557,0.25428328,0.02181396,0.0005880394,0.00060933025,0.0003203081,0.000013678417,0.00002596159],"genre_scores_gemma":[0.9343524,0.0049270783,0.0544383,0.005236292,0.00091354636,0.00008411246,0.00001640668,0.000020829406,0.00001105716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9858674,0.004941986,0.008154934,0.0006183777,0.000060267743,0.00035704352],"domain_scores_gemma":[0.8529589,0.14099553,0.0046870424,0.00033444137,0.0000848017,0.00093927525],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1246596,0.00018544728,0.0023720723,0.00027630883,0.00009699994,0.000044396103,0.00018126899,0.0003469838,0.000021614367],"category_scores_gemma":[0.25742987,0.00017230287,0.00030337233,0.000119222976,0.0003476912,0.0005636416,0.00005546941,0.0007981464,0.000006763349],"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":[0.0007298534,0.00007187211,0.865727,0.0003984017,0.000106207575,0.0000053399594,0.00017466415,0.0001982663,6.372007e-8,0.12500092,0.0007127415,0.006874655],"study_design_scores_gemma":[0.00044279746,0.00015558062,0.5757985,0.00014165357,0.000036224563,0.0000049622063,0.00009151182,0.06252828,1.6033773e-8,0.35966888,0.0010308474,0.000100758145],"about_ca_topic_score_codex":0.00011534421,"about_ca_topic_score_gemma":0.00006870892,"teacher_disagreement_score":0.28992853,"about_ca_system_score_codex":0.00018354972,"about_ca_system_score_gemma":0.00034139477,"threshold_uncertainty_score":0.90134716},"labels":[],"label_agreement":null},{"id":"W4402082756","doi":"10.1016/j.jclinepi.2024.111512","title":"A survey of experts to identify methods to detect problematic studies: stage 1 of the INveStigating ProblEmatic Clinical Trials in Systematic Reviews project","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University","funders":"Research for Patient Benefit Programme; Department of Health and Social Care; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research","keywords":"Stage (stratigraphy); Systematic review; Medicine; MEDLINE; Data science; Computer science; Political science; Biology","score_opus":0.98807501326807,"score_gpt":0.8130868499801053,"score_spread":0.17498816328796474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402082756","genre_codex":"empirical","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":[0.5306735,0.07158333,0.34247646,0.014198879,0.008691312,0.03216368,0.00004749741,0.000011295481,0.00015404973],"genre_scores_gemma":[0.25442466,0.0026680008,0.7360759,0.003878663,0.0005046008,0.00085346145,9.560467e-7,0.00006871577,0.0015250699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.01934214,0.75963426,0.21625532,0.0012247253,0.0030339726,0.00050958834],"domain_scores_gemma":[0.011856369,0.8698453,0.110135555,0.004078466,0.0035589787,0.00052537624],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97845614,0.0005689718,0.065344326,0.0012415638,0.00005905237,0.00013671957,0.0038882904,0.00042620662,0.00028660815],"category_scores_gemma":[0.9954921,0.00019782275,0.012398409,0.0051404466,0.0003967999,0.0002371359,0.0006585272,0.0012085214,0.000150047],"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":[0.0003319117,0.00079015497,0.3833682,0.29896012,0.010439322,0.00004338289,0.01157504,0.003501722,0.0010157649,0.0022003504,0.18070702,0.107067026],"study_design_scores_gemma":[0.0027778863,0.0057453644,0.40433586,0.3560644,0.0074115563,0.00022149917,0.007749144,0.03934731,0.000086721186,0.16223624,0.0126280505,0.0013959745],"about_ca_topic_score_codex":0.000048935155,"about_ca_topic_score_gemma":0.00019172447,"teacher_disagreement_score":0.39359942,"about_ca_system_score_codex":0.000082987266,"about_ca_system_score_gemma":0.0009848909,"threshold_uncertainty_score":0.9974922},"labels":[],"label_agreement":null},{"id":"W4402311821","doi":"10.1016/j.jclinepi.2024.111518","title":"Key concepts in rapid reviews: an overview","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Public Health Agency of Canada; University of Ottawa","funders":"University of Galway; Public Health Agency","keywords":"Key (lock); Data science; Computer science; Medicine; Computer security","score_opus":0.9843755823877942,"score_gpt":0.7904426472526447,"score_spread":0.19393293513514953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402311821","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000052577393,0.9901404,0.000662678,0.0013062798,0.0053414386,0.0011253553,0.000020374084,0.0000030446963,0.0013951915],"genre_scores_gemma":[0.000001831291,0.9853577,0.006718036,0.0027975023,0.0026126057,0.000032795397,0.000010795003,0.000042979835,0.0024257274],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.1907362,0.5596563,0.2427179,0.0024678253,0.0036252562,0.00079647684],"domain_scores_gemma":[0.1833445,0.5437394,0.25754842,0.011015934,0.002485435,0.0018663154],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8846152,0.0011020559,0.12965168,0.00142641,0.00004535585,0.00025129932,0.0068272203,0.001629572,0.013744794],"category_scores_gemma":[0.85024524,0.00040041725,0.045725554,0.0025946337,0.00036552112,0.00037284245,0.00041294374,0.0045816787,0.013931122],"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":[0.0000045307243,0.000080041355,0.00032826109,0.005315923,0.0004573776,0.000082245075,0.00002248308,0.0000018066795,1.4321262e-9,0.00299384,0.20889248,0.781821],"study_design_scores_gemma":[0.00016086068,0.00036709977,0.00015303848,0.023279566,0.004023749,0.00038558457,0.000020331827,0.0001135312,5.6280997e-10,0.02295278,0.9482467,0.00029675642],"about_ca_topic_score_codex":0.000004945452,"about_ca_topic_score_gemma":0.000023762743,"teacher_disagreement_score":0.78152424,"about_ca_system_score_codex":0.00010131886,"about_ca_system_score_gemma":0.0011297156,"threshold_uncertainty_score":0.9998448},"labels":[],"label_agreement":null},{"id":"W4402537836","doi":"10.1016/j.jclinepi.2024.111534","title":"Comments, suggestions, and criticisms of the Pragmatic Explanatory Continuum Indicator Summary-2 design tool: a citation analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Western University; Centre for Family Medicine; Ottawa Hospital","funders":"Health Research Board","keywords":"Citation; Citation analysis; Medicine; Data science; Psychology; Information retrieval; Computer science; Library science","score_opus":0.835104217688364,"score_gpt":0.6349352798674791,"score_spread":0.20016893782088485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402537836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3317978,0.014359992,0.6170879,0.03377125,0.0020186135,0.00060623646,0.000034633347,0.0000046872906,0.00031888366],"genre_scores_gemma":[0.97113943,0.0007183298,0.02465432,0.0026888822,0.00018284335,0.000009153571,0.0000027266485,0.00000827746,0.0005960471],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.84079933,0.12032257,0.03606572,0.0005571168,0.002013378,0.0002418872],"domain_scores_gemma":[0.4713571,0.49777913,0.027082724,0.0020238191,0.0014307931,0.00032641832],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5371923,0.00018807263,0.008007352,0.00074188784,0.000077449746,0.00011981115,0.0011458882,0.00022330396,0.0009912584],"category_scores_gemma":[0.61739314,0.00007468255,0.0041371533,0.0014920393,0.00036666417,0.00020805249,0.000108237065,0.0006312962,0.00006588716],"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":[0.000040723207,0.00011995964,0.64970803,0.00011978829,0.0038484416,0.0000137899015,0.00027717263,0.00035530754,0.000013939505,0.013653495,0.31110084,0.020748526],"study_design_scores_gemma":[0.0004380833,0.00033139004,0.7543775,0.00034359182,0.0065484755,0.000067624744,0.0004796844,0.033917807,0.000005566713,0.14304183,0.060287174,0.00016126508],"about_ca_topic_score_codex":0.0000050847525,"about_ca_topic_score_gemma":0.000013248489,"teacher_disagreement_score":0.63934165,"about_ca_system_score_codex":0.000019508358,"about_ca_system_score_gemma":0.00021126158,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4402563075","doi":"10.1016/j.jclinepi.2024.111510","title":"Corrigendum to ‘Pilot and feasibility trials in surgery are incompletely reported according to the CONSORT checklist: a meta-research study’ [Journal of Clinical Epidemiology 170 (2024)]","year":2024,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","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. Joseph’s Healthcare Hamilton; Impact; McMaster University","funders":"","keywords":"Checklist; Consolidated Standards of Reporting Trials; Epidemiology; Medicine; Clinical trial; Meta-analysis; Family medicine; Environmental health; Psychology; Internal medicine","score_opus":0.8974961246414908,"score_gpt":0.6598661853431784,"score_spread":0.23762993929831233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402563075","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5839698,0.03355924,0.00049581553,0.20104389,0.17333852,0.005572293,0.000115303905,0.00004143157,0.0018637271],"genre_scores_gemma":[0.6805983,0.046563994,0.007609428,0.080263816,0.103968725,0.00034996818,0.000088204186,0.0005868798,0.07997066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6065389,0.2897564,0.09519745,0.0028831586,0.0028969217,0.0027271658],"domain_scores_gemma":[0.0777485,0.8771245,0.033958532,0.002519741,0.0046995273,0.0039492226],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.7692842,0.0010383248,0.064222775,0.002168655,0.00016715436,0.000053264626,0.0012102762,0.0026233965,0.00034490268],"category_scores_gemma":[0.9423002,0.00053611014,0.015979521,0.0015314806,0.001473356,0.00012491787,0.00082505116,0.02001702,0.00005554162],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007994241,0.0008806552,0.5342934,0.0002080695,0.006977282,0.0056268824,0.00007264398,0.000009609194,4.7638434e-7,0.000114994444,0.4411822,0.0026395577],"study_design_scores_gemma":[0.00204954,0.005701716,0.58578354,0.0008806197,0.005690179,0.00382172,0.0006852581,0.000025055815,1.2061659e-7,0.0011793387,0.39390823,0.00027468565],"about_ca_topic_score_codex":0.00041698432,"about_ca_topic_score_gemma":0.000493022,"teacher_disagreement_score":0.5873681,"about_ca_system_score_codex":0.0003441797,"about_ca_system_score_gemma":0.0059389668,"threshold_uncertainty_score":0.99970907},"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":"W4402666994","doi":"10.1016/j.jclinepi.2024.111529","title":"Farewell and thanks to Tony and Inday Dans","year":2024,"lang":"fr","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diversity and Impact of Dance","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Bruyère; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine","score_opus":0.32472843985818756,"score_gpt":0.5593634772376337,"score_spread":0.23463503737944613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402666994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7465105,0.06887866,0.0063569155,0.14129184,0.024785973,0.0001354175,0.00007137276,0.0000150647065,0.011954265],"genre_scores_gemma":[0.91434675,0.023238635,0.0054273494,0.031469703,0.005442118,0.0000010701852,0.0000019148376,0.000033917444,0.020038517],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99113417,0.004775603,0.002911562,0.00046328735,0.00013350292,0.0005819029],"domain_scores_gemma":[0.96942693,0.028438028,0.00082403235,0.00023558772,0.000108962246,0.0009664879],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021417731,0.00024060362,0.0021106214,0.00019149347,0.00007085742,0.000041238727,0.00031399322,0.0009017888,0.0007591587],"category_scores_gemma":[0.023818495,0.00019790001,0.0004512327,0.00016972299,0.0009305173,0.00026043446,0.00021893601,0.0020033973,0.0003641697],"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":[0.00085350644,0.0003474842,0.31569344,0.00022862823,0.0008787692,0.0009267804,0.0036774913,0.000025679557,0.000027006907,0.065544404,0.24867462,0.3631222],"study_design_scores_gemma":[0.0008531501,0.003418109,0.3891042,0.0004959245,0.00022563688,0.0012011203,0.00058184075,0.00011758457,0.0000030673323,0.012385299,0.5914503,0.0001638305],"about_ca_topic_score_codex":0.00014009236,"about_ca_topic_score_gemma":0.00002896852,"teacher_disagreement_score":0.36295837,"about_ca_system_score_codex":0.00003812767,"about_ca_system_score_gemma":0.00016604451,"threshold_uncertainty_score":0.9844043},"labels":[],"label_agreement":null},{"id":"W4402676327","doi":"10.1016/j.jclinepi.2024.111537","title":"Network meta-analysis: a powerful tool for clinicians, decision-makers, and methodologists","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","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":"St. Michael's Hospital","funders":"Universidad de Antioquia","keywords":"Meta-analysis; MEDLINE; Medicine; Data science; Gerontology; Psychology; Computer science; Political science; Internal medicine","score_opus":0.8221595929952566,"score_gpt":0.7069162742305957,"score_spread":0.11524331876466098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402676327","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02784941,0.17598963,0.70199037,0.07819312,0.013459708,0.0011387957,0.00010130604,0.00006000574,0.0012176782],"genre_scores_gemma":[0.1592787,0.0076470426,0.76431894,0.05357712,0.009706704,0.000114344104,0.000020435165,0.00010197098,0.0052347057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.970236,0.019276533,0.008494958,0.00075836666,0.00030928306,0.00092488556],"domain_scores_gemma":[0.7004643,0.29670537,0.0016583246,0.00046824384,0.00023836235,0.00046541053],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1736466,0.00027195708,0.006526136,0.00035546324,0.00008742026,0.000028567161,0.00051889586,0.00082454825,0.001966025],"category_scores_gemma":[0.12907162,0.00017126901,0.0045707757,0.0005692059,0.00047615694,0.000109883615,0.00014167826,0.0019261256,0.00009668188],"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":[0.0049946047,0.00034982496,0.06019842,0.00019497988,0.17772792,0.00048961496,0.00015162672,0.00053439866,4.9166636e-7,0.0990964,0.39849532,0.2577664],"study_design_scores_gemma":[0.0015073186,0.004074174,0.07902109,0.000054686876,0.06947614,0.00028412155,0.00011809837,0.0019038912,2.2555284e-7,0.38926846,0.45400813,0.00028364404],"about_ca_topic_score_codex":0.000031512966,"about_ca_topic_score_gemma":0.000037322436,"teacher_disagreement_score":0.29017207,"about_ca_system_score_codex":0.0000438741,"about_ca_system_score_gemma":0.00028306697,"threshold_uncertainty_score":0.9989463},"labels":[],"label_agreement":null},{"id":"W4402737940","doi":"10.1016/j.jclinepi.2024.111545","title":"Development of a Canadian Guidance for reporting real-world evidence for regulatory and health-technology assessment (HTA) decision-making","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"McGill University; University of British Columbia; Institute of Health Economics; University of Alberta; Université Laval; University of Manitoba; Canadian Agency for Drugs and Technologies in Health; St. Michael's Hospital; Sunnybrook Hospital; Dalhousie University; University of New Brunswick; University of Toronto","funders":"Health Canada; National Institute for Health and Care Research; Canadian Defence Academy","keywords":"Clinical decision making; Health technology; Policy making; Medicine; MEDLINE; Environmental health; Risk analysis (engineering); Intensive care medicine; Political science; Economic growth; Health care; Public administration; Economics","score_opus":0.8756252443528417,"score_gpt":0.6853199142414161,"score_spread":0.19030533011142559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402737940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30369055,0.027036157,0.36974138,0.29344478,0.0043350332,0.0013763679,0.00007958967,0.000030940737,0.00026518476],"genre_scores_gemma":[0.40054047,0.0012004751,0.5915596,0.0059958133,0.00056136627,0.000058947437,0.000002117142,0.000022535141,0.00005869622],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95803255,0.0007506742,0.03998558,0.0005946829,0.00007990059,0.0005566364],"domain_scores_gemma":[0.86395645,0.09256519,0.04205662,0.00047250313,0.0004165941,0.00053261983],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33281675,0.00016208128,0.0037821918,0.001614931,0.00018211544,0.000019133464,0.00030390985,0.00032005814,0.000024760775],"category_scores_gemma":[0.30134225,0.00016767773,0.00041827076,0.00036000987,0.00015592754,0.00023218512,0.000054233475,0.0004424026,0.000006386275],"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":[0.00008971508,0.000045321653,0.46235055,0.0016642323,0.00027939523,0.0000050967183,0.00039094622,0.00025188364,0.0000017797297,0.42283994,0.04693544,0.065145716],"study_design_scores_gemma":[0.000626167,0.00051112834,0.5356003,0.0047479146,0.000020326344,0.000049111688,0.00036311147,0.0144374445,0.0000013025194,0.23171811,0.21169114,0.00023393745],"about_ca_topic_score_codex":0.0018160468,"about_ca_topic_score_gemma":0.023480237,"teacher_disagreement_score":0.28744897,"about_ca_system_score_codex":0.0009517184,"about_ca_system_score_gemma":0.0049303975,"threshold_uncertainty_score":0.9943387},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":true,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":true,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4402910077","doi":"10.1016/j.jclinepi.2024.111546","title":"A review of health equity considerations in Cochrane reviews of lifestyle interventions for cardiovascular health in adults","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Cardiovascular Health and Risk Factors","field":"Medicine","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":"Bruyère; University of Ottawa","funders":"National Center for Complementary and Integrative Health; National Institutes of Health","keywords":"Psychological intervention; Medicine; Cardiovascular health; Gerontology; Environmental health; MEDLINE; Health equity; Equity (law); Public health; Nursing; Disease; Internal medicine; Political science","score_opus":0.5874224824908911,"score_gpt":0.6547444366391239,"score_spread":0.06732195414823272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402910077","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":[0.0000026583978,0.9837435,0.0012915585,0.008473156,0.0018141958,0.0045290045,0.000120972756,0.0000053943377,0.000019586527],"genre_scores_gemma":[0.000010903876,0.99016774,0.0049246964,0.0039577605,0.0006808975,0.000101880876,0.00010639772,0.0000409327,0.000008767511],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.93744195,0.024689386,0.03628636,0.0005828966,0.00035798494,0.00064141134],"domain_scores_gemma":[0.95664316,0.023778377,0.016868258,0.001138303,0.0008458243,0.0007260813],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.20303822,0.00042724342,0.043481544,0.00079748133,0.000030883908,0.000001964754,0.00024132316,0.0006714908,0.000047357385],"category_scores_gemma":[0.23850317,0.0002739493,0.030217728,0.0006551846,0.00025363688,0.00004509734,0.00011900981,0.0026611725,0.000006370132],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035324407,0.00023832446,0.00016840985,0.5015177,0.0009729121,0.000012039518,0.000014497333,0.0000021225592,5.3688026e-10,0.00014937036,0.015533746,0.48135552],"study_design_scores_gemma":[0.0010969947,0.0011149433,0.00039287983,0.5094274,0.0021283145,0.00033866812,0.0000056812246,0.0000026245236,2.274441e-9,0.00034991757,0.48506296,0.00007959609],"about_ca_topic_score_codex":0.0004069371,"about_ca_topic_score_gemma":0.00028113183,"teacher_disagreement_score":0.48127595,"about_ca_system_score_codex":0.00040097607,"about_ca_system_score_gemma":0.008560742,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W4402990981","doi":"10.1016/j.jclinepi.2024.111514","title":"Corrigendum to “Development of an international glossary for clinical guidelines collaboration” “[Journal of Clinical Epidemiology 158 (2023) 84-91]”","year":2024,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; Canadian Institutes of Health Research; Canadian Thoracic Society; Institute of Health Economics; Western University; Impact; The Society of Obstetricians and Gynaecologists of Canada; Public Health Agency of Canada","funders":"","keywords":"Glossary; Medicine; Library science; Medical education; Engineering ethics; Engineering; Computer science; Philosophy","score_opus":0.7948329839807938,"score_gpt":0.7031021703299198,"score_spread":0.09173081365087399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402990981","genre_codex":"editorial","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":[0.034253675,0.009042661,0.09406185,0.21607059,0.64110136,0.0029747603,0.0009267627,0.00006661669,0.0015017156],"genre_scores_gemma":[0.0016057782,0.031422097,0.73613983,0.062886134,0.14326756,0.000043471882,0.0015915614,0.00031511986,0.022728436],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.84554976,0.022675132,0.12652561,0.0019872754,0.0019053832,0.0013568508],"domain_scores_gemma":[0.5278655,0.30746782,0.1188218,0.0027503353,0.03813879,0.0049557206],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.32751969,0.0010769982,0.019778648,0.0013154217,0.0001204312,0.000037102578,0.0023012473,0.00516079,0.0007663669],"category_scores_gemma":[0.86358947,0.0008137871,0.0067752884,0.0007560843,0.0011910617,0.0006641836,0.00068269187,0.010473758,0.00013856219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011499749,0.0018356753,0.07691087,0.0004148238,0.00416165,0.00020660885,0.00006509062,0.00009870964,0.0000044627513,0.00041009017,0.77935076,0.12504151],"study_design_scores_gemma":[0.007731298,0.014437695,0.08530658,0.002089887,0.0029009476,0.00090760796,0.00043661415,0.0027362884,0.0000030041804,0.0064404006,0.87647027,0.000539386],"about_ca_topic_score_codex":0.0000453586,"about_ca_topic_score_gemma":0.00020633619,"teacher_disagreement_score":0.642078,"about_ca_system_score_codex":0.00039974245,"about_ca_system_score_gemma":0.021540504,"threshold_uncertainty_score":0.9994313},"labels":[],"label_agreement":null},{"id":"W4403267879","doi":"10.1016/j.jclinepi.2024.111553","title":"Joint models inform the longitudinal assessment of patient-reported outcomes in clinical trials: a simulation study and secondary analysis of the restrictive Vs. liberal fluid therapy for major abdominal surgery (RELIEF) randomized controlled trial","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Frailty in Older Adults","field":"Medicine","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":"St. Michael's Hospital; Mount Sinai Hospital; Institute for Work & Health; University of Toronto; University Health Network; Public Health Ontario; Toronto Rehabilitation Institute","funders":"Medical Research Council; National Health and Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Randomized controlled trial; Medicine; Physical therapy; Clinical trial; Surgery; Internal medicine","score_opus":0.34190616447477085,"score_gpt":0.5511871272683779,"score_spread":0.20928096279360708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403267879","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":[0.9752294,0.0010588677,0.0058709425,0.0075617624,0.0023862387,0.007833379,0.000022372535,0.000007998983,0.000029054834],"genre_scores_gemma":[0.9963124,0.0011980153,0.0009561777,0.00080119254,0.00047728422,0.00019714964,0.0000074880886,0.000018875395,0.000031445747],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.94392097,0.026984284,0.02767135,0.00043463055,0.0006731883,0.00031555217],"domain_scores_gemma":[0.3767589,0.6048376,0.016377509,0.00067089294,0.0011217177,0.00023334766],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21100429,0.00032383646,0.01899992,0.00073836494,0.000053800795,0.000015985961,0.00021187268,0.0004528508,0.00003780775],"category_scores_gemma":[0.36375684,0.00013511787,0.008958581,0.0005876378,0.00068511517,0.00017799523,0.00008888643,0.0015410173,1.07717874e-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":[0.6687418,0.0018256556,0.28724605,0.000038116283,0.021122906,0.000021724343,0.0002493035,0.007371776,0.0000013182945,0.00010587085,0.00025265457,0.013022779],"study_design_scores_gemma":[0.42219424,0.0038049747,0.37450352,0.00012795917,0.0067977235,0.000010133842,0.00010237824,0.19033344,6.978366e-7,0.0020489253,0.000012090572,0.00006390748],"about_ca_topic_score_codex":0.00008716849,"about_ca_topic_score_gemma":0.00004343874,"teacher_disagreement_score":0.5778533,"about_ca_system_score_codex":0.00007388637,"about_ca_system_score_gemma":0.0015718912,"threshold_uncertainty_score":0.99556404},"labels":[],"label_agreement":null},{"id":"W4403268193","doi":"10.1016/j.jclinepi.2024.111552","title":"Persistent ethnic disparities in authorship within top European and North American medical journals: a serial cross-sectional analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Diversity and Career in Medicine","field":"Social Sciences","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":"Institut National de Santé Publique du Québec; McGill University; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Cross-sectional study; Ethnic group; Medicine; Demography; Family medicine; Environmental health; Sociology; Pathology; Anthropology","score_opus":0.40064706310411435,"score_gpt":0.5439387831325252,"score_spread":0.14329172002841084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403268193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9766281,0.0025591447,0.00042384004,0.016466722,0.0027902469,0.000040528335,0.000006166682,0.000014986523,0.001070214],"genre_scores_gemma":[0.98824435,0.0051511475,0.00033569644,0.0028491125,0.0031614287,4.6486866e-7,0.0000025768798,0.0000062499385,0.00024894677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9833846,0.011884051,0.0029667548,0.0003056449,0.0010098811,0.00044905755],"domain_scores_gemma":[0.9823818,0.015257764,0.0010607507,0.00010808679,0.00023206211,0.00095949904],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12765598,0.000119232056,0.0014230674,0.00032861868,0.00017434043,0.00010582469,0.00056136237,0.00026759543,0.0003761243],"category_scores_gemma":[0.09088305,0.00008940361,0.0008817227,0.00096867594,0.002620588,0.00020589362,0.00012326898,0.0023720898,0.000009699349],"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":[0.00018483278,0.00005497919,0.98415536,0.000014099701,0.0005529126,0.00033208693,0.002112486,0.00036263352,1.0660238e-7,0.002280777,0.0005898896,0.009359862],"study_design_scores_gemma":[0.000383123,0.0003919467,0.9916407,0.00007445457,0.00027613065,0.000056682176,0.002167823,0.00068976695,2.3616794e-8,0.0015557624,0.002675416,0.000088162364],"about_ca_topic_score_codex":0.0011077827,"about_ca_topic_score_gemma":0.0084026875,"teacher_disagreement_score":0.036772933,"about_ca_system_score_codex":0.00008459539,"about_ca_system_score_gemma":0.00054545415,"threshold_uncertainty_score":0.9999295},"labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","research_integrity","scholarly_communication"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4403458056","doi":"10.1016/j.jclinepi.2024.111568","title":"Many randomized trials in a large systematic review were not registered and had evidence of selective outcome reporting: a metaepidemiological study","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Epidemiology; Medicine; Meta-analysis; Randomized controlled trial; Systematic review; Outcome (game theory); MEDLINE; Internal medicine","score_opus":0.9846993043956908,"score_gpt":0.7822405296101224,"score_spread":0.2024587747855684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403458056","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009643299,0.9779673,0.0039939987,0.0025120322,0.0014988647,0.013846411,0.000024481958,0.000005390204,0.00005508996],"genre_scores_gemma":[0.0007624637,0.9912897,0.0044003725,0.0016434861,0.00039274807,0.0004778021,0.000002700416,0.00004007169,0.0009906831],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.010927121,0.5942986,0.38881776,0.0021063613,0.0032704761,0.0005796953],"domain_scores_gemma":[0.0034944476,0.5869243,0.40318665,0.0038061258,0.0021497093,0.00043876912],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.9888144,0.0015044984,0.42977157,0.0017128917,0.00006690104,0.00016440653,0.0042817146,0.001442572,0.0005349628],"category_scores_gemma":[0.99846905,0.000498301,0.085722394,0.0024058314,0.00055076956,0.00027097124,0.0008057558,0.0051843487,0.00023314572],"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":[0.0022620333,0.0006344581,0.0067457655,0.93467224,0.015683558,0.0005324971,0.000100686746,0.0000029002586,1.7310493e-8,0.0018908613,0.017036801,0.020438166],"study_design_scores_gemma":[0.0091517875,0.0011122457,0.00034987018,0.80409336,0.13683061,0.0013443644,0.00015990522,0.0003643959,5.100067e-9,0.0097913705,0.03626098,0.0005410998],"about_ca_topic_score_codex":0.000015812146,"about_ca_topic_score_gemma":0.000017576673,"teacher_disagreement_score":0.3440492,"about_ca_system_score_codex":0.00012878554,"about_ca_system_score_gemma":0.0009198567,"threshold_uncertainty_score":0.9998538},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad","research_integrity"],"domain":"reporting","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4403500042","doi":"10.1016/j.jclinepi.2024.111569","title":"Cross-cultural adaptation and validation to Spanish of the PANELVIEW instrument to evaluate the health guidelines development process","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; McMaster University","funders":"","keywords":"Adaptation (eye); Cross-cultural; Process (computing); Cross-cultural studies; Medicine; Psychology; Computer science; Sociology; Social psychology; Anthropology","score_opus":0.7940754109441899,"score_gpt":0.689176668843959,"score_spread":0.10489874210023087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403500042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70506066,0.00062515604,0.006379678,0.28609923,0.0012367242,0.0005717922,0.0000034498894,0.0000074787854,0.000015833777],"genre_scores_gemma":[0.9364976,0.00085682695,0.025267018,0.03639049,0.0008790477,0.000016476697,0.000007020038,0.00001403033,0.00007145447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98781586,0.002364455,0.00877201,0.00029042186,0.00051424303,0.00024301428],"domain_scores_gemma":[0.974144,0.020533673,0.0023950234,0.0002840526,0.0022683516,0.00037488877],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05035847,0.00014696352,0.0011666953,0.00007205717,0.000100439145,0.000029357772,0.00021065961,0.000113503076,0.000053274984],"category_scores_gemma":[0.26125994,0.00006805093,0.00027144764,0.00030333418,0.0001501335,0.0002035526,0.00011494515,0.0005874847,0.000013628251],"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":[0.0010060633,0.00011339465,0.13017873,0.00035863096,0.0002884811,0.0000038972903,0.0013070938,0.0028770384,0.000075230644,0.0006530701,0.010958639,0.8521797],"study_design_scores_gemma":[0.0017997767,0.0028472263,0.8659188,0.001704958,0.0003449235,0.0003184272,0.0010981819,0.004910829,0.00020148497,0.003403358,0.11730537,0.00014664463],"about_ca_topic_score_codex":0.00007554101,"about_ca_topic_score_gemma":0.00005828805,"teacher_disagreement_score":0.8520331,"about_ca_system_score_codex":0.00010331958,"about_ca_system_score_gemma":0.0014792063,"threshold_uncertainty_score":0.9778558},"labels":[],"label_agreement":null},{"id":"W4403532912","doi":"10.1016/j.jclinepi.2024.111572","title":"“How-to”: scoping review?","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Queen's University; St. Michael's Hospital","funders":"National Health and Medical Research Council","keywords":"Medicine; MEDLINE; Political science","score_opus":0.9665318706159284,"score_gpt":0.7560317524350013,"score_spread":0.21050011818092706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403532912","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":[0.007739248,0.26477066,0.36409616,0.347621,0.009454783,0.000949984,0.000004686659,0.000007801332,0.005355666],"genre_scores_gemma":[0.21907619,0.13378838,0.300785,0.26028877,0.018577082,0.00005811658,0.0000042064344,0.000102985134,0.06731924],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7076865,0.1734983,0.11236051,0.001452818,0.0044166287,0.00058526435],"domain_scores_gemma":[0.18324071,0.75560695,0.050379273,0.0051469733,0.0040552593,0.0015708178],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8060857,0.0002282814,0.01829493,0.00040290397,0.00004387429,0.0002825209,0.0021535365,0.00020090112,0.0054063722],"category_scores_gemma":[0.9292855,0.000087986184,0.009362581,0.001149647,0.00010483316,0.00027404894,0.00015896384,0.0008743525,0.0043303054],"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":[0.000008791762,0.00002284421,0.015034049,0.0009629892,0.00026401447,0.000056342767,0.000017542043,0.00003832819,0.0000025762408,0.0054010074,0.81852704,0.15966445],"study_design_scores_gemma":[0.00011845958,0.00035504307,0.0074646194,0.02669091,0.00043987617,0.0002810609,0.000036369624,0.0015285509,8.9175376e-7,0.046032857,0.9169017,0.0001496509],"about_ca_topic_score_codex":7.509544e-7,"about_ca_topic_score_gemma":0.0000042114034,"teacher_disagreement_score":0.5821087,"about_ca_system_score_codex":0.00001758849,"about_ca_system_score_gemma":0.00034229938,"threshold_uncertainty_score":0.99644494},"labels":[],"label_agreement":null},{"id":"W4403566155","doi":"10.1016/j.jclinepi.2024.111579","title":"What advice can we offer to authors? Reflections from the statisticians’ bench","year":2024,"lang":"en","type":"editorial","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Toronto; St. Michael's Hospital","funders":"","keywords":"Advice (programming); Bench to bedside; Medical education; Medicine; Medical physics; Psychology; Computer science","score_opus":0.8859619843426795,"score_gpt":0.7010354682968198,"score_spread":0.18492651604585963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403566155","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012963738,0.00929647,0.019890128,0.12800646,0.8413088,0.00037752453,0.0004422932,0.0000054599545,0.0005432794],"genre_scores_gemma":[0.00013727792,0.009119588,0.02140883,0.009977642,0.9265083,0.000023539887,0.00005140872,0.000049479284,0.03272392],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.63878393,0.24272686,0.10521514,0.0025788292,0.009809835,0.0008853778],"domain_scores_gemma":[0.06699774,0.8684026,0.052088674,0.0050103315,0.0063585807,0.0011420749],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.6432152,0.0006784797,0.0237552,0.00054132007,0.0002147862,0.0011103487,0.0058356947,0.002008697,0.008214703],"category_scores_gemma":[0.9375064,0.00025276782,0.010098961,0.001437057,0.00030075954,0.00026640523,0.00047801615,0.006434369,0.004744661],"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":[0.00005259571,0.000044815642,0.0006925828,0.000027489736,0.0013003919,0.000038016187,0.00030747187,0.00010074801,2.5231626e-7,0.0006236572,0.968043,0.028768929],"study_design_scores_gemma":[0.00013608654,0.0003415951,0.0014290853,0.0005647268,0.0016575545,0.000011752042,0.00050958776,0.00034563706,3.605806e-8,0.16389018,0.8309293,0.00018449302],"about_ca_topic_score_codex":0.00028760286,"about_ca_topic_score_gemma":0.0030077414,"teacher_disagreement_score":0.62567574,"about_ca_system_score_codex":0.00012266924,"about_ca_system_score_gemma":0.001618726,"threshold_uncertainty_score":0.99999243},"labels":[],"label_agreement":null},{"id":"W4403566336","doi":"10.1016/j.jclinepi.2024.111573","title":"When results from clinical trials are different from observational studies","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Public Health; Children's Hospital of Eastern Ontario; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Observational study; Medicine; Medical physics; Family medicine; Internal medicine","score_opus":0.9913192770044542,"score_gpt":0.7615032332523817,"score_spread":0.22981604375207254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403566336","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014088172,0.022807559,0.0041559497,0.92263615,0.032973513,0.0005801139,0.0024947796,0.000007938754,0.0002558387],"genre_scores_gemma":[0.0010389606,0.008359903,0.0207786,0.8498315,0.10528685,0.000020585458,0.00049807347,0.00006338128,0.014122132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.08475197,0.60732716,0.2952567,0.003605278,0.008307562,0.00075130665],"domain_scores_gemma":[0.004807855,0.7826064,0.20253865,0.004844308,0.0046651303,0.00053763384],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.8816932,0.0011558819,0.097625844,0.000627465,0.000110645306,0.00042478362,0.0061186072,0.004170788,0.00842916],"category_scores_gemma":[0.98561925,0.00044126494,0.045605086,0.0004421997,0.0007806347,0.00022662812,0.00082636107,0.011749779,0.0047751814],"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":[0.00028618562,0.00009572516,0.08569673,0.000041652707,0.013252606,0.00038748223,0.00006620643,0.000013480328,1.16856086e-7,0.00011005436,0.8885387,0.01151104],"study_design_scores_gemma":[0.0008340148,0.0001991141,0.0928507,0.0006632796,0.0039693387,0.000009476609,0.00006976414,0.0004901467,5.0882722e-8,0.3058387,0.594852,0.00022341435],"about_ca_topic_score_codex":0.000038084785,"about_ca_topic_score_gemma":0.00004926516,"teacher_disagreement_score":0.30572867,"about_ca_system_score_codex":0.00010002187,"about_ca_system_score_gemma":0.0006158526,"threshold_uncertainty_score":0.9998039},"labels":[],"label_agreement":null},{"id":"W4403587378","doi":"10.1016/j.jclinepi.2024.111578","title":"GRADE Notes 4: how to use GRADE when there is “no” evidence? A case study of using unpublished registry data","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Medicine; Family medicine","score_opus":0.9802702806093347,"score_gpt":0.7200195068608085,"score_spread":0.26025077374852623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403587378","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":[0.9231879,0.004200831,0.031482268,0.03824959,0.002240689,0.00057052984,0.00004216403,0.000004405038,0.000021618896],"genre_scores_gemma":[0.9491247,0.00027794685,0.046140835,0.0024099082,0.0009995278,0.0000031972475,0.0000014057515,0.000020033985,0.0010224645],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.78112894,0.1481094,0.062368117,0.0025869566,0.00510704,0.00069953484],"domain_scores_gemma":[0.26403254,0.67661893,0.04160306,0.012405533,0.004141325,0.0011986145],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.54681695,0.00038256144,0.013226672,0.00059861335,0.00009548688,0.00082164555,0.004942399,0.00035315842,0.0016624305],"category_scores_gemma":[0.89218026,0.00016679677,0.0034326282,0.0012561894,0.00022535947,0.0016550114,0.00089099654,0.0012418734,0.00016882044],"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":[0.00007887769,0.00041647116,0.5361083,0.00013256683,0.0015522346,0.002428288,0.00090749556,0.00023260016,0.000020757834,0.00015084319,0.44706032,0.010911216],"study_design_scores_gemma":[0.0025554162,0.0068316148,0.11566213,0.004699137,0.010079923,0.021519499,0.019130731,0.26208478,0.000007835822,0.055826206,0.50020033,0.0014023812],"about_ca_topic_score_codex":0.00052346394,"about_ca_topic_score_gemma":0.00023767006,"teacher_disagreement_score":0.5285095,"about_ca_system_score_codex":0.000034568973,"about_ca_system_score_gemma":0.00045512425,"threshold_uncertainty_score":0.9992502},"labels":[],"label_agreement":null},{"id":"W4403616350","doi":"10.1016/j.jclinepi.2024.111575","title":"Paper 6: engaging racially and ethnically diverse interest holders in evidence syntheses","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"University of Ottawa; Bruyère","funders":"Robert Wood Johnson Foundation","keywords":"Ethnically diverse; Health equity; Equity (law); Systematic review; MEDLINE; Medicine; Psychology; Business; Public health; Political science; Environmental health; Nursing","score_opus":0.9812146410306677,"score_gpt":0.8353292348981347,"score_spread":0.14588540613253298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403616350","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":[0.00037062695,0.9511575,0.00022715768,0.042481933,0.0045976676,0.00083303696,0.000026531867,0.000020612775,0.00028492312],"genre_scores_gemma":[0.0006054749,0.9659799,0.0017857173,0.02944525,0.0019477939,0.00004424078,8.1429414e-7,0.000037811882,0.00015302944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9085829,0.07047851,0.018818473,0.00070474047,0.00033778808,0.0010775421],"domain_scores_gemma":[0.37027118,0.617909,0.010055791,0.00047443112,0.00034403335,0.0009455297],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.17267323,0.00041628943,0.008253766,0.00065684423,0.00022053886,0.000013531023,0.0009267447,0.0013226126,0.0004743499],"category_scores_gemma":[0.7371803,0.00026360806,0.0009992989,0.00052052015,0.0007064266,0.0004272675,0.00068364514,0.009908133,0.0003791619],"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":[0.000061970866,0.000029144629,0.008119601,0.015727464,0.00011690938,0.00014350555,0.00089065643,7.861186e-7,6.251752e-8,0.0016011655,0.022220818,0.9510879],"study_design_scores_gemma":[0.00027477284,0.00025669028,0.0031429033,0.10186315,0.00040649838,0.000066782006,0.00050539,0.000008869531,1.6673011e-9,0.0017111453,0.89157695,0.00018682545],"about_ca_topic_score_codex":0.00013447682,"about_ca_topic_score_gemma":0.00060414494,"teacher_disagreement_score":0.9509011,"about_ca_system_score_codex":0.00030787397,"about_ca_system_score_gemma":0.0057940925,"threshold_uncertainty_score":0.99998164},"labels":[],"label_agreement":null},{"id":"W4403626031","doi":"10.1016/j.jclinepi.2024.111581","title":"Exposure misclassification: an “immortal time” bias in observational studies of training load and injury","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sports Performance and Training","field":"Medicine","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":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Observational study; Medicine; Training (meteorology); Physical therapy; Physical medicine and rehabilitation; Statistics; Internal medicine; Geography; Mathematics; Meteorology","score_opus":0.7754623047941801,"score_gpt":0.5918495844245124,"score_spread":0.1836127203696677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403626031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884419,0.0053916005,0.00002695198,0.0052046096,0.00041670084,0.000059404585,0.0000018765022,0.000008571057,0.0004483963],"genre_scores_gemma":[0.9934546,0.0011585128,0.0031801353,0.0010414736,0.0008209055,0.0000016436808,0.0000050167378,0.00000918548,0.0003285594],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99606174,0.00023736047,0.0031860194,0.00018391333,0.00017593434,0.00015505053],"domain_scores_gemma":[0.99290687,0.0057289354,0.0008564041,0.00011887381,0.0002505857,0.0001383563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01662294,0.00010362458,0.0015626242,0.00014258038,0.000018012493,0.0000030206702,0.00006392078,0.00018918801,0.00006040754],"category_scores_gemma":[0.0114824185,0.00007108315,0.00021580516,0.00012607101,0.00030969546,0.0001838514,0.000016617192,0.00065275846,0.0000033623915],"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":[0.00046244083,0.00009079016,0.9216404,0.00010754403,0.00024621346,0.00011078554,0.001137283,0.00004284152,0.00010125979,0.0018219794,0.0007174807,0.073520966],"study_design_scores_gemma":[0.0008571477,0.0018374377,0.9856512,0.0006254213,0.00010728186,0.00029402116,0.0006470917,0.0038293053,0.0000069476823,0.0033949995,0.0026866002,0.00006254996],"about_ca_topic_score_codex":0.0000017082427,"about_ca_topic_score_gemma":0.000004347383,"teacher_disagreement_score":0.07345841,"about_ca_system_score_codex":0.000029286171,"about_ca_system_score_gemma":0.0005645384,"threshold_uncertainty_score":0.9968443},"labels":[],"label_agreement":null},{"id":"W4403628371","doi":"10.1016/j.jclinepi.2024.111576","title":"Paper 5: a methodological overview of methods and interventions","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Cultural Competency in Health Care","field":"Social Sciences","cited_by":9,"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; Bruyère; University of Ottawa","funders":"Kaiser Permanente; Robert Wood Johnson Foundation","keywords":"Psychological intervention; Health equity; Equity (law); Systematic review; Medicine; Actuarial science; MEDLINE; Psychology; Management science; Public health; Economics; Political science; Nursing","score_opus":0.9480157533957708,"score_gpt":0.7945174226915437,"score_spread":0.15349833070422714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403628371","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":[0.0000042008733,0.98852164,0.00091204135,0.0043187365,0.0050043585,0.0003261811,0.00001685956,0.000014395852,0.00088156975],"genre_scores_gemma":[0.0000017758582,0.8874213,0.1098841,0.00063849223,0.0018110827,0.000009902926,0.0000022012082,0.000015394713,0.00021576621],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8727267,0.11395172,0.012268017,0.00041408325,0.00022439702,0.000415079],"domain_scores_gemma":[0.7652714,0.22417107,0.009168426,0.00030889877,0.0005257137,0.00055445614],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.19093779,0.00029793772,0.011965892,0.00020519612,0.00010052,0.000012934824,0.0007177644,0.0014656478,0.00048601063],"category_scores_gemma":[0.3939958,0.0001641449,0.006646068,0.0004345167,0.0011857523,0.00011368709,0.00027441204,0.0030720418,0.00001822543],"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":[0.00001034191,0.000038261245,0.000056901736,0.01657336,0.00033541393,0.000012676251,0.00010931081,1.188518e-7,1.4908462e-8,0.05692962,0.00493843,0.92099553],"study_design_scores_gemma":[0.000080006386,0.0004435921,0.00016909404,0.024696935,0.0021917415,0.00011032866,0.00012910526,9.550738e-7,2.9411766e-9,0.047230408,0.92482257,0.00012523955],"about_ca_topic_score_codex":0.00012435748,"about_ca_topic_score_gemma":0.00009447587,"teacher_disagreement_score":0.9208703,"about_ca_system_score_codex":0.000093793555,"about_ca_system_score_gemma":0.0010823712,"threshold_uncertainty_score":0.99983066},"labels":[],"label_agreement":null},{"id":"W4403660817","doi":"10.1016/j.jclinepi.2024.111574","title":"Paper 2: themes from semistructured interviews","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Bruyère; University of Ottawa","funders":"Colorado School of Public Health; Chicago Center for Diabetes Translation Research; University of California, San Diego; University of California, Los Angeles; Agency for Healthcare Research and Quality; RTI International; Cedars-Sinai Medical Center; University of Pittsburgh; Ohio State University; Bruyère Research Institute; Patient-Centered Outcomes Research Institute; Kaiser Permanente; University of Ottawa; American Heart Association; National Institute on Minority Health and Health Disparities; College of Medicine, Drexel University; Centers for Disease Control and Prevention; University of Pennsylvania; Robert Wood Johnson Foundation","keywords":"Health equity; Equity (law); Systematic review; MEDLINE; Sociology; Medicine; Psychology; Public health; Political science; Nursing","score_opus":0.9032539451022398,"score_gpt":0.8023161251313916,"score_spread":0.10093781997084816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403660817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4988131,0.004668149,0.01662135,0.44536895,0.02678447,0.00048947503,0.00013187491,0.000092658585,0.0070299893],"genre_scores_gemma":[0.7160086,0.0020464596,0.014484766,0.25738183,0.008933402,0.000014771046,0.0000050435456,0.00002569847,0.0010994532],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718381,0.017844908,0.009212952,0.00029676093,0.00023157249,0.00057569175],"domain_scores_gemma":[0.80450344,0.19149166,0.002849647,0.00032286573,0.00027239113,0.00056001294],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04415511,0.00013795376,0.0017466492,0.00010969865,0.00014983717,0.000006450858,0.00049030996,0.000406385,0.0076789632],"category_scores_gemma":[0.16882977,0.00008341841,0.00048779842,0.00019771494,0.00022266411,0.00023195583,0.00012228734,0.0023815392,0.00066694367],"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":[0.00014578826,0.00002337788,0.13024542,0.00021716746,0.00015815697,0.000043615528,0.004963343,0.000008750667,0.00017880609,0.009971019,0.76110965,0.09293488],"study_design_scores_gemma":[0.0005028842,0.00015747714,0.109454,0.00034229094,0.000028283743,0.000013554844,0.00066397636,0.00025577494,0.000002765302,0.071140565,0.8173689,0.00006950336],"about_ca_topic_score_codex":0.00013876008,"about_ca_topic_score_gemma":0.00008581306,"teacher_disagreement_score":0.21719547,"about_ca_system_score_codex":0.00008640121,"about_ca_system_score_gemma":0.0013137237,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W4403827847","doi":"10.1016/j.jclinepi.2024.111580","title":"Paper 3: a systematic review of definitions for “racial health equity” and related terms within health-related articles","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Racial and Ethnic Identity Research","field":"Social Sciences","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":"Bruyère; University of Ottawa","funders":"RTI International; National Institutes of Health; Kaiser Permanente; Georgia Clinical and Translational Science Alliance; National Center for Advancing Translational Sciences; Robert Wood Johnson Foundation","keywords":"Health equity; Equity (law); Systematic review; Actuarial science; MEDLINE; Psychology; Public health; Medicine; Public economics; Sociology; Economics; Political science; Nursing","score_opus":0.6990124921745311,"score_gpt":0.6656520511679617,"score_spread":0.03336044100656943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403827847","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":[0.000004168121,0.9552048,0.000043311065,0.040491764,0.0016944221,0.0019346703,0.00004922969,0.000016199696,0.0005614388],"genre_scores_gemma":[0.00003219697,0.99620634,0.00044186035,0.0023232803,0.00047632077,0.000055111777,0.000013884113,0.000026244035,0.00042477623],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95273775,0.027205601,0.018355798,0.00039555435,0.0006018767,0.0007034311],"domain_scores_gemma":[0.94975543,0.035592534,0.013232689,0.00028695626,0.00041529903,0.000717076],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18622808,0.00027326058,0.012993829,0.00027021053,0.00034055876,0.00003262617,0.0006453388,0.0008280515,0.00008950299],"category_scores_gemma":[0.21859108,0.00017097498,0.002610248,0.0006323391,0.0010788396,0.00016668528,0.00024928802,0.0021433167,0.000049569957],"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":[0.000015794976,0.000096400094,0.000008416482,0.81077284,0.00059123617,0.000011795929,0.00067168043,1.7525383e-7,5.325911e-9,0.054079082,0.0076341974,0.12611836],"study_design_scores_gemma":[0.00024955618,0.0007969871,0.000012770509,0.718315,0.0017551457,0.0001471492,0.0001628583,0.000007382665,1.367429e-9,0.15884347,0.119557686,0.00015201478],"about_ca_topic_score_codex":0.00045645057,"about_ca_topic_score_gemma":0.000615434,"teacher_disagreement_score":0.12596636,"about_ca_system_score_codex":0.00022213729,"about_ca_system_score_gemma":0.005161539,"threshold_uncertainty_score":0.9311763},"labels":[],"label_agreement":null},{"id":"W4403897519","doi":"10.1016/j.jclinepi.2024.111577","title":"Paper 1: introduction to the series","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Race, Genetics, and Society","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Bruyère; University of Ottawa","funders":"Robert Wood Johnson Foundation","keywords":"Series (stratigraphy); Equity (law); Health equity; Actuarial science; Econometrics; Sociology; Public health; Economics; Medicine; Political science; Geology; Nursing; Law","score_opus":0.07959686103006923,"score_gpt":0.43613229032846035,"score_spread":0.3565354292983911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403897519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.558323,0.013159994,0.02179041,0.39183205,0.013976008,0.00016546393,0.000008125208,0.000013448702,0.0007314443],"genre_scores_gemma":[0.8684493,0.017501682,0.011766194,0.024068216,0.07210254,0.000007678509,0.000013891171,0.000039157647,0.006051384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99671817,0.001239075,0.001489114,0.000261671,0.0000874807,0.00020448225],"domain_scores_gemma":[0.9980761,0.0010013101,0.0003137259,0.0003096372,0.00015370306,0.00014553333],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011545974,0.00010167085,0.00053629506,0.000021740436,0.00006164784,0.000013590933,0.0002506929,0.0002772766,0.000054930813],"category_scores_gemma":[0.017410906,0.000058901467,0.00054461055,0.00007001945,0.00021469918,0.0000062634963,0.00008140048,0.0004491969,0.000042585692],"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":[0.0002869618,0.000050772855,0.0048962804,0.00002098245,0.0003179275,0.000010602097,0.00012958341,0.0011877397,0.009565873,0.0030216284,0.9453525,0.035159145],"study_design_scores_gemma":[0.00012776928,0.00097352895,0.0138037065,0.0000110670835,0.000036014982,0.00020571736,0.00010260157,0.000048344828,0.0004775918,0.0027767208,0.981365,0.000071939416],"about_ca_topic_score_codex":0.0000024778171,"about_ca_topic_score_gemma":0.000013562528,"teacher_disagreement_score":0.36776385,"about_ca_system_score_codex":0.000008042012,"about_ca_system_score_gemma":0.00014112999,"threshold_uncertainty_score":0.9908659},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4403910515","doi":"10.1016/j.jclinepi.2024.111583","title":"Paper 4: a systematic review on the use of logic models and frameworks for methodological conduct of evidence synthesis","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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 Ottawa; Bruyère","funders":"Kaiser Permanente; Robert Wood Johnson Foundation","keywords":"Systematic review; Equity (law); Health equity; Management science; MEDLINE; Psychology; Medicine; Public health; Economics; Political science; Pathology","score_opus":0.9961940437007423,"score_gpt":0.8574348571440866,"score_spread":0.13875918655665564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403910515","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":[0.000004996265,0.9202747,0.016215472,0.057902332,0.00092271663,0.004557331,0.000103686456,0.000006720218,0.000012086627],"genre_scores_gemma":[0.000010454338,0.8976325,0.03264445,0.06874111,0.00033164627,0.0005585134,7.314637e-7,0.000024423804,0.000056217028],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.82370627,0.15246181,0.022318278,0.00048877794,0.00043376203,0.0005911154],"domain_scores_gemma":[0.16979145,0.80458206,0.023666648,0.00074664614,0.0008763866,0.00033684436],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.29245123,0.00039736563,0.019369638,0.00022363817,0.00013908806,0.0000049637692,0.0009469574,0.0018152731,0.00019111551],"category_scores_gemma":[0.9140847,0.00014643493,0.0022490937,0.00042379674,0.00073117093,0.00019040349,0.00025102097,0.005146117,0.000022536791],"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":[0.000045186516,0.00002516806,0.000011758722,0.9219694,0.0003179933,0.0000027024819,0.00007142044,0.0000056109106,4.6648214e-8,0.023139106,0.030305073,0.024106499],"study_design_scores_gemma":[0.000089194684,0.0006091476,0.000009309111,0.8184423,0.0047418564,0.00004075668,0.00005159546,0.00016041777,1.569813e-8,0.022571012,0.15316811,0.00011631462],"about_ca_topic_score_codex":0.000014116772,"about_ca_topic_score_gemma":0.0000029288908,"teacher_disagreement_score":0.6539148,"about_ca_system_score_codex":0.00009591205,"about_ca_system_score_gemma":0.0021312293,"threshold_uncertainty_score":0.9994806},"labels":[],"label_agreement":null},{"id":"W4404203790","doi":"10.1016/j.jclinepi.2024.111610","title":"The influence of intervention fidelity on treatment effect estimates in clinical trials of complex interventions: a metaepidemiological study","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":31,"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":"Concordia University; University of Sheffield; University of Oxford","keywords":"Meta-analysis; Psychological intervention; Epidemiology; Medicine; Intervention (counseling); Fidelity; Clinical trial; Randomized controlled trial; Physical therapy; Internal medicine; Psychiatry; Computer science","score_opus":0.986289619663549,"score_gpt":0.819838185501042,"score_spread":0.16645143416250696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404203790","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030910715,0.96149284,0.0013494637,0.00057914056,0.002110621,0.0034616673,0.000057301255,0.0000032755213,0.00003498624],"genre_scores_gemma":[0.015758596,0.98129827,0.00208018,0.000093138064,0.0004322527,0.00013688087,0.000010195979,0.00002183451,0.00016863752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.046838757,0.6707855,0.2782343,0.0015141118,0.0021858609,0.00044149713],"domain_scores_gemma":[0.0135344025,0.79002094,0.1911683,0.0034541348,0.0014971732,0.00032504686],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9531654,0.0010052694,0.12300273,0.0010546095,0.000067811,0.00009517013,0.0041648936,0.0010385135,0.0006045885],"category_scores_gemma":[0.97720265,0.00028163148,0.09738607,0.0013872932,0.0009241408,0.000116348594,0.000486555,0.0026804043,0.00029073897],"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":[0.00032586546,0.0020616169,0.041385613,0.0034424036,0.0076145995,0.000028375734,0.000017260974,0.00032052913,2.6545921e-8,0.00088428264,0.005389325,0.9385301],"study_design_scores_gemma":[0.0038838892,0.04461679,0.20708978,0.06095989,0.05530848,0.00014495826,0.00023570987,0.0020049785,8.8767834e-8,0.06129182,0.56386346,0.0006001914],"about_ca_topic_score_codex":0.000056129953,"about_ca_topic_score_gemma":0.000083643834,"teacher_disagreement_score":0.9379299,"about_ca_system_score_codex":0.0001361062,"about_ca_system_score_gemma":0.00038389757,"threshold_uncertainty_score":0.9999636},"labels":[],"label_agreement":null},{"id":"W4404210001","doi":"10.1016/j.jclinepi.2024.111606","title":"Sociodemographic bias in clinical machine learning models: a scoping review of algorithmic bias instances and mechanisms","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Psychology; MEDLINE; Data science; Cognitive psychology; Medicine; Econometrics; Mathematics; Political science","score_opus":0.884224973394516,"score_gpt":0.6781846192456815,"score_spread":0.20604035414883448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404210001","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":[0.00016377035,0.9903743,0.002663289,0.003455675,0.0023413603,0.0009316313,0.0000058912137,0.000013293124,0.00005073486],"genre_scores_gemma":[0.0001319876,0.9896842,0.0066653327,0.0020724703,0.0013348289,0.000021581827,0.0000182266,0.000043531592,0.000027826529],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.964469,0.0125666,0.021628525,0.00059024995,0.00031665261,0.00042896593],"domain_scores_gemma":[0.92563474,0.06112639,0.011794911,0.000382872,0.00053647225,0.0005246013],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09260274,0.0004032204,0.013572904,0.0006107444,0.000044322314,0.0000068084537,0.00026679828,0.0013414819,0.000036759524],"category_scores_gemma":[0.12662779,0.00025622355,0.00280848,0.0006240359,0.00049400766,0.00011055283,0.000100455894,0.0057364423,0.000013143555],"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":[0.000050696213,0.0001272915,0.0029046054,0.1764422,0.00023464755,0.000046547826,0.000029301933,0.0000034267161,5.9287184e-9,0.0010752463,0.00018284749,0.8189032],"study_design_scores_gemma":[0.00013754243,0.0019189552,0.000059267426,0.92553276,0.002385138,0.0005096979,0.00006511878,0.0021747786,5.945679e-8,0.033761512,0.033243638,0.0002115462],"about_ca_topic_score_codex":0.00010020479,"about_ca_topic_score_gemma":0.0000613685,"teacher_disagreement_score":0.8186916,"about_ca_system_score_codex":0.00007203184,"about_ca_system_score_gemma":0.0028534762,"threshold_uncertainty_score":0.999989},"labels":[],"label_agreement":null},{"id":"W4404630651","doi":"10.1016/j.jclinepi.2024.111616","title":"Research culture influences in health and biomedical research: rapid scoping review and content analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Ottawa; Ottawa Hospital; Queen's University; St. Michael's Hospital","funders":"Medical Research Council; Anschutz Medical Campus, University of Colorado; Agence Nationale de la Recherche; UK Research and Innovation","keywords":"Content analysis; Medicine; Psychology; Sociology; Social science","score_opus":0.9880919341178612,"score_gpt":0.8100845576768024,"score_spread":0.1780073764410588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404630651","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06600754,0.80613524,0.002008607,0.12455723,0.00034359342,0.0006926136,0.0000045851566,0.0000019778433,0.00024863583],"genre_scores_gemma":[0.1989464,0.7799353,0.00876336,0.010552442,0.0006411353,0.000022887429,0.0000031639179,0.000011257046,0.0011240277],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.41893873,0.49163213,0.078869574,0.0019474156,0.007489192,0.0011229559],"domain_scores_gemma":[0.16451107,0.8029616,0.020194449,0.0030176635,0.006402658,0.0029125677],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90982014,0.0001899617,0.014823574,0.0023188824,0.00014861012,0.00025684288,0.0011998625,0.00029432,0.0012481312],"category_scores_gemma":[0.8218359,0.0000762634,0.002191015,0.005993498,0.0013307914,0.00024297985,0.00032730433,0.002757023,0.0001098671],"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":[0.000066277964,0.0001622801,0.4746964,0.008004919,0.0022715437,0.0001533984,0.0008036696,0.000018529814,0.0000035868395,0.008014039,0.2533547,0.25245064],"study_design_scores_gemma":[0.0011257285,0.0049403645,0.32460985,0.085682504,0.0017536995,0.0005348179,0.0060138493,0.009637372,3.3005276e-7,0.09940003,0.46584967,0.00045180015],"about_ca_topic_score_codex":0.000059478945,"about_ca_topic_score_gemma":0.00009425722,"teacher_disagreement_score":0.31132945,"about_ca_system_score_codex":0.000042834836,"about_ca_system_score_gemma":0.0008850607,"threshold_uncertainty_score":0.9998024},"labels":[],"label_agreement":null},{"id":"W4404733343","doi":"10.1016/j.jclinepi.2024.111618","title":"Key challenges in epidemiology: embracing open science","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Key (lock); Epidemiology; MEDLINE; Medicine; Data science; Computer science; Political science; Pathology; Computer security","score_opus":0.4807128686165083,"score_gpt":0.5498567331577753,"score_spread":0.06914386454126698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404733343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8263176,0.008774644,0.0056830854,0.104684815,0.003207488,0.0005669771,0.000003883519,0.000035490237,0.05072602],"genre_scores_gemma":[0.9597038,0.012611944,0.017655909,0.009358319,0.0005193721,0.000010165801,5.8056474e-7,0.000024625366,0.00011525836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98214716,0.009420019,0.005757296,0.0012183356,0.0003367498,0.0011204261],"domain_scores_gemma":[0.93776375,0.059295308,0.0016546466,0.00054704736,0.0000256665,0.00071357086],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22331084,0.00023569845,0.0022811256,0.00024317083,0.00013181951,0.000023078263,0.0019525819,0.00036082932,0.0007909897],"category_scores_gemma":[0.17084208,0.00017719564,0.00034097498,0.00048959185,0.0021538716,0.0010392844,0.0014141917,0.0022165864,0.0006745597],"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":[0.00009500127,0.00017637882,0.5528092,0.000041711555,0.000033220404,0.00022297991,0.00035788177,0.0020260965,0.00013361895,0.011827621,0.0013116256,0.4309647],"study_design_scores_gemma":[0.0005023428,0.00049449876,0.84755486,0.00032274498,0.0000207293,0.00021468489,0.00016788646,0.0058609224,0.000014257274,0.09916703,0.045485176,0.00019488265],"about_ca_topic_score_codex":0.00020204032,"about_ca_topic_score_gemma":0.00014285659,"teacher_disagreement_score":0.4307698,"about_ca_system_score_codex":0.00042372182,"about_ca_system_score_gemma":0.00032779388,"threshold_uncertainty_score":0.96300876},"labels":[],"label_agreement":null},{"id":"W4405012215","doi":"10.1016/j.jclinepi.2024.111621","title":"Determinants of cost-effectiveness results of biological therapies for severe asthma: a systematic methodological assessment","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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; Hamilton Health Sciences","funders":"Instituto de Salud Carlos III; European Social Fund; Centro Nacional de Investigaciones Cardiovasculares","keywords":"Medicine; Cost effectiveness; Systematic review; Asthma; Intensive care medicine; MEDLINE; Internal medicine; Risk analysis (engineering); Biology","score_opus":0.9496577169345581,"score_gpt":0.7265652004275072,"score_spread":0.22309251650705098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405012215","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":[0.00083258824,0.97335094,0.016161256,0.0013082887,0.0032730128,0.00374084,0.0012367108,0.000012220654,0.00008416503],"genre_scores_gemma":[0.0013136385,0.9610701,0.0356275,0.0006125914,0.00089108956,0.00035935565,0.000029454564,0.000049749415,0.00004652537],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.87947005,0.05481364,0.06404158,0.0009516638,0.00014643597,0.0005766574],"domain_scores_gemma":[0.5970594,0.34389305,0.057818852,0.0006146839,0.00036729805,0.00024671576],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49946532,0.0005581804,0.03808304,0.0006195396,0.00005452688,0.000014094074,0.0009839382,0.0018606103,0.000037842514],"category_scores_gemma":[0.47217146,0.0003741684,0.005134367,0.00026128642,0.00048894313,0.00013034754,0.00017167305,0.0013524017,0.00005636726],"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":[0.0007223556,0.0008745104,0.011145378,0.8417117,0.0045935633,0.000019854233,0.0001735029,0.00007241103,8.06494e-8,0.06721733,0.0056089684,0.06786033],"study_design_scores_gemma":[0.005194987,0.009454658,0.0137208095,0.24205582,0.0021876686,0.0006740626,0.0003626407,0.0016230481,2.4680145e-7,0.15301813,0.570459,0.0012489293],"about_ca_topic_score_codex":0.000030570423,"about_ca_topic_score_gemma":0.00000625529,"teacher_disagreement_score":0.5996559,"about_ca_system_score_codex":0.0003836223,"about_ca_system_score_gemma":0.0010385279,"threshold_uncertainty_score":0.999871},"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":"W4405187752","doi":"10.1016/j.jclinepi.2024.111635","title":"Cobuilding patient and public capacity in knowledge synthesis: designed and delivered by patient and public partners for patient and public partners","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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":"Public Health Ontario; Toronto Rehabilitation Institute; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Canadian HIV Trials Network, Canadian Institutes of Health Research","keywords":"Public health; Medicine; Business; Nursing","score_opus":0.6582861340908388,"score_gpt":0.5603594572901279,"score_spread":0.09792667680071088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405187752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690992,0.01669651,0.0006611988,0.010094794,0.0016489953,0.001513644,0.000115948074,0.000028875907,0.00014079179],"genre_scores_gemma":[0.98446375,0.0072529283,0.0024389466,0.0052705607,0.00020799281,0.00028480944,0.00003217167,0.000036153448,0.000012680241],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98277473,0.008945,0.005844214,0.0007676198,0.00028223646,0.0013862082],"domain_scores_gemma":[0.9510299,0.044186864,0.0021915145,0.00024221369,0.0004100875,0.001939432],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015034499,0.00039918663,0.0020819502,0.0004291027,0.0005622873,0.00005300884,0.0001620736,0.0006763486,0.00004947088],"category_scores_gemma":[0.02322593,0.0002987171,0.0001990898,0.00025230565,0.0005719339,0.0004760635,0.0002935418,0.0014362634,0.000004500553],"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":[0.0006890882,0.0006714512,0.73847395,0.0020002695,0.0001968171,0.000014019744,0.0031854308,0.0000018789167,0.00001937833,0.0055030975,0.018907119,0.23033752],"study_design_scores_gemma":[0.019983327,0.03636565,0.11292032,0.012242637,0.000715449,0.00024517492,0.05366342,0.028693471,0.00007825214,0.030784592,0.7015688,0.002738931],"about_ca_topic_score_codex":0.00021213156,"about_ca_topic_score_gemma":0.0005097052,"teacher_disagreement_score":0.68266165,"about_ca_system_score_codex":0.00027791306,"about_ca_system_score_gemma":0.0007161448,"threshold_uncertainty_score":0.9999465},"labels":[],"label_agreement":null},{"id":"W4405212503","doi":"10.1016/j.jclinepi.2024.111639","title":"Defining decision thresholds for judgments on health benefits and harms using the grading of recommendations assessment, development, and evaluation (GRADE) evidence to decision (EtD) frameworks: a randomized methodological study (GRADE-THRESHOLD)","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Western University; McMaster University Medical Centre; Impact; McMaster University","funders":"","keywords":"Grading (engineering); Categorization; Guideline; Medicine; Evidence-based medicine; Actuarial science; Psychology; Management science; Alternative medicine; Computer science; Artificial intelligence","score_opus":0.902069972364624,"score_gpt":0.6969552872768768,"score_spread":0.20511468508774722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405212503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6057449,0.012699851,0.3273751,0.05058585,0.0015928776,0.001961967,0.000021312699,0.000008463577,0.000009665222],"genre_scores_gemma":[0.5759803,0.003779031,0.41136655,0.008446814,0.0002792961,0.00011809539,0.0000045916468,0.000022160715,0.0000031366894],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96419054,0.013603295,0.020429457,0.00093474984,0.00032938892,0.0005125543],"domain_scores_gemma":[0.64037293,0.35054433,0.00812541,0.00035671724,0.00024500006,0.00035561467],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47282323,0.00025537534,0.004375304,0.00059081556,0.0003667337,0.00008558575,0.0003393181,0.0003894368,0.0000359895],"category_scores_gemma":[0.30082536,0.00018839166,0.00042412465,0.00027014024,0.00017051584,0.00039527286,0.00014536726,0.0010300789,0.000006305072],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010549987,0.00089512015,0.34061912,0.000470032,0.001358806,0.000002416941,0.004689992,0.020737406,0.0000016144279,0.24556237,0.011089138,0.364024],"study_design_scores_gemma":[0.042807665,0.003520347,0.17472273,0.007584627,0.00030046672,0.0000656401,0.0021535337,0.3054504,0.0000025004845,0.45867267,0.004181818,0.00053757505],"about_ca_topic_score_codex":0.000051338986,"about_ca_topic_score_gemma":0.000045241646,"teacher_disagreement_score":0.36348644,"about_ca_system_score_codex":0.00036248178,"about_ca_system_score_gemma":0.0005641728,"threshold_uncertainty_score":0.76823884},"labels":[],"label_agreement":null},{"id":"W4405293073","doi":"10.1016/j.jclinepi.2024.111615","title":"Corrigendum to ‘Identification of homelessness using health administrative data in Ontario, Canada following a national coding mandate: a validation study’ [Journal of Clinical Epidemiology 172 (2024) 111430]","year":2024,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Homelessness and Social Issues","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Toronto Public Health; Public Health Ontario; University of Toronto; London Health Sciences Centre","funders":"","keywords":"Mandate; Epidemiology; Identification (biology); Coding (social sciences); Public health; Environmental health; Medicine; Public administration; Political science; Sociology; Nursing; Law; Social science; Pathology; Biology","score_opus":0.6878621657538403,"score_gpt":0.6472457585742227,"score_spread":0.040616407179617564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405293073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7048087,0.0031327098,0.004747029,0.0061091282,0.27848423,0.0017226444,0.00062522915,0.000012602198,0.000357692],"genre_scores_gemma":[0.9798566,0.0020267677,0.0023823888,0.0014938398,0.009642637,0.000022980088,0.0004064142,0.00009446035,0.0040739286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8777224,0.0652373,0.052412905,0.0014373701,0.0017190542,0.0014710224],"domain_scores_gemma":[0.8676773,0.07471932,0.051720224,0.0011464638,0.0035132756,0.0012234643],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2379259,0.0006244589,0.01615328,0.00090216286,0.000362551,0.000018452893,0.0020297265,0.0022036375,0.00026254903],"category_scores_gemma":[0.23005936,0.0005129977,0.0012947557,0.00073913357,0.0002880241,0.00039361606,0.0007239442,0.01284866,0.000009452245],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094339513,0.0007439701,0.81886125,0.0007494262,0.0014149051,0.0002629294,0.0044094296,0.00018970712,9.851311e-7,0.00071931165,0.16898839,0.0027163124],"study_design_scores_gemma":[0.0033876158,0.0026777945,0.8785313,0.006631233,0.0008534795,0.00002661668,0.0348395,0.0012391605,4.3874903e-7,0.0061396733,0.06507492,0.0005982926],"about_ca_topic_score_codex":0.54140586,"about_ca_topic_score_gemma":0.95611024,"teacher_disagreement_score":0.41470438,"about_ca_system_score_codex":0.0024186478,"about_ca_system_score_gemma":0.07431159,"threshold_uncertainty_score":0.99973214},"labels":[],"label_agreement":null},{"id":"W4405437513","doi":"10.1016/j.jclinepi.2024.111644","title":"Identification of latent classes of randomized controlled trials based on integrity and reporting characteristics","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University; Nova Scotia Health Authority","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Identification (biology); Medicine; Internal medicine; Biology","score_opus":0.9290253707040388,"score_gpt":0.6990929105773075,"score_spread":0.2299324601267313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405437513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7824301,0.0033252968,0.19896123,0.010874132,0.0030046455,0.0011307952,0.000015575471,0.0000023140078,0.00025588198],"genre_scores_gemma":[0.9944049,0.00078236696,0.0038906923,0.00032618313,0.00030961708,0.000008633976,0.0000013031054,0.0000048179236,0.0002714703],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.13697185,0.4461146,0.4123522,0.000895152,0.0034054224,0.00026078845],"domain_scores_gemma":[0.012985877,0.7218599,0.26130134,0.00095786655,0.0027447902,0.0001502496],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.95044327,0.00018878865,0.06149614,0.0005052835,0.0000227848,0.00008180023,0.0005150251,0.00026280648,0.00063361344],"category_scores_gemma":[0.9918905,0.00006538752,0.015581102,0.00031743592,0.00031056616,0.000085640095,0.000035849847,0.0007136848,0.000018438674],"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":[0.1257237,0.0010003046,0.59886014,0.0013488397,0.014619921,0.00009094923,0.00024936354,0.0013218912,0.0014479734,0.05130367,0.028435651,0.17559762],"study_design_scores_gemma":[0.07017682,0.0007784077,0.17457846,0.0015281311,0.008484401,0.0000631866,0.0000879211,0.62457603,0.0000790207,0.116772726,0.0026798798,0.00019501276],"about_ca_topic_score_codex":0.0000031730551,"about_ca_topic_score_gemma":7.761575e-7,"teacher_disagreement_score":0.6232542,"about_ca_system_score_codex":0.000010550423,"about_ca_system_score_gemma":0.00029752334,"threshold_uncertainty_score":0.9942776},"labels":[],"label_agreement":null},{"id":"W4405557323","doi":"10.1016/j.jclinepi.2024.111646","title":"Generative artificial intelligence and academic writing: friend or foe?","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Generative grammar; Psychology; Artificial intelligence; Computer science","score_opus":0.7849452716882626,"score_gpt":0.6600597812574187,"score_spread":0.12488549043084385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405557323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76348186,0.008362232,0.081213824,0.1410104,0.0053973943,0.0002282622,0.0000033758713,0.000032557386,0.0002701204],"genre_scores_gemma":[0.96541953,0.008427442,0.013156199,0.005267012,0.0075415694,0.0000042817264,0.000002379315,0.000015784315,0.00016578623],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930442,0.0012212981,0.0049586096,0.00030071865,0.00015717112,0.0003179888],"domain_scores_gemma":[0.96507734,0.03295792,0.0009069737,0.00015920261,0.0003749098,0.0005236416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016553257,0.00013747743,0.0012956192,0.00017311783,0.00007032695,0.000014142402,0.000111166955,0.00050393195,0.0002587426],"category_scores_gemma":[0.0671819,0.00008663992,0.00028932258,0.00021660536,0.00041621435,0.00014560256,0.0000349533,0.0020480426,0.00006632753],"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":[0.0009345002,0.000098426906,0.03967281,0.00014556067,0.000111483474,0.00017188513,0.0007736811,0.000032174063,0.00011161215,0.03009723,0.0048581203,0.9229925],"study_design_scores_gemma":[0.00012811401,0.0100982,0.033324424,0.0023137485,0.00057011464,0.005021574,0.0070336456,0.04650642,0.003755227,0.83825845,0.05253464,0.00045546878],"about_ca_topic_score_codex":0.000028496162,"about_ca_topic_score_gemma":0.000014410008,"teacher_disagreement_score":0.922537,"about_ca_system_score_codex":0.000047301848,"about_ca_system_score_gemma":0.00084316125,"threshold_uncertainty_score":0.9406756},"labels":[],"label_agreement":null},{"id":"W4405596178","doi":"10.1016/j.jclinepi.2024.111648","title":"Meta-epidemiology and reporting characteristics of mapping reviews: a scoping review","year":2024,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Data-Driven Disease Surveillance","field":"Medicine","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 Medical Centre; Bruyère","funders":"National Office for Philosophy and Social Sciences","keywords":"Epidemiology; MEDLINE; Systematic review; Meta-analysis; Medicine; Data science; Environmental health; Computer science; Political science; Pathology","score_opus":0.8119543235295741,"score_gpt":0.6447508381367261,"score_spread":0.16720348539284802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405596178","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":[0.000007874815,0.9935285,0.00055540033,0.002206715,0.0016684923,0.0017878059,0.00009607185,0.00002691702,0.0001222402],"genre_scores_gemma":[0.000001254376,0.97823197,0.013496792,0.006012145,0.0018968445,0.00005950384,0.000113586175,0.00007700115,0.00011088661],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8886112,0.027370116,0.08182331,0.001119927,0.00030161766,0.00077382603],"domain_scores_gemma":[0.58420694,0.16200982,0.24768999,0.0028051294,0.001369185,0.0019189419],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.24342027,0.0008414085,0.082744494,0.000420118,0.000037539463,0.00000505785,0.00049054704,0.0010620985,0.00018623628],"category_scores_gemma":[0.7407177,0.00047038135,0.012495778,0.00048007304,0.0006901933,0.000090888025,0.00043404417,0.0037169994,0.00006175353],"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":[0.000024845533,0.000057316545,0.002103488,0.4296501,0.005149013,0.00034751513,0.0000026865632,3.1339287e-8,3.1110186e-8,0.00008069262,0.009418879,0.55316544],"study_design_scores_gemma":[0.00013677665,0.00024390407,0.00053820526,0.45870078,0.036250997,0.0027051433,8.369e-7,0.0000037241566,3.1504421e-9,0.00022869212,0.5010246,0.00016636388],"about_ca_topic_score_codex":0.000005261656,"about_ca_topic_score_gemma":0.0000013339447,"teacher_disagreement_score":0.5529991,"about_ca_system_score_codex":0.00007384746,"about_ca_system_score_gemma":0.0018099813,"threshold_uncertainty_score":0.9997748},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4405656537","doi":"10.1016/j.jclinepi.2024.111650","title":"Screening for diseases versus screening for health status","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Nutrition, Genetics, and Disease","field":"Biochemistry, Genetics and Molecular Biology","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":"Ottawa Public Health; Children's Hospital of Eastern Ontario; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Public health; MEDLINE; Environmental health; Pathology; Biology","score_opus":0.2844218433416407,"score_gpt":0.5196369390569742,"score_spread":0.23521509571533344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405656537","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":[0.0019251594,0.05261187,0.25630894,0.67530894,0.009339035,0.0010052623,0.0034381049,0.000024100886,0.000038624064],"genre_scores_gemma":[0.0014301561,0.012591888,0.096989736,0.8038038,0.079869464,0.0001039162,0.0041896785,0.00019362605,0.00082771754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921673,0.0016292129,0.0042251586,0.00077600055,0.00021114982,0.000991174],"domain_scores_gemma":[0.98527616,0.009965384,0.0030958056,0.00047128732,0.00051246217,0.0006789193],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005954532,0.00042912268,0.0025789996,0.00016583983,0.00013618656,0.00002864728,0.00046426922,0.0014337805,0.000017428118],"category_scores_gemma":[0.035868093,0.0003700031,0.0028707902,0.000059645758,0.00031055903,0.0000065328545,0.00012724541,0.001268622,0.0000027176964],"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":[0.0050093876,0.00008928276,0.0027281241,0.00069945346,0.00082583376,0.000020101297,0.000004012157,0.00010771366,0.000012083483,0.000045363024,0.9774883,0.012970363],"study_design_scores_gemma":[0.005098808,0.005447747,0.0016378693,0.00030675944,0.0005780268,0.000018767065,0.000021555366,0.00020810644,0.000012109274,0.0039842026,0.9823423,0.0003437306],"about_ca_topic_score_codex":0.00000977349,"about_ca_topic_score_gemma":0.000009390209,"teacher_disagreement_score":0.15931919,"about_ca_system_score_codex":0.000032826865,"about_ca_system_score_gemma":0.0010942423,"threshold_uncertainty_score":0.9998752},"labels":[],"label_agreement":null},{"id":"W4405747285","doi":"10.1016/j.jclinepi.2024.111653","title":"Confidence intervals of the relative risk and odds ratio can predict when the optimal information size in a meta-analysis is not met","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Impact; Toronto General Hospital","funders":"","keywords":"Confidence interval; Odds ratio; Meta-analysis; Relative risk; Statistics; Medicine; Mathematics; Internal medicine","score_opus":0.8610448185638434,"score_gpt":0.6283855817333882,"score_spread":0.2326592368304552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405747285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2667178,0.010672174,0.5989239,0.12058981,0.0011158999,0.0009894001,0.00019787492,0.0000033833444,0.0007897507],"genre_scores_gemma":[0.9877571,0.00051080383,0.0065196124,0.004368743,0.00008287476,0.000009612822,5.601375e-7,0.0000035096361,0.0007471957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8285387,0.12326062,0.04503147,0.0005266196,0.0023979717,0.00024457616],"domain_scores_gemma":[0.3945846,0.55511916,0.045380037,0.0025927713,0.0020816573,0.00024177594],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5688426,0.00022439467,0.011815296,0.00038076213,0.00007125255,0.0001728504,0.0016764492,0.00022119647,0.0031839772],"category_scores_gemma":[0.7032167,0.000066241955,0.011500638,0.0013793743,0.0004791481,0.0006037995,0.00022584853,0.0011673667,0.00004552882],"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":[0.0003245729,0.0001276143,0.47186434,0.00017111786,0.2774793,0.0000142379595,0.016911555,0.01496035,0.000006463652,0.10809268,0.08364982,0.026397951],"study_design_scores_gemma":[0.00047804936,0.0005557272,0.3904806,0.00008957831,0.17098467,0.000063041385,0.0014756962,0.20690776,0.000011134784,0.2027994,0.025967613,0.00018673358],"about_ca_topic_score_codex":0.00012674592,"about_ca_topic_score_gemma":0.00015001043,"teacher_disagreement_score":0.7210393,"about_ca_system_score_codex":0.00002065852,"about_ca_system_score_gemma":0.00022462921,"threshold_uncertainty_score":0.99839896},"labels":[],"label_agreement":null},{"id":"W4405801883","doi":"10.1016/j.jclinepi.2024.111657","title":"Guidance reconciliation and practice question prioritization for a World Health Organization's Ebola and Marburg Disease guideline","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Viral Infections and Outbreaks Research","field":"Medicine","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":"Centers for Disease Control and Prevention; World Health Organization","keywords":"Guideline; Prioritization; Medicine; Disease; Ebola virus; Family medicine; Management science; Pathology; Engineering","score_opus":0.23199104410188526,"score_gpt":0.5888598484609677,"score_spread":0.35686880435908247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405801883","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":[0.02560889,0.016866848,0.51293457,0.44252834,0.0012471708,0.00061323325,0.00001757703,0.000042380645,0.00014097748],"genre_scores_gemma":[0.7039643,0.045820933,0.19960567,0.0404038,0.0071481992,0.000022008004,0.00013810988,0.0000751348,0.0028218823],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995527,0.0016599842,0.0023097834,0.0002191721,0.000120549026,0.00016348537],"domain_scores_gemma":[0.9808577,0.016560128,0.0008996857,0.000101672966,0.0011457581,0.00043508515],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024899818,0.000086571505,0.00073133514,0.00019192384,0.00008113433,0.000023945158,0.000029827108,0.00010652355,0.00002632175],"category_scores_gemma":[0.18803953,0.00006473103,0.000105194435,0.00027383614,0.00010544304,0.00026523144,0.000024709303,0.00040132643,0.0000022061477],"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":[0.003043638,0.00035483495,0.2704317,0.0012075973,0.00032130774,0.0000666023,0.00009034339,0.00019986005,0.00017773792,0.042900767,0.144959,0.5362466],"study_design_scores_gemma":[0.0025403614,0.0026862808,0.37072557,0.0011584606,0.00034152326,0.0008726422,0.00005200668,0.04970836,0.00000860517,0.015105398,0.55665183,0.00014898213],"about_ca_topic_score_codex":0.000028201173,"about_ca_topic_score_gemma":0.000015120683,"teacher_disagreement_score":0.6783554,"about_ca_system_score_codex":0.000080581965,"about_ca_system_score_gemma":0.00068592676,"threshold_uncertainty_score":0.862983},"labels":[],"label_agreement":null},{"id":"W4406270013","doi":"10.1016/j.jclinepi.2025.111673","title":"What happened next? A survey of review clients evaluating impacts of rapid reviews","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"McMaster University Medical Centre; McMaster University","funders":"Public Health Agency of Canada; McMaster University","keywords":"Medicine; Psychology","score_opus":0.9601633841922903,"score_gpt":0.837028511803585,"score_spread":0.12313487238870535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406270013","genre_codex":"empirical","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":[0.6718093,0.14955473,0.0038817425,0.15482374,0.014200536,0.0043594963,0.00005876391,0.000015739335,0.0012959375],"genre_scores_gemma":[0.11026281,0.6420301,0.010322981,0.23672609,0.0003851584,0.000033289223,0.000008091795,0.00001555656,0.00021590493],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.79255533,0.16498981,0.04014648,0.0004823954,0.00069553143,0.0011304683],"domain_scores_gemma":[0.48399743,0.45794418,0.05090239,0.0012679665,0.004880399,0.0010076258],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42933396,0.0001843509,0.0057684495,0.0002569767,0.00015184248,0.000003284954,0.00074358727,0.00035300464,0.0008086189],"category_scores_gemma":[0.7860025,0.00012503583,0.0006350588,0.0009400255,0.00034923322,0.000516717,0.00021876044,0.0015200085,0.00006220207],"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":[0.00033605422,0.000102965445,0.7146994,0.0062876353,0.00007805851,9.136669e-7,0.0002803939,0.000004044446,0.000055248984,0.0005143766,0.121622376,0.15601856],"study_design_scores_gemma":[0.0019910182,0.0011297264,0.8983239,0.026496015,0.0001109565,0.0000035566864,0.00018285037,0.000116799565,0.000004828052,0.0018138967,0.06973931,0.00008715207],"about_ca_topic_score_codex":0.00041313644,"about_ca_topic_score_gemma":0.00024638727,"teacher_disagreement_score":0.5615465,"about_ca_system_score_codex":0.00010020328,"about_ca_system_score_gemma":0.0041937763,"threshold_uncertainty_score":0.885381},"labels":[],"label_agreement":null},{"id":"W4406614612","doi":"10.1016/j.jclinepi.2025.111680","title":"Data management and sharing","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"University of Ottawa","funders":"European Commission","keywords":"Interoperability; Data sharing; Mandate; Business; Intellectual property; Data governance; Data management; Knowledge sharing; Knowledge management; Quality (philosophy); Data quality; Public relations; Computer science; Marketing; Political science; Medicine; World Wide Web","score_opus":0.9217053330973967,"score_gpt":0.7670213984582112,"score_spread":0.1546839346391855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406614612","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":[0.38139048,0.01104691,0.041744776,0.46056437,0.0051334063,0.0006725538,0.000016830625,0.000041510884,0.09938914],"genre_scores_gemma":[0.6315631,0.0847801,0.18472299,0.07135704,0.0024594625,0.0000039150596,0.000013942188,0.000030404068,0.025069008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99295133,0.0012010254,0.004779464,0.0004558861,0.00031506718,0.00029722965],"domain_scores_gemma":[0.51310986,0.47839338,0.003025434,0.0032686335,0.0011001875,0.0011024959],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11935935,0.000088301,0.0017459233,0.00015682456,0.000039303148,0.0000068471854,0.0007727074,0.0004993197,0.00006955857],"category_scores_gemma":[0.44013822,0.000060303824,0.00023094808,0.00014080999,0.00054229307,0.00006911102,0.0014341763,0.0036476194,0.000013320148],"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":[0.0006619114,0.00018521215,0.7735525,0.00033949772,0.00048508172,0.00017476878,0.0000033820647,0.000003130949,0.0000019586282,0.15240785,0.017947394,0.054237306],"study_design_scores_gemma":[0.0017557245,0.00046504644,0.57636344,0.00066460477,0.0001829926,0.000065410495,0.000029145294,0.0010413901,9.71482e-7,0.3548356,0.06455612,0.00003953903],"about_ca_topic_score_codex":0.0000056410568,"about_ca_topic_score_gemma":0.000011987375,"teacher_disagreement_score":0.47984147,"about_ca_system_score_codex":0.000021724381,"about_ca_system_score_gemma":0.0002809678,"threshold_uncertainty_score":0.998651},"labels":[],"label_agreement":null},{"id":"W4406615490","doi":"10.1016/j.jclinepi.2025.111682","title":"You wait ages, and then two arrive at once: reporting guidelines should not be like buses","year":2025,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Medicine; Family medicine","score_opus":0.9095760156988876,"score_gpt":0.6551539843626637,"score_spread":0.2544220313362239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406615490","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":[0.013390355,0.008576209,0.0013685927,0.96719027,0.0074521583,0.00044464043,0.0003422056,0.000029539608,0.0012060584],"genre_scores_gemma":[0.0009015972,0.007616349,0.016324414,0.94865066,0.019545602,0.000021815047,0.000097689255,0.00006474824,0.006777131],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9137067,0.007353131,0.07641286,0.0013325283,0.00024202447,0.0009527341],"domain_scores_gemma":[0.7289852,0.13324924,0.13502109,0.0013286622,0.00088052254,0.00053531944],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2862096,0.0005863515,0.012193458,0.00063780154,0.00023996578,0.000050690505,0.0008903505,0.0025176557,0.00042409202],"category_scores_gemma":[0.6333837,0.0005599291,0.001648173,0.00014867084,0.0005117758,0.0002994634,0.00039786307,0.004758051,0.00016541044],"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":[0.000059993177,0.000028896146,0.12113685,0.0003951444,0.00046492385,0.000088376764,0.000098488366,0.00012673002,1.2220161e-7,0.0023469,0.87461066,0.0006428956],"study_design_scores_gemma":[0.0011070555,0.0002491968,0.021099588,0.0006156666,0.000106268635,0.00022107504,0.000062141655,0.0009853066,2.2642435e-7,0.024259208,0.95085776,0.00043652073],"about_ca_topic_score_codex":0.00083854905,"about_ca_topic_score_gemma":0.00010180844,"teacher_disagreement_score":0.34717405,"about_ca_system_score_codex":0.0005276116,"about_ca_system_score_gemma":0.0008285303,"threshold_uncertainty_score":0.9996852},"labels":[],"label_agreement":null},{"id":"W4406682337","doi":"10.1016/j.jclinepi.2025.111684","title":"Risk of bias assessment tools often addressed items not related to risk of bias and used numerical scores","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Risk assessment; Medicine; Statistics; Environmental health; Computer science; Psychology; Mathematics","score_opus":0.9081162111132932,"score_gpt":0.674554332401094,"score_spread":0.23356187871219924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406682337","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":[0.9296261,0.0011228133,0.058806825,0.008180558,0.0009787119,0.00047288075,0.00006141951,0.000002524571,0.0007481431],"genre_scores_gemma":[0.963888,0.0013751031,0.032281414,0.0016198794,0.000095284,0.0000059466606,0.0000017657335,0.000009204949,0.00072342006],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.77297014,0.15782742,0.06511028,0.0009812437,0.002696765,0.00041417094],"domain_scores_gemma":[0.46584973,0.47132754,0.05770699,0.0021572458,0.0024726745,0.0004858283],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5839194,0.00033021675,0.018128071,0.00074251037,0.00007707067,0.000071814444,0.0017187928,0.00047032672,0.0011115881],"category_scores_gemma":[0.893011,0.00014853754,0.0052888244,0.0014800581,0.0003896633,0.0001790041,0.0003067399,0.0012277586,0.00005970424],"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":[0.00019611741,0.00019001453,0.92695147,0.000040891402,0.0015785749,0.000006054544,0.000064989865,0.0018919723,0.0000380738,0.002092984,0.03266699,0.034281854],"study_design_scores_gemma":[0.0009956191,0.0008479637,0.9387552,0.00025389896,0.0012228197,0.00001235297,0.00013125935,0.014272212,0.000019779769,0.026501196,0.016867591,0.00012011958],"about_ca_topic_score_codex":0.00007299055,"about_ca_topic_score_gemma":0.000016278771,"teacher_disagreement_score":0.3135001,"about_ca_system_score_codex":0.000025498815,"about_ca_system_score_gemma":0.00038446722,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W4406757179","doi":"10.1016/j.jclinepi.2025.111686","title":"Scoping review of registration of observational studies finds inadequate registration policies, increased registration, and a debate converging toward proregistration","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Women's College Hospital","funders":"","keywords":"Observational study; Image registration; Trial registration; Pre-Registration; Medicine; Medical physics; Computer science; Artificial intelligence; Clinical trial; Medical education; Pathology","score_opus":0.9213214502791692,"score_gpt":0.6788924227953477,"score_spread":0.24242902748382156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406757179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39886168,0.16197215,0.26543868,0.1623233,0.0020705617,0.0038190747,0.000040040253,0.000012755733,0.0054617613],"genre_scores_gemma":[0.90861964,0.053012673,0.03082328,0.0059007495,0.00038888227,0.000033220764,0.000035832552,0.000011746629,0.0011739644],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.87391406,0.045729794,0.075975046,0.0009717149,0.003062788,0.0003466091],"domain_scores_gemma":[0.6206201,0.18762738,0.17102142,0.0033251198,0.017011847,0.00039416502],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38254556,0.00027080072,0.009255894,0.00037978575,0.000095415926,0.000055799643,0.00076303416,0.0002498587,0.000112331036],"category_scores_gemma":[0.72040284,0.00015528158,0.0016361543,0.001014674,0.000596203,0.0004675064,0.00007811314,0.00040116452,0.000003546917],"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":[0.00047620444,0.0003455667,0.5193073,0.037550583,0.0020269486,0.000013433422,0.000531258,0.0005189527,0.00026706004,0.2555906,0.15312794,0.030244142],"study_design_scores_gemma":[0.0028234047,0.0017332797,0.5731409,0.12728642,0.0025247796,0.00018162666,0.0013967325,0.011450957,0.00023396197,0.26848635,0.010163367,0.00057818904],"about_ca_topic_score_codex":0.00005664461,"about_ca_topic_score_gemma":0.00011501965,"teacher_disagreement_score":0.50975794,"about_ca_system_score_codex":0.000045367902,"about_ca_system_score_gemma":0.0013890141,"threshold_uncertainty_score":0.6357993},"labels":[],"label_agreement":null},{"id":"W4406788176","doi":"10.1016/j.jclinepi.2025.111687","title":"Pain and physical function are common core domains across 40 core outcome sets of musculoskeletal conditions: a systematic review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Western University","funders":"Caring for our Country; National Health and Medical Research Council; Medical Research Council; Australian Government","keywords":"Core (optical fiber); Outcome (game theory); Medicine; Musculoskeletal pain; Systematic review; Common core; Physical therapy; MEDLINE; Physical medicine and rehabilitation; Computer science; Mathematics; Biology","score_opus":0.6146223269836836,"score_gpt":0.6873810050712015,"score_spread":0.0727586780875179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406788176","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":[0.00030294395,0.9937473,0.00043281636,0.001864837,0.0007696125,0.0025254788,0.00015062782,0.000032653406,0.00017374846],"genre_scores_gemma":[0.00083279394,0.9966636,0.00032336917,0.0012872228,0.0005638132,0.00013972323,0.000028720022,0.000025562276,0.00013519709],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9430327,0.04278819,0.012172049,0.0005119976,0.0008190777,0.00067603035],"domain_scores_gemma":[0.80948406,0.1748671,0.013852061,0.0006132567,0.0007639887,0.00041952042],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14423467,0.00043469484,0.017641993,0.00024245931,0.0002652227,0.000018572868,0.0011426676,0.0012597151,0.00003986989],"category_scores_gemma":[0.3944064,0.00029020853,0.0039348155,0.00069318654,0.0021130953,0.00013585814,0.0003006713,0.0030427035,0.00001379281],"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":[0.000042498734,0.00027306972,0.0035634278,0.87160647,0.000636184,0.00006476557,0.00006192393,3.604669e-7,1.5414573e-8,0.0051219603,0.009260645,0.109368674],"study_design_scores_gemma":[0.00040203106,0.0011699778,0.001251398,0.8412952,0.004186544,0.000094108036,0.00048430488,0.000021276624,2.6146196e-9,0.020508911,0.13022609,0.00036019104],"about_ca_topic_score_codex":0.00006188048,"about_ca_topic_score_gemma":0.00012490022,"teacher_disagreement_score":0.25017172,"about_ca_system_score_codex":0.00019469287,"about_ca_system_score_gemma":0.00093482237,"threshold_uncertainty_score":0.999955},"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":"W4407252929","doi":"10.1016/j.jclinepi.2025.111712","title":"Scoping reviews and their role in identifying research priorities","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Queen's University","funders":"National Health and Medical Research Council","keywords":"Medicine; Data science; Computer science","score_opus":0.9766174710971349,"score_gpt":0.7756920353259925,"score_spread":0.2009254357711424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407252929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66641957,0.2511522,0.040225655,0.027109373,0.0028278762,0.0013704482,0.0000018561324,0.000002471547,0.010890555],"genre_scores_gemma":[0.9117554,0.047764573,0.026465088,0.006010534,0.0010864212,0.000028084418,4.6068612e-7,0.000012899816,0.0068765264],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4405106,0.44614714,0.10879492,0.0013326369,0.002423899,0.00079078355],"domain_scores_gemma":[0.16010343,0.7997097,0.033462875,0.0032035818,0.003077037,0.00044341825],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.878517,0.00016871131,0.013622031,0.0009552311,0.00010442729,0.00016434325,0.0015242763,0.00023716746,0.00054300105],"category_scores_gemma":[0.88315284,0.00006943837,0.0024327666,0.0011930763,0.0003336845,0.00022789615,0.00031853563,0.0013536921,0.00015697871],"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":[0.000028723402,0.000039479983,0.7735669,0.00022688511,0.00009676401,0.00000645946,0.00020601126,0.000013459088,0.000016102213,0.009180684,0.02969242,0.1869261],"study_design_scores_gemma":[0.00039760376,0.00013013087,0.34357053,0.0034827208,0.000046675425,0.000028904,0.0012233753,0.0017762559,0.0000027630451,0.46808523,0.18116869,0.000087116685],"about_ca_topic_score_codex":0.0000145876975,"about_ca_topic_score_gemma":0.0000890911,"teacher_disagreement_score":0.45890456,"about_ca_system_score_codex":0.00002613499,"about_ca_system_score_gemma":0.0002848515,"threshold_uncertainty_score":0.93117476},"labels":[],"label_agreement":null},{"id":"W4407272435","doi":"10.1016/j.jclinepi.2025.111717","title":"Inequities in glaucoma research: an analysis of Cochrane systematic reviews and randomized trials","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Glaucoma and retinal disorders","field":"Medicine","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 Alberta; McGill University; University of Calgary; University of Toronto; Bruyère; University of Ottawa; University of British Columbia","funders":"National Eye Institute; National Institutes of Health","keywords":"Randomized controlled trial; Systematic review; Medicine; Meta-analysis; Cochrane collaboration; Glaucoma; MEDLINE; Cochrane Library; Ophthalmology; Internal medicine; Political science","score_opus":0.69368860799137,"score_gpt":0.6622320326974845,"score_spread":0.03145657529388546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407272435","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":[0.0013069095,0.99300617,0.00018520799,0.0008640899,0.0005119318,0.003922635,0.000011343296,0.0000038010057,0.0001878969],"genre_scores_gemma":[0.000112932714,0.99787533,0.0009831975,0.0003391466,0.00032189302,0.000101641854,0.000030792617,0.000017868866,0.00021721386],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6682997,0.28322953,0.046801012,0.0005438998,0.00059470494,0.0005311845],"domain_scores_gemma":[0.17236738,0.7952518,0.029613676,0.0010367833,0.0011327231,0.0005976237],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.538492,0.00044651274,0.11548402,0.0033599515,0.000033401506,0.000008330475,0.00047335672,0.0012368677,0.000079744816],"category_scores_gemma":[0.8528481,0.00021493965,0.011239146,0.0016236822,0.0012070045,0.000058046877,0.00012614153,0.0027784545,0.0000034822701],"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":[0.019200966,0.0005530011,0.008461193,0.8406782,0.012010055,0.00013260319,0.00007334984,5.35257e-7,7.618954e-8,0.0025000346,0.0008495053,0.11554049],"study_design_scores_gemma":[0.05125068,0.0021657837,0.0037577657,0.7543394,0.13209485,0.0002747205,0.00019126447,0.00026851415,2.026278e-8,0.003249815,0.052125357,0.00028180022],"about_ca_topic_score_codex":0.00008331694,"about_ca_topic_score_gemma":0.000054496057,"teacher_disagreement_score":0.5120223,"about_ca_system_score_codex":0.0000648341,"about_ca_system_score_gemma":0.0011118534,"threshold_uncertainty_score":0.99952215},"labels":[],"label_agreement":null},{"id":"W4407358242","doi":"10.1016/j.jclinepi.2025.111719","title":"Cochrane reviews’ authorship has become more gender-diverse but remains geographically concentrated: a meta-research study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","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":"Bruyère; University of Ottawa; McMaster University; Impact; McMaster University Medical Centre","funders":"","keywords":"Meta-analysis; Cochrane collaboration; Systematic review; MEDLINE; Geography; Medicine; Library science; Genealogy; History; Political science; Cochrane Library; Computer science; Pathology","score_opus":0.970973840257367,"score_gpt":0.7733534434701769,"score_spread":0.19762039678719012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407358242","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":[0.89975995,0.029575579,0.008691516,0.054523576,0.0045428197,0.001319721,0.000040690386,0.000022593063,0.0015235797],"genre_scores_gemma":[0.97517556,0.0136333555,0.005104902,0.00378737,0.0006395314,0.000022848468,0.0000022670656,0.000015001685,0.0016191751],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7941562,0.14303437,0.034903094,0.003282779,0.02070614,0.0039174356],"domain_scores_gemma":[0.24770416,0.70541245,0.010111348,0.0035146768,0.02937608,0.0038812663],"candidate_categories":["metaresearch","bibliometrics","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.7270951,0.00038639654,0.007668905,0.040539324,0.00063967344,0.00073208875,0.0064635384,0.00085091905,0.0015287693],"category_scores_gemma":[0.8965565,0.00021066048,0.0035816042,0.1024492,0.002687672,0.00047569303,0.0015242028,0.005387556,0.0002381671],"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":[0.00045352243,0.0013955116,0.86129886,0.000028066046,0.0013962367,0.00032478385,0.00014894758,0.00011065877,0.000016919414,0.004304697,0.10819347,0.02232832],"study_design_scores_gemma":[0.0023766086,0.0027051773,0.79835075,0.00006458397,0.0006175942,0.000055137323,0.001728428,0.0014236823,0.0000049508453,0.097376116,0.0950361,0.0002608971],"about_ca_topic_score_codex":0.00015331706,"about_ca_topic_score_gemma":0.00007983102,"teacher_disagreement_score":0.5623781,"about_ca_system_score_codex":0.00013238858,"about_ca_system_score_gemma":0.0017683251,"threshold_uncertainty_score":0.999384},"labels":[],"label_agreement":null},{"id":"W4407512472","doi":"10.1016/j.jclinepi.2025.111723","title":"Author’s reply: “The importance of properly specifying your target trial emulation: commentary on Mésidor et al.”","year":2025,"lang":"fr","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire de cardiologie et de pneumologie de Québec; Centre hospitalier de l'Université Laval; Université Laval; Institut National de Santé Publique du Québec; Institut National de la Recherche Scientifique","funders":"","keywords":"Emulation; Psychology; Medicine; Computer science; Social psychology","score_opus":0.9104910697410754,"score_gpt":0.6719743925924444,"score_spread":0.238516677148631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407512472","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007172526,0.004567043,0.016358707,0.94892496,0.01913668,0.0017882565,0.00008158078,0.0000028871527,0.001967334],"genre_scores_gemma":[0.0017070867,0.001098267,0.029756099,0.93633837,0.010748237,0.000024246227,0.0000389496,0.000033623204,0.020255126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.4540314,0.37793538,0.1578205,0.0024568336,0.0067058923,0.0010499816],"domain_scores_gemma":[0.36996216,0.45527607,0.16383947,0.006691668,0.0036966077,0.0005340246],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.73585546,0.000979811,0.035438668,0.00067907077,0.00026929032,0.00018688977,0.005485209,0.0014034242,0.013295324],"category_scores_gemma":[0.71815073,0.00040844572,0.01938976,0.0011308031,0.0009685083,0.00031997275,0.00044185916,0.008232302,0.0004383114],"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":[0.0032819095,0.0003152001,0.09519111,0.00015413521,0.0019799722,0.00012388275,0.00008045605,0.0008618082,4.626889e-7,0.0016309606,0.88662475,0.009755337],"study_design_scores_gemma":[0.0055547575,0.0022889809,0.011872927,0.0010699611,0.0013554799,0.0000876183,0.00011939491,0.0032275931,5.3395553e-7,0.023228578,0.95089996,0.00029422887],"about_ca_topic_score_codex":0.00003972687,"about_ca_topic_score_gemma":0.00001891181,"teacher_disagreement_score":0.08406926,"about_ca_system_score_codex":0.00015650128,"about_ca_system_score_gemma":0.0014128007,"threshold_uncertainty_score":0.9998956},"labels":[],"label_agreement":null},{"id":"W4407598427","doi":"10.1016/j.jclinepi.2025.111726","title":"Review of the quality of reporting of statistical analysis plans for cluster randomized trials","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Ottawa Hospital","funders":"National Institute for Health and Care Research; Canadian Institutes of Health Research; Department of Health and Social Care; Medical Research Council; University of Birmingham; Race Forward","keywords":"Randomized controlled trial; Cluster (spacecraft); Quality (philosophy); Cluster randomised controlled trial; Medicine; Statistics; Computer science; Mathematics; Internal medicine; Physics","score_opus":0.978608925241826,"score_gpt":0.8016430446490015,"score_spread":0.17696588059282448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407598427","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007303327,0.76048034,0.23448572,0.0010295628,0.00089549896,0.0025369665,0.00036958687,4.1973715e-7,0.00019457251],"genre_scores_gemma":[0.000022174554,0.96643156,0.031859767,0.0009565811,0.00025885235,0.000046096797,0.000020514886,0.000009237764,0.00039524044],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.025194596,0.567293,0.40365294,0.00082201714,0.0027666234,0.00027082083],"domain_scores_gemma":[0.0016502829,0.57338643,0.4178532,0.0026968468,0.0042767916,0.00013644563],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.97527605,0.000545813,0.26922828,0.0008270584,0.00004117493,0.000018086132,0.003588829,0.0007925191,0.0016481094],"category_scores_gemma":[0.99783564,0.00016939535,0.13614915,0.0024487982,0.0007780856,0.00005319058,0.00030716808,0.0010719784,0.0000058252617],"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":[0.00284494,0.00022523146,0.005618716,0.27516198,0.038992196,0.0000013987421,0.000013006505,0.00003702178,3.8439865e-8,0.008829992,0.09443464,0.57384086],"study_design_scores_gemma":[0.010062728,0.00018191991,0.00083441916,0.12571216,0.18612777,0.000023312887,0.000020285934,0.00030088276,8.99658e-8,0.030131327,0.6463814,0.00022374844],"about_ca_topic_score_codex":0.00001681635,"about_ca_topic_score_gemma":0.0000150023725,"teacher_disagreement_score":0.5736171,"about_ca_system_score_codex":0.000025297051,"about_ca_system_score_gemma":0.0017511607,"threshold_uncertainty_score":0.99926454},"labels":[],"label_agreement":null},{"id":"W4407621336","doi":"10.1016/j.jclinepi.2025.111706","title":"Corrigendum to ʻMethodological systematic review recommends improvements to conduct and reporting when meta-analyzing interrupted time series studies’. Journal of Clinical Epidemiology 145 (2022) 55–69","year":2025,"lang":"en","type":"erratum","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Interrupted time series; Epidemiology; Meta-analysis; Medicine; Series (stratigraphy); Clinical epidemiology; Computer science; Internal medicine; Nursing; Biology","score_opus":0.9767739070445735,"score_gpt":0.739472509018612,"score_spread":0.2373013980259615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407621336","genre_codex":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008320399,0.5769925,0.09540661,0.17649393,0.14152353,0.0064103096,0.00013569181,0.0000214576,0.0021839147],"genre_scores_gemma":[0.00017282124,0.14098859,0.3907486,0.14451577,0.010171922,0.00023755629,0.00005082191,0.00015280469,0.31296113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.09531199,0.5410429,0.35429624,0.0034342539,0.0043753656,0.0015392619],"domain_scores_gemma":[0.01598079,0.51676536,0.44198057,0.006139913,0.016573241,0.0025601443],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.9452056,0.0018768607,0.1885241,0.002174618,0.00028440132,0.0001948635,0.007214739,0.0026942682,0.006154645],"category_scores_gemma":[0.9942858,0.0008041003,0.03909341,0.0020391427,0.0007945938,0.0004848856,0.002541103,0.009174761,0.00043963184],"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":[0.00030764774,0.00016203902,0.006759445,0.01886933,0.042811733,0.00019995202,0.0000920756,0.000012840877,0.000001421502,0.00021737292,0.92095774,0.009608371],"study_design_scores_gemma":[0.001207813,0.0074824695,0.0029175833,0.07543692,0.12281474,0.0026633362,0.00092270254,0.00045421714,7.094704e-7,0.05029682,0.7344826,0.0013201333],"about_ca_topic_score_codex":0.000013938333,"about_ca_topic_score_gemma":0.000026970467,"teacher_disagreement_score":0.43600392,"about_ca_system_score_codex":0.0002350389,"about_ca_system_score_gemma":0.0018003064,"threshold_uncertainty_score":0.99944097},"labels":[],"label_agreement":null},{"id":"W4407640883","doi":"10.1016/j.jclinepi.2025.111727","title":"The GIN-McMaster Guideline Development Checklist extension for engagement","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Ottawa; St. Joseph’s Healthcare Hamilton; Dalhousie University; Cochrane; Ottawa Public Health; Bruyère; Canadian Council on Animal Care; Alberta Health Services; Montfort Hospital; McMaster University; University of Calgary; Impact","funders":"Canadian Institutes of Health Research","keywords":"Checklist; Guideline; Medicine; Extension (predicate logic); Psychology; Computer science; Pathology","score_opus":0.61509462064241,"score_gpt":0.6433514798159039,"score_spread":0.028256859173493853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407640883","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":[0.08382179,0.0017339332,0.44273728,0.46226177,0.006684325,0.0012684152,0.0000040501054,0.000027646658,0.0014608104],"genre_scores_gemma":[0.20797989,0.0028453358,0.5989111,0.17724107,0.004850825,0.000058092224,0.00004703628,0.000048055597,0.0080185775],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98121226,0.0027299237,0.015007839,0.00034048109,0.00028790048,0.00042157646],"domain_scores_gemma":[0.81693065,0.1730512,0.006532078,0.000556223,0.0025572323,0.00037263127],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11111374,0.00018054762,0.0017861222,0.00010659324,0.00022800836,0.000012822778,0.0002731826,0.0002587468,0.0001242856],"category_scores_gemma":[0.46332106,0.0001021271,0.0007648616,0.00014034608,0.0002232387,0.00008987527,0.00014777631,0.0010877615,0.000019103021],"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":[0.0035583533,0.00032163496,0.035479188,0.000049685925,0.0004844294,0.000010075853,0.000019705829,0.00006421386,0.000096297445,0.0025780604,0.37285987,0.5844785],"study_design_scores_gemma":[0.004412968,0.0008292677,0.12387302,0.00013998657,0.00032934776,0.000043967957,0.00017854954,0.0017106354,0.000055645338,0.006137704,0.8622129,0.00007602789],"about_ca_topic_score_codex":0.000008361114,"about_ca_topic_score_gemma":0.000021941947,"teacher_disagreement_score":0.58440244,"about_ca_system_score_codex":0.000106980115,"about_ca_system_score_gemma":0.0011062011,"threshold_uncertainty_score":0.9152955},"labels":[],"label_agreement":null},{"id":"W4407909572","doi":"10.1016/j.jclinepi.2025.111731","title":"Patient- and public-driven health research: a model of co-leadership and partnership in research priority setting using a modified James Lind Alliance approach","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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":"Public Health Ontario; University of Calgary; University of Toronto; London Health Sciences Centre; Institute for Work & Health; Western University; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Alliance; General partnership; Public health; Medicine; Public relations; Political science; Nursing","score_opus":0.968645376141783,"score_gpt":0.720973259731389,"score_spread":0.247672116410394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407909572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9709327,0.0033177475,0.0018174459,0.021373041,0.00031577612,0.0012719545,0.0000143864545,0.0000055579812,0.00095136766],"genre_scores_gemma":[0.9716157,0.002413162,0.019079387,0.006475758,0.0002734086,0.000030998184,0.000009396809,0.000012648106,0.00008956842],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9286482,0.059991352,0.008136306,0.00059811655,0.0007232896,0.0019027409],"domain_scores_gemma":[0.93685234,0.05837517,0.00256193,0.000312042,0.0010609638,0.00083755533],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1541515,0.00016599007,0.0020406633,0.0005686332,0.00059714064,0.00000718574,0.00028179347,0.00061825826,0.000005865741],"category_scores_gemma":[0.056199357,0.00012872822,0.00013022986,0.00051439024,0.0009538971,0.00015646197,0.00030503684,0.0054669557,0.0000011030911],"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":[0.0013998771,0.0005538308,0.9622384,0.0041477457,0.000043785065,0.000002959321,0.004927523,0.00058304414,0.0000075339076,0.0076959627,0.005342646,0.013056709],"study_design_scores_gemma":[0.011535964,0.006379257,0.15119258,0.013998099,0.000034374025,0.000009418971,0.07867378,0.64457315,0.000009226356,0.08867189,0.0045283446,0.0003939087],"about_ca_topic_score_codex":0.0005132401,"about_ca_topic_score_gemma":0.00013853709,"teacher_disagreement_score":0.8110458,"about_ca_system_score_codex":0.00027646698,"about_ca_system_score_gemma":0.004284977,"threshold_uncertainty_score":0.9968275},"labels":[],"label_agreement":null},{"id":"W4407925758","doi":"10.1016/j.jclinepi.2025.111738","title":"Comparing Artificial Intelligence and manual methods in systematic review processes: protocol for a systematic review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"College of Medicine, Nursing and Health Sciences, National University of Ireland, Galway; China Scholarship Council; University of Galway","keywords":"Systematic review; Protocol (science); Stage (stratigraphy); Medicine; Computer science; MEDLINE; Alternative medicine; Biology; Pathology","score_opus":0.8548363439343531,"score_gpt":0.7538432043518545,"score_spread":0.10099313958249867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407925758","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":[3.181006e-8,0.75553036,0.01821035,0.0017033871,0.0003457091,0.22417355,0.0000022198976,0.000007781986,0.000026602427],"genre_scores_gemma":[1.1470124e-7,0.82991546,0.015215111,0.0037725074,0.00042587047,0.1505765,0.000007295884,0.000023755621,0.00006335864],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9455489,0.019906934,0.033199485,0.00058988336,0.0002605952,0.00049421773],"domain_scores_gemma":[0.69155616,0.27205923,0.031846944,0.0012579219,0.0025505018,0.0007292315],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.115294226,0.0005136527,0.032649104,0.000407117,0.00005993617,0.000013797362,0.00050466217,0.000755375,0.00002043845],"category_scores_gemma":[0.6162165,0.00030236354,0.0018950427,0.00076043466,0.00018793302,0.000092427144,0.00008521004,0.0019046718,0.000014573434],"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":[0.0000531634,0.00018915522,0.000026085281,0.9075741,0.0002305616,0.0000098399605,0.000020621295,2.9569432e-7,1.5164983e-9,0.00033643094,0.00047225598,0.09108748],"study_design_scores_gemma":[0.000038609414,0.00068949815,6.4024204e-7,0.97945476,0.008716349,0.0005208492,0.00006320408,0.00009349791,1.5158454e-7,0.003756005,0.006477315,0.00018913782],"about_ca_topic_score_codex":0.000012467489,"about_ca_topic_score_gemma":0.000015690044,"teacher_disagreement_score":0.50092226,"about_ca_system_score_codex":0.00019501949,"about_ca_system_score_gemma":0.003541425,"threshold_uncertainty_score":0.99994284},"labels":[],"label_agreement":null},{"id":"W4408160042","doi":"10.1016/j.jclinepi.2025.111752","title":"Definitions of validity terms for use in discussions of randomized controlled trials","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Public Health; Ottawa Hospital; University of Ottawa; Western University","funders":"","keywords":"Randomized controlled trial; External validity; Psychology; Medicine; Social psychology; Surgery","score_opus":0.9842806358083748,"score_gpt":0.7543407124057709,"score_spread":0.22993992340260383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408160042","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036310943,0.9092984,0.08032618,0.0011358364,0.002299569,0.0061010583,0.00032266224,8.645117e-7,0.00047910315],"genre_scores_gemma":[0.000100352234,0.9730701,0.025267899,0.00019231549,0.00035140422,0.0002629883,0.000016554863,0.000011365132,0.00072702905],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.04986847,0.65373236,0.2933335,0.0008134548,0.0019189563,0.0003332535],"domain_scores_gemma":[0.0037100317,0.7527042,0.23900361,0.001994162,0.0023657344,0.00022225847],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9445666,0.00060014287,0.3261659,0.0019384774,0.000044272107,0.000052880805,0.0025544302,0.0011127894,0.0012845631],"category_scores_gemma":[0.9958105,0.0001781064,0.14562596,0.0010850662,0.0005497272,0.00013622406,0.00017292867,0.001150267,0.000022412358],"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":[0.034134973,0.0014995623,0.0046713357,0.016548341,0.02426688,0.000012462583,0.0000385001,0.00010995651,1.05435866e-7,0.10592457,0.09667105,0.71612227],"study_design_scores_gemma":[0.12323645,0.00037540356,0.0002112642,0.028049702,0.051235974,0.000025471716,0.00003063659,0.00053079944,3.6253965e-8,0.3739046,0.42213786,0.00026182074],"about_ca_topic_score_codex":0.0000066265197,"about_ca_topic_score_gemma":0.000016513324,"teacher_disagreement_score":0.7158604,"about_ca_system_score_codex":0.000027180224,"about_ca_system_score_gemma":0.001247455,"threshold_uncertainty_score":0.9996284},"labels":[],"label_agreement":null},{"id":"W4408360842","doi":"10.1016/j.jclinepi.2025.111756","title":"A metaresearch study finds unclear impact of institutional conflicts of interest on conclusions of studies investigating volume–outcome relationships","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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; Impact","funders":"","keywords":"Outcome (game theory); Meta-analysis; Conflict of interest; Volume (thermodynamics); Medicine; Psychology; Political science; Economics; Internal medicine; Law","score_opus":0.983862817229963,"score_gpt":0.8101861272737629,"score_spread":0.17367668995620011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408360842","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":[0.097431056,0.89611834,0.00002864595,0.001812715,0.0023110555,0.0013407628,0.00049342896,0.000011384003,0.00045260717],"genre_scores_gemma":[0.23846674,0.75985295,0.00033022574,0.0005806691,0.00050908,0.000021616941,0.000022881168,0.000021187536,0.00019465483],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9353856,0.048177283,0.014983951,0.00047994242,0.0003706141,0.0006026124],"domain_scores_gemma":[0.77983767,0.2043791,0.01235044,0.0005025979,0.0019956022,0.0009345638],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06558824,0.00052458426,0.011616159,0.00076966075,0.00027587812,0.00000286171,0.0010451811,0.0024238373,0.00046887083],"category_scores_gemma":[0.2903091,0.0003525415,0.0029289816,0.0007998719,0.002906317,0.00010201156,0.00060947373,0.014373962,0.000013842148],"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":[0.0018769625,0.0047298456,0.68139726,0.030223716,0.016970186,0.00014395402,0.00072614977,0.0020999615,0.0000060950597,0.01567611,0.0049188966,0.24123083],"study_design_scores_gemma":[0.015729656,0.036594614,0.20123519,0.07952566,0.026228026,0.0003985497,0.0019153927,0.0014872908,0.000025853726,0.0134550305,0.6217827,0.0016220438],"about_ca_topic_score_codex":0.000054559536,"about_ca_topic_score_gemma":0.000021951482,"teacher_disagreement_score":0.6168638,"about_ca_system_score_codex":0.0002556341,"about_ca_system_score_gemma":0.004150047,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W4408514388","doi":"10.1016/j.jclinepi.2025.111759","title":"Methods resources for authors new to conducting systematic reviews with network meta-analysis: a scoping review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Faculty of Medicine and Health, University of Sydney; Universitetet i Oslo; Universiteit Stellenbosch; Universidad de Antioquia; University of Ioannina; University of Toronto; Government of the United Kingdom","keywords":"Meta-analysis; Systematic review; Medicine; Data science; MEDLINE; Computer science; Management science; Engineering; Political science; Pathology","score_opus":0.9882160922035522,"score_gpt":0.7936850226481404,"score_spread":0.19453106955541177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408514388","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4751813e-8,0.6094024,0.3766594,0.0023832412,0.0009995119,0.010386658,0.000009810584,0.00000413181,0.0001547891],"genre_scores_gemma":[1.3187089e-8,0.6113977,0.37543574,0.0054873168,0.001036052,0.0006432955,0.0000047436642,0.000032543718,0.005962611],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.1343587,0.6228235,0.23486818,0.0031572648,0.0036453546,0.0011470377],"domain_scores_gemma":[0.015480937,0.7126044,0.25811055,0.008069941,0.0041646613,0.0015694901],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.9373108,0.0018308896,0.32934743,0.0020952532,0.00025689916,0.00039818068,0.00798138,0.0011824488,0.0028596406],"category_scores_gemma":[0.96180284,0.0006267334,0.15326904,0.010324082,0.00017805072,0.0002474123,0.0005306525,0.002454447,0.00036687215],"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":[0.000012441326,0.000025993426,0.000015732858,0.5009924,0.16775532,0.00000607908,0.000018646688,0.00022668163,8.046421e-10,0.0003155353,0.13814247,0.19248867],"study_design_scores_gemma":[0.000056105575,0.00014783304,4.125634e-7,0.2626578,0.3490777,0.000053985594,0.00000990969,0.000029820878,9.1201285e-10,0.0008728734,0.3868796,0.00021396583],"about_ca_topic_score_codex":0.0000066995735,"about_ca_topic_score_gemma":0.000043482207,"teacher_disagreement_score":0.24873713,"about_ca_system_score_codex":0.00008610316,"about_ca_system_score_gemma":0.0023518677,"threshold_uncertainty_score":0.99984694},"labels":[],"label_agreement":null},{"id":"W4408515389","doi":"10.1016/j.jclinepi.2025.111760","title":"A scoping review identifies comments suggesting modifications to PRISMA-P 2015","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Michael's Hospital; Ottawa Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Systematic review; MEDLINE; Data science; Medicine; Management science; Psychology; Computer science; Biology; Engineering","score_opus":0.9702381121086805,"score_gpt":0.7769018401399942,"score_spread":0.1933362719686863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408515389","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":[0.0000011817158,0.9550012,0.02714895,0.011134477,0.0028821253,0.002674189,0.00002267927,0.0000038599383,0.0011313679],"genre_scores_gemma":[6.1897504e-7,0.97000945,0.016569594,0.0074000936,0.00073603174,0.0001011336,0.000011156177,0.000020164867,0.005151779],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.46180868,0.31698424,0.21392797,0.0021400668,0.0043548215,0.0007842204],"domain_scores_gemma":[0.06986639,0.72568184,0.18950856,0.007755823,0.0059904656,0.0011969282],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","insufficient_payload"],"category_scores_codex":[0.76445895,0.00074360374,0.076998234,0.0012033901,0.00017192756,0.00023698226,0.006398131,0.0007228029,0.0021780443],"category_scores_gemma":[0.950042,0.00033446995,0.022276238,0.0025733917,0.00016895775,0.00020737307,0.0007124024,0.0020304858,0.003040608],"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":[0.0000018204397,0.000049972947,0.0003183266,0.043273713,0.0005023289,0.000007267041,0.0000053390677,0.000009589689,2.3957352e-9,0.00028339648,0.43126738,0.52428085],"study_design_scores_gemma":[0.00006513167,0.000056282548,0.00006284568,0.34686795,0.0028133565,0.000064679305,0.0000066786156,0.000020945581,2.836173e-9,0.0020154424,0.64787096,0.00015569669],"about_ca_topic_score_codex":0.000004448041,"about_ca_topic_score_gemma":0.000008872397,"teacher_disagreement_score":0.52412516,"about_ca_system_score_codex":0.00007915849,"about_ca_system_score_gemma":0.0020659824,"threshold_uncertainty_score":0.9999107},"labels":[],"label_agreement":null},{"id":"W4408848235","doi":"10.1016/j.jclinepi.2025.111768","title":"GRADE notes 5: comparing a new intervention with an established treatment. Practical and methodological issues","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","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":"Intervention (counseling); Medicine; Medical physics; Psychology; Nursing","score_opus":0.7787526128967386,"score_gpt":0.6727471439429115,"score_spread":0.10600546895382712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408848235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8242744,0.0025836655,0.046555452,0.12569433,0.00029968607,0.00030180073,0.0000010155113,0.000024324758,0.00026531474],"genre_scores_gemma":[0.6539789,0.0065424843,0.33736742,0.0010925186,0.0007381905,0.0000053444414,0.0000033154688,0.000009368202,0.00026248064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895945,0.0071180146,0.0024447655,0.00032959293,0.00018577195,0.00032731507],"domain_scores_gemma":[0.9205728,0.077124566,0.0011270525,0.00026749173,0.00031513177,0.00059291604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01530048,0.00017553764,0.0029968177,0.00017237625,0.00006324245,0.000017483857,0.000102625614,0.00024374721,0.000053139414],"category_scores_gemma":[0.23881453,0.00009305253,0.0003808717,0.00014741902,0.0005296184,0.00018972569,0.000097660864,0.0009172071,0.0000019955412],"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":[0.005996484,0.00096292194,0.8740268,0.000049081445,0.0006535422,0.000100363126,0.000058559595,0.0000119052775,0.00007715639,0.001527796,0.0022455277,0.114289895],"study_design_scores_gemma":[0.0071746954,0.011864147,0.963111,0.00037652426,0.00036014966,0.00031239883,0.0001862439,0.001963464,0.00006115619,0.005781129,0.008731939,0.000077176395],"about_ca_topic_score_codex":0.00027375756,"about_ca_topic_score_gemma":0.00016437304,"teacher_disagreement_score":0.290812,"about_ca_system_score_codex":0.000056624034,"about_ca_system_score_gemma":0.00030205664,"threshold_uncertainty_score":0.76759726},"labels":[],"label_agreement":null},{"id":"W4408880194","doi":"10.1016/j.jclinepi.2025.111777","title":"Seven principles for integrating health equity considerations in the practice guideline enterprise","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":6,"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 Canada; Western University; Centre for Global Health Research; Impact; McMaster University; University of Ottawa; Cochrane; Bruyère","funders":"Public Health Agency of Canada","keywords":"Guideline; Equity (law); Business; Medicine; Management science; Actuarial science; Political science; Economics","score_opus":0.9007054767796374,"score_gpt":0.8221216698081616,"score_spread":0.07858380697147582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408880194","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","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":[0.004616652,0.00016034096,0.19607754,0.7921547,0.0018144057,0.0010744873,0.000020333377,0.00000887095,0.004072623],"genre_scores_gemma":[0.14654833,0.0002844813,0.17575908,0.67637,0.00082432583,0.0000814856,0.0000033144483,0.000006019575,0.00012292295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9203681,0.05650816,0.021414144,0.00035339475,0.0003385092,0.0010177279],"domain_scores_gemma":[0.29659116,0.6880786,0.0127380835,0.0004965897,0.001738599,0.0003570079],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30159262,0.00012157847,0.0015166544,0.00020384278,0.0006203783,0.000009242908,0.0004757879,0.00022783247,0.00010832106],"category_scores_gemma":[0.79992354,0.000073541356,0.00025390708,0.00030550407,0.00019323884,0.00024075781,0.00017606275,0.002039346,0.000011820964],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023604814,0.00016383374,0.12334651,0.00015303948,0.000045096305,0.0000051258216,0.00605967,0.00019874399,0.0000023179787,0.2134062,0.63773805,0.018645355],"study_design_scores_gemma":[0.002052954,0.0005342492,0.054309227,0.00034536954,0.000023831955,0.000023882778,0.009866409,0.0017651586,2.7695802e-7,0.06378077,0.8672356,0.00006228551],"about_ca_topic_score_codex":0.00034791147,"about_ca_topic_score_gemma":0.001558236,"teacher_disagreement_score":0.6315704,"about_ca_system_score_codex":0.00026826415,"about_ca_system_score_gemma":0.0082290815,"threshold_uncertainty_score":0.9973933},"labels":[],"label_agreement":null},{"id":"W4409246914","doi":"10.1016/j.jclinepi.2025.111780","title":"Author's reply: letter to the editor regarding the paper “How the PICAR framework can benefit guideline systematic reviews: a call for greater attention”","year":2025,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"","keywords":"Guideline; Systematic review; Medicine; Psychology; Library science; Computer science; MEDLINE; Political science; Law; Pathology","score_opus":0.1943487247173759,"score_gpt":0.4583664304830066,"score_spread":0.2640177057656307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409246914","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":[0.0000580916,0.0037727891,0.008241048,0.9660637,0.018201571,0.0034420034,0.000024497951,0.00001937799,0.00017697157],"genre_scores_gemma":[0.00006977018,0.00094621937,0.0035259647,0.8070091,0.16145526,0.0003147854,0.000023903733,0.00005416225,0.02660085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9720674,0.01501613,0.010463519,0.0007338133,0.00082570466,0.00089342246],"domain_scores_gemma":[0.73131454,0.2570562,0.007083356,0.002762893,0.001394971,0.00038802205],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.08737992,0.000673802,0.011061552,0.00016000148,0.0003283233,0.00007539226,0.0013418732,0.0020556431,0.000068415575],"category_scores_gemma":[0.34802476,0.0002282894,0.009382247,0.00028062533,0.00039935877,0.000056103847,0.00020125754,0.007689393,0.00003793604],"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":[0.00027983094,0.000020713287,0.0026120266,0.0026897907,0.0014485109,0.00018813135,0.00006027814,0.000014116844,2.895567e-7,0.0005700768,0.99146175,0.0006544837],"study_design_scores_gemma":[0.00069463335,0.00044044154,0.0019681752,0.010072772,0.0041956753,0.0006253856,0.000041924814,0.000045345958,9.61314e-8,0.00096267246,0.9807195,0.00023336436],"about_ca_topic_score_codex":0.000027627066,"about_ca_topic_score_gemma":0.000010425939,"teacher_disagreement_score":0.26064485,"about_ca_system_score_codex":0.0001480276,"about_ca_system_score_gemma":0.00029530682,"threshold_uncertainty_score":0.9992399},"labels":[],"label_agreement":null},{"id":"W4409284031","doi":"10.1016/j.jclinepi.2025.111783","title":"Gaps in completeness of reporting and methodological quality: a metaresearch study of 139 network meta-analyses published in January 2023 using PRISMA-NMA and AMSTAR-2","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Michael's Hospital","funders":"Ministero della Salute","keywords":"Meta-analysis; Completeness (order theory); Medicine; Systematic review; Family medicine; Psychology; MEDLINE; Mathematics; Internal medicine; Political science","score_opus":0.9937202421116609,"score_gpt":0.8081032306384291,"score_spread":0.18561701147323173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409284031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96698356,0.010577651,0.01900023,0.0024716333,0.00023708443,0.0005605083,0.0000028565548,7.419371e-7,0.00016572514],"genre_scores_gemma":[0.9141159,0.00031804657,0.0849761,0.0004213072,0.000066178334,0.000007840312,7.13689e-7,0.0000048882844,0.00008903064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.13168801,0.65160596,0.20938408,0.0021194078,0.004333452,0.00086906477],"domain_scores_gemma":[0.110962585,0.7439244,0.13811067,0.0028541484,0.0037456444,0.00040257283],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.88889766,0.00030918894,0.036729213,0.0012976317,0.000058972833,0.00008451094,0.0012627599,0.00034287438,0.0004923754],"category_scores_gemma":[0.9179108,0.00013561244,0.0037455999,0.002917001,0.00046918824,0.00027144246,0.00067139964,0.0012718459,9.3048567e-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":[0.00023208556,0.00036602252,0.9855282,0.00013276911,0.004205185,0.000047932193,0.00013246156,0.0043034954,0.000040641662,0.00063585537,0.001004864,0.003370546],"study_design_scores_gemma":[0.00088670116,0.00044409125,0.9087749,0.00011088466,0.00301787,0.000031290343,0.0021004362,0.012117526,0.000002587904,0.07217394,0.00023967362,0.00010008846],"about_ca_topic_score_codex":0.0007428061,"about_ca_topic_score_gemma":0.0006935271,"teacher_disagreement_score":0.09231841,"about_ca_system_score_codex":0.000022887643,"about_ca_system_score_gemma":0.0002690957,"threshold_uncertainty_score":0.97757155},"labels":[],"label_agreement":null},{"id":"W4409539156","doi":"10.1016/j.jclinepi.2025.111792","title":"Improving the completeness and transparency of protocols and reports of randomized trials: SPIRIT 2025 and CONSORT 2025","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Women's College Hospital; University of Toronto; University of Ottawa","funders":"","keywords":"Consolidated Standards of Reporting Trials; Transparency (behavior); Completeness (order theory); Randomized controlled trial; Medicine; Computer science; Mathematics; Surgery; Computer security","score_opus":0.935760884183555,"score_gpt":0.7066085383977609,"score_spread":0.22915234578579402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409539156","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.707685,0.044498082,0.18897882,0.03186829,0.0014219284,0.024067167,0.000025734385,0.0000028536504,0.0014521091],"genre_scores_gemma":[0.9746204,0.0032982558,0.019255562,0.0014673243,0.00020955557,0.0003785526,7.288861e-7,0.0000074432783,0.00076214684],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5225615,0.3010332,0.17246367,0.001316987,0.0022068678,0.00041776165],"domain_scores_gemma":[0.22376646,0.68339294,0.088634565,0.0016850955,0.0022889168,0.00023203343],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8032475,0.00020855918,0.028934812,0.00026543994,0.000066983106,0.000052448675,0.0005652704,0.00022860334,0.00030599357],"category_scores_gemma":[0.8705561,0.00007468796,0.0034656355,0.00034520045,0.0011821003,0.00009648327,0.000118817494,0.00043295935,8.1795287e-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":[0.0073620486,0.00014659578,0.81929594,0.0007756429,0.002286823,0.000018495066,0.00013784565,0.000030317644,0.00011193506,0.0140909515,0.010023286,0.1457201],"study_design_scores_gemma":[0.06029514,0.00094897515,0.54375565,0.0018611316,0.006286699,0.00034850865,0.0005320508,0.00887447,0.000046211306,0.33577734,0.040987704,0.0002861002],"about_ca_topic_score_codex":0.000037193295,"about_ca_topic_score_gemma":0.0000127216545,"teacher_disagreement_score":0.3823597,"about_ca_system_score_codex":0.000003844537,"about_ca_system_score_gemma":0.0002706118,"threshold_uncertainty_score":0.9854817},"labels":[],"label_agreement":null},{"id":"W4409657097","doi":"10.1016/j.jclinepi.2025.111800","title":"Use of the pragmatic-explanatory continuum indicator summary tool in low- and middle-income country settings: systematic review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Low and middle income countries; Systematic review; Medicine; Low income; MEDLINE; Econometrics; Economics; Demographic economics; Developing country; Political science; Economic growth","score_opus":0.7382905424749643,"score_gpt":0.6045994632068149,"score_spread":0.13369107926814938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409657097","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":[0.00008084526,0.9934707,0.00017923677,0.001027196,0.0015414583,0.003486827,0.00008871321,0.0000018126123,0.00012318777],"genre_scores_gemma":[0.000007946284,0.9921471,0.0015214977,0.004591782,0.0001791744,0.000070400856,0.0000066251355,0.000020557012,0.0014549491],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.45808572,0.35554117,0.18035142,0.0014059688,0.0039987974,0.00061694323],"domain_scores_gemma":[0.14504488,0.62854904,0.21843286,0.0059475964,0.0016801239,0.00034551503],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6870168,0.000797654,0.08627428,0.0009025858,0.00006988164,0.00012084956,0.004657849,0.0010841643,0.00041966166],"category_scores_gemma":[0.9176168,0.00028791107,0.013634109,0.0018122663,0.00050482474,0.00027223505,0.0006347642,0.0025666652,0.00013019559],"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":[0.000006649066,0.000081494116,0.007581537,0.9309327,0.0012719065,0.000022703332,0.000014552949,7.2130797e-7,2.7097462e-9,0.00067070674,0.048330873,0.011086166],"study_design_scores_gemma":[0.00015192978,0.00004166237,0.00065675203,0.70018977,0.006525143,0.0001525198,0.000019676967,0.000033552333,3.5320888e-9,0.0011656516,0.2908895,0.00017383843],"about_ca_topic_score_codex":0.000004074253,"about_ca_topic_score_gemma":0.000018398465,"teacher_disagreement_score":0.31304082,"about_ca_system_score_codex":0.00008602929,"about_ca_system_score_gemma":0.0015495567,"threshold_uncertainty_score":0.9999573},"labels":[],"label_agreement":null},{"id":"W4409859887","doi":"10.1016/j.jclinepi.2025.111810","title":"Multistate modeling in long-term follow-up studies, with application to a multiple sclerosis cohort","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Multiple Sclerosis Research Studies","field":"Medicine","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 British Columbia; Centre for Advancing Health Outcomes","funders":"Canadian Institutes of Health Research","keywords":"Term (time); Multiple sclerosis; Medicine; Cohort; Cohort study; Internal medicine; Immunology; Physics","score_opus":0.42401904445180977,"score_gpt":0.530299770849386,"score_spread":0.10628072639757619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409859887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89042073,0.00167604,0.09342547,0.012943011,0.00044647697,0.0009894063,0.000004624729,0.000018275163,0.00007596308],"genre_scores_gemma":[0.9709533,0.0095648235,0.015707152,0.003157913,0.00031748685,0.00010871362,0.000005180275,0.000020019905,0.00016544422],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99247277,0.0016178443,0.004420228,0.0005370296,0.00036662753,0.0005855191],"domain_scores_gemma":[0.9759893,0.02073122,0.0011065918,0.0005047685,0.0012124041,0.00045575033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01801147,0.00024820896,0.003506213,0.00044599135,0.00008475583,0.0000067285227,0.0002861361,0.00023647392,0.0000071191525],"category_scores_gemma":[0.118325435,0.00016429576,0.00043081367,0.0005325964,0.0002996414,0.00009229355,0.00021432631,0.0012047713,0.000013525129],"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":[0.0044384683,0.00032926234,0.9280492,0.00015854894,0.000922144,0.000033854565,0.00010507861,0.0044309543,0.00029344248,0.000038396603,0.0011889215,0.060011715],"study_design_scores_gemma":[0.008309669,0.00095663115,0.94928133,0.001557278,0.00017377948,0.00001605386,0.0001335222,0.038972035,0.000025873082,0.000180395,0.00026834957,0.00012507729],"about_ca_topic_score_codex":0.00017043194,"about_ca_topic_score_gemma":0.0010261012,"teacher_disagreement_score":0.10031397,"about_ca_system_score_codex":0.00025948798,"about_ca_system_score_gemma":0.00034537868,"threshold_uncertainty_score":0.88910127},"labels":[],"label_agreement":null},{"id":"W4410091066","doi":"10.1016/j.jclinepi.2025.111813","title":"Prospective registration was associated with a reduced risk of bias for randomized controlled trials: a meta-research study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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 Alberta","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Randomized controlled trial; Meta-analysis; Medicine; MEDLINE; Trial registration; Internal medicine; Political science","score_opus":0.9039292352733046,"score_gpt":0.7442704780675578,"score_spread":0.15965875720574685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410091066","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90276057,0.0027346718,0.015300923,0.05633279,0.0011152362,0.019700626,0.000028605176,0.000024335795,0.0020022339],"genre_scores_gemma":[0.9849293,0.0026728143,0.0076594213,0.000589553,0.0006232969,0.0007232671,0.0000038721937,0.000023596995,0.002774859],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.6662949,0.28882617,0.0398494,0.0010746728,0.0029540923,0.0010007836],"domain_scores_gemma":[0.0049459,0.9615558,0.01832703,0.00070184993,0.014087454,0.00038200646],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86152965,0.00029217004,0.03431412,0.0006824034,0.00014704754,0.000017456068,0.000493902,0.0012046888,0.00007234538],"category_scores_gemma":[0.9962404,0.00013194191,0.008045906,0.0007340258,0.0022779813,0.00007279723,0.00010208892,0.0076571037,0.0000015786553],"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":[0.7978963,0.004086954,0.10165634,0.000116797804,0.07371713,0.000026865619,0.0001413103,0.00008104034,0.000027680744,0.019876016,0.0017228184,0.0006507133],"study_design_scores_gemma":[0.6116435,0.017682435,0.041872874,0.00068249885,0.026749786,0.000007816455,0.00052279094,0.0011567237,0.00004813163,0.29949838,0.000044747772,0.000090321766],"about_ca_topic_score_codex":0.00012172687,"about_ca_topic_score_gemma":0.00028420854,"teacher_disagreement_score":0.6727296,"about_ca_system_score_codex":0.00015702927,"about_ca_system_score_gemma":0.0050987564,"threshold_uncertainty_score":0.99463224},"labels":[],"label_agreement":null},{"id":"W4410197347","doi":"10.1016/j.jclinepi.2025.111818","title":"Do peer reviewers comment on reporting items as instructed by the journal? A secondary analysis of two randomized trials","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; McMaster University; Ottawa Public Health; University of Alberta","funders":"Janggen-Pöhn-Stiftung; Magyar Tudományos Akadémia; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Peer review; Alternative medicine; MEDLINE; Medicine; Psychology; Family medicine; Political science","score_opus":0.905153981802102,"score_gpt":0.715132319149437,"score_spread":0.19002166265266507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410197347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47970608,0.042425267,0.11818975,0.32939807,0.009445387,0.0026385076,0.000041104784,0.0000052613436,0.01815058],"genre_scores_gemma":[0.81442744,0.020966616,0.019457696,0.13216123,0.0016217267,0.0000355427,0.000019004865,0.00003415242,0.011276583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.09096726,0.63898844,0.2630357,0.0008554165,0.005668437,0.00048472802],"domain_scores_gemma":[0.008216149,0.6791502,0.30283287,0.0028094326,0.00663307,0.00035823925],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.96696913,0.0003861394,0.060860652,0.0012963497,0.00020861143,0.00018450353,0.0027497213,0.00031310125,0.006369766],"category_scores_gemma":[0.9885736,0.0001271911,0.031502526,0.0030065393,0.00052163814,0.00015268457,0.0001717127,0.0020462365,0.000059957583],"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":[0.0052487156,0.00013706755,0.048407353,0.000032857097,0.020667247,0.000012714416,0.000115824056,0.00095316686,0.000006217584,0.0033779212,0.8003256,0.120715365],"study_design_scores_gemma":[0.041320927,0.00048988865,0.0121070715,0.0006485003,0.03916027,0.00020708183,0.0008654147,0.0067343507,0.0000073317105,0.11443007,0.783787,0.00024209303],"about_ca_topic_score_codex":0.00005045148,"about_ca_topic_score_gemma":0.000010342947,"teacher_disagreement_score":0.33472136,"about_ca_system_score_codex":0.000052259355,"about_ca_system_score_gemma":0.0005703357,"threshold_uncertainty_score":0.99453855},"labels":[],"label_agreement":null},{"id":"W4410218088","doi":"10.1016/j.jclinepi.2025.111822","title":"Metaresearch on patient-reported outcomes in trial protocols and results publications suggested large outcome reporting bias","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Impact; McMaster University","funders":"Canadian Institutes of Health Research; Bundesamt für Gesundheit; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Magyar Tudományos Akadémia; Janggen-Pöhn-Stiftung; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Outcome (game theory); Meta-analysis; Medicine; MEDLINE; Reporting bias; Publication bias; Clinical trial; Protocol (science); Alternative medicine; Internal medicine; Pathology; Biology","score_opus":0.6134528869978573,"score_gpt":0.6242846014544053,"score_spread":0.01083171445654807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410218088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93287873,0.00009390324,0.00014151678,0.05896307,0.0010179207,0.0048821378,0.000012593436,0.000020217458,0.0019899225],"genre_scores_gemma":[0.99148405,0.00006256425,0.00078889605,0.005623337,0.00029751746,0.0005960163,0.000014492056,0.000012736832,0.0011204224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9774086,0.003730976,0.017625092,0.00042324065,0.00037836417,0.00043372042],"domain_scores_gemma":[0.9383283,0.045369614,0.0140395705,0.00079439365,0.0010120363,0.00045608333],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0684102,0.0001658585,0.003255453,0.0005639883,0.000057081983,0.000014800392,0.00015701907,0.0003912937,0.000032685377],"category_scores_gemma":[0.64597523,0.00010814738,0.0006830522,0.000500408,0.00014404331,0.00008234781,0.00009878874,0.0017283177,0.0000022715478],"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":[0.03133759,0.00074077863,0.9528908,0.00005073018,0.00022726072,0.00012239549,0.000057712932,0.000003987008,0.0000024554954,0.0010436719,0.00239128,0.011131313],"study_design_scores_gemma":[0.041913833,0.002873506,0.9154204,0.00028063616,0.00009274637,0.000053858697,0.00011640198,0.000064007974,0.000006637582,0.0016780962,0.037421208,0.000078632096],"about_ca_topic_score_codex":0.00017940335,"about_ca_topic_score_gemma":0.0005024862,"teacher_disagreement_score":0.577565,"about_ca_system_score_codex":0.0000820265,"about_ca_system_score_gemma":0.00074153236,"threshold_uncertainty_score":0.95926774},"labels":[],"label_agreement":null},{"id":"W4410218096","doi":"10.1016/j.jclinepi.2025.111825","title":"Randomization procedures in parallel-arm cluster randomized trials in low- and middle-income countries: a review of 300 trials published between 2017-2022","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Public Health Ontario; St. Joseph’s Healthcare Hamilton; Western University; Ottawa Hospital; Canada Research Chairs; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Randomization; Low and middle income countries; Cluster (spacecraft); Cluster randomised controlled trial; Randomized controlled trial; Medicine; Clinical trial; Computer science; Internal medicine; Developing country; Economics; Economic growth","score_opus":0.7321278997452273,"score_gpt":0.6843300543923413,"score_spread":0.047797845352886004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410218096","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039961855,0.9597702,0.0008072629,0.02748774,0.0012150118,0.010324399,0.000067722875,0.000008779813,0.0002789181],"genre_scores_gemma":[0.000026505693,0.9889159,0.0032962533,0.0049619987,0.0019018496,0.000375456,0.00007431364,0.000050181934,0.00039754654],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.2291851,0.5632636,0.19995154,0.0024994635,0.003251214,0.0018490407],"domain_scores_gemma":[0.0029179815,0.9467989,0.046211176,0.0010110522,0.0023720697,0.00068877457],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.86241525,0.0007942645,0.11831596,0.0019414303,0.00003949259,0.00003142172,0.0011318616,0.004865721,0.00047817203],"category_scores_gemma":[0.9952347,0.00044422242,0.010553245,0.0011983484,0.0016331782,0.00021728438,0.00045854575,0.01198852,0.0000074520544],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17491311,0.0005304395,0.0039741024,0.76627356,0.003113729,0.00010268525,0.000025870737,0.0000070542733,3.9061008e-9,0.0015632231,0.0039017606,0.045594443],"study_design_scores_gemma":[0.2541074,0.00073583284,0.00024627696,0.67302513,0.0063911104,0.000058736612,0.000005401889,0.000019601037,2.8810685e-8,0.026811223,0.038360022,0.00023925278],"about_ca_topic_score_codex":0.000037722668,"about_ca_topic_score_gemma":0.00007021786,"teacher_disagreement_score":0.38353533,"about_ca_system_score_codex":0.0002452268,"about_ca_system_score_gemma":0.013162523,"threshold_uncertainty_score":0.999801},"labels":[],"label_agreement":null},{"id":"W4410218125","doi":"10.1016/j.jclinepi.2025.111823","title":"Adapting World Health Organization COVID-19 living guidelines balancing methodological rigor with efficiency and flexibility: a case study from Argentina","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"World Health Organization","keywords":"Rigour; Coronavirus disease 2019 (COVID-19); Flexibility (engineering); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); MEDLINE; Medicine; Virology; Political science; Statistics; Outbreak; Mathematics","score_opus":0.9415733070006505,"score_gpt":0.8003418050861025,"score_spread":0.14123150191454792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410218125","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":[0.61698455,0.00015642782,0.2994314,0.08190604,0.0008131977,0.00063298125,0.000008312563,0.000032743734,0.00003435605],"genre_scores_gemma":[0.6570368,0.00016003284,0.17785859,0.16407503,0.0007352874,0.000014204221,0.0000014058246,0.000013188906,0.000105513245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9279182,0.058988377,0.011266239,0.0006614839,0.00033221897,0.00083350134],"domain_scores_gemma":[0.45782676,0.52701753,0.011111229,0.0005994976,0.0017876856,0.0016572832],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21867938,0.00021540932,0.0026127796,0.0003698625,0.0012153358,0.000012123363,0.0003225077,0.00022567785,0.00030983577],"category_scores_gemma":[0.73483735,0.00014049404,0.00011569746,0.0012005154,0.00027950748,0.00016504368,0.00031853083,0.0017180431,0.000007268222],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011391315,0.00013262688,0.98452115,0.00011675426,0.00005107691,0.00011965477,0.0035363273,0.0003613622,0.0000032305707,0.00068700896,0.0053212256,0.0050356793],"study_design_scores_gemma":[0.0050559756,0.0021875633,0.89551306,0.0010116849,0.00017030998,0.0005301024,0.055430587,0.0076606805,6.2061395e-7,0.0049353126,0.027192023,0.00031208227],"about_ca_topic_score_codex":0.004113751,"about_ca_topic_score_gemma":0.005612265,"teacher_disagreement_score":0.516158,"about_ca_system_score_codex":0.00034197644,"about_ca_system_score_gemma":0.0057401443,"threshold_uncertainty_score":0.9998964},"labels":[],"label_agreement":null},{"id":"W4410221436","doi":"10.1016/j.jclinepi.2025.111824","title":"Assessing the feasibility and impact of clinical trial trustworthiness checks via an application to Cochrane Reviews: Stage 2 of the INSPECT-SR project","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Dalhousie University","funders":"Department of Health and Social Care; National Institute for Health and Care Research","keywords":"Trustworthiness; Stage (stratigraphy); Systematic review; Meta-analysis; Medicine; Cochrane collaboration; Clinical trial; Medical physics; MEDLINE; Computer science; Internal medicine; Cochrane Library; Political science","score_opus":0.9158969746153991,"score_gpt":0.7556013264309793,"score_spread":0.16029564818441977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410221436","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":[0.9219749,0.0029713605,0.06788219,0.0037545906,0.0010171414,0.002066353,0.000008276647,0.000001354089,0.00032384144],"genre_scores_gemma":[0.9910959,0.0013437856,0.005462907,0.0012477229,0.0005548294,0.000017358865,9.238558e-7,0.0000062630565,0.00027030156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.53555745,0.3328193,0.12625456,0.0016919744,0.0031549141,0.00052177266],"domain_scores_gemma":[0.40897226,0.43354204,0.14140865,0.009859782,0.0055850246,0.00063222775],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.74537927,0.0002678568,0.015647907,0.0002027796,0.00011159667,0.000080886704,0.0024885212,0.00036278155,0.00024435704],"category_scores_gemma":[0.78347963,0.00008331559,0.0072854585,0.0014485256,0.0006356728,0.0002539414,0.00026916215,0.0010968863,0.000008400782],"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":[0.0017005799,0.00039491063,0.8523735,0.0001139883,0.00033448587,4.998773e-7,0.000065968925,0.0001707803,0.000018219378,0.0007010484,0.005087663,0.13903837],"study_design_scores_gemma":[0.0035457402,0.0011457469,0.96616715,0.00021429229,0.0004891053,0.000009872986,0.00012658023,0.0066343616,0.0000019923534,0.011543082,0.010039861,0.00008219961],"about_ca_topic_score_codex":0.00006426389,"about_ca_topic_score_gemma":0.0000756529,"teacher_disagreement_score":0.13895616,"about_ca_system_score_codex":0.00003449424,"about_ca_system_score_gemma":0.0008270704,"threshold_uncertainty_score":0.99896586},"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":"W4410292541","doi":"10.1016/j.jclinepi.2025.111831","title":"Permissibility and necessity in the ethical justification of randomized controlled trials: the four quadrants framework and the case of endovascular thrombectomy trials for acute ischemic stroke","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Acute Ischemic Stroke Management","field":"Medicine","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; Ottawa Hospital","funders":"Department of Medicine, Ottawa Hospital; Canadian Institutes of Health Research; University of Ottawa; Heart and Stroke Foundation of Canada","keywords":"Medicine; Stroke (engine); Randomized controlled trial; Ischemic stroke; Emergency medicine; Surgery; Internal medicine; Ischemia","score_opus":0.2887063449012381,"score_gpt":0.5495334220480269,"score_spread":0.2608270771467888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410292541","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":[0.80048203,0.007839829,0.05774616,0.12786,0.0005025541,0.0053082346,0.000021204409,0.0000037593927,0.0002362061],"genre_scores_gemma":[0.98267746,0.0055945516,0.006486703,0.004648859,0.0003992893,0.000133449,0.000001890196,0.000007104785,0.000050680148],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8707447,0.105318405,0.022465207,0.0005671615,0.00048479624,0.00041973253],"domain_scores_gemma":[0.14032239,0.8437174,0.014378158,0.0008280394,0.0006382588,0.00011578787],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49787137,0.00022349218,0.016272089,0.00012034449,0.00008526978,0.000010494289,0.0003575976,0.0007140008,0.00002238454],"category_scores_gemma":[0.83860976,0.00007681799,0.003518993,0.00015539306,0.0020917268,0.000037624228,0.00010369871,0.0021214972,1.2596202e-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":[0.91525435,0.00047873257,0.013442571,0.00051183265,0.01838714,0.00008078921,0.00095903093,0.000021714815,0.00052616134,0.019058714,0.012377121,0.018901814],"study_design_scores_gemma":[0.8904348,0.0006448436,0.017078334,0.0007963665,0.037748773,0.0006722103,0.0018209836,0.0108791115,0.00022452617,0.038312998,0.0012510992,0.0001359359],"about_ca_topic_score_codex":0.00007151969,"about_ca_topic_score_gemma":0.000008923883,"teacher_disagreement_score":0.73839897,"about_ca_system_score_codex":0.000021060652,"about_ca_system_score_gemma":0.00027643488,"threshold_uncertainty_score":0.9983324},"labels":[],"label_agreement":null},{"id":"W4410883535","doi":"10.1016/j.jclinepi.2025.111857","title":"Enhancing risk prediction base on health administrative data using high-dimensional prediction model","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","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":"BC Centre for Disease Control; Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"University of British Columbia","keywords":"Base (topology); Predictive modelling; Computer science; Medicine; Data mining; Statistics; Machine learning; Mathematics","score_opus":0.4602822623245787,"score_gpt":0.5816821289161638,"score_spread":0.12139986659158508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410883535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7205168,0.0010862265,0.19684169,0.07762643,0.0025957364,0.00051074196,0.0005330457,0.000041888445,0.0002474775],"genre_scores_gemma":[0.8900027,0.004297284,0.07542388,0.027560432,0.0022892805,0.0000055385144,0.0002302411,0.000024485962,0.0001661525],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98283494,0.0088610565,0.006576396,0.0006924566,0.00037771842,0.0006574232],"domain_scores_gemma":[0.96176326,0.0322387,0.0036119123,0.0009460855,0.00053919136,0.0009008637],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052126538,0.00024227971,0.0030228847,0.00037663925,0.00020555775,0.000005214428,0.0003398019,0.0005581033,0.00005335272],"category_scores_gemma":[0.18792972,0.00017259845,0.00048604954,0.0002401548,0.0003612452,0.0002056414,0.00019554845,0.0028568597,0.000011449281],"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":[0.0154183,0.0022644685,0.5955469,0.00027545795,0.002332186,0.00012334855,0.000051690622,0.09973307,0.00066608965,0.0049283924,0.22973217,0.048927926],"study_design_scores_gemma":[0.0035356898,0.0059045814,0.2497664,0.0007905916,0.0003105675,0.00022708255,0.000039506886,0.7266286,0.00005183546,0.010752796,0.0018976962,0.00009466786],"about_ca_topic_score_codex":0.0002301904,"about_ca_topic_score_gemma":0.00006330817,"teacher_disagreement_score":0.62689555,"about_ca_system_score_codex":0.00027059563,"about_ca_system_score_gemma":0.0030052767,"threshold_uncertainty_score":0.9994436},"labels":[],"label_agreement":null},{"id":"W4410946344","doi":"10.1016/j.jclinepi.2025.111858","title":"Prevalence of patient and public involvement in child health randomized controlled trials and impact on research quality, loss to follow-up, and dissemination","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Mental Health and Patient Involvement","field":"Health Professions","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 Toronto; SickKids Foundation; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Randomized controlled trial; Medicine; Public health; Quality (philosophy); Family medicine; Clinical trial; Physical therapy; Environmental health; Pediatrics; Nursing; Surgery; Internal medicine","score_opus":0.7693120649460229,"score_gpt":0.7243295779673876,"score_spread":0.04498248697863527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410946344","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":[0.03555213,0.9429106,0.000049972892,0.006729348,0.0016935397,0.012806851,0.00015555443,0.0000038915973,0.00009809325],"genre_scores_gemma":[0.01179869,0.9844624,0.00022233116,0.0025044843,0.00028814192,0.00055135426,0.000037850965,0.00001672547,0.000118014264],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.6087961,0.3433163,0.04451821,0.0009288038,0.0010625316,0.0013780834],"domain_scores_gemma":[0.5265556,0.4548251,0.016742356,0.00032414854,0.0005300603,0.0010227275],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45446563,0.00045008026,0.030618373,0.0013236583,0.00029377275,0.000008844885,0.00027964637,0.0008363044,0.00005574114],"category_scores_gemma":[0.388287,0.00023401088,0.0016148413,0.00034709257,0.0003969172,0.000076627926,0.00037356457,0.0032084286,0.0000023318787],"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":[0.104800604,0.0008061679,0.06982276,0.1425658,0.0008178868,0.0000049361415,0.0010419188,0.0000011532566,1.6003433e-8,0.005352232,0.0021210136,0.67266554],"study_design_scores_gemma":[0.31257114,0.0188086,0.018780671,0.5965581,0.0012554006,0.000015793948,0.0013285257,0.000047271515,6.831074e-8,0.009495101,0.040574055,0.00056527834],"about_ca_topic_score_codex":0.00044459334,"about_ca_topic_score_gemma":0.00014850886,"teacher_disagreement_score":0.67210025,"about_ca_system_score_codex":0.00043354472,"about_ca_system_score_gemma":0.002662948,"threshold_uncertainty_score":0.9990912},"labels":[],"label_agreement":null},{"id":"W4411252122","doi":"10.1016/j.jclinepi.2025.111865","title":"Public availability of randomized clinical trial protocols: a repeated meta-research study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"McMaster University; University of Alberta","funders":"Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Magyar Tudományos Akadémia; Janggen-Pöhn-Stiftung; Bundesamt für Gesundheit; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Randomized controlled trial; Meta-analysis; Protocol (science); Medicine; Research design; Clinical trial; Public health; MEDLINE; Alternative medicine; Surgery; Statistics; Internal medicine; Political science; Nursing; Pathology; Mathematics","score_opus":0.9655448082521385,"score_gpt":0.79496542811529,"score_spread":0.17057938013684848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411252122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7779805,0.0013816338,0.0036593308,0.13593322,0.00398255,0.0694554,0.000010054382,0.00006055255,0.007536772],"genre_scores_gemma":[0.96820265,0.0021408466,0.014958957,0.004171809,0.0027441205,0.004182773,0.0000037375949,0.000047233807,0.0035478936],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.2921378,0.57435125,0.119611405,0.0033258297,0.00768625,0.0028874474],"domain_scores_gemma":[0.015054,0.9533474,0.010863031,0.0027676607,0.016569747,0.0013981571],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.8756742,0.00038279567,0.023696661,0.0009301478,0.00014464269,0.000027939941,0.0017494208,0.0025853545,0.0010057925],"category_scores_gemma":[0.9890067,0.00021739025,0.010273241,0.0014372872,0.008021152,0.00014699108,0.0009395883,0.020519573,0.00004363936],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6830412,0.014507449,0.26436204,0.0003126971,0.012201014,0.00009294546,0.000031802345,0.000002940851,0.0000030520307,0.013444846,0.005003822,0.0069961865],"study_design_scores_gemma":[0.6974262,0.026812619,0.041903682,0.00042407724,0.0035727115,0.000021271493,0.00015007774,0.00025354425,0.000008993788,0.22498143,0.004309656,0.00013571698],"about_ca_topic_score_codex":0.00009788023,"about_ca_topic_score_gemma":0.000079696234,"teacher_disagreement_score":0.37899613,"about_ca_system_score_codex":0.00013289133,"about_ca_system_score_gemma":0.009550428,"threshold_uncertainty_score":0.99990743},"labels":[],"label_agreement":null},{"id":"W4411507891","doi":"10.1016/j.jclinepi.2025.111872","title":"Target trial emulation of cardiovascular outcome trials of medications used to treat type 2 diabetes using real-world data: a systematic review of observational studies","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Diabetes Treatment and Management","field":"Medicine","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":"Jewish General Hospital","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Observational study; Medicine; Type 2 diabetes; Emulation; Clinical trial; Diabetes mellitus; Meta-analysis; Systematic review; MEDLINE; Outcome (game theory); Randomized controlled trial; Intensive care medicine; Internal medicine; Psychology; Endocrinology","score_opus":0.8697186499513354,"score_gpt":0.6643221108102215,"score_spread":0.2053965391411139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411507891","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":[0.00026729153,0.99279,0.00031008312,0.0008074734,0.0012746146,0.0043530143,0.00014930121,0.0000056080853,0.00004263076],"genre_scores_gemma":[0.000037068505,0.9891386,0.009337164,0.00028318734,0.00061636796,0.00005618973,0.00036829026,0.000020923751,0.00014219925],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9597299,0.013794952,0.025158122,0.00041019902,0.0006699694,0.00023683756],"domain_scores_gemma":[0.86142325,0.10773792,0.027314473,0.0016991555,0.0016184781,0.00020673864],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.096695706,0.00037906814,0.045774534,0.0007015734,0.000022874387,0.0000020414648,0.00055364956,0.00026879914,0.00002648405],"category_scores_gemma":[0.39589563,0.0002194168,0.0053871875,0.0009290991,0.00022799917,0.00008696773,0.000249386,0.00039019177,0.000001912704],"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":[0.0004951144,0.00047993925,0.003294305,0.94577247,0.03209683,0.0000043286186,0.000008313324,0.00004809399,8.0803616e-8,0.0004335544,0.0022833373,0.01508363],"study_design_scores_gemma":[0.0068333806,0.0016697879,0.00037607903,0.7883712,0.16335945,0.0000021275603,0.000011050294,0.0000397144,3.1652513e-7,0.00024115492,0.038945984,0.00014972592],"about_ca_topic_score_codex":0.00001628345,"about_ca_topic_score_gemma":0.0000036177705,"teacher_disagreement_score":0.2991999,"about_ca_system_score_codex":0.00014588103,"about_ca_system_score_gemma":0.0011727591,"threshold_uncertainty_score":0.96839195},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaepi_broad"],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4411555570","doi":"10.1016/j.jclinepi.2025.111876","title":"Adherence to RECORD reporting guidelines among observational studies using routinely collected health data published in general medical journals: a meta-epidemiologic study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"SickKids Foundation; Hospital for Sick Children; Queen's University; McMaster University; Women's College Hospital","funders":"","keywords":"Observational study; Medicine; Family medicine; MEDLINE; Epidemiology; Medical record; Environmental health; Pathology; Internal medicine","score_opus":0.9959672742694313,"score_gpt":0.8133929164219663,"score_spread":0.182574357847465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411555570","genre_codex":"empirical","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79799134,0.009276228,0.08430225,0.10342471,0.003711106,0.0011628963,0.000013935944,0.000007072639,0.000110468216],"genre_scores_gemma":[0.28155446,0.0029885122,0.6396344,0.06993259,0.0029342335,0.00007114457,0.000017024346,0.00003328684,0.0028343734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.13898952,0.40668106,0.4396299,0.0040209983,0.009112604,0.0015659035],"domain_scores_gemma":[0.0128943045,0.57061183,0.38273326,0.008837804,0.022965293,0.001957477],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.93506414,0.00058345526,0.045370147,0.0014912533,0.00027310455,0.00026808455,0.006555663,0.00047993526,0.0025576125],"category_scores_gemma":[0.9953631,0.00025628178,0.005513322,0.0049835234,0.0002920355,0.00081502873,0.0017554385,0.0022072054,0.0000249184],"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":[0.00006803317,0.00022259497,0.72884035,0.000021212321,0.00292393,0.00006451692,0.00006328422,0.0031241153,5.5375506e-7,0.00018894747,0.2493368,0.015145702],"study_design_scores_gemma":[0.0008598241,0.0007009885,0.8672074,0.00047616952,0.0011687473,0.000113013964,0.0011184447,0.08938029,5.439221e-8,0.029115802,0.009657467,0.00020179721],"about_ca_topic_score_codex":0.0006400462,"about_ca_topic_score_gemma":0.0033710944,"teacher_disagreement_score":0.5553321,"about_ca_system_score_codex":0.00018131442,"about_ca_system_score_gemma":0.0033655553,"threshold_uncertainty_score":0.9999889},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4411635310","doi":"10.1016/j.jclinepi.2025.111880","title":"Metformin to treat breast cancer: an application of the prevalent new-user design for observational studies with no active comparator","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Metabolism, Diabetes, and Cancer","field":"Biochemistry, Genetics and Molecular Biology","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 Health Centre; Jewish General Hospital","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Observational study; Metformin; Medicine; Oncology; Breast cancer; Internal medicine; Comparator; Cancer; Insulin; Engineering","score_opus":0.2974590623209456,"score_gpt":0.5198137294789871,"score_spread":0.22235466715804147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411635310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8475372,0.03581022,0.11116252,0.0036425495,0.0008952247,0.0008112539,0.000101877406,0.0000029760454,0.000036157653],"genre_scores_gemma":[0.7469613,0.08672658,0.11774668,0.03665917,0.008525762,0.0006479742,0.00005487332,0.000072222894,0.0026054305],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974144,0.00081857486,0.0012837127,0.00022617396,0.00009175836,0.00016535641],"domain_scores_gemma":[0.9958047,0.0018674182,0.0011500445,0.00025314148,0.0008086016,0.00011609022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031777958,0.00012298183,0.00096292933,0.000029058352,0.000044665252,0.0000022749928,0.00029462858,0.00014776405,0.000007313803],"category_scores_gemma":[0.0038187671,0.00006827575,0.00025582052,0.00009049445,0.00014314061,0.00000921263,0.000047538266,0.00013789214,5.5048673e-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":[0.018024677,0.0007193816,0.27140853,0.00024946683,0.002440747,3.6315353e-7,0.00011996187,0.016188124,0.010918915,0.0059833312,0.14909631,0.5248502],"study_design_scores_gemma":[0.0051920814,0.0034220242,0.48682073,0.0002344979,0.00087297725,0.000015758862,0.0001475133,0.00071213226,0.028791858,0.006660802,0.4668285,0.00030112301],"about_ca_topic_score_codex":0.000018249406,"about_ca_topic_score_gemma":0.000048251575,"teacher_disagreement_score":0.52454907,"about_ca_system_score_codex":0.00002402855,"about_ca_system_score_gemma":0.0006375018,"threshold_uncertainty_score":0.45716968},"labels":[],"label_agreement":null},{"id":"W4411928219","doi":"10.1016/j.jclinepi.2025.111892","title":"Response to the letter ‘Balancing methodological rigor and simplicity in ROBUST-RCT: is optional assessment of bias domains the ideal path forward’","year":2025,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Rigour; Simplicity; Ideal (ethics); Path (computing); Computer science; Medicine; Mathematics; Epistemology; Philosophy","score_opus":0.754285470495182,"score_gpt":0.6616606810892643,"score_spread":0.09262478940591767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411928219","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":[0.07479794,0.00012061882,0.06810854,0.85461706,0.0016733407,0.00038635315,0.00005347792,0.000003528021,0.00023915421],"genre_scores_gemma":[0.019661603,0.00037819578,0.063761234,0.91288424,0.0027811443,0.000023423689,0.0000052935216,0.000010744429,0.00049411826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8678252,0.10875847,0.017107613,0.0012343957,0.0041240854,0.00095021335],"domain_scores_gemma":[0.5697914,0.42202523,0.006253677,0.000872527,0.0008894927,0.00016767377],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4310589,0.0003516454,0.0037677197,0.00051486306,0.00018766084,0.00006739809,0.0018630021,0.001117771,0.0005876401],"category_scores_gemma":[0.29997972,0.00014804206,0.0011684863,0.0006245838,0.00057965075,0.00014654617,0.0005822176,0.005433095,0.00001569729],"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":[0.0006774408,0.0000528387,0.11191714,0.000013198952,0.00011124728,0.000035367477,0.000110207424,0.0047702603,0.000005961733,0.00063015637,0.87448055,0.007195616],"study_design_scores_gemma":[0.0005985591,0.0004771777,0.44461542,0.00009217593,0.000054823366,0.0000459159,0.000074097195,0.005508314,6.7381103e-7,0.015911397,0.5325189,0.00010252213],"about_ca_topic_score_codex":0.000047017034,"about_ca_topic_score_gemma":0.00006391003,"teacher_disagreement_score":0.34196165,"about_ca_system_score_codex":0.00013704716,"about_ca_system_score_gemma":0.0014667168,"threshold_uncertainty_score":0.9968614},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4412979870","doi":"10.1016/j.jclinepi.2025.111921","title":"GRADE concept paper 9: rationale and process for creating a GRADE Ontology","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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":"Hamilton Health Sciences; Bruyère; Western University; University of Alberta; McMaster University; Impact","funders":"","keywords":"Ontology; Computer science; Process (computing); Medicine; Information retrieval; Epistemology; Philosophy; Programming language","score_opus":0.19519089316649038,"score_gpt":0.5127765105814261,"score_spread":0.31758561741493574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412979870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83723944,0.013720576,0.10442266,0.041679107,0.0018744984,0.00038303525,0.000024814777,0.000016518676,0.00063936034],"genre_scores_gemma":[0.95306593,0.0012451714,0.028798608,0.014658027,0.0013800354,0.000028233115,0.000028016924,0.00001243445,0.0007835396],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966143,0.0009121924,0.0018608682,0.00028704977,0.00006400196,0.00026162513],"domain_scores_gemma":[0.9910915,0.0075161485,0.00091038353,0.0001408273,0.00020678317,0.00013434555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050115166,0.00013022254,0.0010562928,0.000050281673,0.00008177382,0.0000049377027,0.00021152574,0.00055164966,0.000010491927],"category_scores_gemma":[0.057111774,0.00009388699,0.00030410642,0.000056093726,0.00064574904,0.0000047589406,0.000057251837,0.00033947514,4.1811361e-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":[0.0032627517,0.001076428,0.54030955,0.00043011093,0.0018608943,0.00002937672,0.00042995418,0.00038619014,0.010961356,0.037642106,0.11491928,0.28869197],"study_design_scores_gemma":[0.008486263,0.0054294663,0.15236332,0.00023677529,0.00026882673,0.000317304,0.0009250958,0.0010879212,0.0017653784,0.10661718,0.7220827,0.00041979548],"about_ca_topic_score_codex":0.000005680674,"about_ca_topic_score_gemma":0.000018488126,"teacher_disagreement_score":0.60716337,"about_ca_system_score_codex":0.000005890587,"about_ca_system_score_gemma":0.0002563966,"threshold_uncertainty_score":0.9508306},"labels":[],"label_agreement":null},{"id":"W4413001977","doi":"10.1016/j.jclinepi.2025.111920","title":"FAIRification of biomedical research data","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Research Data Management Practices","field":"Computer Science","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 Ottawa","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; European Commission","keywords":"Epidemiology; Key (lock); Data science; Clinical epidemiology; MEDLINE; Medicine; Computer science; Pathology; Biology; Computer security","score_opus":0.8705691041212151,"score_gpt":0.71467241904853,"score_spread":0.15589668507268517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413001977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029174709,0.0006404202,0.86714447,0.12536995,0.0010352681,0.00010375288,0.000004326351,0.000008032078,0.0027763173],"genre_scores_gemma":[0.483681,0.016988242,0.49399447,0.002897522,0.0009132177,0.0000046075606,0.000031042626,0.000009069263,0.0014808273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9749482,0.017981559,0.0051893075,0.00058329693,0.00084416225,0.00045344705],"domain_scores_gemma":[0.79788524,0.19120406,0.0041361563,0.00484982,0.0015150841,0.0004096587],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2373341,0.000071497554,0.0010412812,0.0006309538,0.00006061406,0.000080577505,0.009561974,0.00019507213,0.00001605215],"category_scores_gemma":[0.47280666,0.00005071011,0.00015297181,0.0010290447,0.0007898987,0.006032558,0.0034305688,0.00149123,0.000019668048],"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":[0.00010389825,0.00039540493,0.01966279,0.00005563493,0.00015080128,0.000023527225,0.000008902884,0.0000077511595,0.00005623541,0.7170483,0.12726355,0.13522324],"study_design_scores_gemma":[0.00070416124,0.00070820504,0.11478904,0.000117946634,0.000020687872,0.000014446018,0.00004209573,0.022983301,0.000021677852,0.08198543,0.77855563,0.000057391124],"about_ca_topic_score_codex":0.000031765932,"about_ca_topic_score_gemma":0.0000037185105,"teacher_disagreement_score":0.6512921,"about_ca_system_score_codex":0.000023717072,"about_ca_system_score_gemma":0.0008073196,"threshold_uncertainty_score":0.99579674},"labels":[],"label_agreement":null},{"id":"W4413139298","doi":"10.1016/j.jclinepi.2025.111928","title":"Scoping review authors view knowledge user consultations as beneficial but not without challenges: a qualitative study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Canadian Arthritis Patient Alliance; Toronto Rehabilitation Institute; University of Toronto","funders":"University of Galway","keywords":"CLARITY; Thematic analysis; Reflexivity; Systematic review; Dyad; Ambiguity; Qualitative research; Medicine; Psychology; Medical education; MEDLINE; Computer science; Sociology; Social psychology; Political science","score_opus":0.919424750491952,"score_gpt":0.8289965812017699,"score_spread":0.09042816929018216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413139298","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":[0.30307147,0.038493823,0.008338377,0.62243557,0.011378041,0.009015707,0.000060829596,0.00009322789,0.0071129478],"genre_scores_gemma":[0.35120043,0.18296914,0.01453866,0.44252434,0.0032653175,0.0008873487,0.0000062538847,0.00006532717,0.0045431815],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.8811927,0.099601574,0.017262701,0.00057581195,0.00041779364,0.00094943994],"domain_scores_gemma":[0.56612957,0.41691488,0.0119464565,0.00070414,0.0032965324,0.0010084116],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1864168,0.00026019174,0.0043400796,0.0003409249,0.00066467666,0.000005134867,0.000640872,0.00040707955,0.0005070032],"category_scores_gemma":[0.549053,0.00019411427,0.00044460242,0.00065835053,0.0003947616,0.00022986712,0.00021999747,0.0025572206,0.0004997501],"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":false,"study_design_scores_codex":[0.0018658098,0.003019927,0.15513629,0.055233296,0.0014472322,0.000055973942,0.31434286,0.00003992703,0.000010624376,0.19249846,0.1779283,0.098421276],"study_design_scores_gemma":[0.017027171,0.00625167,0.18626583,0.22931579,0.0011804517,0.00004108901,0.25569794,0.00012214643,0.0000028247684,0.032144293,0.27098855,0.0009622372],"about_ca_topic_score_codex":0.00017277893,"about_ca_topic_score_gemma":0.0011896542,"teacher_disagreement_score":0.36263624,"about_ca_system_score_codex":0.00018135292,"about_ca_system_score_gemma":0.008289024,"threshold_uncertainty_score":0.99974394},"labels":[],"label_agreement":null},{"id":"W4413292442","doi":"10.1016/j.jclinepi.2025.111931","title":"Including conference abstracts rarely changed systematic review conclusions: a case study from a living network meta-analysis of COVID-19 treatments","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Impact","funders":"Canadian Institutes of Health Research","keywords":"Coronavirus disease 2019 (COVID-19); Meta-analysis; 2019-20 coronavirus outbreak; Systematic review; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; MEDLINE; Gerontology; Virology; Political science; Pathology; Outbreak; Disease","score_opus":0.9797672594205503,"score_gpt":0.7447018379593056,"score_spread":0.23506542146124476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413292442","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036606234,0.9843509,0.00727418,0.00083321694,0.00084640004,0.0062514497,0.00025213617,0.0000055466885,0.00014952141],"genre_scores_gemma":[0.00068453554,0.9897578,0.003380914,0.0045974143,0.0003057585,0.00035724672,0.000028851484,0.000028888862,0.0008586329],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.32010132,0.48533693,0.18669407,0.0024234238,0.0047231545,0.0007210853],"domain_scores_gemma":[0.070288114,0.681819,0.23647122,0.0066723377,0.0035440975,0.0012051824],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.7714184,0.0015241891,0.25278723,0.0022453929,0.00033472173,0.00019699214,0.005782701,0.0010806333,0.0070112594],"category_scores_gemma":[0.9250117,0.00061194965,0.091659404,0.0064711156,0.00027485096,0.0002292781,0.0013566213,0.0020938106,0.0001722872],"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":[0.000011900025,0.00071124936,0.0010303196,0.2606352,0.71235764,0.0019018962,0.00023307286,0.00034411627,1.5025654e-9,0.00010164463,0.01074667,0.0119262785],"study_design_scores_gemma":[0.00022382698,0.00032572227,0.00005124513,0.1145155,0.84945464,0.00041875624,0.00051255204,0.00024923257,3.4855177e-10,0.0009343139,0.032985035,0.00032915224],"about_ca_topic_score_codex":0.00031896034,"about_ca_topic_score_gemma":0.00040314527,"teacher_disagreement_score":0.24981321,"about_ca_system_score_codex":0.00023355926,"about_ca_system_score_gemma":0.0028370586,"threshold_uncertainty_score":0.9997507},"labels":[],"label_agreement":null},{"id":"W4413294654","doi":"10.1016/j.jclinepi.2025.111932","title":"Prevalence and predictors of potentially inappropriate prescribing using codified STOPP-START and Beers criteria: a retrospective cohort study in Ontario's older population","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical Practices and Patient Outcomes","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Children's Hospital of Eastern Ontario; Ottawa Hospital; Ottawa Public Health; Institut du Savoir Montfort; Bruyère; University of Ottawa","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Canadian Institutes of Health Research; Institut du savoir Montfort-Recherche; University of Ottawa","keywords":"Beers Criteria; Medicine; Retrospective cohort study; Cohort; Cohort study; Family medicine; Epidemiology; Population; Gerontology; Environmental health; Demography; Polypharmacy; Intensive care medicine; Internal medicine","score_opus":0.29976009074271237,"score_gpt":0.5152769364106738,"score_spread":0.21551684566796148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413294654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99663836,0.0002819123,0.0007466934,0.0008305079,0.0006950452,0.000698995,0.0000022036181,0.0000038440667,0.00010243164],"genre_scores_gemma":[0.99739784,0.00030885843,0.0016079585,0.0005490374,0.00007690229,0.0000021086848,0.0000012823537,0.000005840513,0.000050187056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99454975,0.0019801487,0.0028059077,0.00027662888,0.00019734644,0.00019022092],"domain_scores_gemma":[0.9935582,0.004428686,0.0015172694,0.00013773344,0.00020195404,0.00015611199],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012234555,0.00012787494,0.0017500708,0.0001689633,0.000035634104,0.000006159733,0.00007010639,0.00019210862,0.000029651545],"category_scores_gemma":[0.021113673,0.00009594234,0.00013794308,0.000100040204,0.00017222976,0.00019613632,0.00008995036,0.000994244,7.386905e-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":[0.002099378,0.00044325885,0.99607253,0.00014399349,0.00033671866,0.000024471374,0.0002444335,0.000060114227,0.000047006764,0.00008016914,0.000020425876,0.0004274825],"study_design_scores_gemma":[0.0037001309,0.0013231229,0.98998016,0.00041900063,0.0007811642,0.000030803596,0.000096741096,0.0028698414,0.000002787645,0.0007051582,0.000029550367,0.00006151544],"about_ca_topic_score_codex":0.0039577633,"about_ca_topic_score_gemma":0.0011125329,"teacher_disagreement_score":0.008879119,"about_ca_system_score_codex":0.000114054514,"about_ca_system_score_gemma":0.00018562686,"threshold_uncertainty_score":0.9871319},"labels":[],"label_agreement":null},{"id":"W4413581527","doi":"10.1016/j.jclinepi.2025.111937","title":"Psychometric validation of the pictorial ecological momentary well-being instrument","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","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":"Université de Montréal; Institut National de Santé Publique du Québec","funders":"Public Health Agency of Canada","keywords":"Psychometrics; Ecology; Psychology; Biology; Clinical psychology","score_opus":0.35265187415675375,"score_gpt":0.5890263717990207,"score_spread":0.23637449764226698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413581527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93390226,0.00030507642,0.00081674854,0.02205374,0.02344015,0.00033536507,0.000002747952,0.0000063212715,0.01913756],"genre_scores_gemma":[0.9908139,0.00043471903,0.0011231377,0.005050136,0.0015518707,0.000009286524,0.0000018439251,0.0000071084946,0.0010079793],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9848758,0.00875448,0.0053084954,0.00027574995,0.00032973225,0.00045572972],"domain_scores_gemma":[0.9722831,0.024169354,0.0026724124,0.00044716714,0.00020619002,0.00022172376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027541343,0.00013739006,0.0014986354,0.0003368239,0.000088639965,0.0000042247625,0.00075120805,0.0004741017,0.001423321],"category_scores_gemma":[0.032679178,0.00008183087,0.0006428995,0.00065683806,0.00038107953,0.00005998532,0.00020498519,0.001546586,0.000038270337],"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":[0.0009191621,0.0008590981,0.8809474,0.00005126357,0.0002356064,0.000005021793,0.000049707283,0.000026155512,0.000014410937,0.03549184,0.02741903,0.053981286],"study_design_scores_gemma":[0.002325367,0.0013713618,0.8966318,0.000076295364,0.000050703373,0.00001921875,0.00007281989,0.000023585597,0.00007063005,0.054417778,0.044883557,0.000056919613],"about_ca_topic_score_codex":0.000049580965,"about_ca_topic_score_gemma":0.000004745248,"teacher_disagreement_score":0.05691163,"about_ca_system_score_codex":0.00015022987,"about_ca_system_score_gemma":0.00026988407,"threshold_uncertainty_score":0.9994895},"labels":[],"label_agreement":null},{"id":"W4413584208","doi":"10.1016/j.jclinepi.2025.111944","title":"Use of artificial intelligence to support the assessment of the methodological quality of systematic reviews","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Systematic review; Quality assessment; MEDLINE; Medicine; Psychology; Management science; Engineering; Political science; Pathology","score_opus":0.9941548078090001,"score_gpt":0.8082536389011452,"score_spread":0.1859011689078549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413584208","genre_codex":"methods","genre_gemma":"empirical","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":[0.10610469,0.001136362,0.874919,0.013905845,0.0017611388,0.0017561308,0.0000102681215,7.17989e-7,0.00040582573],"genre_scores_gemma":[0.8129885,0.0008036815,0.18077374,0.0046236482,0.00014914568,0.000025036072,3.0910863e-7,0.000005073445,0.0006308517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.1561184,0.6692147,0.16978432,0.00078269193,0.0037385467,0.00036131032],"domain_scores_gemma":[0.0583688,0.81644124,0.11604584,0.005012869,0.003925317,0.00020596792],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.867749,0.00022334259,0.024427528,0.00022512456,0.000052586787,0.00002960478,0.0038272724,0.00024761117,0.0009308786],"category_scores_gemma":[0.9554313,0.00006292768,0.009481761,0.0013861067,0.0005804112,0.00008383413,0.00042045978,0.0007151474,0.00003102634],"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":[0.00018379757,0.0006674384,0.5086439,0.0077133756,0.0015989128,0.0000019864117,0.0002065092,0.0030554223,0.00024637004,0.36703748,0.03689714,0.07374763],"study_design_scores_gemma":[0.00013008353,0.0012390269,0.62212443,0.0048893713,0.0022050664,0.000027189628,0.00087729347,0.0067223674,0.00013961956,0.3439762,0.01747798,0.00019139743],"about_ca_topic_score_codex":0.000015853604,"about_ca_topic_score_gemma":0.000024151994,"teacher_disagreement_score":0.70688385,"about_ca_system_score_codex":0.000021571466,"about_ca_system_score_gemma":0.0003722093,"threshold_uncertainty_score":0.9999824},"labels":[],"label_agreement":null},{"id":"W4413854149","doi":"10.1016/j.jclinepi.2025.111962","title":"Trustworthiness of treatment clinical practice guidelines has modestly improved since the introduction of Institute of Medicine standards: a systematic survey","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; University of Ottawa; McMaster University","funders":"Einstein Stiftung Berlin","keywords":"Trustworthiness; Medicine; Alternative medicine; Systematic review; Clinical Practice; Family medicine; MEDLINE; Evidence-based medicine; Psychology; Political science; Pathology","score_opus":0.658780580790509,"score_gpt":0.659997611965975,"score_spread":0.0012170311754658991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413854149","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":[0.29359582,0.0054607424,0.1309154,0.5569192,0.010304597,0.0024945184,0.00009833687,0.000019482446,0.00019188378],"genre_scores_gemma":[0.9325854,0.0088633485,0.0468375,0.007930321,0.003549485,0.000016006354,0.000046776175,0.000028403241,0.00014275206],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93219817,0.020327182,0.045494303,0.0006140296,0.00097407895,0.00039223512],"domain_scores_gemma":[0.612831,0.30710608,0.04787755,0.0019517499,0.029817138,0.0004164917],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2096486,0.0003138159,0.0075157057,0.0002635347,0.000062773324,0.0000050095964,0.00043952905,0.00048315822,0.000042028783],"category_scores_gemma":[0.90907925,0.00016486614,0.0011550828,0.00063925365,0.0023957633,0.00036734634,0.00011590825,0.0010967178,0.0000010029482],"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":[0.10337768,0.009971219,0.50236964,0.021353336,0.019230595,0.0000934298,0.00059097755,0.008612872,0.0011695281,0.018403886,0.16620092,0.1486259],"study_design_scores_gemma":[0.07402547,0.0726414,0.5715147,0.023720596,0.034201816,0.001622327,0.00437016,0.05704116,0.00025783599,0.016984796,0.14284845,0.000771298],"about_ca_topic_score_codex":0.0017268504,"about_ca_topic_score_gemma":0.0003926601,"teacher_disagreement_score":0.69943064,"about_ca_system_score_codex":0.00019283484,"about_ca_system_score_gemma":0.0042676,"threshold_uncertainty_score":0.882729},"labels":[],"label_agreement":null},{"id":"W4413884121","doi":"10.1016/j.jclinepi.2025.111959","title":"Retrospective use of the Pragmatic-Explanatory Continuum Indicator Summary-2 trial design tool to assess design choices in randomized controlled trials: an empirical review","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Western University; Ottawa Hospital; University of Ottawa","funders":"Health Research Board; H&R BLOCK","keywords":"Medicine; Research design; Clinical study design; Medical physics; Alternative medicine; Physical therapy; Clinical trial; Statistics; Internal medicine; Pathology; Mathematics","score_opus":0.9147139184638746,"score_gpt":0.6853601322090322,"score_spread":0.22935378625484237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413884121","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054349426,0.024376625,0.85855836,0.031208124,0.006067149,0.024966165,0.000021028685,0.000006689142,0.00044644746],"genre_scores_gemma":[0.29633126,0.04372298,0.51038885,0.1336298,0.0045568566,0.002877935,0.000009751519,0.00011959882,0.008362949],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.06054287,0.8024917,0.13208926,0.0010652377,0.0033411998,0.0004697156],"domain_scores_gemma":[0.011603158,0.87482184,0.10739363,0.0029370284,0.0028436547,0.0004006662],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.95255196,0.00049343874,0.0890484,0.000915876,0.00008564556,0.0001660324,0.003318332,0.0005675114,0.0011728096],"category_scores_gemma":[0.9915298,0.00016745257,0.018635238,0.0016725846,0.00045764682,0.0004053514,0.00019906758,0.0013690137,0.0000441579],"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":[0.47914994,0.0008525639,0.11747177,0.00021277659,0.0048286566,0.000014542636,0.00008877866,0.00049999764,0.000008128445,0.0028794226,0.38555777,0.008435659],"study_design_scores_gemma":[0.76525044,0.0023056013,0.07893321,0.0056372187,0.010435284,0.00002115346,0.00011457403,0.011892271,0.000008336348,0.07619134,0.04872261,0.00048797033],"about_ca_topic_score_codex":0.000009838185,"about_ca_topic_score_gemma":0.00002494593,"teacher_disagreement_score":0.34816948,"about_ca_system_score_codex":0.00008891556,"about_ca_system_score_gemma":0.0015488054,"threshold_uncertainty_score":0.99974024},"labels":[],"label_agreement":null},{"id":"W4414041103","doi":"10.1016/j.jclinepi.2025.111970","title":"Overview of evidence synthesis types and modes","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"St. Michael's Hospital; Ottawa Public Health; Ottawa Hospital; University of Ottawa; Public Health Agency of Canada","funders":"NÖ Gesundheits- und Sozialfonds; National Health and Medical Research Council; Donau-Universität Krems; National Institute for Health and Care Research","keywords":"Evidence-based medicine; Systematic review; Evidence-based practice; Best evidence; MEDLINE","score_opus":0.9799444139081491,"score_gpt":0.7494701738068754,"score_spread":0.2304742401012737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414041103","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6514547,0.155812,0.107523024,0.07486794,0.0019466995,0.00042450684,0.000007817348,0.0000028382053,0.0079604685],"genre_scores_gemma":[0.96062183,0.013407985,0.021605795,0.0025286858,0.00014142043,0.0000021035712,4.4143853e-8,0.0000030240958,0.0016890862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7938018,0.13412696,0.06904259,0.0007766777,0.0019629982,0.00028898878],"domain_scores_gemma":[0.13712609,0.81906956,0.039054953,0.002095239,0.0023976865,0.00025649986],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.60421824,0.00013956137,0.0121207675,0.00027980108,0.000031876232,0.00003177524,0.0012550898,0.00018767109,0.0014545387],"category_scores_gemma":[0.923352,0.000051035073,0.0031535565,0.0005084295,0.00026702628,0.00015922346,0.00014839199,0.0003282702,0.00007782211],"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":[0.00006147204,0.0000554767,0.7009754,0.00016231772,0.0005123506,0.0000035041737,0.000015431715,0.00013898064,0.000013008408,0.02945693,0.04585852,0.22274661],"study_design_scores_gemma":[0.00018515125,0.00019700573,0.6433996,0.001142667,0.0009821132,0.000030452478,0.000098456636,0.0074388403,0.0000181013,0.2760848,0.07033159,0.00009122662],"about_ca_topic_score_codex":0.000006862104,"about_ca_topic_score_gemma":0.000005674674,"teacher_disagreement_score":0.6849426,"about_ca_system_score_codex":0.000007130627,"about_ca_system_score_gemma":0.00016740973,"threshold_uncertainty_score":0.99945825},"labels":[],"label_agreement":null},{"id":"W4414166979","doi":"10.1016/j.jclinepi.2025.111974","title":"Virtual versus in-person meetings for practice guideline panels: A qualitative study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Conferences and Exhibitions Management","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"American University of Beirut","keywords":"Guideline; Qualitative research; Online discussion; MEDLINE; Qualitative analysis","score_opus":0.5149637425125909,"score_gpt":0.646271193037529,"score_spread":0.13130745052493809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414166979","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":[0.25561273,0.0005142017,0.0704918,0.617462,0.010772944,0.0014527218,0.0000082732795,0.000029461304,0.043655876],"genre_scores_gemma":[0.9704127,0.00051432115,0.017499195,0.009637351,0.0010995922,0.000022106338,0.0000015795775,0.000005149576,0.00080801354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9832674,0.012467559,0.0035039135,0.00023951722,0.0002089759,0.00031257828],"domain_scores_gemma":[0.83650756,0.15913218,0.002744221,0.00016629908,0.0012925338,0.00015722857],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1110986,0.000094456336,0.0011565632,0.00017042866,0.00015569497,0.000017163471,0.00032428576,0.00015365047,0.000059361384],"category_scores_gemma":[0.4315445,0.000075697564,0.00035481417,0.00027713986,0.0002620137,0.00018947918,0.000051076277,0.0004654335,0.0000050991025],"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":[0.0076769725,0.002406638,0.008794199,0.000019152207,0.0008295868,0.00003804532,0.09573715,0.00047306114,9.793035e-7,0.5943116,0.13422878,0.15548383],"study_design_scores_gemma":[0.0033936072,0.002516486,0.0019962778,0.00005480853,0.00014598924,3.9813645e-7,0.6078226,0.00023908103,1.0321154e-7,0.015900914,0.3678544,0.000075324046],"about_ca_topic_score_codex":0.0017722114,"about_ca_topic_score_gemma":0.0021742024,"teacher_disagreement_score":0.71479994,"about_ca_system_score_codex":0.000092131144,"about_ca_system_score_gemma":0.00051414367,"threshold_uncertainty_score":0.91531104},"labels":[],"label_agreement":null},{"id":"W4414286696","doi":"10.1016/j.jclinepi.2025.111977","title":"Citizen science as an approach for engaging underrepresented communities in codevelopment of health research","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Arthritis Research Centre of Canada; Research Canada","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Canadian Arthritis Network; Michael Smith Health Research BC; Arthritis Society","keywords":"Citizen science; Underrepresented Minority; Community-based participatory research; Public health; Health equity; Community participation","score_opus":0.7286731750768154,"score_gpt":0.6134058338959623,"score_spread":0.11526734118085313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414286696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9513376,0.00021826301,0.013564641,0.011586104,0.00034480265,0.00030906007,0.000008814045,0.000006065129,0.022624694],"genre_scores_gemma":[0.9912683,0.00054586615,0.006078194,0.0019802074,0.00002207009,0.000009026894,0.000010291657,0.0000034334032,0.00008264598],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9903112,0.005797536,0.002824534,0.00021077975,0.00034771356,0.00050823373],"domain_scores_gemma":[0.98519796,0.013288855,0.0009082952,0.00026946308,0.00015671697,0.0001786795],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.116191715,0.00007658891,0.00096189586,0.00021250338,0.00023751683,0.00000902882,0.0007449115,0.00010282206,0.0007254559],"category_scores_gemma":[0.030583771,0.000061031817,0.00013227596,0.0006027574,0.0023167122,0.00013415683,0.00034321152,0.0007421618,0.0000049915066],"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":[0.00032198871,0.0007579199,0.92767596,0.000058623256,0.000022887867,0.0000012203202,0.0008048749,0.00064462965,0.0000706004,0.034096476,0.006906452,0.02863835],"study_design_scores_gemma":[0.0011451221,0.00051200634,0.94722813,0.000078569996,0.0000037149603,0.000008455986,0.021091124,0.0032098677,0.00004153353,0.021007864,0.0056088394,0.00006479295],"about_ca_topic_score_codex":0.0008116444,"about_ca_topic_score_gemma":0.0001925517,"teacher_disagreement_score":0.085607946,"about_ca_system_score_codex":0.00052191707,"about_ca_system_score_gemma":0.00043318473,"threshold_uncertainty_score":0.97758204},"labels":[],"label_agreement":null},{"id":"W4414308075","doi":"10.1016/j.jclinepi.2025.111976","title":"GRADE notes 6: Three strategies to determine the clinically important thresholds for outcomes in evidence-based guideline development","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Impact; University of British Columbia; McMaster University","funders":"","keywords":"Guideline; Judgement; Clinical judgement; Certainty; MEDLINE; Evidence-based medicine","score_opus":0.7049873849763499,"score_gpt":0.6475969269750136,"score_spread":0.05739045800133635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414308075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46565282,0.00047677042,0.2042419,0.3271798,0.0013723423,0.0010341526,0.000004847534,0.000015170291,0.00002221841],"genre_scores_gemma":[0.6564327,0.00038282617,0.24349226,0.09881297,0.0007438241,0.000060887796,0.000011043688,0.000022445025,0.00004106373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9685969,0.0020525558,0.027773907,0.0005419502,0.00044029145,0.00059442024],"domain_scores_gemma":[0.61610675,0.3734541,0.0076308046,0.0008462647,0.001486342,0.00047572723],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10860134,0.00032078603,0.003530291,0.0003214812,0.00009194529,0.000025165464,0.00062036625,0.00044227828,0.000066394605],"category_scores_gemma":[0.64778966,0.00018243748,0.0011186062,0.00037778317,0.00028436948,0.00024762598,0.00015774278,0.0013508,0.000008114341],"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":[0.004612515,0.00056285184,0.90531605,0.00006474087,0.00027699326,0.000038085203,0.000024503275,0.00095539837,0.000048719165,0.00086606387,0.0063460367,0.080888055],"study_design_scores_gemma":[0.0079526035,0.0035847863,0.93102735,0.00079427037,0.00044778961,0.000036031037,0.00018692108,0.005358954,0.000049613504,0.020461695,0.029903142,0.000196863],"about_ca_topic_score_codex":0.00008991579,"about_ca_topic_score_gemma":0.001328314,"teacher_disagreement_score":0.5391883,"about_ca_system_score_codex":0.00013234018,"about_ca_system_score_gemma":0.0041575273,"threshold_uncertainty_score":0.9178825},"labels":[],"label_agreement":null},{"id":"W4414422261","doi":"10.1016/j.jclinepi.2025.111981","title":"Statistical model assessment in published dose-response meta-analyses is suboptimal: evidence from a methodological review and reanalysis of 242 datasets","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; Impact","funders":"McMaster University","keywords":"Credibility; Statistical model; Selection (genetic algorithm); Statistical analysis; Model selection; Key (lock); Statistical hypothesis testing","score_opus":0.9862737106190819,"score_gpt":0.7952418118600114,"score_spread":0.19103189875907045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414422261","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03321298,0.08220837,0.80173194,0.08145009,0.0002150127,0.0005471061,0.00047857076,0.0000023889538,0.00015350712],"genre_scores_gemma":[0.16129342,0.023715148,0.79631835,0.01808217,0.00006519048,0.000027261305,0.0000278066,0.00001056634,0.00046008683],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.27281576,0.6001842,0.11833091,0.0028704484,0.0050810184,0.0007176691],"domain_scores_gemma":[0.09573522,0.84968525,0.046082143,0.00504904,0.002827557,0.0006207651],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.824057,0.00047268596,0.040024135,0.00093109545,0.000053742755,0.00013936214,0.0029178672,0.0004201814,0.01052663],"category_scores_gemma":[0.9446887,0.0001951324,0.008226491,0.0019970643,0.0005625941,0.0005519454,0.0005809056,0.0014585641,0.00003092896],"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":[0.0016306756,0.0007071817,0.30926338,0.0005881477,0.029242767,0.0001040819,0.00006778573,0.006094207,0.000109484885,0.005198935,0.627827,0.019166375],"study_design_scores_gemma":[0.0009196957,0.0005239316,0.5394548,0.00078708905,0.071867995,0.000029475743,0.000101939906,0.17928135,0.0000055785526,0.19825296,0.00845247,0.00032268255],"about_ca_topic_score_codex":0.00012772754,"about_ca_topic_score_gemma":0.000044618984,"teacher_disagreement_score":0.6193745,"about_ca_system_score_codex":0.00004769596,"about_ca_system_score_gemma":0.0007580564,"threshold_uncertainty_score":0.9903779},"labels":[],"label_agreement":null},{"id":"W4414422782","doi":"10.1016/j.jclinepi.2025.111985","title":"Updating the PRISMA reporting guideline for network meta-analysis: a scoping review","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Public Health Agency of Canada; University of Ottawa; Ottawa Hospital; Canadian Arthritis Patient Alliance; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; University of British Columbia","keywords":"Guideline; Trustworthiness; MEDLINE; Systematic review; Critical appraisal; Health services research","score_opus":0.9703870573823761,"score_gpt":0.7562780712197349,"score_spread":0.21410898616264118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414422782","genre_codex":"methods","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016577351,0.17942104,0.6812107,0.13551876,0.0010313117,0.0011815956,0.0000023605178,0.0000026988146,0.0014657746],"genre_scores_gemma":[0.011556061,0.016285568,0.72628707,0.23668568,0.0033060466,0.0001803908,0.000011438905,0.000026987944,0.005660797],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.29828075,0.23684457,0.4581044,0.0019503882,0.0038487872,0.0009711223],"domain_scores_gemma":[0.027305292,0.57376975,0.38557357,0.005300033,0.0077355183,0.00031582013],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.94163525,0.0003466095,0.046153214,0.0003262794,0.00027483635,0.00014471613,0.0029616565,0.00024541738,0.00321746],"category_scores_gemma":[0.9705634,0.00011600642,0.049778707,0.0029672815,0.00015825283,0.00015318852,0.0002788066,0.0008785538,0.000056460412],"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":[0.000023707873,0.00003995077,0.035816967,0.00062150613,0.11385432,0.0000069594876,0.000010376753,0.009274985,2.013911e-7,0.007506348,0.8112592,0.02158549],"study_design_scores_gemma":[0.00032471886,0.0001536385,0.003974562,0.0029270125,0.4533172,0.000058999292,0.000107678825,0.03118328,3.2046557e-7,0.13775109,0.36998433,0.00021715258],"about_ca_topic_score_codex":0.000004822181,"about_ca_topic_score_gemma":0.00003466201,"teacher_disagreement_score":0.44127485,"about_ca_system_score_codex":0.000017058284,"about_ca_system_score_gemma":0.00052608474,"threshold_uncertainty_score":0.9976937},"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":"W4414625230","doi":"10.1016/j.jclinepi.2025.111969","title":"Corrigendum to GRADE guidance 39: using GRADE-ADOLOPMENT to adopt, adapt or create contextualized recommendations from source guidelines and evidence syntheses [Journal of Clinical Epidemiology 81 (2024) 111494]","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Calgary; Impact; McMaster University","funders":"","keywords":"Regret; Publishing; MEDLINE; Clinical epidemiology; Epidemiology; Alternative medicine","score_opus":0.7415211049083584,"score_gpt":0.6211341321327252,"score_spread":0.12038697277563326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414625230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17463784,0.012045902,0.62340885,0.17867987,0.010422843,0.0007295744,0.000015438809,0.000020723579,0.000038979393],"genre_scores_gemma":[0.4066755,0.036998674,0.4516324,0.09605371,0.005898398,0.000030397072,0.000007339142,0.00006753477,0.002636024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93363416,0.043230206,0.021114985,0.00078942446,0.00046498913,0.00076620554],"domain_scores_gemma":[0.8811501,0.103881605,0.009276574,0.0008619154,0.0027854335,0.0020443262],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16811997,0.00038531004,0.0073905145,0.0004837677,0.00017312916,0.000014168756,0.00049460726,0.00078462646,0.00035200123],"category_scores_gemma":[0.66710705,0.00026617316,0.0020207085,0.00044512172,0.00037874156,0.00020700856,0.00026087352,0.0019871334,0.00001894111],"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":[0.0061026393,0.00095418247,0.3795803,0.00035043157,0.0028719548,0.00019911832,0.00022392416,0.0010458605,0.00016370337,0.0004915035,0.19936153,0.40865487],"study_design_scores_gemma":[0.0075795376,0.0071747736,0.5096853,0.022920635,0.0025186045,0.0019679707,0.0009389218,0.0042882483,0.00005237702,0.0051247836,0.4372187,0.0005301717],"about_ca_topic_score_codex":0.00025303115,"about_ca_topic_score_gemma":0.000052526822,"teacher_disagreement_score":0.49898708,"about_ca_system_score_codex":0.00017523309,"about_ca_system_score_gemma":0.0018799164,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W4415327295","doi":"10.1016/j.jclinepi.2025.112025","title":"Jurisdictional scans: methodological considerations for systematically analyzing and comparing policy approaches across different jurisdictions","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Health Research Board","keywords":"Work (physics); Strengths and weaknesses; Jurisdiction; Public policy","score_opus":0.9533352786344016,"score_gpt":0.7826644227689205,"score_spread":0.17067085586548114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415327295","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":[0.2565237,0.00015788664,0.5906335,0.1490025,0.0016637809,0.00090675626,0.000053561453,0.00003195618,0.0010263234],"genre_scores_gemma":[0.872445,0.00023609163,0.10145439,0.023953373,0.0015564226,0.00016528262,0.0000031578825,0.0000107388905,0.00017552766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.969988,0.018888593,0.009672449,0.00039843319,0.00021621212,0.0008363156],"domain_scores_gemma":[0.57605064,0.41758087,0.004553161,0.00032200568,0.0008262294,0.000667054],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.078515366,0.00019505534,0.00289324,0.00033708257,0.0013650475,0.00001787795,0.000238963,0.00045948374,0.000054990473],"category_scores_gemma":[0.3565794,0.00013405392,0.00043242666,0.00031947216,0.0006241353,0.00016172318,0.0001831583,0.0014746622,0.0000065408235],"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":[0.00015354263,0.00008878035,0.62917477,0.0005614503,0.0002097925,0.0000011020916,0.0012051257,0.00035372953,0.0000068223067,0.35849294,0.008546762,0.0012051929],"study_design_scores_gemma":[0.0027081661,0.0003626633,0.7527576,0.00050513144,0.00013920125,0.00004003001,0.001516313,0.01483108,0.000001370518,0.21927002,0.007734193,0.00013423958],"about_ca_topic_score_codex":0.00005450619,"about_ca_topic_score_gemma":0.00016930842,"teacher_disagreement_score":0.6159213,"about_ca_system_score_codex":0.00020231464,"about_ca_system_score_gemma":0.0018444958,"threshold_uncertainty_score":0.99993503},"labels":[],"label_agreement":null},{"id":"W4415531216","doi":"10.1016/j.jclinepi.2025.112019","title":"Identifying potentially inappropriate prescribing in entire populations: coding the STOPP-START and Beers criteria for use with large, routinely collected population health datasets","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical Practices and Patient Outcomes","field":"Medicine","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":"Children's Hospital of Eastern Ontario; Ottawa Hospital; Institut du Savoir Montfort; Bruyère; University of Ottawa","funders":"Institut canadien d'information sur la santé; Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Diagnosis code; Coding (social sciences); Operationalization; Health care; Population; Population health; MEDLINE; Public health; Identification (biology)","score_opus":0.5977242493142151,"score_gpt":0.5947199475460048,"score_spread":0.0030043017682103157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415531216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8686724,0.0007163586,0.09058921,0.03791264,0.0009281649,0.0010859335,0.00006533522,0.000012477277,0.000017479151],"genre_scores_gemma":[0.96376264,0.0005211088,0.02420725,0.011143483,0.00014816305,0.000007313947,0.00014629535,0.000010572903,0.0000531952],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99400675,0.00241418,0.002877719,0.00023379599,0.00014857613,0.00031894768],"domain_scores_gemma":[0.98657936,0.011004769,0.0019005273,0.0001789051,0.00016642176,0.0001700009],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014834366,0.0001275719,0.0012497816,0.00017427302,0.00018627326,0.00003104171,0.000104592225,0.0001333499,0.0000106813695],"category_scores_gemma":[0.035901763,0.00007784451,0.00016712355,0.00022695935,0.00007725734,0.00035788064,0.000062965526,0.00072543713,2.5761602e-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":[0.0033462609,0.00018911876,0.9867043,0.00019519206,0.00015760165,0.000011170059,0.00008382648,0.00013439402,0.000012360677,0.0026537832,0.002454119,0.00405786],"study_design_scores_gemma":[0.00485867,0.0005713658,0.95922565,0.0006214678,0.00025304288,0.000043051183,0.00013997522,0.026157152,0.0000012693052,0.0020099015,0.0060488856,0.00006954501],"about_ca_topic_score_codex":0.00023206865,"about_ca_topic_score_gemma":0.0003272984,"teacher_disagreement_score":0.09509022,"about_ca_system_score_codex":0.00006174265,"about_ca_system_score_gemma":0.00019902994,"threshold_uncertainty_score":0.9722192},"labels":[],"label_agreement":null},{"id":"W4416010559","doi":"10.1016/j.jclinepi.2025.112045","title":"A qualitative study among guideline developers revealed challenges and strategies for rare disease guideline development","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","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":"Thrombosis and Atherosclerosis Research Institute","funders":"European Commission","keywords":"Guideline; Qualitative research; Salient; MEDLINE; Rare disease","score_opus":0.22150740028382596,"score_gpt":0.5322790142651601,"score_spread":0.3107716139813341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416010559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95876694,0.017615931,0.017027013,0.005538492,0.00046101442,0.00043543766,0.000021660908,0.0000048736306,0.00012861677],"genre_scores_gemma":[0.9627986,0.0039043636,0.02976732,0.0027433205,0.00043509708,0.00003391293,0.000056069566,0.000016303755,0.00024500382],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934449,0.0018044466,0.0039772866,0.00041474454,0.0000899684,0.00026862518],"domain_scores_gemma":[0.9952308,0.0021270066,0.0012930253,0.00023546175,0.00080665195,0.00030705836],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013864903,0.00021223241,0.0011924931,0.000090805086,0.00008870277,0.0000109652565,0.0002656044,0.00020156821,0.0000055431246],"category_scores_gemma":[0.023875585,0.0001557501,0.00032261826,0.000044658154,0.0002117079,0.000009212048,0.00015637332,0.00019110306,5.2460285e-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":[0.026354728,0.0067499843,0.32567587,0.0012282099,0.011173333,0.0003854249,0.015637651,0.0024102814,0.00094562874,0.01941476,0.26940417,0.32061997],"study_design_scores_gemma":[0.0095104,0.0036267482,0.57381946,0.0002810647,0.0005823767,0.000026387179,0.075561434,0.00032290188,0.00004099628,0.034409348,0.301078,0.0007409255],"about_ca_topic_score_codex":0.000004896588,"about_ca_topic_score_gemma":0.00007689817,"teacher_disagreement_score":0.31987903,"about_ca_system_score_codex":0.000014599928,"about_ca_system_score_gemma":0.0012641967,"threshold_uncertainty_score":0.98434675},"labels":[],"label_agreement":null},{"id":"W4416018474","doi":"10.1016/j.jclinepi.2025.112047","title":"Core GRADE unpacked: a summary of recent innovations in complementary GRADE methodology","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Grading (engineering); Certainty; Core (optical fiber); MEDLINE; Evidence-based medicine; Work (physics); Clinical Practice","score_opus":0.9823013435272192,"score_gpt":0.7503404818406014,"score_spread":0.23196086168661778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416018474","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":[0.59373516,0.0037100762,0.22747599,0.16417633,0.0054624197,0.00085849897,0.000036107434,0.0000037123395,0.0045417324],"genre_scores_gemma":[0.4833143,0.0046416847,0.47343317,0.035700135,0.0006882138,0.000019413439,0.000031075906,0.00002003396,0.0021519673],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.522307,0.31483757,0.15749952,0.0014838238,0.0030443203,0.0008277803],"domain_scores_gemma":[0.39318827,0.5467319,0.053914182,0.0027157075,0.0031690944,0.00028089673],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.65956277,0.0002371034,0.015317196,0.0013233894,0.000048399885,0.000017447304,0.0020803022,0.00031461095,0.0034432446],"category_scores_gemma":[0.7307444,0.00011802766,0.0031585183,0.0028243272,0.0004168255,0.000118474454,0.00025231446,0.0011079252,0.000046779467],"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":[0.00007455107,0.00025902863,0.69782895,0.000031398922,0.00044983375,0.000008684593,0.00005177775,0.00017594673,0.000033606735,0.06972109,0.19760786,0.03375729],"study_design_scores_gemma":[0.00078656356,0.0002273814,0.3598893,0.00008648711,0.00019573244,0.000020065383,0.00037194815,0.0010373541,0.0000056308195,0.44545594,0.19185013,0.00007345489],"about_ca_topic_score_codex":0.000044037282,"about_ca_topic_score_gemma":0.00017765151,"teacher_disagreement_score":0.37573487,"about_ca_system_score_codex":0.000045298693,"about_ca_system_score_gemma":0.0004190641,"threshold_uncertainty_score":0.99930143},"labels":[],"label_agreement":null},{"id":"W4416119070","doi":"10.1016/j.jclinepi.2025.112050","title":"Influence of focusing on dominant first order loop when assessing the certainty of evidence of network meta-analysis: a case study","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Ministry of Education - Singapore; Ministry of Health -Singapore","keywords":"Certainty; First order; Meta-analysis; Order (exchange); Confidence interval; Loop (graph theory)","score_opus":0.950673557480007,"score_gpt":0.7105103482581071,"score_spread":0.24016320922189993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416119070","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":[0.9241632,0.0058892732,0.05962724,0.009421458,0.00028989845,0.0005334858,0.0000024368585,7.069822e-7,0.00007227962],"genre_scores_gemma":[0.9865341,0.00015548377,0.011648399,0.0013493596,0.00010313629,0.0000073041424,9.425748e-8,0.0000053225267,0.00019676953],"study_design_codex":"observational","study_design_gemma":"meta_analysis","domain_scores_codex":[0.6770776,0.21708013,0.09982865,0.0012528959,0.0042114505,0.0005492592],"domain_scores_gemma":[0.30111527,0.5970074,0.089905754,0.004393707,0.0073726457,0.00020519963],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.6761639,0.00033522063,0.028919706,0.0006390632,0.00015263919,0.00006237844,0.002576567,0.0002942208,0.0006294995],"category_scores_gemma":[0.75562805,0.00010998277,0.01390245,0.0033474518,0.00057352975,0.00023684518,0.00033025094,0.0010450722,0.00000812968],"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":[0.00016424953,0.00041549664,0.53618145,0.00010408993,0.0716722,0.00010314129,0.00034715165,0.38378215,0.000006162209,0.00077574985,0.003621129,0.0028270218],"study_design_scores_gemma":[0.0015586083,0.00284543,0.3658763,0.0011407116,0.5107485,0.00034339516,0.0062521608,0.05977126,0.000020736356,0.048660193,0.0023834524,0.00039928022],"about_ca_topic_score_codex":0.00036364608,"about_ca_topic_score_gemma":0.00043716302,"teacher_disagreement_score":0.43907627,"about_ca_system_score_codex":0.000022437162,"about_ca_system_score_gemma":0.0004285982,"threshold_uncertainty_score":0.99597305},"labels":[],"label_agreement":null},{"id":"W4416202488","doi":"10.1016/j.jclinepi.2025.112048","title":"Dysinclusion: naming and defining the inequitable absence of marginalized populations in health research","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health disparities and outcomes","field":"Social Sciences","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":"Public Health Ontario; University of Toronto; Ontario Clinical Oncology Group; Centre for Addiction and Mental Health; Toronto Public Health; St Joseph's Health Centre; Brock University","funders":"Department of Family and Community Medicine, University of Toronto","keywords":"Intersection (aeronautics); Research ethics; Health equity; Identity (music); Face (sociological concept); Public health; Race (biology); Term (time); Economic Justice","score_opus":0.6285492534174396,"score_gpt":0.6622184640385838,"score_spread":0.03366921062114414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416202488","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":[0.49042365,0.011028906,0.001031747,0.49201623,0.0012112802,0.00020278028,0.0000017408839,0.0000039387746,0.004079712],"genre_scores_gemma":[0.97746956,0.007936569,0.005196802,0.008865448,0.00014763167,0.000001928389,2.9581025e-7,0.0000025805944,0.0003792075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9812925,0.014212154,0.0035710891,0.00013285855,0.0002676284,0.00052378053],"domain_scores_gemma":[0.9197285,0.07844617,0.0012430112,0.00012959477,0.00026834707,0.0001843514],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14706494,0.000048427668,0.0010248675,0.00016026966,0.00052717864,0.000008368488,0.0002722563,0.0001496528,0.000034784818],"category_scores_gemma":[0.17050949,0.00003135546,0.00011699337,0.00044678024,0.000675374,0.000085067,0.00014581777,0.0008767881,8.78254e-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":[0.000038350827,0.000020921807,0.55028045,0.00005109334,0.000004723876,0.0000013290473,0.0004974959,0.000043832886,7.569375e-8,0.43661603,0.0017016047,0.010744077],"study_design_scores_gemma":[0.000357462,0.00008899944,0.80568624,0.00043754638,0.000002794199,0.0000019042182,0.002712157,0.00028979662,6.639223e-8,0.15179291,0.03860716,0.0000229769],"about_ca_topic_score_codex":0.011011607,"about_ca_topic_score_gemma":0.0065995916,"teacher_disagreement_score":0.48704588,"about_ca_system_score_codex":0.00008730533,"about_ca_system_score_gemma":0.0015341513,"threshold_uncertainty_score":0.9955742},"labels":[],"label_agreement":null},{"id":"W4416204130","doi":"10.1016/j.jclinepi.2026.112342","title":"Frameworks to identify research gaps, frame research needs, and derive research priorities from evidence syntheses: a scoping review","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Élisabeth Bruyère Hospital; McMaster University; University of Toronto; University of Ottawa","funders":"","keywords":"Framing (construction); Systematic review; Certainty; Conceptual framework; Research methodology; Multimethodology; Evidence-based practice; Web of science","score_opus":0.9757534841213521,"score_gpt":0.8772634965267347,"score_spread":0.09848998759461736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416204130","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22944139,0.062432896,0.0058786925,0.69377595,0.002630131,0.0044220956,0.000032743945,0.000028941658,0.0013571542],"genre_scores_gemma":[0.34282744,0.4182756,0.027023237,0.20582007,0.004312215,0.00064410124,0.0000015261721,0.00005191945,0.0010439097],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.71233845,0.26443362,0.015192461,0.0011666426,0.0031727767,0.003696015],"domain_scores_gemma":[0.054012563,0.9311484,0.0021959085,0.0012648633,0.009600762,0.001777486],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5766636,0.0002247747,0.0032962644,0.002207626,0.0022233543,0.00006311053,0.0019364664,0.0014255292,0.00091699377],"category_scores_gemma":[0.9514227,0.00017689234,0.00026708812,0.0041314606,0.0025860039,0.00055199774,0.0020622225,0.02203723,0.00043001692],"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":[0.00077471964,0.000093739145,0.3282047,0.011972004,0.00010754138,0.000047976486,0.006351803,0.0000045449806,0.00008387674,0.015046427,0.6051774,0.032135308],"study_design_scores_gemma":[0.0005958407,0.0013054794,0.22476551,0.56122583,0.000035594283,0.000010499157,0.012454437,0.000050282833,0.000008318734,0.10297425,0.09635935,0.00021461431],"about_ca_topic_score_codex":0.0024494184,"about_ca_topic_score_gemma":0.00071887515,"teacher_disagreement_score":0.6667148,"about_ca_system_score_codex":0.0005590323,"about_ca_system_score_gemma":0.012637734,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4416273645","doi":"10.1016/j.jclinepi.2025.112051","title":"Identifying ethical issues in stepped-wedge cluster randomized trials to inform the Ottawa Statement update: a systematic review of trials published 2016–2022","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Western University; McMaster University; Dalhousie University; Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Statement (logic); Informed consent; Psychological intervention; Research ethics; Cluster (spacecraft); Ethical issues; Consolidated Standards of Reporting Trials; Alternative medicine","score_opus":0.7193184939498822,"score_gpt":0.7156016689576787,"score_spread":0.0037168249922034935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416273645","genre_codex":"commentary","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028646532,0.08472302,0.013840225,0.8819838,0.0036747733,0.011940225,0.000016307531,0.000015440673,0.00094153674],"genre_scores_gemma":[0.022559356,0.5919459,0.020300638,0.3563776,0.001935191,0.00082741806,0.000022749937,0.000063582884,0.005967609],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.19227533,0.58794737,0.20987302,0.0017208721,0.005978352,0.002205064],"domain_scores_gemma":[0.0051343082,0.9660787,0.022695167,0.0015478549,0.0038741,0.0006698507],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.92168665,0.00036583364,0.03342346,0.00075211516,0.00008354991,0.00004999952,0.001470768,0.0018672531,0.000851243],"category_scores_gemma":[0.9945066,0.00016922114,0.005064772,0.0011087869,0.0010280065,0.00019355767,0.000672549,0.0111999065,0.00006248328],"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":[0.15635316,0.00089437567,0.0036103202,0.36966822,0.0054851286,0.0000863224,0.0002822784,0.000030840223,0.000016456492,0.061614074,0.39949304,0.0024657939],"study_design_scores_gemma":[0.21234226,0.0017509144,0.0018792589,0.5259812,0.0056946515,0.000055330696,0.00034404692,0.00030014152,0.000027363632,0.23551776,0.01582326,0.00028381334],"about_ca_topic_score_codex":0.00008754904,"about_ca_topic_score_gemma":0.00010304549,"teacher_disagreement_score":0.5256062,"about_ca_system_score_codex":0.0002048178,"about_ca_system_score_gemma":0.0031454435,"threshold_uncertainty_score":0.9994285},"labels":[],"label_agreement":null},{"id":"W4416371050","doi":"10.1016/j.jclinepi.2026.112288","title":"The Inclusion and Intended Use of Prediction Models in Clinical Guidelines: A systematic review of five clinical domains in four countries","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"Predictive modelling; Guideline; Clinical Practice; MEDLINE; Model validation; Clinical trial","score_opus":0.505518106485441,"score_gpt":0.5805626626017145,"score_spread":0.07504455611627348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416371050","genre_codex":"empirical","genre_gemma":"review","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":[0.834856,0.098423034,0.0016231313,0.061733145,0.0014157165,0.0018509867,0.000021028409,0.000007296748,0.00006966427],"genre_scores_gemma":[0.48108685,0.50324357,0.003055452,0.012381519,0.00016471825,0.000022615333,0.0000029495523,0.000008746611,0.00003356396],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96574545,0.0098693045,0.023474744,0.00033127898,0.00032991637,0.00024928604],"domain_scores_gemma":[0.8199709,0.16937073,0.00820371,0.00065128895,0.0015699869,0.00023338474],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08414553,0.00018572914,0.006387294,0.00020011947,0.00004358001,0.000003497728,0.00022011595,0.00049333513,0.0000052340133],"category_scores_gemma":[0.38891715,0.000096208736,0.001056239,0.0002531909,0.0006475827,0.00010925785,0.0003160365,0.0010128206,6.900142e-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":[0.0018565829,0.0009930265,0.9628555,0.022004304,0.00066614844,0.000054834392,0.000043022676,0.00008919311,3.2012673e-7,0.0031139704,0.0056839576,0.002639122],"study_design_scores_gemma":[0.007355633,0.002957018,0.70435965,0.25137064,0.001574477,0.000095702504,0.000132083,0.013282296,0.0000011471942,0.018090514,0.00069832243,0.00008253058],"about_ca_topic_score_codex":0.000085688574,"about_ca_topic_score_gemma":0.000115762006,"teacher_disagreement_score":0.40482056,"about_ca_system_score_codex":0.00007722908,"about_ca_system_score_gemma":0.0005789036,"threshold_uncertainty_score":0.9430649},"labels":[],"label_agreement":null},{"id":"W4416409135","doi":"10.1016/j.jclinepi.2025.112069","title":"Guideline organizations' guidance documents paper 11: quality assurance and improvement in guideline development","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Guideline; Terminology; Quality assurance; Quality (philosophy); MEDLINE","score_opus":0.2776774704263029,"score_gpt":0.601123606897308,"score_spread":0.3234461364710051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416409135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6318734,0.0014485918,0.14379224,0.21951088,0.002137936,0.0007243354,0.0000075866433,0.000027564813,0.00047741504],"genre_scores_gemma":[0.48119703,0.001956715,0.39388973,0.121176206,0.00092079665,0.000014245423,0.000075023636,0.00003093486,0.0007393237],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9717202,0.0026844917,0.02423992,0.00052620075,0.00039716202,0.00043202227],"domain_scores_gemma":[0.9550428,0.033232782,0.007550114,0.0006297024,0.0030877152,0.00045690086],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06995044,0.00025934412,0.0026300251,0.0002522902,0.00006977505,0.000012389916,0.00024969113,0.0003562154,0.00037282406],"category_scores_gemma":[0.35985884,0.00020260434,0.00024707319,0.0005454899,0.00018994637,0.00031167886,0.00021145327,0.000918193,0.000012811603],"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":[0.00070459134,0.0005254115,0.8177921,0.0000759685,0.00019943125,0.00002501346,0.000028843666,0.00015293412,0.0003933407,0.0010409992,0.080679126,0.098382205],"study_design_scores_gemma":[0.0068059694,0.00043436346,0.6579351,0.00023972725,0.00013416991,0.00003815762,0.00013576291,0.0005203406,0.00007629058,0.00404468,0.32948902,0.00014644758],"about_ca_topic_score_codex":0.00026166893,"about_ca_topic_score_gemma":0.0006682852,"teacher_disagreement_score":0.2899084,"about_ca_system_score_codex":0.00020282304,"about_ca_system_score_gemma":0.0018599965,"threshold_uncertainty_score":0.9576817},"labels":[],"label_agreement":null},{"id":"W4416409230","doi":"10.1016/j.jclinepi.2025.112067","title":"Guideline organizations' guidance documents paper 8: considering equity","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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; University of Toronto","funders":"","keywords":"Guideline; Equity (law); MEDLINE; Public health","score_opus":0.46599812335676233,"score_gpt":0.6492065010764101,"score_spread":0.18320837771964776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416409230","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":[0.16810521,0.0025073213,0.3330084,0.47717413,0.008447373,0.00071637396,0.000010886818,0.00008230131,0.009947992],"genre_scores_gemma":[0.5848461,0.0021754522,0.21771023,0.19164257,0.0023684509,0.0000042946654,0.000027544718,0.00003168681,0.0011936683],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9809293,0.0027001468,0.015332956,0.00034627775,0.00031454265,0.00037677455],"domain_scores_gemma":[0.90651953,0.07986554,0.008139123,0.00080728956,0.004079601,0.00058891624],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04756375,0.00019117082,0.0024224133,0.00018135417,0.00007949446,0.00001232446,0.0002789346,0.0003623568,0.0011946985],"category_scores_gemma":[0.6182515,0.00014720262,0.0005284783,0.0004767143,0.0002611512,0.00032395753,0.00029484983,0.001192409,0.00006346985],"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":[0.000840897,0.00040725552,0.6205312,0.00006301082,0.0004886842,0.00006812398,0.0000125540655,0.00026258713,0.00029209856,0.005840368,0.3069972,0.06419604],"study_design_scores_gemma":[0.008394304,0.001108877,0.36322758,0.00044431075,0.0008924454,0.0003806174,0.0001505023,0.0014934697,0.00009279458,0.054640673,0.56897813,0.00019630736],"about_ca_topic_score_codex":0.000064549466,"about_ca_topic_score_gemma":0.000028704748,"teacher_disagreement_score":0.5706878,"about_ca_system_score_codex":0.00011560776,"about_ca_system_score_gemma":0.0015026759,"threshold_uncertainty_score":0.99971837},"labels":[],"label_agreement":null},{"id":"W4416416885","doi":"10.1016/j.jclinepi.2025.112065","title":"Guideline organizations’ guidance documents paper 3: contributions and authorship","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Guideline; Peer review; MEDLINE; Evidence-based medicine","score_opus":0.3228633073924097,"score_gpt":0.6276289485053183,"score_spread":0.30476564111290855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416416885","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":[0.17769825,0.002719417,0.24374183,0.57058513,0.0032403078,0.0004948316,0.000023860219,0.000039746752,0.0014565984],"genre_scores_gemma":[0.800473,0.0028596243,0.08399533,0.10961427,0.0017185933,0.000004937786,0.000048656235,0.000020100491,0.0012655213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9848907,0.0033814458,0.01094131,0.00029077692,0.0001999739,0.00029577618],"domain_scores_gemma":[0.91265243,0.07601865,0.0056700762,0.00054510316,0.0044171214,0.0006966139],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044518705,0.00015455308,0.0018917951,0.00016311597,0.00009334679,0.000010965568,0.00015687475,0.000413055,0.00045753605],"category_scores_gemma":[0.67126036,0.000116021605,0.00030984147,0.000427955,0.0002799248,0.00024896493,0.000110183544,0.0011483027,0.000024593093],"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":[0.00081656117,0.00033753135,0.71360314,0.000036146834,0.00040498032,0.000029233392,0.000015248013,0.000042759697,0.00018008058,0.02163166,0.23346204,0.029440593],"study_design_scores_gemma":[0.006206835,0.00082207855,0.55763507,0.00021317884,0.0007488513,0.00023552348,0.0000759499,0.0008819987,0.000026104131,0.067582786,0.36546078,0.00011083182],"about_ca_topic_score_codex":0.000049234157,"about_ca_topic_score_gemma":0.000020256835,"teacher_disagreement_score":0.62674165,"about_ca_system_score_codex":0.000074410396,"about_ca_system_score_gemma":0.00092115765,"threshold_uncertainty_score":0.9838691},"labels":[],"label_agreement":null},{"id":"W4416423996","doi":"10.1016/j.jclinepi.2025.112068","title":"Guideline organizations’ guidance documents paper 10: developing recommendations about diagnostic tests and strategies","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Guideline; Diagnostic test; Test (biology); Diagnostic accuracy; MEDLINE","score_opus":0.3298983066855122,"score_gpt":0.6153491820543529,"score_spread":0.2854508753688407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416423996","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":[0.11034049,0.0031873428,0.27478823,0.60527736,0.0032157763,0.0005983563,0.000014482873,0.00005320316,0.0025247775],"genre_scores_gemma":[0.40194795,0.017726474,0.45175037,0.12490135,0.001981494,0.000016320852,0.00012437654,0.000043014883,0.00150865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98685944,0.0020945328,0.010257829,0.00032152745,0.00018004389,0.00028661505],"domain_scores_gemma":[0.8261632,0.16423558,0.005378928,0.0004700272,0.0033735689,0.00037874424],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020962112,0.0001871622,0.0016270013,0.00018800884,0.0001177478,0.000027429278,0.00018015031,0.00027839013,0.0008432389],"category_scores_gemma":[0.6428833,0.00014656523,0.00020160172,0.0004632311,0.00021897149,0.00051355246,0.00013483694,0.00076615426,0.00003304046],"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":[0.00032382697,0.000257795,0.5938476,0.00007956983,0.00038592558,0.00002925795,0.000029230705,0.00013445683,0.000056346646,0.013280871,0.29779157,0.09378355],"study_design_scores_gemma":[0.0032408051,0.00048799094,0.62691665,0.00057157007,0.00042466552,0.00015286558,0.00028565372,0.00037777997,0.000007688418,0.032151874,0.33525223,0.0001302677],"about_ca_topic_score_codex":0.000058835973,"about_ca_topic_score_gemma":0.00007968553,"teacher_disagreement_score":0.6219212,"about_ca_system_score_codex":0.00008546359,"about_ca_system_score_gemma":0.001693078,"threshold_uncertainty_score":0.9232875},"labels":[],"label_agreement":null},{"id":"W4416425001","doi":"10.1016/j.jclinepi.2025.112063","title":"Guideline organizations' guidance documents paper 1: Introduction","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Checklist; Guideline; Sample (material); MEDLINE","score_opus":0.2744523502660621,"score_gpt":0.6056157137660814,"score_spread":0.3311633635000193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416425001","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":[0.07085607,0.0010701567,0.21694621,0.7003118,0.008729441,0.0003869713,0.0000040477494,0.000041530177,0.0016537609],"genre_scores_gemma":[0.39477396,0.0046059703,0.32409337,0.25052977,0.020542605,0.00000862383,0.000114998475,0.0000559185,0.0052747494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9825353,0.002784982,0.013784728,0.00034852055,0.0002643097,0.00028217337],"domain_scores_gemma":[0.953154,0.034399807,0.007027328,0.00072502176,0.004307243,0.00038658016],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03966739,0.00016618005,0.002000857,0.00021088646,0.00006580213,0.000008568267,0.00021509014,0.000335297,0.0014353076],"category_scores_gemma":[0.58302945,0.0001252545,0.00046140415,0.0006016607,0.0001965195,0.0003477334,0.000096286836,0.0010805964,0.000080658945],"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":[0.0009179936,0.00037607228,0.30425373,0.000029869432,0.0003227528,0.00001626322,0.000007427343,0.00021769099,0.00025662666,0.004456036,0.6335081,0.055637423],"study_design_scores_gemma":[0.004050632,0.0008156467,0.21898896,0.0000948369,0.0005175693,0.00019101509,0.00007302223,0.00060954114,0.00004686997,0.016279794,0.7582396,0.0000924743],"about_ca_topic_score_codex":0.000039440558,"about_ca_topic_score_gemma":0.000013051867,"teacher_disagreement_score":0.5433621,"about_ca_system_score_codex":0.0001046622,"about_ca_system_score_gemma":0.00092371687,"threshold_uncertainty_score":0.9994775},"labels":[],"label_agreement":null},{"id":"W4416425039","doi":"10.1016/j.jclinepi.2025.112064","title":"Guideline organizations’ guidance documents paper 6: adaptation of practice guidelines","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Adaptation (eye); Guideline; MEDLINE; Clinical Practice","score_opus":0.43613413090768705,"score_gpt":0.6401387195832835,"score_spread":0.20400458867559645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416425039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032372534,0.003264243,0.5206895,0.43696052,0.0038642755,0.0005475297,0.000011819242,0.00003243132,0.0022571716],"genre_scores_gemma":[0.12732902,0.0054556946,0.7172249,0.14712524,0.0019364594,0.000005234735,0.00005368538,0.000033094257,0.00083664176],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97083306,0.0038954166,0.024082072,0.00037522288,0.0005065689,0.00030764044],"domain_scores_gemma":[0.83913505,0.108512074,0.021050608,0.0009891985,0.02985251,0.0004605835],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058778252,0.00022065346,0.0025937448,0.00028132804,0.00005968059,0.00000770384,0.00031161978,0.0004095862,0.00047760273],"category_scores_gemma":[0.8645901,0.0001699576,0.0005843192,0.0008098279,0.00024344216,0.0006612262,0.00012474612,0.0009182008,0.000028475217],"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":[0.0037852898,0.0013422598,0.2114806,0.00014021936,0.0012617736,0.000053172225,0.000076474105,0.0048191957,0.00051095185,0.009229617,0.5435839,0.2237165],"study_design_scores_gemma":[0.008288391,0.0019951316,0.087787874,0.00060505257,0.0018061191,0.00030612262,0.0011146928,0.007431807,0.0000893093,0.011761242,0.8786285,0.0001857579],"about_ca_topic_score_codex":0.00026068513,"about_ca_topic_score_gemma":0.000034304398,"teacher_disagreement_score":0.8058118,"about_ca_system_score_codex":0.000085144515,"about_ca_system_score_gemma":0.0019791077,"threshold_uncertainty_score":0.9691859},"labels":[],"label_agreement":null},{"id":"W4416425046","doi":"10.1016/j.jclinepi.2025.112061","title":"Guideline organizations' guidance documents paper 5: conflict of interest and funding","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Guideline; Conflict of interest; MEDLINE; Public health","score_opus":0.5945935564959699,"score_gpt":0.6368657680910805,"score_spread":0.04227221159511063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416425046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74618876,0.0025141388,0.09130019,0.15556003,0.0026822921,0.0003810409,0.000009771783,0.00001883535,0.0013449093],"genre_scores_gemma":[0.9026558,0.0031930432,0.055983588,0.036941268,0.00073425245,0.0000014312031,0.000014416787,0.000015557176,0.00046065744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98599654,0.0017147296,0.011699103,0.00024021133,0.00013507964,0.00021433558],"domain_scores_gemma":[0.9365042,0.054126594,0.0063938685,0.0003909659,0.0022652324,0.00031914716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02832884,0.00013752571,0.0020098272,0.00018263508,0.000036851758,0.0000055075197,0.00016580695,0.00026012296,0.00041543742],"category_scores_gemma":[0.46692774,0.00010284415,0.00027376777,0.00031443746,0.0002932382,0.00021063614,0.00013991947,0.0007354271,0.000007320979],"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":[0.00106212,0.00028938026,0.8641389,0.000098987046,0.00045847608,0.000018117076,0.000025896848,0.000034083936,0.0007978806,0.008324258,0.08126688,0.04348501],"study_design_scores_gemma":[0.008449761,0.0019706748,0.6438701,0.0007649574,0.0008842054,0.0002462936,0.00031194874,0.0011460797,0.00014922043,0.014699218,0.32736212,0.00014537807],"about_ca_topic_score_codex":0.000060647595,"about_ca_topic_score_gemma":0.00002862285,"teacher_disagreement_score":0.4385989,"about_ca_system_score_codex":0.00004031196,"about_ca_system_score_gemma":0.00047783885,"threshold_uncertainty_score":0.98182666},"labels":[],"label_agreement":null},{"id":"W4416425138","doi":"10.1016/j.jclinepi.2025.112066","title":"Guideline organizations' guidance documents paper 9: co-operative approaches","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Guideline; Component (thermodynamics); MEDLINE; Public health","score_opus":0.49381093256135306,"score_gpt":0.6321981624542931,"score_spread":0.13838722989294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416425138","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":[0.1026059,0.0026524807,0.36427435,0.5069115,0.0047603543,0.0011005115,0.000023805767,0.00006849872,0.017602554],"genre_scores_gemma":[0.5631736,0.0020410724,0.24050784,0.1879308,0.0034530712,0.000012766687,0.00012485705,0.00004746798,0.002708514],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98121756,0.004037384,0.013719328,0.00039008015,0.00030085532,0.0003347612],"domain_scores_gemma":[0.93571734,0.054441895,0.006084722,0.0006475001,0.0026429866,0.00046556094],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038269855,0.000218484,0.0025047536,0.0001881539,0.00009127183,0.000012919983,0.0002846087,0.00039734304,0.0009912718],"category_scores_gemma":[0.46424997,0.00015628237,0.00052296184,0.0004715049,0.0003186405,0.00036535173,0.0001011712,0.0012526342,0.00008130287],"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":[0.001201798,0.0006924398,0.566819,0.000048517326,0.0007016243,0.000036931982,0.000039849583,0.00030328007,0.00012243826,0.008116318,0.3766915,0.0452263],"study_design_scores_gemma":[0.010024773,0.0018876771,0.37257135,0.00033583704,0.00095168507,0.00025818482,0.0005144938,0.0030835166,0.00013380751,0.025796048,0.58419836,0.0002442858],"about_ca_topic_score_codex":0.000028752562,"about_ca_topic_score_gemma":0.000012765016,"teacher_disagreement_score":0.4605677,"about_ca_system_score_codex":0.00010181034,"about_ca_system_score_gemma":0.0013618557,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4416543157","doi":"10.1016/j.jclinepi.2025.112086","title":"GRADE Guidance 44: strategies to enhance the utilization of randomized and non-randomized studies in evidence syntheses of health interventions","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Ottawa Hospital; Impact","funders":"","keywords":"Randomized controlled trial; Psychological intervention; Complement (music); MEDLINE; Evidence-based medicine; Evidence-based practice; Alternative medicine","score_opus":0.938704978188362,"score_gpt":0.7457919370234694,"score_spread":0.1929130411648926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416543157","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2422456,0.14697514,0.56291574,0.044906043,0.0010274495,0.0016800736,0.0000030120061,0.000001096066,0.00024587146],"genre_scores_gemma":[0.9662466,0.023173831,0.00936812,0.00087283115,0.00003914498,0.000031907908,8.30109e-8,0.0000024630856,0.0002649862],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3176758,0.52211285,0.15615636,0.0011002476,0.00247028,0.00048446265],"domain_scores_gemma":[0.05689348,0.88579637,0.053506546,0.0012820152,0.0024132677,0.00010830561],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7812727,0.00017469472,0.025641385,0.00045532963,0.000053861975,0.00003096112,0.001084912,0.00009837464,0.00009604194],"category_scores_gemma":[0.9499592,0.000064203196,0.0048876265,0.00075264333,0.0014135051,0.00019496355,0.00016098624,0.0003149472,0.000004173601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.22755274,0.0014721403,0.23951031,0.0073394035,0.014417934,0.0000095230935,0.012584496,0.015843445,0.000087581844,0.21107864,0.06634983,0.20375396],"study_design_scores_gemma":[0.12273954,0.0010058358,0.09186515,0.03995227,0.002464429,0.000020735497,0.014392651,0.017331924,0.000061062274,0.70842946,0.0014487698,0.00028816905],"about_ca_topic_score_codex":0.0000533631,"about_ca_topic_score_gemma":0.00013928238,"teacher_disagreement_score":0.72400105,"about_ca_system_score_codex":0.00001676462,"about_ca_system_score_gemma":0.0002912285,"threshold_uncertainty_score":0.988824},"labels":[],"label_agreement":null},{"id":"W4416572953","doi":"10.1016/j.jclinepi.2025.112085","title":"Guideline organizations’ guidance documents paper 4: interest-holder engagement","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Pharmaceutical industry and healthcare","field":"Pharmacology, Toxicology and Pharmaceutics","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 Saskatchewan","funders":"","keywords":"Guideline; MEDLINE; Public health","score_opus":0.7838259113493447,"score_gpt":0.7118573937824589,"score_spread":0.07196851756688571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416572953","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":[0.35823268,0.012086312,0.031601347,0.53420854,0.03623856,0.0010971186,0.00007082281,0.00015258443,0.026312074],"genre_scores_gemma":[0.7589677,0.0038977822,0.0051987185,0.22555433,0.0023421724,0.0000111160325,0.000014998618,0.000023200422,0.0039899847],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9776086,0.013837952,0.007353006,0.0003911627,0.00014668176,0.00066257454],"domain_scores_gemma":[0.97219384,0.023094662,0.0023313,0.00035182128,0.0012326164,0.00079574453],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.041464705,0.0002740057,0.0018079592,0.00018248148,0.00025412664,0.000010932646,0.0007539931,0.0013131814,0.0067722555],"category_scores_gemma":[0.07561406,0.00021521609,0.0004392323,0.00047798658,0.0004766655,0.00022541378,0.0002656894,0.005712037,0.00017312907],"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":[0.0009445871,0.0008189132,0.3580521,0.000092029295,0.00078785175,0.00009594305,0.00006183517,0.0007780304,0.00048814924,0.03914821,0.54730034,0.05143197],"study_design_scores_gemma":[0.0028398437,0.00034995598,0.037616726,0.00011146419,0.00028444975,0.00004292503,0.000074518975,0.0010170348,0.00039497484,0.021407893,0.9356919,0.0001683276],"about_ca_topic_score_codex":0.000011071389,"about_ca_topic_score_gemma":0.00001223461,"teacher_disagreement_score":0.40073502,"about_ca_system_score_codex":0.00008795241,"about_ca_system_score_gemma":0.0007007487,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W4416580955","doi":"10.1016/j.jclinepi.2025.112088","title":"The Risk of Bias in Vaccine Effectiveness (RoB-VE) project: introduction to a methodological initiative to improve risk-of-bias assessment and reporting in vaccine effectiveness research","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","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":"Bruyère; Public Health Agency of Canada; Dalhousie University; BC Children's Hospital; University of Ottawa; Canadian Institute for Advanced Research; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Guideline; Data collection; Reliability (semiconductor); Process (computing); Work (physics); External validity; Validity; Measure (data warehouse)","score_opus":0.5902029675872124,"score_gpt":0.6445591380839768,"score_spread":0.054356170496764444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416580955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97552156,0.00056441524,0.01013759,0.011227479,0.00096923835,0.0013947028,0.0000043531327,0.0000060866078,0.00017454295],"genre_scores_gemma":[0.98991597,0.00276832,0.0062711732,0.00017130915,0.00077655364,0.00006832938,6.0166906e-7,0.000009374454,0.000018352606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8421023,0.14764881,0.008354747,0.00071425375,0.00047612088,0.00070378534],"domain_scores_gemma":[0.6214045,0.36869004,0.0076899473,0.00041095784,0.0015934083,0.0002110836],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45958963,0.00019883455,0.0032306993,0.00069545966,0.0002716804,0.000018359033,0.00044090915,0.0004259984,0.0000088283705],"category_scores_gemma":[0.77940273,0.00012326112,0.00041045682,0.0017630167,0.00011218251,0.00016805546,0.0003287749,0.0023635998,7.380188e-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":[0.004164848,0.00029289577,0.94999975,0.00011205195,0.00018034298,0.00002311691,0.00082580926,0.0007251632,0.00024270033,0.0034382937,0.0003850545,0.039609972],"study_design_scores_gemma":[0.0017566441,0.0026455366,0.9462601,0.00045470943,0.00007587017,0.000005147443,0.0014634858,0.00012114355,0.00022781828,0.04640565,0.00048704125,0.00009686378],"about_ca_topic_score_codex":0.0030366625,"about_ca_topic_score_gemma":0.0030873264,"teacher_disagreement_score":0.31981307,"about_ca_system_score_codex":0.00032681043,"about_ca_system_score_gemma":0.0011103516,"threshold_uncertainty_score":0.999938},"labels":[],"label_agreement":null},{"id":"W4416642995","doi":"10.1016/j.jclinepi.2025.112089","title":"Methodological guidance for individual participant data meta-analyses: a systematic review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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","funders":"","keywords":"Observational study; Checklist; Set (abstract data type); Identification (biology); Guideline; Quality (philosophy); Forcing (mathematics); Observational methods in psychology","score_opus":0.9985771036472134,"score_gpt":0.8425318825246398,"score_spread":0.15604522112257357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416642995","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2712964e-8,0.8461591,0.14363945,0.0031116095,0.0016066058,0.004791952,0.0005500188,0.000004250186,0.00013701811],"genre_scores_gemma":[2.4088226e-7,0.8577132,0.13074389,0.007707912,0.00075836637,0.00048456574,0.0000974818,0.000028644776,0.0024657066],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.08227892,0.65137273,0.25680512,0.0032514003,0.005360015,0.0009318304],"domain_scores_gemma":[0.0074666548,0.7363753,0.23604487,0.0152389575,0.0041158884,0.0007583474],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.9602397,0.0015607921,0.29471952,0.0010240419,0.00015206693,0.00029606995,0.025051879,0.0015858148,0.0036617743],"category_scores_gemma":[0.9936827,0.0005037224,0.10882897,0.0025768764,0.00042572495,0.0003459747,0.0020612495,0.0026493038,0.00070200046],"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":[0.000008779714,0.00010907265,0.000008860293,0.5501724,0.0812319,0.000019107505,0.0000036287488,0.000005528882,1.3974933e-9,0.0011369706,0.29909256,0.0682112],"study_design_scores_gemma":[0.000095822834,0.00014567588,0.0000030812685,0.14086737,0.3814532,0.00012568587,0.000009534606,0.00010905459,1.4296563e-9,0.006224383,0.4707642,0.00020199684],"about_ca_topic_score_codex":0.0000023141533,"about_ca_topic_score_gemma":0.0000052543587,"teacher_disagreement_score":0.40930504,"about_ca_system_score_codex":0.00003481382,"about_ca_system_score_gemma":0.00222233,"threshold_uncertainty_score":0.99974144},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"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":"high"}],"label_agreement":"split"},{"id":"W4416683217","doi":"10.1016/j.jclinepi.2025.112090","title":"The many roles of decision thresholds for primary research, evidence synthesis, and health decision-making","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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; Canadian Journal of Communication (Canada)","funders":"","keywords":"Transparency (behavior); Sample (material); Focus (optics); Decision analysis; Decision aids; Decision process; Decision rule; MEDLINE","score_opus":0.7918676551576369,"score_gpt":0.6747839378775028,"score_spread":0.11708371728013411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416683217","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2558218,0.11963117,0.25352225,0.36704713,0.00250867,0.00095675985,0.000046437453,0.000008414481,0.0004573873],"genre_scores_gemma":[0.83477455,0.05039608,0.086595766,0.027227266,0.00085857214,0.0000453989,6.532805e-7,0.00002146742,0.00008025652],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9663316,0.007046628,0.025224013,0.00056029076,0.00018889781,0.0006485735],"domain_scores_gemma":[0.3013337,0.68415684,0.01308361,0.00065229693,0.0005164639,0.00025709748],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.514484,0.00013324656,0.0035267037,0.0004295676,0.00039050746,0.000029435309,0.0007143348,0.00031038612,0.000019269779],"category_scores_gemma":[0.66818553,0.00010394575,0.00048253845,0.00020267315,0.0005085513,0.00025952887,0.00019126546,0.00071750203,0.000016477541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008021251,0.000104473074,0.41135362,0.00043381986,0.00015651529,9.798081e-7,0.00010745031,0.00022114952,3.23268e-7,0.29163975,0.10604343,0.18913637],"study_design_scores_gemma":[0.00044168113,0.00040252096,0.3892374,0.0021567198,0.000009095286,0.000011024795,0.00021353512,0.0021908784,3.7417024e-7,0.5653305,0.039937448,0.00006878945],"about_ca_topic_score_codex":0.00005754469,"about_ca_topic_score_gemma":0.00013561237,"teacher_disagreement_score":0.6771102,"about_ca_system_score_codex":0.0002909035,"about_ca_system_score_gemma":0.0009860201,"threshold_uncertainty_score":0.4999409},"labels":[],"label_agreement":null},{"id":"W4417068344","doi":"10.1016/j.jclinepi.2026.112306","title":"When and how to establish a new reference standard for medical tests: a scoping review identifying methodological priorities","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","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":"Reference data; Test (biology); Workflow; Gold standard (test); Guideline; Reference model; Reference values; Health care","score_opus":0.8169739210829675,"score_gpt":0.6993830391793203,"score_spread":0.1175908819036472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417068344","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":[0.0000032891114,0.8747188,0.0291815,0.09228139,0.0012624617,0.0024044618,0.000057370085,0.00002185801,0.00006887932],"genre_scores_gemma":[3.469311e-7,0.84747124,0.11596493,0.033330567,0.0027273586,0.000057131845,0.000014379129,0.00002900156,0.00040502977],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96175635,0.022859504,0.012963084,0.0009894765,0.00074440235,0.0006872059],"domain_scores_gemma":[0.13364324,0.8430714,0.016224595,0.0011928091,0.0022564991,0.003611471],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1647331,0.00057536154,0.024688128,0.00027688188,0.00009101968,0.00006575404,0.00068616023,0.0019986578,0.00026385454],"category_scores_gemma":[0.9160606,0.0003551945,0.002693877,0.0003563717,0.00034533307,0.00022363315,0.00039763274,0.004280959,0.0000053521408],"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":[0.0006590904,0.00006446634,0.00024765378,0.15896507,0.0005417798,0.00008643283,0.000006817291,3.0108332e-8,2.0397698e-8,0.0013883275,0.03544659,0.8025937],"study_design_scores_gemma":[0.0012152208,0.0017491272,0.00005064888,0.41021824,0.003465346,0.00024496595,0.000008699726,0.0000014074199,8.49536e-9,0.001813376,0.58106107,0.00017190151],"about_ca_topic_score_codex":0.000012552095,"about_ca_topic_score_gemma":0.000043839314,"teacher_disagreement_score":0.8281131,"about_ca_system_score_codex":0.00010236494,"about_ca_system_score_gemma":0.0109612215,"threshold_uncertainty_score":0.99989},"labels":[],"label_agreement":null},{"id":"W4417185206","doi":"10.1016/j.jclinepi.2025.112099","title":"A decision algorithm for assessing indirectness in core GRADE","year":2025,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","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":"Core (optical fiber); Decision aids; MEDLINE; Decision theory; Decision support system","score_opus":0.48275410352632575,"score_gpt":0.569952786167713,"score_spread":0.0871986826413873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417185206","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006422958,0.00082421355,0.8159814,0.17188025,0.01100821,0.00017093582,0.0000054887946,0.00005488673,0.000010381374],"genre_scores_gemma":[0.000007735845,0.00041451145,0.7995354,0.19672877,0.0031727487,0.000012498016,0.000005062113,0.00001955206,0.00010374693],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986805,0.0050680228,0.0063940203,0.0007130456,0.00030156004,0.00071835465],"domain_scores_gemma":[0.6702087,0.32526276,0.0035666043,0.00055869186,0.00030973012,0.00009352888],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.042557817,0.00037614958,0.0048222234,0.00072174665,0.0000493491,0.000034261102,0.0023605619,0.0022807966,0.000002276381],"category_scores_gemma":[0.30929986,0.00029353326,0.0011073425,0.00045413175,0.00018141196,0.00037125914,0.00040568,0.0063308403,0.0000018929052],"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":[0.000016826183,0.00003809482,0.0012489932,0.00008390548,0.000072575334,0.0004477248,0.000011733032,0.005511606,3.8437594e-7,0.00026903738,0.31872386,0.6735753],"study_design_scores_gemma":[0.001461781,0.00041356,0.007990065,0.0013453537,0.000053556338,0.0002471689,0.0000043152463,0.03698373,0.0000034817092,0.5438748,0.40720183,0.00042038888],"about_ca_topic_score_codex":0.0000036578301,"about_ca_topic_score_gemma":0.000001183607,"teacher_disagreement_score":0.6731549,"about_ca_system_score_codex":0.0001418514,"about_ca_system_score_gemma":0.00067887385,"threshold_uncertainty_score":0.99995166},"labels":[],"label_agreement":null},{"id":"W4417274408","doi":"10.1016/j.jclinepi.2025.112098","title":"Participant diversity and inclusive trial design: a meta-epidemiologic study of Canadian randomized clinical trials","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; Sinai Health System; McGill University Health Centre; Ottawa Hospital; Bruyère; University of Ottawa; University of Alberta; McGill University; University of Calgary","funders":"","keywords":"Clinical trial; Ethnic group; Diversity (politics); Alternative medicine; Race (biology); Randomized controlled trial","score_opus":0.9702195413321656,"score_gpt":0.758053697684673,"score_spread":0.21216584364749258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417274408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91002476,0.0032684228,0.0077724424,0.07074627,0.0031063447,0.0045957924,0.000009820521,0.000013805981,0.0004623433],"genre_scores_gemma":[0.9647259,0.014381172,0.0082920985,0.011240703,0.0010176684,0.000044608583,0.0000012388763,0.000013745707,0.00028282567],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.3582294,0.5643111,0.07192578,0.001868294,0.0018171947,0.0018482493],"domain_scores_gemma":[0.009851329,0.97322416,0.01173907,0.0008903721,0.0023597246,0.0019353164],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.8307718,0.00036607718,0.029802157,0.0011116607,0.0003635562,0.000007435038,0.0007911798,0.0021286625,0.00020385244],"category_scores_gemma":[0.9844154,0.00020288372,0.005642367,0.0006812687,0.0030704038,0.00008104194,0.0015298793,0.0073229033,0.00000518968],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7408927,0.002543244,0.21955933,0.00009379149,0.019623812,0.00022410038,0.00027923324,0.000080580496,9.884095e-7,0.009574591,0.0034963645,0.0036312428],"study_design_scores_gemma":[0.64835507,0.021800034,0.07478151,0.00023585734,0.024356984,0.000027806822,0.0007194779,0.0008354845,0.0000018976998,0.22799847,0.00071988674,0.00016750724],"about_ca_topic_score_codex":0.015291708,"about_ca_topic_score_gemma":0.010046412,"teacher_disagreement_score":0.4089131,"about_ca_system_score_codex":0.000089796915,"about_ca_system_score_gemma":0.004416919,"threshold_uncertainty_score":0.99964267},"labels":[],"label_agreement":null},{"id":"W4417279895","doi":"10.1016/j.jclinepi.2025.112103","title":"Defining racial health equity: an integrative analysis of terminology and conceptualizations","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Racial and Ethnic Identity Research","field":"Social Sciences","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":"Bruyère; University of Ottawa","funders":"Colorado Clinical and Translational Sciences Institute; National Center for Advancing Translational Sciences; National Institutes of Health; Robert Wood Johnson Foundation","keywords":"Terminology; Health equity; Race and health; Psychological intervention; Ethnic group; Equity (law); Health care; Race (biology)","score_opus":0.4263743454708638,"score_gpt":0.6706752670592582,"score_spread":0.2443009215883944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417279895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8652239,0.0058353795,0.040770337,0.068694934,0.0021851487,0.0002560964,0.00002979869,0.000019833487,0.01698462],"genre_scores_gemma":[0.9899564,0.0048326557,0.001645611,0.0028827714,0.00024857957,0.0000013614481,0.0000049666696,0.0000025619784,0.00042513866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9854229,0.01100694,0.0028589608,0.00018431929,0.00019994495,0.00032690624],"domain_scores_gemma":[0.97693056,0.020320434,0.0018829496,0.00012351987,0.00048231127,0.00026021444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037540317,0.00007350741,0.0020305477,0.0004816881,0.00027223444,0.000012744701,0.00035233388,0.00028247733,0.00010699173],"category_scores_gemma":[0.10688653,0.000056220375,0.00039652726,0.00087211496,0.0020466705,0.00017762308,0.00012892544,0.00059659465,0.0000013763604],"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":[0.00010182231,0.00011151338,0.36925146,0.000008899646,0.00057993346,0.0000027289166,0.004907007,0.000060856695,0.0000016740157,0.49654883,0.0011614504,0.12726381],"study_design_scores_gemma":[0.00094197463,0.0014554218,0.78534544,0.00012641979,0.000682498,0.0000029830912,0.014794053,0.001688393,0.00000256996,0.16653001,0.028297959,0.00013227818],"about_ca_topic_score_codex":0.0026941062,"about_ca_topic_score_gemma":0.014912948,"teacher_disagreement_score":0.41609398,"about_ca_system_score_codex":0.00005698474,"about_ca_system_score_gemma":0.0016994528,"threshold_uncertainty_score":0.9910548},"labels":[],"label_agreement":null},{"id":"W4417410410","doi":"10.1016/j.jclinepi.2025.112110","title":"A semi-automated approach facilitated the assessment of the certainty of evidence in a network meta-analysis: Part 2 – Indirect and Mixed comparisons","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Mental Health Research Topics","field":"Psychology","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; Public Health Ontario; University of Toronto; University of Ottawa; Ottawa Hospital; Impact; University of Calgary; Alberta Bone and Joint Health Institute","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research; Australia and New Zealand Musculoskeletal Clinical Trials Network","keywords":"Certainty; Work (physics)","score_opus":0.840758906716416,"score_gpt":0.6656223695411599,"score_spread":0.175136537175256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417410410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88506305,0.022067277,0.00873263,0.077608675,0.002003039,0.0018502896,0.000059366314,0.00002741544,0.0025882677],"genre_scores_gemma":[0.994779,0.00052190264,0.002207154,0.0021311217,0.000059694175,0.000037781483,0.0000022588183,0.000005060333,0.0002560075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9464196,0.04575829,0.0066380887,0.00034502047,0.00034879573,0.0004902185],"domain_scores_gemma":[0.9149152,0.08032037,0.0036665278,0.00067102764,0.00027734725,0.00014950507],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07996523,0.00017450815,0.0048283185,0.00021758447,0.00007506212,0.0000044166613,0.0007744978,0.00043454804,0.00015071918],"category_scores_gemma":[0.031062366,0.00007679139,0.0014971831,0.0013578384,0.00089487404,0.00003636029,0.00024517055,0.0022041013,8.614608e-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":[0.00042498662,0.0004400073,0.9274529,0.00012714342,0.028995553,0.000004423692,0.00015721472,0.011004067,0.0000016120008,0.0034173003,0.027007006,0.00096774753],"study_design_scores_gemma":[0.0007373255,0.00038230573,0.9546719,0.00007992079,0.00886406,0.000009460161,0.00034514855,0.030944837,0.000001614538,0.0017359594,0.0021709832,0.00005644337],"about_ca_topic_score_codex":0.00041379634,"about_ca_topic_score_gemma":0.00033982212,"teacher_disagreement_score":0.109715976,"about_ca_system_score_codex":0.00005520873,"about_ca_system_score_gemma":0.000434206,"threshold_uncertainty_score":0.9770994},"labels":[],"label_agreement":null},{"id":"W4417467068","doi":"10.1016/j.jclinepi.2025.112109","title":"A semi-automated approach facilitated the assessment of the certainty of evidence in a network meta-analysis: Part 1 – Direct comparisons","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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; Public Health Ontario; University of Toronto; University of Ottawa; Ottawa Hospital; Impact; University of Calgary; Alberta Bone and Joint Health Institute","funders":"Canadian Institutes of Health Research; Australia and New Zealand Musculoskeletal Clinical Trials Network; National Health and Medical Research Council; Hospital Research Foundation","keywords":"Certainty; Decision aids; Clinical judgment; MEDLINE; Decision theory; Expert system","score_opus":0.9707319188783519,"score_gpt":0.7110557379960946,"score_spread":0.2596761808822573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417467068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22050078,0.05864943,0.52339834,0.17218964,0.0040777004,0.00500238,0.00013022083,0.000025596288,0.016025918],"genre_scores_gemma":[0.9880051,0.00028666778,0.00866597,0.0020575405,0.00005688269,0.000024786383,0.0000011857533,0.0000038467747,0.0008980298],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5102662,0.39825553,0.08599051,0.0011054378,0.0038132232,0.00056911825],"domain_scores_gemma":[0.42125884,0.5086574,0.062047888,0.0048717177,0.002973252,0.000190907],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.70302606,0.000310612,0.028947698,0.00042638805,0.0000925919,0.000043615106,0.003926111,0.00035418398,0.0008758981],"category_scores_gemma":[0.598795,0.000086885484,0.021350663,0.005715302,0.00062980864,0.000093352784,0.00035264366,0.0013891024,0.000008469082],"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":[0.000035669396,0.0001648007,0.60474646,0.000036626374,0.04812911,9.0181493e-7,0.000046203233,0.23610778,0.0000010329965,0.001896958,0.10857519,0.00025929091],"study_design_scores_gemma":[0.000214105,0.000095596006,0.5295229,0.00007614178,0.057674736,0.000003868687,0.00026460373,0.39453232,5.9389396e-7,0.005330546,0.012212258,0.00007233742],"about_ca_topic_score_codex":0.000083649495,"about_ca_topic_score_gemma":0.00017374041,"teacher_disagreement_score":0.76750433,"about_ca_system_score_codex":0.00003416704,"about_ca_system_score_gemma":0.0005221234,"threshold_uncertainty_score":0.9884503},"labels":[],"label_agreement":null},{"id":"W4417505513","doi":"10.1016/j.jclinepi.2025.112117","title":"Sequential sample size calculations and learning curves safeguard the robust development of a clinical prediction model for individuals","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","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":"National Institute for Health and Care Research; Engineering and Physical Sciences Research Council; Department of Health and Social Care; Medical Research Council; Birmingham Biomedical Research Centre; University Hospitals Birmingham NHS Foundation Trust","keywords":"Sample size determination; Safeguard; Sample (material); Large sample; Predictive modelling; Early stopping","score_opus":0.3581055674125369,"score_gpt":0.5342643376275771,"score_spread":0.17615877021504017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417505513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07624114,0.0005353691,0.896749,0.02517006,0.0009885023,0.0002496868,0.000007890455,0.000019120926,0.000039224986],"genre_scores_gemma":[0.29515994,0.0005467499,0.7005891,0.0032644782,0.00032787814,0.000012375388,0.0000036218883,0.0000068474806,0.00008901241],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98545104,0.007108833,0.0065794135,0.00034617446,0.00022715745,0.00028739648],"domain_scores_gemma":[0.7659158,0.22701646,0.0055408673,0.0004675915,0.0007943091,0.00026497932],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0643865,0.00013408747,0.0015289008,0.00009495077,0.00028910817,0.000014111016,0.00065396505,0.0003213304,0.0000068072136],"category_scores_gemma":[0.3108932,0.00008951235,0.00045089485,0.00018765502,0.00025791166,0.00014775257,0.00030159924,0.0016757456,4.8345265e-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":[0.0000847225,0.000085058324,0.78732204,0.00016242993,0.00019512886,5.290727e-7,0.00029389528,0.12328248,0.0000013070284,0.011994381,0.0019256545,0.074652396],"study_design_scores_gemma":[0.00064093375,0.00024888953,0.37221983,0.00021466787,0.000045426354,0.0000086674945,0.000016354823,0.60817343,7.145749e-7,0.013205693,0.0051751784,0.0000502136],"about_ca_topic_score_codex":0.00002762699,"about_ca_topic_score_gemma":0.000026354379,"teacher_disagreement_score":0.48489097,"about_ca_system_score_codex":0.000025844018,"about_ca_system_score_gemma":0.0012418074,"threshold_uncertainty_score":0.963411},"labels":[],"label_agreement":null},{"id":"W4417516132","doi":"10.1016/j.jclinepi.2025.112115","title":"The use of guidelines in multimorbidity-related practice: an exploratory questionnaire survey","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Chronic Disease Management Strategies","field":"Medicine","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":"Sample (material); Exploratory research; Questionnaire; MEDLINE; Computer-assisted web interviewing; Public health","score_opus":0.5984144356554614,"score_gpt":0.6065106305834982,"score_spread":0.008096194928036815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417516132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.898004,0.006475844,0.0033024824,0.08707128,0.003984962,0.00049512816,0.0000079901665,0.000029592498,0.0006287015],"genre_scores_gemma":[0.9737499,0.011589549,0.0059023695,0.007803139,0.00038593623,0.0000057650923,0.0000128745505,0.000016176635,0.00053432566],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9820201,0.011045615,0.006264015,0.00022236459,0.00020367056,0.0002442506],"domain_scores_gemma":[0.9351624,0.059007287,0.003454437,0.000553517,0.0016224829,0.00019986606],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05080334,0.0001344648,0.0015451651,0.00017755968,0.000044456112,0.000010120826,0.00024518557,0.00025561245,0.000024603865],"category_scores_gemma":[0.5100081,0.00008256816,0.00033204642,0.0003078859,0.00050133385,0.00038535916,0.000088253146,0.00091408874,0.000004476151],"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":[0.0030784495,0.0008371969,0.88353235,0.000093696224,0.0005463109,0.00012751212,0.000032536977,0.0033296335,0.0000049115633,0.009543224,0.059731405,0.039142802],"study_design_scores_gemma":[0.0025948565,0.0006192627,0.94102633,0.0006008984,0.0002159892,0.000019107,0.00018731022,0.0057000304,0.000001234853,0.003922769,0.045049056,0.000063127045],"about_ca_topic_score_codex":0.0003634156,"about_ca_topic_score_gemma":0.0005754836,"teacher_disagreement_score":0.45920473,"about_ca_system_score_codex":0.000066175024,"about_ca_system_score_gemma":0.0010549171,"threshold_uncertainty_score":0.9773977},"labels":[],"label_agreement":null},{"id":"W600840809","doi":"10.1016/j.jclinepi.2015.06.005","title":"ROBIS: A new tool to assess risk of bias in systematic reviews was developed","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2208,"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 Population and Public Health","funders":"Monash University; Medical Research Council; National Institute for Health and Care Research; University of Alberta; Johns Hopkins University","keywords":"Systematic review; Psychological intervention; Relevance (law); Selection bias; Identification (biology); Scope (computer science); Psychology; Guideline; Medicine; MEDLINE; Process (computing); Risk analysis (engineering); Applied psychology; Computer science; Pathology; Nursing","score_opus":0.9813208922076017,"score_gpt":0.7157097203841251,"score_spread":0.2656111718234766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W600840809","genre_codex":"empirical","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6005988,0.01723371,0.36151147,0.011083175,0.003997977,0.0035017242,0.0000075994026,0.000004036628,0.0020614902],"genre_scores_gemma":[0.38584313,0.0048355963,0.58881176,0.010256503,0.0016978455,0.00006720743,0.0000018776038,0.000044331387,0.008441754],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.3510628,0.4586889,0.18403058,0.0011609807,0.0044175326,0.00063916075],"domain_scores_gemma":[0.120536946,0.6677082,0.19673103,0.0062377923,0.0066320044,0.002154018],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8870792,0.00035526793,0.036526643,0.0007207837,0.00002555635,0.00007284378,0.0029623252,0.00035500078,0.00072991167],"category_scores_gemma":[0.98310506,0.00014071907,0.0060850102,0.0017779057,0.00008809088,0.00025256068,0.00022705054,0.0008800606,0.0018893289],"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":[0.00011282854,0.00016022043,0.65412813,0.0012508634,0.00049127464,0.000022253147,0.00034379947,0.0015159535,0.0000021341316,0.0014491249,0.3179352,0.02258822],"study_design_scores_gemma":[0.0034083882,0.002042138,0.40108848,0.013266859,0.00235985,0.00035936022,0.0012861956,0.008261728,0.000004684225,0.12755346,0.43962708,0.0007417812],"about_ca_topic_score_codex":0.00004751016,"about_ca_topic_score_gemma":0.00012524864,"teacher_disagreement_score":0.25303966,"about_ca_system_score_codex":0.00006249338,"about_ca_system_score_gemma":0.0009752564,"threshold_uncertainty_score":0.99888784},"labels":[],"label_agreement":null},{"id":"W656140997","doi":"10.1016/j.jclinepi.2015.05.001","title":"Clinical practice guidelines were adapted and implemented meeting country-specific requirements—the example of Kazakhstan","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","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 Calgary; Alberta Health Services; Canadian Society for International Health; McMaster University; University of Ottawa","funders":"","keywords":"Process (computing); Adaptation (eye); General partnership; Process management; Christian ministry; Quality (philosophy); Prioritization; Medicine; Capacity building; Scale (ratio); Medical education; Business; Political science; Computer science; Psychology; Geography","score_opus":0.8134892117267929,"score_gpt":0.6656222216379869,"score_spread":0.147866990088806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W656140997","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":[0.5852853,0.010019203,0.02859763,0.3648276,0.0072417418,0.0015403889,0.00005418469,0.000059801227,0.0023741147],"genre_scores_gemma":[0.43578306,0.024009641,0.4432913,0.085361324,0.011157447,0.000012860489,0.00009388326,0.000112879716,0.00017760113],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9572391,0.011015229,0.029367656,0.0006466854,0.0011164893,0.00061484124],"domain_scores_gemma":[0.7189813,0.23659842,0.028905699,0.0013687571,0.012595217,0.0015505891],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20466109,0.00031292706,0.0036794138,0.00014247095,0.00009625484,0.000016898905,0.0004185688,0.0004850106,0.00014599854],"category_scores_gemma":[0.7227761,0.0001996415,0.00071829185,0.00031667046,0.00078502024,0.00047957228,0.00029094247,0.0019306944,0.000015164086],"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":[0.009828034,0.001009865,0.4414189,0.000068008216,0.0012348897,0.00012829337,0.0001267282,0.000059658683,0.00009717578,0.0049584024,0.39378375,0.14728631],"study_design_scores_gemma":[0.0105595095,0.005205629,0.07587454,0.0002796905,0.001040989,0.00088501564,0.0030216894,0.0011319461,0.000008262897,0.0029697313,0.89884305,0.00017994258],"about_ca_topic_score_codex":0.00069077883,"about_ca_topic_score_gemma":0.00009449086,"teacher_disagreement_score":0.518115,"about_ca_system_score_codex":0.000088413355,"about_ca_system_score_gemma":0.0011958508,"threshold_uncertainty_score":0.8388014},"labels":[],"label_agreement":null},{"id":"W7117365583","doi":"10.1016/j.jclinepi.2025.112120","title":"An imputation study shows that missing outcome data can substantially bias pooled estimates in systematic reviews of patient-reported outcomes","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"National Natural Science Foundation of China","keywords":"Missing data; Imputation (statistics); Systematic review; Outcome (game theory); Meta-analysis; Systematic error","score_opus":0.9408736266434724,"score_gpt":0.6979426045741942,"score_spread":0.2429310220692782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117365583","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":[0.9490977,0.0027342425,0.041033864,0.003108583,0.001543127,0.002372432,0.0000119087335,0.0000038988087,0.00009425037],"genre_scores_gemma":[0.97720575,0.00013361718,0.02116487,0.0013254894,0.000047665522,0.00001219033,0.0000083927325,0.000010576218,0.00009142305],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.61061275,0.2309376,0.15314004,0.0015153994,0.0032869442,0.00050724257],"domain_scores_gemma":[0.2680354,0.51609814,0.19984461,0.011821638,0.0035526557,0.00064754084],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.70182914,0.00042518292,0.03154685,0.00097580085,0.00007117617,0.00015131582,0.003673386,0.00026863077,0.00037585158],"category_scores_gemma":[0.8940713,0.00018120033,0.0032948898,0.001235118,0.00014708009,0.00047437818,0.0002861465,0.00067689316,0.000025389796],"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":[0.00004484694,0.00051134865,0.98444057,0.0010477654,0.00079477474,0.000036569974,0.00021162246,0.00045500288,0.000005114121,0.00014457278,0.00093488186,0.011372959],"study_design_scores_gemma":[0.001156048,0.0005430635,0.94922286,0.0018957243,0.0026268612,0.000038856357,0.0017332712,0.029861277,0.0000017818764,0.012429021,0.0003004754,0.0001907321],"about_ca_topic_score_codex":0.000092813694,"about_ca_topic_score_gemma":0.0005605961,"teacher_disagreement_score":0.34257737,"about_ca_system_score_codex":0.000045279103,"about_ca_system_score_gemma":0.0003699065,"threshold_uncertainty_score":0.9828308},"labels":[],"label_agreement":null},{"id":"W7117368100","doi":"10.1016/j.jclinepi.2025.112121","title":"Systematic reviews of quasi-experimental studies: challenges and considerations","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Systematic review; Preprint; Consistency (knowledge bases); Variety (cybernetics); Transparency (behavior); Grey literature; MEDLINE; Protocol (science); Identification (biology); Comparability","score_opus":0.9664743422323613,"score_gpt":0.7342298440974422,"score_spread":0.2322444981349191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117368100","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051501077,0.8969989,0.010957228,0.032559026,0.0025021564,0.001398182,0.000002626174,0.0000020768996,0.004078732],"genre_scores_gemma":[0.85831285,0.11083207,0.02469429,0.0045745936,0.0002920986,0.000035727266,2.2806839e-7,0.000006986292,0.0012511598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5701527,0.29362932,0.13313125,0.00093481335,0.0018275912,0.00032434775],"domain_scores_gemma":[0.23717219,0.6895519,0.06778111,0.0023308473,0.0029039234,0.00026001988],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6651582,0.00021743396,0.02824038,0.0003361355,0.00006373704,0.000028085147,0.0006731523,0.00018141649,0.0006333097],"category_scores_gemma":[0.9228594,0.00008648804,0.0039576967,0.00025434679,0.00038246316,0.00012669753,0.00013910608,0.00036129932,0.000087114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093531264,0.0016960436,0.043838017,0.024227295,0.008886334,0.000031280248,0.002804486,0.00006265313,0.000046119556,0.62067586,0.27387816,0.023760233],"study_design_scores_gemma":[0.0018934703,0.0029226216,0.027832493,0.015068934,0.0032703697,0.00035983912,0.014155797,0.002466925,0.00002360819,0.86502826,0.06660215,0.0003755277],"about_ca_topic_score_codex":9.722763e-7,"about_ca_topic_score_gemma":0.000007756372,"teacher_disagreement_score":0.80681175,"about_ca_system_score_codex":0.00001705018,"about_ca_system_score_gemma":0.00012482623,"threshold_uncertainty_score":0.9861864},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"systematic_review","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W946614547","doi":"10.1016/j.jclinepi.2015.07.006","title":"Competing risk bias was common in Kaplan–Meier risk estimates published in prominent medical journals","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":137,"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; Ottawa Hospital; Alberta Innovates; University of Ottawa","funders":"","keywords":"Survival analysis; Publication bias; Medicine; Relative risk; Proportional hazards model; Demography; Psychology; Meta-analysis; Internal medicine; Confidence interval","score_opus":0.9362520028653889,"score_gpt":0.6896696056469209,"score_spread":0.24658239721846797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W946614547","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":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96321356,0.004114566,0.0063178106,0.022894021,0.0018372666,0.00033445552,0.00000783197,0.0000031291422,0.001277363],"genre_scores_gemma":[0.9700639,0.0015402897,0.025103867,0.0021586572,0.0009793548,0.000007552144,0.0000027807248,0.00001745094,0.00012614252],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.50899214,0.34937093,0.13044089,0.0014507729,0.008626074,0.0011191817],"domain_scores_gemma":[0.11315061,0.73905313,0.13688953,0.0037270403,0.0040505687,0.0031291267],"candidate_categories":["metaresearch","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8992546,0.0004086806,0.020591117,0.0012001544,0.00007355562,0.00028248673,0.0034670718,0.0007397369,0.0053523215],"category_scores_gemma":[0.9747352,0.0001790297,0.0037957912,0.0014937144,0.00035368634,0.00053447275,0.00038255265,0.004193368,0.0005331541],"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":[0.00012766403,0.000226575,0.9217629,0.000011206183,0.00018920073,0.0001504232,0.0001962843,0.0017932464,2.9331272e-7,0.00016588643,0.04281035,0.032565992],"study_design_scores_gemma":[0.0021026162,0.00040648188,0.7983411,0.0003580141,0.00019500879,0.0003260854,0.0005653405,0.083303854,6.9871237e-7,0.09545305,0.018771665,0.00017608619],"about_ca_topic_score_codex":0.00024229825,"about_ca_topic_score_gemma":0.0008333332,"teacher_disagreement_score":0.39584154,"about_ca_system_score_codex":0.00009399198,"about_ca_system_score_gemma":0.00070526515,"threshold_uncertainty_score":0.998104},"labels":[],"label_agreement":null},{"id":"W98805395","doi":"10.1016/s0895-4356(00)00211-0","title":"Construction of the Patient-Oriented Prostate Utility Scale (PORPUS)","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":90,"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":"CLARITY; Quality of life (healthcare); Set (abstract data type); Scale (ratio); Medicine; Content validity; Prostate cancer; Index (typography); Psychometrics; Quality (philosophy); Computer science; Data mining; Clinical psychology; Cancer; Nursing","score_opus":0.5379063891531359,"score_gpt":0.5359087841037511,"score_spread":0.001997605049384843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98805395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9514419,0.0007726252,0.0012189551,0.04121027,0.0025414391,0.00029171852,0.000089204594,0.000007073239,0.0024267992],"genre_scores_gemma":[0.9716283,0.0008245735,0.0121984035,0.014389494,0.0006486895,0.000006657178,0.0000037446696,0.000015662552,0.00028448246],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.973556,0.005192816,0.020525245,0.00031821275,0.0000919054,0.0003158388],"domain_scores_gemma":[0.96720076,0.014026021,0.017792769,0.00051943364,0.00022366238,0.00023736808],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08641138,0.0001323608,0.002869591,0.00010297889,0.0000938478,0.000004980556,0.00031493325,0.00029159902,0.0012908621],"category_scores_gemma":[0.076395385,0.00010698422,0.0007108334,0.00016764674,0.00059837097,0.00022624551,0.00003954349,0.00062597834,0.0001938806],"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":[0.00017017884,0.00016258091,0.9618482,0.000059070408,0.000077921446,4.5526662e-7,0.00024140914,0.00016337913,3.6462592e-7,0.014225322,0.010881087,0.012170061],"study_design_scores_gemma":[0.001188748,0.00042049983,0.7601631,0.00010228713,0.000016662947,0.00005274827,0.00023443543,0.0019115092,0.0000047853105,0.08114314,0.15463987,0.00012217564],"about_ca_topic_score_codex":0.00015169116,"about_ca_topic_score_gemma":0.000023682745,"teacher_disagreement_score":0.20168504,"about_ca_system_score_codex":0.000087448476,"about_ca_system_score_gemma":0.00024765445,"threshold_uncertainty_score":0.9996221},"labels":[],"label_agreement":null}]}